linux_dsm_epyc7002/fs/f2fs/checkpoint.c

1473 lines
36 KiB
C
Raw Normal View History

/*
* fs/f2fs/checkpoint.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#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;
struct kmem_cache *inode_entry_slab;
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
{
set_ckpt_flags(sbi, CP_ERROR_FLAG);
if (!end_io)
f2fs_flush_merged_writes(sbi);
}
/*
* We guarantee no failure on the returned page.
*/
struct page *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);
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,
};
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;
if (f2fs_submit_page_bio(&fio)) {
f2fs_put_page(page, 1);
goto repeat;
}
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
/*
* if there is any IO error when accessing device, make our filesystem
* readonly and make sure do not write checkpoint with non-uptodate
* meta page.
*/
if (unlikely(!PageUptodate(page)))
f2fs_stop_checkpoint(sbi, false);
out:
return page;
}
struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, true);
}
/* for POR only */
struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, false);
}
bool is_valid_blkaddr(struct f2fs_sb_info *sbi, 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:
if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
blkaddr < MAIN_BLKADDR(sbi)))
return false;
break;
default:
BUG();
}
return true;
}
/*
* Readahead CP/NAT/SIT/SSA pages
*/
int 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,
};
struct blk_plug plug;
if (unlikely(type == META_POR))
fio.op_flags &= ~REQ_META;
blk_start_plug(&plug);
for (; nrpages-- > 0; blkno++) {
if (!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;
}
void 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)
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))) {
dec_page_count(sbi, F2FS_DIRTY_META);
unlock_page(page);
return 0;
}
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;
write_meta_page(sbi, page, io_type);
dec_page_count(sbi, F2FS_DIRTY_META);
if (wbc->for_reclaim)
f2fs_submit_merged_write_cond(sbi, page->mapping->host,
0, page->index, 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->for_kupdate ||
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);
written = 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;
}
long 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 06:42:55 +07:00
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);
BUG_ON(PageWriteback(page));
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 06:42:55 +07:00
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 06:42:55 +07:00
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)) {
f2fs_set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
SetPagePrivate(page);
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);
}
void 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);
}
void 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 */
bool 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;
}
void 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);
}
}
void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type)
{
__add_ino_entry(sbi, ino, devidx, type);
}
bool 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;
}
int acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
int err = 0;
spin_lock(&im->ino_lock);
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_ORPHAN)) {
spin_unlock(&im->ino_lock);
f2fs_show_injection_info(FAULT_ORPHAN);
return -ENOSPC;
}
#endif
if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
im->ino_num++;
spin_unlock(&im->ino_lock);
return err;
}
void 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);
}
void 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);
update_inode_page(inode);
}
void 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;
f2fs: handle errors during recover_orphan_inodes This patch fixes to handle EIO during recover_orphan_inode() given the below panic. F2FS-fs : inject IO error in f2fs_read_end_io+0xe6/0x100 [f2fs] ------------[ cut here ]------------ RIP: 0010:[<ffffffffc0b244e3>] [<ffffffffc0b244e3>] f2fs_evict_inode+0x433/0x470 [f2fs] RSP: 0018:ffff92f8b7fb7c30 EFLAGS: 00010246 RAX: ffff92fb88a13500 RBX: ffff92f890566ea0 RCX: 00000000fd3c255c RDX: 0000000000000001 RSI: ffff92fb88a13d90 RDI: ffff92fb8ee127e8 RBP: ffff92f8b7fb7c58 R08: 0000000000000001 R09: ffff92fb88a13d58 R10: 000000005a6a9373 R11: 0000000000000001 R12: 00000000fffffffb R13: ffff92fb8ee12000 R14: 00000000000034ca R15: ffff92fb8ee12620 FS: 00007f1fefd8e880(0000) GS:ffff92fb95600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc211d34cdb CR3: 000000012d43a000 CR4: 00000000001406e0 Stack: ffff92f890566ea0 ffff92f890567078 ffffffffc0b5a0c0 ffff92f890566f28 ffff92fb888b2000 ffff92f8b7fb7c80 ffffffffbc27ff55 ffff92f890566ea0 ffff92fb8bf10000 ffffffffc0b5a0c0 ffff92f8b7fb7cb0 ffffffffbc28090d Call Trace: [<ffffffffbc27ff55>] evict+0xc5/0x1a0 [<ffffffffbc28090d>] iput+0x1ad/0x2c0 [<ffffffffc0b3304c>] recover_orphan_inodes+0x10c/0x2e0 [f2fs] [<ffffffffc0b2e0f4>] f2fs_fill_super+0x884/0x1150 [f2fs] [<ffffffffbc2644ac>] mount_bdev+0x18c/0x1c0 [<ffffffffc0b2d870>] ? f2fs_commit_super+0x100/0x100 [f2fs] [<ffffffffc0b2a755>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffffbc264e49>] mount_fs+0x39/0x170 [<ffffffffbc28555b>] vfs_kern_mount+0x6b/0x160 [<ffffffffbc2881df>] do_mount+0x1cf/0xd00 [<ffffffffbc287f2c>] ? copy_mount_options+0xac/0x170 [<ffffffffbc289003>] SyS_mount+0x83/0xd0 [<ffffffffbc8ee880>] entry_SYSCALL_64_fastpath+0x23/0xc1 Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-09-22 01:39:42 +07:00
int err = acquire_orphan_inode(sbi);
if (err) {
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;
}
__add_ino_entry(sbi, ino, 0, ORPHAN_INO);
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);
}
clear_nlink(inode);
/* truncate all the data during iput */
iput(inode);
get_node_info(sbi, ino, &ni);
/* ENOMEM was fully retried in f2fs_evict_inode. */
if (ni.blk_addr != NULL_ADDR) {
f2fs: handle errors during recover_orphan_inodes This patch fixes to handle EIO during recover_orphan_inode() given the below panic. F2FS-fs : inject IO error in f2fs_read_end_io+0xe6/0x100 [f2fs] ------------[ cut here ]------------ RIP: 0010:[<ffffffffc0b244e3>] [<ffffffffc0b244e3>] f2fs_evict_inode+0x433/0x470 [f2fs] RSP: 0018:ffff92f8b7fb7c30 EFLAGS: 00010246 RAX: ffff92fb88a13500 RBX: ffff92f890566ea0 RCX: 00000000fd3c255c RDX: 0000000000000001 RSI: ffff92fb88a13d90 RDI: ffff92fb8ee127e8 RBP: ffff92f8b7fb7c58 R08: 0000000000000001 R09: ffff92fb88a13d58 R10: 000000005a6a9373 R11: 0000000000000001 R12: 00000000fffffffb R13: ffff92fb8ee12000 R14: 00000000000034ca R15: ffff92fb8ee12620 FS: 00007f1fefd8e880(0000) GS:ffff92fb95600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc211d34cdb CR3: 000000012d43a000 CR4: 00000000001406e0 Stack: ffff92f890566ea0 ffff92f890567078 ffffffffc0b5a0c0 ffff92f890566f28 ffff92fb888b2000 ffff92f8b7fb7c80 ffffffffbc27ff55 ffff92f890566ea0 ffff92fb8bf10000 ffffffffc0b5a0c0 ffff92f8b7fb7cb0 ffffffffbc28090d Call Trace: [<ffffffffbc27ff55>] evict+0xc5/0x1a0 [<ffffffffbc28090d>] iput+0x1ad/0x2c0 [<ffffffffc0b3304c>] recover_orphan_inodes+0x10c/0x2e0 [f2fs] [<ffffffffc0b2e0f4>] f2fs_fill_super+0x884/0x1150 [f2fs] [<ffffffffbc2644ac>] mount_bdev+0x18c/0x1c0 [<ffffffffc0b2d870>] ? f2fs_commit_super+0x100/0x100 [f2fs] [<ffffffffc0b2a755>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffffbc264e49>] mount_fs+0x39/0x170 [<ffffffffbc28555b>] vfs_kern_mount+0x6b/0x160 [<ffffffffbc2881df>] do_mount+0x1cf/0xd00 [<ffffffffbc287f2c>] ? copy_mount_options+0xac/0x170 [<ffffffffbc289003>] SyS_mount+0x83/0xd0 [<ffffffffbc8ee880>] entry_SYSCALL_64_fastpath+0x23/0xc1 Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-09-22 01:39:42 +07:00
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: orphan failed (ino=%x) by kernel, retry mount.",
f2fs: handle errors during recover_orphan_inodes This patch fixes to handle EIO during recover_orphan_inode() given the below panic. F2FS-fs : inject IO error in f2fs_read_end_io+0xe6/0x100 [f2fs] ------------[ cut here ]------------ RIP: 0010:[<ffffffffc0b244e3>] [<ffffffffc0b244e3>] f2fs_evict_inode+0x433/0x470 [f2fs] RSP: 0018:ffff92f8b7fb7c30 EFLAGS: 00010246 RAX: ffff92fb88a13500 RBX: ffff92f890566ea0 RCX: 00000000fd3c255c RDX: 0000000000000001 RSI: ffff92fb88a13d90 RDI: ffff92fb8ee127e8 RBP: ffff92f8b7fb7c58 R08: 0000000000000001 R09: ffff92fb88a13d58 R10: 000000005a6a9373 R11: 0000000000000001 R12: 00000000fffffffb R13: ffff92fb8ee12000 R14: 00000000000034ca R15: ffff92fb8ee12620 FS: 00007f1fefd8e880(0000) GS:ffff92fb95600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc211d34cdb CR3: 000000012d43a000 CR4: 00000000001406e0 Stack: ffff92f890566ea0 ffff92f890567078 ffffffffc0b5a0c0 ffff92f890566f28 ffff92fb888b2000 ffff92f8b7fb7c80 ffffffffbc27ff55 ffff92f890566ea0 ffff92fb8bf10000 ffffffffc0b5a0c0 ffff92f8b7fb7cb0 ffffffffbc28090d Call Trace: [<ffffffffbc27ff55>] evict+0xc5/0x1a0 [<ffffffffbc28090d>] iput+0x1ad/0x2c0 [<ffffffffc0b3304c>] recover_orphan_inodes+0x10c/0x2e0 [f2fs] [<ffffffffc0b2e0f4>] f2fs_fill_super+0x884/0x1150 [f2fs] [<ffffffffbc2644ac>] mount_bdev+0x18c/0x1c0 [<ffffffffc0b2d870>] ? f2fs_commit_super+0x100/0x100 [f2fs] [<ffffffffc0b2a755>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffffbc264e49>] mount_fs+0x39/0x170 [<ffffffffbc28555b>] vfs_kern_mount+0x6b/0x160 [<ffffffffbc2881df>] do_mount+0x1cf/0xd00 [<ffffffffbc287f2c>] ? copy_mount_options+0xac/0x170 [<ffffffffbc289003>] SyS_mount+0x83/0xd0 [<ffffffffbc8ee880>] entry_SYSCALL_64_fastpath+0x23/0xc1 Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-09-22 01:39:42 +07:00
__func__, ino);
return -EIO;
}
f2fs: handle errors during recover_orphan_inodes This patch fixes to handle EIO during recover_orphan_inode() given the below panic. F2FS-fs : inject IO error in f2fs_read_end_io+0xe6/0x100 [f2fs] ------------[ cut here ]------------ RIP: 0010:[<ffffffffc0b244e3>] [<ffffffffc0b244e3>] f2fs_evict_inode+0x433/0x470 [f2fs] RSP: 0018:ffff92f8b7fb7c30 EFLAGS: 00010246 RAX: ffff92fb88a13500 RBX: ffff92f890566ea0 RCX: 00000000fd3c255c RDX: 0000000000000001 RSI: ffff92fb88a13d90 RDI: ffff92fb8ee127e8 RBP: ffff92f8b7fb7c58 R08: 0000000000000001 R09: ffff92fb88a13d58 R10: 000000005a6a9373 R11: 0000000000000001 R12: 00000000fffffffb R13: ffff92fb8ee12000 R14: 00000000000034ca R15: ffff92fb8ee12620 FS: 00007f1fefd8e880(0000) GS:ffff92fb95600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc211d34cdb CR3: 000000012d43a000 CR4: 00000000001406e0 Stack: ffff92f890566ea0 ffff92f890567078 ffffffffc0b5a0c0 ffff92f890566f28 ffff92fb888b2000 ffff92f8b7fb7c80 ffffffffbc27ff55 ffff92f890566ea0 ffff92fb8bf10000 ffffffffc0b5a0c0 ffff92f8b7fb7cb0 ffffffffbc28090d Call Trace: [<ffffffffbc27ff55>] evict+0xc5/0x1a0 [<ffffffffbc28090d>] iput+0x1ad/0x2c0 [<ffffffffc0b3304c>] recover_orphan_inodes+0x10c/0x2e0 [f2fs] [<ffffffffc0b2e0f4>] f2fs_fill_super+0x884/0x1150 [f2fs] [<ffffffffbc2644ac>] mount_bdev+0x18c/0x1c0 [<ffffffffc0b2d870>] ? f2fs_commit_super+0x100/0x100 [f2fs] [<ffffffffc0b2a755>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffffbc264e49>] mount_fs+0x39/0x170 [<ffffffffbc28555b>] vfs_kern_mount+0x6b/0x160 [<ffffffffbc2881df>] do_mount+0x1cf/0xd00 [<ffffffffbc287f2c>] ? copy_mount_options+0xac/0x170 [<ffffffffbc289003>] SyS_mount+0x83/0xd0 [<ffffffffbc8ee880>] entry_SYSCALL_64_fastpath+0x23/0xc1 Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-09-22 01:39:42 +07:00
__remove_ino_entry(sbi, ino, ORPHAN_INO);
return 0;
}
int 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;
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>
2017-11-28 04:05:09 +07:00
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>
2017-11-28 04:05:09 +07:00
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>
2017-11-28 04:05:09 +07:00
sbi->sb->s_flags |= SB_ACTIVE;
/* Turn on quotas so that they are updated correctly */
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 04:05:09 +07:00
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);
ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
for (i = 0; i < orphan_blocks; i++) {
struct page *page = get_meta_page(sbi, start_blk + i);
struct f2fs_orphan_block *orphan_blk;
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:
#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>
2017-11-28 04:05:09 +07:00
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) {
page = 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 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)
{
unsigned long blk_size = sbi->blocksize;
size_t crc_offset = 0;
__u32 crc = 0;
*cp_page = get_meta_page(sbi, cp_addr);
*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
if (crc_offset > (blk_size - sizeof(__le32))) {
f2fs_msg(sbi->sb, KERN_WARNING,
"invalid crc_offset: %zu", crc_offset);
return -EINVAL;
}
crc = cur_cp_crc(*cp_block);
if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
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)
goto invalid_cp1;
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)
goto invalid_cp2;
cur_version = *version;
if (cur_version == pre_version) {
*version = cur_version;
f2fs_put_page(cp_page_2, 1);
return cp_page_1;
}
invalid_cp2:
f2fs_put_page(cp_page_2, 1);
invalid_cp1:
f2fs_put_page(cp_page_1, 1);
return NULL;
}
int 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;
sbi->ckpt = f2fs_kzalloc(sbi, cp_blks * blk_size, 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);
/* Sanity checking of checkpoint */
if (sanity_check_ckpt(sbi))
goto free_fail_no_cp;
if (cur_page == cp1)
sbi->cur_cp_pack = 1;
else
sbi->cur_cp_pack = 2;
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;
cur_page = get_meta_page(sbi, cp_blk_no + i);
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:
kfree(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);
}
void 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]);
SetPagePrivate(page);
f2fs_trace_pid(page);
}
void 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]);
}
int 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;
if (is_dir)
F2FS_I(inode)->cp_task = current;
filemap_fdatawrite(inode->i_mapping);
if (is_dir)
F2FS_I(inode)->cp_task = NULL;
iput(inode);
/* We need to give cpu to another writers. */
if (ino == cur_ino) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
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 19:13:14 +07:00
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))
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);
}
/*
* 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 11:19:56 +07:00
struct blk_plug plug;
int err = 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 11:19:56 +07:00
blk_start_plug(&plug);
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 14:21:29 +07:00
retry_flush_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 17:08:30 +07:00
f2fs_lock_all(sbi);
/* 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 17:08:30 +07:00
f2fs_unlock_all(sbi);
err = sync_dirty_inodes(sbi, DIR_INODE);
if (err)
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 14:21:29 +07:00
goto retry_flush_dents;
}
/*
* 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 (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_dents;
}
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 14:21:29 +07:00
retry_flush_nodes:
down_write(&sbi->node_write);
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
err = sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
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 14:21:29 +07:00
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 11:19:56 +07:00
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 17:08:30 +07:00
f2fs_unlock_all(sbi);
}
static void 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;
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 13:10:15 +07:00
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 13:10:15 +07:00
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);
/* 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 13:10:15 +07:00
spin_unlock_irqrestore(&sbi->cp_lock, flags);
}
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 13:10:15 +07:00
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 */
while (get_pages(sbi, F2FS_DIRTY_META)) {
sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
}
/*
* modify checkpoint
* version number is already updated
*/
ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi));
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 */
data_sum_blocks = 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 13:10:15 +07:00
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 13:10:15 +07:00
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_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset));
*((__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++)
update_meta_page(sbi, nm_i->nat_bits +
(i << F2FS_BLKSIZE_BITS), blk + i);
/* Flush all the NAT BITS pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
}
}
/* need to wait for end_io results */
wait_on_all_pages_writeback(sbi);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
/* flush all device cache */
err = f2fs_flush_device_cache(sbi);
if (err)
return err;
/* write out checkpoint buffer at block 0 */
update_meta_page(sbi, ckpt, start_blk++);
for (i = 1; i < 1 + cp_payload_blks; i++)
update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
start_blk++);
if (orphan_num) {
write_orphan_inodes(sbi, start_blk);
start_blk += orphan_blocks;
}
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)) {
write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
/* writeout checkpoint block */
update_meta_page(sbi, ckpt, start_blk);
/* wait for previous submitted node/meta pages writeback */
wait_on_all_pages_writeback(sbi);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX);
filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX);
/* 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 only have one bio having CP pack */
sync_meta_pages(sbi, META_FLUSH, LONG_MAX, FS_CP_META_IO);
/* wait for previous submitted meta pages writeback */
wait_on_all_pages_writeback(sbi);
release_ino_entry(sbi, false);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
clear_sbi_flag(sbi, SBI_IS_DIRTY);
clear_sbi_flag(sbi, SBI_NEED_CP);
__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 09:43:19 +07:00
/*
* 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 0;
}
/*
* We guarantee that this checkpoint procedure will not fail.
*/
int 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;
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;
}
if (f2fs_readonly(sbi->sb)) {
err = -EROFS;
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) {
if (!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) {
flush_sit_entries(sbi, cpc);
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 */
flush_nat_entries(sbi, cpc);
flush_sit_entries(sbi, cpc);
/* unlock all the fs_lock[] in do_checkpoint() */
err = do_checkpoint(sbi, cpc);
if (err)
release_discard_addrs(sbi);
else
clear_prefree_segments(sbi, cpc);
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;
}
void 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;
}
int __init create_checkpoint_caches(void)
{
ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry",
sizeof(struct ino_entry));
if (!ino_entry_slab)
return -ENOMEM;
inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
sizeof(struct inode_entry));
if (!inode_entry_slab) {
kmem_cache_destroy(ino_entry_slab);
return -ENOMEM;
}
return 0;
}
void destroy_checkpoint_caches(void)
{
kmem_cache_destroy(ino_entry_slab);
kmem_cache_destroy(inode_entry_slab);
}