summaryrefslogtreecommitdiff
path: root/fs/f2fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/f2fs')
-rw-r--r--fs/f2fs/Kconfig8
-rw-r--r--fs/f2fs/acl.c16
-rw-r--r--fs/f2fs/acl.h2
-rw-r--r--fs/f2fs/checkpoint.c141
-rw-r--r--fs/f2fs/data.c575
-rw-r--r--fs/f2fs/debug.c34
-rw-r--r--fs/f2fs/dir.c253
-rw-r--r--fs/f2fs/extent_cache.c53
-rw-r--r--fs/f2fs/f2fs.h464
-rw-r--r--fs/f2fs/file.c879
-rw-r--r--fs/f2fs/gc.c91
-rw-r--r--fs/f2fs/inline.c198
-rw-r--r--fs/f2fs/inode.c117
-rw-r--r--fs/f2fs/namei.c165
-rw-r--r--fs/f2fs/node.c476
-rw-r--r--fs/f2fs/node.h14
-rw-r--r--fs/f2fs/recovery.c172
-rw-r--r--fs/f2fs/segment.c95
-rw-r--r--fs/f2fs/segment.h31
-rw-r--r--fs/f2fs/shrinker.c5
-rw-r--r--fs/f2fs/super.c525
-rw-r--r--fs/f2fs/trace.c7
-rw-r--r--fs/f2fs/xattr.c49
23 files changed, 2926 insertions, 1444 deletions
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 1f8982a957f1..378c221d68a9 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -94,3 +94,11 @@ config F2FS_IO_TRACE
information and block IO patterns in the filesystem level.
If unsure, say N.
+
+config F2FS_FAULT_INJECTION
+ bool "F2FS fault injection facility"
+ depends on F2FS_FS
+ help
+ Test F2FS to inject faults such as ENOMEM, ENOSPC, and so on.
+
+ If unsure, say N.
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index c8f25f7241f0..4dcc9e28dc5c 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -115,7 +115,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
struct f2fs_acl_entry *entry;
int i;
- f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
+ f2fs_acl = f2fs_kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
sizeof(struct f2fs_acl_entry), GFP_NOFS);
if (!f2fs_acl)
return ERR_PTR(-ENOMEM);
@@ -175,7 +175,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage);
if (retval > 0) {
- value = kmalloc(retval, GFP_F2FS_ZERO);
+ value = f2fs_kmalloc(retval, GFP_F2FS_ZERO);
if (!value)
return ERR_PTR(-ENOMEM);
retval = f2fs_getxattr(inode, name_index, "", value,
@@ -190,9 +190,6 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
acl = ERR_PTR(retval);
kfree(value);
- if (!IS_ERR(acl))
- set_cached_acl(inode, type, acl);
-
return acl;
}
@@ -204,7 +201,6 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
static int __f2fs_set_acl(struct inode *inode, int type,
struct posix_acl *acl, struct page *ipage)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
int name_index;
void *value = NULL;
size_t size = 0;
@@ -217,7 +213,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
error = posix_acl_equiv_mode(acl, &inode->i_mode);
if (error < 0)
return error;
- set_acl_inode(fi, inode->i_mode);
+ set_acl_inode(inode, inode->i_mode);
if (error == 0)
acl = NULL;
}
@@ -236,7 +232,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
if (acl) {
value = f2fs_acl_to_disk(acl, &size);
if (IS_ERR(value)) {
- clear_inode_flag(fi, FI_ACL_MODE);
+ clear_inode_flag(inode, FI_ACL_MODE);
return (int)PTR_ERR(value);
}
}
@@ -247,7 +243,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
if (!error)
set_cached_acl(inode, type, acl);
- clear_inode_flag(fi, FI_ACL_MODE);
+ clear_inode_flag(inode, FI_ACL_MODE);
return error;
}
@@ -388,6 +384,8 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
if (error)
return error;
+ f2fs_mark_inode_dirty_sync(inode);
+
if (default_acl) {
error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl,
ipage);
diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h
index 997ca8edb6cb..b2334d11dae8 100644
--- a/fs/f2fs/acl.h
+++ b/fs/f2fs/acl.h
@@ -37,7 +37,7 @@ struct f2fs_acl_header {
#ifdef CONFIG_F2FS_FS_POSIX_ACL
extern struct posix_acl *f2fs_get_acl(struct inode *, int);
-extern int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int f2fs_set_acl(struct inode *, struct posix_acl *, int);
extern int f2fs_init_acl(struct inode *, struct inode *, struct page *,
struct page *);
#else
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 0955312e5ca0..f94d01e7d001 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -26,6 +26,14 @@
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->ckpt, CP_ERROR_FLAG);
+ sbi->sb->s_flags |= MS_RDONLY;
+ if (!end_io)
+ f2fs_flush_merged_bios(sbi);
+}
+
/*
* We guarantee no failure on the returned page.
*/
@@ -34,13 +42,14 @@ 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 = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
}
f2fs_wait_on_page_writeback(page, META, true);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
return page;
}
@@ -55,16 +64,17 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
- .rw = READ_SYNC | REQ_META | REQ_PRIO,
+ .op = REQ_OP_READ,
+ .op_flags = READ_SYNC | REQ_META | REQ_PRIO,
.old_blkaddr = index,
.new_blkaddr = index,
.encrypted_page = NULL,
};
if (unlikely(!is_meta))
- fio.rw &= ~REQ_META;
+ fio.op_flags &= ~REQ_META;
repeat:
- page = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
@@ -91,7 +101,7 @@ repeat:
* meta page.
*/
if (unlikely(!PageUptodate(page)))
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
out:
return page;
}
@@ -149,13 +159,14 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
- .rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
+ .op = REQ_OP_READ,
+ .op_flags = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : REQ_RAHEAD,
.encrypted_page = NULL,
};
struct blk_plug plug;
if (unlikely(type == META_POR))
- fio.rw &= ~REQ_META;
+ fio.op_flags &= ~REQ_META;
blk_start_plug(&plug);
for (; nrpages-- > 0; blkno++) {
@@ -186,7 +197,8 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
BUG();
}
- page = grab_cache_page(META_MAPPING(sbi), fio.new_blkaddr);
+ page = f2fs_grab_cache_page(META_MAPPING(sbi),
+ fio.new_blkaddr, false);
if (!page)
continue;
if (PageUptodate(page)) {
@@ -211,7 +223,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
bool readahead = false;
page = find_get_page(META_MAPPING(sbi), index);
- if (!page || (page && !PageUptodate(page)))
+ if (!page || !PageUptodate(page))
readahead = true;
f2fs_put_page(page, 0);
@@ -255,6 +267,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
+ struct blk_plug plug;
long diff, written;
/* collect a number of dirty meta pages and write together */
@@ -267,7 +280,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
/* if mounting is failed, skip writing node pages */
mutex_lock(&sbi->cp_mutex);
diff = nr_pages_to_write(sbi, META, wbc);
+ blk_start_plug(&plug);
written = sync_meta_pages(sbi, META, wbc->nr_to_write);
+ blk_finish_plug(&plug);
mutex_unlock(&sbi->cp_mutex);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
return 0;
@@ -355,9 +370,10 @@ static int f2fs_set_meta_page_dirty(struct page *page)
{
trace_f2fs_set_page_dirty(page, META);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
if (!PageDirty(page)) {
- __set_page_dirty_nobuffers(page);
+ f2fs_set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
SetPagePrivate(page);
f2fs_trace_pid(page);
@@ -448,12 +464,12 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
return e ? true : false;
}
-void release_ino_entry(struct f2fs_sb_info *sbi)
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
{
struct ino_entry *e, *tmp;
int i;
- for (i = APPEND_INO; i <= UPDATE_INO; i++) {
+ for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) {
struct inode_management *im = &sbi->im[i];
spin_lock(&im->ino_lock);
@@ -473,6 +489,13 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
int err = 0;
spin_lock(&im->ino_lock);
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_ORPHAN)) {
+ spin_unlock(&im->ino_lock);
+ return -ENOSPC;
+ }
+#endif
if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
@@ -492,10 +515,11 @@ void release_orphan_inode(struct f2fs_sb_info *sbi)
spin_unlock(&im->ino_lock);
}
-void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+void add_orphan_inode(struct inode *inode)
{
/* add new orphan ino entry into list */
- __add_ino_entry(sbi, ino, ORPHAN_INO);
+ __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO);
+ update_inode_page(inode);
}
void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
@@ -743,28 +767,25 @@ fail_no_cp:
static void __add_dirty_inode(struct inode *inode, enum inode_type type)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
- if (is_inode_flag_set(fi, flag))
+ if (is_inode_flag_set(inode, flag))
return;
- set_inode_flag(fi, flag);
- list_add_tail(&fi->dirty_list, &sbi->inode_list[type]);
+ 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)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
- if (get_dirty_pages(inode) ||
- !is_inode_flag_set(F2FS_I(inode), flag))
+ if (get_dirty_pages(inode) || !is_inode_flag_set(inode, flag))
return;
- list_del_init(&fi->dirty_list);
- clear_inode_flag(fi, flag);
+ list_del_init(&F2FS_I(inode)->dirty_list);
+ clear_inode_flag(inode, flag);
stat_dec_dirty_inode(F2FS_I_SB(inode), type);
}
@@ -778,7 +799,8 @@ void update_dirty_page(struct inode *inode, struct page *page)
return;
spin_lock(&sbi->inode_lock[type]);
- __add_dirty_inode(inode, 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]);
@@ -786,34 +808,21 @@ void update_dirty_page(struct inode *inode, struct page *page)
f2fs_trace_pid(page);
}
-void add_dirty_dir_inode(struct inode *inode)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-
- spin_lock(&sbi->inode_lock[DIR_INODE]);
- __add_dirty_inode(inode, DIR_INODE);
- spin_unlock(&sbi->inode_lock[DIR_INODE]);
-}
-
void remove_dirty_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(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]);
-
- /* Only from the recovery routine */
- if (is_inode_flag_set(fi, FI_DELAY_IPUT)) {
- clear_inode_flag(fi, FI_DELAY_IPUT);
- iput(inode);
- }
}
int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
@@ -857,6 +866,34 @@ retry:
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_entry(head->next, struct f2fs_inode_info,
+ gdirty_list);
+ inode = igrab(&fi->vfs_inode);
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ if (inode) {
+ update_inode_page(inode);
+ iput(inode);
+ }
+ };
+ return 0;
+}
+
/*
* Freeze all the FS-operations for checkpoint.
*/
@@ -883,6 +920,14 @@ retry_flush_dents:
goto retry_flush_dents;
}
+ if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
+ f2fs_unlock_all(sbi);
+ err = f2fs_sync_inode_meta(sbi);
+ if (err)
+ goto out;
+ goto retry_flush_dents;
+ }
+
/*
* POR: we should ensure that there are no dirty node pages
* until finishing nat/sit flush.
@@ -892,7 +937,7 @@ retry_flush_nodes:
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
- err = sync_node_pages(sbi, 0, &wbc);
+ err = sync_node_pages(sbi, &wbc);
if (err) {
f2fs_unlock_all(sbi);
goto out;
@@ -907,6 +952,8 @@ out:
static void unblock_operations(struct f2fs_sb_info *sbi)
{
up_write(&sbi->node_write);
+
+ build_free_nids(sbi);
f2fs_unlock_all(sbi);
}
@@ -917,7 +964,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
for (;;) {
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
- if (!get_pages(sbi, F2FS_WRITEBACK))
+ if (!atomic_read(&sbi->nr_wb_bios))
break;
io_schedule_timeout(5*HZ);
@@ -947,7 +994,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
* This avoids to conduct wrong roll-forward operations and uses
* metapages, so should be called prior to sync_meta_pages below.
*/
- if (discard_next_dnode(sbi, discard_blk))
+ if (!test_opt(sbi, LFS) && discard_next_dnode(sbi, discard_blk))
invalidate = true;
/* Flush all the NAT/SIT pages */
@@ -1082,7 +1129,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* update user_block_counts */
sbi->last_valid_block_count = sbi->total_valid_block_count;
- sbi->alloc_valid_block_count = 0;
+ 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);
@@ -1098,7 +1145,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
discard_blk);
- release_ino_entry(sbi);
+ release_ino_entry(sbi, false);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index e5c762b37239..d64d2a515cb2 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -19,6 +19,8 @@
#include <linux/bio.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
+#include <linux/mm.h>
+#include <linux/memcontrol.h>
#include <linux/cleancache.h>
#include "f2fs.h"
@@ -45,7 +47,8 @@ static void f2fs_read_end_io(struct bio *bio)
struct page *page = bvec->bv_page;
if (!bio->bi_error) {
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
} else {
ClearPageUptodate(page);
SetPageError(page);
@@ -68,13 +71,12 @@ static void f2fs_write_end_io(struct bio *bio)
if (unlikely(bio->bi_error)) {
set_bit(AS_EIO, &page->mapping->flags);
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, true);
}
end_page_writeback(page);
- dec_page_count(sbi, F2FS_WRITEBACK);
}
-
- if (!get_pages(sbi, F2FS_WRITEBACK) && wq_has_sleeper(&sbi->cp_wait))
+ if (atomic_dec_and_test(&sbi->nr_wb_bios) &&
+ wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
bio_put(bio);
@@ -98,6 +100,18 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
return bio;
}
+static inline void __submit_bio(struct f2fs_sb_info *sbi,
+ struct bio *bio, enum page_type type)
+{
+ if (!is_read_io(bio_op(bio))) {
+ atomic_inc(&sbi->nr_wb_bios);
+ if (f2fs_sb_mounted_hmsmr(sbi->sb) &&
+ current->plug && (type == DATA || type == NODE))
+ blk_finish_plug(current->plug);
+ }
+ submit_bio(bio);
+}
+
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
@@ -105,12 +119,14 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
if (!io->bio)
return;
- if (is_read_io(fio->rw))
+ if (is_read_io(fio->op))
trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
else
trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
- submit_bio(fio->rw, io->bio);
+ bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
+
+ __submit_bio(io->sbi, io->bio, fio->type);
io->bio = NULL;
}
@@ -176,10 +192,12 @@ static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
+ io->fio.op = REQ_OP_WRITE;
if (test_opt(sbi, NOBARRIER))
- io->fio.rw = WRITE_FLUSH | REQ_META | REQ_PRIO;
+ io->fio.op_flags = WRITE_FLUSH | REQ_META | REQ_PRIO;
else
- io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO;
+ io->fio.op_flags = WRITE_FLUSH_FUA | REQ_META |
+ REQ_PRIO;
}
__submit_merged_bio(io);
out:
@@ -221,14 +239,15 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
f2fs_trace_ios(fio, 0);
/* Allocate a new bio */
- bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->rw));
+ bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->op));
- if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
}
+ bio_set_op_attrs(bio, fio->op, fio->op_flags);
- submit_bio(fio->rw, bio);
+ __submit_bio(fio->sbi, bio, fio->type);
return 0;
}
@@ -237,7 +256,7 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io;
- bool is_read = is_read_io(fio->rw);
+ bool is_read = is_read_io(fio->op);
struct page *bio_page;
io = is_read ? &sbi->read_io : &sbi->write_io[btype];
@@ -248,11 +267,8 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
down_write(&io->io_rwsem);
- if (!is_read)
- inc_page_count(sbi, F2FS_WRITEBACK);
-
if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
- io->fio.rw != fio->rw))
+ (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
@@ -265,8 +281,8 @@ alloc_new:
bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
- if (bio_add_page(io->bio, bio_page, PAGE_CACHE_SIZE, 0) <
- PAGE_CACHE_SIZE) {
+ if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
+ PAGE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
@@ -278,6 +294,16 @@ alloc_new:
trace_f2fs_submit_page_mbio(fio->page, fio);
}
+static void __set_data_blkaddr(struct dnode_of_data *dn)
+{
+ struct f2fs_node *rn = F2FS_NODE(dn->node_page);
+ __le32 *addr_array;
+
+ /* Get physical address of data block */
+ addr_array = blkaddr_in_node(rn);
+ addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
+}
+
/*
* Lock ordering for the change of data block address:
* ->data_page
@@ -286,19 +312,9 @@ alloc_new:
*/
void set_data_blkaddr(struct dnode_of_data *dn)
{
- struct f2fs_node *rn;
- __le32 *addr_array;
- struct page *node_page = dn->node_page;
- unsigned int ofs_in_node = dn->ofs_in_node;
-
- f2fs_wait_on_page_writeback(node_page, NODE, true);
-
- rn = F2FS_NODE(node_page);
-
- /* Get physical address of data block */
- addr_array = blkaddr_in_node(rn);
- addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
- if (set_page_dirty(node_page))
+ f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+ __set_data_blkaddr(dn);
+ if (set_page_dirty(dn->node_page))
dn->node_changed = true;
}
@@ -309,24 +325,50 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
f2fs_update_extent_cache(dn);
}
-int reserve_new_block(struct dnode_of_data *dn)
+/* dn->ofs_in_node will be returned with up-to-date last block pointer */
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
- if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
+ if (!count)
+ return 0;
+
+ if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
- if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+ if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
return -ENOSPC;
- trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
+ trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
+ dn->ofs_in_node, count);
- dn->data_blkaddr = NEW_ADDR;
- set_data_blkaddr(dn);
- mark_inode_dirty(dn->inode);
- sync_inode_page(dn);
+ f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+
+ for (; count > 0; dn->ofs_in_node++) {
+ block_t blkaddr =
+ datablock_addr(dn->node_page, dn->ofs_in_node);
+ if (blkaddr == NULL_ADDR) {
+ dn->data_blkaddr = NEW_ADDR;
+ __set_data_blkaddr(dn);
+ count--;
+ }
+ }
+
+ if (set_page_dirty(dn->node_page))
+ dn->node_changed = true;
return 0;
}
+/* Should keep dn->ofs_in_node unchanged */
+int reserve_new_block(struct dnode_of_data *dn)
+{
+ unsigned int ofs_in_node = dn->ofs_in_node;
+ int ret;
+
+ ret = reserve_new_blocks(dn, 1);
+ dn->ofs_in_node = ofs_in_node;
+ return ret;
+}
+
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
{
bool need_put = dn->inode_page ? false : true;
@@ -357,7 +399,7 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
}
struct page *get_read_data_page(struct inode *inode, pgoff_t index,
- int rw, bool for_write)
+ int op_flags, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
@@ -367,7 +409,8 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
.type = DATA,
- .rw = rw,
+ .op = REQ_OP_READ,
+ .op_flags = op_flags,
.encrypted_page = NULL,
};
@@ -406,8 +449,9 @@ got_it:
* see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
- SetPageUptodate(page);
+ zero_user_segment(page, 0, PAGE_SIZE);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
unlock_page(page);
return page;
}
@@ -466,14 +510,14 @@ repeat:
/* wait for read completion */
lock_page(page);
- if (unlikely(!PageUptodate(page))) {
- f2fs_put_page(page, 1);
- return ERR_PTR(-EIO);
- }
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
+ if (unlikely(!PageUptodate(page))) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(-EIO);
+ }
return page;
}
@@ -517,8 +561,9 @@ struct page *get_new_data_page(struct inode *inode,
goto got_it;
if (dn.data_blkaddr == NEW_ADDR) {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
- SetPageUptodate(page);
+ zero_user_segment(page, 0, PAGE_SIZE);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
} else {
f2fs_put_page(page, 1);
@@ -530,11 +575,8 @@ struct page *get_new_data_page(struct inode *inode,
}
got_it:
if (new_i_size && i_size_read(inode) <
- ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)) {
- i_size_write(inode, ((loff_t)(index + 1) << PAGE_CACHE_SHIFT));
- /* Only the directory inode sets new_i_size */
- set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
- }
+ ((loff_t)(index + 1) << PAGE_SHIFT))
+ f2fs_i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT));
return page;
}
@@ -545,15 +587,16 @@ static int __allocate_data_block(struct dnode_of_data *dn)
struct node_info ni;
int seg = CURSEG_WARM_DATA;
pgoff_t fofs;
+ blkcnt_t count = 1;
- if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
+ if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
if (dn->data_blkaddr == NEW_ADDR)
goto alloc;
- if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+ if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
return -ENOSPC;
alloc:
@@ -570,9 +613,9 @@ alloc:
/* update i_size */
fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
dn->ofs_in_node;
- if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT))
- i_size_write(dn->inode,
- ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT));
+ if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT))
+ f2fs_i_size_write(dn->inode,
+ ((loff_t)(fofs + 1) << PAGE_SHIFT));
return 0;
}
@@ -582,8 +625,8 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
struct f2fs_map_blocks map;
ssize_t ret = 0;
- map.m_lblk = F2FS_BYTES_TO_BLK(iocb->ki_pos);
- map.m_len = F2FS_BLK_ALIGN(iov_iter_count(from));
+ map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
+ map.m_len = F2FS_BYTES_TO_BLK(iov_iter_count(from));
map.m_next_pgofs = NULL;
if (f2fs_encrypted_inode(inode))
@@ -620,9 +663,11 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
- pgoff_t pgofs, end_offset;
+ int mode = create ? ALLOC_NODE : LOOKUP_NODE;
+ pgoff_t pgofs, end_offset, end;
int err = 0, ofs = 1;
+ unsigned int ofs_in_node, last_ofs_in_node;
+ blkcnt_t prealloc;
struct extent_info ei;
bool allocated = false;
block_t blkaddr;
@@ -632,6 +677,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
/* it only supports block size == page size */
pgofs = (pgoff_t)map->m_lblk;
+ end = pgofs + maxblocks;
if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
map->m_pblk = ei.blk + pgofs - ei.fofs;
@@ -648,6 +694,8 @@ next_dnode:
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, mode);
if (err) {
+ if (flag == F2FS_GET_BLOCK_BMAP)
+ map->m_pblk = 0;
if (err == -ENOENT) {
err = 0;
if (map->m_next_pgofs)
@@ -657,6 +705,8 @@ next_dnode:
goto unlock_out;
}
+ prealloc = 0;
+ ofs_in_node = dn.ofs_in_node;
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
next_block:
@@ -669,31 +719,40 @@ next_block:
goto sync_out;
}
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
- if (blkaddr == NULL_ADDR)
- err = reserve_new_block(&dn);
+ if (blkaddr == NULL_ADDR) {
+ prealloc++;
+ last_ofs_in_node = dn.ofs_in_node;
+ }
} else {
err = __allocate_data_block(&dn);
+ if (!err) {
+ set_inode_flag(inode, FI_APPEND_WRITE);
+ allocated = true;
+ }
}
if (err)
goto sync_out;
- allocated = true;
map->m_flags = F2FS_MAP_NEW;
blkaddr = dn.data_blkaddr;
} else {
+ if (flag == F2FS_GET_BLOCK_BMAP) {
+ map->m_pblk = 0;
+ goto sync_out;
+ }
if (flag == F2FS_GET_BLOCK_FIEMAP &&
blkaddr == NULL_ADDR) {
if (map->m_next_pgofs)
*map->m_next_pgofs = pgofs + 1;
}
if (flag != F2FS_GET_BLOCK_FIEMAP ||
- blkaddr != NEW_ADDR) {
- if (flag == F2FS_GET_BLOCK_BMAP)
- err = -ENOENT;
+ blkaddr != NEW_ADDR)
goto sync_out;
- }
}
}
+ if (flag == F2FS_GET_BLOCK_PRE_AIO)
+ goto skip;
+
if (map->m_len == 0) {
/* preallocated unwritten block should be mapped for fiemap. */
if (blkaddr == NEW_ADDR)
@@ -705,36 +764,49 @@ next_block:
} else if ((map->m_pblk != NEW_ADDR &&
blkaddr == (map->m_pblk + ofs)) ||
(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
- flag == F2FS_GET_BLOCK_PRE_DIO ||
- flag == F2FS_GET_BLOCK_PRE_AIO) {
+ flag == F2FS_GET_BLOCK_PRE_DIO) {
ofs++;
map->m_len++;
} else {
goto sync_out;
}
+skip:
dn.ofs_in_node++;
pgofs++;
- if (map->m_len < maxblocks) {
- if (dn.ofs_in_node < end_offset)
- goto next_block;
+ /* preallocate blocks in batch for one dnode page */
+ if (flag == F2FS_GET_BLOCK_PRE_AIO &&
+ (pgofs == end || dn.ofs_in_node == end_offset)) {
- if (allocated)
- sync_inode_page(&dn);
- f2fs_put_dnode(&dn);
+ dn.ofs_in_node = ofs_in_node;
+ err = reserve_new_blocks(&dn, prealloc);
+ if (err)
+ goto sync_out;
- if (create) {
- f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, allocated);
+ map->m_len += dn.ofs_in_node - ofs_in_node;
+ if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
+ err = -ENOSPC;
+ goto sync_out;
}
- allocated = false;
- goto next_dnode;
+ dn.ofs_in_node = end_offset;
}
+ if (pgofs >= end)
+ goto sync_out;
+ else if (dn.ofs_in_node < end_offset)
+ goto next_block;
+
+ f2fs_put_dnode(&dn);
+
+ if (create) {
+ f2fs_unlock_op(sbi);
+ f2fs_balance_fs(sbi, allocated);
+ }
+ allocated = false;
+ goto next_dnode;
+
sync_out:
- if (allocated)
- sync_inode_page(&dn);
f2fs_put_dnode(&dn);
unlock_out:
if (create) {
@@ -894,6 +966,37 @@ out:
return ret;
}
+struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
+ unsigned nr_pages)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct fscrypt_ctx *ctx = NULL;
+ struct block_device *bdev = sbi->sb->s_bdev;
+ struct bio *bio;
+
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+ ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+ if (IS_ERR(ctx))
+ return ERR_CAST(ctx);
+
+ /* wait the page to be moved by cleaning */
+ f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+ }
+
+ bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+ if (!bio) {
+ if (ctx)
+ fscrypt_release_ctx(ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+ bio->bi_bdev = bdev;
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blkaddr);
+ bio->bi_end_io = f2fs_read_end_io;
+ bio->bi_private = ctx;
+
+ return bio;
+}
+
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
@@ -912,7 +1015,6 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
- struct block_device *bdev = inode->i_sb->s_bdev;
struct f2fs_map_blocks map;
map.m_pblk = 0;
@@ -928,7 +1030,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
page = list_entry(pages->prev, struct page, lru);
list_del(&page->lru);
if (add_to_page_cache_lru(page, mapping,
- page->index, GFP_KERNEL))
+ page->index,
+ readahead_gfp_mask(mapping)))
goto next_page;
}
@@ -971,8 +1074,9 @@ got_it:
goto confused;
}
} else {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
- SetPageUptodate(page);
+ zero_user_segment(page, 0, PAGE_SIZE);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
unlock_page(page);
goto next_page;
}
@@ -983,35 +1087,16 @@ got_it:
*/
if (bio && (last_block_in_bio != block_nr - 1)) {
submit_and_realloc:
- submit_bio(READ, bio);
+ __submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
if (bio == NULL) {
- struct fscrypt_ctx *ctx = NULL;
-
- if (f2fs_encrypted_inode(inode) &&
- S_ISREG(inode->i_mode)) {
-
- ctx = fscrypt_get_ctx(inode);
- if (IS_ERR(ctx))
- goto set_error_page;
-
- /* wait the page to be moved by cleaning */
- f2fs_wait_on_encrypted_page_writeback(
- F2FS_I_SB(inode), block_nr);
- }
-
- bio = bio_alloc(GFP_KERNEL,
- min_t(int, nr_pages, BIO_MAX_PAGES));
- if (!bio) {
- if (ctx)
- fscrypt_release_ctx(ctx);
+ bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+ if (IS_ERR(bio)) {
+ bio = NULL;
goto set_error_page;
}
- bio->bi_bdev = bdev;
- bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr);
- bio->bi_end_io = f2fs_read_end_io;
- bio->bi_private = ctx;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
@@ -1021,22 +1106,22 @@ submit_and_realloc:
goto next_page;
set_error_page:
SetPageError(page);
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ zero_user_segment(page, 0, PAGE_SIZE);
unlock_page(page);
goto next_page;
confused:
if (bio) {
- submit_bio(READ, bio);
+ __submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
unlock_page(page);
next_page:
if (pages)
- page_cache_release(page);
+ put_page(page);
}
BUG_ON(pages && !list_empty(pages));
if (bio)
- submit_bio(READ, bio);
+ __submit_bio(F2FS_I_SB(inode), bio, DATA);
return 0;
}
@@ -1092,14 +1177,24 @@ int do_write_data_page(struct f2fs_io_info *fio)
}
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+ gfp_t gfp_flags = GFP_NOFS;
/* wait for GCed encrypted page writeback */
f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
fio->old_blkaddr);
-
- fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page);
+retry_encrypt:
+ fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
+ gfp_flags);
if (IS_ERR(fio->encrypted_page)) {
err = PTR_ERR(fio->encrypted_page);
+ if (err == -ENOMEM) {
+ /* flush pending ios and wait for a while */
+ f2fs_flush_merged_bios(F2FS_I_SB(inode));
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ gfp_flags |= __GFP_NOFAIL;
+ err = 0;
+ goto retry_encrypt;
+ }
goto out_writepage;
}
}
@@ -1115,14 +1210,14 @@ int do_write_data_page(struct f2fs_io_info *fio)
!IS_ATOMIC_WRITTEN_PAGE(page) &&
need_inplace_update(inode))) {
rewrite_data_page(fio);
- set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
+ set_inode_flag(inode, FI_UPDATE_WRITE);
trace_f2fs_do_write_data_page(page, IPU);
} else {
write_data_page(&dn, fio);
trace_f2fs_do_write_data_page(page, OPU);
- set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
+ set_inode_flag(inode, FI_APPEND_WRITE);
if (page->index == 0)
- set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+ set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
}
out_writepage:
f2fs_put_dnode(&dn);
@@ -1136,14 +1231,16 @@ static int f2fs_write_data_page(struct page *page,
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;
+ >> PAGE_SHIFT;
+ loff_t psize = (page->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
bool need_balance_fs = false;
int err = 0;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = DATA,
- .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+ .op = REQ_OP_WRITE,
+ .op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0,
.page = page,
.encrypted_page = NULL,
};
@@ -1157,34 +1254,34 @@ static int f2fs_write_data_page(struct page *page,
* If the offset is out-of-range of file size,
* this page does not have to be written to disk.
*/
- offset = i_size & (PAGE_CACHE_SIZE - 1);
+ offset = i_size & (PAGE_SIZE - 1);
if ((page->index >= end_index + 1) || !offset)
goto out;
- zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+ zero_user_segment(page, offset, PAGE_SIZE);
write:
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (f2fs_is_drop_cache(inode))
goto out;
- if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
- available_free_memory(sbi, BASE_CHECK))
+ /* we should not write 0'th page having journal header */
+ if (f2fs_is_volatile_file(inode) && (!page->index ||
+ (!wbc->for_reclaim &&
+ available_free_memory(sbi, BASE_CHECK))))
goto redirty_out;
+ /* we should bypass data pages to proceed the kworkder jobs */
+ if (unlikely(f2fs_cp_error(sbi))) {
+ mapping_set_error(page->mapping, -EIO);
+ goto out;
+ }
+
/* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
- if (unlikely(f2fs_cp_error(sbi)))
- goto redirty_out;
err = do_write_data_page(&fio);
goto done;
}
- /* we should bypass data pages to proceed the kworkder jobs */
- if (unlikely(f2fs_cp_error(sbi))) {
- SetPageError(page);
- goto out;
- }
-
if (!wbc->for_reclaim)
need_balance_fs = true;
else if (has_not_enough_free_secs(sbi, 0))
@@ -1196,6 +1293,8 @@ write:
err = f2fs_write_inline_data(inode, page);
if (err == -EAGAIN)
err = do_write_data_page(&fio);
+ if (F2FS_I(inode)->last_disk_size < psize)
+ F2FS_I(inode)->last_disk_size = psize;
f2fs_unlock_op(sbi);
done:
if (err && err != -ENOENT)
@@ -1222,16 +1321,8 @@ out:
redirty_out:
redirty_page_for_writepage(wbc, page);
- return AOP_WRITEPAGE_ACTIVATE;
-}
-
-static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
- void *data)
-{
- struct address_space *mapping = data;
- int ret = mapping->a_ops->writepage(page, wbc);
- mapping_set_error(mapping, ret);
- return ret;
+ unlock_page(page);
+ return err;
}
/*
@@ -1240,8 +1331,7 @@ static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
* warm/hot data page.
*/
static int f2fs_write_cache_pages(struct address_space *mapping,
- struct writeback_control *wbc, writepage_t writepage,
- void *data)
+ struct writeback_control *wbc)
{
int ret = 0;
int done = 0;
@@ -1254,10 +1344,9 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
int cycled;
int range_whole = 0;
int tag;
- int step = 0;
pagevec_init(&pvec, 0);
-next:
+
if (wbc->range_cyclic) {
writeback_index = mapping->writeback_index; /* prev offset */
index = writeback_index;
@@ -1267,8 +1356,8 @@ next:
cycled = 0;
end = -1;
} else {
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ index = wbc->range_start >> PAGE_SHIFT;
+ end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
@@ -1312,9 +1401,6 @@ continue_unlock:
goto continue_unlock;
}
- if (step == is_cold_data(page))
- goto continue_unlock;
-
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
f2fs_wait_on_page_writeback(page,
@@ -1327,16 +1413,11 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- ret = (*writepage)(page, wbc, data);
+ ret = mapping->a_ops->writepage(page, wbc);
if (unlikely(ret)) {
- if (ret == AOP_WRITEPAGE_ACTIVATE) {
- unlock_page(page);
- ret = 0;
- } else {
- done_index = page->index + 1;
- done = 1;
- break;
- }
+ done_index = page->index + 1;
+ done = 1;
+ break;
}
if (--wbc->nr_to_write <= 0 &&
@@ -1349,11 +1430,6 @@ continue_unlock:
cond_resched();
}
- if (step < 1) {
- step++;
- goto next;
- }
-
if (!cycled && !done) {
cycled = 1;
index = 0;
@@ -1371,9 +1447,8 @@ static int f2fs_write_data_pages(struct address_space *mapping,
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- bool locked = false;
+ struct blk_plug plug;
int ret;
- long diff;
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
@@ -1389,7 +1464,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
goto skip_write;
/* skip writing during file defragment */
- if (is_inode_flag_set(F2FS_I(inode), FI_DO_DEFRAG))
+ if (is_inode_flag_set(inode, FI_DO_DEFRAG))
goto skip_write;
/* during POR, we don't need to trigger writepage at all. */
@@ -1398,20 +1473,16 @@ static int f2fs_write_data_pages(struct address_space *mapping,
trace_f2fs_writepages(mapping->host, wbc, DATA);
- diff = nr_pages_to_write(sbi, DATA, wbc);
-
- if (!S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_ALL) {
- mutex_lock(&sbi->writepages);
- locked = true;
- }
- ret = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
- f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
- if (locked)
- mutex_unlock(&sbi->writepages);
+ blk_start_plug(&plug);
+ ret = f2fs_write_cache_pages(mapping, wbc);
+ blk_finish_plug(&plug);
+ /*
+ * if some pages were truncated, we cannot guarantee its mapping->host
+ * to detect pending bios.
+ */
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
remove_dirty_inode(inode);
-
- wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
return ret;
skip_write:
@@ -1448,11 +1519,11 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
* the block addresses when there is no need to fill the page.
*/
if (!f2fs_has_inline_data(inode) && !f2fs_encrypted_inode(inode) &&
- len == PAGE_CACHE_SIZE)
+ len == PAGE_SIZE)
return 0;
if (f2fs_has_inline_data(inode) ||
- (pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
+ (pos & PAGE_MASK) >= i_size_read(inode)) {
f2fs_lock_op(sbi);
locked = true;
}
@@ -1469,8 +1540,9 @@ restart:
if (f2fs_has_inline_data(inode)) {
if (pos + len <= MAX_INLINE_DATA) {
read_inline_data(page, ipage);
- set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
- set_inline_node(ipage);
+ set_inode_flag(inode, FI_DATA_EXIST);
+ if (inode->i_nlink)
+ set_inline_node(ipage);
} else {
err = f2fs_convert_inline_page(&dn, page);
if (err)
@@ -1486,7 +1558,7 @@ restart:
} else {
/* hole case */
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
- if (err || (!err && dn.data_blkaddr == NULL_ADDR)) {
+ if (err || dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
f2fs_lock_op(sbi);
locked = true;
@@ -1513,7 +1585,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page = NULL;
- pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
+ pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
bool need_balance = false;
block_t blkaddr = NULL_ADDR;
int err = 0;
@@ -1561,55 +1633,52 @@ repeat:
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
- if (len == PAGE_CACHE_SIZE)
+ if (len == PAGE_SIZE)
goto out_update;
if (PageUptodate(page))
goto out_clear;
- if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
- unsigned start = pos & (PAGE_CACHE_SIZE - 1);
+ if ((pos & PAGE_MASK) >= i_size_read(inode)) {
+ unsigned start = pos & (PAGE_SIZE - 1);
unsigned end = start + len;
/* Reading beyond i_size is simple: memset to zero */
- zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
+ zero_user_segments(page, 0, start, end, PAGE_SIZE);
goto out_update;
}
if (blkaddr == NEW_ADDR) {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ zero_user_segment(page, 0, PAGE_SIZE);
} else {
- struct f2fs_io_info fio = {
- .sbi = sbi,
- .type = DATA,
- .rw = READ_SYNC,
- .old_blkaddr = blkaddr,
- .new_blkaddr = blkaddr,
- .page = page,
- .encrypted_page = NULL,
- };
- err = f2fs_submit_page_bio(&fio);
- if (err)
- goto fail;
+ struct bio *bio;
- lock_page(page);
- if (unlikely(!PageUptodate(page))) {
- err = -EIO;
+ bio = f2fs_grab_bio(inode, blkaddr, 1);
+ if (IS_ERR(bio)) {
+ err = PTR_ERR(bio);
+ goto fail;
+ }
+ bio_set_op_attrs(bio, REQ_OP_READ, READ_SYNC);
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+ bio_put(bio);
+ err = -EFAULT;
goto fail;
}
+
+ __submit_bio(sbi, bio, DATA);
+
+ lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
-
- /* avoid symlink page */
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
- err = fscrypt_decrypt_page(page);
- if (err)
- goto fail;
+ if (unlikely(!PageUptodate(page))) {
+ err = -EIO;
+ goto fail;
}
}
out_update:
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
out_clear:
clear_cold_data(page);
return 0;
@@ -1630,13 +1699,11 @@ static int f2fs_write_end(struct file *file,
trace_f2fs_write_end(inode, pos, len, copied);
set_page_dirty(page);
+ f2fs_put_page(page, 1);
- if (pos + copied > i_size_read(inode)) {
- i_size_write(inode, pos + copied);
- mark_inode_dirty(inode);
- }
+ if (pos + copied > i_size_read(inode))
+ f2fs_i_size_write(inode, pos + copied);
- f2fs_put_page(page, 1);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
@@ -1655,12 +1722,13 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
return 0;
}
-static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
+ loff_t offset = iocb->ki_pos;
+ int rw = iov_iter_rw(iter);
int err;
err = check_direct_IO(inode, iter, offset);
@@ -1669,14 +1737,23 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
return 0;
+ if (test_opt(F2FS_I_SB(inode), LFS))
+ return 0;
- trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
+ trace_f2fs_direct_IO_enter(inode, offset, count, rw);
- err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);
- if (err < 0 && iov_iter_rw(iter) == WRITE)
- f2fs_write_failed(mapping, offset + count);
+ down_read(&F2FS_I(inode)->dio_rwsem[rw]);
+ err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
+ up_read(&F2FS_I(inode)->dio_rwsem[rw]);
+
+ if (rw == WRITE) {
+ if (err > 0)
+ set_inode_flag(inode, FI_UPDATE_WRITE);
+ else if (err < 0)
+ f2fs_write_failed(mapping, offset + count);
+ }
- trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);
+ trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
return err;
}
@@ -1688,7 +1765,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
- (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE))
+ (offset % PAGE_SIZE || length != PAGE_SIZE))
return;
if (PageDirty(page)) {
@@ -1704,6 +1781,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
if (IS_ATOMIC_WRITTEN_PAGE(page))
return;
+ set_page_private(page, 0);
ClearPagePrivate(page);
}
@@ -1717,10 +1795,40 @@ int f2fs_release_page(struct page *page, gfp_t wait)
if (IS_ATOMIC_WRITTEN_PAGE(page))
return 0;
+ set_page_private(page, 0);
ClearPagePrivate(page);
return 1;
}
+/*
+ * This was copied from __set_page_dirty_buffers which gives higher performance
+ * in very high speed storages. (e.g., pmem)
+ */
+void f2fs_set_page_dirty_nobuffers(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ unsigned long flags;
+
+ if (unlikely(!mapping))
+ return;
+
+ spin_lock(&mapping->private_lock);
+ lock_page_memcg(page);
+ SetPageDirty(page);
+ spin_unlock(&mapping->private_lock);
+
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ WARN_ON_ONCE(!PageUptodate(page));
+ account_page_dirtied(page, mapping);
+ radix_tree_tag_set(&mapping->page_tree,
+ page_index(page), PAGECACHE_TAG_DIRTY);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+ unlock_page_memcg(page);
+
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+ return;
+}
+
static int f2fs_set_data_page_dirty(struct page *page)
{
struct address_space *mapping = page->mapping;
@@ -1728,7 +1836,8 @@ static int f2fs_set_data_page_dirty(struct page *page)
trace_f2fs_set_page_dirty(page, DATA);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
if (f2fs_is_atomic_file(inode)) {
if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
@@ -1743,7 +1852,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
}
if (!PageDirty(page)) {
- __set_page_dirty_nobuffers(page);
+ f2fs_set_page_dirty_nobuffers(page);
update_dirty_page(inode, page);
return 1;
}
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 4fb6ef88a34f..badd407bb622 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -47,8 +47,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+ si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
- si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
+ si->wb_bios = atomic_read(&sbi->nr_wb_bios);
si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
si->rsvd_segs = reserved_segments(sbi);
si->overp_segs = overprovision_segments(sbi);
@@ -58,6 +59,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->inline_xattr = atomic_read(&sbi->inline_xattr);
si->inline_inode = atomic_read(&sbi->inline_inode);
si->inline_dir = atomic_read(&sbi->inline_dir);
+ si->orphans = sbi->im[ORPHAN_INO].ino_num;
si->utilization = utilization(sbi);
si->free_segs = free_segments(sbi);
@@ -143,6 +145,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
si->base_mem += 2 * sizeof(struct f2fs_inode_info);
si->base_mem += sizeof(*sbi->ckpt);
+ si->base_mem += sizeof(struct percpu_counter) * NR_COUNT_TYPE;
/* build sm */
si->base_mem += sizeof(struct f2fs_sm_info);
@@ -164,7 +167,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
/* build curseg */
si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
- si->base_mem += PAGE_CACHE_SIZE * NR_CURSEG_TYPE;
+ si->base_mem += PAGE_SIZE * NR_CURSEG_TYPE;
/* build dirty segmap */
si->base_mem += sizeof(struct dirty_seglist_info);
@@ -192,7 +195,7 @@ get_cache:
si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
sizeof(struct nat_entry_set);
si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
- for (i = 0; i <= UPDATE_INO; i++)
+ for (i = 0; i <= ORPHAN_INO; i++)
si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
si->cache_mem += atomic_read(&sbi->total_ext_tree) *
sizeof(struct extent_tree);
@@ -201,9 +204,9 @@ get_cache:
si->page_mem = 0;
npages = NODE_MAPPING(sbi)->nrpages;
- si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
+ si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
npages = META_MAPPING(sbi)->nrpages;
- si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
+ si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
}
static int stat_show(struct seq_file *s, void *v)
@@ -216,8 +219,9 @@ static int stat_show(struct seq_file *s, void *v)
list_for_each_entry(si, &f2fs_stat_list, stat_list) {
update_general_status(si->sbi);
- seq_printf(s, "\n=====[ partition info(%pg). #%d ]=====\n",
- si->sbi->sb->s_bdev, i++);
+ seq_printf(s, "\n=====[ partition info(%pg). #%d, %s]=====\n",
+ si->sbi->sb->s_bdev, i++,
+ f2fs_readonly(si->sbi->sb) ? "RO": "RW");
seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
si->sit_area_segs, si->nat_area_segs);
seq_printf(s, "[SSA: %d] [MAIN: %d",
@@ -237,6 +241,8 @@ static int stat_show(struct seq_file *s, void *v)
si->inline_inode);
seq_printf(s, " - Inline_dentry Inode: %u\n",
si->inline_dir);
+ seq_printf(s, " - Orphan Inode: %u\n",
+ si->orphans);
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
si->main_area_segs, si->main_area_sections,
si->main_area_zones);
@@ -295,15 +301,15 @@ static int stat_show(struct seq_file *s, void *v)
seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n",
si->ext_tree, si->zombie_tree, si->ext_node);
seq_puts(s, "\nBalancing F2FS Async:\n");
- seq_printf(s, " - inmem: %4d, wb: %4d\n",
- si->inmem_pages, si->wb_pages);
- seq_printf(s, " - nodes: %4d in %4d\n",
+ seq_printf(s, " - inmem: %4lld, wb_bios: %4d\n",
+ si->inmem_pages, si->wb_bios);
+ seq_printf(s, " - nodes: %4lld in %4d\n",
si->ndirty_node, si->node_pages);
- seq_printf(s, " - dents: %4d in dirs:%4d\n",
- si->ndirty_dent, si->ndirty_dirs);
- seq_printf(s, " - datas: %4d in files:%4d\n",
+ seq_printf(s, " - dents: %4lld in dirs:%4d (%4d)\n",
+ si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
+ seq_printf(s, " - datas: %4lld in files:%4d\n",
si->ndirty_data, si->ndirty_files);
- seq_printf(s, " - meta: %4d in %4d\n",
+ seq_printf(s, " - meta: %4lld in %4d\n",
si->ndirty_meta, si->meta_pages);
seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n",
si->dirty_nats, si->nats, si->dirty_sits, si->sits);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 80641ad82745..9054aeac8015 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -17,8 +17,8 @@
static unsigned long dir_blocks(struct inode *inode)
{
- return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1))
- >> PAGE_CACHE_SHIFT;
+ return ((unsigned long long) (i_size_read(inode) + PAGE_SIZE - 1))
+ >> PAGE_SHIFT;
}
static unsigned int dir_buckets(unsigned int level, int dir_level)
@@ -48,7 +48,6 @@ unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
[F2FS_FT_SYMLINK] = DT_LNK,
};
-#define S_SHIFT 12
static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = F2FS_FT_DIR,
@@ -64,6 +63,13 @@ void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
}
+unsigned char get_de_type(struct f2fs_dir_entry *de)
+{
+ if (de->file_type < F2FS_FT_MAX)
+ return f2fs_filetype_table[de->file_type];
+ return DT_UNKNOWN;
+}
+
static unsigned long dir_block_index(unsigned int level,
int dir_level, unsigned int idx)
{
@@ -95,11 +101,6 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
else
kunmap(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(F2FS_P_SB(dentry_page), d.max < 0);
return de;
}
@@ -124,6 +125,11 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
de = &d->dentry[bit_pos];
+ if (unlikely(!de->name_len)) {
+ bit_pos++;
+ continue;
+ }
+
/* encrypted case */
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
@@ -141,10 +147,6 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
*max_slots = max_len;
max_len = 0;
- /* remain bug on condition */
- if (unlikely(!de->name_len))
- d->max = -1;
-
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
}
@@ -183,8 +185,13 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
/* no need to allocate new dentry pages to all the indices */
dentry_page = find_data_page(dir, bidx);
if (IS_ERR(dentry_page)) {
- room = true;
- continue;
+ if (PTR_ERR(dentry_page) == -ENOENT) {
+ room = true;
+ continue;
+ } else {
+ *res_page = dentry_page;
+ break;
+ }
}
de = find_in_block(dentry_page, fname, namehash, &max_slots,
@@ -212,7 +219,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
* Entry is guaranteed to be valid.
*/
struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
- struct qstr *child, struct page **res_page)
+ const struct qstr *child, struct page **res_page)
{
unsigned long npages = dir_blocks(dir);
struct f2fs_dir_entry *de = NULL;
@@ -221,19 +228,22 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
struct fscrypt_name fname;
int err;
- *res_page = NULL;
-
err = fscrypt_setup_filename(dir, child, 1, &fname);
- if (err)
+ if (err) {
+ *res_page = ERR_PTR(err);
return NULL;
+ }
if (f2fs_has_inline_dentry(dir)) {
+ *res_page = NULL;
de = find_in_inline_dir(dir, &fname, res_page);
goto out;
}
- if (npages == 0)
+ if (npages == 0) {
+ *res_page = NULL;
goto out;
+ }
max_depth = F2FS_I(dir)->i_current_depth;
if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
@@ -241,13 +251,13 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
"Corrupted max_depth of %lu: %u",
dir->i_ino, max_depth);
max_depth = MAX_DIR_HASH_DEPTH;
- F2FS_I(dir)->i_current_depth = max_depth;
- mark_inode_dirty(dir);
+ f2fs_i_depth_write(dir, max_depth);
}
for (level = 0; level < max_depth; level++) {
+ *res_page = NULL;
de = find_in_level(dir, level, &fname, res_page);
- if (de)
+ if (de || IS_ERR(*res_page))
break;
}
out:
@@ -257,35 +267,22 @@ out:
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
{
- struct page *page;
- struct f2fs_dir_entry *de;
- struct f2fs_dentry_block *dentry_blk;
-
- if (f2fs_has_inline_dentry(dir))
- return f2fs_parent_inline_dir(dir, p);
-
- page = get_lock_data_page(dir, 0, false);
- if (IS_ERR(page))
- return NULL;
+ struct qstr dotdot = QSTR_INIT("..", 2);
- dentry_blk = kmap(page);
- de = &dentry_blk->dentry[1];
- *p = page;
- unlock_page(page);
- return de;
+ return f2fs_find_entry(dir, &dotdot, p);
}
-ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
+ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
+ struct page **page)
{
ino_t res = 0;
struct f2fs_dir_entry *de;
- struct page *page;
- de = f2fs_find_entry(dir, qstr, &page);
+ de = f2fs_find_entry(dir, qstr, page);
if (de) {
res = le32_to_cpu(de->ino);
- f2fs_dentry_kunmap(dir, page);
- f2fs_put_page(page, 0);
+ f2fs_dentry_kunmap(dir, *page);
+ f2fs_put_page(*page, 0);
}
return res;
@@ -301,9 +298,9 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
set_de_type(de, inode->i_mode);
f2fs_dentry_kunmap(dir, page);
set_page_dirty(page);
- dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- mark_inode_dirty(dir);
+ dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+ f2fs_mark_inode_dirty_sync(dir);
f2fs_put_page(page, 1);
}
@@ -383,15 +380,20 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
struct page *page;
int err;
- if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
+ if (is_inode_flag_set(inode, FI_NEW_INODE)) {
page = new_inode_page(inode);
if (IS_ERR(page))
return page;
if (S_ISDIR(inode->i_mode)) {
+ /* in order to handle error case */
+ get_page(page);
err = make_empty_dir(inode, dir, page);
- if (err)
- goto error;
+ if (err) {
+ lock_page(page);
+ goto put_error;
+ }
+ put_page(page);
}
err = f2fs_init_acl(inode, dir, page, dpage);
@@ -422,7 +424,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
* This file should be checkpointed during fsync.
* We lost i_pino from now on.
*/
- if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
+ if (is_inode_flag_set(inode, FI_INC_LINK)) {
file_lost_pino(inode);
/*
* If link the tmpfile to alias through linkat path,
@@ -430,41 +432,33 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
*/
if (inode->i_nlink == 0)
remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
- inc_nlink(inode);
+ f2fs_i_links_write(inode, true);
}
return page;
put_error:
+ clear_nlink(inode);
+ update_inode(inode, page);
f2fs_put_page(page, 1);
-error:
- /* once the failed inode becomes a bad inode, i_mode is S_IFREG */
- truncate_inode_pages(&inode->i_data, 0);
- truncate_blocks(inode, 0, false);
- remove_dirty_inode(inode);
- remove_inode_page(inode);
return ERR_PTR(err);
}
void update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth)
{
- if (inode && is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
- if (S_ISDIR(inode->i_mode)) {
- inc_nlink(dir);
- set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
- }
- clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+ if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) {
+ if (S_ISDIR(inode->i_mode))
+ f2fs_i_links_write(dir, true);
+ clear_inode_flag(inode, FI_NEW_INODE);
}
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- mark_inode_dirty(dir);
+ f2fs_mark_inode_dirty_sync(dir);
- if (F2FS_I(dir)->i_current_depth != current_depth) {
- F2FS_I(dir)->i_current_depth = current_depth;
- set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
- }
+ if (F2FS_I(dir)->i_current_depth != current_depth)
+ f2fs_i_depth_write(dir, current_depth);
- if (inode && is_inode_flag_set(F2FS_I(inode), FI_INC_LINK))
- clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ if (inode && is_inode_flag_set(inode, FI_INC_LINK))
+ clear_inode_flag(inode, FI_INC_LINK);
}
int room_for_filename(const void *bitmap, int slots, int max_slots)
@@ -509,11 +503,7 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
}
}
-/*
- * Caller should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op().
- */
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
struct inode *inode, nid_t ino, umode_t mode)
{
unsigned int bit_pos;
@@ -526,28 +516,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
struct f2fs_dentry_block *dentry_blk = NULL;
struct f2fs_dentry_ptr d;
struct page *page = NULL;
- struct fscrypt_name fname;
- struct qstr new_name;
- int slots, err;
-
- err = fscrypt_setup_filename(dir, name, 0, &fname);
- if (err)
- return err;
-
- new_name.name = fname_name(&fname);
- new_name.len = fname_len(&fname);
-
- if (f2fs_has_inline_dentry(dir)) {
- err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
- if (!err || err != -EAGAIN)
- goto out;
- else
- err = 0;
- }
+ int slots, err = 0;
level = 0;
- slots = GET_DENTRY_SLOTS(new_name.len);
- dentry_hash = f2fs_dentry_hash(&new_name);
+ slots = GET_DENTRY_SLOTS(new_name->len);
+ dentry_hash = f2fs_dentry_hash(new_name);
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
@@ -556,10 +529,12 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
}
start:
- if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) {
- err = -ENOSPC;
- goto out;
- }
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_DIR_DEPTH))
+ return -ENOSPC;
+#endif
+ if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
+ return -ENOSPC;
/* Increase the depth, if required */
if (level == current_depth)
@@ -573,10 +548,8 @@ start:
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = get_new_data_page(dir, NULL, block, true);
- if (IS_ERR(dentry_page)) {
- err = PTR_ERR(dentry_page);
- goto out;
- }
+ if (IS_ERR(dentry_page))
+ return PTR_ERR(dentry_page);
dentry_blk = kmap(dentry_page);
bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
@@ -596,7 +569,7 @@ add_dentry:
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, &new_name, NULL);
+ page = init_inode_metadata(inode, dir, new_name, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -606,14 +579,12 @@ add_dentry:
}
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
- f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos);
+ f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
set_page_dirty(dentry_page);
if (inode) {
- /* we don't need to mark_inode_dirty now */
- F2FS_I(inode)->i_pino = dir->i_ino;
- update_inode(inode, page);
+ f2fs_i_pino_write(inode, dir->i_ino);
f2fs_put_page(page, 1);
}
@@ -622,13 +593,36 @@ fail:
if (inode)
up_write(&F2FS_I(inode)->i_sem);
- if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
- update_inode_page(dir);
- clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
- }
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
-out:
+
+ return err;
+}
+
+/*
+ * Caller should grab and release a rwsem by calling f2fs_lock_op() and
+ * f2fs_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+ struct inode *inode, nid_t ino, umode_t mode)
+{
+ struct fscrypt_name fname;
+ struct qstr new_name;
+ int err;
+
+ err = fscrypt_setup_filename(dir, name, 0, &fname);
+ if (err)
+ return err;
+
+ new_name.name = fname_name(&fname);
+ new_name.len = fname_len(&fname);
+
+ err = -EAGAIN;
+ if (f2fs_has_inline_dentry(dir))
+ err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
+ if (err == -EAGAIN)
+ err = f2fs_add_regular_entry(dir, &new_name, inode, ino, mode);
+
fscrypt_free_filename(&fname);
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
return err;
@@ -645,42 +639,34 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
err = PTR_ERR(page);
goto fail;
}
- /* we don't need to mark_inode_dirty now */
- update_inode(inode, page);
f2fs_put_page(page, 1);
- clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+ clear_inode_flag(inode, FI_NEW_INODE);
fail:
up_write(&F2FS_I(inode)->i_sem);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return err;
}
-void f2fs_drop_nlink(struct inode *dir, struct inode *inode, struct page *page)
+void f2fs_drop_nlink(struct inode *dir, struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
down_write(&F2FS_I(inode)->i_sem);
- if (S_ISDIR(inode->i_mode)) {
- drop_nlink(dir);
- if (page)
- update_inode(dir, page);
- else
- update_inode_page(dir);
- }
+ if (S_ISDIR(inode->i_mode))
+ f2fs_i_links_write(dir, false);
inode->i_ctime = CURRENT_TIME;
- drop_nlink(inode);
+ f2fs_i_links_write(inode, false);
if (S_ISDIR(inode->i_mode)) {
- drop_nlink(inode);
- i_size_write(inode, 0);
+ f2fs_i_links_write(inode, false);
+ f2fs_i_size_write(inode, 0);
}
up_write(&F2FS_I(inode)->i_sem);
- update_inode_page(inode);
if (inode->i_nlink == 0)
- add_orphan_inode(sbi, inode->i_ino);
+ add_orphan_inode(inode);
else
release_orphan_inode(sbi);
}
@@ -718,9 +704,10 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
set_page_dirty(page);
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+ f2fs_mark_inode_dirty_sync(dir);
if (inode)
- f2fs_drop_nlink(dir, inode, NULL);
+ f2fs_drop_nlink(dir, inode);
if (bit_pos == NR_DENTRY_IN_BLOCK &&
!truncate_hole(dir, page->index, page->index + 1)) {
@@ -792,10 +779,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
continue;
}
- if (de->file_type < F2FS_FT_MAX)
- d_type = f2fs_filetype_table[de->file_type];
- else
- d_type = DT_UNKNOWN;
+ d_type = get_de_type(de);
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
@@ -804,7 +788,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
int save_len = fstr->len;
int ret;
- de_name.name = kmalloc(de_name.len, GFP_NOFS);
+ de_name.name = f2fs_kmalloc(de_name.len, GFP_NOFS);
if (!de_name.name)
return false;
@@ -887,6 +871,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
}
+ err = 0;
out:
fscrypt_fname_free_buffer(&fstr);
return err;
@@ -902,7 +887,7 @@ static int f2fs_dir_open(struct inode *inode, struct file *filp)
const struct file_operations f2fs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = f2fs_readdir,
+ .iterate_shared = f2fs_readdir,
.fsync = f2fs_sync_file,
.open = f2fs_dir_open,
.unlocked_ioctl = f2fs_ioctl,
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index c859bb044728..2b06d4fcd954 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -170,8 +170,10 @@ static void __drop_largest_extent(struct inode *inode,
{
struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
- if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs)
+ if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
largest->len = 0;
+ f2fs_mark_inode_dirty_sync(inode);
+ }
}
/* return true, if inode page is changed */
@@ -196,8 +198,7 @@ bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
if (!i_ext || !i_ext->len)
return false;
- set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
- le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
+ get_extent_info(&ei, i_ext);
write_lock(&et->lock);
if (atomic_read(&et->node_cnt))
@@ -336,11 +337,12 @@ lookup_neighbors:
return en;
}
-static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
+static struct extent_node *__try_merge_extent_node(struct inode *inode,
struct extent_tree *et, struct extent_info *ei,
struct extent_node *prev_ex,
struct extent_node *next_ex)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_node *en = NULL;
if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {
@@ -361,7 +363,7 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
if (!en)
return NULL;
- __try_update_largest_extent(et, en);
+ __try_update_largest_extent(inode, et, en);
spin_lock(&sbi->extent_lock);
if (!list_empty(&en->list)) {
@@ -372,11 +374,12 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
return en;
}
-static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
+static struct extent_node *__insert_extent_tree(struct inode *inode,
struct extent_tree *et, struct extent_info *ei,
struct rb_node **insert_p,
struct rb_node *insert_parent)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct rb_node **p = &et->root.rb_node;
struct rb_node *parent = NULL;
struct extent_node *en = NULL;
@@ -403,7 +406,7 @@ do_insert:
if (!en)
return NULL;
- __try_update_largest_extent(et, en);
+ __try_update_largest_extent(inode, et, en);
/* update in global extent list */
spin_lock(&sbi->extent_lock);
@@ -432,7 +435,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
write_lock(&et->lock);
- if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) {
+ if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
write_unlock(&et->lock);
return false;
}
@@ -474,7 +477,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
set_extent_info(&ei, end,
end - dei.fofs + dei.blk,
org_end - end);
- en1 = __insert_extent_tree(sbi, et, &ei,
+ en1 = __insert_extent_tree(inode, et, &ei,
NULL, NULL);
next_en = en1;
} else {
@@ -495,7 +498,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
}
if (parts)
- __try_update_largest_extent(et, en);
+ __try_update_largest_extent(inode, et, en);
else
__release_extent_node(sbi, et, en);
@@ -515,20 +518,20 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
if (blkaddr) {
set_extent_info(&ei, fofs, blkaddr, len);
- if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
- __insert_extent_tree(sbi, et, &ei,
+ if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en))
+ __insert_extent_tree(inode, et, &ei,
insert_p, insert_parent);
/* give up extent_cache, if split and small updates happen */
if (dei.len >= 1 &&
prev.len < F2FS_MIN_EXTENT_LEN &&
et->largest.len < F2FS_MIN_EXTENT_LEN) {
- et->largest.len = 0;
- set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
+ __drop_largest_extent(inode, 0, UINT_MAX);
+ set_inode_flag(inode, FI_NO_EXTENT);
}
}
- if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+ if (is_inode_flag_set(inode, FI_NO_EXTENT))
__free_extent_tree(sbi, et);
write_unlock(&et->lock);
@@ -628,6 +631,19 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode)
return node_cnt;
}
+void f2fs_drop_extent_tree(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct extent_tree *et = F2FS_I(inode)->extent_tree;
+
+ set_inode_flag(inode, FI_NO_EXTENT);
+
+ write_lock(&et->lock);
+ __free_extent_tree(sbi, et);
+ __drop_largest_extent(inode, 0, UINT_MAX);
+ write_unlock(&et->lock);
+}
+
void f2fs_destroy_extent_tree(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -686,9 +702,7 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
dn->ofs_in_node;
-
- if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1))
- sync_inode_page(dn);
+ f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1);
}
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
@@ -698,8 +712,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
if (!f2fs_may_extent_tree(dn->inode))
return;
- if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len))
- sync_inode_page(dn);
+ f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len);
}
void init_extent_cache_info(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index bbe2cd1265d0..675fa79d86f6 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -37,6 +37,60 @@
} while (0)
#endif
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+enum {
+ FAULT_KMALLOC,
+ FAULT_PAGE_ALLOC,
+ FAULT_ALLOC_NID,
+ FAULT_ORPHAN,
+ FAULT_BLOCK,
+ FAULT_DIR_DEPTH,
+ FAULT_EVICT_INODE,
+ FAULT_MAX,
+};
+
+struct f2fs_fault_info {
+ atomic_t inject_ops;
+ unsigned int inject_rate;
+ unsigned int inject_type;
+};
+
+extern struct f2fs_fault_info f2fs_fault;
+extern char *fault_name[FAULT_MAX];
+#define IS_FAULT_SET(type) (f2fs_fault.inject_type & (1 << (type)))
+
+static inline bool time_to_inject(int type)
+{
+ if (!f2fs_fault.inject_rate)
+ return false;
+ if (type == FAULT_KMALLOC && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_PAGE_ALLOC && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_ALLOC_NID && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_ORPHAN && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_BLOCK && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_DIR_DEPTH && !IS_FAULT_SET(type))
+ return false;
+ else if (type == FAULT_EVICT_INODE && !IS_FAULT_SET(type))
+ return false;
+
+ atomic_inc(&f2fs_fault.inject_ops);
+ if (atomic_read(&f2fs_fault.inject_ops) >= f2fs_fault.inject_rate) {
+ atomic_set(&f2fs_fault.inject_ops, 0);
+ printk("%sF2FS-fs : inject %s in %pF\n",
+ KERN_INFO,
+ fault_name[type],
+ __builtin_return_address(0));
+ return true;
+ }
+ return false;
+}
+#endif
+
/*
* For mount options
*/
@@ -56,6 +110,9 @@
#define F2FS_MOUNT_EXTENT_CACHE 0x00002000
#define F2FS_MOUNT_FORCE_FG_GC 0x00004000
#define F2FS_MOUNT_DATA_FLUSH 0x00008000
+#define F2FS_MOUNT_FAULT_INJECTION 0x00010000
+#define F2FS_MOUNT_ADAPTIVE 0x00020000
+#define F2FS_MOUNT_LFS 0x00040000
#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -76,6 +133,7 @@ struct f2fs_mount_info {
};
#define F2FS_FEATURE_ENCRYPT 0x0001
+#define F2FS_FEATURE_HMSMR 0x0002
#define F2FS_HAS_FEATURE(sb, mask) \
((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -106,7 +164,7 @@ enum {
#define BATCHED_TRIM_BLOCKS(sbi) \
(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
#define DEF_CP_INTERVAL 60 /* 60 secs */
-#define DEF_IDLE_INTERVAL 120 /* 2 mins */
+#define DEF_IDLE_INTERVAL 5 /* 5 secs */
struct cp_control {
int reason;
@@ -159,7 +217,6 @@ struct fsync_inode_entry {
struct inode *inode; /* vfs inode pointer */
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(jnl) (le16_to_cpu(jnl->n_nats))
@@ -211,6 +268,8 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
#define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6)
#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7)
#define F2FS_IOC_DEFRAGMENT _IO(F2FS_IOCTL_MAGIC, 8)
+#define F2FS_IOC_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \
+ struct f2fs_move_range)
#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
@@ -240,6 +299,13 @@ struct f2fs_defragment {
u64 len;
};
+struct f2fs_move_range {
+ u32 dst_fd; /* destination fd */
+ u64 pos_in; /* start position in src_fd */
+ u64 pos_out; /* start position in dst_fd */
+ u64 len; /* size to move */
+};
+
/*
* For INODE and NODE manager
*/
@@ -385,24 +451,27 @@ 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_pages; /* # of dirty pages */
+ struct percpu_counter 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 */
+ loff_t last_disk_size; /* lastly written file size */
- struct list_head dirty_list; /* linked in global dirty list */
+ struct list_head dirty_list; /* dirty list for dirs and files */
+ struct list_head gdirty_list; /* linked in global dirty list */
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
struct mutex inmem_lock; /* lock for inmemory pages */
struct extent_tree *extent_tree; /* cached extent_tree entry */
+ struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
};
static inline void get_extent_info(struct extent_info *ext,
- struct f2fs_extent i_ext)
+ struct f2fs_extent *i_ext)
{
- ext->fofs = le32_to_cpu(i_ext.fofs);
- ext->blk = le32_to_cpu(i_ext.blk);
- ext->len = le32_to_cpu(i_ext.len);
+ ext->fofs = le32_to_cpu(i_ext->fofs);
+ ext->blk = le32_to_cpu(i_ext->blk);
+ ext->len = le32_to_cpu(i_ext->len);
}
static inline void set_raw_extent(struct extent_info *ext,
@@ -447,11 +516,14 @@ static inline bool __is_front_mergeable(struct extent_info *cur,
return __is_extent_mergeable(cur, front);
}
-static inline void __try_update_largest_extent(struct extent_tree *et,
- struct extent_node *en)
+extern void f2fs_mark_inode_dirty_sync(struct inode *);
+static inline void __try_update_largest_extent(struct inode *inode,
+ struct extent_tree *et, struct extent_node *en)
{
- if (en->ei.len > et->largest.len)
+ if (en->ei.len > et->largest.len) {
et->largest = en->ei;
+ f2fs_mark_inode_dirty_sync(inode);
+ }
}
struct f2fs_nm_info {
@@ -466,7 +538,7 @@ 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 */
- struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
+ struct percpu_rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
@@ -548,6 +620,7 @@ struct flush_cmd {
struct flush_cmd_control {
struct task_struct *f2fs_issue_flush; /* flush thread */
wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */
+ atomic_t submit_flush; /* # of issued flushes */
struct llist_head issue_list; /* list for command issue */
struct llist_node *dispatch_list; /* list for command dispatch */
};
@@ -599,12 +672,12 @@ struct f2fs_sm_info {
* dirty dentry blocks, dirty node blocks, and dirty meta blocks.
*/
enum count_type {
- F2FS_WRITEBACK,
F2FS_DIRTY_DENTS,
F2FS_DIRTY_DATA,
F2FS_DIRTY_NODES,
F2FS_DIRTY_META,
F2FS_INMEM_PAGES,
+ F2FS_DIRTY_IMETA,
NR_COUNT_TYPE,
};
@@ -636,14 +709,15 @@ enum page_type {
struct f2fs_io_info {
struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
- int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */
+ int op; /* contains REQ_OP_ */
+ int op_flags; /* rq_flag_bits */
block_t new_blkaddr; /* new block address to be written */
block_t old_blkaddr; /* old block address before Cow */
struct page *page; /* page to be written */
struct page *encrypted_page; /* encrypted page */
};
-#define is_read_io(rw) (((rw) & 1) == READ)
+#define is_read_io(rw) (rw == READ)
struct f2fs_bio_info {
struct f2fs_sb_info *sbi; /* f2fs superblock */
struct bio *bio; /* bios to merge */
@@ -655,6 +729,7 @@ struct f2fs_bio_info {
enum inode_type {
DIR_INODE, /* for dirty dir inode */
FILE_INODE, /* for dirty regular/symlink inode */
+ DIRTY_META, /* for all dirtied inode metadata */
NR_INODE_TYPE,
};
@@ -672,6 +747,7 @@ enum {
SBI_IS_CLOSE, /* specify unmounting */
SBI_NEED_FSCK, /* need fsck.f2fs to fix */
SBI_POR_DOING, /* recovery is doing or not */
+ SBI_NEED_SB_WRITE, /* need to recover superblock */
};
enum {
@@ -680,6 +756,10 @@ enum {
MAX_TIME,
};
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+#define F2FS_KEY_DESC_PREFIX "f2fs:"
+#define F2FS_KEY_DESC_PREFIX_SIZE 5
+#endif
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
@@ -687,6 +767,10 @@ struct f2fs_sb_info {
int valid_super_block; /* valid super block no */
int s_flag; /* flags for sbi */
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ u8 key_prefix[F2FS_KEY_DESC_PREFIX_SIZE];
+ u8 key_prefix_size;
+#endif
/* for node-related operations */
struct f2fs_nm_info *nm_info; /* node manager */
struct inode *node_inode; /* cache node blocks */
@@ -697,14 +781,14 @@ struct f2fs_sb_info {
/* for bio operations */
struct f2fs_bio_info read_io; /* for read bios */
struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */
+ struct mutex wio_mutex[NODE + 1]; /* bio ordering for NODE/DATA */
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
struct inode *meta_inode; /* cache meta blocks */
struct mutex cp_mutex; /* checkpoint procedure lock */
- struct rw_semaphore cp_rwsem; /* blocking FS operations */
+ struct percpu_rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
- struct mutex writepages; /* mutex for writepages() */
wait_queue_head_t cp_wait;
unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
long interval_time[MAX_TIME]; /* to store thresholds */
@@ -742,18 +826,24 @@ struct f2fs_sb_info {
unsigned int total_sections; /* total section count */
unsigned int total_node_count; /* total node block count */
unsigned int total_valid_node_count; /* valid node block count */
- unsigned int total_valid_inode_count; /* valid inode count */
loff_t max_file_blocks; /* max block index of file */
int active_logs; /* # of active logs */
int dir_level; /* directory level */
block_t user_block_count; /* # of user blocks */
block_t total_valid_block_count; /* # of valid blocks */
- block_t alloc_valid_block_count; /* # of allocated blocks */
block_t discard_blks; /* discard command candidats */
block_t last_valid_block_count; /* for recovery */
u32 s_next_generation; /* for NFS support */
- atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */
+ atomic_t nr_wb_bios; /* # of writeback bios */
+
+ /* # of pages, see count_type */
+ struct percpu_counter nr_pages[NR_COUNT_TYPE];
+ /* # of allocated blocks */
+ struct percpu_counter alloc_valid_block_count;
+
+ /* valid inode count */
+ struct percpu_counter total_valid_inode_count;
struct f2fs_mount_info mount_opt; /* mount options */
@@ -984,22 +1074,22 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
{
- down_read(&sbi->cp_rwsem);
+ percpu_down_read(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
- up_read(&sbi->cp_rwsem);
+ percpu_up_read(&sbi->cp_rwsem);
}
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
- down_write(&sbi->cp_rwsem);
+ percpu_down_write(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
{
- up_write(&sbi->cp_rwsem);
+ percpu_up_write(&sbi->cp_rwsem);
}
static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
@@ -1054,22 +1144,37 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
return ofs == XATTR_NODE_OFFSET;
}
+static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool);
static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
- struct inode *inode, blkcnt_t count)
+ struct inode *inode, blkcnt_t *count)
{
- block_t valid_block_count;
+ blkcnt_t diff;
- spin_lock(&sbi->stat_lock);
- valid_block_count =
- sbi->total_valid_block_count + (block_t)count;
- if (unlikely(valid_block_count > sbi->user_block_count)) {
- spin_unlock(&sbi->stat_lock);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_BLOCK))
return false;
+#endif
+ /*
+ * let's increase this in prior to actual block count change in order
+ * for f2fs_sync_file to avoid data races when deciding checkpoint.
+ */
+ percpu_counter_add(&sbi->alloc_valid_block_count, (*count));
+
+ spin_lock(&sbi->stat_lock);
+ sbi->total_valid_block_count += (block_t)(*count);
+ if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) {
+ diff = sbi->total_valid_block_count - sbi->user_block_count;
+ *count -= diff;
+ sbi->total_valid_block_count = sbi->user_block_count;
+ if (!*count) {
+ spin_unlock(&sbi->stat_lock);
+ percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
+ return false;
+ }
}
- inode->i_blocks += count;
- sbi->total_valid_block_count = valid_block_count;
- sbi->alloc_valid_block_count += (block_t)count;
spin_unlock(&sbi->stat_lock);
+
+ f2fs_i_blocks_write(inode, *count, true);
return true;
}
@@ -1080,27 +1185,27 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
spin_lock(&sbi->stat_lock);
f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
f2fs_bug_on(sbi, inode->i_blocks < count);
- inode->i_blocks -= count;
sbi->total_valid_block_count -= (block_t)count;
spin_unlock(&sbi->stat_lock);
+ f2fs_i_blocks_write(inode, count, false);
}
static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
- atomic_inc(&sbi->nr_pages[count_type]);
+ percpu_counter_inc(&sbi->nr_pages[count_type]);
set_sbi_flag(sbi, SBI_IS_DIRTY);
}
static inline void inode_inc_dirty_pages(struct inode *inode)
{
- atomic_inc(&F2FS_I(inode)->dirty_pages);
+ percpu_counter_inc(&F2FS_I(inode)->dirty_pages);
inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
}
static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
{
- atomic_dec(&sbi->nr_pages[count_type]);
+ percpu_counter_dec(&sbi->nr_pages[count_type]);
}
static inline void inode_dec_dirty_pages(struct inode *inode)
@@ -1109,26 +1214,28 @@ static inline void inode_dec_dirty_pages(struct inode *inode)
!S_ISLNK(inode->i_mode))
return;
- atomic_dec(&F2FS_I(inode)->dirty_pages);
+ percpu_counter_dec(&F2FS_I(inode)->dirty_pages);
dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
}
-static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
+static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
{
- return atomic_read(&sbi->nr_pages[count_type]);
+ return percpu_counter_sum_positive(&sbi->nr_pages[count_type]);
}
-static inline int get_dirty_pages(struct inode *inode)
+static inline s64 get_dirty_pages(struct inode *inode)
{
- return atomic_read(&F2FS_I(inode)->dirty_pages);
+ return percpu_counter_sum_positive(&F2FS_I(inode)->dirty_pages);
}
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
- return ((get_pages(sbi, block_type) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+ unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
+ sbi->log_blocks_per_seg;
+
+ return segs / sbi->segs_per_sec;
}
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
@@ -1215,13 +1322,13 @@ static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
}
if (inode)
- inode->i_blocks++;
+ f2fs_i_blocks_write(inode, 1, true);
- sbi->alloc_valid_block_count++;
sbi->total_valid_node_count++;
sbi->total_valid_block_count++;
spin_unlock(&sbi->stat_lock);
+ percpu_counter_inc(&sbi->alloc_valid_block_count);
return true;
}
@@ -1234,7 +1341,7 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
f2fs_bug_on(sbi, !sbi->total_valid_node_count);
f2fs_bug_on(sbi, !inode->i_blocks);
- inode->i_blocks--;
+ f2fs_i_blocks_write(inode, 1, false);
sbi->total_valid_node_count--;
sbi->total_valid_block_count--;
@@ -1248,28 +1355,30 @@ static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count);
- sbi->total_valid_inode_count++;
- spin_unlock(&sbi->stat_lock);
+ percpu_counter_inc(&sbi->total_valid_inode_count);
}
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, !sbi->total_valid_inode_count);
- sbi->total_valid_inode_count--;
- spin_unlock(&sbi->stat_lock);
+ percpu_counter_dec(&sbi->total_valid_inode_count);
}
-static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi)
+static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
{
- return sbi->total_valid_inode_count;
+ return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
}
static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
pgoff_t index, bool for_write)
{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ struct page *page = find_lock_page(mapping, index);
+ if (page)
+ return page;
+
+ if (time_to_inject(FAULT_PAGE_ALLOC))
+ return NULL;
+#endif
if (!for_write)
return grab_cache_page(mapping, index);
return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
@@ -1294,7 +1403,7 @@ static inline void f2fs_put_page(struct page *page, int unlock)
f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
unlock_page(page);
}
- page_cache_release(page);
+ put_page(page);
}
static inline void f2fs_put_dnode(struct dnode_of_data *dn)
@@ -1429,13 +1538,12 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
FI_DIRTY_INODE, /* indicate inode is dirty or not */
+ FI_AUTO_RECOVER, /* indicate inode is recoverable */
FI_DIRTY_DIR, /* indicate directory has dirty pages */
FI_INC_LINK, /* need to increment i_nlink */
FI_ACL_MODE, /* indicate acl mode */
FI_NO_ALLOC, /* should not allocate any blocks */
FI_FREE_NID, /* free allocated nide */
- FI_UPDATE_DIR, /* should update inode block for consistency */
- FI_DELAY_IPUT, /* used for the recovery */
FI_NO_EXTENT, /* not to use the extent cache */
FI_INLINE_XATTR, /* used for inline xattr */
FI_INLINE_DATA, /* used for inline data*/
@@ -1453,64 +1561,143 @@ enum {
FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
};
-static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
+static inline void __mark_inode_dirty_flag(struct inode *inode,
+ int flag, bool set)
+{
+ switch (flag) {
+ case FI_INLINE_XATTR:
+ case FI_INLINE_DATA:
+ case FI_INLINE_DENTRY:
+ if (set)
+ return;
+ case FI_DATA_EXIST:
+ case FI_INLINE_DOTS:
+ f2fs_mark_inode_dirty_sync(inode);
+ }
+}
+
+static inline void set_inode_flag(struct inode *inode, int flag)
+{
+ if (!test_bit(flag, &F2FS_I(inode)->flags))
+ set_bit(flag, &F2FS_I(inode)->flags);
+ __mark_inode_dirty_flag(inode, flag, true);
+}
+
+static inline int is_inode_flag_set(struct inode *inode, int flag)
+{
+ return test_bit(flag, &F2FS_I(inode)->flags);
+}
+
+static inline void clear_inode_flag(struct inode *inode, int flag)
+{
+ if (test_bit(flag, &F2FS_I(inode)->flags))
+ clear_bit(flag, &F2FS_I(inode)->flags);
+ __mark_inode_dirty_flag(inode, flag, false);
+}
+
+static inline void set_acl_inode(struct inode *inode, umode_t mode)
+{
+ F2FS_I(inode)->i_acl_mode = mode;
+ set_inode_flag(inode, FI_ACL_MODE);
+ f2fs_mark_inode_dirty_sync(inode);
+}
+
+static inline void f2fs_i_links_write(struct inode *inode, bool inc)
+{
+ if (inc)
+ inc_nlink(inode);
+ else
+ drop_nlink(inode);
+ f2fs_mark_inode_dirty_sync(inode);
+}
+
+static inline void f2fs_i_blocks_write(struct inode *inode,
+ blkcnt_t diff, bool add)
+{
+ bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
+ bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
+
+ inode->i_blocks = add ? inode->i_blocks + diff :
+ inode->i_blocks - diff;
+ f2fs_mark_inode_dirty_sync(inode);
+ if (clean || recover)
+ set_inode_flag(inode, FI_AUTO_RECOVER);
+}
+
+static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
{
- if (!test_bit(flag, &fi->flags))
- set_bit(flag, &fi->flags);
+ bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
+ bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
+
+ if (i_size_read(inode) == i_size)
+ return;
+
+ i_size_write(inode, i_size);
+ f2fs_mark_inode_dirty_sync(inode);
+ if (clean || recover)
+ set_inode_flag(inode, FI_AUTO_RECOVER);
+}
+
+static inline bool f2fs_skip_inode_update(struct inode *inode)
+{
+ if (!is_inode_flag_set(inode, FI_AUTO_RECOVER))
+ return false;
+ return F2FS_I(inode)->last_disk_size == i_size_read(inode);
}
-static inline int is_inode_flag_set(struct f2fs_inode_info *fi, int flag)
+static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
{
- return test_bit(flag, &fi->flags);
+ F2FS_I(inode)->i_current_depth = depth;
+ f2fs_mark_inode_dirty_sync(inode);
}
-static inline void clear_inode_flag(struct f2fs_inode_info *fi, int flag)
+static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
{
- if (test_bit(flag, &fi->flags))
- clear_bit(flag, &fi->flags);
+ F2FS_I(inode)->i_xattr_nid = xnid;
+ f2fs_mark_inode_dirty_sync(inode);
}
-static inline void set_acl_inode(struct f2fs_inode_info *fi, umode_t mode)
+static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
- fi->i_acl_mode = mode;
- set_inode_flag(fi, FI_ACL_MODE);
+ F2FS_I(inode)->i_pino = pino;
+ f2fs_mark_inode_dirty_sync(inode);
}
-static inline void get_inline_info(struct f2fs_inode_info *fi,
- struct f2fs_inode *ri)
+static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+
if (ri->i_inline & F2FS_INLINE_XATTR)
- set_inode_flag(fi, FI_INLINE_XATTR);
+ set_bit(FI_INLINE_XATTR, &fi->flags);
if (ri->i_inline & F2FS_INLINE_DATA)
- set_inode_flag(fi, FI_INLINE_DATA);
+ set_bit(FI_INLINE_DATA, &fi->flags);
if (ri->i_inline & F2FS_INLINE_DENTRY)
- set_inode_flag(fi, FI_INLINE_DENTRY);
+ set_bit(FI_INLINE_DENTRY, &fi->flags);
if (ri->i_inline & F2FS_DATA_EXIST)
- set_inode_flag(fi, FI_DATA_EXIST);
+ set_bit(FI_DATA_EXIST, &fi->flags);
if (ri->i_inline & F2FS_INLINE_DOTS)
- set_inode_flag(fi, FI_INLINE_DOTS);
+ set_bit(FI_INLINE_DOTS, &fi->flags);
}
-static inline void set_raw_inline(struct f2fs_inode_info *fi,
- struct f2fs_inode *ri)
+static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
{
ri->i_inline = 0;
- if (is_inode_flag_set(fi, FI_INLINE_XATTR))
+ if (is_inode_flag_set(inode, FI_INLINE_XATTR))
ri->i_inline |= F2FS_INLINE_XATTR;
- if (is_inode_flag_set(fi, FI_INLINE_DATA))
+ if (is_inode_flag_set(inode, FI_INLINE_DATA))
ri->i_inline |= F2FS_INLINE_DATA;
- if (is_inode_flag_set(fi, FI_INLINE_DENTRY))
+ if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
ri->i_inline |= F2FS_INLINE_DENTRY;
- if (is_inode_flag_set(fi, FI_DATA_EXIST))
+ if (is_inode_flag_set(inode, FI_DATA_EXIST))
ri->i_inline |= F2FS_DATA_EXIST;
- if (is_inode_flag_set(fi, FI_INLINE_DOTS))
+ if (is_inode_flag_set(inode, FI_INLINE_DOTS))
ri->i_inline |= F2FS_INLINE_DOTS;
}
static inline int f2fs_has_inline_xattr(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR);
+ return is_inode_flag_set(inode, FI_INLINE_XATTR);
}
static inline unsigned int addrs_per_inode(struct inode *inode)
@@ -1537,43 +1724,43 @@ static inline int inline_xattr_size(struct inode *inode)
static inline int f2fs_has_inline_data(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA);
+ return is_inode_flag_set(inode, FI_INLINE_DATA);
}
static inline void f2fs_clear_inline_inode(struct inode *inode)
{
- clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
- clear_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+ clear_inode_flag(inode, FI_INLINE_DATA);
+ clear_inode_flag(inode, FI_DATA_EXIST);
}
static inline int f2fs_exist_data(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_DATA_EXIST);
+ return is_inode_flag_set(inode, FI_DATA_EXIST);
}
static inline int f2fs_has_inline_dots(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DOTS);
+ return is_inode_flag_set(inode, FI_INLINE_DOTS);
}
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE);
+ return is_inode_flag_set(inode, FI_ATOMIC_FILE);
}
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
+ return is_inode_flag_set(inode, FI_VOLATILE_FILE);
}
static inline bool f2fs_is_first_block_written(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+ return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
}
static inline bool f2fs_is_drop_cache(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE);
+ return is_inode_flag_set(inode, FI_DROP_CACHE);
}
static inline void *inline_data_addr(struct page *page)
@@ -1584,7 +1771,7 @@ static inline void *inline_data_addr(struct page *page)
static inline int f2fs_has_inline_dentry(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DENTRY);
+ return is_inode_flag_set(inode, FI_INLINE_DENTRY);
}
static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page)
@@ -1601,11 +1788,13 @@ static inline int is_file(struct inode *inode, int type)
static inline void set_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise |= type;
+ f2fs_mark_inode_dirty_sync(inode);
}
static inline void clear_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise &= ~type;
+ f2fs_mark_inode_dirty_sync(inode);
}
static inline int f2fs_readonly(struct super_block *sb)
@@ -1618,12 +1807,6 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
return is_set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
}
-static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
-{
- set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
- sbi->sb->s_flags |= MS_RDONLY;
-}
-
static inline bool is_dot_dotdot(const struct qstr *str)
{
if (str->len == 1 && str->name[0] == '.')
@@ -1638,12 +1821,21 @@ static inline bool is_dot_dotdot(const struct qstr *str)
static inline bool f2fs_may_extent_tree(struct inode *inode)
{
if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
- is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+ is_inode_flag_set(inode, FI_NO_EXTENT))
return false;
return S_ISREG(inode->i_mode);
}
+static inline void *f2fs_kmalloc(size_t size, gfp_t flags)
+{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_KMALLOC))
+ return NULL;
+#endif
+ return kmalloc(size, flags);
+}
+
static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
{
void *ret;
@@ -1665,7 +1857,7 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
}
#define get_inode_mode(i) \
- ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
+ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
/* get offset of first page in next direct node */
@@ -1680,7 +1872,7 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
int f2fs_sync_file(struct file *, loff_t, loff_t, int);
void truncate_data_blocks(struct dnode_of_data *);
int truncate_blocks(struct inode *, u64, bool);
-int f2fs_truncate(struct inode *, bool);
+int f2fs_truncate(struct inode *);
int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
int f2fs_setattr(struct dentry *, struct iattr *);
int truncate_hole(struct inode *, pgoff_t, pgoff_t);
@@ -1710,7 +1902,7 @@ struct dentry *f2fs_get_parent(struct dentry *child);
*/
extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
void set_de_type(struct f2fs_dir_entry *, umode_t);
-
+unsigned char get_de_type(struct f2fs_dir_entry *);
struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
@@ -1721,16 +1913,18 @@ struct page *init_inode_metadata(struct inode *, struct inode *,
const struct qstr *, struct page *);
void update_parent_metadata(struct inode *, struct inode *, unsigned int);
int room_for_filename(const void *, int, int);
-void f2fs_drop_nlink(struct inode *, struct inode *, struct page *);
-struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *,
+void f2fs_drop_nlink(struct inode *, struct inode *);
+struct f2fs_dir_entry *f2fs_find_entry(struct inode *, const struct qstr *,
struct page **);
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
-ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
+ino_t f2fs_inode_by_name(struct inode *, const struct qstr *, struct page **);
void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
struct page *, struct inode *);
int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
const struct qstr *, f2fs_hash_t , unsigned int);
+int f2fs_add_regular_entry(struct inode *, const struct qstr *,
+ struct inode *, nid_t, umode_t);
int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
umode_t);
void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
@@ -1747,6 +1941,8 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
/*
* super.c
*/
+int f2fs_inode_dirtied(struct inode *);
+void f2fs_inode_synced(struct inode *);
int f2fs_commit_super(struct f2fs_sb_info *, bool);
int f2fs_sync_fs(struct super_block *, int);
extern __printf(3, 4)
@@ -1780,8 +1976,11 @@ struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
void ra_node_page(struct f2fs_sb_info *, nid_t);
struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_node_page_ra(struct page *, int);
-void sync_inode_page(struct dnode_of_data *);
-int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *);
+void move_node_page(struct page *, int);
+int fsync_node_pages(struct f2fs_sb_info *, struct inode *,
+ struct writeback_control *, bool);
+int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *);
+void build_free_nids(struct f2fs_sb_info *);
bool alloc_nid(struct f2fs_sb_info *, nid_t *);
void alloc_nid_done(struct f2fs_sb_info *, nid_t);
void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
@@ -1843,6 +2042,7 @@ void destroy_segment_manager_caches(void);
/*
* checkpoint.c
*/
+void f2fs_stop_checkpoint(struct f2fs_sb_info *, bool);
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
@@ -1852,16 +2052,16 @@ void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
void add_ino_entry(struct f2fs_sb_info *, nid_t, int type);
void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void release_ino_entry(struct f2fs_sb_info *);
+void release_ino_entry(struct f2fs_sb_info *, bool);
bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
+int f2fs_sync_inode_meta(struct f2fs_sb_info *);
int acquire_orphan_inode(struct f2fs_sb_info *);
void release_orphan_inode(struct f2fs_sb_info *);
-void add_orphan_inode(struct f2fs_sb_info *, nid_t);
+void add_orphan_inode(struct inode *);
void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
int recover_orphan_inodes(struct f2fs_sb_info *);
int get_valid_checkpoint(struct f2fs_sb_info *);
void update_dirty_page(struct inode *, struct page *);
-void add_dirty_dir_inode(struct inode *);
void remove_dirty_inode(struct inode *);
int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type);
int write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
@@ -1880,6 +2080,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *);
void f2fs_submit_page_mbio(struct f2fs_io_info *);
void set_data_blkaddr(struct dnode_of_data *);
void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
+int reserve_new_blocks(struct dnode_of_data *, blkcnt_t);
int reserve_new_block(struct dnode_of_data *);
int f2fs_get_block(struct dnode_of_data *, pgoff_t);
ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
@@ -1891,6 +2092,7 @@ struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
int do_write_data_page(struct f2fs_io_info *);
int f2fs_map_blocks(struct inode *, struct f2fs_map_blocks *, int, int);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void f2fs_set_page_dirty_nobuffers(struct page *);
void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
int f2fs_release_page(struct page *, gfp_t);
@@ -1906,7 +2108,7 @@ void build_gc_manager(struct f2fs_sb_info *);
/*
* recovery.c
*/
-int recover_fsync_data(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *, bool);
bool space_for_roll_forward(struct f2fs_sb_info *);
/*
@@ -1921,12 +2123,12 @@ struct f2fs_stat_info {
unsigned long long hit_largest, hit_cached, hit_rbtree;
unsigned long long hit_total, total_ext;
int ext_tree, zombie_tree, ext_node;
- int ndirty_node, ndirty_meta;
- int ndirty_dent, ndirty_dirs, ndirty_data, ndirty_files;
+ s64 ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, inmem_pages;
+ unsigned int ndirty_dirs, ndirty_files, ndirty_all;
int nats, dirty_nats, sits, dirty_sits, fnids;
int total_count, utilization;
- int bg_gc, inmem_pages, wb_pages;
- int inline_xattr, inline_inode, inline_dir;
+ int bg_gc, wb_bios;
+ int inline_xattr, inline_inode, inline_dir, orphans;
unsigned int valid_count, valid_node_count, valid_inode_count;
unsigned int bimodal, avg_vblocks;
int util_free, util_valid, util_invalid;
@@ -2091,7 +2293,6 @@ int f2fs_write_inline_data(struct inode *, struct page *);
bool recover_inline_data(struct inode *, struct page *);
struct f2fs_dir_entry *find_in_inline_dir(struct inode *,
struct fscrypt_name *, struct page **);
-struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **);
int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *,
nid_t, umode_t);
@@ -2116,6 +2317,7 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *);
*/
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
bool f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
+void f2fs_drop_extent_tree(struct inode *);
unsigned int f2fs_destroy_extent_node(struct inode *);
void f2fs_destroy_extent_tree(struct inode *);
bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *);
@@ -2151,6 +2353,26 @@ static inline int f2fs_sb_has_crypto(struct super_block *sb)
return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
}
+static inline int f2fs_sb_mounted_hmsmr(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_HMSMR);
+}
+
+static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)
+{
+ clear_opt(sbi, ADAPTIVE);
+ clear_opt(sbi, LFS);
+
+ switch (mt) {
+ case F2FS_MOUNT_ADAPTIVE:
+ set_opt(sbi, ADAPTIVE);
+ break;
+ case F2FS_MOUNT_LFS:
+ set_opt(sbi, LFS);
+ break;
+ }
+}
+
static inline bool f2fs_may_encrypt(struct inode *inode)
{
#ifdef CONFIG_F2FS_FS_ENCRYPTION
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index b41c3579ea9e..0e493f63ea41 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -20,7 +20,8 @@
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>
-#include <linux/random.h>
+#include <linux/uuid.h>
+#include <linux/file.h>
#include "f2fs.h"
#include "node.h"
@@ -74,14 +75,15 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
goto mapped;
/* page is wholly or partially inside EOF */
- if (((loff_t)(page->index + 1) << PAGE_CACHE_SHIFT) >
+ if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
i_size_read(inode)) {
unsigned offset;
- offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
- zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+ offset = i_size_read(inode) & ~PAGE_MASK;
+ zero_user_segment(page, offset, PAGE_SIZE);
}
set_page_dirty(page);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
@@ -171,21 +173,16 @@ static void try_to_fix_pino(struct inode *inode)
fi->xattr_ver = 0;
if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
get_parent_ino(inode, &pino)) {
- fi->i_pino = pino;
+ f2fs_i_pino_write(inode, pino);
file_got_pino(inode);
- up_write(&fi->i_sem);
-
- mark_inode_dirty_sync(inode);
- f2fs_write_inode(inode, NULL);
- } else {
- up_write(&fi->i_sem);
}
+ up_write(&fi->i_sem);
}
-int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
+ int datasync, bool atomic)
{
struct inode *inode = file->f_mapping->host;
- struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t ino = inode->i_ino;
int ret = 0;
@@ -203,9 +200,9 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
/* if fdatasync is triggered, let's do in-place-update */
if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
- set_inode_flag(fi, FI_NEED_IPU);
+ set_inode_flag(inode, FI_NEED_IPU);
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- clear_inode_flag(fi, FI_NEED_IPU);
+ clear_inode_flag(inode, FI_NEED_IPU);
if (ret) {
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
@@ -213,7 +210,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
}
/* if the inode is dirty, let's recover all the time */
- if (!datasync) {
+ if (!datasync && !f2fs_skip_inode_update(inode)) {
f2fs_write_inode(inode, NULL);
goto go_write;
}
@@ -221,14 +218,14 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
/*
* if there is no written data, don't waste time to write recovery info.
*/
- if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
+ if (!is_inode_flag_set(inode, FI_APPEND_WRITE) &&
!exist_written_data(sbi, ino, APPEND_INO)) {
/* it may call write_inode just prior to fsync */
if (need_inode_page_update(sbi, ino))
goto go_write;
- if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
+ if (is_inode_flag_set(inode, FI_UPDATE_WRITE) ||
exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
@@ -238,9 +235,9 @@ go_write:
* Both of fdatasync() and fsync() are able to be recovered from
* sudden-power-off.
*/
- down_read(&fi->i_sem);
+ down_read(&F2FS_I(inode)->i_sem);
need_cp = need_do_checkpoint(inode);
- up_read(&fi->i_sem);
+ up_read(&F2FS_I(inode)->i_sem);
if (need_cp) {
/* all the dirty node pages should be flushed for POR */
@@ -251,12 +248,14 @@ go_write:
* will be used only for fsynced inodes after checkpoint.
*/
try_to_fix_pino(inode);
- clear_inode_flag(fi, FI_APPEND_WRITE);
- clear_inode_flag(fi, FI_UPDATE_WRITE);
+ clear_inode_flag(inode, FI_APPEND_WRITE);
+ clear_inode_flag(inode, FI_UPDATE_WRITE);
goto out;
}
sync_nodes:
- sync_node_pages(sbi, ino, &wbc);
+ ret = fsync_node_pages(sbi, inode, &wbc, atomic);
+ if (ret)
+ goto out;
/* if cp_error was enabled, we should avoid infinite loop */
if (unlikely(f2fs_cp_error(sbi))) {
@@ -265,7 +264,7 @@ sync_nodes:
}
if (need_inode_block_update(sbi, ino)) {
- mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
}
@@ -276,10 +275,10 @@ sync_nodes:
/* once recovery info is written, don't need to tack this */
remove_ino_entry(sbi, ino, APPEND_INO);
- clear_inode_flag(fi, FI_APPEND_WRITE);
+ clear_inode_flag(inode, FI_APPEND_WRITE);
flush_out:
remove_ino_entry(sbi, ino, UPDATE_INO);
- clear_inode_flag(fi, FI_UPDATE_WRITE);
+ clear_inode_flag(inode, FI_UPDATE_WRITE);
ret = f2fs_issue_flush(sbi);
f2fs_update_time(sbi, REQ_TIME);
out:
@@ -288,6 +287,11 @@ out:
return ret;
}
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+{
+ return f2fs_do_sync_file(file, start, end, datasync, false);
+}
+
static pgoff_t __get_first_dirty_index(struct address_space *mapping,
pgoff_t pgofs, int whence)
{
@@ -346,13 +350,13 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
goto found;
}
- pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
+ pgofs = (pgoff_t)(offset >> PAGE_SHIFT);
dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
- for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
+ for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+ err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
@@ -370,7 +374,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
/* find data/hole in dnode block */
for (; dn.ofs_in_node < end_offset;
dn.ofs_in_node++, pgofs++,
- data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
+ data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
block_t blkaddr;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
@@ -441,7 +445,7 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
int ret = generic_file_open(inode, filp);
- struct inode *dir = filp->f_path.dentry->d_parent->d_inode;
+ struct dentry *dir;
if (!ret && f2fs_encrypted_inode(inode)) {
ret = fscrypt_get_encryption_info(inode);
@@ -450,9 +454,13 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
if (!fscrypt_has_encryption_key(inode))
return -ENOKEY;
}
- if (f2fs_encrypted_inode(dir) &&
- !fscrypt_has_permitted_context(dir, inode))
+ dir = dget_parent(file_dentry(filp));
+ if (f2fs_encrypted_inode(d_inode(dir)) &&
+ !fscrypt_has_permitted_context(d_inode(dir), inode)) {
+ dput(dir);
return -EPERM;
+ }
+ dput(dir);
return ret;
}
@@ -475,8 +483,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
set_data_blkaddr(dn);
invalidate_blocks(sbi, blkaddr);
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
- clear_inode_flag(F2FS_I(dn->inode),
- FI_FIRST_BLOCK_WRITTEN);
+ clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
nr_free++;
}
@@ -490,7 +497,6 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
dn->inode) + ofs;
f2fs_update_extent_cache_range(dn, fofs, 0, len);
dec_valid_block_count(sbi, dn->inode, nr_free);
- sync_inode_page(dn);
}
dn->ofs_in_node = ofs;
@@ -508,8 +514,8 @@ void truncate_data_blocks(struct dnode_of_data *dn)
static int truncate_partial_data_page(struct inode *inode, u64 from,
bool cache_only)
{
- unsigned offset = from & (PAGE_CACHE_SIZE - 1);
- pgoff_t index = from >> PAGE_CACHE_SHIFT;
+ unsigned offset = from & (PAGE_SIZE - 1);
+ pgoff_t index = from >> PAGE_SHIFT;
struct address_space *mapping = inode->i_mapping;
struct page *page;
@@ -529,7 +535,7 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
return 0;
truncate_out:
f2fs_wait_on_page_writeback(page, DATA, true);
- zero_user(page, offset, PAGE_CACHE_SIZE - offset);
+ zero_user(page, offset, PAGE_SIZE - offset);
if (!cache_only || !f2fs_encrypted_inode(inode) ||
!S_ISREG(inode->i_mode))
set_page_dirty(page);
@@ -551,6 +557,9 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
+ if (free_from >= sbi->max_file_blocks)
+ goto free_partial;
+
if (lock)
f2fs_lock_op(sbi);
@@ -569,7 +578,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
- err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
+ err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
if (err) {
if (err == -ENOENT)
goto free_next;
@@ -592,7 +601,7 @@ free_next:
out:
if (lock)
f2fs_unlock_op(sbi);
-
+free_partial:
/* lastly zero out the first data page */
if (!err)
err = truncate_partial_data_page(inode, from, truncate_page);
@@ -601,7 +610,7 @@ out:
return err;
}
-int f2fs_truncate(struct inode *inode, bool lock)
+int f2fs_truncate(struct inode *inode)
{
int err;
@@ -618,12 +627,12 @@ int f2fs_truncate(struct inode *inode, bool lock)
return err;
}
- err = truncate_blocks(inode, i_size_read(inode), lock);
+ err = truncate_blocks(inode, i_size_read(inode), true);
if (err)
return err;
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
+ f2fs_mark_inode_dirty_sync(inode);
return 0;
}
@@ -639,7 +648,6 @@ int f2fs_getattr(struct vfsmount *mnt,
#ifdef CONFIG_F2FS_FS_POSIX_ACL
static void __setattr_copy(struct inode *inode, const struct iattr *attr)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & ATTR_UID)
@@ -660,7 +668,7 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr)
if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
mode &= ~S_ISGID;
- set_acl_inode(fi, mode);
+ set_acl_inode(inode, mode);
}
}
#else
@@ -670,7 +678,6 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr)
int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
- struct f2fs_inode_info *fi = F2FS_I(inode);
int err;
err = inode_change_ok(inode, attr);
@@ -684,7 +691,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
if (attr->ia_size <= i_size_read(inode)) {
truncate_setsize(inode, attr->ia_size);
- err = f2fs_truncate(inode, true);
+ err = f2fs_truncate(inode);
if (err)
return err;
f2fs_balance_fs(F2FS_I_SB(inode), true);
@@ -709,13 +716,13 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
if (attr->ia_valid & ATTR_MODE) {
err = posix_acl_chmod(inode, get_inode_mode(inode));
- if (err || is_inode_flag_set(fi, FI_ACL_MODE)) {
- inode->i_mode = fi->i_acl_mode;
- clear_inode_flag(fi, FI_ACL_MODE);
+ if (err || is_inode_flag_set(inode, FI_ACL_MODE)) {
+ inode->i_mode = F2FS_I(inode)->i_acl_mode;
+ clear_inode_flag(inode, FI_ACL_MODE);
}
}
- mark_inode_dirty(inode);
+ f2fs_mark_inode_dirty_sync(inode);
return err;
}
@@ -799,11 +806,11 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
- pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
- pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+ pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
+ pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
- off_start = offset & (PAGE_CACHE_SIZE - 1);
- off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+ off_start = offset & (PAGE_SIZE - 1);
+ off_end = (offset + len) & (PAGE_SIZE - 1);
if (pg_start == pg_end) {
ret = fill_zero(inode, pg_start, off_start,
@@ -813,7 +820,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
- PAGE_CACHE_SIZE - off_start);
+ PAGE_SIZE - off_start);
if (ret)
return ret;
}
@@ -830,8 +837,8 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
f2fs_balance_fs(sbi, true);
- blk_start = (loff_t)pg_start << PAGE_CACHE_SHIFT;
- blk_end = (loff_t)pg_end << PAGE_CACHE_SHIFT;
+ blk_start = (loff_t)pg_start << PAGE_SHIFT;
+ blk_end = (loff_t)pg_end << PAGE_SHIFT;
truncate_inode_pages_range(mapping, blk_start,
blk_end - 1);
@@ -844,79 +851,199 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
return ret;
}
-static int __exchange_data_block(struct inode *inode, pgoff_t src,
- pgoff_t dst, bool full)
+static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
+ int *do_replace, pgoff_t off, pgoff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
- block_t new_addr;
- bool do_replace = false;
- int ret;
+ int ret, done, i;
+next_dnode:
set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = get_dnode_of_data(&dn, src, LOOKUP_NODE_RA);
+ ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
return ret;
} else if (ret == -ENOENT) {
- new_addr = NULL_ADDR;
- } else {
- new_addr = dn.data_blkaddr;
- if (!is_checkpointed_data(sbi, new_addr)) {
+ if (dn.max_level == 0)
+ return -ENOENT;
+ done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len);
+ blkaddr += done;
+ do_replace += done;
+ goto next;
+ }
+
+ done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
+ dn.ofs_in_node, len);
+ for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
+ *blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+ if (!is_checkpointed_data(sbi, *blkaddr)) {
+
+ if (test_opt(sbi, LFS)) {
+ f2fs_put_dnode(&dn);
+ return -ENOTSUPP;
+ }
+
/* do not invalidate this block address */
f2fs_update_data_blkaddr(&dn, NULL_ADDR);
- do_replace = true;
+ *do_replace = 1;
}
- f2fs_put_dnode(&dn);
}
+ f2fs_put_dnode(&dn);
+next:
+ len -= done;
+ off += done;
+ if (len)
+ goto next_dnode;
+ return 0;
+}
- if (new_addr == NULL_ADDR)
- return full ? truncate_hole(inode, dst, dst + 1) : 0;
+static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
+ int *do_replace, pgoff_t off, int len)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct dnode_of_data dn;
+ int ret, i;
- if (do_replace) {
- struct page *ipage = get_node_page(sbi, inode->i_ino);
- struct node_info ni;
+ for (i = 0; i < len; i++, do_replace++, blkaddr++) {
+ if (*do_replace == 0)
+ continue;
- if (IS_ERR(ipage)) {
- ret = PTR_ERR(ipage);
- goto err_out;
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
+ if (ret) {
+ dec_valid_block_count(sbi, inode, 1);
+ invalidate_blocks(sbi, *blkaddr);
+ } else {
+ f2fs_update_data_blkaddr(&dn, *blkaddr);
+ }
+ f2fs_put_dnode(&dn);
+ }
+ return 0;
+}
+
+static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
+ block_t *blkaddr, int *do_replace,
+ pgoff_t src, pgoff_t dst, pgoff_t len, bool full)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(src_inode);
+ pgoff_t i = 0;
+ int ret;
+
+ while (i < len) {
+ if (blkaddr[i] == NULL_ADDR && !full) {
+ i++;
+ continue;
}
- set_new_dnode(&dn, inode, ipage, NULL, 0);
- ret = f2fs_reserve_block(&dn, dst);
- if (ret)
- goto err_out;
+ if (do_replace[i] || blkaddr[i] == NULL_ADDR) {
+ struct dnode_of_data dn;
+ struct node_info ni;
+ size_t new_size;
+ pgoff_t ilen;
- truncate_data_blocks_range(&dn, 1);
+ set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
+ if (ret)
+ return ret;
- get_node_info(sbi, dn.nid, &ni);
- f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
- ni.version, true, false);
- f2fs_put_dnode(&dn);
- } else {
- struct page *psrc, *pdst;
+ get_node_info(sbi, dn.nid, &ni);
+ ilen = min((pgoff_t)
+ ADDRS_PER_PAGE(dn.node_page, dst_inode) -
+ dn.ofs_in_node, len - i);
+ do {
+ dn.data_blkaddr = datablock_addr(dn.node_page,
+ dn.ofs_in_node);
+ truncate_data_blocks_range(&dn, 1);
+
+ if (do_replace[i]) {
+ f2fs_i_blocks_write(src_inode,
+ 1, false);
+ f2fs_i_blocks_write(dst_inode,
+ 1, true);
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+ blkaddr[i], ni.version, true, false);
+
+ do_replace[i] = 0;
+ }
+ dn.ofs_in_node++;
+ i++;
+ new_size = (dst + i) << PAGE_SHIFT;
+ if (dst_inode->i_size < new_size)
+ f2fs_i_size_write(dst_inode, new_size);
+ } while ((do_replace[i] || blkaddr[i] == NULL_ADDR) && --ilen);
- psrc = get_lock_data_page(inode, src, true);
- if (IS_ERR(psrc))
- return PTR_ERR(psrc);
- pdst = get_new_data_page(inode, NULL, dst, true);
- if (IS_ERR(pdst)) {
+ f2fs_put_dnode(&dn);
+ } else {
+ struct page *psrc, *pdst;
+
+ psrc = get_lock_data_page(src_inode, src + i, true);
+ if (IS_ERR(psrc))
+ return PTR_ERR(psrc);
+ pdst = get_new_data_page(dst_inode, NULL, dst + i,
+ true);
+ if (IS_ERR(pdst)) {
+ f2fs_put_page(psrc, 1);
+ return PTR_ERR(pdst);
+ }
+ f2fs_copy_page(psrc, pdst);
+ set_page_dirty(pdst);
+ f2fs_put_page(pdst, 1);
f2fs_put_page(psrc, 1);
- return PTR_ERR(pdst);
- }
- f2fs_copy_page(psrc, pdst);
- set_page_dirty(pdst);
- f2fs_put_page(pdst, 1);
- f2fs_put_page(psrc, 1);
- return truncate_hole(inode, src, src + 1);
+ ret = truncate_hole(src_inode, src + i, src + i + 1);
+ if (ret)
+ return ret;
+ i++;
+ }
}
return 0;
+}
-err_out:
- if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) {
- f2fs_update_data_blkaddr(&dn, new_addr);
- f2fs_put_dnode(&dn);
+static int __exchange_data_block(struct inode *src_inode,
+ struct inode *dst_inode, pgoff_t src, pgoff_t dst,
+ pgoff_t len, bool full)
+{
+ block_t *src_blkaddr;
+ int *do_replace;
+ pgoff_t olen;
+ int ret;
+
+ while (len) {
+ olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);
+
+ src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
+ if (!src_blkaddr)
+ return -ENOMEM;
+
+ do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
+ if (!do_replace) {
+ kvfree(src_blkaddr);
+ return -ENOMEM;
+ }
+
+ ret = __read_out_blkaddrs(src_inode, src_blkaddr,
+ do_replace, src, olen);
+ if (ret)
+ goto roll_back;
+
+ ret = __clone_blkaddrs(src_inode, dst_inode, src_blkaddr,
+ do_replace, src, dst, olen, full);
+ if (ret)
+ goto roll_back;
+
+ src += olen;
+ dst += olen;
+ len -= olen;
+
+ kvfree(src_blkaddr);
+ kvfree(do_replace);
}
+ return 0;
+
+roll_back:
+ __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len);
+ kvfree(src_blkaddr);
+ kvfree(do_replace);
return ret;
}
@@ -924,16 +1051,15 @@ static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
- int ret = 0;
+ int ret;
- for (; end < nrpages; start++, end++) {
- f2fs_balance_fs(sbi, true);
- f2fs_lock_op(sbi);
- ret = __exchange_data_block(inode, end, start, true);
- f2fs_unlock_op(sbi);
- if (ret)
- break;
- }
+ f2fs_balance_fs(sbi, true);
+ f2fs_lock_op(sbi);
+
+ f2fs_drop_extent_tree(inode);
+
+ ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
+ f2fs_unlock_op(sbi);
return ret;
}
@@ -954,8 +1080,8 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
- pg_start = offset >> PAGE_CACHE_SHIFT;
- pg_end = (offset + len) >> PAGE_CACHE_SHIFT;
+ pg_start = offset >> PAGE_SHIFT;
+ pg_end = (offset + len) >> PAGE_SHIFT;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
@@ -977,7 +1103,50 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
ret = truncate_blocks(inode, new_size, true);
if (!ret)
- i_size_write(inode, new_size);
+ f2fs_i_size_write(inode, new_size);
+
+ return ret;
+}
+
+static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
+ pgoff_t end)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ pgoff_t index = start;
+ unsigned int ofs_in_node = dn->ofs_in_node;
+ blkcnt_t count = 0;
+ int ret;
+
+ for (; index < end; index++, dn->ofs_in_node++) {
+ if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR)
+ count++;
+ }
+
+ dn->ofs_in_node = ofs_in_node;
+ ret = reserve_new_blocks(dn, count);
+ if (ret)
+ return ret;
+
+ dn->ofs_in_node = ofs_in_node;
+ for (index = start; index < end; index++, dn->ofs_in_node++) {
+ dn->data_blkaddr =
+ datablock_addr(dn->node_page, dn->ofs_in_node);
+ /*
+ * reserve_new_blocks will not guarantee entire block
+ * allocation.
+ */
+ if (dn->data_blkaddr == NULL_ADDR) {
+ ret = -ENOSPC;
+ break;
+ }
+ if (dn->data_blkaddr != NEW_ADDR) {
+ invalidate_blocks(sbi, dn->data_blkaddr);
+ dn->data_blkaddr = NEW_ADDR;
+ set_data_blkaddr(dn);
+ }
+ }
+
+ f2fs_update_extent_cache_range(dn, start, 0, index - start);
return ret;
}
@@ -1006,11 +1175,11 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
truncate_pagecache_range(inode, offset, offset + len - 1);
- pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
- pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+ pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
+ pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
- off_start = offset & (PAGE_CACHE_SIZE - 1);
- off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+ off_start = offset & (PAGE_SIZE - 1);
+ off_end = (offset + len) & (PAGE_SIZE - 1);
if (pg_start == pg_end) {
ret = fill_zero(inode, pg_start, off_start,
@@ -1024,43 +1193,40 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
- PAGE_CACHE_SIZE - off_start);
+ PAGE_SIZE - off_start);
if (ret)
return ret;
new_size = max_t(loff_t, new_size,
- (loff_t)pg_start << PAGE_CACHE_SHIFT);
+ (loff_t)pg_start << PAGE_SHIFT);
}
- for (index = pg_start; index < pg_end; index++) {
+ for (index = pg_start; index < pg_end;) {
struct dnode_of_data dn;
- struct page *ipage;
+ unsigned int end_offset;
+ pgoff_t end;
f2fs_lock_op(sbi);
- ipage = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(ipage)) {
- ret = PTR_ERR(ipage);
- f2fs_unlock_op(sbi);
- goto out;
- }
-
- set_new_dnode(&dn, inode, ipage, NULL, 0);
- ret = f2fs_reserve_block(&dn, index);
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
if (ret) {
f2fs_unlock_op(sbi);
goto out;
}
- if (dn.data_blkaddr != NEW_ADDR) {
- invalidate_blocks(sbi, dn.data_blkaddr);
- f2fs_update_data_blkaddr(&dn, NEW_ADDR);
- }
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+ end = min(pg_end, end_offset - dn.ofs_in_node + index);
+
+ ret = f2fs_do_zero_range(&dn, index, end);
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
+ if (ret)
+ goto out;
+ index = end;
new_size = max_t(loff_t, new_size,
- (loff_t)(index + 1) << PAGE_CACHE_SHIFT);
+ (loff_t)index << PAGE_SHIFT);
}
if (off_end) {
@@ -1073,11 +1239,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
}
out:
- if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) {
- i_size_write(inode, new_size);
- mark_inode_dirty(inode);
- update_inode_page(inode);
- }
+ if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
+ f2fs_i_size_write(inode, new_size);
return ret;
}
@@ -1085,7 +1248,7 @@ out:
static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- pgoff_t pg_start, pg_end, delta, nrpages, idx;
+ pgoff_t nr, pg_start, pg_end, delta, idx;
loff_t new_size;
int ret = 0;
@@ -1117,17 +1280,23 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
truncate_pagecache(inode, offset);
- pg_start = offset >> PAGE_CACHE_SHIFT;
- pg_end = (offset + len) >> PAGE_CACHE_SHIFT;
+ pg_start = offset >> PAGE_SHIFT;
+ pg_end = (offset + len) >> PAGE_SHIFT;
delta = pg_end - pg_start;
- nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+ idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+
+ while (!ret && idx > pg_start) {
+ nr = idx - pg_start;
+ if (nr > delta)
+ nr = delta;
+ idx -= nr;
- for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) {
f2fs_lock_op(sbi);
- ret = __exchange_data_block(inode, idx, idx + delta, false);
+ f2fs_drop_extent_tree(inode);
+
+ ret = __exchange_data_block(inode, inode, idx,
+ idx + delta, nr, false);
f2fs_unlock_op(sbi);
- if (ret)
- break;
}
/* write out all moved pages, if possible */
@@ -1135,7 +1304,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
truncate_pagecache(inode, offset);
if (!ret)
- i_size_write(inode, new_size);
+ f2fs_i_size_write(inode, new_size);
return ret;
}
@@ -1143,10 +1312,11 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
loff_t len, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- pgoff_t index, pg_start, pg_end;
+ struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
+ pgoff_t pg_end;
loff_t new_size = i_size_read(inode);
- loff_t off_start, off_end;
- int ret = 0;
+ loff_t off_end;
+ int ret;
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
@@ -1158,43 +1328,32 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
f2fs_balance_fs(sbi, true);
- pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
- pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+ pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT;
+ off_end = (offset + len) & (PAGE_SIZE - 1);
- off_start = offset & (PAGE_CACHE_SIZE - 1);
- off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+ map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT;
+ map.m_len = pg_end - map.m_lblk;
+ if (off_end)
+ map.m_len++;
- f2fs_lock_op(sbi);
+ ret = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+ if (ret) {
+ pgoff_t last_off;
- for (index = pg_start; index <= pg_end; index++) {
- struct dnode_of_data dn;
+ if (!map.m_len)
+ return ret;
- if (index == pg_end && !off_end)
- goto noalloc;
+ last_off = map.m_lblk + map.m_len - 1;
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = f2fs_reserve_block(&dn, index);
- if (ret)
- break;
-noalloc:
- if (pg_start == pg_end)
- new_size = offset + len;
- else if (index == pg_start && off_start)
- new_size = (loff_t)(index + 1) << PAGE_CACHE_SHIFT;
- else if (index == pg_end)
- new_size = ((loff_t)index << PAGE_CACHE_SHIFT) +
- off_end;
- else
- new_size += PAGE_CACHE_SIZE;
+ /* update new size to the failed position */
+ new_size = (last_off == pg_end) ? offset + len:
+ (loff_t)(last_off + 1) << PAGE_SHIFT;
+ } else {
+ new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
}
- if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- i_size_read(inode) < new_size) {
- i_size_write(inode, new_size);
- mark_inode_dirty(inode);
- update_inode_page(inode);
- }
- f2fs_unlock_op(sbi);
+ if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
+ f2fs_i_size_write(inode, new_size);
return ret;
}
@@ -1237,7 +1396,7 @@ static long f2fs_fallocate(struct file *file, int mode,
if (!ret) {
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
+ f2fs_mark_inode_dirty_sync(inode);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
}
@@ -1250,13 +1409,22 @@ out:
static int f2fs_release_file(struct inode *inode, struct file *filp)
{
+ /*
+ * f2fs_relase_file is called at every close calls. So we should
+ * not drop any inmemory pages by close called by other process.
+ */
+ if (!(filp->f_mode & FMODE_WRITE) ||
+ atomic_read(&inode->i_writecount) != 1)
+ return 0;
+
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
- set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+ clear_inode_flag(inode, FI_VOLATILE_FILE);
+ set_inode_flag(inode, FI_DROP_CACHE);
filemap_fdatawrite(inode->i_mapping);
- clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+ clear_inode_flag(inode, FI_DROP_CACHE);
}
return 0;
}
@@ -1290,20 +1458,16 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
unsigned int oldflags;
int ret;
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (get_user(flags, (int __user *)arg))
+ return -EFAULT;
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out;
- }
-
- if (get_user(flags, (int __user *)arg)) {
- ret = -EFAULT;
- goto out;
- }
-
flags = f2fs_mask_flags(inode->i_mode, flags);
inode_lock(inode);
@@ -1323,9 +1487,8 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
fi->i_flags = flags;
inode_unlock(inode);
- f2fs_set_inode_flags(inode);
inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
+ f2fs_set_inode_flags(inode);
out:
mnt_drop_write_file(filp);
return ret;
@@ -1346,17 +1509,35 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
if (f2fs_is_atomic_file(inode))
- return 0;
+ goto out;
ret = f2fs_convert_inline_inode(inode);
if (ret)
- return ret;
+ goto out;
- set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ set_inode_flag(inode, FI_ATOMIC_FILE);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return 0;
+ if (!get_dirty_pages(inode))
+ goto out;
+
+ f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
+ "Unexpected flush for atomic writes: ino=%lu, npages=%lld",
+ inode->i_ino, get_dirty_pages(inode));
+ ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
+ if (ret)
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_commit_atomic_write(struct file *filp)
@@ -1367,24 +1548,27 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
- if (f2fs_is_volatile_file(inode))
- return 0;
-
ret = mnt_want_write_file(filp);
if (ret)
return ret;
+ inode_lock(inode);
+
+ if (f2fs_is_volatile_file(inode))
+ goto err_out;
+
if (f2fs_is_atomic_file(inode)) {
- clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
ret = commit_inmem_pages(inode);
if (ret) {
- set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ set_inode_flag(inode, FI_ATOMIC_FILE);
goto err_out;
}
}
- ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
err_out:
+ inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
@@ -1397,32 +1581,54 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
if (!inode_owner_or_capable(inode))
return -EACCES;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
if (f2fs_is_volatile_file(inode))
- return 0;
+ goto out;
ret = f2fs_convert_inline_inode(inode);
if (ret)
- return ret;
+ goto out;
- set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+ set_inode_flag(inode, FI_VOLATILE_FILE);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return 0;
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_release_volatile_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
+ int ret;
if (!inode_owner_or_capable(inode))
return -EACCES;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
if (!f2fs_is_volatile_file(inode))
- return 0;
+ goto out;
- if (!f2fs_is_first_block_written(inode))
- return truncate_partial_data_page(inode, 0, true);
+ if (!f2fs_is_first_block_written(inode)) {
+ ret = truncate_partial_data_page(inode, 0, true);
+ goto out;
+ }
- return punch_hole(inode, 0, F2FS_BLKSIZE);
+ ret = punch_hole(inode, 0, F2FS_BLKSIZE);
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_abort_volatile_write(struct file *filp)
@@ -1437,15 +1643,17 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
if (ret)
return ret;
- if (f2fs_is_atomic_file(inode)) {
- clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ inode_lock(inode);
+
+ if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
- }
if (f2fs_is_volatile_file(inode)) {
- clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
- ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
+ clear_inode_flag(inode, FI_VOLATILE_FILE);
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
}
+ inode_unlock(inode);
+
mnt_drop_write_file(filp);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return ret;
@@ -1457,6 +1665,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct super_block *sb = sbi->sb;
__u32 in;
+ int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1464,31 +1673,38 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
if (get_user(in, (__u32 __user *)arg))
return -EFAULT;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
switch (in) {
case F2FS_GOING_DOWN_FULLSYNC:
sb = freeze_bdev(sb->s_bdev);
if (sb && !IS_ERR(sb)) {
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
thaw_bdev(sb->s_bdev, sb);
}
break;
case F2FS_GOING_DOWN_METASYNC:
/* do checkpoint only */
f2fs_sync_fs(sb, 1);
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
break;
case F2FS_GOING_DOWN_NOSYNC:
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
break;
case F2FS_GOING_DOWN_METAFLUSH:
sync_meta_pages(sbi, META, LONG_MAX);
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
f2fs_update_time(sbi, REQ_TIME);
- return 0;
+out:
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
@@ -1509,9 +1725,14 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
sizeof(range)))
return -EFAULT;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = f2fs_trim_fs(F2FS_SB(sb), &range);
+ mnt_drop_write_file(filp);
if (ret < 0)
return ret;
@@ -1536,13 +1757,21 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
struct fscrypt_policy policy;
struct inode *inode = file_inode(filp);
+ int ret;
if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
sizeof(policy)))
return -EFAULT;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return fscrypt_process_policy(inode, &policy);
+ ret = fscrypt_process_policy(inode, &policy);
+
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
@@ -1599,6 +1828,7 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
__u32 sync;
+ int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1609,20 +1839,30 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
if (f2fs_readonly(sbi->sb))
return -EROFS;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
if (!sync) {
- if (!mutex_trylock(&sbi->gc_mutex))
- return -EBUSY;
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ ret = -EBUSY;
+ goto out;
+ }
} else {
mutex_lock(&sbi->gc_mutex);
}
- return f2fs_gc(sbi, sync);
+ ret = f2fs_gc(sbi, sync);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1630,7 +1870,14 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
if (f2fs_readonly(sbi->sb))
return -EROFS;
- return f2fs_sync_fs(sbi->sb, 1);
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ ret = f2fs_sync_fs(sbi->sb, 1);
+
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
@@ -1652,8 +1899,8 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
if (need_inplace_update(inode))
return -EINVAL;
- pg_start = range->start >> PAGE_CACHE_SHIFT;
- pg_end = (range->start + range->len) >> PAGE_CACHE_SHIFT;
+ pg_start = range->start >> PAGE_SHIFT;
+ pg_end = (range->start + range->len) >> PAGE_SHIFT;
f2fs_balance_fs(sbi, true);
@@ -1734,7 +1981,7 @@ do_map:
continue;
}
- set_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+ set_inode_flag(inode, FI_DO_DEFRAG);
idx = map.m_lblk;
while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
@@ -1759,18 +2006,18 @@ do_map:
if (idx < pg_end && cnt < blk_per_seg)
goto do_map;
- clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+ clear_inode_flag(inode, FI_DO_DEFRAG);
err = filemap_fdatawrite(inode->i_mapping);
if (err)
goto out;
}
clear_out:
- clear_inode_flag(F2FS_I(inode), FI_DO_DEFRAG);
+ clear_inode_flag(inode, FI_DO_DEFRAG);
out:
inode_unlock(inode);
if (!err)
- range->len = (u64)total << PAGE_CACHE_SHIFT;
+ range->len = (u64)total << PAGE_SHIFT;
return err;
}
@@ -1822,6 +2069,133 @@ out:
return err;
}
+static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, size_t len)
+{
+ struct inode *src = file_inode(file_in);
+ struct inode *dst = file_inode(file_out);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(src);
+ size_t olen = len, dst_max_i_size = 0;
+ size_t dst_osize;
+ int ret;
+
+ if (file_in->f_path.mnt != file_out->f_path.mnt ||
+ src->i_sb != dst->i_sb)
+ return -EXDEV;
+
+ if (unlikely(f2fs_readonly(src->i_sb)))
+ return -EROFS;
+
+ if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode))
+ return -EISDIR;
+
+ if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
+ return -EOPNOTSUPP;
+
+ inode_lock(src);
+ if (src != dst)
+ inode_lock(dst);
+
+ ret = -EINVAL;
+ if (pos_in + len > src->i_size || pos_in + len < pos_in)
+ goto out_unlock;
+ if (len == 0)
+ olen = len = src->i_size - pos_in;
+ if (pos_in + len == src->i_size)
+ len = ALIGN(src->i_size, F2FS_BLKSIZE) - pos_in;
+ if (len == 0) {
+ ret = 0;
+ goto out_unlock;
+ }
+
+ dst_osize = dst->i_size;
+ if (pos_out + olen > dst->i_size)
+ dst_max_i_size = pos_out + olen;
+
+ /* verify the end result is block aligned */
+ if (!IS_ALIGNED(pos_in, F2FS_BLKSIZE) ||
+ !IS_ALIGNED(pos_in + len, F2FS_BLKSIZE) ||
+ !IS_ALIGNED(pos_out, F2FS_BLKSIZE))
+ goto out_unlock;
+
+ ret = f2fs_convert_inline_inode(src);
+ if (ret)
+ goto out_unlock;
+
+ ret = f2fs_convert_inline_inode(dst);
+ if (ret)
+ goto out_unlock;
+
+ /* write out all dirty pages from offset */
+ ret = filemap_write_and_wait_range(src->i_mapping,
+ pos_in, pos_in + len);
+ if (ret)
+ goto out_unlock;
+
+ ret = filemap_write_and_wait_range(dst->i_mapping,
+ pos_out, pos_out + len);
+ if (ret)
+ goto out_unlock;
+
+ f2fs_balance_fs(sbi, true);
+ f2fs_lock_op(sbi);
+ ret = __exchange_data_block(src, dst, pos_in,
+ pos_out, len >> F2FS_BLKSIZE_BITS, false);
+
+ if (!ret) {
+ if (dst_max_i_size)
+ f2fs_i_size_write(dst, dst_max_i_size);
+ else if (dst_osize != dst->i_size)
+ f2fs_i_size_write(dst, dst_osize);
+ }
+ f2fs_unlock_op(sbi);
+out_unlock:
+ if (src != dst)
+ inode_unlock(dst);
+ inode_unlock(src);
+ return ret;
+}
+
+static int f2fs_ioc_move_range(struct file *filp, unsigned long arg)
+{
+ struct f2fs_move_range range;
+ struct fd dst;
+ int err;
+
+ if (!(filp->f_mode & FMODE_READ) ||
+ !(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(&range, (struct f2fs_move_range __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ dst = fdget(range.dst_fd);
+ if (!dst.file)
+ return -EBADF;
+
+ if (!(dst.file->f_mode & FMODE_WRITE)) {
+ err = -EBADF;
+ goto err_out;
+ }
+
+ err = mnt_want_write_file(filp);
+ if (err)
+ goto err_out;
+
+ err = f2fs_move_file_range(filp, range.pos_in, dst.file,
+ range.pos_out, range.len);
+
+ mnt_drop_write_file(filp);
+
+ if (copy_to_user((struct f2fs_move_range __user *)arg,
+ &range, sizeof(range)))
+ err = -EFAULT;
+err_out:
+ fdput(dst);
+ return err;
+}
+
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
@@ -1857,6 +2231,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_write_checkpoint(filp, arg);
case F2FS_IOC_DEFRAGMENT:
return f2fs_ioc_defragment(filp, arg);
+ case F2FS_IOC_MOVE_RANGE:
+ return f2fs_ioc_move_range(filp, arg);
default:
return -ENOTTY;
}
@@ -1866,6 +2242,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
+ struct blk_plug plug;
ssize_t ret;
if (f2fs_encrypted_inode(inode) &&
@@ -1877,18 +2254,16 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
ret = generic_write_checks(iocb, from);
if (ret > 0) {
ret = f2fs_preallocate_blocks(iocb, from);
- if (!ret)
+ if (!ret) {
+ blk_start_plug(&plug);
ret = __generic_file_write_iter(iocb, from);
+ blk_finish_plug(&plug);
+ }
}
inode_unlock(inode);
- if (ret > 0) {
- ssize_t err;
-
- err = generic_write_sync(file, iocb->ki_pos - ret, ret);
- if (err < 0)
- ret = err;
- }
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
return ret;
}
@@ -1918,6 +2293,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_WRITE_CHECKPOINT:
case F2FS_IOC_DEFRAGMENT:
break;
+ case F2FS_IOC_MOVE_RANGE:
+ break;
default:
return -ENOIOCTLCMD;
}
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index b0051a97824c..8f7fa326ce95 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -96,7 +96,7 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
dev_t dev = sbi->sb->s_bdev->bd_dev;
int err = 0;
- gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
+ gc_th = f2fs_kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
if (!gc_th) {
err = -ENOMEM;
goto out;
@@ -465,15 +465,7 @@ next_step:
continue;
}
- /* set page dirty and write it */
- if (gc_type == FG_GC) {
- f2fs_wait_on_page_writeback(node_page, NODE, true);
- set_page_dirty(node_page);
- } else {
- if (!PageWriteback(node_page))
- set_page_dirty(node_page);
- }
- f2fs_put_page(node_page, 1);
+ move_node_page(node_page, gc_type);
stat_inc_node_blk_count(sbi, 1, gc_type);
}
@@ -546,7 +538,8 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
.type = DATA,
- .rw = READ_SYNC,
+ .op = REQ_OP_READ,
+ .op_flags = READ_SYNC,
.encrypted_page = NULL,
};
struct dnode_of_data dn;
@@ -601,11 +594,11 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
/* write page */
lock_page(fio.encrypted_page);
- if (unlikely(!PageUptodate(fio.encrypted_page))) {
+ if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
err = -EIO;
goto put_page_out;
}
- if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
+ if (unlikely(!PageUptodate(fio.encrypted_page))) {
err = -EIO;
goto put_page_out;
}
@@ -620,14 +613,15 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
/* allocate block address */
f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
- fio.rw = WRITE_SYNC;
+ fio.op = REQ_OP_WRITE;
+ fio.op_flags = WRITE_SYNC;
fio.new_blkaddr = newaddr;
f2fs_submit_page_mbio(&fio);
f2fs_update_data_blkaddr(&dn, newaddr);
- set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
+ set_inode_flag(inode, FI_APPEND_WRITE);
if (page->index == 0)
- set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+ set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
put_page_out:
f2fs_put_page(fio.encrypted_page, 1);
recover_block:
@@ -657,16 +651,28 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
.type = DATA,
- .rw = WRITE_SYNC,
+ .op = REQ_OP_WRITE,
+ .op_flags = WRITE_SYNC,
.page = page,
.encrypted_page = NULL,
};
+ bool is_dirty = PageDirty(page);
+ int err;
+
+retry:
set_page_dirty(page);
f2fs_wait_on_page_writeback(page, DATA, true);
if (clear_page_dirty_for_io(page))
inode_dec_dirty_pages(inode);
+
set_cold_data(page);
- do_write_data_page(&fio);
+
+ err = do_write_data_page(&fio);
+ if (err == -ENOMEM && is_dirty) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
+
clear_cold_data(page);
}
out:
@@ -738,7 +744,8 @@ next_step:
start_bidx = start_bidx_of_node(nofs, inode);
data_page = get_read_data_page(inode,
- start_bidx + ofs_in_node, READA, true);
+ start_bidx + ofs_in_node, REQ_RAHEAD,
+ true);
if (IS_ERR(data_page)) {
iput(inode);
continue;
@@ -752,12 +759,32 @@ next_step:
/* phase 3 */
inode = find_gc_inode(gc_list, dni.ino);
if (inode) {
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ bool locked = false;
+
+ if (S_ISREG(inode->i_mode)) {
+ if (!down_write_trylock(&fi->dio_rwsem[READ]))
+ continue;
+ if (!down_write_trylock(
+ &fi->dio_rwsem[WRITE])) {
+ up_write(&fi->dio_rwsem[READ]);
+ continue;
+ }
+ locked = true;
+ }
+
start_bidx = start_bidx_of_node(nofs, inode)
+ ofs_in_node;
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
move_encrypted_block(inode, start_bidx);
else
move_data_page(inode, start_bidx, gc_type);
+
+ if (locked) {
+ up_write(&fi->dio_rwsem[WRITE]);
+ up_write(&fi->dio_rwsem[READ]);
+ }
+
stat_inc_data_blk_count(sbi, 1, gc_type);
}
}
@@ -806,6 +833,10 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
blk_start_plug(&plug);
for (segno = start_segno; segno < end_segno; segno++) {
+
+ if (get_valid_blocks(sbi, segno, 1) == 0)
+ continue;
+
/* find segment summary of victim */
sum_page = find_get_page(META_MAPPING(sbi),
GET_SUM_BLOCK(sbi, segno));
@@ -834,18 +865,9 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
f2fs_put_page(sum_page, 0);
}
- if (gc_type == FG_GC) {
- if (type == SUM_TYPE_NODE) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .nr_to_write = LONG_MAX,
- .for_reclaim = 0,
- };
- sync_node_pages(sbi, 0, &wbc);
- } else {
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
- }
- }
+ if (gc_type == FG_GC)
+ f2fs_submit_merged_bio(sbi,
+ (type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
blk_finish_plug(&plug);
@@ -890,10 +912,13 @@ gc_more:
* enough free sections, we should flush dent/node blocks and do
* garbage collections.
*/
- if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
+ if (__get_victim(sbi, &segno, gc_type) ||
+ prefree_segments(sbi)) {
write_checkpoint(sbi, &cpc);
- else if (has_not_enough_free_secs(sbi, 0))
+ segno = NULL_SEGNO;
+ } else if (has_not_enough_free_secs(sbi, 0)) {
write_checkpoint(sbi, &cpc);
+ }
}
if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 358214e9f707..ccea8735de59 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -51,7 +51,7 @@ void read_inline_data(struct page *page, struct page *ipage)
f2fs_bug_on(F2FS_P_SB(page), page->index);
- zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+ zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(ipage);
@@ -59,7 +59,8 @@ void read_inline_data(struct page *page, struct page *ipage)
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
flush_dcache_page(page);
kunmap_atomic(dst_addr);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
}
bool truncate_inline_inode(struct page *ipage, u64 from)
@@ -73,7 +74,7 @@ bool truncate_inline_inode(struct page *ipage, u64 from)
f2fs_wait_on_page_writeback(ipage, NODE, true);
memset(addr + from, 0, MAX_INLINE_DATA - from);
-
+ set_page_dirty(ipage);
return true;
}
@@ -93,11 +94,12 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
}
if (page->index)
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ zero_user_segment(page, 0, PAGE_SIZE);
else
read_inline_data(page, ipage);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
f2fs_put_page(ipage, 1);
unlock_page(page);
return 0;
@@ -108,7 +110,8 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
.type = DATA,
- .rw = WRITE_SYNC | REQ_PRIO,
+ .op = REQ_OP_WRITE,
+ .op_flags = WRITE_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
};
@@ -138,7 +141,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
inode_dec_dirty_pages(dn->inode);
/* this converted inline_data should be recovered. */
- set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
+ set_inode_flag(dn->inode, FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode_page, 0);
@@ -146,7 +149,6 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
clear_out:
stat_dec_inline_inode(dn->inode);
f2fs_clear_inline_inode(dn->inode);
- sync_inode_page(dn);
f2fs_put_dnode(dn);
return 0;
}
@@ -161,7 +163,7 @@ int f2fs_convert_inline_inode(struct inode *inode)
if (!f2fs_has_inline_data(inode))
return 0;
- page = grab_cache_page(inode->i_mapping, 0);
+ page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
if (!page)
return -ENOMEM;
@@ -212,11 +214,11 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
dst_addr = inline_data_addr(dn.inode_page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap_atomic(src_addr);
+ set_page_dirty(dn.inode_page);
- set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
- set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+ set_inode_flag(inode, FI_APPEND_WRITE);
+ set_inode_flag(inode, FI_DATA_EXIST);
- sync_inode_page(&dn);
clear_inline_node(dn.inode_page);
f2fs_put_dnode(&dn);
return 0;
@@ -252,10 +254,10 @@ process_inline:
dst_addr = inline_data_addr(ipage);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
- set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
- set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+ set_inode_flag(inode, FI_INLINE_DATA);
+ set_inode_flag(inode, FI_DATA_EXIST);
- update_inode(inode, ipage);
+ set_page_dirty(ipage);
f2fs_put_page(ipage, 1);
return true;
}
@@ -266,7 +268,6 @@ process_inline:
if (!truncate_inline_inode(ipage, 0))
return false;
f2fs_clear_inline_inode(inode);
- update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
if (truncate_blocks(inode, 0, false))
@@ -288,8 +289,10 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
f2fs_hash_t namehash;
ipage = get_node_page(sbi, dir->i_ino);
- if (IS_ERR(ipage))
+ if (IS_ERR(ipage)) {
+ *res_page = ipage;
return NULL;
+ }
namehash = f2fs_dentry_hash(&name);
@@ -303,30 +306,6 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
else
f2fs_put_page(ipage, 0);
- /*
- * 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(sbi, d.max < 0);
- return de;
-}
-
-struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *dir,
- struct page **p)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
- struct page *ipage;
- struct f2fs_dir_entry *de;
- struct f2fs_inline_dentry *dentry_blk;
-
- ipage = get_node_page(sbi, dir->i_ino);
- if (IS_ERR(ipage))
- return NULL;
-
- dentry_blk = inline_data_addr(ipage);
- de = &dentry_blk->dentry[1];
- *p = ipage;
- unlock_page(ipage);
return de;
}
@@ -344,10 +323,8 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
set_page_dirty(ipage);
/* update i_size to MAX_INLINE_DATA */
- if (i_size_read(inode) < MAX_INLINE_DATA) {
- i_size_write(inode, MAX_INLINE_DATA);
- set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
- }
+ if (i_size_read(inode) < MAX_INLINE_DATA)
+ f2fs_i_size_write(inode, MAX_INLINE_DATA);
return 0;
}
@@ -355,7 +332,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
* NOTE: ipage is grabbed by caller, but if any error occurs, we should
* release ipage in this function.
*/
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
struct page *page;
@@ -363,7 +340,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
struct f2fs_dentry_block *dentry_blk;
int err;
- page = grab_cache_page(dir->i_mapping, 0);
+ page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
if (!page) {
f2fs_put_page(ipage, 1);
return -ENOMEM;
@@ -375,7 +352,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
goto out;
f2fs_wait_on_page_writeback(page, DATA, true);
- zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+ zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
dentry_blk = kmap_atomic(page);
@@ -396,26 +373,121 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
NR_INLINE_DENTRY * F2FS_SLOT_LEN);
kunmap_atomic(dentry_blk);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
set_page_dirty(page);
/* clear inline dir and flag after data writeback */
truncate_inline_inode(ipage, 0);
stat_dec_inline_dir(dir);
- clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
-
- if (i_size_read(dir) < PAGE_CACHE_SIZE) {
- i_size_write(dir, PAGE_CACHE_SIZE);
- set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
- }
+ clear_inode_flag(dir, FI_INLINE_DENTRY);
- sync_inode_page(&dn);
+ f2fs_i_depth_write(dir, 1);
+ if (i_size_read(dir) < PAGE_SIZE)
+ f2fs_i_size_write(dir, PAGE_SIZE);
out:
f2fs_put_page(page, 1);
return err;
}
+static int f2fs_add_inline_entries(struct inode *dir,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_dentry_ptr d;
+ unsigned long bit_pos = 0;
+ int err = 0;
+
+ make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+
+ while (bit_pos < d.max) {
+ struct f2fs_dir_entry *de;
+ struct qstr new_name;
+ nid_t ino;
+ umode_t fake_mode;
+
+ if (!test_bit_le(bit_pos, d.bitmap)) {
+ bit_pos++;
+ continue;
+ }
+
+ de = &d.dentry[bit_pos];
+
+ if (unlikely(!de->name_len)) {
+ bit_pos++;
+ continue;
+ }
+
+ new_name.name = d.filename[bit_pos];
+ new_name.len = de->name_len;
+
+ ino = le32_to_cpu(de->ino);
+ fake_mode = get_de_type(de) << S_SHIFT;
+
+ err = f2fs_add_regular_entry(dir, &new_name, NULL,
+ ino, fake_mode);
+ if (err)
+ goto punch_dentry_pages;
+
+ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+ }
+ return 0;
+punch_dentry_pages:
+ truncate_inode_pages(&dir->i_data, 0);
+ truncate_blocks(dir, 0, false);
+ remove_dirty_inode(dir);
+ return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_inline_dentry *backup_dentry;
+ int err;
+
+ backup_dentry = f2fs_kmalloc(sizeof(struct f2fs_inline_dentry),
+ GFP_F2FS_ZERO);
+ if (!backup_dentry) {
+ f2fs_put_page(ipage, 1);
+ return -ENOMEM;
+ }
+
+ memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+ truncate_inline_inode(ipage, 0);
+
+ unlock_page(ipage);
+
+ err = f2fs_add_inline_entries(dir, backup_dentry);
+ if (err)
+ goto recover;
+
+ lock_page(ipage);
+
+ stat_dec_inline_dir(dir);
+ clear_inode_flag(dir, FI_INLINE_DENTRY);
+ kfree(backup_dentry);
+ return 0;
+recover:
+ lock_page(ipage);
+ memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+ f2fs_i_depth_write(dir, 0);
+ f2fs_i_size_write(dir, MAX_INLINE_DATA);
+ set_page_dirty(ipage);
+ f2fs_put_page(ipage, 1);
+
+ kfree(backup_dentry);
+ return err;
+}
+
+static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ if (!F2FS_I(dir)->i_dir_level)
+ return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
+ else
+ return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
+}
+
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode)
{
@@ -464,8 +536,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
/* we don't need to mark_inode_dirty now */
if (inode) {
- F2FS_I(inode)->i_pino = dir->i_ino;
- update_inode(inode, page);
+ f2fs_i_pino_write(inode, dir->i_ino);
f2fs_put_page(page, 1);
}
@@ -473,11 +544,6 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
fail:
if (inode)
up_write(&F2FS_I(inode)->i_sem);
-
- if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
- update_inode(dir, ipage);
- clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
- }
out:
f2fs_put_page(ipage, 1);
return err;
@@ -501,13 +567,13 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
&inline_dentry->dentry_bitmap);
set_page_dirty(page);
+ f2fs_put_page(page, 1);
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+ f2fs_mark_inode_dirty_sync(dir);
if (inode)
- f2fs_drop_nlink(dir, inode, page);
-
- f2fs_put_page(page, 1);
+ f2fs_drop_nlink(dir, inode);
}
bool f2fs_empty_inline_dir(struct inode *dir)
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index cb269c46ac25..9ac5efc15347 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -18,6 +18,13 @@
#include <trace/events/f2fs.h>
+void f2fs_mark_inode_dirty_sync(struct inode *inode)
+{
+ if (f2fs_inode_dirtied(inode))
+ return;
+ mark_inode_dirty_sync(inode);
+}
+
void f2fs_set_inode_flags(struct inode *inode)
{
unsigned int flags = F2FS_I(inode)->i_flags;
@@ -35,6 +42,7 @@ void f2fs_set_inode_flags(struct inode *inode)
new_fl |= S_DIRSYNC;
inode_set_flags(inode, new_fl,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+ f2fs_mark_inode_dirty_sync(inode);
}
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -85,8 +93,8 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
if (*start++) {
f2fs_wait_on_page_writeback(ipage, NODE, true);
- set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
- set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
+ set_inode_flag(inode, FI_DATA_EXIST);
+ set_raw_inline(inode, F2FS_INODE(ipage));
set_page_dirty(ipage);
return;
}
@@ -141,7 +149,7 @@ static int do_read_inode(struct inode *inode)
if (f2fs_init_extent_tree(inode, &ri->i_ext))
set_page_dirty(node_page);
- get_inline_info(fi, ri);
+ get_inline_info(inode, ri);
/* check data exist */
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
@@ -151,7 +159,10 @@ static int do_read_inode(struct inode *inode)
__get_inode_rdev(inode, ri);
if (__written_first_block(ri))
- set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+ set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
+
+ if (!need_inode_block_update(sbi, inode->i_ino))
+ fi->last_disk_size = inode->i_size;
f2fs_put_page(node_page, 1);
@@ -227,6 +238,8 @@ int update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
+ f2fs_inode_synced(inode);
+
f2fs_wait_on_page_writeback(node_page, NODE, true);
ri = F2FS_INODE(node_page);
@@ -244,7 +257,7 @@ int update_inode(struct inode *inode, struct page *node_page)
&ri->i_ext);
else
memset(&ri->i_ext, 0, sizeof(ri->i_ext));
- set_raw_inline(F2FS_I(inode), ri);
+ set_raw_inline(inode, ri);
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
@@ -261,7 +274,6 @@ int update_inode(struct inode *inode, struct page *node_page)
__set_inode_rdev(inode, ri);
set_cold_node(inode, node_page);
- clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
/* deleted inode */
if (inode->i_nlink == 0)
@@ -283,8 +295,9 @@ retry:
cond_resched();
goto retry;
} else if (err != -ENOENT) {
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
}
+ f2fs_inode_synced(inode);
return 0;
}
ret = update_inode(inode, node_page);
@@ -300,7 +313,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
inode->i_ino == F2FS_META_INO(sbi))
return 0;
- if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE))
+ if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
return 0;
/*
@@ -318,8 +331,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
void f2fs_evict_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- nid_t xnid = fi->i_xattr_nid;
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
int err = 0;
/* some remained atomic pages should discarded */
@@ -341,12 +353,17 @@ void f2fs_evict_inode(struct inode *inode)
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_EVICT_INODE))
+ goto no_delete;
+#endif
+
sb_start_intwrite(inode->i_sb);
- set_inode_flag(fi, FI_NO_ALLOC);
+ set_inode_flag(inode, FI_NO_ALLOC);
i_size_write(inode, 0);
-
+retry:
if (F2FS_HAS_BLOCKS(inode))
- err = f2fs_truncate(inode, true);
+ err = f2fs_truncate(inode);
if (!err) {
f2fs_lock_op(sbi);
@@ -354,6 +371,14 @@ void f2fs_evict_inode(struct inode *inode)
f2fs_unlock_op(sbi);
}
+ /* give more chances, if ENOMEM case */
+ if (err == -ENOMEM) {
+ err = 0;
+ goto retry;
+ }
+
+ if (err)
+ update_inode_page(inode);
sb_end_intwrite(inode->i_sb);
no_delete:
stat_dec_inline_xattr(inode);
@@ -363,31 +388,16 @@ no_delete:
invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
if (xnid)
invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
- if (is_inode_flag_set(fi, FI_APPEND_WRITE))
+ if (is_inode_flag_set(inode, FI_APPEND_WRITE))
add_ino_entry(sbi, inode->i_ino, APPEND_INO);
- if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
+ if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
- if (is_inode_flag_set(fi, FI_FREE_NID)) {
- if (err && err != -ENOENT)
- alloc_nid_done(sbi, inode->i_ino);
- else
- alloc_nid_failed(sbi, inode->i_ino);
- clear_inode_flag(fi, FI_FREE_NID);
- }
-
- if (err && err != -ENOENT) {
- if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) {
- /*
- * get here because we failed to release resource
- * of inode previously, reminder our user to run fsck
- * for fixing.
- */
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_msg(sbi->sb, KERN_WARNING,
- "inode (ino:%lu) resource leak, run fsck "
- "to fix this issue!", inode->i_ino);
- }
+ if (is_inode_flag_set(inode, FI_FREE_NID)) {
+ alloc_nid_failed(sbi, inode->i_ino);
+ clear_inode_flag(inode, FI_FREE_NID);
}
+ f2fs_bug_on(sbi, err &&
+ !exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
out_clear:
fscrypt_put_encryption_info(inode, NULL);
clear_inode(inode);
@@ -397,37 +407,32 @@ out_clear:
void handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- int err = 0;
+ struct node_info ni;
- clear_nlink(inode);
- make_bad_inode(inode);
+ /* don't make bad inode, since it becomes a regular file. */
unlock_new_inode(inode);
- i_size_write(inode, 0);
- if (F2FS_HAS_BLOCKS(inode))
- err = f2fs_truncate(inode, false);
-
- if (!err)
- err = remove_inode_page(inode);
-
/*
- * if we skip truncate_node in remove_inode_page bacause we failed
- * before, it's better to find another way to release resource of
- * this inode (e.g. valid block count, node block or nid). Here we
- * choose to add this inode to orphan list, so that we can call iput
- * for releasing in orphan recovery flow.
- *
* Note: we should add inode to orphan list before f2fs_unlock_op()
* so we can prevent losing this orphan when encoutering checkpoint
* and following suddenly power-off.
*/
- if (err && err != -ENOENT) {
- err = acquire_orphan_inode(sbi);
- if (!err)
- add_orphan_inode(sbi, inode->i_ino);
+ get_node_info(sbi, inode->i_ino, &ni);
+
+ if (ni.blk_addr != NULL_ADDR) {
+ int err = acquire_orphan_inode(sbi);
+ if (err) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Too many orphan inodes, run fsck to fix.");
+ } else {
+ add_orphan_inode(inode);
+ }
+ alloc_nid_done(sbi, inode->i_ino);
+ } else {
+ set_inode_flag(inode, FI_FREE_NID);
}
- set_inode_flag(F2FS_I(inode), FI_FREE_NID);
f2fs_unlock_op(sbi);
/* iput will drop the inode object */
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 7876f1052101..73fa356f8fbb 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -60,10 +60,14 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
f2fs_set_encrypted_inode(inode);
+ set_inode_flag(inode, FI_NEW_INODE);
+
+ if (test_opt(sbi, INLINE_XATTR))
+ set_inode_flag(inode, FI_INLINE_XATTR);
if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
- set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+ set_inode_flag(inode, FI_INLINE_DATA);
if (f2fs_may_inline_dentry(inode))
- set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
+ set_inode_flag(inode, FI_INLINE_DENTRY);
f2fs_init_extent_tree(inode, NULL);
@@ -72,14 +76,13 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
stat_inc_inline_dir(inode);
trace_f2fs_new_inode(inode, 0);
- mark_inode_dirty(inode);
return inode;
fail:
trace_f2fs_new_inode(inode, err);
make_bad_inode(inode);
if (nid_free)
- set_inode_flag(F2FS_I(inode), FI_FREE_NID);
+ set_inode_flag(inode, FI_FREE_NID);
iput(inode);
return ERR_PTR(err);
}
@@ -177,7 +180,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
inode->i_ctime = CURRENT_TIME;
ihold(inode);
- set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ set_inode_flag(inode, FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
@@ -190,7 +193,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
f2fs_sync_fs(sbi->sb, 1);
return 0;
out:
- clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ clear_inode_flag(inode, FI_INC_LINK);
iput(inode);
f2fs_unlock_op(sbi);
return err;
@@ -199,10 +202,14 @@ out:
struct dentry *f2fs_get_parent(struct dentry *child)
{
struct qstr dotdot = QSTR_INIT("..", 2);
- unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot);
- if (!ino)
+ struct page *page;
+ unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot, &page);
+ if (!ino) {
+ if (IS_ERR(page))
+ return ERR_CAST(page);
return ERR_PTR(-ENOENT);
- return d_obtain_alias(f2fs_iget(d_inode(child)->i_sb, ino));
+ }
+ return d_obtain_alias(f2fs_iget(child->d_sb, ino));
}
static int __recover_dot_dentries(struct inode *dir, nid_t pino)
@@ -229,6 +236,9 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
if (de) {
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
+ } else if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto out;
} else {
err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
if (err)
@@ -239,14 +249,14 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
if (de) {
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
+ } else if (IS_ERR(page)) {
+ err = PTR_ERR(page);
} else {
err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
}
out:
- if (!err) {
- clear_inode_flag(F2FS_I(dir), FI_INLINE_DOTS);
- mark_inode_dirty(dir);
- }
+ if (!err)
+ clear_inode_flag(dir, FI_INLINE_DOTS);
f2fs_unlock_op(sbi);
return err;
@@ -281,8 +291,11 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
return ERR_PTR(-ENAMETOOLONG);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
- if (!de)
+ if (!de) {
+ if (IS_ERR(page))
+ return (struct dentry *)page;
return d_splice_alias(inode, dentry);
+ }
ino = le32_to_cpu(de->ino);
f2fs_dentry_kunmap(dir, page);
@@ -329,8 +342,11 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
trace_f2fs_unlink_enter(dir, dentry);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
- if (!de)
+ if (!de) {
+ if (IS_ERR(page))
+ err = PTR_ERR(page);
goto fail;
+ }
f2fs_balance_fs(sbi, true);
@@ -345,9 +361,6 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
f2fs_delete_entry(de, page, dir, inode);
f2fs_unlock_op(sbi);
- /* In order to evict this inode, we set it dirty */
- mark_inode_dirty(inode);
-
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
fail:
@@ -492,7 +505,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
f2fs_balance_fs(sbi, true);
- set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ set_inode_flag(inode, FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
@@ -509,7 +522,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
return 0;
out_fail:
- clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ clear_inode_flag(inode, FI_INC_LINK);
handle_failed_inode(inode);
return err;
}
@@ -592,17 +605,17 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
* add this non-linked tmpfile to orphan list, in this way we could
* remove all unused data of tmpfile after abnormal power-off.
*/
- add_orphan_inode(sbi, inode->i_ino);
- f2fs_unlock_op(sbi);
-
+ add_orphan_inode(inode);
alloc_nid_done(sbi, inode->i_ino);
if (whiteout) {
- inode_dec_link_count(inode);
+ f2fs_i_links_write(inode, false);
*whiteout = inode;
} else {
d_tmpfile(dentry, inode);
}
+ /* link_count was changed by d_tmpfile as well. */
+ f2fs_unlock_op(sbi);
unlock_new_inode(inode);
return 0;
@@ -652,14 +665,19 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
- if (!old_entry)
+ if (!old_entry) {
+ if (IS_ERR(old_page))
+ err = PTR_ERR(old_page);
goto out;
+ }
if (S_ISDIR(old_inode->i_mode)) {
- err = -EIO;
old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
- if (!old_dir_entry)
+ if (!old_dir_entry) {
+ if (IS_ERR(old_dir_page))
+ err = PTR_ERR(old_dir_page);
goto out_old;
+ }
}
if (flags & RENAME_WHITEOUT) {
@@ -677,8 +695,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
err = -ENOENT;
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
&new_page);
- if (!new_entry)
+ if (!new_entry) {
+ if (IS_ERR(new_page))
+ err = PTR_ERR(new_page);
goto out_whiteout;
+ }
f2fs_balance_fs(sbi, true);
@@ -700,19 +721,14 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
new_inode->i_ctime = CURRENT_TIME;
down_write(&F2FS_I(new_inode)->i_sem);
if (old_dir_entry)
- drop_nlink(new_inode);
- drop_nlink(new_inode);
+ f2fs_i_links_write(new_inode, false);
+ f2fs_i_links_write(new_inode, false);
up_write(&F2FS_I(new_inode)->i_sem);
- mark_inode_dirty(new_inode);
-
if (!new_inode->i_nlink)
- add_orphan_inode(sbi, new_inode->i_ino);
+ add_orphan_inode(new_inode);
else
release_orphan_inode(sbi);
-
- update_inode_page(old_inode);
- update_inode_page(new_inode);
} else {
f2fs_balance_fs(sbi, true);
@@ -724,10 +740,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out_whiteout;
}
- if (old_dir_entry) {
- inc_nlink(new_dir);
- update_inode_page(new_dir);
- }
+ if (old_dir_entry)
+ f2fs_i_links_write(new_dir, true);
/*
* old entry and new entry can locate in the same inline
@@ -743,7 +757,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
old_entry = f2fs_find_entry(old_dir,
&old_dentry->d_name, &old_page);
if (!old_entry) {
- err = -EIO;
+ err = -ENOENT;
+ if (IS_ERR(old_page))
+ err = PTR_ERR(old_page);
f2fs_unlock_op(sbi);
goto out_whiteout;
}
@@ -757,13 +773,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
up_write(&F2FS_I(old_inode)->i_sem);
old_inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(old_inode);
+ f2fs_mark_inode_dirty_sync(old_inode);
f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
if (whiteout) {
whiteout->i_state |= I_LINKABLE;
- set_inode_flag(F2FS_I(whiteout), FI_INC_LINK);
+ set_inode_flag(whiteout, FI_INC_LINK);
err = f2fs_add_link(old_dentry, whiteout);
if (err)
goto put_out_dir;
@@ -775,14 +791,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (old_dir != new_dir && !whiteout) {
f2fs_set_link(old_inode, old_dir_entry,
old_dir_page, new_dir);
- update_inode_page(old_inode);
} else {
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
- drop_nlink(old_dir);
- mark_inode_dirty(old_dir);
- update_inode_page(old_dir);
+ f2fs_i_links_write(old_dir, false);
}
f2fs_unlock_op(sbi);
@@ -832,29 +845,39 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
return -EPERM;
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
- if (!old_entry)
+ if (!old_entry) {
+ if (IS_ERR(old_page))
+ err = PTR_ERR(old_page);
goto out;
+ }
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page);
- if (!new_entry)
+ if (!new_entry) {
+ if (IS_ERR(new_page))
+ err = PTR_ERR(new_page);
goto out_old;
+ }
/* prepare for updating ".." directory entry info later */
if (old_dir != new_dir) {
if (S_ISDIR(old_inode->i_mode)) {
- err = -EIO;
old_dir_entry = f2fs_parent_dir(old_inode,
&old_dir_page);
- if (!old_dir_entry)
+ if (!old_dir_entry) {
+ if (IS_ERR(old_dir_page))
+ err = PTR_ERR(old_dir_page);
goto out_new;
+ }
}
if (S_ISDIR(new_inode->i_mode)) {
- err = -EIO;
new_dir_entry = f2fs_parent_dir(new_inode,
&new_dir_page);
- if (!new_dir_entry)
+ if (!new_dir_entry) {
+ if (IS_ERR(new_dir_page))
+ err = PTR_ERR(new_dir_page);
goto out_old_dir;
+ }
}
}
@@ -904,19 +927,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
file_lost_pino(old_inode);
up_write(&F2FS_I(old_inode)->i_sem);
- update_inode_page(old_inode);
-
old_dir->i_ctime = CURRENT_TIME;
if (old_nlink) {
down_write(&F2FS_I(old_dir)->i_sem);
- if (old_nlink < 0)
- drop_nlink(old_dir);
- else
- inc_nlink(old_dir);
+ f2fs_i_links_write(old_dir, old_nlink > 0);
up_write(&F2FS_I(old_dir)->i_sem);
}
- mark_inode_dirty(old_dir);
- update_inode_page(old_dir);
+ f2fs_mark_inode_dirty_sync(old_dir);
/* update directory entry info of new dir inode */
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
@@ -925,19 +942,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
file_lost_pino(new_inode);
up_write(&F2FS_I(new_inode)->i_sem);
- update_inode_page(new_inode);
-
new_dir->i_ctime = CURRENT_TIME;
if (new_nlink) {
down_write(&F2FS_I(new_dir)->i_sem);
- if (new_nlink < 0)
- drop_nlink(new_dir);
- else
- inc_nlink(new_dir);
+ f2fs_i_links_write(new_dir, new_nlink > 0);
up_write(&F2FS_I(new_dir)->i_sem);
}
- mark_inode_dirty(new_dir);
- update_inode_page(new_dir);
+ f2fs_mark_inode_dirty_sync(new_dir);
f2fs_unlock_op(sbi);
@@ -1027,12 +1038,6 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
goto errout;
}
- /* this is broken symlink case */
- if (unlikely(cstr.name[0] == 0)) {
- res = -ENOENT;
- goto errout;
- }
-
if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
/* Symlink data on the disk is corrupted */
res = -EIO;
@@ -1046,17 +1051,23 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
if (res < 0)
goto errout;
+ /* this is broken symlink case */
+ if (unlikely(pstr.name[0] == 0)) {
+ res = -ENOENT;
+ goto errout;
+ }
+
paddr = pstr.name;
/* Null-terminate the name */
paddr[res] = '\0';
- page_cache_release(cpage);
+ put_page(cpage);
set_delayed_call(done, kfree_link, paddr);
return paddr;
errout:
fscrypt_fname_free_buffer(&pstr);
- page_cache_release(cpage);
+ put_page(cpage);
return ERR_PTR(res);
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 118321bd1a7f..b2fa4b615925 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -46,12 +46,16 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
*/
if (type == FREE_NIDS) {
mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >>
- PAGE_CACHE_SHIFT;
+ PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
} else if (type == NAT_ENTRIES) {
mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
- PAGE_CACHE_SHIFT;
+ PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
+ if (excess_cached_nats(sbi))
+ res = false;
+ if (nm_i->nat_cnt > DEF_NAT_CACHE_THRESHOLD)
+ res = false;
} else if (type == DIRTY_DENTS) {
if (sbi->sb->s_bdi->wb.dirty_exceeded)
return false;
@@ -62,13 +66,13 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
for (i = 0; i <= UPDATE_INO; i++)
mem_size += (sbi->im[i].ino_num *
- sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT;
+ sizeof(struct ino_entry)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
} else if (type == EXTENT_CACHE) {
mem_size = (atomic_read(&sbi->total_ext_tree) *
sizeof(struct extent_tree) +
atomic_read(&sbi->total_ext_node) *
- sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT;
+ sizeof(struct extent_node)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
} else {
if (!sbi->sb->s_bdi->wb.dirty_exceeded)
@@ -121,7 +125,7 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
- memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
+ memcpy(dst_addr, src_addr, PAGE_SIZE);
set_page_dirty(dst_page);
f2fs_put_page(src_page, 1);
@@ -202,14 +206,14 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
struct nat_entry *e;
bool need = false;
- down_read(&nm_i->nat_tree_lock);
+ percpu_down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
if (!get_nat_flag(e, IS_CHECKPOINTED) &&
!get_nat_flag(e, HAS_FSYNCED_INODE))
need = true;
}
- up_read(&nm_i->nat_tree_lock);
+ percpu_up_read(&nm_i->nat_tree_lock);
return need;
}
@@ -219,11 +223,11 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
struct nat_entry *e;
bool is_cp = true;
- down_read(&nm_i->nat_tree_lock);
+ percpu_down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e && !get_nat_flag(e, IS_CHECKPOINTED))
is_cp = false;
- up_read(&nm_i->nat_tree_lock);
+ percpu_up_read(&nm_i->nat_tree_lock);
return is_cp;
}
@@ -233,13 +237,13 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
struct nat_entry *e;
bool need_update = true;
- down_read(&nm_i->nat_tree_lock);
+ percpu_down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ino);
if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
(get_nat_flag(e, IS_CHECKPOINTED) ||
get_nat_flag(e, HAS_FSYNCED_INODE)))
need_update = false;
- up_read(&nm_i->nat_tree_lock);
+ percpu_up_read(&nm_i->nat_tree_lock);
return need_update;
}
@@ -280,7 +284,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
- down_write(&nm_i->nat_tree_lock);
+ percpu_down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ni->nid);
if (!e) {
e = grab_nat_entry(nm_i, ni->nid);
@@ -330,7 +334,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
set_nat_flag(e, HAS_FSYNCED_INODE, true);
set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
}
- up_write(&nm_i->nat_tree_lock);
+ percpu_up_write(&nm_i->nat_tree_lock);
}
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -338,8 +342,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
struct f2fs_nm_info *nm_i = NM_I(sbi);
int nr = nr_shrink;
- if (!down_write_trylock(&nm_i->nat_tree_lock))
- return 0;
+ percpu_down_write(&nm_i->nat_tree_lock);
while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
struct nat_entry *ne;
@@ -348,7 +351,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
__del_from_nat_cache(nm_i, ne);
nr_shrink--;
}
- up_write(&nm_i->nat_tree_lock);
+ percpu_up_write(&nm_i->nat_tree_lock);
return nr - nr_shrink;
}
@@ -370,13 +373,13 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
ni->nid = nid;
/* Check nat cache */
- down_read(&nm_i->nat_tree_lock);
+ percpu_down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
ni->ino = nat_get_ino(e);
ni->blk_addr = nat_get_blkaddr(e);
ni->version = nat_get_version(e);
- up_read(&nm_i->nat_tree_lock);
+ percpu_up_read(&nm_i->nat_tree_lock);
return;
}
@@ -400,11 +403,34 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
node_info_from_raw_nat(ni, &ne);
f2fs_put_page(page, 1);
cache:
- up_read(&nm_i->nat_tree_lock);
+ percpu_up_read(&nm_i->nat_tree_lock);
/* cache nat entry */
- down_write(&nm_i->nat_tree_lock);
+ percpu_down_write(&nm_i->nat_tree_lock);
cache_nat_entry(sbi, nid, &ne);
- up_write(&nm_i->nat_tree_lock);
+ percpu_up_write(&nm_i->nat_tree_lock);
+}
+
+/*
+ * readahead MAX_RA_NODE number of node pages.
+ */
+static void ra_node_pages(struct page *parent, int start, int n)
+{
+ struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
+ struct blk_plug plug;
+ int i, end;
+ nid_t nid;
+
+ blk_start_plug(&plug);
+
+ /* Then, try readahead for siblings of the desired node */
+ end = start + n;
+ end = min(end, NIDS_PER_BLOCK);
+ for (i = start; i < end; i++) {
+ nid = get_nid(parent, i, false);
+ ra_node_page(sbi, nid);
+ }
+
+ blk_finish_plug(&plug);
}
pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
@@ -623,6 +649,7 @@ release_out:
if (err == -ENOENT) {
dn->cur_level = i;
dn->max_level = level;
+ dn->ofs_in_node = offset[level];
}
return err;
}
@@ -647,8 +674,7 @@ static void truncate_node(struct dnode_of_data *dn)
if (dn->nid == dn->inode->i_ino) {
remove_orphan_inode(sbi, dn->nid);
dec_valid_inode_count(sbi);
- } else {
- sync_inode_page(dn);
+ f2fs_inode_synced(dn->inode);
}
invalidate:
clear_node_page_dirty(dn->node_page);
@@ -707,6 +733,8 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
return PTR_ERR(page);
}
+ ra_node_pages(page, ofs, NIDS_PER_BLOCK);
+
rn = F2FS_NODE(page);
if (depth < 3) {
for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) {
@@ -784,6 +812,8 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
nid[i + 1] = get_nid(pages[i], offset[i + 1], false);
}
+ ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK);
+
/* free direct nodes linked to a partial indirect node */
for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) {
child_nid = get_nid(pages[idx], i, false);
@@ -832,7 +862,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
trace_f2fs_truncate_inode_blocks_enter(inode, from);
level = get_node_path(inode, from, offset, noffset);
-restart:
+
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
@@ -896,10 +926,7 @@ skip_partial:
if (offset[1] == 0 &&
ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) {
lock_page(page);
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
- f2fs_put_page(page, 1);
- goto restart;
- }
+ BUG_ON(page->mapping != NODE_MAPPING(sbi));
f2fs_wait_on_page_writeback(page, NODE, true);
ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
set_page_dirty(page);
@@ -929,7 +956,7 @@ int truncate_xattr_node(struct inode *inode, struct page *page)
if (IS_ERR(npage))
return PTR_ERR(npage);
- F2FS_I(inode)->i_xattr_nid = 0;
+ f2fs_i_xnid_write(inode, 0);
/* need to do checkpoint during fsync */
F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
@@ -995,10 +1022,10 @@ struct page *new_node_page(struct dnode_of_data *dn,
struct page *page;
int err;
- if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
+ if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return ERR_PTR(-EPERM);
- page = grab_cache_page(NODE_MAPPING(sbi), dn->nid);
+ page = f2fs_grab_cache_page(NODE_MAPPING(sbi), dn->nid, false);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -1018,21 +1045,16 @@ struct page *new_node_page(struct dnode_of_data *dn,
f2fs_wait_on_page_writeback(page, NODE, true);
fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
set_cold_node(dn->inode, page);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
if (set_page_dirty(page))
dn->node_changed = true;
if (f2fs_has_xattr_block(ofs))
- F2FS_I(dn->inode)->i_xattr_nid = dn->nid;
+ f2fs_i_xnid_write(dn->inode, dn->nid);
- dn->node_page = page;
- if (ipage)
- update_inode(dn->inode, ipage);
- else
- sync_inode_page(dn);
if (ofs == 0)
inc_valid_inode_count(sbi);
-
return page;
fail:
@@ -1046,18 +1068,22 @@ fail:
* 0: f2fs_put_page(page, 0)
* LOCKED_PAGE or error: f2fs_put_page(page, 1)
*/
-static int read_node_page(struct page *page, int rw)
+static int read_node_page(struct page *page, int op_flags)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
struct node_info ni;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = NODE,
- .rw = rw,
+ .op = REQ_OP_READ,
+ .op_flags = op_flags,
.page = page,
.encrypted_page = NULL,
};
+ if (PageUptodate(page))
+ return LOCKED_PAGE;
+
get_node_info(sbi, page->index, &ni);
if (unlikely(ni.blk_addr == NULL_ADDR)) {
@@ -1065,9 +1091,6 @@ static int read_node_page(struct page *page, int rw)
return -ENOENT;
}
- if (PageUptodate(page))
- return LOCKED_PAGE;
-
fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr;
return f2fs_submit_page_bio(&fio);
}
@@ -1090,37 +1113,14 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
if (apage)
return;
- apage = grab_cache_page(NODE_MAPPING(sbi), nid);
+ apage = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
if (!apage)
return;
- err = read_node_page(apage, READA);
+ err = read_node_page(apage, REQ_RAHEAD);
f2fs_put_page(apage, err ? 1 : 0);
}
-/*
- * readahead MAX_RA_NODE number of node pages.
- */
-static void ra_node_pages(struct page *parent, int start)
-{
- struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
- struct blk_plug plug;
- int i, end;
- nid_t nid;
-
- blk_start_plug(&plug);
-
- /* Then, try readahead for siblings of the desired node */
- end = start + MAX_RA_NODE;
- end = min(end, NIDS_PER_BLOCK);
- for (i = start; i < end; i++) {
- nid = get_nid(parent, i, false);
- ra_node_page(sbi, nid);
- }
-
- blk_finish_plug(&plug);
-}
-
static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
struct page *parent, int start)
{
@@ -1131,7 +1131,7 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
return ERR_PTR(-ENOENT);
f2fs_bug_on(sbi, check_nid_range(sbi, nid));
repeat:
- page = grab_cache_page(NODE_MAPPING(sbi), nid);
+ page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -1144,20 +1144,25 @@ repeat:
}
if (parent)
- ra_node_pages(parent, start + 1);
+ ra_node_pages(parent, start + 1, MAX_RA_NODE);
lock_page(page);
- if (unlikely(!PageUptodate(page))) {
- f2fs_put_page(page, 1);
- return ERR_PTR(-EIO);
- }
if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
f2fs_put_page(page, 1);
goto repeat;
}
+
+ if (unlikely(!PageUptodate(page)))
+ goto out_err;
page_hit:
- f2fs_bug_on(sbi, nid != nid_of_node(page));
+ if(unlikely(nid != nid_of_node(page))) {
+ f2fs_bug_on(sbi, 1);
+ ClearPageUptodate(page);
+out_err:
+ f2fs_put_page(page, 1);
+ return ERR_PTR(-EIO);
+ }
return page;
}
@@ -1174,41 +1179,21 @@ struct page *get_node_page_ra(struct page *parent, int start)
return __get_node_page(sbi, nid, parent, start);
}
-void sync_inode_page(struct dnode_of_data *dn)
-{
- int ret = 0;
-
- if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) {
- ret = update_inode(dn->inode, dn->node_page);
- } else if (dn->inode_page) {
- if (!dn->inode_page_locked)
- lock_page(dn->inode_page);
- ret = update_inode(dn->inode, dn->inode_page);
- if (!dn->inode_page_locked)
- unlock_page(dn->inode_page);
- } else {
- ret = update_inode_page(dn->inode);
- }
- dn->node_changed = ret ? true: false;
-}
-
static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode;
struct page *page;
+ int ret;
/* should flush inline_data before evict_inode */
inode = ilookup(sbi->sb, ino);
if (!inode)
return;
- page = pagecache_get_page(inode->i_mapping, 0, FGP_NOWAIT, 0);
+ page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0);
if (!page)
goto iput_out;
- if (!trylock_page(page))
- goto release_out;
-
if (!PageUptodate(page))
goto page_out;
@@ -1218,24 +1203,219 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
if (!clear_page_dirty_for_io(page))
goto page_out;
- if (!f2fs_write_inline_data(inode, page))
- inode_dec_dirty_pages(inode);
- else
+ ret = f2fs_write_inline_data(inode, page);
+ inode_dec_dirty_pages(inode);
+ if (ret)
set_page_dirty(page);
page_out:
- unlock_page(page);
-release_out:
- f2fs_put_page(page, 0);
+ f2fs_put_page(page, 1);
iput_out:
iput(inode);
}
-int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
- struct writeback_control *wbc)
+void move_node_page(struct page *node_page, int gc_type)
+{
+ if (gc_type == FG_GC) {
+ struct f2fs_sb_info *sbi = F2FS_P_SB(node_page);
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = 1,
+ .for_reclaim = 0,
+ };
+
+ set_page_dirty(node_page);
+ f2fs_wait_on_page_writeback(node_page, NODE, true);
+
+ f2fs_bug_on(sbi, PageWriteback(node_page));
+ if (!clear_page_dirty_for_io(node_page))
+ goto out_page;
+
+ if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc))
+ unlock_page(node_page);
+ goto release_page;
+ } else {
+ /* set page dirty and write it */
+ if (!PageWriteback(node_page))
+ set_page_dirty(node_page);
+ }
+out_page:
+ unlock_page(node_page);
+release_page:
+ f2fs_put_page(node_page, 0);
+}
+
+static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
+{
+ pgoff_t index, end;
+ struct pagevec pvec;
+ struct page *last_page = NULL;
+
+ pagevec_init(&pvec, 0);
+ index = 0;
+ end = ULONG_MAX;
+
+ while (index <= end) {
+ int i, nr_pages;
+ nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ if (nr_pages == 0)
+ break;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_put_page(last_page, 0);
+ pagevec_release(&pvec);
+ return ERR_PTR(-EIO);
+ }
+
+ if (!IS_DNODE(page) || !is_cold_node(page))
+ continue;
+ if (ino_of_node(page) != ino)
+ continue;
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+ if (ino_of_node(page) != ino)
+ goto continue_unlock;
+
+ if (!PageDirty(page)) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ if (last_page)
+ f2fs_put_page(last_page, 0);
+
+ get_page(page);
+ last_page = page;
+ unlock_page(page);
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+ return last_page;
+}
+
+int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
+ struct writeback_control *wbc, bool atomic)
+{
+ pgoff_t index, end;
+ struct pagevec pvec;
+ int ret = 0;
+ struct page *last_page = NULL;
+ bool marked = false;
+ nid_t ino = inode->i_ino;
+
+ if (atomic) {
+ last_page = last_fsync_dnode(sbi, ino);
+ if (IS_ERR_OR_NULL(last_page))
+ return PTR_ERR_OR_ZERO(last_page);
+ }
+retry:
+ pagevec_init(&pvec, 0);
+ index = 0;
+ end = ULONG_MAX;
+
+ while (index <= end) {
+ int i, nr_pages;
+ nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ if (nr_pages == 0)
+ break;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_put_page(last_page, 0);
+ pagevec_release(&pvec);
+ return -EIO;
+ }
+
+ if (!IS_DNODE(page) || !is_cold_node(page))
+ continue;
+ if (ino_of_node(page) != ino)
+ continue;
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+ if (ino_of_node(page) != ino)
+ goto continue_unlock;
+
+ if (!PageDirty(page) && page != last_page) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ f2fs_wait_on_page_writeback(page, NODE, true);
+ BUG_ON(PageWriteback(page));
+
+ if (!atomic || page == last_page) {
+ set_fsync_mark(page, 1);
+ if (IS_INODE(page)) {
+ if (is_inode_flag_set(inode,
+ FI_DIRTY_INODE))
+ update_inode(inode, page);
+ set_dentry_mark(page,
+ need_dentry_mark(sbi, ino));
+ }
+ /* may be written by other thread */
+ if (!PageDirty(page))
+ set_page_dirty(page);
+ }
+
+ if (!clear_page_dirty_for_io(page))
+ goto continue_unlock;
+
+ ret = NODE_MAPPING(sbi)->a_ops->writepage(page, wbc);
+ if (ret) {
+ unlock_page(page);
+ f2fs_put_page(last_page, 0);
+ break;
+ }
+ if (page == last_page) {
+ f2fs_put_page(page, 0);
+ marked = true;
+ break;
+ }
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+
+ if (ret || marked)
+ break;
+ }
+ if (!ret && atomic && !marked) {
+ f2fs_msg(sbi->sb, KERN_DEBUG,
+ "Retry to write fsync mark: ino=%u, idx=%lx",
+ ino, last_page->index);
+ lock_page(last_page);
+ set_page_dirty(last_page);
+ unlock_page(last_page);
+ goto retry;
+ }
+ return ret ? -EIO: 0;
+}
+
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
{
pgoff_t index, end;
struct pagevec pvec;
- int step = ino ? 2 : 0;
+ int step = 0;
int nwritten = 0;
pagevec_init(&pvec, 0);
@@ -1274,15 +1454,8 @@ next_step:
if (step == 2 && (!IS_DNODE(page) ||
!is_cold_node(page)))
continue;
-
- /*
- * If an fsync mode,
- * we should not skip writing node pages.
- */
lock_node:
- if (ino && ino_of_node(page) == ino)
- lock_page(page);
- else if (!trylock_page(page))
+ if (!trylock_page(page))
continue;
if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
@@ -1290,8 +1463,6 @@ continue_unlock:
unlock_page(page);
continue;
}
- if (ino && ino_of_node(page) != ino)
- goto continue_unlock;
if (!PageDirty(page)) {
/* someone wrote it for us */
@@ -1299,7 +1470,7 @@ continue_unlock:
}
/* flush inline_data */
- if (!ino && is_inline_node(page)) {
+ if (is_inline_node(page)) {
clear_inline_node(page);
unlock_page(page);
flush_inline_data(sbi, ino_of_node(page));
@@ -1312,17 +1483,8 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- /* called by fsync() */
- if (ino && IS_DNODE(page)) {
- set_fsync_mark(page, 1);
- if (IS_INODE(page))
- set_dentry_mark(page,
- need_dentry_mark(sbi, ino));
- nwritten++;
- } else {
- set_fsync_mark(page, 0);
- set_dentry_mark(page, 0);
- }
+ set_fsync_mark(page, 0);
+ set_dentry_mark(page, 0);
if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
unlock_page(page);
@@ -1397,7 +1559,8 @@ static int f2fs_write_node_page(struct page *page,
struct f2fs_io_info fio = {
.sbi = sbi,
.type = NODE,
- .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+ .op = REQ_OP_WRITE,
+ .op_flags = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : 0,
.page = page,
.encrypted_page = NULL,
};
@@ -1457,6 +1620,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
+ struct blk_plug plug;
long diff;
/* balancing f2fs's metadata in background */
@@ -1470,7 +1634,9 @@ static int f2fs_write_node_pages(struct address_space *mapping,
diff = nr_pages_to_write(sbi, NODE, wbc);
wbc->sync_mode = WB_SYNC_NONE;
- sync_node_pages(sbi, 0, wbc);
+ blk_start_plug(&plug);
+ sync_node_pages(sbi, wbc);
+ blk_finish_plug(&plug);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
return 0;
@@ -1484,9 +1650,10 @@ static int f2fs_set_node_page_dirty(struct page *page)
{
trace_f2fs_set_page_dirty(page, NODE);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
if (!PageDirty(page)) {
- __set_page_dirty_nobuffers(page);
+ f2fs_set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
SetPagePrivate(page);
f2fs_trace_pid(page);
@@ -1524,7 +1691,6 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
struct nat_entry *ne;
- bool allocated = false;
if (!available_free_memory(sbi, FREE_NIDS))
return -1;
@@ -1538,8 +1704,6 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
ne = __lookup_nat_cache(nm_i, nid);
if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
nat_get_blkaddr(ne) != NULL_ADDR))
- allocated = true;
- if (allocated)
return 0;
}
@@ -1608,7 +1772,7 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
}
}
-static void build_free_nids(struct f2fs_sb_info *sbi)
+void build_free_nids(struct f2fs_sb_info *sbi)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -1617,14 +1781,14 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
nid_t nid = nm_i->next_scan_nid;
/* Enough entries */
- if (nm_i->fcnt > NAT_ENTRY_PER_BLOCK)
+ if (nm_i->fcnt >= NAT_ENTRY_PER_BLOCK)
return;
/* readahead nat pages to be scanned */
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
- down_read(&nm_i->nat_tree_lock);
+ percpu_down_read(&nm_i->nat_tree_lock);
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
@@ -1656,7 +1820,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
remove_free_nid(nm_i, nid);
}
up_read(&curseg->journal_rwsem);
- up_read(&nm_i->nat_tree_lock);
+ percpu_up_read(&nm_i->nat_tree_lock);
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
nm_i->ra_nid_pages, META_NAT, false);
@@ -1672,6 +1836,10 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i = NULL;
retry:
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(FAULT_ALLOC_NID))
+ return false;
+#endif
if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
return false;
@@ -1751,12 +1919,15 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
struct free_nid *i, *next;
int nr = nr_shrink;
+ if (nm_i->fcnt <= MAX_FREE_NIDS)
+ return 0;
+
if (!mutex_trylock(&nm_i->build_lock))
return 0;
spin_lock(&nm_i->free_nid_list_lock);
list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) {
- if (nr_shrink <= 0 || nm_i->fcnt <= NAT_ENTRY_PER_BLOCK)
+ if (nr_shrink <= 0 || nm_i->fcnt <= MAX_FREE_NIDS)
break;
if (i->state == NID_ALLOC)
continue;
@@ -1783,7 +1954,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
ri = F2FS_INODE(page);
if (!(ri->i_inline & F2FS_INLINE_XATTR)) {
- clear_inode_flag(F2FS_I(inode), FI_INLINE_XATTR);
+ clear_inode_flag(inode, FI_INLINE_XATTR);
goto update_inode;
}
@@ -1825,13 +1996,11 @@ recover_xnid:
get_node_info(sbi, new_xnid, &ni);
ni.ino = inode->i_ino;
set_node_addr(sbi, &ni, NEW_ADDR, false);
- F2FS_I(inode)->i_xattr_nid = new_xnid;
+ f2fs_i_xnid_write(inode, new_xnid);
/* 3: update xattr blkaddr */
refresh_sit_entry(sbi, NEW_ADDR, blkaddr);
set_node_addr(sbi, &ni, blkaddr, false);
-
- update_inode_page(inode);
}
int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -1846,14 +2015,15 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
if (unlikely(old_ni.blk_addr != NULL_ADDR))
return -EINVAL;
- ipage = grab_cache_page(NODE_MAPPING(sbi), ino);
+ ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false);
if (!ipage)
return -ENOMEM;
/* Should not use this inode from free nid list */
remove_free_nid(NM_I(sbi), ino);
- SetPageUptodate(ipage);
+ if (!PageUptodate(ipage))
+ SetPageUptodate(ipage);
fill_node_footer(ipage, ino, ino, 0, true);
src = F2FS_INODE(page);
@@ -2039,7 +2209,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
if (!nm_i->dirty_nat_cnt)
return;
- down_write(&nm_i->nat_tree_lock);
+ percpu_down_write(&nm_i->nat_tree_lock);
/*
* if there are no enough space in journal to store dirty nat
@@ -2062,7 +2232,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
list_for_each_entry_safe(set, tmp, &sets, set_list)
__flush_nat_entry_set(sbi, set);
- up_write(&nm_i->nat_tree_lock);
+ percpu_up_write(&nm_i->nat_tree_lock);
f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
}
@@ -2098,7 +2268,8 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
mutex_init(&nm_i->build_lock);
spin_lock_init(&nm_i->free_nid_list_lock);
- init_rwsem(&nm_i->nat_tree_lock);
+ if (percpu_init_rwsem(&nm_i->nat_tree_lock))
+ return -ENOMEM;
nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
@@ -2155,7 +2326,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
spin_unlock(&nm_i->free_nid_list_lock);
/* destroy nat cache */
- down_write(&nm_i->nat_tree_lock);
+ percpu_down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_cache(nm_i,
nid, NATVEC_SIZE, natvec))) {
unsigned idx;
@@ -2180,8 +2351,9 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
kmem_cache_free(nat_entry_set_slab, setvec[idx]);
}
}
- up_write(&nm_i->nat_tree_lock);
+ percpu_up_write(&nm_i->nat_tree_lock);
+ percpu_free_rwsem(&nm_i->nat_tree_lock);
kfree(nm_i->nat_bitmap);
sbi->nm_info = NULL;
kfree(nm_i);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 1f4f9d4569d9..fc7684554b1a 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -15,18 +15,21 @@
#define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
/* # of pages to perform synchronous readahead before building free nids */
-#define FREE_NID_PAGES 4
+#define FREE_NID_PAGES 8
+#define MAX_FREE_NIDS (NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES)
-#define DEF_RA_NID_PAGES 4 /* # of nid pages to be readaheaded */
+#define DEF_RA_NID_PAGES 0 /* # of nid pages to be readaheaded */
/* maximum readahead size for node during getting data blocks */
#define MAX_RA_NODE 128
/* control the memory footprint threshold (10MB per 1GB ram) */
-#define DEF_RAM_THRESHOLD 10
+#define DEF_RAM_THRESHOLD 1
/* control dirty nats ratio threshold (default: 10% over max nid count) */
#define DEF_DIRTY_NAT_RATIO_THRESHOLD 10
+/* control total # of nats */
+#define DEF_NAT_CACHE_THRESHOLD 100000
/* vector size for gang look-up from nat cache that consists of radix tree */
#define NATVEC_SIZE 64
@@ -126,6 +129,11 @@ static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
NM_I(sbi)->dirty_nats_ratio / 100;
}
+static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
+{
+ return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD;
+}
+
enum mem_type {
FREE_NIDS, /* indicates the free nid list */
NAT_ENTRIES, /* indicates the cached nat entry */
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 0b30cd2aeebd..9e652d5a659b 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -49,8 +49,9 @@ static struct kmem_cache *fsync_entry_slab;
bool space_for_roll_forward(struct f2fs_sb_info *sbi)
{
- if (sbi->last_valid_block_count + sbi->alloc_valid_block_count
- > sbi->user_block_count)
+ s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
+
+ if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
return false;
return true;
}
@@ -67,7 +68,30 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
return NULL;
}
-static int recover_dentry(struct inode *inode, struct page *ipage)
+static struct fsync_inode_entry *add_fsync_inode(struct list_head *head,
+ struct inode *inode)
+{
+ struct fsync_inode_entry *entry;
+
+ entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+ if (!entry)
+ return NULL;
+
+ entry->inode = inode;
+ list_add_tail(&entry->list, head);
+
+ return entry;
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry)
+{
+ iput(entry->inode);
+ list_del(&entry->list);
+ kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int recover_dentry(struct inode *inode, struct page *ipage,
+ struct list_head *dir_list)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
@@ -75,18 +99,29 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
struct qstr name;
struct page *page;
struct inode *dir, *einode;
+ struct fsync_inode_entry *entry;
int err = 0;
- dir = f2fs_iget(inode->i_sb, pino);
- if (IS_ERR(dir)) {
- err = PTR_ERR(dir);
- goto out;
+ entry = get_fsync_inode(dir_list, pino);
+ if (!entry) {
+ dir = f2fs_iget(inode->i_sb, pino);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto out;
+ }
+
+ entry = add_fsync_inode(dir_list, dir);
+ if (!entry) {
+ err = -ENOMEM;
+ iput(dir);
+ goto out;
+ }
}
- if (file_enc_name(inode)) {
- iput(dir);
+ dir = entry->inode;
+
+ if (file_enc_name(inode))
return 0;
- }
name.len = le32_to_cpu(raw_inode->i_namelen);
name.name = raw_inode->i_name;
@@ -94,7 +129,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
if (unlikely(name.len > F2FS_NAME_LEN)) {
WARN_ON(1);
err = -ENAMETOOLONG;
- goto out_err;
+ goto out;
}
retry:
de = f2fs_find_entry(dir, &name, &page);
@@ -118,25 +153,17 @@ retry:
f2fs_delete_entry(de, page, dir, einode);
iput(einode);
goto retry;
- }
- err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
- if (err)
- goto out_err;
-
- if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
- iput(dir);
+ } else if (IS_ERR(page)) {
+ err = PTR_ERR(page);
} else {
- add_dirty_dir_inode(dir);
- set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
+ err = __f2fs_add_link(dir, &name, inode,
+ inode->i_ino, inode->i_mode);
}
-
goto out;
out_unmap_put:
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
-out_err:
- iput(dir);
out:
f2fs_msg(inode->i_sb, KERN_NOTICE,
"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -151,7 +178,7 @@ static void recover_inode(struct inode *inode, struct page *page)
char *name;
inode->i_mode = le16_to_cpu(raw->i_mode);
- i_size_write(inode, le64_to_cpu(raw->i_size));
+ f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
@@ -198,6 +225,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
+ struct inode *inode;
struct page *page = NULL;
block_t blkaddr;
int err = 0;
@@ -206,8 +234,6 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- ra_meta_pages(sbi, blkaddr, 1, META_POR, true);
-
while (1) {
struct fsync_inode_entry *entry;
@@ -233,35 +259,32 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
break;
}
- /* add this fsync inode to the list */
- entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
- if (!entry) {
- err = -ENOMEM;
- break;
- }
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
- entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
- if (IS_ERR(entry->inode)) {
- err = PTR_ERR(entry->inode);
- kmem_cache_free(fsync_entry_slab, entry);
+ inode = f2fs_iget(sbi->sb, ino_of_node(page));
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
if (err == -ENOENT) {
err = 0;
goto next;
}
break;
}
- list_add_tail(&entry->list, head);
+
+ /* add this fsync inode to the list */
+ entry = add_fsync_inode(head, inode);
+ if (!entry) {
+ err = -ENOMEM;
+ iput(inode);
+ break;
+ }
}
entry->blkaddr = blkaddr;
- if (IS_INODE(page)) {
- entry->last_inode = blkaddr;
- if (is_dent_dnode(page))
- entry->last_dentry = blkaddr;
- }
+ if (IS_INODE(page) && is_dent_dnode(page))
+ entry->last_dentry = blkaddr;
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
@@ -277,11 +300,8 @@ static void destroy_fsync_dnodes(struct list_head *head)
{
struct fsync_inode_entry *entry, *tmp;
- list_for_each_entry_safe(entry, tmp, head, list) {
- iput(entry->inode);
- list_del(&entry->list);
- kmem_cache_free(fsync_entry_slab, entry);
- }
+ list_for_each_entry_safe(entry, tmp, head, list)
+ del_fsync_inode(entry);
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -438,14 +458,16 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
continue;
}
+ if ((start + 1) << PAGE_SHIFT > i_size_read(inode))
+ f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT);
+
/*
* dest is reserved block, invalidate src block
* and then reserve one new block in dnode page.
*/
if (dest == NEW_ADDR) {
truncate_data_blocks_range(&dn, 1);
- err = reserve_new_block(&dn);
- f2fs_bug_on(sbi, err);
+ reserve_new_block(&dn);
continue;
}
@@ -454,8 +476,14 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ while (err)
+ err = reserve_new_block(&dn);
+#endif
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
+ if (err)
+ goto err;
}
/* Check the previous node page having this index */
@@ -470,9 +498,6 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
}
}
- if (IS_INODE(dn.node_page))
- sync_inode_page(&dn);
-
copy_node_footer(dn.node_page, page);
fill_node_footer(dn.node_page, dn.nid, ni.ino,
ofs_of_node(page), false);
@@ -486,7 +511,8 @@ out:
return err;
}
-static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+ struct list_head *dir_list)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
@@ -513,7 +539,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
break;
}
- entry = get_fsync_inode(head, ino_of_node(page));
+ entry = get_fsync_inode(inode_list, ino_of_node(page));
if (!entry)
goto next;
/*
@@ -521,10 +547,10 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
* In this case, we can lose the latest inode(x).
* So, call recover_inode for the inode update.
*/
- if (entry->last_inode == blkaddr)
+ if (IS_INODE(page))
recover_inode(entry->inode, page);
if (entry->last_dentry == blkaddr) {
- err = recover_dentry(entry->inode, page);
+ err = recover_dentry(entry->inode, page, dir_list);
if (err) {
f2fs_put_page(page, 1);
break;
@@ -536,11 +562,8 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
break;
}
- if (entry->blkaddr == blkaddr) {
- iput(entry->inode);
- list_del(&entry->list);
- kmem_cache_free(fsync_entry_slab, entry);
- }
+ if (entry->blkaddr == blkaddr)
+ del_fsync_inode(entry);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
@@ -551,12 +574,14 @@ next:
return err;
}
-int recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct list_head inode_list;
+ struct list_head dir_list;
block_t blkaddr;
int err;
+ int ret = 0;
bool need_writecp = false;
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -565,6 +590,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
return -ENOMEM;
INIT_LIST_HEAD(&inode_list);
+ INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
@@ -573,25 +599,26 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
/* step #1: find fsynced inode numbers */
err = find_fsync_dnodes(sbi, &inode_list);
- if (err)
+ if (err || list_empty(&inode_list))
goto out;
- if (list_empty(&inode_list))
+ if (check_only) {
+ ret = 1;
goto out;
+ }
need_writecp = true;
/* step #2: recover data */
- err = recover_data(sbi, &inode_list);
+ err = recover_data(sbi, &inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
out:
destroy_fsync_dnodes(&inode_list);
- kmem_cache_destroy(fsync_entry_slab);
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
- (loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
+ (loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1);
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
@@ -602,8 +629,12 @@ out:
if (err) {
bool invalidate = false;
- if (discard_next_dnode(sbi, blkaddr))
+ if (test_opt(sbi, LFS)) {
+ update_meta_page(sbi, NULL, blkaddr);
+ invalidate = true;
+ } else if (discard_next_dnode(sbi, blkaddr)) {
invalidate = true;
+ }
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META))
@@ -625,5 +656,8 @@ out:
} else {
mutex_unlock(&sbi->cp_mutex);
}
- return err;
+
+ destroy_fsync_dnodes(&dir_list);
+ kmem_cache_destroy(fsync_entry_slab);
+ return ret ? ret: err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 6f16b39f0b52..a46296f57b02 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -223,9 +223,11 @@ static int __revoke_inmem_pages(struct inode *inode,
f2fs_put_dnode(&dn);
}
next:
- ClearPageUptodate(page);
+ /* we don't need to invalidate this in the sccessful status */
+ if (drop || recover)
+ ClearPageUptodate(page);
set_page_private(page, 0);
- ClearPageUptodate(page);
+ ClearPagePrivate(page);
f2fs_put_page(page, 1);
list_del(&cur->list);
@@ -239,6 +241,8 @@ void drop_inmem_pages(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+
mutex_lock(&fi->inmem_lock);
__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
mutex_unlock(&fi->inmem_lock);
@@ -253,7 +257,8 @@ static int __commit_inmem_pages(struct inode *inode,
struct f2fs_io_info fio = {
.sbi = sbi,
.type = DATA,
- .rw = WRITE_SYNC | REQ_PRIO,
+ .op = REQ_OP_WRITE,
+ .op_flags = WRITE_SYNC | REQ_PRIO,
.encrypted_page = NULL,
};
bool submit_bio = false;
@@ -341,6 +346,11 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
if (!need)
return;
+
+ /* balance_fs_bg is able to be pending */
+ if (excess_cached_nats(sbi))
+ f2fs_balance_fs_bg(sbi);
+
/*
* We should do GC or end up with checkpoint, if there are so many dirty
* dir/node pages without enough free segments.
@@ -362,7 +372,9 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
if (!available_free_memory(sbi, FREE_NIDS))
- try_to_free_nids(sbi, NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES);
+ try_to_free_nids(sbi, MAX_FREE_NIDS);
+ else
+ build_free_nids(sbi);
/* checkpoint is the only way to shrink partial cached entries */
if (!available_free_memory(sbi, NAT_ENTRIES) ||
@@ -402,7 +414,8 @@ repeat:
fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
bio->bi_bdev = sbi->sb->s_bdev;
- ret = submit_bio_wait(WRITE_FLUSH, bio);
+ bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+ ret = submit_bio_wait(bio);
llist_for_each_entry_safe(cmd, next,
fcc->dispatch_list, llnode) {
@@ -429,24 +442,29 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
if (test_opt(sbi, NOBARRIER))
return 0;
- if (!test_opt(sbi, FLUSH_MERGE)) {
+ if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
struct bio *bio = f2fs_bio_alloc(0);
int ret;
+ atomic_inc(&fcc->submit_flush);
bio->bi_bdev = sbi->sb->s_bdev;
- ret = submit_bio_wait(WRITE_FLUSH, bio);
+ bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
+ ret = submit_bio_wait(bio);
+ atomic_dec(&fcc->submit_flush);
bio_put(bio);
return ret;
}
init_completion(&cmd.wait);
+ atomic_inc(&fcc->submit_flush);
llist_add(&cmd.llnode, &fcc->issue_list);
if (!fcc->dispatch_list)
wake_up(&fcc->flush_wait_queue);
wait_for_completion(&cmd.wait);
+ atomic_dec(&fcc->submit_flush);
return cmd.ret;
}
@@ -460,6 +478,7 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
if (!fcc)
return -ENOMEM;
+ atomic_set(&fcc->submit_flush, 0);
init_waitqueue_head(&fcc->flush_wait_queue);
init_llist_head(&fcc->issue_list);
SM_I(sbi)->cmd_control_info = fcc;
@@ -661,6 +680,10 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
break;
end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
+ if (force && start && end != max_blocks
+ && (end - start) < cpc->trim_minlen)
+ continue;
+
__add_discard_entry(sbi, cpc, se, start, end);
}
}
@@ -698,6 +721,8 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
unsigned int start = 0, end = -1;
+ unsigned int secno, start_segno;
+ bool force = (cpc->reason == CP_DISCARD);
mutex_lock(&dirty_i->seglist_lock);
@@ -714,17 +739,31 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
dirty_i->nr_dirty[PRE] -= end - start;
- if (!test_opt(sbi, DISCARD))
+ if (force || !test_opt(sbi, DISCARD))
continue;
- f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
+ if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
+ f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
(end - start) << sbi->log_blocks_per_seg);
+ continue;
+ }
+next:
+ secno = GET_SECNO(sbi, start);
+ start_segno = secno * sbi->segs_per_sec;
+ if (!IS_CURSEC(sbi, secno) &&
+ !get_valid_blocks(sbi, start, sbi->segs_per_sec))
+ f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
+ sbi->segs_per_sec << sbi->log_blocks_per_seg);
+
+ start = start_segno + sbi->segs_per_sec;
+ if (start < end)
+ goto next;
}
mutex_unlock(&dirty_i->seglist_lock);
/* send small discards */
list_for_each_entry_safe(entry, this, head, list) {
- if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen)
+ if (force && entry->len < cpc->trim_minlen)
goto skip;
f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
cpc->trimmed += entry->len;
@@ -885,12 +924,12 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
}
}
- sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
+ sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE -
SUM_FOOTER_SIZE) / SUMMARY_SIZE;
if (valid_sum_count <= sum_in_page)
return 1;
else if ((valid_sum_count - sum_in_page) <=
- (PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
+ (PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
return 2;
return 3;
}
@@ -909,9 +948,9 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
void *dst = page_address(page);
if (src)
- memcpy(dst, src, PAGE_CACHE_SIZE);
+ memcpy(dst, src, PAGE_SIZE);
else
- memset(dst, 0, PAGE_CACHE_SIZE);
+ memset(dst, 0, PAGE_SIZE);
set_page_dirty(page);
f2fs_put_page(page, 1);
}
@@ -1212,6 +1251,9 @@ void allocate_new_segments(struct f2fs_sb_info *sbi)
{
int i;
+ if (test_opt(sbi, LFS))
+ return;
+
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
__allocate_new_segments(sbi, i);
}
@@ -1385,11 +1427,17 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
{
int type = __get_segment_type(fio->page, fio->type);
+ if (fio->type == NODE || fio->type == DATA)
+ mutex_lock(&fio->sbi->wio_mutex[fio->type]);
+
allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
&fio->new_blkaddr, sum, type);
/* writeout dirty page into bdev */
f2fs_submit_page_mbio(fio);
+
+ if (fio->type == NODE || fio->type == DATA)
+ mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
}
void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -1397,7 +1445,8 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
- .rw = WRITE_SYNC | REQ_META | REQ_PRIO,
+ .op = REQ_OP_WRITE,
+ .op_flags = WRITE_SYNC | REQ_META | REQ_PRIO,
.old_blkaddr = page->index,
.new_blkaddr = page->index,
.page = page,
@@ -1405,7 +1454,7 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
};
if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
- fio.rw &= ~REQ_META;
+ fio.op_flags &= ~REQ_META;
set_page_writeback(page);
f2fs_submit_page_mbio(&fio);
@@ -1596,7 +1645,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
s = (struct f2fs_summary *)(kaddr + offset);
seg_i->sum_blk->entries[j] = *s;
offset += SUMMARY_SIZE;
- if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+ if (offset + SUMMARY_SIZE <= PAGE_SIZE -
SUM_FOOTER_SIZE)
continue;
@@ -1757,7 +1806,7 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
*summary = seg_i->sum_blk->entries[j];
written_size += SUMMARY_SIZE;
- if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+ if (written_size + SUMMARY_SIZE <= PAGE_SIZE -
SUM_FOOTER_SIZE)
continue;
@@ -1844,7 +1893,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
- memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
+ memcpy(dst_addr, src_addr, PAGE_SIZE);
set_page_dirty(dst_page);
f2fs_put_page(src_page, 1);
@@ -2171,7 +2220,7 @@ static int build_curseg(struct f2fs_sb_info *sbi)
for (i = 0; i < NR_CURSEG_TYPE; i++) {
mutex_init(&array[i].curseg_mutex);
- array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+ array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL);
if (!array[i].sum_blk)
return -ENOMEM;
init_rwsem(&array[i].journal_rwsem);
@@ -2369,7 +2418,11 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
sm_info->rec_prefree_segments = sm_info->main_segments *
DEF_RECLAIM_PREFREE_SEGMENTS / 100;
- sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
+ if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS)
+ sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS;
+
+ if (!test_opt(sbi, LFS))
+ sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 975c33df65c7..b33f73ec60a4 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -16,6 +16,7 @@
#define NULL_SECNO ((unsigned int)(~0))
#define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */
+#define DEF_MAX_RECLAIM_PREFREE_SEGMENTS 4096 /* 8GB in maximum */
/* L: Logical segment # in volume, R: Relative segment # in main area */
#define GET_L2R_SEGNO(free_i, segno) (segno - free_i->start_segno)
@@ -158,16 +159,17 @@ struct victim_sel_policy {
};
struct seg_entry {
- unsigned short valid_blocks; /* # of valid blocks */
+ unsigned int type:6; /* segment type like CURSEG_XXX_TYPE */
+ unsigned int valid_blocks:10; /* # of valid blocks */
+ unsigned int ckpt_valid_blocks:10; /* # of valid blocks last cp */
+ unsigned int padding:6; /* padding */
unsigned char *cur_valid_map; /* validity bitmap of blocks */
/*
* # of valid blocks and the validity bitmap stored in the the last
* checkpoint pack. This information is used by the SSR mode.
*/
- unsigned short ckpt_valid_blocks;
- unsigned char *ckpt_valid_map;
+ unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */
unsigned char *discard_map;
- unsigned char type; /* segment type like CURSEG_XXX_TYPE */
unsigned long long mtime; /* modification time of the segment */
};
@@ -469,6 +471,10 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi)
{
int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+
+ if (test_opt(sbi, LFS))
+ return false;
+
return free_sections(sbi) <= (node_secs + 2 * dent_secs +
reserved_sections(sbi) + 1);
}
@@ -478,6 +484,8 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+ node_secs += get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
return false;
@@ -530,6 +538,9 @@ static inline bool need_inplace_update(struct inode *inode)
if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
return false;
+ if (test_opt(sbi, LFS))
+ return false;
+
if (policy & (0x1 << F2FS_IPU_FORCE))
return true;
if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
@@ -543,7 +554,7 @@ static inline bool need_inplace_update(struct inode *inode)
/* this is only set during fdatasync */
if (policy & (0x1 << F2FS_IPU_FSYNC) &&
- is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
+ is_inode_flag_set(inode, FI_NEED_IPU))
return true;
return false;
@@ -705,9 +716,9 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
if (type == DATA)
return sbi->blocks_per_seg;
else if (type == NODE)
- return 3 * sbi->blocks_per_seg;
+ return 8 * sbi->blocks_per_seg;
else if (type == META)
- return MAX_BIO_BLOCKS(sbi);
+ return 8 * MAX_BIO_BLOCKS(sbi);
else
return 0;
}
@@ -725,10 +736,8 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
nr_to_write = wbc->nr_to_write;
- if (type == DATA)
- desired = 4096;
- else if (type == NODE)
- desired = 3 * max_hw_blocks(sbi);
+ if (type == NODE)
+ desired = 2 * max_hw_blocks(sbi);
else
desired = MAX_BIO_BLOCKS(sbi);
diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
index 93606f281bf9..46c915425923 100644
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -13,6 +13,7 @@
#include <linux/f2fs_fs.h>
#include "f2fs.h"
+#include "node.h"
static LIST_HEAD(f2fs_list);
static DEFINE_SPINLOCK(f2fs_list_lock);
@@ -25,8 +26,8 @@ static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
{
- if (NM_I(sbi)->fcnt > NAT_ENTRY_PER_BLOCK)
- return NM_I(sbi)->fcnt - NAT_ENTRY_PER_BLOCK;
+ if (NM_I(sbi)->fcnt > MAX_FREE_NIDS)
+ return NM_I(sbi)->fcnt - MAX_FREE_NIDS;
return 0;
}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 15bb81f8dac2..1b86d3f638ef 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -39,6 +39,31 @@ static struct proc_dir_entry *f2fs_proc_root;
static struct kmem_cache *f2fs_inode_cachep;
static struct kset *f2fs_kset;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+struct f2fs_fault_info f2fs_fault;
+
+char *fault_name[FAULT_MAX] = {
+ [FAULT_KMALLOC] = "kmalloc",
+ [FAULT_PAGE_ALLOC] = "page alloc",
+ [FAULT_ALLOC_NID] = "alloc nid",
+ [FAULT_ORPHAN] = "orphan",
+ [FAULT_BLOCK] = "no more block",
+ [FAULT_DIR_DEPTH] = "too big dir depth",
+ [FAULT_EVICT_INODE] = "evict_inode fail",
+};
+
+static void f2fs_build_fault_attr(unsigned int rate)
+{
+ if (rate) {
+ atomic_set(&f2fs_fault.inject_ops, 0);
+ f2fs_fault.inject_rate = rate;
+ f2fs_fault.inject_type = (1 << FAULT_MAX) - 1;
+ } else {
+ memset(&f2fs_fault, 0, sizeof(struct f2fs_fault_info));
+ }
+}
+#endif
+
/* f2fs-wide shrinker description */
static struct shrinker f2fs_shrinker_info = {
.scan_objects = f2fs_shrink_scan,
@@ -51,6 +76,7 @@ enum {
Opt_disable_roll_forward,
Opt_norecovery,
Opt_discard,
+ Opt_nodiscard,
Opt_noheap,
Opt_user_xattr,
Opt_nouser_xattr,
@@ -62,12 +88,17 @@ enum {
Opt_inline_data,
Opt_inline_dentry,
Opt_flush_merge,
+ Opt_noflush_merge,
Opt_nobarrier,
Opt_fastboot,
Opt_extent_cache,
Opt_noextent_cache,
Opt_noinline_data,
Opt_data_flush,
+ Opt_mode,
+ Opt_fault_injection,
+ Opt_lazytime,
+ Opt_nolazytime,
Opt_err,
};
@@ -76,6 +107,7 @@ static match_table_t f2fs_tokens = {
{Opt_disable_roll_forward, "disable_roll_forward"},
{Opt_norecovery, "norecovery"},
{Opt_discard, "discard"},
+ {Opt_nodiscard, "nodiscard"},
{Opt_noheap, "no_heap"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
@@ -87,12 +119,17 @@ static match_table_t f2fs_tokens = {
{Opt_inline_data, "inline_data"},
{Opt_inline_dentry, "inline_dentry"},
{Opt_flush_merge, "flush_merge"},
+ {Opt_noflush_merge, "noflush_merge"},
{Opt_nobarrier, "nobarrier"},
{Opt_fastboot, "fastboot"},
{Opt_extent_cache, "extent_cache"},
{Opt_noextent_cache, "noextent_cache"},
{Opt_noinline_data, "noinline_data"},
{Opt_data_flush, "data_flush"},
+ {Opt_mode, "mode=%s"},
+ {Opt_fault_injection, "fault_injection=%u"},
+ {Opt_lazytime, "lazytime"},
+ {Opt_nolazytime, "nolazytime"},
{Opt_err, NULL},
};
@@ -102,6 +139,10 @@ enum {
SM_INFO, /* struct f2fs_sm_info */
NM_INFO, /* struct f2fs_nm_info */
F2FS_SBI, /* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ FAULT_INFO_RATE, /* struct f2fs_fault_info */
+ FAULT_INFO_TYPE, /* struct f2fs_fault_info */
+#endif
};
struct f2fs_attr {
@@ -123,6 +164,11 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
return (unsigned char *)NM_I(sbi);
else if (struct_type == F2FS_SBI)
return (unsigned char *)sbi;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ else if (struct_type == FAULT_INFO_RATE ||
+ struct_type == FAULT_INFO_TYPE)
+ return (unsigned char *)&f2fs_fault;
+#endif
return NULL;
}
@@ -172,6 +218,10 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret < 0)
return ret;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
+ return -EINVAL;
+#endif
*ui = t;
return count;
}
@@ -237,6 +287,10 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
+F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
+#endif
F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
@@ -273,6 +327,22 @@ static struct kobj_type f2fs_ktype = {
.release = f2fs_sb_release,
};
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+/* sysfs for f2fs fault injection */
+static struct kobject f2fs_fault_inject;
+
+static struct attribute *f2fs_fault_attrs[] = {
+ ATTR_LIST(inject_rate),
+ ATTR_LIST(inject_type),
+ NULL
+};
+
+static struct kobj_type f2fs_fault_ktype = {
+ .default_attrs = f2fs_fault_attrs,
+ .sysfs_ops = &f2fs_attr_ops,
+};
+#endif
+
void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
{
struct va_format vaf;
@@ -300,6 +370,10 @@ static int parse_options(struct super_block *sb, char *options)
char *p, *name;
int arg = 0;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ f2fs_build_fault_attr(0);
+#endif
+
if (!options)
return 0;
@@ -354,6 +428,8 @@ static int parse_options(struct super_block *sb, char *options)
"the device does not support discard");
}
break;
+ case Opt_nodiscard:
+ clear_opt(sbi, DISCARD);
case Opt_noheap:
set_opt(sbi, NOHEAP);
break;
@@ -415,6 +491,9 @@ static int parse_options(struct super_block *sb, char *options)
case Opt_flush_merge:
set_opt(sbi, FLUSH_MERGE);
break;
+ case Opt_noflush_merge:
+ clear_opt(sbi, FLUSH_MERGE);
+ break;
case Opt_nobarrier:
set_opt(sbi, NOBARRIER);
break;
@@ -433,6 +512,39 @@ static int parse_options(struct super_block *sb, char *options)
case Opt_data_flush:
set_opt(sbi, DATA_FLUSH);
break;
+ case Opt_mode:
+ name = match_strdup(&args[0]);
+
+ if (!name)
+ return -ENOMEM;
+ if (strlen(name) == 8 &&
+ !strncmp(name, "adaptive", 8)) {
+ set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
+ } else if (strlen(name) == 3 &&
+ !strncmp(name, "lfs", 3)) {
+ set_opt_mode(sbi, F2FS_MOUNT_LFS);
+ } else {
+ kfree(name);
+ return -EINVAL;
+ }
+ kfree(name);
+ break;
+ case Opt_fault_injection:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ f2fs_build_fault_attr(arg);
+#else
+ f2fs_msg(sb, KERN_INFO,
+ "FAULT_INJECTION was not selected");
+#endif
+ break;
+ case Opt_lazytime:
+ sb->s_flags |= MS_LAZYTIME;
+ break;
+ case Opt_nolazytime:
+ sb->s_flags &= ~MS_LAZYTIME;
+ break;
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
@@ -453,20 +565,22 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
init_once((void *) fi);
+ if (percpu_counter_init(&fi->dirty_pages, 0, GFP_NOFS)) {
+ kmem_cache_free(f2fs_inode_cachep, fi);
+ return NULL;
+ }
+
/* Initialize f2fs-specific inode info */
fi->vfs_inode.i_version = 1;
- atomic_set(&fi->dirty_pages, 0);
fi->i_current_depth = 1;
fi->i_advise = 0;
init_rwsem(&fi->i_sem);
INIT_LIST_HEAD(&fi->dirty_list);
+ INIT_LIST_HEAD(&fi->gdirty_list);
INIT_LIST_HEAD(&fi->inmem_pages);
mutex_init(&fi->inmem_lock);
-
- set_inode_flag(fi, FI_NEW_INODE);
-
- if (test_opt(F2FS_SB(sb), INLINE_XATTR))
- set_inode_flag(fi, FI_INLINE_XATTR);
+ init_rwsem(&fi->dio_rwsem[READ]);
+ init_rwsem(&fi->dio_rwsem[WRITE]);
/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
@@ -482,7 +596,7 @@ static int f2fs_drop_inode(struct inode *inode)
* - f2fs_gc -> iput -> evict
* - inode_wait_for_writeback(inode)
*/
- if (!inode_unhashed(inode) && inode->i_state & I_SYNC) {
+ if ((!inode_unhashed(inode) && inode->i_state & I_SYNC)) {
if (!inode->i_nlink && !is_bad_inode(inode)) {
/* to avoid evict_inode call simultaneously */
atomic_inc(&inode->i_count);
@@ -496,10 +610,10 @@ static int f2fs_drop_inode(struct inode *inode)
f2fs_destroy_extent_node(inode);
sb_start_intwrite(inode->i_sb);
- i_size_write(inode, 0);
+ f2fs_i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
- f2fs_truncate(inode, true);
+ f2fs_truncate(inode);
sb_end_intwrite(inode->i_sb);
@@ -509,9 +623,47 @@ static int f2fs_drop_inode(struct inode *inode)
}
return 0;
}
+
return generic_drop_inode(inode);
}
+int f2fs_inode_dirtied(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ spin_lock(&sbi->inode_lock[DIRTY_META]);
+ if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ return 1;
+ }
+
+ set_inode_flag(inode, FI_DIRTY_INODE);
+ list_add_tail(&F2FS_I(inode)->gdirty_list,
+ &sbi->inode_list[DIRTY_META]);
+ inc_page_count(sbi, F2FS_DIRTY_IMETA);
+ stat_inc_dirty_inode(sbi, DIRTY_META);
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+
+ return 0;
+}
+
+void f2fs_inode_synced(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ spin_lock(&sbi->inode_lock[DIRTY_META]);
+ if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ return;
+ }
+ list_del_init(&F2FS_I(inode)->gdirty_list);
+ clear_inode_flag(inode, FI_DIRTY_INODE);
+ clear_inode_flag(inode, FI_AUTO_RECOVER);
+ dec_page_count(sbi, F2FS_DIRTY_IMETA);
+ stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META);
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+}
+
/*
* f2fs_dirty_inode() is called from __mark_inode_dirty()
*
@@ -519,7 +671,19 @@ static int f2fs_drop_inode(struct inode *inode)
*/
static void f2fs_dirty_inode(struct inode *inode, int flags)
{
- set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ if (inode->i_ino == F2FS_NODE_INO(sbi) ||
+ inode->i_ino == F2FS_META_INO(sbi))
+ return;
+
+ if (flags == I_DIRTY_TIME)
+ return;
+
+ if (is_inode_flag_set(inode, FI_AUTO_RECOVER))
+ clear_inode_flag(inode, FI_AUTO_RECOVER);
+
+ f2fs_inode_dirtied(inode);
}
static void f2fs_i_callback(struct rcu_head *head)
@@ -530,15 +694,29 @@ static void f2fs_i_callback(struct rcu_head *head)
static void f2fs_destroy_inode(struct inode *inode)
{
+ percpu_counter_destroy(&F2FS_I(inode)->dirty_pages);
call_rcu(&inode->i_rcu, f2fs_i_callback);
}
+static void destroy_percpu_info(struct f2fs_sb_info *sbi)
+{
+ int i;
+
+ for (i = 0; i < NR_COUNT_TYPE; i++)
+ percpu_counter_destroy(&sbi->nr_pages[i]);
+ percpu_counter_destroy(&sbi->alloc_valid_block_count);
+ percpu_counter_destroy(&sbi->total_valid_inode_count);
+
+ percpu_free_rwsem(&sbi->cp_rwsem);
+}
+
static void f2fs_put_super(struct super_block *sb)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
+ remove_proc_entry("segment_bits", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
kobject_del(&sbi->s_kobj);
@@ -568,15 +746,14 @@ static void f2fs_put_super(struct super_block *sb)
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
*/
- release_ino_entry(sbi);
+ release_ino_entry(sbi, true);
release_discard_addrs(sbi);
f2fs_leave_shrinker(sbi);
mutex_unlock(&sbi->umount_mutex);
/* our cp_error case, we can wait for any writeback page */
- if (get_pages(sbi, F2FS_WRITEBACK))
- f2fs_flush_merged_bios(sbi);
+ f2fs_flush_merged_bios(sbi);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -593,6 +770,8 @@ static void f2fs_put_super(struct super_block *sb)
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi->raw_super);
+
+ destroy_percpu_info(sbi);
kfree(sbi);
}
@@ -648,7 +827,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_bsize = sbi->blocksize;
buf->f_blocks = total_count - start_count;
- buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
+ buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count;
buf->f_bavail = user_block_count - valid_user_blocks(sbi);
buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
@@ -713,6 +892,12 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",noextent_cache");
if (test_opt(sbi, DATA_FLUSH))
seq_puts(seq, ",data_flush");
+
+ seq_puts(seq, ",mode=");
+ if (test_opt(sbi, ADAPTIVE))
+ seq_puts(seq, "adaptive");
+ else if (test_opt(sbi, LFS))
+ seq_puts(seq, "lfs");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
return 0;
@@ -745,19 +930,46 @@ static int segment_info_seq_show(struct seq_file *seq, void *offset)
return 0;
}
-static int segment_info_open_fs(struct inode *inode, struct file *file)
+static int segment_bits_seq_show(struct seq_file *seq, void *offset)
{
- return single_open(file, segment_info_seq_show, PDE_DATA(inode));
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ unsigned int total_segs =
+ le32_to_cpu(sbi->raw_super->segment_count_main);
+ int i, j;
+
+ seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+ "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+ for (i = 0; i < total_segs; i++) {
+ struct seg_entry *se = get_seg_entry(sbi, i);
+
+ seq_printf(seq, "%-10d", i);
+ seq_printf(seq, "%d|%-3u|", se->type,
+ get_valid_blocks(sbi, i, 1));
+ for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
+ seq_printf(seq, "%x ", se->cur_valid_map[j]);
+ seq_putc(seq, '\n');
+ }
+ return 0;
}
-static const struct file_operations f2fs_seq_segment_info_fops = {
- .owner = THIS_MODULE,
- .open = segment_info_open_fs,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
+#define F2FS_PROC_FILE_DEF(_name) \
+static int _name##_open_fs(struct inode *inode, struct file *file) \
+{ \
+ return single_open(file, _name##_seq_show, PDE_DATA(inode)); \
+} \
+ \
+static const struct file_operations f2fs_seq_##_name##_fops = { \
+ .open = _name##_open_fs, \
+ .read = seq_read, \
+ .llseek = seq_lseek, \
+ .release = single_release, \
};
+F2FS_PROC_FILE_DEF(segment_info);
+F2FS_PROC_FILE_DEF(segment_bits);
+
static void default_options(struct f2fs_sb_info *sbi)
{
/* init some FS parameters */
@@ -766,6 +978,14 @@ static void default_options(struct f2fs_sb_info *sbi)
set_opt(sbi, BG_GC);
set_opt(sbi, INLINE_DATA);
set_opt(sbi, EXTENT_CACHE);
+ sbi->sb->s_flags |= MS_LAZYTIME;
+ set_opt(sbi, FLUSH_MERGE);
+ if (f2fs_sb_mounted_hmsmr(sbi->sb)) {
+ set_opt_mode(sbi, F2FS_MOUNT_LFS);
+ set_opt(sbi, DISCARD);
+ } else {
+ set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
+ }
#ifdef CONFIG_F2FS_FS_XATTR
set_opt(sbi, XATTR_USER);
@@ -791,13 +1011,15 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
org_mount_opt = sbi->mount_opt;
active_logs = sbi->active_logs;
- if (*flags & MS_RDONLY) {
- set_opt(sbi, FASTBOOT);
- set_sbi_flag(sbi, SBI_IS_DIRTY);
+ /* recover superblocks we couldn't write due to previous RO mount */
+ if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
+ err = f2fs_commit_super(sbi, false);
+ f2fs_msg(sb, KERN_INFO,
+ "Try to recover all the superblocks, ret: %d", err);
+ if (!err)
+ clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
}
- sync_filesystem(sb);
-
sbi->mount_opt.opt = 0;
default_options(sbi);
@@ -829,7 +1051,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
if (sbi->gc_thread) {
stop_gc_thread(sbi);
- f2fs_sync_fs(sb, 1);
need_restart_gc = true;
}
} else if (!sbi->gc_thread) {
@@ -839,6 +1060,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
need_stop_gc = true;
}
+ if (*flags & MS_RDONLY) {
+ writeback_inodes_sb(sb, WB_REASON_SYNC);
+ sync_inodes_sb(sb);
+
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+ set_sbi_flag(sbi, SBI_IS_CLOSE);
+ f2fs_sync_fs(sb, 1);
+ clear_sbi_flag(sbi, SBI_IS_CLOSE);
+ }
+
/*
* We stop issue flush thread if FS is mounted as RO
* or if flush_merge is not passed in mount option.
@@ -852,8 +1083,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
}
skip:
/* Update the POSIXACL Flag */
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+
return 0;
restore_gc:
if (need_restart_gc) {
@@ -893,6 +1125,12 @@ static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
ctx, len, NULL);
}
+static int f2fs_key_prefix(struct inode *inode, u8 **key)
+{
+ *key = F2FS_I_SB(inode)->key_prefix;
+ return F2FS_I_SB(inode)->key_prefix_size;
+}
+
static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
void *fs_data)
{
@@ -909,6 +1147,7 @@ static unsigned f2fs_max_namelen(struct inode *inode)
static struct fscrypt_operations f2fs_cryptops = {
.get_context = f2fs_get_context,
+ .key_prefix = f2fs_key_prefix,
.set_context = f2fs_set_context,
.is_encrypted = f2fs_encrypted_inode,
.empty_dir = f2fs_empty_dir,
@@ -984,9 +1223,26 @@ static loff_t max_file_blocks(void)
return result;
}
-static inline bool sanity_check_area_boundary(struct super_block *sb,
- struct f2fs_super_block *raw_super)
+static int __f2fs_commit_super(struct buffer_head *bh,
+ struct f2fs_super_block *super)
{
+ lock_buffer(bh);
+ if (super)
+ memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
+ set_buffer_uptodate(bh);
+ set_buffer_dirty(bh);
+ unlock_buffer(bh);
+
+ /* it's rare case, we can do fua all the time */
+ return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
+}
+
+static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
+ struct buffer_head *bh)
+{
+ struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
+ (bh->b_data + F2FS_SUPER_OFFSET);
+ struct super_block *sb = sbi->sb;
u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
@@ -1000,6 +1256,10 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main);
u32 segment_count = le32_to_cpu(raw_super->segment_count);
u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+ u64 main_end_blkaddr = main_blkaddr +
+ (segment_count_main << log_blocks_per_seg);
+ u64 seg_end_blkaddr = segment0_blkaddr +
+ (segment_count << log_blocks_per_seg);
if (segment0_blkaddr != cp_blkaddr) {
f2fs_msg(sb, KERN_INFO,
@@ -1044,22 +1304,47 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
return true;
}
- if (main_blkaddr + (segment_count_main << log_blocks_per_seg) !=
- segment0_blkaddr + (segment_count << log_blocks_per_seg)) {
+ if (main_end_blkaddr > seg_end_blkaddr) {
f2fs_msg(sb, KERN_INFO,
- "Wrong MAIN_AREA boundary, start(%u) end(%u) blocks(%u)",
+ "Wrong MAIN_AREA boundary, start(%u) end(%u) block(%u)",
main_blkaddr,
- segment0_blkaddr + (segment_count << log_blocks_per_seg),
+ segment0_blkaddr +
+ (segment_count << log_blocks_per_seg),
segment_count_main << log_blocks_per_seg);
return true;
+ } else if (main_end_blkaddr < seg_end_blkaddr) {
+ int err = 0;
+ char *res;
+
+ /* fix in-memory information all the time */
+ raw_super->segment_count = cpu_to_le32((main_end_blkaddr -
+ segment0_blkaddr) >> log_blocks_per_seg);
+
+ if (f2fs_readonly(sb) || bdev_read_only(sb->s_bdev)) {
+ set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
+ res = "internally";
+ } else {
+ err = __f2fs_commit_super(bh, NULL);
+ res = err ? "failed" : "done";
+ }
+ f2fs_msg(sb, KERN_INFO,
+ "Fix alignment : %s, start(%u) end(%u) block(%u)",
+ res, main_blkaddr,
+ segment0_blkaddr +
+ (segment_count << log_blocks_per_seg),
+ segment_count_main << log_blocks_per_seg);
+ if (err)
+ return true;
}
-
return false;
}
-static int sanity_check_raw_super(struct super_block *sb,
- struct f2fs_super_block *raw_super)
+static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
+ struct buffer_head *bh)
{
+ struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
+ (bh->b_data + F2FS_SUPER_OFFSET);
+ struct super_block *sb = sbi->sb;
unsigned int blocksize;
if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -1070,10 +1355,10 @@ static int sanity_check_raw_super(struct super_block *sb,
}
/* Currently, support only 4KB page cache size */
- if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
+ if (F2FS_BLKSIZE != PAGE_SIZE) {
f2fs_msg(sb, KERN_INFO,
"Invalid page_cache_size (%lu), supports only 4KB\n",
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
return 1;
}
@@ -1126,7 +1411,7 @@ static int sanity_check_raw_super(struct super_block *sb,
}
/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
- if (sanity_check_area_boundary(sb, raw_super))
+ if (sanity_check_area_boundary(sbi, bh))
return 1;
return 0;
@@ -1158,7 +1443,6 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
static void init_sb_info(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = sbi->raw_super;
- int i;
sbi->log_sectors_per_block =
le32_to_cpu(raw_super->log_sectors_per_block);
@@ -1178,9 +1462,6 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
sbi->cur_victim_sec = NULL_SECNO;
sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
- for (i = 0; i < NR_COUNT_TYPE; i++)
- atomic_set(&sbi->nr_pages[i], 0);
-
sbi->dir_level = DEF_DIR_LEVEL;
sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL;
@@ -1188,6 +1469,35 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
INIT_LIST_HEAD(&sbi->s_list);
mutex_init(&sbi->umount_mutex);
+ mutex_init(&sbi->wio_mutex[NODE]);
+ mutex_init(&sbi->wio_mutex[DATA]);
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ memcpy(sbi->key_prefix, F2FS_KEY_DESC_PREFIX,
+ F2FS_KEY_DESC_PREFIX_SIZE);
+ sbi->key_prefix_size = F2FS_KEY_DESC_PREFIX_SIZE;
+#endif
+}
+
+static int init_percpu_info(struct f2fs_sb_info *sbi)
+{
+ int i, err;
+
+ if (percpu_init_rwsem(&sbi->cp_rwsem))
+ return -ENOMEM;
+
+ for (i = 0; i < NR_COUNT_TYPE; i++) {
+ err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
+ if (err)
+ return err;
+ }
+
+ err = percpu_counter_init(&sbi->alloc_valid_block_count, 0, GFP_KERNEL);
+ if (err)
+ return err;
+
+ return percpu_counter_init(&sbi->total_valid_inode_count, 0,
+ GFP_KERNEL);
}
/*
@@ -1196,13 +1506,14 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
* to get the first valid one. If any one of them is broken, we pass
* them recovery flag back to the caller.
*/
-static int read_raw_super_block(struct super_block *sb,
+static int read_raw_super_block(struct f2fs_sb_info *sbi,
struct f2fs_super_block **raw_super,
int *valid_super_block, int *recovery)
{
+ struct super_block *sb = sbi->sb;
int block;
struct buffer_head *bh;
- struct f2fs_super_block *super, *buf;
+ struct f2fs_super_block *super;
int err = 0;
super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL);
@@ -1218,11 +1529,8 @@ static int read_raw_super_block(struct super_block *sb,
continue;
}
- buf = (struct f2fs_super_block *)
- (bh->b_data + F2FS_SUPER_OFFSET);
-
/* sanity checking of raw super */
- if (sanity_check_raw_super(sb, buf)) {
+ if (sanity_check_raw_super(sbi, bh)) {
f2fs_msg(sb, KERN_ERR,
"Can't find valid F2FS filesystem in %dth superblock",
block + 1);
@@ -1232,7 +1540,8 @@ static int read_raw_super_block(struct super_block *sb,
}
if (!*raw_super) {
- memcpy(super, buf, sizeof(*super));
+ memcpy(super, bh->b_data + F2FS_SUPER_OFFSET,
+ sizeof(*super));
*valid_super_block = block;
*raw_super = super;
}
@@ -1252,42 +1561,35 @@ static int read_raw_super_block(struct super_block *sb,
return err;
}
-static int __f2fs_commit_super(struct f2fs_sb_info *sbi, int block)
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
{
- struct f2fs_super_block *super = F2FS_RAW_SUPER(sbi);
struct buffer_head *bh;
int err;
- bh = sb_getblk(sbi->sb, block);
+ if ((recover && f2fs_readonly(sbi->sb)) ||
+ bdev_read_only(sbi->sb->s_bdev)) {
+ set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
+ return -EROFS;
+ }
+
+ /* write back-up superblock first */
+ bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
if (!bh)
return -EIO;
-
- lock_buffer(bh);
- memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
- set_buffer_uptodate(bh);
- set_buffer_dirty(bh);
- unlock_buffer(bh);
-
- /* it's rare case, we can do fua all the time */
- err = __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
+ err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
brelse(bh);
- return err;
-}
-
-int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
-{
- int err;
-
- /* write back-up superblock first */
- err = __f2fs_commit_super(sbi, sbi->valid_super_block ? 0 : 1);
-
/* if we are in recovery path, skip writing valid superblock */
if (recover || err)
return err;
/* write current valid superblock */
- return __f2fs_commit_super(sbi, sbi->valid_super_block);
+ bh = sb_getblk(sbi->sb, sbi->valid_super_block);
+ if (!bh)
+ return -EIO;
+ err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
+ brelse(bh);
+ return err;
}
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
@@ -1295,7 +1597,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
struct f2fs_sb_info *sbi;
struct f2fs_super_block *raw_super;
struct inode *root;
- long err;
+ int err;
bool retry = true, need_fsck = false;
char *options = NULL;
int recovery, i, valid_super_block;
@@ -1312,6 +1614,8 @@ try_onemore:
if (!sbi)
return -ENOMEM;
+ sbi->sb = sb;
+
/* Load the checksum driver */
sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
if (IS_ERR(sbi->s_chksum_driver)) {
@@ -1327,12 +1631,14 @@ try_onemore:
goto free_sbi;
}
- err = read_raw_super_block(sb, &raw_super, &valid_super_block,
+ err = read_raw_super_block(sbi, &raw_super, &valid_super_block,
&recovery);
if (err)
goto free_sbi;
sb->s_fs_info = sbi;
+ sbi->raw_super = raw_super;
+
default_options(sbi);
/* parse mount options */
options = kstrdup((const char *)data, GFP_KERNEL);
@@ -1362,11 +1668,8 @@ try_onemore:
memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
/* init f2fs-specific super block info */
- sbi->sb = sb;
- sbi->raw_super = raw_super;
sbi->valid_super_block = valid_super_block;
mutex_init(&sbi->gc_mutex);
- mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
@@ -1383,10 +1686,13 @@ try_onemore:
sbi->write_io[i].bio = NULL;
}
- init_rwsem(&sbi->cp_rwsem);
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
+ err = init_percpu_info(sbi);
+ if (err)
+ goto free_options;
+
/* get an inode for meta space */
sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
if (IS_ERR(sbi->meta_inode)) {
@@ -1403,13 +1709,13 @@ try_onemore:
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
- sbi->total_valid_inode_count =
- le32_to_cpu(sbi->ckpt->valid_inode_count);
+ percpu_counter_set(&sbi->total_valid_inode_count,
+ le32_to_cpu(sbi->ckpt->valid_inode_count));
sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
sbi->total_valid_block_count =
le64_to_cpu(sbi->ckpt->valid_block_count);
sbi->last_valid_block_count = sbi->total_valid_block_count;
- sbi->alloc_valid_block_count = 0;
+
for (i = 0; i < NR_INODE_TYPE; i++) {
INIT_LIST_HEAD(&sbi->inode_list[i]);
spin_lock_init(&sbi->inode_lock[i]);
@@ -1442,7 +1748,7 @@ try_onemore:
seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
if (__exist_node_summaries(sbi))
sbi->kbytes_written =
- le64_to_cpu(seg_i->sum_blk->journal.info.kbytes_written);
+ le64_to_cpu(seg_i->journal->info.kbytes_written);
build_gc_manager(sbi);
@@ -1487,9 +1793,12 @@ try_onemore:
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
- if (sbi->s_proc)
+ if (sbi->s_proc) {
proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
&f2fs_seq_segment_info_fops, sb);
+ proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_segment_bits_fops, sb);
+ }
sbi->s_kobj.kset = f2fs_kset;
init_completion(&sbi->s_kobj_unregister);
@@ -1513,14 +1822,24 @@ try_onemore:
if (need_fsck)
set_sbi_flag(sbi, SBI_NEED_FSCK);
- err = recover_fsync_data(sbi);
- if (err) {
+ err = recover_fsync_data(sbi, false);
+ if (err < 0) {
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
- "Cannot recover all fsync data errno=%ld", err);
+ "Cannot recover all fsync data errno=%d", err);
+ goto free_kobj;
+ }
+ } else {
+ err = recover_fsync_data(sbi, true);
+
+ if (!f2fs_readonly(sb) && err > 0) {
+ err = -EINVAL;
+ f2fs_msg(sb, KERN_ERR,
+ "Need to recover fsync data");
goto free_kobj;
}
}
+
/* recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
@@ -1537,10 +1856,10 @@ try_onemore:
kfree(options);
/* recover broken superblock */
- if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
+ if (recovery) {
err = f2fs_commit_super(sbi, true);
f2fs_msg(sb, KERN_INFO,
- "Try to recover %dth superblock, ret: %ld",
+ "Try to recover %dth superblock, ret: %d",
sbi->valid_super_block ? 1 : 2, err);
}
@@ -1549,12 +1868,14 @@ try_onemore:
return 0;
free_kobj:
+ f2fs_sync_inode_meta(sbi);
kobject_del(&sbi->s_kobj);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
free_proc:
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
+ remove_proc_entry("segment_bits", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
f2fs_destroy_stats(sbi);
@@ -1575,6 +1896,7 @@ free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
free_options:
+ destroy_percpu_info(sbi);
kfree(options);
free_sb_buf:
kfree(raw_super);
@@ -1660,6 +1982,16 @@ static int __init init_f2fs_fs(void)
err = -ENOMEM;
goto free_extent_cache;
}
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ f2fs_fault_inject.kset = f2fs_kset;
+ f2fs_build_fault_attr(0);
+ err = kobject_init_and_add(&f2fs_fault_inject, &f2fs_fault_ktype,
+ NULL, "fault_injection");
+ if (err) {
+ f2fs_fault_inject.kset = NULL;
+ goto free_kset;
+ }
+#endif
err = register_shrinker(&f2fs_shrinker_info);
if (err)
goto free_kset;
@@ -1678,6 +2010,10 @@ free_filesystem:
free_shrinker:
unregister_shrinker(&f2fs_shrinker_info);
free_kset:
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (f2fs_fault_inject.kset)
+ kobject_put(&f2fs_fault_inject);
+#endif
kset_unregister(f2fs_kset);
free_extent_cache:
destroy_extent_cache();
@@ -1697,14 +2033,17 @@ static void __exit exit_f2fs_fs(void)
{
remove_proc_entry("fs/f2fs", NULL);
f2fs_destroy_root_stats();
- unregister_shrinker(&f2fs_shrinker_info);
unregister_filesystem(&f2fs_fs_type);
+ unregister_shrinker(&f2fs_shrinker_info);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ kobject_put(&f2fs_fault_inject);
+#endif
+ kset_unregister(f2fs_kset);
destroy_extent_cache();
destroy_checkpoint_caches();
destroy_segment_manager_caches();
destroy_node_manager_caches();
destroy_inodecache();
- kset_unregister(f2fs_kset);
f2fs_destroy_trace_ios();
}
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
index 562ce0821559..73b4e1d1912a 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -25,11 +25,11 @@ static inline void __print_last_io(void)
if (!last_io.len)
return;
- trace_printk("%3x:%3x %4x %-16s %2x %5x %12x %4x\n",
+ trace_printk("%3x:%3x %4x %-16s %2x %5x %5x %12x %4x\n",
last_io.major, last_io.minor,
last_io.pid, "----------------",
last_io.type,
- last_io.fio.rw,
+ last_io.fio.op, last_io.fio.op_flags,
last_io.fio.new_blkaddr,
last_io.len);
memset(&last_io, 0, sizeof(last_io));
@@ -101,7 +101,8 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
if (last_io.major == major && last_io.minor == minor &&
last_io.pid == pid &&
last_io.type == __file_type(inode, pid) &&
- last_io.fio.rw == fio->rw &&
+ last_io.fio.op == fio->op &&
+ last_io.fio.op_flags == fio->op_flags &&
last_io.fio.new_blkaddr + last_io.len ==
fio->new_blkaddr) {
last_io.len++;
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 06a72dc0191a..c8898b5148eb 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -26,10 +26,10 @@
#include "xattr.h"
static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, void *buffer,
- size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
switch (handler->flags) {
case F2FS_XATTR_INDEX_USER:
@@ -45,15 +45,16 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
default:
return -EINVAL;
}
- return f2fs_getxattr(d_inode(dentry), handler->flags, name,
+ return f2fs_getxattr(inode, handler->flags, name,
buffer, size, NULL);
}
static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, const void *value,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
size_t size, int flags)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
switch (handler->flags) {
case F2FS_XATTR_INDEX_USER:
@@ -69,7 +70,7 @@ static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
default:
return -EINVAL;
}
- return f2fs_setxattr(d_inode(dentry), handler->flags, name,
+ return f2fs_setxattr(inode, handler->flags, name,
value, size, NULL, flags);
}
@@ -86,29 +87,26 @@ static bool f2fs_xattr_trusted_list(struct dentry *dentry)
}
static int f2fs_xattr_advise_get(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, void *buffer,
- size_t size)
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- struct inode *inode = d_inode(dentry);
-
if (buffer)
*((char *)buffer) = F2FS_I(inode)->i_advise;
return sizeof(char);
}
static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
- struct dentry *dentry, const char *name, const void *value,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
size_t size, int flags)
{
- struct inode *inode = d_inode(dentry);
-
if (!inode_owner_or_capable(inode))
return -EPERM;
if (value == NULL)
return -EINVAL;
F2FS_I(inode)->i_advise |= *(char *)value;
- mark_inode_dirty(inode);
+ f2fs_mark_inode_dirty_sync(inode);
return 0;
}
@@ -301,6 +299,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
if (ipage) {
inline_addr = inline_xattr_addr(ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true);
+ set_page_dirty(ipage);
} else {
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
@@ -443,13 +442,12 @@ static int __f2fs_setxattr(struct inode *inode, int index,
const char *name, const void *value, size_t size,
struct page *ipage, int flags)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_xattr_entry *here, *last;
void *base_addr;
int found, newsize;
size_t len;
__u32 new_hsize;
- int error = -ENOMEM;
+ int error = 0;
if (name == NULL)
return -EINVAL;
@@ -467,7 +465,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
base_addr = read_all_xattrs(inode, ipage);
if (!base_addr)
- goto exit;
+ return -ENOMEM;
/* find entry with wanted name. */
here = __find_xattr(base_addr, index, len, name);
@@ -500,7 +498,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
free = free + ENTRY_SIZE(here);
if (unlikely(free < newsize)) {
- error = -ENOSPC;
+ error = -E2BIG;
goto exit;
}
}
@@ -528,7 +526,6 @@ static int __f2fs_setxattr(struct inode *inode, int index,
* Before we come here, old entry is removed.
* We just write new entry.
*/
- memset(last, 0, newsize);
last->e_name_index = index;
last->e_name_len = len;
memcpy(last->e_name, name, len);
@@ -542,19 +539,15 @@ static int __f2fs_setxattr(struct inode *inode, int index,
if (error)
goto exit;
- if (is_inode_flag_set(fi, FI_ACL_MODE)) {
- inode->i_mode = fi->i_acl_mode;
+ if (is_inode_flag_set(inode, FI_ACL_MODE)) {
+ inode->i_mode = F2FS_I(inode)->i_acl_mode;
inode->i_ctime = CURRENT_TIME;
- clear_inode_flag(fi, FI_ACL_MODE);
+ clear_inode_flag(inode, FI_ACL_MODE);
}
if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
f2fs_set_encrypted_inode(inode);
-
- if (ipage)
- update_inode(inode, ipage);
- else
- update_inode_page(inode);
+ f2fs_mark_inode_dirty_sync(inode);
exit:
kzfree(base_addr);
return error;
generated by cgit v1.2.3 (git 2.46.0) at 2025-12-09 12:59:34 +0000