2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/fs/f2fs/checkpoint.c
Linus Torvalds 1501f707d2 f2fs-for-5.19
In this round, we've refactored the existing atomic write support implemented
 by in-memory operations to have storing data in disk temporarily, which can give
 us a benefit to accept more atomic writes. At the same time, we removed the
 existing volatile write support. We've also revisited the file pinning and GC
 flows and found some corner cases which contributeed abnormal system behaviours.
 As usual, there're several minor code refactoring for readability, sanity check,
 and clean ups.
 
 Enhancement
  - allow compression for mmap files in compress_mode=user
  - kill volatile write support
  - change the current atomic write way
  - give priority to select unpinned section for foreground GC
  - introduce data read/write showing path info
  - remove unnecessary f2fs_lock_op in f2fs_new_inode
 
 Bug fix
  - fix the file pinning flow during checkpoint=disable and GCs
  - fix foreground and background GCs to select the right victims and get free
    sections on time
  - fix GC flags on defragmenting pages
  - avoid an infinite loop to flush node pages
  - fix fallocate to use file_modified to update permissions consistently
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAmKWfyEACgkQQBSofoJI
 UNJaAQ/9Hs3aGIyriGV8CMbarklRuQ24o3khQKdia5gHseFVsydMfba8tyvl7vYV
 fZnHKp9rnEV1emxWn7hHLaGOvPV8leajZqMLhqG384BIb0yoTnRipnK5t0JkoiJX
 53XC5yfxQd01dwS+J4uOSu2jW0Gs6iBLD6H9ahOs86OE6jF1TeQ/fqjsrhm9I8Zr
 GsNON6zxafPn248sYyVBB3Y5GjPBPf+USif3ZEidAWimW/TIGbXLUT1hA0B79YoX
 DRAmN3tYS75yXauQvFPerMbOmP2gwCPcvdCI/PZ4U/ApsEPP7k1SbOZYAjjGUB30
 Qn8cSMxzPZ1cHvzIC96vwJk8XPdcDhICfzROb7jJdeznD8cWTDv0E+Vd33HUf/mG
 pi5Lkpc4STvYD+KUaKpdnHVg6ARWw4HOnUtW43MF3OsfuyGEEPlROs6lBVYnk/Hz
 smlrgnnLMTOpH9y2JyuyExeHEJ3EAgWbJ8aRpq7Ua7FvKF45Yj1lIytWlvWXSnRf
 rp+A5QJhVtYvT+y2Rk2h5oTRj/9l3+pR0X7CTOfSivJuf6aH5XVgI0EmxT2iBTCp
 4SDBjLC+nXXP3EK1HamLiz1mU23Qg1Qwvx3Wc4xgdwQf3s+jyYxki9tIjzdwJCCZ
 adjd3fc/GrD9UPDmJDXlD5QSoOJ94K/NOwYpu1L1/Q+dVwkl+IE=
 =ta8Y
 -----END PGP SIGNATURE-----

Merge tag 'f2fs-for-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've refactored the existing atomic write support
  implemented by in-memory operations to have storing data in disk
  temporarily, which can give us a benefit to accept more atomic writes.

  At the same time, we removed the existing volatile write support.

  We've also revisited the file pinning and GC flows and found some
  corner cases which contributeed abnormal system behaviours.

  As usual, there're several minor code refactoring for readability,
  sanity check, and clean ups.

  Enhancements:

   - allow compression for mmap files in compress_mode=user

   - kill volatile write support

   - change the current atomic write way

   - give priority to select unpinned section for foreground GC

   - introduce data read/write showing path info

   - remove unnecessary f2fs_lock_op in f2fs_new_inode

  Bug fixes:

   - fix the file pinning flow during checkpoint=disable and GCs

   - fix foreground and background GCs to select the right victims and
     get free sections on time

   - fix GC flags on defragmenting pages

   - avoid an infinite loop to flush node pages

   - fix fallocate to use file_modified to update permissions
     consistently"

* tag 'f2fs-for-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (40 commits)
  f2fs: fix to tag gcing flag on page during file defragment
  f2fs: replace F2FS_I(inode) and sbi by the local variable
  f2fs: add f2fs_init_write_merge_io function
  f2fs: avoid unneeded error handling for revoke_entry_slab allocation
  f2fs: allow compression for mmap files in compress_mode=user
  f2fs: fix typo in comment
  f2fs: make f2fs_read_inline_data() more readable
  f2fs: fix to do sanity check for inline inode
  f2fs: fix fallocate to use file_modified to update permissions consistently
  f2fs: don't use casefolded comparison for "." and ".."
  f2fs: do not stop GC when requiring a free section
  f2fs: keep wait_ms if EAGAIN happens
  f2fs: introduce f2fs_gc_control to consolidate f2fs_gc parameters
  f2fs: reject test_dummy_encryption when !CONFIG_FS_ENCRYPTION
  f2fs: kill volatile write support
  f2fs: change the current atomic write way
  f2fs: don't need inode lock for system hidden quota
  f2fs: stop allocating pinned sections if EAGAIN happens
  f2fs: skip GC if possible when checkpoint disabling
  f2fs: give priority to select unpinned section for foreground GC
  ...
2022-05-31 16:52:59 -07:00

1920 lines
47 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/checkpoint.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/bio.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/f2fs_fs.h>
#include <linux/pagevec.h>
#include <linux/swap.h>
#include <linux/kthread.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "iostat.h"
#include <trace/events/f2fs.h>
#define DEFAULT_CHECKPOINT_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
static struct kmem_cache *ino_entry_slab;
struct kmem_cache *f2fs_inode_entry_slab;
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
{
f2fs_build_fault_attr(sbi, 0, 0);
set_ckpt_flags(sbi, CP_ERROR_FLAG);
if (!end_io)
f2fs_flush_merged_writes(sbi);
}
/*
* We guarantee no failure on the returned page.
*/
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page;
repeat:
page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
}
f2fs_wait_on_page_writeback(page, META, true, true);
if (!PageUptodate(page))
SetPageUptodate(page);
return page;
}
static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
bool is_meta)
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
.op = REQ_OP_READ,
.op_flags = REQ_META | REQ_PRIO,
.old_blkaddr = index,
.new_blkaddr = index,
.encrypted_page = NULL,
.is_por = !is_meta,
};
int err;
if (unlikely(!is_meta))
fio.op_flags &= ~REQ_META;
repeat:
page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
}
if (PageUptodate(page))
goto out;
fio.page = page;
err = f2fs_submit_page_bio(&fio);
if (err) {
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
f2fs_update_iostat(sbi, FS_META_READ_IO, F2FS_BLKSIZE);
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
if (unlikely(!PageUptodate(page))) {
f2fs_handle_page_eio(sbi, page->index, META);
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
out:
return page;
}
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, true);
}
struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct page *page;
int count = 0;
retry:
page = __get_meta_page(sbi, index, true);
if (IS_ERR(page)) {
if (PTR_ERR(page) == -EIO &&
++count <= DEFAULT_RETRY_IO_COUNT)
goto retry;
f2fs_stop_checkpoint(sbi, false);
}
return page;
}
/* for POR only */
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, false);
}
static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
int type)
{
struct seg_entry *se;
unsigned int segno, offset;
bool exist;
if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ)
return true;
segno = GET_SEGNO(sbi, blkaddr);
offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
se = get_seg_entry(sbi, segno);
exist = f2fs_test_bit(offset, se->cur_valid_map);
if (!exist && type == DATA_GENERIC_ENHANCE) {
f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
blkaddr, exist);
set_sbi_flag(sbi, SBI_NEED_FSCK);
dump_stack();
}
return exist;
}
bool f2fs_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;
case DATA_GENERIC:
case DATA_GENERIC_ENHANCE:
case DATA_GENERIC_ENHANCE_READ:
if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
blkaddr < MAIN_BLKADDR(sbi))) {
f2fs_warn(sbi, "access invalid blkaddr:%u",
blkaddr);
set_sbi_flag(sbi, SBI_NEED_FSCK);
dump_stack();
return false;
} else {
return __is_bitmap_valid(sbi, blkaddr, type);
}
break;
case META_GENERIC:
if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
blkaddr >= MAIN_BLKADDR(sbi)))
return false;
break;
default:
BUG();
}
return true;
}
/*
* Readahead CP/NAT/SIT/SSA/POR pages
*/
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int type, bool sync)
{
struct page *page;
block_t blkno = start;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
.op = REQ_OP_READ,
.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
.encrypted_page = NULL,
.in_list = false,
.is_por = (type == META_POR),
};
struct blk_plug plug;
int err;
if (unlikely(type == META_POR))
fio.op_flags &= ~REQ_META;
blk_start_plug(&plug);
for (; nrpages-- > 0; blkno++) {
if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
goto out;
switch (type) {
case META_NAT:
if (unlikely(blkno >=
NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
blkno = 0;
/* get nat block addr */
fio.new_blkaddr = current_nat_addr(sbi,
blkno * NAT_ENTRY_PER_BLOCK);
break;
case META_SIT:
if (unlikely(blkno >= TOTAL_SEGS(sbi)))
goto out;
/* 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;
err = f2fs_submit_page_bio(&fio);
f2fs_put_page(page, err ? 1 : 0);
if (!err)
f2fs_update_iostat(sbi, FS_META_READ_IO, F2FS_BLKSIZE);
}
out:
blk_finish_plug(&plug);
return blkno - start;
}
void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index,
unsigned int ra_blocks)
{
struct page *page;
bool readahead = false;
if (ra_blocks == RECOVERY_MIN_RA_BLOCKS)
return;
page = find_get_page(META_MAPPING(sbi), index);
if (!page || !PageUptodate(page))
readahead = true;
f2fs_put_page(page, 0);
if (readahead)
f2fs_ra_meta_pages(sbi, index, ra_blocks, META_POR, true);
}
static int __f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
trace_f2fs_writepage(page, META);
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
f2fs_do_write_meta_page(sbi, page, io_type);
dec_page_count(sbi, F2FS_DIRTY_META);
if (wbc->for_reclaim)
f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META);
unlock_page(page);
if (unlikely(f2fs_cp_error(sbi)))
f2fs_submit_merged_write(sbi, META);
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
static int f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc)
{
return __f2fs_write_meta_page(page, wbc, FS_META_IO);
}
static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff, written;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto skip_write;
/* collect a number of dirty meta pages and write together */
if (wbc->sync_mode != WB_SYNC_ALL &&
get_pages(sbi, F2FS_DIRTY_META) <
nr_pages_to_skip(sbi, META))
goto skip_write;
/* if locked failed, cp will flush dirty pages instead */
if (!f2fs_down_write_trylock(&sbi->cp_global_sem))
goto skip_write;
trace_f2fs_writepages(mapping->host, wbc, META);
diff = nr_pages_to_write(sbi, META, wbc);
written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
f2fs_up_write(&sbi->cp_global_sem);
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 f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
long nr_to_write, enum iostat_type io_type)
{
struct address_space *mapping = META_MAPPING(sbi);
pgoff_t index = 0, prev = ULONG_MAX;
struct pagevec pvec;
long nwritten = 0;
int nr_pages;
struct writeback_control wbc = {
.for_reclaim = 0,
};
struct blk_plug plug;
pagevec_init(&pvec);
blk_start_plug(&plug);
while ((nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY))) {
int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (prev == ULONG_MAX)
prev = page->index - 1;
if (nr_to_write != LONG_MAX && page->index != prev + 1) {
pagevec_release(&pvec);
goto stop;
}
lock_page(page);
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
f2fs_wait_on_page_writeback(page, META, true, true);
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
if (__f2fs_write_meta_page(page, &wbc, io_type)) {
unlock_page(page);
break;
}
nwritten++;
prev = page->index;
if (unlikely(nwritten >= nr_to_write))
break;
}
pagevec_release(&pvec);
cond_resched();
}
stop:
if (nwritten)
f2fs_submit_merged_write(sbi, type);
blk_finish_plug(&plug);
return nwritten;
}
static bool f2fs_dirty_meta_folio(struct address_space *mapping,
struct folio *folio)
{
trace_f2fs_set_page_dirty(&folio->page, META);
if (!folio_test_uptodate(folio))
folio_mark_uptodate(folio);
if (!folio_test_dirty(folio)) {
filemap_dirty_folio(mapping, folio);
inc_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_META);
set_page_private_reference(&folio->page);
return true;
}
return false;
}
const struct address_space_operations f2fs_meta_aops = {
.writepage = f2fs_write_meta_page,
.writepages = f2fs_write_meta_pages,
.dirty_folio = f2fs_dirty_meta_folio,
.invalidate_folio = f2fs_invalidate_folio,
.release_folio = f2fs_release_folio,
#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 = NULL, *new = NULL;
if (type == FLUSH_INO) {
rcu_read_lock();
e = radix_tree_lookup(&im->ino_root, ino);
rcu_read_unlock();
}
retry:
if (!e)
new = f2fs_kmem_cache_alloc(ino_entry_slab,
GFP_NOFS, true, NULL);
radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
spin_lock(&im->ino_lock);
e = radix_tree_lookup(&im->ino_root, ino);
if (!e) {
if (!new) {
spin_unlock(&im->ino_lock);
goto retry;
}
e = new;
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 (new && e != new)
kmem_cache_free(ino_entry_slab, new);
}
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 f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* add new dirty ino entry into list */
__add_ino_entry(sbi, ino, 0, type);
}
void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* remove dirty ino entry from list */
__remove_ino_entry(sbi, ino, type);
}
/* mode should be APPEND_INO, UPDATE_INO or TRANS_DIR_INO */
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
struct inode_management *im = &sbi->im[mode];
struct ino_entry *e;
spin_lock(&im->ino_lock);
e = radix_tree_lookup(&im->ino_root, ino);
spin_unlock(&im->ino_lock);
return e ? true : false;
}
void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all)
{
struct ino_entry *e, *tmp;
int i;
for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) {
struct inode_management *im = &sbi->im[i];
spin_lock(&im->ino_lock);
list_for_each_entry_safe(e, tmp, &im->ino_list, list) {
list_del(&e->list);
radix_tree_delete(&im->ino_root, e->ino);
kmem_cache_free(ino_entry_slab, e);
im->ino_num--;
}
spin_unlock(&im->ino_lock);
}
}
void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type)
{
__add_ino_entry(sbi, ino, devidx, type);
}
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type)
{
struct inode_management *im = &sbi->im[type];
struct ino_entry *e;
bool is_dirty = false;
spin_lock(&im->ino_lock);
e = radix_tree_lookup(&im->ino_root, ino);
if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device))
is_dirty = true;
spin_unlock(&im->ino_lock);
return is_dirty;
}
int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
int err = 0;
spin_lock(&im->ino_lock);
if (time_to_inject(sbi, FAULT_ORPHAN)) {
spin_unlock(&im->ino_lock);
f2fs_show_injection_info(sbi, FAULT_ORPHAN);
return -ENOSPC;
}
if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
im->ino_num++;
spin_unlock(&im->ino_lock);
return err;
}
void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
spin_lock(&im->ino_lock);
f2fs_bug_on(sbi, im->ino_num == 0);
im->ino_num--;
spin_unlock(&im->ino_lock);
}
void f2fs_add_orphan_inode(struct inode *inode)
{
/* add new orphan ino entry into list */
__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO);
f2fs_update_inode_page(inode);
}
void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
/* remove orphan entry from orphan list */
__remove_ino_entry(sbi, ino, ORPHAN_INO);
}
static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode;
struct node_info ni;
int err;
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode)) {
/*
* there should be a bug that we can't find the entry
* to orphan inode.
*/
f2fs_bug_on(sbi, PTR_ERR(inode) == -ENOENT);
return PTR_ERR(inode);
}
err = f2fs_dquot_initialize(inode);
if (err) {
iput(inode);
goto err_out;
}
clear_nlink(inode);
/* truncate all the data during iput */
iput(inode);
err = f2fs_get_node_info(sbi, ino, &ni, false);
if (err)
goto err_out;
/* ENOMEM was fully retried in f2fs_evict_inode. */
if (ni.blk_addr != NULL_ADDR) {
err = -EIO;
goto err_out;
}
return 0;
err_out:
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "%s: orphan failed (ino=%x), run fsck to fix.",
__func__, ino);
return err;
}
int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
{
block_t start_blk, orphan_blocks, i, j;
unsigned int s_flags = sbi->sb->s_flags;
int err = 0;
#ifdef CONFIG_QUOTA
int quota_enabled;
#endif
if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
return 0;
if (bdev_read_only(sbi->sb->s_bdev)) {
f2fs_info(sbi, "write access unavailable, skipping orphan cleanup");
return 0;
}
if (s_flags & SB_RDONLY) {
f2fs_info(sbi, "orphan cleanup on readonly fs");
sbi->sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
/*
* Turn on quotas which were not enabled for read-only mounts if
* filesystem has quota feature, so that they are updated correctly.
*/
quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
#endif
start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
for (i = 0; i < orphan_blocks; i++) {
struct page *page;
struct f2fs_orphan_block *orphan_blk;
page = f2fs_get_meta_page(sbi, start_blk + i);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out;
}
orphan_blk = (struct f2fs_orphan_block *)page_address(page);
for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
err = recover_orphan_inode(sbi, ino);
if (err) {
f2fs_put_page(page, 1);
goto out;
}
}
f2fs_put_page(page, 1);
}
/* clear Orphan Flag */
clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
out:
set_sbi_flag(sbi, SBI_IS_RECOVERED);
#ifdef CONFIG_QUOTA
/* Turn quotas off */
if (quota_enabled)
f2fs_quota_off_umount(sbi->sb);
#endif
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 = f2fs_grab_meta_page(sbi, start_blk++);
orphan_blk =
(struct f2fs_orphan_block *)page_address(page);
memset(orphan_blk, 0, sizeof(*orphan_blk));
}
orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino);
if (nentries == F2FS_ORPHANS_PER_BLOCK) {
/*
* an orphan block is full of 1020 entries,
* then we need to flush current orphan blocks
* and bring another one in memory
*/
orphan_blk->blk_addr = cpu_to_le16(index);
orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
orphan_blk->entry_count = cpu_to_le32(nentries);
set_page_dirty(page);
f2fs_put_page(page, 1);
index++;
nentries = 0;
page = NULL;
}
}
if (page) {
orphan_blk->blk_addr = cpu_to_le16(index);
orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
orphan_blk->entry_count = cpu_to_le32(nentries);
set_page_dirty(page);
f2fs_put_page(page, 1);
}
}
static __u32 f2fs_checkpoint_chksum(struct f2fs_sb_info *sbi,
struct f2fs_checkpoint *ckpt)
{
unsigned int chksum_ofs = le32_to_cpu(ckpt->checksum_offset);
__u32 chksum;
chksum = f2fs_crc32(sbi, ckpt, chksum_ofs);
if (chksum_ofs < CP_CHKSUM_OFFSET) {
chksum_ofs += sizeof(chksum);
chksum = f2fs_chksum(sbi, chksum, (__u8 *)ckpt + chksum_ofs,
F2FS_BLKSIZE - chksum_ofs);
}
return chksum;
}
static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
struct f2fs_checkpoint **cp_block, struct page **cp_page,
unsigned long long *version)
{
size_t crc_offset = 0;
__u32 crc;
*cp_page = f2fs_get_meta_page(sbi, cp_addr);
if (IS_ERR(*cp_page))
return PTR_ERR(*cp_page);
*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
if (crc_offset < CP_MIN_CHKSUM_OFFSET ||
crc_offset > CP_CHKSUM_OFFSET) {
f2fs_put_page(*cp_page, 1);
f2fs_warn(sbi, "invalid crc_offset: %zu", crc_offset);
return -EINVAL;
}
crc = f2fs_checkpoint_chksum(sbi, *cp_block);
if (crc != cur_cp_crc(*cp_block)) {
f2fs_put_page(*cp_page, 1);
f2fs_warn(sbi, "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;
unsigned int cp_blocks;
int err;
err = get_checkpoint_version(sbi, cp_addr, &cp_block,
&cp_page_1, version);
if (err)
return NULL;
cp_blocks = le32_to_cpu(cp_block->cp_pack_total_block_count);
if (cp_blocks > sbi->blocks_per_seg || cp_blocks <= F2FS_CP_PACKS) {
f2fs_warn(sbi, "invalid cp_pack_total_block_count:%u",
le32_to_cpu(cp_block->cp_pack_total_block_count));
goto invalid_cp;
}
pre_version = *version;
cp_addr += cp_blocks - 1;
err = get_checkpoint_version(sbi, cp_addr, &cp_block,
&cp_page_2, version);
if (err)
goto invalid_cp;
cur_version = *version;
if (cur_version == pre_version) {
*version = cur_version;
f2fs_put_page(cp_page_2, 1);
return cp_page_1;
}
f2fs_put_page(cp_page_2, 1);
invalid_cp:
f2fs_put_page(cp_page_1, 1);
return NULL;
}
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *cp_block;
struct f2fs_super_block *fsb = sbi->raw_super;
struct page *cp1, *cp2, *cur_page;
unsigned long blk_size = sbi->blocksize;
unsigned long long cp1_version = 0, cp2_version = 0;
unsigned long long cp_start_blk_no;
unsigned int cp_blks = 1 + __cp_payload(sbi);
block_t cp_blk_no;
int i;
int err;
sbi->ckpt = f2fs_kvzalloc(sbi, array_size(blk_size, cp_blks),
GFP_KERNEL);
if (!sbi->ckpt)
return -ENOMEM;
/*
* Finding out valid cp block involves read both
* sets( cp pack 1 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 {
err = -EFSCORRUPTED;
goto fail_no_cp;
}
cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
memcpy(sbi->ckpt, cp_block, blk_size);
if (cur_page == cp1)
sbi->cur_cp_pack = 1;
else
sbi->cur_cp_pack = 2;
/* Sanity checking of checkpoint */
if (f2fs_sanity_check_ckpt(sbi)) {
err = -EFSCORRUPTED;
goto free_fail_no_cp;
}
if (cp_blks <= 1)
goto done;
cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
if (cur_page == cp2)
cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
for (i = 1; i < cp_blks; i++) {
void *sit_bitmap_ptr;
unsigned char *ckpt = (unsigned char *)sbi->ckpt;
cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i);
if (IS_ERR(cur_page)) {
err = PTR_ERR(cur_page);
goto free_fail_no_cp;
}
sit_bitmap_ptr = page_address(cur_page);
memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
f2fs_put_page(cur_page, 1);
}
done:
f2fs_put_page(cp1, 1);
f2fs_put_page(cp2, 1);
return 0;
free_fail_no_cp:
f2fs_put_page(cp1, 1);
f2fs_put_page(cp2, 1);
fail_no_cp:
kvfree(sbi->ckpt);
return err;
}
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);
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 f2fs_update_dirty_folio(struct inode *inode, struct folio *folio)
{
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]);
set_page_private_reference(&folio->page);
}
void f2fs_remove_dirty_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
!S_ISLNK(inode->i_mode))
return;
if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH))
return;
spin_lock(&sbi->inode_lock[type]);
__remove_dirty_inode(inode, type);
spin_unlock(&sbi->inode_lock[type]);
}
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
{
struct list_head *head;
struct inode *inode;
struct f2fs_inode_info *fi;
bool is_dir = (type == DIR_INODE);
unsigned long ino = 0;
trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
get_pages(sbi, is_dir ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
retry:
if (unlikely(f2fs_cp_error(sbi))) {
trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
get_pages(sbi, is_dir ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
return -EIO;
}
spin_lock(&sbi->inode_lock[type]);
head = &sbi->inode_list[type];
if (list_empty(head)) {
spin_unlock(&sbi->inode_lock[type]);
trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
get_pages(sbi, is_dir ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
return 0;
}
fi = list_first_entry(head, struct f2fs_inode_info, dirty_list);
inode = igrab(&fi->vfs_inode);
spin_unlock(&sbi->inode_lock[type]);
if (inode) {
unsigned long cur_ino = inode->i_ino;
F2FS_I(inode)->cp_task = current;
filemap_fdatawrite(inode->i_mapping);
F2FS_I(inode)->cp_task = NULL;
iput(inode);
/* We need to give cpu to another writers. */
if (ino == cur_ino)
cond_resched();
else
ino = cur_ino;
} else {
/*
* We should submit bio, since it exists several
* wribacking dentry pages in the freeing inode.
*/
f2fs_submit_merged_write(sbi, DATA);
cond_resched();
}
goto retry;
}
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
{
struct list_head *head = &sbi->inode_list[DIRTY_META];
struct inode *inode;
struct f2fs_inode_info *fi;
s64 total = get_pages(sbi, F2FS_DIRTY_IMETA);
while (total--) {
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
spin_lock(&sbi->inode_lock[DIRTY_META]);
if (list_empty(head)) {
spin_unlock(&sbi->inode_lock[DIRTY_META]);
return 0;
}
fi = list_first_entry(head, struct f2fs_inode_info,
gdirty_list);
inode = igrab(&fi->vfs_inode);
spin_unlock(&sbi->inode_lock[DIRTY_META]);
if (inode) {
sync_inode_metadata(inode, 0);
/* it's on eviction */
if (is_inode_flag_set(inode, FI_DIRTY_INODE))
f2fs_update_inode_page(inode);
iput(inode);
}
}
return 0;
}
static void __prepare_cp_block(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct f2fs_nm_info *nm_i = NM_I(sbi);
nid_t last_nid = nm_i->next_scan_nid;
next_free_nid(sbi, &last_nid);
ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
ckpt->next_free_nid = cpu_to_le32(last_nid);
}
static bool __need_flush_quota(struct f2fs_sb_info *sbi)
{
bool ret = false;
if (!is_journalled_quota(sbi))
return false;
if (!f2fs_down_write_trylock(&sbi->quota_sem))
return true;
if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) {
ret = false;
} else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) {
ret = false;
} else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) {
clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
ret = true;
} else if (get_pages(sbi, F2FS_DIRTY_QDATA)) {
ret = true;
}
f2fs_up_write(&sbi->quota_sem);
return ret;
}
/*
* 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,
};
int err = 0, cnt = 0;
/*
* Let's flush inline_data in dirty node pages.
*/
f2fs_flush_inline_data(sbi);
retry_flush_quotas:
f2fs_lock_all(sbi);
if (__need_flush_quota(sbi)) {
int locked;
if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) {
set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
goto retry_flush_dents;
}
f2fs_unlock_all(sbi);
/* only failed during mount/umount/freeze/quotactl */
locked = down_read_trylock(&sbi->sb->s_umount);
f2fs_quota_sync(sbi->sb, -1);
if (locked)
up_read(&sbi->sb->s_umount);
cond_resched();
goto retry_flush_quotas;
}
retry_flush_dents:
/* write all the dirty dentry pages */
if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
f2fs_unlock_all(sbi);
err = f2fs_sync_dirty_inodes(sbi, DIR_INODE);
if (err)
return err;
cond_resched();
goto retry_flush_quotas;
}
/*
* POR: we should ensure that there are no dirty node pages
* until finishing nat/sit flush. inode->i_blocks can be updated.
*/
f2fs_down_write(&sbi->node_change);
if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
f2fs_up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
err = f2fs_sync_inode_meta(sbi);
if (err)
return err;
cond_resched();
goto retry_flush_quotas;
}
retry_flush_nodes:
f2fs_down_write(&sbi->node_write);
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
f2fs_up_write(&sbi->node_write);
atomic_inc(&sbi->wb_sync_req[NODE]);
err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
atomic_dec(&sbi->wb_sync_req[NODE]);
if (err) {
f2fs_up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
return err;
}
cond_resched();
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);
f2fs_up_write(&sbi->node_change);
return err;
}
static void unblock_operations(struct f2fs_sb_info *sbi)
{
f2fs_up_write(&sbi->node_write);
f2fs_unlock_all(sbi);
}
void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type)
{
DEFINE_WAIT(wait);
for (;;) {
if (!get_pages(sbi, type))
break;
if (unlikely(f2fs_cp_error(sbi)))
break;
if (type == F2FS_DIRTY_META)
f2fs_sync_meta_pages(sbi, META, LONG_MAX,
FS_CP_META_IO);
else if (type == F2FS_WB_CP_DATA)
f2fs_submit_merged_write(sbi, DATA);
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
io_schedule_timeout(DEFAULT_IO_TIMEOUT);
}
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);
unsigned long flags;
if (cpc->reason & CP_UMOUNT) {
if (le32_to_cpu(ckpt->cp_pack_total_block_count) +
NM_I(sbi)->nat_bits_blocks > sbi->blocks_per_seg) {
clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
f2fs_notice(sbi, "Disable nat_bits due to no space");
} else if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG) &&
f2fs_nat_bitmap_enabled(sbi)) {
f2fs_enable_nat_bits(sbi);
set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
f2fs_notice(sbi, "Rebuild and enable nat_bits");
}
}
spin_lock_irqsave(&sbi->cp_lock, flags);
if (cpc->reason & CP_TRIMMED)
__set_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
else
__clear_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
if (cpc->reason & CP_UMOUNT)
__set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
else
__clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
if (cpc->reason & CP_FASTBOOT)
__set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
else
__clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
if (orphan_num)
__set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
else
__clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
__set_ckpt_flags(ckpt, CP_FSCK_FLAG);
if (is_sbi_flag_set(sbi, SBI_IS_RESIZEFS))
__set_ckpt_flags(ckpt, CP_RESIZEFS_FLAG);
else
__clear_ckpt_flags(ckpt, CP_RESIZEFS_FLAG);
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
__set_ckpt_flags(ckpt, CP_DISABLED_FLAG);
else
__clear_ckpt_flags(ckpt, CP_DISABLED_FLAG);
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK))
__set_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG);
else
__clear_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG);
if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH))
__set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
else
__clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR))
__set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
/* set this flag to activate crc|cp_ver for recovery */
__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
__clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG);
spin_unlock_irqrestore(&sbi->cp_lock, flags);
}
static void commit_checkpoint(struct f2fs_sb_info *sbi,
void *src, block_t blk_addr)
{
struct writeback_control wbc = {
.for_reclaim = 0,
};
/*
* pagevec_lookup_tag and lock_page again will take
* some extra time. Therefore, f2fs_update_meta_pages and
* f2fs_sync_meta_pages are combined in this function.
*/
struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
int err;
f2fs_wait_on_page_writeback(page, META, true, true);
memcpy(page_address(page), src, PAGE_SIZE);
set_page_dirty(page);
if (unlikely(!clear_page_dirty_for_io(page)))
f2fs_bug_on(sbi, 1);
/* writeout cp pack 2 page */
err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO);
if (unlikely(err && f2fs_cp_error(sbi))) {
f2fs_put_page(page, 1);
return;
}
f2fs_bug_on(sbi, err);
f2fs_put_page(page, 0);
/* submit checkpoint (with barrier if NOBARRIER is not set) */
f2fs_submit_merged_write(sbi, META_FLUSH);
}
static inline u64 get_sectors_written(struct block_device *bdev)
{
return (u64)part_stat_read(bdev, sectors[STAT_WRITE]);
}
u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi)
{
if (f2fs_is_multi_device(sbi)) {
u64 sectors = 0;
int i;
for (i = 0; i < sbi->s_ndevs; i++)
sectors += get_sectors_written(FDEV(i).bdev);
return sectors;
}
return get_sectors_written(sbi->sb->s_bdev);
}
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);
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 curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
u64 kbytes_written;
int err;
/* Flush all the NAT/SIT pages */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
/* start to update checkpoint, cp ver is already updated previously */
ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true));
ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
ckpt->cur_node_segno[i] =
cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE));
ckpt->cur_node_blkoff[i] =
cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_NODE));
ckpt->alloc_type[i + CURSEG_HOT_NODE] =
curseg_alloc_type(sbi, i + CURSEG_HOT_NODE);
}
for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
ckpt->cur_data_segno[i] =
cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA));
ckpt->cur_data_blkoff[i] =
cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_DATA));
ckpt->alloc_type[i + CURSEG_HOT_DATA] =
curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
}
/* 2 cp + n data seg summary + orphan inode blocks */
data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false);
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);
spin_unlock_irqrestore(&sbi->cp_lock, flags);
orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
orphan_blocks);
if (__remain_node_summaries(cpc->reason))
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
cp_payload_blks + data_sum_blocks +
orphan_blocks + NR_CURSEG_NODE_TYPE);
else
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
cp_payload_blks + data_sum_blocks +
orphan_blocks);
/* update ckpt flag for checkpoint */
update_ckpt_flags(sbi, cpc);
/* update SIT/NAT bitmap */
get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
crc32 = f2fs_checkpoint_chksum(sbi, ckpt);
*((__le32 *)((unsigned char *)ckpt +
le32_to_cpu(ckpt->checksum_offset)))
= cpu_to_le32(crc32);
start_blk = __start_cp_next_addr(sbi);
/* write nat bits */
if ((cpc->reason & CP_UMOUNT) &&
is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG)) {
__u64 cp_ver = cur_cp_version(ckpt);
block_t blk;
cp_ver |= ((__u64)crc32 << 32);
*(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
for (i = 0; i < nm_i->nat_bits_blocks; i++)
f2fs_update_meta_page(sbi, nm_i->nat_bits +
(i << F2FS_BLKSIZE_BITS), blk + i);
}
/* write out checkpoint buffer at block 0 */
f2fs_update_meta_page(sbi, ckpt, start_blk++);
for (i = 1; i < 1 + cp_payload_blks; i++)
f2fs_update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
start_blk++);
if (orphan_num) {
write_orphan_inodes(sbi, start_blk);
start_blk += orphan_blocks;
}
f2fs_write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
/* Record write statistics in the hot node summary */
kbytes_written = sbi->kbytes_written;
kbytes_written += (f2fs_get_sectors_written(sbi) -
sbi->sectors_written_start) >> 1;
seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
if (__remain_node_summaries(cpc->reason)) {
f2fs_write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
/* update user_block_counts */
sbi->last_valid_block_count = sbi->total_valid_block_count;
percpu_counter_set(&sbi->alloc_valid_block_count, 0);
percpu_counter_set(&sbi->rf_node_block_count, 0);
/* Here, we have one bio having CP pack except cp pack 2 page */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
/* Wait for all dirty meta pages to be submitted for IO */
f2fs_wait_on_all_pages(sbi, F2FS_DIRTY_META);
/* wait for previous submitted meta pages writeback */
f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
/* flush all device cache */
err = f2fs_flush_device_cache(sbi);
if (err)
return err;
/* barrier and flush checkpoint cp pack 2 page if it can */
commit_checkpoint(sbi, ckpt, start_blk);
f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
/*
* invalidate intermediate page cache borrowed from meta inode which are
* used for migration of encrypted, verity or compressed inode's blocks.
*/
if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi) ||
f2fs_sb_has_compression(sbi))
invalidate_mapping_pages(META_MAPPING(sbi),
MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
f2fs_release_ino_entry(sbi, false);
f2fs_reset_fsync_node_info(sbi);
clear_sbi_flag(sbi, SBI_IS_DIRTY);
clear_sbi_flag(sbi, SBI_NEED_CP);
clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
spin_lock(&sbi->stat_lock);
sbi->unusable_block_count = 0;
spin_unlock(&sbi->stat_lock);
__set_cp_next_pack(sbi);
/*
* redirty superblock if metadata like node page or inode cache is
* updated during writing checkpoint.
*/
if (get_pages(sbi, F2FS_DIRTY_NODES) ||
get_pages(sbi, F2FS_DIRTY_IMETA))
set_sbi_flag(sbi, SBI_IS_DIRTY);
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS));
return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0;
}
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
int err = 0;
if (f2fs_readonly(sbi->sb) || f2fs_hw_is_readonly(sbi))
return -EROFS;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
if (cpc->reason != CP_PAUSE)
return 0;
f2fs_warn(sbi, "Start checkpoint disabled!");
}
if (cpc->reason != CP_RESIZE)
f2fs_down_write(&sbi->cp_global_sem);
if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
((cpc->reason & CP_DISCARD) && !sbi->discard_blks)))
goto out;
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto out;
}
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
err = block_operations(sbi);
if (err)
goto out;
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
f2fs_flush_merged_writes(sbi);
/* this is the case of multiple fstrims without any changes */
if (cpc->reason & CP_DISCARD) {
if (!f2fs_exist_trim_candidates(sbi, cpc)) {
unblock_operations(sbi);
goto out;
}
if (NM_I(sbi)->nat_cnt[DIRTY_NAT] == 0 &&
SIT_I(sbi)->dirty_sentries == 0 &&
prefree_segments(sbi) == 0) {
f2fs_flush_sit_entries(sbi, cpc);
f2fs_clear_prefree_segments(sbi, cpc);
unblock_operations(sbi);
goto out;
}
}
/*
* update checkpoint pack index
* Increase the version number so that
* SIT entries and seg summaries are written at correct place
*/
ckpt_ver = cur_cp_version(ckpt);
ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
/* write cached NAT/SIT entries to NAT/SIT area */
err = f2fs_flush_nat_entries(sbi, cpc);
if (err) {
f2fs_err(sbi, "f2fs_flush_nat_entries failed err:%d, stop checkpoint", err);
f2fs_bug_on(sbi, !f2fs_cp_error(sbi));
goto stop;
}
f2fs_flush_sit_entries(sbi, cpc);
/* save inmem log status */
f2fs_save_inmem_curseg(sbi);
err = do_checkpoint(sbi, cpc);
if (err) {
f2fs_err(sbi, "do_checkpoint failed err:%d, stop checkpoint", err);
f2fs_bug_on(sbi, !f2fs_cp_error(sbi));
f2fs_release_discard_addrs(sbi);
} else {
f2fs_clear_prefree_segments(sbi, cpc);
}
f2fs_restore_inmem_curseg(sbi);
stop:
unblock_operations(sbi);
stat_inc_cp_count(sbi->stat_info);
if (cpc->reason & CP_RECOVERY)
f2fs_notice(sbi, "checkpoint: version = %llx", ckpt_ver);
/* update CP_TIME to trigger checkpoint periodically */
f2fs_update_time(sbi, CP_TIME);
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
out:
if (cpc->reason != CP_RESIZE)
f2fs_up_write(&sbi->cp_global_sem);
return err;
}
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi)
{
int i;
for (i = 0; i < MAX_INO_ENTRY; i++) {
struct inode_management *im = &sbi->im[i];
INIT_RADIX_TREE(&im->ino_root, GFP_ATOMIC);
spin_lock_init(&im->ino_lock);
INIT_LIST_HEAD(&im->ino_list);
im->ino_num = 0;
}
sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
NR_CURSEG_PERSIST_TYPE - __cp_payload(sbi)) *
F2FS_ORPHANS_PER_BLOCK;
}
int __init f2fs_create_checkpoint_caches(void)
{
ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry",
sizeof(struct ino_entry));
if (!ino_entry_slab)
return -ENOMEM;
f2fs_inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
sizeof(struct inode_entry));
if (!f2fs_inode_entry_slab) {
kmem_cache_destroy(ino_entry_slab);
return -ENOMEM;
}
return 0;
}
void f2fs_destroy_checkpoint_caches(void)
{
kmem_cache_destroy(ino_entry_slab);
kmem_cache_destroy(f2fs_inode_entry_slab);
}
static int __write_checkpoint_sync(struct f2fs_sb_info *sbi)
{
struct cp_control cpc = { .reason = CP_SYNC, };
int err;
f2fs_down_write(&sbi->gc_lock);
err = f2fs_write_checkpoint(sbi, &cpc);
f2fs_up_write(&sbi->gc_lock);
return err;
}
static void __checkpoint_and_complete_reqs(struct f2fs_sb_info *sbi)
{
struct ckpt_req_control *cprc = &sbi->cprc_info;
struct ckpt_req *req, *next;
struct llist_node *dispatch_list;
u64 sum_diff = 0, diff, count = 0;
int ret;
dispatch_list = llist_del_all(&cprc->issue_list);
if (!dispatch_list)
return;
dispatch_list = llist_reverse_order(dispatch_list);
ret = __write_checkpoint_sync(sbi);
atomic_inc(&cprc->issued_ckpt);
llist_for_each_entry_safe(req, next, dispatch_list, llnode) {
diff = (u64)ktime_ms_delta(ktime_get(), req->queue_time);
req->ret = ret;
complete(&req->wait);
sum_diff += diff;
count++;
}
atomic_sub(count, &cprc->queued_ckpt);
atomic_add(count, &cprc->total_ckpt);
spin_lock(&cprc->stat_lock);
cprc->cur_time = (unsigned int)div64_u64(sum_diff, count);
if (cprc->peak_time < cprc->cur_time)
cprc->peak_time = cprc->cur_time;
spin_unlock(&cprc->stat_lock);
}
static int issue_checkpoint_thread(void *data)
{
struct f2fs_sb_info *sbi = data;
struct ckpt_req_control *cprc = &sbi->cprc_info;
wait_queue_head_t *q = &cprc->ckpt_wait_queue;
repeat:
if (kthread_should_stop())
return 0;
if (!llist_empty(&cprc->issue_list))
__checkpoint_and_complete_reqs(sbi);
wait_event_interruptible(*q,
kthread_should_stop() || !llist_empty(&cprc->issue_list));
goto repeat;
}
static void flush_remained_ckpt_reqs(struct f2fs_sb_info *sbi,
struct ckpt_req *wait_req)
{
struct ckpt_req_control *cprc = &sbi->cprc_info;
if (!llist_empty(&cprc->issue_list)) {
__checkpoint_and_complete_reqs(sbi);
} else {
/* already dispatched by issue_checkpoint_thread */
if (wait_req)
wait_for_completion(&wait_req->wait);
}
}
static void init_ckpt_req(struct ckpt_req *req)
{
memset(req, 0, sizeof(struct ckpt_req));
init_completion(&req->wait);
req->queue_time = ktime_get();
}
int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi)
{
struct ckpt_req_control *cprc = &sbi->cprc_info;
struct ckpt_req req;
struct cp_control cpc;
cpc.reason = __get_cp_reason(sbi);
if (!test_opt(sbi, MERGE_CHECKPOINT) || cpc.reason != CP_SYNC) {
int ret;
f2fs_down_write(&sbi->gc_lock);
ret = f2fs_write_checkpoint(sbi, &cpc);
f2fs_up_write(&sbi->gc_lock);
return ret;
}
if (!cprc->f2fs_issue_ckpt)
return __write_checkpoint_sync(sbi);
init_ckpt_req(&req);
llist_add(&req.llnode, &cprc->issue_list);
atomic_inc(&cprc->queued_ckpt);
/*
* update issue_list before we wake up issue_checkpoint thread,
* this smp_mb() pairs with another barrier in ___wait_event(),
* see more details in comments of waitqueue_active().
*/
smp_mb();
if (waitqueue_active(&cprc->ckpt_wait_queue))
wake_up(&cprc->ckpt_wait_queue);
if (cprc->f2fs_issue_ckpt)
wait_for_completion(&req.wait);
else
flush_remained_ckpt_reqs(sbi, &req);
return req.ret;
}
int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi)
{
dev_t dev = sbi->sb->s_bdev->bd_dev;
struct ckpt_req_control *cprc = &sbi->cprc_info;
if (cprc->f2fs_issue_ckpt)
return 0;
cprc->f2fs_issue_ckpt = kthread_run(issue_checkpoint_thread, sbi,
"f2fs_ckpt-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(cprc->f2fs_issue_ckpt)) {
cprc->f2fs_issue_ckpt = NULL;
return -ENOMEM;
}
set_task_ioprio(cprc->f2fs_issue_ckpt, cprc->ckpt_thread_ioprio);
return 0;
}
void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi)
{
struct ckpt_req_control *cprc = &sbi->cprc_info;
if (cprc->f2fs_issue_ckpt) {
struct task_struct *ckpt_task = cprc->f2fs_issue_ckpt;
cprc->f2fs_issue_ckpt = NULL;
kthread_stop(ckpt_task);
flush_remained_ckpt_reqs(sbi, NULL);
}
}
void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi)
{
struct ckpt_req_control *cprc = &sbi->cprc_info;
atomic_set(&cprc->issued_ckpt, 0);
atomic_set(&cprc->total_ckpt, 0);
atomic_set(&cprc->queued_ckpt, 0);
cprc->ckpt_thread_ioprio = DEFAULT_CHECKPOINT_IOPRIO;
init_waitqueue_head(&cprc->ckpt_wait_queue);
init_llist_head(&cprc->issue_list);
spin_lock_init(&cprc->stat_lock);
}