summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/ABI/testing/sysfs-fs-f2fs7
-rw-r--r--Documentation/filesystems/f2fs.txt13
-rw-r--r--fs/f2fs/checkpoint.c97
-rw-r--r--fs/f2fs/data.c69
-rw-r--r--fs/f2fs/debug.c20
-rw-r--r--fs/f2fs/dir.c19
-rw-r--r--fs/f2fs/f2fs.h163
-rw-r--r--fs/f2fs/file.c257
-rw-r--r--fs/f2fs/gc.c26
-rw-r--r--fs/f2fs/inline.c20
-rw-r--r--fs/f2fs/inode.c37
-rw-r--r--fs/f2fs/namei.c53
-rw-r--r--fs/f2fs/node.c460
-rw-r--r--fs/f2fs/node.h60
-rw-r--r--fs/f2fs/recovery.c191
-rw-r--r--fs/f2fs/segment.c520
-rw-r--r--fs/f2fs/segment.h160
-rw-r--r--fs/f2fs/super.c47
-rw-r--r--fs/f2fs/xattr.c8
-rw-r--r--include/linux/f2fs_fs.h6
-rw-r--r--include/trace/events/f2fs.h16
21 files changed, 1453 insertions, 796 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 62dd72522d6e..6f9157f16725 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -44,6 +44,13 @@ Description:
Controls the FS utilization condition for the in-place-update
policies.
+What: /sys/fs/f2fs/<disk>/min_fsync_blocks
+Date: September 2014
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Controls the dirty page count condition for the in-place-update
+ policies.
+
What: /sys/fs/f2fs/<disk>/max_small_discards
Date: November 2013
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index a2046a7d0a9d..2cca5a25ef89 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -192,15 +192,22 @@ Files in /sys/fs/f2fs/<devname>
ipu_policy This parameter controls the policy of in-place
updates in f2fs. There are five policies:
- 0: F2FS_IPU_FORCE, 1: F2FS_IPU_SSR,
- 2: F2FS_IPU_UTIL, 3: F2FS_IPU_SSR_UTIL,
- 4: F2FS_IPU_DISABLE.
+ 0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
+ 0x04: F2FS_IPU_UTIL, 0x08: F2FS_IPU_SSR_UTIL,
+ 0x10: F2FS_IPU_FSYNC.
min_ipu_util This parameter controls the threshold to trigger
in-place-updates. The number indicates percentage
of the filesystem utilization, and used by
F2FS_IPU_UTIL and F2FS_IPU_SSR_UTIL policies.
+ min_fsync_blocks This parameter controls the threshold to trigger
+ in-place-updates when F2FS_IPU_FSYNC mode is set.
+ The number indicates the number of dirty pages
+ when fsync needs to flush on its call path. If
+ the number is less than this value, it triggers
+ in-place-updates.
+
max_victim_search This parameter controls the number of trials to
find a victim segment when conducting SSR and
cleaning operations. The default value is 4096
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index ec3b7a5381fa..dd10a031c052 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -72,7 +72,22 @@ out:
return page;
}
-static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
+struct page *get_meta_page_ra(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ bool readahead = false;
+ struct page *page;
+
+ page = find_get_page(META_MAPPING(sbi), index);
+ if (!page || (page && !PageUptodate(page)))
+ readahead = true;
+ f2fs_put_page(page, 0);
+
+ if (readahead)
+ ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR);
+ return get_meta_page(sbi, index);
+}
+
+static inline block_t get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
{
switch (type) {
case META_NAT:
@@ -82,6 +97,8 @@ static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
case META_SSA:
case META_CP:
return 0;
+ case META_POR:
+ return MAX_BLKADDR(sbi);
default:
BUG();
}
@@ -90,12 +107,12 @@ static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
/*
* Readahead CP/NAT/SIT/SSA pages
*/
-int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type)
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type)
{
block_t prev_blk_addr = 0;
struct page *page;
- int blkno = start;
- int max_blks = get_max_meta_blks(sbi, type);
+ block_t blkno = start;
+ block_t max_blks = get_max_meta_blks(sbi, type);
struct f2fs_io_info fio = {
.type = META,
@@ -125,7 +142,11 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type)
break;
case META_SSA:
case META_CP:
- /* get ssa/cp block addr */
+ case META_POR:
+ if (unlikely(blkno >= max_blks))
+ goto out;
+ if (unlikely(blkno < SEG0_BLKADDR(sbi)))
+ goto out;
blk_addr = blkno;
break;
default:
@@ -151,8 +172,7 @@ out:
static int f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc)
{
- struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
trace_f2fs_writepage(page, META);
@@ -177,7 +197,7 @@ redirty_out:
static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff, written;
trace_f2fs_writepages(mapping->host, wbc, META);
@@ -259,15 +279,12 @@ continue_unlock:
static int f2fs_set_meta_page_dirty(struct page *page)
{
- struct address_space *mapping = page->mapping;
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
-
trace_f2fs_set_page_dirty(page, META);
SetPageUptodate(page);
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
- inc_page_count(sbi, F2FS_DIRTY_META);
+ inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
return 1;
}
return 0;
@@ -378,7 +395,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
void release_orphan_inode(struct f2fs_sb_info *sbi)
{
spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- f2fs_bug_on(sbi->n_orphans == 0);
+ f2fs_bug_on(sbi, sbi->n_orphans == 0);
sbi->n_orphans--;
spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
}
@@ -398,7 +415,7 @@ void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode = f2fs_iget(sbi->sb, ino);
- f2fs_bug_on(IS_ERR(inode));
+ f2fs_bug_on(sbi, IS_ERR(inode));
clear_nlink(inode);
/* truncate all the data during iput */
@@ -459,7 +476,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
list_for_each_entry(orphan, head, list) {
if (!page) {
page = find_get_page(META_MAPPING(sbi), start_blk++);
- f2fs_bug_on(!page);
+ f2fs_bug_on(sbi, !page);
orphan_blk =
(struct f2fs_orphan_block *)page_address(page);
memset(orphan_blk, 0, sizeof(*orphan_blk));
@@ -619,7 +636,7 @@ fail_no_cp:
static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
return -EEXIST;
@@ -631,32 +648,38 @@ static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
return 0;
}
-void set_dirty_dir_page(struct inode *inode, struct page *page)
+void update_dirty_page(struct inode *inode, struct page *page)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dir_inode_entry *new;
int ret = 0;
- if (!S_ISDIR(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
return;
+ if (!S_ISDIR(inode->i_mode)) {
+ inode_inc_dirty_pages(inode);
+ goto out;
+ }
+
new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
new->inode = inode;
INIT_LIST_HEAD(&new->list);
spin_lock(&sbi->dir_inode_lock);
ret = __add_dirty_inode(inode, new);
- inode_inc_dirty_dents(inode);
- SetPagePrivate(page);
+ inode_inc_dirty_pages(inode);
spin_unlock(&sbi->dir_inode_lock);
if (ret)
kmem_cache_free(inode_entry_slab, new);
+out:
+ SetPagePrivate(page);
}
void add_dirty_dir_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dir_inode_entry *new =
f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
int ret = 0;
@@ -674,14 +697,14 @@ void add_dirty_dir_inode(struct inode *inode)
void remove_dirty_dir_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dir_inode_entry *entry;
if (!S_ISDIR(inode->i_mode))
return;
spin_lock(&sbi->dir_inode_lock);
- if (get_dirty_dents(inode) ||
+ if (get_dirty_pages(inode) ||
!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
spin_unlock(&sbi->dir_inode_lock);
return;
@@ -802,11 +825,12 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
finish_wait(&sbi->cp_wait, &wait);
}
-static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
- nid_t last_nid = 0;
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ nid_t last_nid = nm_i->next_scan_nid;
block_t start_blk;
struct page *cp_page;
unsigned int data_sum_blocks, orphan_blocks;
@@ -869,7 +893,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
orphan_blocks);
- if (is_umount) {
+ if (cpc->reason == CP_UMOUNT) {
set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
cp_payload_blks + data_sum_blocks +
@@ -886,6 +910,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
else
clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+ if (sbi->need_fsck)
+ set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+
/* update SIT/NAT bitmap */
get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
@@ -920,7 +947,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
- if (is_umount) {
+ if (cpc->reason == CP_UMOUNT) {
write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
@@ -960,23 +987,23 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
/*
* We guarantee that this checkpoint procedure will not fail.
*/
-void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
mutex_lock(&sbi->cp_mutex);
- if (!sbi->s_dirty)
+ if (!sbi->s_dirty && cpc->reason != CP_DISCARD)
goto out;
if (unlikely(f2fs_cp_error(sbi)))
goto out;
if (block_operations(sbi))
goto out;
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
f2fs_submit_merged_bio(sbi, DATA, WRITE);
f2fs_submit_merged_bio(sbi, NODE, WRITE);
@@ -992,16 +1019,16 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
/* write cached NAT/SIT entries to NAT/SIT area */
flush_nat_entries(sbi);
- flush_sit_entries(sbi);
+ flush_sit_entries(sbi, cpc);
/* unlock all the fs_lock[] in do_checkpoint() */
- do_checkpoint(sbi, is_umount);
+ do_checkpoint(sbi, cpc);
unblock_operations(sbi);
stat_inc_cp_count(sbi->stat_info);
out:
mutex_unlock(&sbi->cp_mutex);
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
}
void init_ino_entry_info(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 76de83e25a89..8e58c4cc2cb9 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -85,7 +85,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
bio = bio_alloc(GFP_NOIO, npages);
bio->bi_bdev = sbi->sb->s_bdev;
- bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
bio->bi_private = sbi;
@@ -193,7 +193,7 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
- int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ int bio_blocks = MAX_BIO_BLOCKS(sbi);
io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read);
io->fio = *fio;
@@ -236,7 +236,7 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
int reserve_new_block(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return -EPERM;
@@ -258,7 +258,7 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
int err;
/* if inode_page exists, index should be zero */
- f2fs_bug_on(!need_put && index);
+ f2fs_bug_on(F2FS_I_SB(dn->inode), !need_put && index);
err = get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
@@ -321,7 +321,7 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
block_t start_blkaddr, end_blkaddr;
int need_update = true;
- f2fs_bug_on(blk_addr == NEW_ADDR);
+ f2fs_bug_on(F2FS_I_SB(dn->inode), blk_addr == NEW_ADDR);
fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
dn->ofs_in_node;
@@ -396,7 +396,6 @@ end_update:
struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
@@ -429,7 +428,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
return page;
}
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, dn.data_blkaddr,
sync ? READ_SYNC : READA);
if (err)
return ERR_PTR(err);
@@ -451,7 +450,6 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
*/
struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
@@ -490,7 +488,8 @@ repeat:
return page;
}
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, READ_SYNC);
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
+ dn.data_blkaddr, READ_SYNC);
if (err)
return ERR_PTR(err);
@@ -517,7 +516,6 @@ repeat:
struct page *get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct page *page;
struct dnode_of_data dn;
@@ -541,8 +539,8 @@ repeat:
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
SetPageUptodate(page);
} else {
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
- READ_SYNC);
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
+ dn.data_blkaddr, READ_SYNC);
if (err)
goto put_err;
@@ -573,10 +571,12 @@ put_err:
static int __allocate_data_block(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ struct f2fs_inode_info *fi = F2FS_I(dn->inode);
struct f2fs_summary sum;
block_t new_blkaddr;
struct node_info ni;
+ pgoff_t fofs;
int type;
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
@@ -599,6 +599,12 @@ static int __allocate_data_block(struct dnode_of_data *dn)
update_extent_cache(new_blkaddr, dn);
clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
+ /* update i_size */
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+ dn->ofs_in_node;
+ if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
+ i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
+
dn->data_blkaddr = new_blkaddr;
return 0;
}
@@ -614,7 +620,6 @@ static int __allocate_data_block(struct dnode_of_data *dn)
static int __get_data_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create, bool fiemap)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
unsigned int blkbits = inode->i_sb->s_blocksize_bits;
unsigned maxblocks = bh_result->b_size >> blkbits;
struct dnode_of_data dn;
@@ -630,8 +635,8 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
goto out;
if (create) {
- f2fs_balance_fs(sbi);
- f2fs_lock_op(sbi);
+ f2fs_balance_fs(F2FS_I_SB(inode));
+ f2fs_lock_op(F2FS_I_SB(inode));
}
/* When reading holes, we need its node page */
@@ -707,7 +712,7 @@ put_out:
f2fs_put_dnode(&dn);
unlock_out:
if (create)
- f2fs_unlock_op(sbi);
+ f2fs_unlock_op(F2FS_I_SB(inode));
out:
trace_f2fs_get_data_block(inode, iblock, bh_result, err);
return err;
@@ -804,7 +809,7 @@ static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
>> PAGE_CACHE_SHIFT;
@@ -846,7 +851,7 @@ write:
if (unlikely(f2fs_cp_error(sbi))) {
SetPageError(page);
unlock_page(page);
- return 0;
+ goto out;
}
if (!wbc->for_reclaim)
@@ -866,7 +871,7 @@ done:
clear_cold_data(page);
out:
- inode_dec_dirty_dents(inode);
+ inode_dec_dirty_pages(inode);
unlock_page(page);
if (need_balance_fs)
f2fs_balance_fs(sbi);
@@ -892,7 +897,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
bool locked = false;
int ret;
long diff;
@@ -904,7 +909,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
return 0;
if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
- get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) &&
+ get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
@@ -926,7 +931,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
return ret;
skip_write:
- wbc->pages_skipped += get_dirty_dents(inode);
+ wbc->pages_skipped += get_dirty_pages(inode);
return 0;
}
@@ -945,7 +950,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
struct dnode_of_data dn;
@@ -1047,7 +1052,10 @@ static int f2fs_write_end(struct file *file,
trace_f2fs_write_end(inode, pos, len, copied);
- set_page_dirty(page);
+ if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
+ register_inmem_page(inode, page);
+ else
+ set_page_dirty(page);
if (pos + copied > i_size_read(inode)) {
i_size_write(inode, pos + copied);
@@ -1092,9 +1100,6 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
if (check_direct_IO(inode, rw, iter, offset))
return 0;
- /* clear fsync mark to recover these blocks */
- fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino);
-
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block);
@@ -1110,8 +1115,12 @@ static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
unsigned int length)
{
struct inode *inode = page->mapping->host;
+
+ if (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)
+ return;
+
if (PageDirty(page))
- inode_dec_dirty_dents(inode);
+ inode_dec_dirty_pages(inode);
ClearPagePrivate(page);
}
@@ -1133,7 +1142,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
- set_dirty_dir_page(inode, page);
+ update_dirty_page(inode, page);
return 1;
}
return 0;
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index fecebdbfd781..0a91ab813a9e 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -93,7 +93,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
total_vblocks = 0;
blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg);
hblks_per_sec = blks_per_sec / 2;
- for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) {
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
dist = abs(vblocks - hblks_per_sec);
bimodal += dist * dist;
@@ -103,7 +103,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
ndirty++;
}
}
- dist = TOTAL_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
+ dist = MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
si->bimodal = bimodal / dist;
if (si->dirty_count)
si->avg_vblocks = total_vblocks / ndirty;
@@ -131,17 +131,17 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
/* build sit */
si->base_mem += sizeof(struct sit_info);
- si->base_mem += TOTAL_SEGS(sbi) * sizeof(struct seg_entry);
- si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * TOTAL_SEGS(sbi);
+ si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
+ si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
if (sbi->segs_per_sec > 1)
- si->base_mem += TOTAL_SECS(sbi) * sizeof(struct sec_entry);
+ si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
/* build free segmap */
si->base_mem += sizeof(struct free_segmap_info);
- si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
/* build curseg */
si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
@@ -149,8 +149,8 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
/* build dirty segmap */
si->base_mem += sizeof(struct dirty_seglist_info);
- si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
+ si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
/* build nm */
si->base_mem += sizeof(struct f2fs_nm_info);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 155fb056b7f1..b54f87149c09 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -126,7 +126,7 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
* For the most part, it should be a bug when name_len is zero.
* We stop here for figuring out where the bugs has occurred.
*/
- f2fs_bug_on(!de->name_len);
+ f2fs_bug_on(F2FS_P_SB(dentry_page), !de->name_len);
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
}
@@ -151,7 +151,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
bool room = false;
int max_slots = 0;
- f2fs_bug_on(level > MAX_DIR_HASH_DEPTH);
+ f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
nblock = bucket_blocks(level);
@@ -284,10 +284,9 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
int update_dent_inode(struct inode *inode, const struct qstr *name)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *page;
- page = get_node_page(sbi, inode->i_ino);
+ page = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(page))
return PTR_ERR(page);
@@ -337,7 +336,6 @@ static int make_empty_dir(struct inode *inode,
static struct page *init_inode_metadata(struct inode *inode,
struct inode *dir, const struct qstr *name)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
struct page *page;
int err;
@@ -360,7 +358,7 @@ static struct page *init_inode_metadata(struct inode *inode,
if (err)
goto put_error;
} else {
- page = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
+ page = get_node_page(F2FS_I_SB(dir), inode->i_ino);
if (IS_ERR(page))
return page;
@@ -381,7 +379,7 @@ static struct page *init_inode_metadata(struct inode *inode,
* we should remove this inode from orphan list.
*/
if (inode->i_nlink == 0)
- remove_orphan_inode(sbi, inode->i_ino);
+ remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
inc_nlink(inode);
}
return page;
@@ -571,8 +569,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
{
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
- struct address_space *mapping = page->mapping;
- struct inode *dir = mapping->host;
+ struct inode *dir = page->mapping->host;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
int i;
@@ -594,7 +591,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
if (inode) {
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
down_write(&F2FS_I(inode)->i_sem);
@@ -621,7 +618,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
truncate_hole(dir, page->index, page->index + 1);
clear_page_dirty_for_io(page);
ClearPageUptodate(page);
- inode_dec_dirty_dents(dir);
+ inode_dec_dirty_pages(dir);
}
f2fs_put_page(page, 1);
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e921242186f6..8171e80b2ee9 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -21,10 +21,16 @@
#include <linux/sched.h>
#ifdef CONFIG_F2FS_CHECK_FS
-#define f2fs_bug_on(condition) BUG_ON(condition)
+#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
#define f2fs_down_write(x, y) down_write_nest_lock(x, y)
#else
-#define f2fs_bug_on(condition) WARN_ON(condition)
+#define f2fs_bug_on(sbi, condition) \
+ do { \
+ if (unlikely(condition)) { \
+ WARN_ON(1); \
+ sbi->need_fsck = true; \
+ } \
+ } while (0)
#define f2fs_down_write(x, y) down_write(x)
#endif
@@ -90,6 +96,20 @@ enum {
SIT_BITMAP
};
+enum {
+ CP_UMOUNT,
+ CP_SYNC,
+ CP_DISCARD,
+};
+
+struct cp_control {
+ int reason;
+ __u64 trim_start;
+ __u64 trim_end;
+ __u64 trim_minlen;
+ __u64 trimmed;
+};
+
/*
* For CP/NAT/SIT/SSA readahead
*/
@@ -97,7 +117,8 @@ enum {
META_CP,
META_NAT,
META_SIT,
- META_SSA
+ META_SSA,
+ META_POR,
};
/* for the list of ino */
@@ -130,7 +151,9 @@ struct discard_entry {
struct fsync_inode_entry {
struct list_head list; /* list head */
struct inode *inode; /* vfs inode pointer */
- block_t blkaddr; /* block address locating the last inode */
+ block_t blkaddr; /* block address locating the last fsync */
+ block_t last_dentry; /* block address locating the last dentry */
+ block_t last_inode; /* block address locating the last inode */
};
#define nats_in_cursum(sum) (le16_to_cpu(sum->n_nats))
@@ -141,6 +164,9 @@ struct fsync_inode_entry {
#define sit_in_journal(sum, i) (sum->sit_j.entries[i].se)
#define segno_in_journal(sum, i) (sum->sit_j.entries[i].segno)
+#define MAX_NAT_JENTRIES(sum) (NAT_JOURNAL_ENTRIES - nats_in_cursum(sum))
+#define MAX_SIT_JENTRIES(sum) (SIT_JOURNAL_ENTRIES - sits_in_cursum(sum))
+
static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
{
int before = nats_in_cursum(rs);
@@ -155,11 +181,24 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
return before;
}
+static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
+ int type)
+{
+ if (type == NAT_JOURNAL)
+ return size <= MAX_NAT_JENTRIES(sum);
+ return size <= MAX_SIT_JENTRIES(sum);
+}
+
/*
* ioctl commands
*/
-#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
+#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+
+#define F2FS_IOCTL_MAGIC 0xf5
+#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
+#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
+#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3)
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
@@ -222,13 +261,16 @@ struct f2fs_inode_info {
/* Use below internally in f2fs*/
unsigned long flags; /* use to pass per-file flags */
struct rw_semaphore i_sem; /* protect fi info */
- atomic_t dirty_dents; /* # of dirty dentry pages */
+ atomic_t dirty_pages; /* # of dirty pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
nid_t i_xattr_nid; /* node id that contains xattrs */
unsigned long long xattr_ver; /* cp version of xattr modification */
struct extent_info ext; /* in-memory extent cache entry */
struct dir_inode_entry *dirty_dir; /* the pointer of dirty dir */
+
+ struct list_head inmem_pages; /* inmemory pages managed by f2fs */
+ struct mutex inmem_lock; /* lock for inmemory pages */
};
static inline void get_extent_info(struct extent_info *ext,
@@ -260,11 +302,10 @@ struct f2fs_nm_info {
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
+ struct radix_tree_root nat_set_root;/* root of the nat set cache */
rwlock_t nat_tree_lock; /* protect nat_tree_lock */
- unsigned int nat_cnt; /* the # of cached nat entries */
struct list_head nat_entries; /* cached nat entry list (clean) */
- struct list_head dirty_nat_entries; /* cached nat entry list (dirty) */
- struct list_head nat_entry_set; /* nat entry set list */
+ unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
/* free node ids management */
@@ -332,18 +373,16 @@ enum {
};
struct flush_cmd {
- struct flush_cmd *next;
struct completion wait;
+ struct llist_node llnode;
int ret;
};
struct flush_cmd_control {
struct task_struct *f2fs_issue_flush; /* flush thread */
wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */
- struct flush_cmd *issue_list; /* list for command issue */
- struct flush_cmd *dispatch_list; /* list for command dispatch */
- spinlock_t issue_lock; /* for issue list lock */
- struct flush_cmd *issue_tail; /* list tail of issue list */
+ struct llist_head issue_list; /* list for command issue */
+ struct llist_node *dispatch_list; /* list for command dispatch */
};
struct f2fs_sm_info {
@@ -369,8 +408,11 @@ struct f2fs_sm_info {
int nr_discards; /* # of discards in the list */
int max_discards; /* max. discards to be issued */
+ struct list_head sit_entry_set; /* sit entry set list */
+
unsigned int ipu_policy; /* in-place-update policy */
unsigned int