asgardius/android_kernel_samsung_heroqlte
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update f2fs to kernel.org:f2fs-stable 3.18 (2016-04-02)

Browse source
This commit is contained in:
James Christopher Adduono 2016-03-10 23:37:43 -05:00 committed by HackerOO7
parent 2be4c680cb
commit 3c3684dec4
32 changed files with 9127 additions and 2852 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
Documentation/ABI/testing/sysfs-fs-f2fs
View file

@ -74,3 +74,41 @@ Date: March 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the memory footprint used by f2fs.
What: /sys/fs/f2fs/<disk>/trim_sections
Date: February 2015
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the trimming rate in batch mode.
What: /sys/fs/f2fs/<disk>/cp_interval
Date: October 2015
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the checkpoint timing.
What: /sys/fs/f2fs/<disk>/idle_interval
Date: January 2016
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the idle timing.
What: /sys/fs/f2fs/<disk>/ra_nid_pages
Date: October 2015
Contact: "Chao Yu" <chao2.yu@samsung.com>
Description:
Controls the count of nid pages to be readaheaded.
What: /sys/fs/f2fs/<disk>/dirty_nats_ratio
Date: January 2016
Contact: "Chao Yu" <chao2.yu@samsung.com>
Description:
Controls dirty nat entries ratio threshold, if current
ratio exceeds configured threshold, checkpoint will
be triggered for flushing dirty nat entries.
What: /sys/fs/f2fs/<disk>/lifetime_write_kbytes
Date: January 2016
Contact: "Shuoran Liu" <liushuoran@huawei.com>
Description:
Shows total written kbytes issued to disk.

13
Documentation/filesystems/f2fs.txt
View file

@ -131,6 +131,19 @@ nobarrier This option can be used if underlying storage guarantees
If this option is set, no cache_flush commands are issued
but f2fs still guarantees the write ordering of all the
data writes.
fastboot This option is used when a system wants to reduce mount
time as much as possible, even though normal performance
can be sacrificed.
extent_cache Enable an extent cache based on rb-tree, it can cache
as many as extent which map between contiguous logical
address and physical address per inode, resulting in
increasing the cache hit ratio. Set by default.
noextent_cache Disable an extent cache based on rb-tree explicitly, see
the above extent_cache mount option.
noinline_data Disable the inline data feature, inline data feature is
enabled by default.
data_flush Enable data flushing before checkpoint in order to
persist data of regular and symlink.
================================================================================
DEBUGFS ENTRIES

27
fs/f2fs/Kconfig
View file

@ -1,6 +1,8 @@
config F2FS_FS
tristate "F2FS filesystem support (EXPERIMENTAL)"
tristate "F2FS filesystem support"
depends on BLOCK
select CRYPTO
select CRYPTO_CRC32
help
F2FS is based on Log-structured File System (LFS), which supports
versatile "flash-friendly" features. The design has been focused on
@ -45,7 +47,7 @@ config F2FS_FS_POSIX_ACL
default y
help
Posix Access Control Lists (ACLs) support permissions for users and
gourps beyond the owner/group/world scheme.
groups beyond the owner/group/world scheme.
To learn more about Access Control Lists, visit the POSIX ACLs for
Linux website <http://acl.bestbits.at/>.
@ -71,3 +73,24 @@ config F2FS_CHECK_FS
Enables BUG_ONs which check the filesystem consistency in runtime.
If you want to improve the performance, say N.
config F2FS_FS_ENCRYPTION
bool "F2FS Encryption"
depends on F2FS_FS
depends on F2FS_FS_XATTR
select FS_ENCRYPTION
help
Enable encryption of f2fs files and directories. This
feature is similar to ecryptfs, but it is more memory
efficient since it avoids caching the encrypted and
decrypted pages in the page cache.
config F2FS_IO_TRACE
bool "F2FS IO tracer"
depends on F2FS_FS
depends on FUNCTION_TRACER
help
F2FS IO trace is based on a function trace, which gathers process
information and block IO patterns in the filesystem level.
If unsure, say N.

2
fs/f2fs/Makefile
View file

@ -2,6 +2,8 @@ obj-$(CONFIG_F2FS_FS) += f2fs.o
f2fs-y := dir.o file.o inode.o namei.o hash.o super.o inline.o
f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o
f2fs-y += shrinker.o extent_cache.o
f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o

152
fs/f2fs/acl.c
View file

@ -62,7 +62,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
if (count == 0)
return NULL;
acl = posix_acl_alloc(count, GFP_KERNEL);
acl = posix_acl_alloc(count, GFP_NOFS);
if (!acl)
return ERR_PTR(-ENOMEM);
@ -116,7 +116,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
int i;
f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
sizeof(struct f2fs_acl_entry), GFP_KERNEL);
sizeof(struct f2fs_acl_entry), GFP_NOFS);
if (!f2fs_acl)
return ERR_PTR(-ENOMEM);
@ -162,7 +162,8 @@ fail:
return ERR_PTR(-EINVAL);
}
struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
struct page *dpage)
{
int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT;
void *value = NULL;
@ -172,12 +173,13 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
if (type == ACL_TYPE_ACCESS)
name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
retval = f2fs_getxattr(inode, name_index, "", NULL, 0);
retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage);
if (retval > 0) {
value = kmalloc(retval, GFP_F2FS_ZERO);
if (!value)
return ERR_PTR(-ENOMEM);
retval = f2fs_getxattr(inode, name_index, "", value, retval);
retval = f2fs_getxattr(inode, name_index, "", value,
retval, dpage);
}
if (retval > 0)
@ -194,6 +196,11 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
return acl;
}
struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
{
return __f2fs_get_acl(inode, type, NULL);
}
static int __f2fs_set_acl(struct inode *inode, int type,
struct posix_acl *acl, struct page *ipage)
{
@ -229,7 +236,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
if (acl) {
value = f2fs_acl_to_disk(acl, &size);
if (IS_ERR(value)) {
cond_clear_inode_flag(fi, FI_ACL_MODE);
clear_inode_flag(fi, FI_ACL_MODE);
return (int)PTR_ERR(value);
}
}
@ -240,7 +247,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
if (!error)
set_cached_acl(inode, type, acl);
cond_clear_inode_flag(fi, FI_ACL_MODE);
clear_inode_flag(fi, FI_ACL_MODE);
return error;
}
@ -249,12 +256,135 @@ int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
return __f2fs_set_acl(inode, type, acl, NULL);
}
int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage)
/*
* Most part of f2fs_acl_clone, f2fs_acl_create_masq, f2fs_acl_create
* are copied from posix_acl.c
*/
static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl,
gfp_t flags)
{
struct posix_acl *default_acl, *acl;
struct posix_acl *clone = NULL;
if (acl) {
int size = sizeof(struct posix_acl) + acl->a_count *
sizeof(struct posix_acl_entry);
clone = kmemdup(acl, size, flags);
if (clone)
atomic_set(&clone->a_refcount, 1);
}
return clone;
}
static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
{
struct posix_acl_entry *pa, *pe;
struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
umode_t mode = *mode_p;
int not_equiv = 0;
/* assert(atomic_read(acl->a_refcount) == 1); */
FOREACH_ACL_ENTRY(pa, acl, pe) {
switch(pa->e_tag) {
case ACL_USER_OBJ:
pa->e_perm &= (mode >> 6) | ~S_IRWXO;
mode &= (pa->e_perm << 6) | ~S_IRWXU;
break;
case ACL_USER:
case ACL_GROUP:
not_equiv = 1;
break;
case ACL_GROUP_OBJ:
group_obj = pa;
break;
case ACL_OTHER:
pa->e_perm &= mode | ~S_IRWXO;
mode &= pa->e_perm | ~S_IRWXO;
break;
case ACL_MASK:
mask_obj = pa;
not_equiv = 1;
break;
default:
return -EIO;
}
}
if (mask_obj) {
mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
mode &= (mask_obj->e_perm << 3) | ~S_IRWXG;
} else {
if (!group_obj)
return -EIO;
group_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
mode &= (group_obj->e_perm << 3) | ~S_IRWXG;
}
*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
return not_equiv;
}
static int f2fs_acl_create(struct inode *dir, umode_t *mode,
struct posix_acl **default_acl, struct posix_acl **acl,
struct page *dpage)
{
struct posix_acl *p;
struct posix_acl *clone;
int ret;
*acl = NULL;
*default_acl = NULL;
if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
return 0;
p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage);
if (!p || p == ERR_PTR(-EOPNOTSUPP)) {
*mode &= ~current_umask();
return 0;
}
if (IS_ERR(p))
return PTR_ERR(p);
clone = f2fs_acl_clone(p, GFP_NOFS);
if (!clone)
goto no_mem;
ret = f2fs_acl_create_masq(clone, mode);
if (ret < 0)
goto no_mem_clone;
if (ret == 0)
posix_acl_release(clone);
else
*acl = clone;
if (!S_ISDIR(*mode))
posix_acl_release(p);
else
*default_acl = p;
return 0;
no_mem_clone:
posix_acl_release(clone);
no_mem:
posix_acl_release(p);
return -ENOMEM;
}
int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
struct page *dpage)
{
struct posix_acl *default_acl = NULL, *acl = NULL;
int error = 0;
error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dpage);
if (error)
return error;
@ -264,7 +394,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage)
posix_acl_release(default_acl);
}
if (acl) {
if (error)
if (!error)
error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl,
ipage);
posix_acl_release(acl);

7
fs/f2fs/acl.h
View file

@ -37,15 +37,16 @@ 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_init_acl(struct inode *, struct inode *, struct page *);
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
#define f2fs_check_acl NULL
#define f2fs_get_acl NULL
#define f2fs_set_acl NULL
static inline int f2fs_init_acl(struct inode *inode, struct inode *dir,
struct page *page)
struct page *ipage, struct page *dpage)
{
return 0;
}

674
fs/f2fs/checkpoint.c
View file

File diff suppressed because it is too large Load diff

1543
fs/f2fs/data.c
View file

File diff suppressed because it is too large Load diff

146
fs/f2fs/debug.c
View file

@ -33,19 +33,31 @@ static void update_general_status(struct f2fs_sb_info *sbi)
int i;
/* validation check of the segment numbers */
si->hit_ext = sbi->read_hit_ext;
si->total_ext = sbi->total_hit_ext;
si->hit_largest = atomic64_read(&sbi->read_hit_largest);
si->hit_cached = atomic64_read(&sbi->read_hit_cached);
si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree);
si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree;
si->total_ext = atomic64_read(&sbi->total_hit_ext);
si->ext_tree = atomic_read(&sbi->total_ext_tree);
si->zombie_tree = atomic_read(&sbi->total_zombie_tree);
si->ext_node = atomic_read(&sbi->total_ext_node);
si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
si->ndirty_dirs = sbi->n_dirty_dirs;
si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
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->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
si->rsvd_segs = reserved_segments(sbi);
si->overp_segs = overprovision_segments(sbi);
si->valid_count = valid_user_blocks(sbi);
si->valid_node_count = valid_node_count(sbi);
si->valid_inode_count = valid_inode_count(sbi);
si->inline_inode = sbi->inline_inode;
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->utilization = utilization(sbi);
si->free_segs = free_segments(sbi);
@ -55,7 +67,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->node_pages = NODE_MAPPING(sbi)->nrpages;
si->meta_pages = META_MAPPING(sbi)->nrpages;
si->nats = NM_I(sbi)->nat_cnt;
si->sits = SIT_I(sbi)->dirty_sentries;
si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
si->sits = MAIN_SEGS(sbi);
si->dirty_sits = SIT_I(sbi)->dirty_sentries;
si->fnids = NM_I(sbi)->fcnt;
si->bg_gc = sbi->bg_gc;
si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
@ -77,6 +91,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->segment_count[i] = sbi->segment_count[i];
si->block_count[i] = sbi->block_count[i];
}
si->inplace_count = atomic_read(&sbi->inplace_count);
}
/*
@ -85,13 +101,14 @@ static void update_general_status(struct f2fs_sb_info *sbi)
static void update_sit_info(struct f2fs_sb_info *sbi)
{
struct f2fs_stat_info *si = F2FS_STAT(sbi);
unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist;
unsigned long long blks_per_sec, hblks_per_sec, total_vblocks;
unsigned long long bimodal, dist;
unsigned int segno, vblocks;
int ndirty = 0;
bimodal = 0;
total_vblocks = 0;
blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg);
blks_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
hblks_per_sec = blks_per_sec / 2;
for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
@ -103,10 +120,10 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
ndirty++;
}
}
dist = MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
si->bimodal = bimodal / dist;
dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
si->bimodal = div64_u64(bimodal, dist);
if (si->dirty_count)
si->avg_vblocks = total_vblocks / ndirty;
si->avg_vblocks = div_u64(total_vblocks, ndirty);
else
si->avg_vblocks = 0;
}
@ -118,6 +135,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
{
struct f2fs_stat_info *si = F2FS_STAT(sbi);
unsigned npages;
int i;
if (si->base_mem)
goto get_cache;
@ -133,7 +151,8 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->base_mem += sizeof(struct sit_info);
si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
si->base_mem += 3 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
si->base_mem += SIT_VBLOCK_MAP_SIZE;
if (sbi->segs_per_sec > 1)
si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
@ -156,19 +175,35 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->base_mem += sizeof(struct f2fs_nm_info);
si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
/* build gc */
si->base_mem += sizeof(struct f2fs_gc_kthread);
get_cache:
si->cache_mem = 0;
/* build gc */
if (sbi->gc_thread)
si->cache_mem += sizeof(struct f2fs_gc_kthread);
/* build merge flush thread */
if (SM_I(sbi)->cmd_control_info)
si->cache_mem += sizeof(struct flush_cmd_control);
/* free nids */
si->cache_mem = NM_I(sbi)->fcnt;
si->cache_mem += NM_I(sbi)->nat_cnt;
si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid);
si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
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++)
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);
si->cache_mem += atomic_read(&sbi->total_ext_node) *
sizeof(struct extent_node);
si->page_mem = 0;
npages = NODE_MAPPING(sbi)->nrpages;
si->cache_mem += npages << PAGE_CACHE_SHIFT;
si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
npages = META_MAPPING(sbi)->nrpages;
si->cache_mem += npages << PAGE_CACHE_SHIFT;
si->cache_mem += sbi->n_orphans * sizeof(struct ino_entry);
si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry);
si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
}
static int stat_show(struct seq_file *s, void *v)
@ -198,8 +233,12 @@ static int stat_show(struct seq_file *s, void *v)
seq_printf(s, "Other: %u)\n - Data: %u\n",
si->valid_node_count - si->valid_inode_count,
si->valid_count - si->valid_node_count);
seq_printf(s, " - Inline_xattr Inode: %u\n",
si->inline_xattr);
seq_printf(s, " - Inline_data Inode: %u\n",
si->inline_inode);
seq_printf(s, " - Inline_dentry Inode: %u\n",
si->inline_dir);
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
si->main_area_segs, si->main_area_sections,
si->main_area_zones);
@ -233,25 +272,43 @@ static int stat_show(struct seq_file *s, void *v)
si->dirty_count);
seq_printf(s, " - Prefree: %d\n - Free: %d (%d)\n\n",
si->prefree_count, si->free_segs, si->free_secs);
seq_printf(s, "CP calls: %d\n", si->cp_count);
seq_printf(s, "CP calls: %d (BG: %d)\n",
si->cp_count, si->bg_cp_count);
seq_printf(s, "GC calls: %d (BG: %d)\n",
si->call_count, si->bg_gc);
seq_printf(s, " - data segments : %d\n", si->data_segs);
seq_printf(s, " - node segments : %d\n", si->node_segs);
seq_printf(s, "Try to move %d blocks\n", si->tot_blks);
seq_printf(s, " - data blocks : %d\n", si->data_blks);
seq_printf(s, " - node blocks : %d\n", si->node_blks);
seq_printf(s, "\nExtent Hit Ratio: %d / %d\n",
si->hit_ext, si->total_ext);
seq_printf(s, " - data segments : %d (%d)\n",
si->data_segs, si->bg_data_segs);
seq_printf(s, " - node segments : %d (%d)\n",
si->node_segs, si->bg_node_segs);
seq_printf(s, "Try to move %d blocks (BG: %d)\n", si->tot_blks,
si->bg_data_blks + si->bg_node_blks);
seq_printf(s, " - data blocks : %d (%d)\n", si->data_blks,
si->bg_data_blks);
seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks,
si->bg_node_blks);
seq_puts(s, "\nExtent Cache:\n");
seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n",
si->hit_largest, si->hit_cached,
si->hit_rbtree);
seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n",
!si->total_ext ? 0 :
div64_u64(si->hit_total * 100, si->total_ext),
si->hit_total, si->total_ext);
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",
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",
si->ndirty_data, si->ndirty_files);
seq_printf(s, " - meta: %4d in %4d\n",
si->ndirty_meta, si->meta_pages);
seq_printf(s, " - NATs: %9d\n - SITs: %9d\n",
si->nats, si->sits);
seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n",
si->dirty_nats, si->nats, si->dirty_sits, si->sits);
seq_printf(s, " - free_nids: %9d\n",
si->fnids);
seq_puts(s, "\nDistribution of User Blocks:");
@ -269,6 +326,7 @@ static int stat_show(struct seq_file *s, void *v)
for (j = 0; j < si->util_free; j++)
seq_putc(s, '-');
seq_puts(s, "]\n\n");
seq_printf(s, "IPU: %u blocks\n", si->inplace_count);
seq_printf(s, "SSR: %u blocks in %u segments\n",
si->block_count[SSR], si->segment_count[SSR]);
seq_printf(s, "LFS: %u blocks in %u segments\n",
@ -281,9 +339,14 @@ static int stat_show(struct seq_file *s, void *v)
/* memory footprint */
update_mem_info(si->sbi);
seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
(si->base_mem + si->cache_mem) >> 10,
si->base_mem >> 10, si->cache_mem >> 10);
seq_printf(s, "\nMemory: %llu KB\n",
(si->base_mem + si->cache_mem + si->page_mem) >> 10);
seq_printf(s, " - static: %llu KB\n",
si->base_mem >> 10);
seq_printf(s, " - cached: %llu KB\n",
si->cache_mem >> 10);
seq_printf(s, " - paged : %llu KB\n",
si->page_mem >> 10);
}
mutex_unlock(&f2fs_stat_mutex);
return 0;
@ -321,6 +384,16 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
si->sbi = sbi;
sbi->stat_info = si;
atomic64_set(&sbi->total_hit_ext, 0);
atomic64_set(&sbi->read_hit_rbtree, 0);
atomic64_set(&sbi->read_hit_largest, 0);
atomic64_set(&sbi->read_hit_cached, 0);
atomic_set(&sbi->inline_xattr, 0);
atomic_set(&sbi->inline_inode, 0);
atomic_set(&sbi->inline_dir, 0);
atomic_set(&sbi->inplace_count, 0);
mutex_lock(&f2fs_stat_mutex);
list_add_tail(&si->stat_list, &f2fs_stat_list);
mutex_unlock(&f2fs_stat_mutex);
@ -339,20 +412,23 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
kfree(si);
}
void __init f2fs_create_root_stats(void)
int __init f2fs_create_root_stats(void)
{
struct dentry *file;
f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
if (!f2fs_debugfs_root)
return;
return -ENOMEM;
file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root,
NULL, &stat_fops);
if (!file) {
debugfs_remove(f2fs_debugfs_root);
f2fs_debugfs_root = NULL;
return -ENOMEM;
}
return 0;
}
void f2fs_destroy_root_stats(void)

577
fs/f2fs/dir.c
View file

@ -37,7 +37,7 @@ static unsigned int bucket_blocks(unsigned int level)
return 4;
}
static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
[F2FS_FT_UNKNOWN] = DT_UNKNOWN,
[F2FS_FT_REG_FILE] = DT_REG,
[F2FS_FT_DIR] = DT_DIR,
@ -59,9 +59,8 @@ static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK,
};
static void set_de_type(struct f2fs_dir_entry *de, struct inode *inode)
void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
{
umode_t mode = inode->i_mode;
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
}
@ -77,81 +76,101 @@ static unsigned long dir_block_index(unsigned int level,
return bidx;
}
static bool early_match_name(size_t namelen, f2fs_hash_t namehash,
struct f2fs_dir_entry *de)
static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
struct fscrypt_name *fname,
f2fs_hash_t namehash,
int *max_slots,
struct page **res_page)
{
if (le16_to_cpu(de->name_len) != namelen)
return false;
struct f2fs_dentry_block *dentry_blk;
struct f2fs_dir_entry *de;
struct f2fs_dentry_ptr d;
if (de->hash_code != namehash)
return false;
dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page);
return true;
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
de = find_target_dentry(fname, namehash, max_slots, &d);
if (de)
*res_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;
}
static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
struct qstr *name, int *max_slots,
f2fs_hash_t namehash, struct page **res_page)
struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
f2fs_hash_t namehash, int *max_slots,
struct f2fs_dentry_ptr *d)
{
struct f2fs_dir_entry *de;
unsigned long bit_pos = 0;
struct f2fs_dentry_block *dentry_blk = kmap(dentry_page);
const void *dentry_bits = &dentry_blk->dentry_bitmap;
int max_len = 0;
struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
struct fscrypt_str *name = &fname->disk_name;
while (bit_pos < NR_DENTRY_IN_BLOCK) {
if (!test_bit_le(bit_pos, dentry_bits)) {
if (bit_pos == 0)
max_len = 1;
else if (!test_bit_le(bit_pos - 1, dentry_bits))
max_len++;
if (max_slots)
*max_slots = 0;
while (bit_pos < d->max) {
if (!test_bit_le(bit_pos, d->bitmap)) {
bit_pos++;
max_len++;
continue;
}
de = &dentry_blk->dentry[bit_pos];
if (early_match_name(name->len, namehash, de)) {
if (!memcmp(dentry_blk->filename[bit_pos],
name->name,
name->len)) {
*res_page = dentry_page;
goto found;
}
}
if (max_len > *max_slots) {
*max_slots = max_len;
max_len = 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(F2FS_P_SB(dentry_page), !de->name_len);
de = &d->dentry[bit_pos];
/* encrypted case */
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
/* show encrypted name */
if (fname->hash) {
if (de->hash_code == fname->hash)
goto found;
} else if (de_name.len == name->len &&
de->hash_code == namehash &&
!memcmp(de_name.name, name->name, name->len))
goto found;
if (max_slots && max_len > *max_slots)
*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));
}
de = NULL;
kunmap(dentry_page);
found:
if (max_len > *max_slots)
if (max_slots && max_len > *max_slots)
*max_slots = max_len;
return de;
}
static struct f2fs_dir_entry *find_in_level(struct inode *dir,
unsigned int level, struct qstr *name,
f2fs_hash_t namehash, struct page **res_page)
unsigned int level,
struct fscrypt_name *fname,
struct page **res_page)
{
int s = GET_DENTRY_SLOTS(name->len);
struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
int s = GET_DENTRY_SLOTS(name.len);
unsigned int nbucket, nblock;
unsigned int bidx, end_block;
struct page *dentry_page;
struct f2fs_dir_entry *de = NULL;
bool room = false;
int max_slots = 0;
int max_slots;
f2fs_hash_t namehash;
f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
namehash = f2fs_dentry_hash(&name);
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
nblock = bucket_blocks(level);
@ -162,14 +181,14 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
for (; bidx < end_block; bidx++) {
/* no need to allocate new dentry pages to all the indices */
dentry_page = find_data_page(dir, bidx, true);
dentry_page = find_data_page(dir, bidx);
if (IS_ERR(dentry_page)) {
room = true;
continue;
}
de = find_in_block(dentry_page, name, &max_slots,
namehash, res_page);
de = find_in_block(dentry_page, fname, namehash, &max_slots,
res_page);
if (de)
break;
@ -197,27 +216,42 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
{
unsigned long npages = dir_blocks(dir);
struct f2fs_dir_entry *de = NULL;
f2fs_hash_t name_hash;
unsigned int max_depth;
unsigned int level;
if (npages == 0)
return NULL;
struct fscrypt_name fname;
int err;
*res_page = NULL;
name_hash = f2fs_dentry_hash(child);
err = fscrypt_setup_filename(dir, child, 1, &fname);
if (err)
return NULL;
if (f2fs_has_inline_dentry(dir)) {
de = find_in_inline_dir(dir, &fname, res_page);
goto out;
}
if (npages == 0)
goto out;
max_depth = F2FS_I(dir)->i_current_depth;
if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING,
"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);
}
for (level = 0; level < max_depth; level++) {
de = find_in_level(dir, level, child, name_hash, res_page);
de = find_in_level(dir, level, &fname, res_page);
if (de)
break;
}
if (!de && F2FS_I(dir)->chash != name_hash) {
F2FS_I(dir)->chash = name_hash;
F2FS_I(dir)->clevel = level - 1;
}
out:
fscrypt_free_filename(&fname);
return de;
}
@ -227,7 +261,10 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
struct f2fs_dir_entry *de;
struct f2fs_dentry_block *dentry_blk;
page = get_lock_data_page(dir, 0);
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;
@ -247,7 +284,7 @@ ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
de = f2fs_find_entry(dir, qstr, &page);
if (de) {
res = le32_to_cpu(de->ino);
kunmap(page);
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
}
@ -257,11 +294,12 @@ ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
struct page *page, struct inode *inode)
{
enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
lock_page(page);
f2fs_wait_on_page_writeback(page, DATA);
f2fs_wait_on_page_writeback(page, type, true);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode);
kunmap(page);
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);
@ -273,7 +311,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
{
struct f2fs_inode *ri;
f2fs_wait_on_page_writeback(ipage, NODE);
f2fs_wait_on_page_writeback(ipage, NODE, true);
/* copy name info. to this inode page */
ri = F2FS_INODE(ipage);
@ -282,10 +320,14 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
set_page_dirty(ipage);
}
int update_dent_inode(struct inode *inode, const struct qstr *name)
int update_dent_inode(struct inode *inode, struct inode *to,
const struct qstr *name)
{
struct page *page;
if (file_enc_name(to))
return 0;
page = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(page))
return PTR_ERR(page);
@ -296,36 +338,38 @@ int update_dent_inode(struct inode *inode, const struct qstr *name)
return 0;
}
void do_make_empty_dir(struct inode *inode, struct inode *parent,
struct f2fs_dentry_ptr *d)
{
struct qstr dot = QSTR_INIT(".", 1);
struct qstr dotdot = QSTR_INIT("..", 2);
/* update dirent of "." */
f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0);
/* update dirent of ".." */
f2fs_update_dentry(parent->i_ino, parent->i_mode, d, &dotdot, 0, 1);
}
static int make_empty_dir(struct inode *inode,
struct inode *parent, struct page *page)
{
struct page *dentry_page;
struct f2fs_dentry_block *dentry_blk;
struct f2fs_dir_entry *de;
struct f2fs_dentry_ptr d;
if (f2fs_has_inline_dentry(inode))
return make_empty_inline_dir(inode, parent, page);
dentry_page = get_new_data_page(inode, page, 0, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
dentry_blk = kmap_atomic(dentry_page);
de = &dentry_blk->dentry[0];
de->name_len = cpu_to_le16(1);
de->hash_code = 0;
de->ino = cpu_to_le32(inode->i_ino);
memcpy(dentry_blk->filename[0], ".", 1);
set_de_type(de, inode);
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
do_make_empty_dir(inode, parent, &d);
de = &dentry_blk->dentry[1];
de->hash_code = 0;
de->name_len = cpu_to_le16(2);
de->ino = cpu_to_le32(parent->i_ino);
memcpy(dentry_blk->filename[1], "..", 2);
set_de_type(de, inode);
test_and_set_bit_le(0, &dentry_blk->dentry_bitmap);
test_and_set_bit_le(1, &dentry_blk->dentry_bitmap);
kunmap_atomic(dentry_blk);
set_page_dirty(dentry_page);
@ -333,8 +377,8 @@ static int make_empty_dir(struct inode *inode,
return 0;
}
static struct page *init_inode_metadata(struct inode *inode,
struct inode *dir, const struct qstr *name)
struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
const struct qstr *name, struct page *dpage)
{
struct page *page;
int err;
@ -350,13 +394,19 @@ static struct page *init_inode_metadata(struct inode *inode,
goto error;
}
err = f2fs_init_acl(inode, dir, page);
err = f2fs_init_acl(inode, dir, page, dpage);
if (err)
goto put_error;
err = f2fs_init_security(inode, dir, name, page);
if (err)
goto put_error;
if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) {
err = fscrypt_inherit_context(dir, inode, page, false);
if (err)
goto put_error;
}
} else {
page = get_node_page(F2FS_I_SB(dir), inode->i_ino);
if (IS_ERR(page))
@ -390,15 +440,15 @@ 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_dir_inode(inode);
remove_dirty_inode(inode);
remove_inode_page(inode);
return ERR_PTR(err);
}
static void update_parent_metadata(struct inode *dir, struct inode *inode,
void update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth)
{
if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
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);
@ -413,58 +463,92 @@ static void update_parent_metadata(struct inode *dir, struct inode *inode,
set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
}
if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK))
if (inode && is_inode_flag_set(F2FS_I(inode), FI_INC_LINK))
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
}
static int room_for_filename(struct f2fs_dentry_block *dentry_blk, int slots)
int room_for_filename(const void *bitmap, int slots, int max_slots)
{
int bit_start = 0;
int zero_start, zero_end;
next:
zero_start = find_next_zero_bit_le(&dentry_blk->dentry_bitmap,
NR_DENTRY_IN_BLOCK,
bit_start);
if (zero_start >= NR_DENTRY_IN_BLOCK)
return NR_DENTRY_IN_BLOCK;
zero_start = find_next_zero_bit_le(bitmap, max_slots, bit_start);
if (zero_start >= max_slots)
return max_slots;
zero_end = find_next_bit_le(&dentry_blk->dentry_bitmap,
NR_DENTRY_IN_BLOCK,
zero_start);
zero_end = find_next_bit_le(bitmap, max_slots, zero_start);
if (zero_end - zero_start >= slots)
return zero_start;
bit_start = zero_end + 1;
if (zero_end + 1 >= NR_DENTRY_IN_BLOCK)
return NR_DENTRY_IN_BLOCK;
if (zero_end + 1 >= max_slots)
return max_slots;
goto next;
}
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
const struct qstr *name, f2fs_hash_t name_hash,
unsigned int bit_pos)
{
struct f2fs_dir_entry *de;
int slots = GET_DENTRY_SLOTS(name->len);
int i;
de = &d->dentry[bit_pos];
de->hash_code = name_hash;
de->name_len = cpu_to_le16(name->len);
memcpy(d->filename[bit_pos], name->name, name->len);
de->ino = cpu_to_le32(ino);
set_de_type(de, mode);
for (i = 0; i < slots; i++) {
test_and_set_bit_le(bit_pos + i, (void *)d->bitmap);
/* avoid wrong garbage data for readdir */
if (i)
(de + i)->name_len = 0;
}
}
/*
* 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)
struct inode *inode, nid_t ino, umode_t mode)
{
unsigned int bit_pos;
unsigned int level;
unsigned int current_depth;
unsigned long bidx, block;
f2fs_hash_t dentry_hash;
struct f2fs_dir_entry *de;
unsigned int nbucket, nblock;
size_t namelen = name->len;
struct page *dentry_page = NULL;
struct f2fs_dentry_block *dentry_blk = NULL;
int slots = GET_DENTRY_SLOTS(namelen);
struct page *page;
int err = 0;
int i;
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;
}
dentry_hash = f2fs_dentry_hash(name);
level = 0;
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) {
level = F2FS_I(dir)->clevel;
@ -472,8 +556,10 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
}
start:
if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
return -ENOSPC;
if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) {
err = -ENOSPC;
goto out;
}
/* Increase the depth, if required */
if (level == current_depth)
@ -487,11 +573,14 @@ start:
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = get_new_data_page(dir, NULL, block, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
if (IS_ERR(dentry_page)) {
err = PTR_ERR(dentry_page);
goto out;
}
dentry_blk = kmap(dentry_page);
bit_pos = room_for_filename(dentry_blk, slots);
bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
slots, NR_DENTRY_IN_BLOCK);
if (bit_pos < NR_DENTRY_IN_BLOCK)
goto add_dentry;
@ -503,32 +592,35 @@ start:
++level;
goto start;
add_dentry:
f2fs_wait_on_page_writeback(dentry_page, DATA);
f2fs_wait_on_page_writeback(dentry_page, DATA, true);
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, name);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, &new_name, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
if (f2fs_encrypted_inode(dir))
file_set_enc_name(inode);
}
de = &dentry_blk->dentry[bit_pos];
de->hash_code = dentry_hash;
de->name_len = cpu_to_le16(namelen);
memcpy(dentry_blk->filename[bit_pos], name->name, name->len);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode);
for (i = 0; i < slots; i++)
test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos);
set_page_dirty(dentry_page);
/* we don't need to mark_inode_dirty now */
F2FS_I(inode)->i_pino = dir->i_ino;
update_inode(inode, page);
f2fs_put_page(page, 1);
if (inode) {
/* we don't need to mark_inode_dirty now */
F2FS_I(inode)->i_pino = dir->i_ino;
update_inode(inode, page);
f2fs_put_page(page, 1);
}
update_parent_metadata(dir, inode, current_depth);
fail:
up_write(&F2FS_I(inode)->i_sem);
if (inode)
up_write(&F2FS_I(inode)->i_sem);
if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
update_inode_page(dir);
@ -536,6 +628,9 @@ fail:
}
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
out:
fscrypt_free_filename(&fname);
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
return err;
}
@ -545,7 +640,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
int err = 0;
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, NULL);
page = init_inode_metadata(inode, dir, NULL, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@ -557,24 +652,58 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
clear_inode_flag(F2FS_I(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)
{
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);
}
inode->i_ctime = CURRENT_TIME;
drop_nlink(inode);
if (S_ISDIR(inode->i_mode)) {
drop_nlink(inode);
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);
else
release_orphan_inode(sbi);
}
/*
* It only removes the dentry from the dentry page, corresponding name
* entry in name page does not need to be touched during deletion.
*/
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *inode)
struct inode *dir, struct inode *inode)
{
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
struct inode *dir = page->mapping->host;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
int i;
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
if (f2fs_has_inline_dentry(dir))
return f2fs_delete_inline_entry(dentry, page, dir, inode);
lock_page(page);
f2fs_wait_on_page_writeback(page, DATA);
f2fs_wait_on_page_writeback(page, DATA, true);
dentry_blk = page_address(page);
bit_pos = dentry - dentry_blk->dentry;
@ -590,33 +719,13 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
if (inode) {
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
if (inode)
f2fs_drop_nlink(dir, inode, NULL);
down_write(&F2FS_I(inode)->i_sem);
if (S_ISDIR(inode->i_mode)) {
drop_nlink(dir);
update_inode_page(dir);
}
inode->i_ctime = CURRENT_TIME;
drop_nlink(inode);
if (S_ISDIR(inode->i_mode)) {
drop_nlink(inode);
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);
else
release_orphan_inode(sbi);
}
if (bit_pos == NR_DENTRY_IN_BLOCK) {
truncate_hole(dir, page->index, page->index + 1);
if (bit_pos == NR_DENTRY_IN_BLOCK &&
!truncate_hole(dir, page->index, page->index + 1)) {
clear_page_dirty_for_io(page);
ClearPagePrivate(page);
ClearPageUptodate(page);
inode_dec_dirty_pages(dir);
}
@ -628,11 +737,14 @@ bool f2fs_empty_dir(struct inode *dir)
unsigned long bidx;
struct page *dentry_page;
unsigned int bit_pos;
struct f2fs_dentry_block *dentry_blk;
struct f2fs_dentry_block *dentry_blk;
unsigned long nblock = dir_blocks(dir);
if (f2fs_has_inline_dentry(dir))
return f2fs_empty_inline_dir(dir);
for (bidx = 0; bidx < nblock; bidx++) {
dentry_page = get_lock_data_page(dir, bidx);
dentry_page = get_lock_data_page(dir, bidx, false);
if (IS_ERR(dentry_page)) {
if (PTR_ERR(dentry_page) == -ENOENT)
continue;
@ -640,7 +752,6 @@ bool f2fs_empty_dir(struct inode *dir)
return false;
}
dentry_blk = kmap_atomic(dentry_page);
if (bidx == 0)
bit_pos = 2;
@ -659,19 +770,93 @@ bool f2fs_empty_dir(struct inode *dir)
return true;
}
bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
unsigned int start_pos, struct fscrypt_str *fstr)
{
unsigned char d_type = DT_UNKNOWN;
unsigned int bit_pos;
struct f2fs_dir_entry *de = NULL;
struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
bit_pos = ((unsigned long)ctx->pos % d->max);
while (bit_pos < d->max) {
bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos);
if (bit_pos >= d->max)
break;
de = &d->dentry[bit_pos];
if (de->name_len == 0) {
bit_pos++;
ctx->pos = start_pos + bit_pos;
continue;
}
if (de->file_type < F2FS_FT_MAX)
d_type = f2fs_filetype_table[de->file_type];
else
d_type = DT_UNKNOWN;
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
if (f2fs_encrypted_inode(d->inode)) {
int save_len = fstr->len;
int ret;
de_name.name = kmalloc(de_name.len, GFP_NOFS);
if (!de_name.name)
return false;
memcpy(de_name.name, d->filename[bit_pos], de_name.len);
ret = fscrypt_fname_disk_to_usr(d->inode,
(u32)de->hash_code, 0,
&de_name, fstr);
kfree(de_name.name);
if (ret < 0)
return true;
de_name = *fstr;
fstr->len = save_len;
}
if (!dir_emit(ctx, de_name.name, de_name.len,
le32_to_cpu(de->ino), d_type))
return true;
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
ctx->pos = start_pos + bit_pos;
}
return false;
}
static int f2fs_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
unsigned long npages = dir_blocks(inode);
unsigned int bit_pos = 0;
struct f2fs_dentry_block *dentry_blk = NULL;
struct f2fs_dir_entry *de = NULL;
struct page *dentry_page = NULL;
struct file_ra_state *ra = &file->f_ra;
unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
unsigned char d_type = DT_UNKNOWN;
struct f2fs_dentry_ptr d;
struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
int err = 0;
bit_pos = ((unsigned long)ctx->pos % NR_DENTRY_IN_BLOCK);
if (f2fs_encrypted_inode(inode)) {
err = fscrypt_get_encryption_info(inode);
if (err && err != -ENOKEY)
return err;
err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
if (err < 0)
return err;
}
if (f2fs_has_inline_dentry(inode)) {
err = f2fs_read_inline_dir(file, ctx, &fstr);
goto out;
}
/* readahead for multi pages of dir */
if (npages - n > 1 && !ra_has_index(ra, n))
@ -679,44 +864,38 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
for (; n < npages; n++) {
dentry_page = get_lock_data_page(inode, n);
if (IS_ERR(dentry_page))
continue;
dentry_page = get_lock_data_page(inode, n, false);
if (IS_ERR(dentry_page)) {
err = PTR_ERR(dentry_page);
if (err == -ENOENT)
continue;
else
goto out;
}
dentry_blk = kmap(dentry_page);
while (bit_pos < NR_DENTRY_IN_BLOCK) {
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
NR_DENTRY_IN_BLOCK,
bit_pos);
if (bit_pos >= NR_DENTRY_IN_BLOCK)
break;
de = &dentry_blk->dentry[bit_pos];
if (de->file_type < F2FS_FT_MAX)
d_type = f2fs_filetype_table[de->file_type];
else
d_type = DT_UNKNOWN;
if (!dir_emit(ctx,
dentry_blk->filename[bit_pos],
le16_to_cpu(de->name_len),
le32_to_cpu(de->ino), d_type))
goto stop;
make_dentry_ptr(inode, &d, (void *)dentry_blk, 1);
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
ctx->pos = n * NR_DENTRY_IN_BLOCK + bit_pos;
if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) {
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
break;
}
bit_pos = 0;
ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
dentry_page = NULL;
}
stop:
if (dentry_page && !IS_ERR(dentry_page)) {
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
}
out:
fscrypt_fname_free_buffer(&fstr);
return err;
}
static int f2fs_dir_open(struct inode *inode, struct file *filp)
{
if (f2fs_encrypted_inode(inode))
return fscrypt_get_encryption_info(inode) ? -EACCES : 0;
return 0;
}
@ -725,5 +904,9 @@ const struct file_operations f2fs_dir_operations = {
.read = generic_read_dir,
.iterate = f2fs_readdir,
.fsync = f2fs_sync_file,
.open = f2fs_dir_open,
.unlocked_ioctl = f2fs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = f2fs_compat_ioctl,
#endif
};

736
fs/f2fs/extent_cache.c Normal file
View file

@ -0,0 +1,736 @@
/*
* f2fs extent cache support
*
* Copyright (c) 2015 Motorola Mobility
* Copyright (c) 2015 Samsung Electronics
* Authors: Jaegeuk Kim <jaegeuk@kernel.org>
* Chao Yu <chao2.yu@samsung.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include "f2fs.h"
#include "node.h"
#include <trace/events/f2fs.h>
static struct kmem_cache *extent_tree_slab;
static struct kmem_cache *extent_node_slab;
static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_info *ei,
struct rb_node *parent, struct rb_node **p)
{
struct extent_node *en;
en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC);
if (!en)
return NULL;
en->ei = *ei;
INIT_LIST_HEAD(&en->list);
en->et = et;
rb_link_node(&en->rb_node, parent, p);
rb_insert_color(&en->rb_node, &et->root);
atomic_inc(&et->node_cnt);
atomic_inc(&sbi->total_ext_node);
return en;
}
static void __detach_extent_node(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_node *en)
{
rb_erase(&en->rb_node, &et->root);
atomic_dec(&et->node_cnt);
atomic_dec(&sbi->total_ext_node);
if (et->cached_en == en)
et->cached_en = NULL;
kmem_cache_free(extent_node_slab, en);
}
/*
* Flow to release an extent_node:
* 1. list_del_init
* 2. __detach_extent_node
* 3. kmem_cache_free.
*/
static void __release_extent_node(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_node *en)
{
spin_lock(&sbi->extent_lock);
f2fs_bug_on(sbi, list_empty(&en->list));
list_del_init(&en->list);
spin_unlock(&sbi->extent_lock);
__detach_extent_node(sbi, et, en);
}
static struct extent_tree *__grab_extent_tree(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et;
nid_t ino = inode->i_ino;
down_write(&sbi->extent_tree_lock);
et = radix_tree_lookup(&sbi->extent_tree_root, ino);
if (!et) {
et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et);
memset(et, 0, sizeof(struct extent_tree));
et->ino = ino;
et->root = RB_ROOT;
et->cached_en = NULL;
rwlock_init(&et->lock);
INIT_LIST_HEAD(&et->list);
atomic_set(&et->node_cnt, 0);
atomic_inc(&sbi->total_ext_tree);
} else {
atomic_dec(&sbi->total_zombie_tree);
list_del_init(&et->list);
}
up_write(&sbi->extent_tree_lock);
/* never died until evict_inode */
F2FS_I(inode)->extent_tree = et;
return et;
}
static struct extent_node *__lookup_extent_tree(struct f2fs_sb_info *sbi,
struct extent_tree *et, unsigned int fofs)
{
struct rb_node *node = et->root.rb_node;
struct extent_node *en = et->cached_en;
if (en) {
struct extent_info *cei = &en->ei;
if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) {
stat_inc_cached_node_hit(sbi);
return en;
}
}
while (node) {
en = rb_entry(node, struct extent_node, rb_node);
if (fofs < en->ei.fofs) {
node = node->rb_left;
} else if (fofs >= en->ei.fofs + en->ei.len) {
node = node->rb_right;
} else {
stat_inc_rbtree_node_hit(sbi);
return en;
}
}
return NULL;
}
static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_info *ei)
{
struct rb_node **p = &et->root.rb_node;
struct extent_node *en;
en = __attach_extent_node(sbi, et, ei, NULL, p);
if (!en)
return NULL;
et->largest = en->ei;
et->cached_en = en;
return en;
}
static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
struct extent_tree *et)
{
struct rb_node *node, *next;
struct extent_node *en;
unsigned int count = atomic_read(&et->node_cnt);
node = rb_first(&et->root);
while (node) {
next = rb_next(node);
en = rb_entry(node, struct extent_node, rb_node);
__release_extent_node(sbi, et, en);
node = next;
}
return count - atomic_read(&et->node_cnt);
}
static void __drop_largest_extent(struct inode *inode,
pgoff_t fofs, unsigned int len)
{
struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs)
largest->len = 0;
}
/* return true, if inode page is changed */
bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et;
struct extent_node *en;
struct extent_info ei;
if (!f2fs_may_extent_tree(inode)) {
/* drop largest extent */
if (i_ext && i_ext->len) {
i_ext->len = 0;
return true;
}
return false;
}
et = __grab_extent_tree(inode);
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));
write_lock(&et->lock);
if (atomic_read(&et->node_cnt))
goto out;
en = __init_extent_tree(sbi, et, &ei);
if (en) {
spin_lock(&sbi->extent_lock);
list_add_tail(&en->list, &sbi->extent_list);
spin_unlock(&sbi->extent_lock);
}
out:
write_unlock(&et->lock);
return false;
}
static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
struct extent_info *ei)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et = F2FS_I(inode)->extent_tree;
struct extent_node *en;
bool ret = false;
f2fs_bug_on(sbi, !et);
trace_f2fs_lookup_extent_tree_start(inode, pgofs);
read_lock(&et->lock);
if (et->largest.fofs <= pgofs &&
et->largest.fofs + et->largest.len > pgofs) {
*ei = et->largest;
ret = true;
stat_inc_largest_node_hit(sbi);
goto out;
}
en = __lookup_extent_tree(sbi, et, pgofs);
if (en) {
*ei = en->ei;
spin_lock(&sbi->extent_lock);
if (!list_empty(&en->list)) {
list_move_tail(&en->list, &sbi->extent_list);
et->cached_en = en;
}
spin_unlock(&sbi->extent_lock);
ret = true;
}
out:
stat_inc_total_hit(sbi);
read_unlock(&et->lock);
trace_f2fs_lookup_extent_tree_end(inode, pgofs, ei);
return ret;
}
/*
* lookup extent at @fofs, if hit, return the extent
* if not, return NULL and
* @prev_ex: extent before fofs
* @next_ex: extent after fofs
* @insert_p: insert point for new extent at fofs
* in order to simpfy the insertion after.
* tree must stay unchanged between lookup and insertion.
*/
static struct extent_node *__lookup_extent_tree_ret(struct extent_tree *et,
unsigned int fofs,
struct extent_node **prev_ex,
struct extent_node **next_ex,
struct rb_node ***insert_p,
struct rb_node **insert_parent)
{
struct rb_node **pnode = &et->root.rb_node;
struct rb_node *parent = NULL, *tmp_node;
struct extent_node *en = et->cached_en;
*insert_p = NULL;
*insert_parent = NULL;
*prev_ex = NULL;
*next_ex = NULL;
if (RB_EMPTY_ROOT(&et->root))
return NULL;
if (en) {
struct extent_info *cei = &en->ei;
if (cei->fofs <= fofs && cei->fofs + cei->len > fofs)
goto lookup_neighbors;
}
while (*pnode) {
parent = *pnode;
en = rb_entry(*pnode, struct extent_node, rb_node);
if (fofs < en->ei.fofs)
pnode = &(*pnode)->rb_left;
else if (fofs >= en->ei.fofs + en->ei.len)
pnode = &(*pnode)->rb_right;
else
goto lookup_neighbors;
}
*insert_p = pnode;
*insert_parent = parent;
en = rb_entry(parent, struct extent_node, rb_node);
tmp_node = parent;
if (parent && fofs > en->ei.fofs)
tmp_node = rb_next(parent);
*next_ex = tmp_node ?
rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
tmp_node = parent;
if (parent && fofs < en->ei.fofs)
tmp_node = rb_prev(parent);
*prev_ex = tmp_node ?
rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
return NULL;
lookup_neighbors:
if (fofs == en->ei.fofs) {
/* lookup prev node for merging backward later */
tmp_node = rb_prev(&en->rb_node);
*prev_ex = tmp_node ?
rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
}
if (fofs == en->ei.fofs + en->ei.len - 1) {
/* lookup next node for merging frontward later */
tmp_node = rb_next(&en->rb_node);
*next_ex = tmp_node ?
rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
}
return en;
}
static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_info *ei,
struct extent_node *prev_ex,
struct extent_node *next_ex)
{
struct extent_node *en = NULL;
if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {
prev_ex->ei.len += ei->len;
ei = &prev_ex->ei;
en = prev_ex;
}
if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
if (en)
__release_extent_node(sbi, et, prev_ex);
next_ex->ei.fofs = ei->fofs;
next_ex->ei.blk = ei->blk;
next_ex->ei.len += ei->len;
en = next_ex;
}
if (!en)
return NULL;
__try_update_largest_extent(et, en);
spin_lock(&sbi->extent_lock);
if (!list_empty(&en->list)) {
list_move_tail(&en->list, &sbi->extent_list);
et->cached_en = en;
}
spin_unlock(&sbi->extent_lock);
return en;
}
static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_info *ei,
struct rb_node **insert_p,
struct rb_node *insert_parent)
{
struct rb_node **p = &et->root.rb_node;
struct rb_node *parent = NULL;
struct extent_node *en = NULL;
if (insert_p && insert_parent) {
parent = insert_parent;
p = insert_p;
goto do_insert;
}
while (*p) {
parent = *p;
en = rb_entry(parent, struct extent_node, rb_node);
if (ei->fofs < en->ei.fofs)
p = &(*p)->rb_left;
else if (ei->fofs >= en->ei.fofs + en->ei.len)
p = &(*p)->rb_right;
else
f2fs_bug_on(sbi, 1);
}
do_insert:
en = __attach_extent_node(sbi, et, ei, parent, p);
if (!en)
return NULL;
__try_update_largest_extent(et, en);
/* update in global extent list */
spin_lock(&sbi->extent_lock);
list_add_tail(&en->list, &sbi->extent_list);
et->cached_en = en;
spin_unlock(&sbi->extent_lock);
return en;
}
static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
pgoff_t fofs, block_t blkaddr, unsigned int len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et = F2FS_I(inode)->extent_tree;
struct extent_node *en = NULL, *en1 = NULL;
struct extent_node *prev_en = NULL, *next_en = NULL;
struct extent_info ei, dei, prev;
struct rb_node **insert_p = NULL, *insert_parent = NULL;
unsigned int end = fofs + len;
unsigned int pos = (unsigned int)fofs;
if (!et)
return false;
trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
write_lock(&et->lock);
if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) {
write_unlock(&et->lock);
return false;
}
prev = et->largest;
dei.len = 0;
/*
* drop largest extent before lookup, in case it's already
* been shrunk from extent tree
*/
__drop_largest_extent(inode, fofs, len);
/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
en = __lookup_extent_tree_ret(et, fofs, &prev_en, &next_en,
&insert_p, &insert_parent);
if (!en)
en = next_en;
/* 2. invlidate all extent nodes in range [fofs, fofs + len - 1] */
while (en && en->ei.fofs < end) {
unsigned int org_end;
int parts = 0; /* # of parts current extent split into */
next_en = en1 = NULL;
dei = en->ei;
org_end = dei.fofs + dei.len;
f2fs_bug_on(sbi, pos >= org_end);
if (pos > dei.fofs && pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
en->ei.len = pos - en->ei.fofs;
prev_en = en;
parts = 1;
}
if (end < org_end && org_end - end >= F2FS_MIN_EXTENT_LEN) {
if (parts) {
set_extent_info(&ei, end,
end - dei.fofs + dei.blk,
org_end - end);
en1 = __insert_extent_tree(sbi, et, &ei,
NULL, NULL);
next_en = en1;
} else {
en->ei.fofs = end;
en->ei.blk += end - dei.fofs;
en->ei.len -= end - dei.fofs;
next_en = en;
}
parts++;
}
if (!next_en) {
struct rb_node *node = rb_next(&en->rb_node);
next_en = node ?
rb_entry(node, struct extent_node, rb_node)
: NULL;
}
if (parts)
__try_update_largest_extent(et, en);
else
__release_extent_node(sbi, et, en);
/*
* if original extent is split into zero or two parts, extent
* tree has been altered by deletion or insertion, therefore
* invalidate pointers regard to tree.
*/
if (parts != 1) {
insert_p = NULL;
insert_parent = NULL;
}
en = next_en;
}
/* 3. update extent in extent cache */
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,
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);
}
}
if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
__free_extent_tree(sbi, et);
write_unlock(&et->lock);
return !__is_extent_same(&prev, &et->largest);
}
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct extent_tree *et, *next;
struct extent_node *en;
unsigned int node_cnt = 0, tree_cnt = 0;
int remained;
if (!test_opt(sbi, EXTENT_CACHE))
return 0;
if (!atomic_read(&sbi->total_zombie_tree))
goto free_node;
if (!down_write_trylock(&sbi->extent_tree_lock))
goto out;
/* 1. remove unreferenced extent tree */
list_for_each_entry_safe(et, next, &sbi->zombie_list, list) {
if (atomic_read(&et->node_cnt)) {
write_lock(&et->lock);
node_cnt += __free_extent_tree(sbi, et);
write_unlock(&et->lock);
}
f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
list_del_init(&et->list);
radix_tree_delete(&sbi->extent_tree_root, et->ino);
kmem_cache_free(extent_tree_slab, et);
atomic_dec(&sbi->total_ext_tree);
atomic_dec(&sbi->total_zombie_tree);
tree_cnt++;
if (node_cnt + tree_cnt >= nr_shrink)
goto unlock_out;
cond_resched();
}
up_write(&sbi->extent_tree_lock);
free_node:
/* 2. remove LRU extent entries */
if (!down_write_trylock(&sbi->extent_tree_lock))
goto out;
remained = nr_shrink - (node_cnt + tree_cnt);
spin_lock(&sbi->extent_lock);
for (; remained > 0; remained--) {
if (list_empty(&sbi->extent_list))
break;
en = list_first_entry(&sbi->extent_list,
struct extent_node, list);
et = en->et;
if (!write_trylock(&et->lock)) {
/* refresh this extent node's position in extent list */
list_move_tail(&en->list, &sbi->extent_list);
continue;
}
list_del_init(&en->list);
spin_unlock(&sbi->extent_lock);
__detach_extent_node(sbi, et, en);
write_unlock(&et->lock);
node_cnt++;
spin_lock(&sbi->extent_lock);
}
spin_unlock(&sbi->extent_lock);
unlock_out:
up_write(&sbi->extent_tree_lock);
out:
trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
return node_cnt + tree_cnt;
}
unsigned int f2fs_destroy_extent_node(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et = F2FS_I(inode)->extent_tree;
unsigned int node_cnt = 0;
if (!et || !atomic_read(&et->node_cnt))
return 0;
write_lock(&et->lock);
node_cnt = __free_extent_tree(sbi, et);
write_unlock(&et->lock);
return node_cnt;
}
void f2fs_destroy_extent_tree(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et = F2FS_I(inode)->extent_tree;
unsigned int node_cnt = 0;
if (!et)
return;
if (inode->i_nlink && !is_bad_inode(inode) &&
atomic_read(&et->node_cnt)) {
down_write(&sbi->extent_tree_lock);
list_add_tail(&et->list, &sbi->zombie_list);
atomic_inc(&sbi->total_zombie_tree);
up_write(&sbi->extent_tree_lock);
return;
}
/* free all extent info belong to this extent tree */
node_cnt = f2fs_destroy_extent_node(inode);
/* delete extent tree entry in radix tree */
down_write(&sbi->extent_tree_lock);
f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
kmem_cache_free(extent_tree_slab, et);
atomic_dec(&sbi->total_ext_tree);
up_write(&sbi->extent_tree_lock);
F2FS_I(inode)->extent_tree = NULL;
trace_f2fs_destroy_extent_tree(inode, node_cnt);
}
bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
struct extent_info *ei)
{
if (!f2fs_may_extent_tree(inode))
return false;
return f2fs_lookup_extent_tree(inode, pgofs, ei);
}
void f2fs_update_extent_cache(struct dnode_of_data *dn)
{
pgoff_t fofs;
block_t blkaddr;
if (!f2fs_may_extent_tree(dn->inode))
return;
if (dn->data_blkaddr == NEW_ADDR)
blkaddr = NULL_ADDR;
else
blkaddr = dn->data_blkaddr;
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);
}
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
pgoff_t fofs, block_t blkaddr, unsigned int len)
{
if (!f2fs_may_extent_tree(dn->inode))
return;
if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len))
sync_inode_page(dn);
}
void init_extent_cache_info(struct f2fs_sb_info *sbi)
{
INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
init_rwsem(&sbi->extent_tree_lock);
INIT_LIST_HEAD(&sbi->extent_list);
spin_lock_init(&sbi->extent_lock);
atomic_set(&sbi->total_ext_tree, 0);
INIT_LIST_HEAD(&sbi->zombie_list);
atomic_set(&sbi->total_zombie_tree, 0);
atomic_set(&sbi->total_ext_node, 0);
}
int __init create_extent_cache(void)
{
extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree",
sizeof(struct extent_tree));
if (!extent_tree_slab)
return -ENOMEM;
extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node",
sizeof(struct extent_node));
if (!extent_node_slab) {
kmem_cache_destroy(extent_tree_slab);
return -ENOMEM;
}
return 0;
}
void destroy_extent_cache(void)
{
kmem_cache_destroy(extent_node_slab);
kmem_cache_destroy(extent_tree_slab);
}

1066
fs/f2fs/f2fs.h
View file

File diff suppressed because it is too large Load diff

1282
fs/f2fs/file.c
View file

File diff suppressed because it is too large Load diff

538
fs/f2fs/gc.c
View file

@ -16,7 +16,6 @@
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/freezer.h>
#include <linux/blkdev.h>
#include "f2fs.h"
#include "node.h"
@ -24,8 +23,6 @@
#include "gc.h"
#include <trace/events/f2fs.h>
static struct kmem_cache *winode_slab;
static int gc_thread_func(void *data)
{
struct f2fs_sb_info *sbi = data;
@ -46,7 +43,7 @@ static int gc_thread_func(void *data)
break;
if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
wait_ms = increase_sleep_time(gc_th, wait_ms);
increase_sleep_time(gc_th, &wait_ms);
continue;
}
@ -67,22 +64,25 @@ static int gc_thread_func(void *data)
continue;
if (!is_idle(sbi)) {
wait_ms = increase_sleep_time(gc_th, wait_ms);
increase_sleep_time(gc_th, &wait_ms);
mutex_unlock(&sbi->gc_mutex);
continue;
}
if (has_enough_invalid_blocks(sbi))
wait_ms = decrease_sleep_time(gc_th, wait_ms);
decrease_sleep_time(gc_th, &wait_ms);
else
wait_ms = increase_sleep_time(gc_th, wait_ms);
increase_sleep_time(gc_th, &wait_ms);
stat_inc_bggc_count(sbi);
/* if return value is not zero, no victim was selected */
if (f2fs_gc(sbi))
if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC)))
wait_ms = gc_th->no_gc_sleep_time;
trace_f2fs_background_gc(sbi->sb, wait_ms,
prefree_segments(sbi), free_segments(sbi));
/* balancing f2fs's metadata periodically */
f2fs_balance_fs_bg(sbi);
@ -96,8 +96,6 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
dev_t dev = sbi->sb->s_bdev->bd_dev;
int err = 0;
if (!test_opt(sbi, BG_GC))
goto out;
gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
if (!gc_th) {
err = -ENOMEM;
@ -174,9 +172,9 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
{
/* SSR allocates in a segment unit */
if (p->alloc_mode == SSR)
return 1 << sbi->log_blocks_per_seg;
return sbi->blocks_per_seg;
if (p->gc_mode == GC_GREEDY)
return (1 << sbi->log_blocks_per_seg) * p->ofs_unit;
return sbi->blocks_per_seg * p->ofs_unit;
else if (p->gc_mode == GC_CB)
return UINT_MAX;
else /* No other gc_mode */
@ -247,6 +245,18 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
return get_cb_cost(sbi, segno);
}
static unsigned int count_bits(const unsigned long *addr,
unsigned int offset, unsigned int len)
{
unsigned int end = offset + len, sum = 0;
while (offset < end) {
if (test_bit(offset++, addr))
++sum;
}
return sum;
}
/*
* This function is called from two paths.
* One is garbage collection and the other is SSR segment selection.
@ -260,8 +270,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct victim_sel_policy p;
unsigned int secno, max_cost;
int nsearched = 0;
unsigned int secno, max_cost, last_victim;
unsigned int last_segment = MAIN_SEGS(sbi);
unsigned int nsearched = 0;
mutex_lock(&dirty_i->seglist_lock);
@ -271,6 +282,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
p.min_segno = NULL_SEGNO;
p.min_cost = max_cost = get_max_cost(sbi, &p);
if (p.max_search == 0)
goto out;
last_victim = sbi->last_victim[p.gc_mode];
if (p.alloc_mode == LFS && gc_type == FG_GC) {
p.min_segno = check_bg_victims(sbi);
if (p.min_segno != NULL_SEGNO)
@ -281,9 +296,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
unsigned long cost;
unsigned int segno;
segno = find_next_bit(p.dirty_segmap, MAIN_SEGS(sbi), p.offset);
if (segno >= MAIN_SEGS(sbi)) {
segno = find_next_bit(p.dirty_segmap, last_segment, p.offset);
if (segno >= last_segment) {
if (sbi->last_victim[p.gc_mode]) {
last_segment = sbi->last_victim[p.gc_mode];
sbi->last_victim[p.gc_mode] = 0;
p.offset = 0;
continue;
@ -292,27 +308,35 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
}
p.offset = segno + p.ofs_unit;
if (p.ofs_unit > 1)
if (p.ofs_unit > 1) {
p.offset -= segno % p.ofs_unit;
nsearched += count_bits(p.dirty_segmap,
p.offset - p.ofs_unit,
p.ofs_unit);
} else {
nsearched++;
}
secno = GET_SECNO(sbi, segno);
if (sec_usage_check(sbi, secno))
continue;
goto next;
if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
continue;
goto next;
cost = get_gc_cost(sbi, segno, &p);
if (p.min_cost > cost) {
p.min_segno = segno;
p.min_cost = cost;
} else if (unlikely(cost == max_cost)) {
continue;
}
if (nsearched++ >= p.max_search) {
sbi->last_victim[p.gc_mode] = segno;
next:
if (nsearched >= p.max_search) {
if (!sbi->last_victim[p.gc_mode] && segno <= last_victim)
sbi->last_victim[p.gc_mode] = last_victim + 1;
else
sbi->last_victim[p.gc_mode] = segno + 1;
break;
}
}
@ -331,6 +355,7 @@ got_it:
sbi->cur_victim_sec,
prefree_segments(sbi), free_segments(sbi));
}
out:
mutex_unlock(&dirty_i->seglist_lock);
return (p.min_segno == NULL_SEGNO) ? 0 : 1;
@ -340,37 +365,39 @@ static const struct victim_selection default_v_ops = {
.get_victim = get_victim_by_default,
};
static struct inode *find_gc_inode(nid_t ino, struct list_head *ilist)
static struct inode *find_gc_inode(struct gc_inode_list *gc_list, nid_t ino)
{
struct inode_entry *ie;
list_for_each_entry(ie, ilist, list)
if (ie->inode->i_ino == ino)
return ie->inode;
ie = radix_tree_lookup(&gc_list->iroot, ino);
if (ie)
return ie->inode;
return NULL;
}
static void add_gc_inode(struct inode *inode, struct list_head *ilist)
static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
{
struct inode_entry *new_ie;
if (inode == find_gc_inode(inode->i_ino, ilist)) {
if (inode == find_gc_inode(gc_list, inode->i_ino)) {
iput(inode);
return;
}
new_ie = f2fs_kmem_cache_alloc(winode_slab, GFP_NOFS);
new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
new_ie->inode = inode;
list_add_tail(&new_ie->list, ilist);
f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie);
list_add_tail(&new_ie->list, &gc_list->ilist);
}
static void put_gc_inode(struct list_head *ilist)
static void put_gc_inode(struct gc_inode_list *gc_list)
{
struct inode_entry *ie, *next_ie;
list_for_each_entry_safe(ie, next_ie, ilist, list) {
list_for_each_entry_safe(ie, next_ie, &gc_list->ilist, list) {
radix_tree_delete(&gc_list->iroot, ie->inode->i_ino);
iput(ie->inode);
list_del(&ie->list);
kmem_cache_free(winode_slab, ie);
kmem_cache_free(inode_entry_slab, ie);
}
}
@ -398,14 +425,18 @@ static void gc_node_segment(struct f2fs_sb_info *sbi,
{
bool initial = true;
struct f2fs_summary *entry;
block_t start_addr;
int off;
start_addr = START_BLOCK(sbi, segno);
next_step:
entry = sum;
for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
nid_t nid = le32_to_cpu(entry->nid);
struct page *node_page;
struct node_info ni;
/* stop BG_GC if there is not enough free sections. */
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
@ -428,38 +459,28 @@ next_step:
continue;
}
get_node_info(sbi, nid, &ni);
if (ni.blk_addr != start_addr + off) {
f2fs_put_page(node_page, 1);
continue;
}
/* set page dirty and write it */
if (gc_type == FG_GC) {
f2fs_wait_on_page_writeback(node_page, NODE);
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);
stat_inc_node_blk_count(sbi, 1);
stat_inc_node_blk_count(sbi, 1, gc_type);
}
if (initial) {
initial = false;
goto next_step;
}
if (gc_type == FG_GC) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
sync_node_pages(sbi, 0, &wbc);
/*
* In the case of FG_GC, it'd be better to reclaim this victim
* completely.
*/
if (get_valid_blocks(sbi, segno, 1) != 0)
goto next_step;
}
}
/*
@ -469,7 +490,7 @@ next_step:
* as indirect or double indirect node blocks, are given, it must be a caller's
* bug.
*/
block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
{
unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
unsigned int bidx;
@ -486,10 +507,10 @@ block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
bidx = node_ofs - 5 - dec;
}
return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi);
return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode);
}
static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
struct node_info *dni, block_t blkaddr, unsigned int *nofs)
{
struct page *node_page;
@ -502,13 +523,13 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
node_page = get_node_page(sbi, nid);
if (IS_ERR(node_page))
return 0;
return false;
get_node_info(sbi, nid, dni);
if (sum->version != dni->version) {
f2fs_put_page(node_page, 1);
return 0;
return false;
}
*nofs = ofs_of_node(node_page);
@ -516,16 +537,116 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
f2fs_put_page(node_page, 1);
if (source_blkaddr != blkaddr)
return 0;
return 1;
return false;
return true;
}
static void move_data_page(struct inode *inode, struct page *page, int gc_type)
static void move_encrypted_block(struct inode *inode, block_t bidx)
{
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
.type = DATA,
.rw = WRITE_SYNC,
.rw = READ_SYNC,
.encrypted_page = NULL,
};
struct dnode_of_data dn;
struct f2fs_summary sum;
struct node_info ni;
struct page *page;
block_t newaddr;
int err;
/* do not read out */
page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
if (!page)
return;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
if (err)
goto out;
if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
ClearPageUptodate(page);
goto put_out;
}
/*
* don't cache encrypted data into meta inode until previous dirty
* data were writebacked to avoid racing between GC and flush.
*/
f2fs_wait_on_page_writeback(page, DATA, true);
get_node_info(fio.sbi, dn.nid, &ni);
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
/* read page */
fio.page = page;
fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
&sum, CURSEG_COLD_DATA);
fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
FGP_LOCK | FGP_CREAT, GFP_NOFS);
if (!fio.encrypted_page) {
err = -ENOMEM;
goto recover_block;
}
err = f2fs_submit_page_bio(&fio);
if (err)
goto put_page_out;
/* write page */
lock_page(fio.encrypted_page);
if (unlikely(!PageUptodate(fio.encrypted_page))) {
err = -EIO;
goto put_page_out;
}
if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
err = -EIO;
goto put_page_out;
}
set_page_dirty(fio.encrypted_page);
f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true);
if (clear_page_dirty_for_io(fio.encrypted_page))
dec_page_count(fio.sbi, F2FS_DIRTY_META);
set_page_writeback(fio.encrypted_page);
/* allocate block address */
f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
fio.rw = 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);
if (page->index == 0)
set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
put_page_out:
f2fs_put_page(fio.encrypted_page, 1);
recover_block:
if (err)
__f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
true, true);
put_out:
f2fs_put_dnode(&dn);
out:
f2fs_put_page(page, 1);
}
static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
{
struct page *page;
page = get_lock_data_page(inode, bidx, true);
if (IS_ERR(page))
return;
if (gc_type == BG_GC) {
if (PageWriteback(page))
@ -533,12 +654,19 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type)
set_page_dirty(page);
set_cold_data(page);
} else {
f2fs_wait_on_page_writeback(page, DATA);
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
.type = DATA,
.rw = WRITE_SYNC,
.page = page,
.encrypted_page = NULL,
};
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(page, &fio);
do_write_data_page(&fio);
clear_cold_data(page);
}
out:
@ -553,7 +681,7 @@ out:
* the victim data block is ignored.
*/
static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
struct list_head *ilist, unsigned int segno, int gc_type)
struct gc_inode_list *gc_list, unsigned int segno, int gc_type)
{
struct super_block *sb = sbi->sb;
struct f2fs_summary *entry;
@ -586,7 +714,7 @@ next_step:
}
/* Get an inode by ino with checking validity */
if (check_dnode(sbi, entry, &dni, start_addr + off, &nofs) == 0)
if (!is_alive(sbi, entry, &dni, start_addr + off, &nofs))
continue;
if (phase == 1) {
@ -601,141 +729,199 @@ next_step:
if (IS_ERR(inode) || is_bad_inode(inode))
continue;
start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
/* if encrypted inode, let's go phase 3 */
if (f2fs_encrypted_inode(inode) &&
S_ISREG(inode->i_mode)) {
add_gc_inode(gc_list, inode);
continue;
}
data_page = find_data_page(inode,
start_bidx + ofs_in_node, false);
if (IS_ERR(data_page))
goto next_iput;
start_bidx = start_bidx_of_node(nofs, inode);
data_page = get_read_data_page(inode,
start_bidx + ofs_in_node, READA, true);
if (IS_ERR(data_page)) {
iput(inode);
continue;
}
f2fs_put_page(data_page, 0);
add_gc_inode(inode, ilist);
} else {
inode = find_gc_inode(dni.ino, ilist);
if (inode) {
start_bidx = start_bidx_of_node(nofs,
F2FS_I(inode));
data_page = get_lock_data_page(inode,
start_bidx + ofs_in_node);
if (IS_ERR(data_page))
continue;
move_data_page(inode, data_page, gc_type);
stat_inc_data_blk_count(sbi, 1);
}
add_gc_inode(gc_list, inode);
continue;
}
/* phase 3 */
inode = find_gc_inode(gc_list, dni.ino);
if (inode) {
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);
stat_inc_data_blk_count(sbi, 1, gc_type);
}
continue;
next_iput:
iput(inode);
}
if (++phase < 4)
goto next_step;
if (gc_type == FG_GC) {
f2fs_submit_merged_bio(sbi, DATA, WRITE);
/*
* In the case of FG_GC, it'd be better to reclaim this victim
* completely.
*/
if (get_valid_blocks(sbi, segno, 1) != 0) {
phase = 2;
goto next_step;
}
}
}
static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
int gc_type, int type)
int gc_type)
{
struct sit_info *sit_i = SIT_I(sbi);
int ret;
mutex_lock(&sit_i->sentry_lock);
ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type, type, LFS);
ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type,
NO_CHECK_TYPE, LFS);
mutex_unlock(&sit_i->sentry_lock);
return ret;
}
static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
struct list_head *ilist, int gc_type)
static int do_garbage_collect(struct f2fs_sb_info *sbi,
unsigned int start_segno,
struct gc_inode_list *gc_list, int gc_type)
{
struct page *sum_page;
struct f2fs_summary_block *sum;
struct blk_plug plug;
/* read segment summary of victim */
sum_page = get_sum_page(sbi, segno);
blk_start_plug(&plug);
sum = page_address(sum_page);
switch (GET_SUM_TYPE((&sum->footer))) {
case SUM_TYPE_NODE:
gc_node_segment(sbi, sum->entries, segno, gc_type);
break;
case SUM_TYPE_DATA:
gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
break;
}
blk_finish_plug(&plug);
stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)));
stat_inc_call_count(sbi->stat_info);
f2fs_put_page(sum_page, 1);
}
int f2fs_gc(struct f2fs_sb_info *sbi)
{
struct list_head ilist;
unsigned int segno, i;
int gc_type = BG_GC;
int nfree = 0;
int ret = -1;
struct cp_control cpc = {
.reason = CP_SYNC,
};
INIT_LIST_HEAD(&ilist);
gc_more:
if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
goto stop;
if (unlikely(f2fs_cp_error(sbi)))
goto stop;
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) {
gc_type = FG_GC;
write_checkpoint(sbi, &cpc);
}
if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
goto stop;
ret = 0;
unsigned int segno = start_segno;
unsigned int end_segno = start_segno + sbi->segs_per_sec;
int seg_freed = 0;
unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
SUM_TYPE_DATA : SUM_TYPE_NODE;
/* readahead multi ssa blocks those have contiguous address */
if (sbi->segs_per_sec > 1)
ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec,
META_SSA);
ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
sbi->segs_per_sec, META_SSA, true);
for (i = 0; i < sbi->segs_per_sec; i++)
do_garbage_collect(sbi, segno + i, &ilist, gc_type);
if (gc_type == FG_GC) {
sbi->cur_victim_sec = NULL_SEGNO;
nfree++;
WARN_ON(get_valid_blocks(sbi, segno, sbi->segs_per_sec));
/* reference all summary page */
while (segno < end_segno) {
sum_page = get_sum_page(sbi, segno++);
unlock_page(sum_page);
}
if (has_not_enough_free_secs(sbi, nfree))
goto gc_more;
blk_start_plug(&plug);
for (segno = start_segno; segno < end_segno; segno++) {
/* find segment summary of victim */
sum_page = find_get_page(META_MAPPING(sbi),
GET_SUM_BLOCK(sbi, segno));
f2fs_bug_on(sbi, !PageUptodate(sum_page));
f2fs_put_page(sum_page, 0);
sum = page_address(sum_page);
f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
/*
* this is to avoid deadlock:
* - lock_page(sum_page) - f2fs_replace_block
* - check_valid_map() - mutex_lock(sentry_lock)
* - mutex_lock(sentry_lock) - change_curseg()
* - lock_page(sum_page)
*/
if (type == SUM_TYPE_NODE)
gc_node_segment(sbi, sum->entries, segno, gc_type);
else
gc_data_segment(sbi, sum->entries, gc_list, segno,
gc_type);
stat_inc_seg_count(sbi, type, gc_type);
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);
}
}
blk_finish_plug(&plug);
if (gc_type == FG_GC) {
while (start_segno < end_segno)
if (get_valid_blocks(sbi, start_segno++, 1) == 0)
seg_freed++;
}
stat_inc_call_count(sbi->stat_info);
return seg_freed;
}
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
{
unsigned int segno;
int gc_type = sync ? FG_GC : BG_GC;
int sec_freed = 0, seg_freed;
int ret = -EINVAL;
struct cp_control cpc;
struct gc_inode_list gc_list = {
.ilist = LIST_HEAD_INIT(gc_list.ilist),
.iroot = RADIX_TREE_INIT(GFP_NOFS),
};
cpc.reason = __get_cp_reason(sbi);
gc_more:
segno = NULL_SEGNO;
if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
goto stop;
if (unlikely(f2fs_cp_error(sbi))) {
ret = -EIO;
goto stop;
}
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
gc_type = FG_GC;
/*
* If there is no victim and no prefree segment but still not
* enough free sections, we should flush dent/node blocks and do
* garbage collections.
*/
if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
write_checkpoint(sbi, &cpc);
else if (has_not_enough_free_secs(sbi, 0))
write_checkpoint(sbi, &cpc);
}
if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
goto stop;
ret = 0;
seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
sec_freed++;
if (gc_type == FG_GC)
write_checkpoint(sbi, &cpc);
sbi->cur_victim_sec = NULL_SEGNO;
if (!sync) {
if (has_not_enough_free_secs(sbi, sec_freed))
goto gc_more;
if (gc_type == FG_GC)
write_checkpoint(sbi, &cpc);
}
stop:
mutex_unlock(&sbi->gc_mutex);
put_gc_inode(&ilist);
put_gc_inode(&gc_list);
if (sync)
ret = sec_freed ? 0 : -EAGAIN;
return ret;
}
@ -743,17 +929,3 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
{
DIRTY_I(sbi)->v_ops = &default_v_ops;
}
int __init create_gc_caches(void)
{
winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
sizeof(struct inode_entry));
if (!winode_slab)
return -ENOMEM;
return 0;
}
void destroy_gc_caches(void)
{
kmem_cache_destroy(winode_slab);
}

42
fs/f2fs/gc.h
View file

@ -35,9 +35,9 @@ struct f2fs_gc_kthread {
unsigned int gc_idle;
};
struct inode_entry {
struct list_head list;
struct inode *inode;
struct gc_inode_list {
struct list_head ilist;
struct radix_tree_root iroot;
};
/*
@ -64,26 +64,26 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
}
static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th,
long *wait)
{
if (wait == gc_th->no_gc_sleep_time)
return wait;
if (*wait == gc_th->no_gc_sleep_time)
return;
wait += gc_th->min_sleep_time;
if (wait > gc_th->max_sleep_time)
wait = gc_th->max_sleep_time;
return wait;
*wait += gc_th->min_sleep_time;
if (*wait > gc_th->max_sleep_time)
*wait = gc_th->max_sleep_time;
}
static inline long decrease_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
long *wait)
{
if (wait == gc_th->no_gc_sleep_time)
wait = gc_th->max_sleep_time;
if (*wait == gc_th->no_gc_sleep_time)
*wait = gc_th->max_sleep_time;
wait -= gc_th->min_sleep_time;
if (wait <= gc_th->min_sleep_time)
wait = gc_th->min_sleep_time;
return wait;
*wait -= gc_th->min_sleep_time;
if (*wait <= gc_th->min_sleep_time)
*wait = gc_th->min_sleep_time;
}
static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
@ -100,11 +100,3 @@ static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
return true;
return false;
}
static inline int is_idle(struct f2fs_sb_info *sbi)
{
struct block_device *bdev = sbi->sb->s_bdev;
struct request_queue *q = bdev_get_queue(bdev);
struct request_list *rl = &q->root_rl;
return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
}

3
fs/f2fs/hash.c
View file

@ -79,8 +79,7 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
const unsigned char *name = name_info->name;
size_t len = name_info->len;
if ((len <= 2) && (name[0] == '.') &&
(name[1] == '.' || name[1] == '\0'))
if (is_dot_dotdot(name_info))
return 0;
/* Initialize the default seed for the hash checksum functions */

603
fs/f2fs/inline.c
View file

@ -12,38 +12,74 @@
#include <linux/f2fs_fs.h>
#include "f2fs.h"
#include "node.h"
bool f2fs_may_inline(struct inode *inode)
bool f2fs_may_inline_data(struct inode *inode)
{
block_t nr_blocks;
loff_t i_size;
if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
return false;
if (f2fs_is_atomic_file(inode))
return false;
nr_blocks = F2FS_I(inode)->i_xattr_nid ? 3 : 2;
if (inode->i_blocks > nr_blocks)
if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
return false;
i_size = i_size_read(inode);
if (i_size > MAX_INLINE_DATA)
if (i_size_read(inode) > MAX_INLINE_DATA)
return false;
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
return false;
return true;
}
bool f2fs_may_inline_dentry(struct inode *inode)
{
if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY))
return false;
if (!S_ISDIR(inode->i_mode))
return false;
return true;
}
void read_inline_data(struct page *page, struct page *ipage)
{
void *src_addr, *dst_addr;
if (PageUptodate(page))
return;
f2fs_bug_on(F2FS_P_SB(page), page->index);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(ipage);
dst_addr = kmap_atomic(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
flush_dcache_page(page);
kunmap_atomic(dst_addr);
SetPageUptodate(page);
}
bool truncate_inline_inode(struct page *ipage, u64 from)
{
void *addr;
if (from >= MAX_INLINE_DATA)
return false;
addr = inline_data_addr(ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true);
memset(addr + from, 0, MAX_INLINE_DATA - from);
return true;
}
int f2fs_read_inline_data(struct inode *inode, struct page *page)
{
struct page *ipage;
void *src_addr, *dst_addr;
if (page->index) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
goto out;
}
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage)) {
@ -51,112 +87,111 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
return PTR_ERR(ipage);
}
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
if (!f2fs_has_inline_data(inode)) {
f2fs_put_page(ipage, 1);
return -EAGAIN;
}
/* Copy the whole inline data block */
src_addr = inline_data_addr(ipage);
dst_addr = kmap(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap(page);
f2fs_put_page(ipage, 1);
if (page->index)
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
else
read_inline_data(page, ipage);
out:
SetPageUptodate(page);
f2fs_put_page(ipage, 1);
unlock_page(page);
return 0;
}
static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
{
int err = 0;
struct page *ipage;
struct dnode_of_data dn;
void *src_addr, *dst_addr;
block_t new_blk_addr;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
};
int dirty, err;
if (!f2fs_exist_data(dn->inode))
goto clear_out;
err = f2fs_reserve_block(dn, 0);
if (err)
return err;
f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
read_inline_data(page, dn->inode_page);
set_page_dirty(page);
/* clear dirty state */
dirty = clear_page_dirty_for_io(page);
/* write data page to try to make data consistent */
set_page_writeback(page);
fio.old_blkaddr = dn->data_blkaddr;
write_data_page(dn, &fio);
f2fs_wait_on_page_writeback(page, DATA, true);
if (dirty)
inode_dec_dirty_pages(dn->inode);
/* this converted inline_data should be recovered. */
set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode_page, 0);
clear_inline_node(dn->inode_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;
}
int f2fs_convert_inline_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
struct page *ipage, *page;
int err = 0;
if (!f2fs_has_inline_data(inode))
return 0;
page = grab_cache_page(inode->i_mapping, 0);
if (!page)
return -ENOMEM;
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
/* someone else converted inline_data already */
if (!f2fs_has_inline_data(inode))
goto out;
set_new_dnode(&dn, inode, ipage, ipage, 0);
/*
* i_addr[0] is not used for inline data,
* so reserving new block will not destroy inline data
*/
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, 0);
if (err)
goto out;
if (f2fs_has_inline_data(inode))
err = f2fs_convert_inline_page(&dn, page);
f2fs_wait_on_page_writeback(page, DATA);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(ipage);
dst_addr = kmap(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap(page);
SetPageUptodate(page);
/* write data page to try to make data consistent */
set_page_writeback(page);
write_data_page(page, &dn, &new_blk_addr, &fio);
update_extent_cache(new_blk_addr, &dn);
f2fs_wait_on_page_writeback(page, DATA);
/* clear inline data and flag after data writeback */
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
stat_dec_inline_inode(inode);
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
out:
f2fs_unlock_op(sbi);
f2fs_put_page(page, 1);
f2fs_balance_fs(sbi, dn.node_changed);
return err;
}
int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size,
struct page *page)
{
struct page *new_page = page;
int err;
if (!f2fs_has_inline_data(inode))
return 0;
else if (to_size <= MAX_INLINE_DATA)
return 0;
if (!page || page->index != 0) {
new_page = grab_cache_page(inode->i_mapping, 0);
if (!new_page)
return -ENOMEM;
}
err = __f2fs_convert_inline_data(inode, new_page);
if (!page || page->index != 0)
f2fs_put_page(new_page, 1);
return err;
}
int f2fs_write_inline_data(struct inode *inode,
struct page *page, unsigned size)
int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
struct page *ipage;
struct dnode_of_data dn;
int err;
@ -164,49 +199,29 @@ int f2fs_write_inline_data(struct inode *inode,
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
ipage = dn.inode_page;
f2fs_wait_on_page_writeback(ipage, NODE);
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
src_addr = kmap(page);
dst_addr = inline_data_addr(ipage);
memcpy(dst_addr, src_addr, size);
kunmap(page);
/* Release the first data block if it is allocated */
if (!f2fs_has_inline_data(inode)) {
truncate_data_blocks_range(&dn, 1);
set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
stat_inc_inline_inode(inode);
f2fs_put_dnode(&dn);
return -EAGAIN;
}
f2fs_bug_on(F2FS_I_SB(inode), page->index);
f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
src_addr = kmap_atomic(page);
dst_addr = inline_data_addr(dn.inode_page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap_atomic(src_addr);
set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
sync_inode_page(&dn);
clear_inline_node(dn.inode_page);
f2fs_put_dnode(&dn);
return 0;
}
void truncate_inline_data(struct inode *inode, u64 from)
{
struct page *ipage;
if (from >= MAX_INLINE_DATA)
return;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return;
f2fs_wait_on_page_writeback(ipage, NODE);
zero_user_segment(ipage, INLINE_DATA_OFFSET + from,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
set_page_dirty(ipage);
f2fs_put_page(ipage, 1);
}
bool recover_inline_data(struct inode *inode, struct page *npage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@ -231,11 +246,15 @@ process_inline:
ipage = get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
f2fs_wait_on_page_writeback(ipage, NODE);
f2fs_wait_on_page_writeback(ipage, NODE, true);
src_addr = inline_data_addr(npage);
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);
update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
return true;
@ -244,16 +263,334 @@ process_inline:
if (f2fs_has_inline_data(inode)) {
ipage = get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
f2fs_wait_on_page_writeback(ipage, NODE);
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
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)) {
truncate_blocks(inode, 0, false);
set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
if (truncate_blocks(inode, 0, false))
return false;
goto process_inline;
}
return false;
}
struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
struct f2fs_inline_dentry *inline_dentry;
struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
struct f2fs_dir_entry *de;
struct f2fs_dentry_ptr d;
struct page *ipage;
f2fs_hash_t namehash;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return NULL;
namehash = f2fs_dentry_hash(&name);
inline_dentry = inline_data_addr(ipage);
make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
de = find_target_dentry(fname, namehash, NULL, &d);
unlock_page(ipage);
if (de)
*res_page = ipage;
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;
}
int make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage)
{
struct f2fs_inline_dentry *dentry_blk;
struct f2fs_dentry_ptr d;
dentry_blk = inline_data_addr(ipage);
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
do_make_empty_dir(inode, parent, &d);
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);
}
return 0;
}
/*
* 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,
struct f2fs_inline_dentry *inline_dentry)
{
struct page *page;
struct dnode_of_data dn;
struct f2fs_dentry_block *dentry_blk;
int err;
page = grab_cache_page(dir->i_mapping, 0);
if (!page) {
f2fs_put_page(ipage, 1);
return -ENOMEM;
}
set_new_dnode(&dn, dir, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, 0);
if (err)
goto out;
f2fs_wait_on_page_writeback(page, DATA, true);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
dentry_blk = kmap_atomic(page);
/* copy data from inline dentry block to new dentry block */
memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap,
INLINE_DENTRY_BITMAP_SIZE);
memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0,
SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE);
/*
* we do not need to zero out remainder part of dentry and filename
* field, since we have used bitmap for marking the usage status of
* them, besides, we can also ignore copying/zeroing reserved space
* of dentry block, because them haven't been used so far.
*/
memcpy(dentry_blk->dentry, inline_dentry->dentry,
sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY);
memcpy(dentry_blk->filename, inline_dentry->filename,
NR_INLINE_DENTRY * F2FS_SLOT_LEN);
kunmap_atomic(dentry_blk);
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);
}
sync_inode_page(&dn);
out:
f2fs_put_page(page, 1);
return err;
}
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
unsigned int bit_pos;
f2fs_hash_t name_hash;
size_t namelen = name->len;
struct f2fs_inline_dentry *dentry_blk = NULL;
struct f2fs_dentry_ptr d;
int slots = GET_DENTRY_SLOTS(namelen);
struct page *page = NULL;
int err = 0;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
dentry_blk = inline_data_addr(ipage);
bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
slots, NR_INLINE_DENTRY);
if (bit_pos >= NR_INLINE_DENTRY) {
err = f2fs_convert_inline_dir(dir, ipage, dentry_blk);
if (err)
return err;
err = -EAGAIN;
goto out;
}
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, name, ipage);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
}
f2fs_wait_on_page_writeback(ipage, NODE, true);
name_hash = f2fs_dentry_hash(name);
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos);
set_page_dirty(ipage);
/* we don't need to mark_inode_dirty now */
if (inode) {
F2FS_I(inode)->i_pino = dir->i_ino;
update_inode(inode, page);
f2fs_put_page(page, 1);
}
update_parent_metadata(dir, inode, 0);
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;
}
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode)
{
struct f2fs_inline_dentry *inline_dentry;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
unsigned int bit_pos;
int i;
lock_page(page);
f2fs_wait_on_page_writeback(page, NODE, true);
inline_dentry = inline_data_addr(page);
bit_pos = dentry - inline_dentry->dentry;
for (i = 0; i < slots; i++)
test_and_clear_bit_le(bit_pos + i,
&inline_dentry->dentry_bitmap);
set_page_dirty(page);
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
if (inode)
f2fs_drop_nlink(dir, inode, page);
f2fs_put_page(page, 1);
}
bool f2fs_empty_inline_dir(struct inode *dir)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
unsigned int bit_pos = 2;
struct f2fs_inline_dentry *dentry_blk;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return false;
dentry_blk = inline_data_addr(ipage);
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
NR_INLINE_DENTRY,
bit_pos);
f2fs_put_page(ipage, 1);
if (bit_pos < NR_INLINE_DENTRY)
return false;
return true;
}
int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
struct fscrypt_str *fstr)
{
struct inode *inode = file_inode(file);
struct f2fs_inline_dentry *inline_dentry = NULL;
struct page *ipage = NULL;
struct f2fs_dentry_ptr d;
if (ctx->pos == NR_INLINE_DENTRY)
return 0;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
inline_dentry = inline_data_addr(ipage);
make_dentry_ptr(inode, &d, (void *)inline_dentry, 2);
if (!f2fs_fill_dentries(ctx, &d, 0, fstr))
ctx->pos = NR_INLINE_DENTRY;
f2fs_put_page(ipage, 1);
return 0;
}
int f2fs_inline_data_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, __u64 start, __u64 len)
{
__u64 byteaddr, ilen;
__u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED |
FIEMAP_EXTENT_LAST;
struct node_info ni;
struct page *ipage;
int err = 0;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
if (!f2fs_has_inline_data(inode)) {
err = -EAGAIN;
goto out;
}
ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode));
if (start >= ilen)
goto out;
if (start + len < ilen)
ilen = start + len;
ilen -= start;
get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage);
err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
out:
f2fs_put_page(ipage, 1);
return err;
}

181
fs/f2fs/inode.c
View file

@ -12,7 +12,6 @@
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/bitops.h>
#include "f2fs.h"
#include "node.h"
@ -34,8 +33,8 @@ void f2fs_set_inode_flags(struct inode *inode)
new_fl |= S_NOATIME;
if (flags & FS_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
set_mask_bits(&inode->i_flags,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
inode_set_flags(inode, new_fl,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
}
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@ -51,6 +50,15 @@ static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
}
}
static bool __written_first_block(struct f2fs_inode *ri)
{
block_t addr = le32_to_cpu(ri->i_addr[0]);
if (addr != NEW_ADDR && addr != NULL_ADDR)
return true;
return false;
}
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
@ -67,6 +75,25 @@ static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
}
}
static void __recover_inline_status(struct inode *inode, struct page *ipage)
{
void *inline_data = inline_data_addr(ipage);
__le32 *start = inline_data;
__le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
while (start < end) {
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_page_dirty(ipage);
return;
}
}
return;
}
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@ -111,13 +138,27 @@ static int do_read_inode(struct inode *inode)
fi->i_pino = le32_to_cpu(ri->i_pino);
fi->i_dir_level = ri->i_dir_level;
get_extent_info(&fi->ext, ri->i_ext);
if (f2fs_init_extent_tree(inode, &ri->i_ext))
set_page_dirty(node_page);
get_inline_info(fi, ri);
/* check data exist */
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
__recover_inline_status(inode, node_page);
/* get rdev by using inline_info */
__get_inode_rdev(inode, ri);
if (__written_first_block(ri))
set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
stat_inc_inline_inode(inode);
stat_inc_inline_dir(inode);
return 0;
}
@ -156,9 +197,12 @@ make_now:
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = &f2fs_symlink_inode_operations;
if (f2fs_encrypted_inode(inode))
inode->i_op = &f2fs_encrypted_symlink_inode_operations;
else
inode->i_op = &f2fs_symlink_inode_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
@ -178,11 +222,11 @@ bad_inode:
return ERR_PTR(ret);
}
void update_inode(struct inode *inode, struct page *node_page)
int update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
f2fs_wait_on_page_writeback(node_page, NODE);
f2fs_wait_on_page_writeback(node_page, NODE, true);
ri = F2FS_INODE(node_page);
@ -193,7 +237,12 @@ void update_inode(struct inode *inode, struct page *node_page)
ri->i_links = cpu_to_le32(inode->i_nlink);
ri->i_size = cpu_to_le64(i_size_read(inode));
ri->i_blocks = cpu_to_le64(inode->i_blocks);
set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext);
if (F2FS_I(inode)->extent_tree)
set_raw_extent(&F2FS_I(inode)->extent_tree->largest,
&ri->i_ext);
else
memset(&ri->i_ext, 0, sizeof(ri->i_ext));
set_raw_inline(F2FS_I(inode), ri);
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
@ -211,15 +260,20 @@ void update_inode(struct inode *inode, struct page *node_page)
__set_inode_rdev(inode, ri);
set_cold_node(inode, node_page);
set_page_dirty(node_page);
clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
/* deleted inode */
if (inode->i_nlink == 0)
clear_inline_node(node_page);
return set_page_dirty(node_page);
}
void update_inode_page(struct inode *inode)
int update_inode_page(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *node_page;
int ret = 0;
retry:
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page)) {
@ -230,10 +284,11 @@ retry:
} else if (err != -ENOENT) {
f2fs_stop_checkpoint(sbi);
}
return;
return 0;
}
update_inode(inode, node_page);
ret = update_inode(inode, node_page);
f2fs_put_page(node_page, 1);
return ret;
}
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
@ -248,16 +303,11 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
return 0;
/*
* We need to lock here to prevent from producing dirty node pages
* We need to balance fs here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
*/
f2fs_lock_op(sbi);
update_inode_page(inode);
f2fs_unlock_op(sbi);
if (wbc)
f2fs_balance_fs(sbi);
if (update_inode_page(inode))
f2fs_balance_fs(sbi, true);
return 0;
}
@ -267,47 +317,78 @@ 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);
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
struct f2fs_inode_info *fi = F2FS_I(inode);
nid_t xnid = fi->i_xattr_nid;
int err = 0;
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
commit_inmem_pages(inode, true);
if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
truncate_inode_pages(&inode->i_data, 0);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
goto out_clear;
f2fs_bug_on(sbi, get_dirty_pages(inode));
remove_dirty_dir_inode(inode);
remove_dirty_inode(inode);
f2fs_destroy_extent_tree(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
sb_start_intwrite(inode->i_sb);
set_inode_flag(F2FS_I(inode), FI_NO_ALLOC);
set_inode_flag(fi, FI_NO_ALLOC);
i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
f2fs_truncate(inode);
err = f2fs_truncate(inode, true);
f2fs_lock_op(sbi);
remove_inode_page(inode);
stat_dec_inline_inode(inode);
f2fs_unlock_op(sbi);
if (!err) {
f2fs_lock_op(sbi);
err = remove_inode_page(inode);
f2fs_unlock_op(sbi);
}
sb_end_intwrite(inode->i_sb);
no_delete:
stat_dec_inline_xattr(inode);
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);
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(F2FS_I(inode), FI_APPEND_WRITE))
add_dirty_inode(sbi, inode->i_ino, APPEND_INO);
if (is_inode_flag_set(F2FS_I(inode), FI_UPDATE_WRITE))
add_dirty_inode(sbi, inode->i_ino, UPDATE_INO);
if (is_inode_flag_set(fi, FI_APPEND_WRITE))
add_ino_entry(sbi, inode->i_ino, APPEND_INO);
if (is_inode_flag_set(fi, 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);
}
}
out_clear:
fscrypt_put_encryption_info(inode, NULL);
clear_inode(inode);
}
@ -315,6 +396,7 @@ out_clear:
void handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err = 0;
clear_nlink(inode);
make_bad_inode(inode);
@ -322,12 +404,29 @@ void handle_failed_inode(struct inode *inode)
i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
f2fs_truncate(inode);
err = f2fs_truncate(inode, false);
remove_inode_page(inode);
stat_dec_inline_inode(inode);
if (!err)
err = remove_inode_page(inode);
alloc_nid_failed(sbi, inode->i_ino);
/*
* 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);
}
set_inode_flag(F2FS_I(inode), FI_FREE_NID);
f2fs_unlock_op(sbi);
/* iput will drop the inode object */

591
fs/f2fs/namei.c
View file

@ -9,11 +9,13 @@
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/f2fs_fs.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/ctype.h>
#include <linux/dcache.h>
#include <linux/namei.h>
#include "f2fs.h"
#include "node.h"
@ -52,21 +54,34 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
if (err) {
err = -EINVAL;
nid_free = true;
goto out;
goto fail;
}
/* If the directory encrypted, then we should encrypt the inode. */
if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
f2fs_set_encrypted_inode(inode);
if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
if (f2fs_may_inline_dentry(inode))
set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
f2fs_init_extent_tree(inode, NULL);
stat_inc_inline_xattr(inode);
stat_inc_inline_inode(inode);
stat_inc_inline_dir(inode);
trace_f2fs_new_inode(inode, 0);
mark_inode_dirty(inode);
return inode;
out:
clear_nlink(inode);
unlock_new_inode(inode);
fail:
trace_f2fs_new_inode(inode, err);
make_bad_inode(inode);
iput(inode);
if (nid_free)
alloc_nid_failed(sbi, ino);
set_inode_flag(F2FS_I(inode), FI_FREE_NID);
iput(inode);
return ERR_PTR(err);
}
@ -75,7 +90,14 @@ static int is_multimedia_file(const unsigned char *s, const char *sub)
size_t slen = strlen(s);
size_t sublen = strlen(sub);
if (sublen > slen)
/*
* filename format of multimedia file should be defined as:
* "filename + '.' + extension".
*/
if (slen < sublen + 2)
return 0;
if (s[slen - sublen - 1] != '.')
return 0;
return !strncasecmp(s + slen - sublen, sub, sublen);
@ -107,8 +129,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
nid_t ino = 0;
int err;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@ -121,6 +141,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
inode->i_mapping->a_ops = &f2fs_dblock_aops;
ino = inode->i_ino;
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
@ -131,6 +153,9 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
d_instantiate(dentry, inode);
unlock_new_inode(inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
out:
handle_failed_inode(inode);
@ -144,7 +169,11 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
int err;
f2fs_balance_fs(sbi);
if (f2fs_encrypted_inode(dir) &&
!fscrypt_has_permitted_context(dir, inode))
return -EPERM;
f2fs_balance_fs(sbi, true);
inode->i_ctime = CURRENT_TIME;
ihold(inode);
@ -157,6 +186,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
f2fs_unlock_op(sbi);
d_instantiate(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
out:
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
@ -174,30 +206,110 @@ struct dentry *f2fs_get_parent(struct dentry *child)
return d_obtain_alias(f2fs_iget(child->d_inode->i_sb, ino));
}
static int __recover_dot_dentries(struct inode *dir, nid_t pino)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct qstr dot = {.len = 1, .name = "."};
struct qstr dotdot = {.len = 2, .name = ".."};
struct f2fs_dir_entry *de;
struct page *page;
int err = 0;
if (f2fs_readonly(sbi->sb)) {
f2fs_msg(sbi->sb, KERN_INFO,
"skip recovering inline_dots inode (ino:%lu, pino:%u) "
"in readonly mountpoint", dir->i_ino, pino);
return 0;
}
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
de = f2fs_find_entry(dir, &dot, &page);
if (de) {
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
} else {
err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
if (err)
goto out;
}
de = f2fs_find_entry(dir, &dotdot, &page);
if (de) {
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
} 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);
}
f2fs_unlock_op(sbi);
return err;
}
static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct inode *inode = NULL;
struct f2fs_dir_entry *de;
struct page *page;
nid_t ino;
int err = 0;
if (f2fs_encrypted_inode(dir)) {
int res = fscrypt_get_encryption_info(dir);
/*
* DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
* created while the directory was encrypted and we
* don't have access to the key.
*/
if (fscrypt_has_encryption_key(dir))
fscrypt_set_encrypted_dentry(dentry);
fscrypt_set_d_op(dentry);
if (res && res != -ENOKEY)
return ERR_PTR(res);
}
if (dentry->d_name.len > F2FS_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (de) {
nid_t ino = le32_to_cpu(de->ino);
kunmap(page);
f2fs_put_page(page, 0);
if (!de)
return d_splice_alias(inode, dentry);
inode = f2fs_iget(dir->i_sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
ino = le32_to_cpu(de->ino);
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
stat_inc_inline_inode(inode);
inode = f2fs_iget(dir->i_sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
if (f2fs_has_inline_dots(inode)) {
err = __recover_dot_dentries(inode, dir->i_ino);
if (err)
goto err_out;
}
if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) &&
(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
!fscrypt_has_permitted_context(dir, inode)) {
bool nokey = f2fs_encrypted_inode(inode) &&
!fscrypt_has_encryption_key(inode);
err = nokey ? -ENOKEY : -EPERM;
goto err_out;
}
return d_splice_alias(inode, dentry);
err_out:
iput(inode);
return ERR_PTR(err);
}
static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
@ -209,58 +321,155 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
int err = -ENOENT;
trace_f2fs_unlink_enter(dir, dentry);
f2fs_balance_fs(sbi);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (!de)
goto fail;
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
if (err) {
f2fs_unlock_op(sbi);
kunmap(page);
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
goto fail;
}
f2fs_delete_entry(de, page, inode);
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:
trace_f2fs_unlink_exit(inode, err);
return err;
}
static void *f2fs_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct page *page;
char *link;
page = page_follow_link_light(dentry, nd);
if (IS_ERR(page))
return page;
link = nd_get_link(nd);
if (IS_ERR(link))
return link;
/* this is broken symlink case */
if (*link == 0) {
kunmap(page);
page_cache_release(page);
return ERR_PTR(-ENOENT);
}
return page;
}
static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
size_t symlen = strlen(symname) + 1;
size_t len = strlen(symname);
struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1);
struct fscrypt_symlink_data *sd = NULL;
int err;
f2fs_balance_fs(sbi);
if (f2fs_encrypted_inode(dir)) {
err = fscrypt_get_encryption_info(dir);
if (err)
return err;
if (!fscrypt_has_encryption_key(dir))
return -EPERM;
disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
sizeof(struct fscrypt_symlink_data));
}
if (disk_link.len > dir->i_sb->s_blocksize)
return -ENAMETOOLONG;
inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = &f2fs_symlink_inode_operations;
if (f2fs_encrypted_inode(inode))
inode->i_op = &f2fs_encrypted_symlink_inode_operations;
else
inode->i_op = &f2fs_symlink_inode_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
goto out;
f2fs_unlock_op(sbi);
err = page_symlink(inode, symname, symlen);
alloc_nid_done(sbi, inode->i_ino);
if (f2fs_encrypted_inode(inode)) {
struct qstr istr = QSTR_INIT(symname, len);
struct fscrypt_str ostr;
sd = kzalloc(disk_link.len, GFP_NOFS);
if (!sd) {
err = -ENOMEM;
goto err_out;
}
err = fscrypt_get_encryption_info(inode);
if (err)
goto err_out;
if (!fscrypt_has_encryption_key(inode)) {
err = -EPERM;
goto err_out;
}
ostr.name = sd->encrypted_path;
ostr.len = disk_link.len;
err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
if (err < 0)
goto err_out;
sd->len = cpu_to_le16(ostr.len);
disk_link.name = (char *)sd;
}
err = page_symlink(inode, disk_link.name, disk_link.len);
err_out:
d_instantiate(dentry, inode);
unlock_new_inode(inode);
/*
* Let's flush symlink data in order to avoid broken symlink as much as
* possible. Nevertheless, fsyncing is the best way, but there is no
* way to get a file descriptor in order to flush that.
*
* Note that, it needs to do dir->fsync to make this recoverable.
* If the symlink path is stored into inline_data, there is no
* performance regression.
*/
if (!err) {
filemap_write_and_wait_range(inode->i_mapping, 0,
disk_link.len - 1);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
} else {
f2fs_unlink(dir, dentry);
}
kfree(sd);
return err;
out:
handle_failed_inode(inode);
@ -273,8 +482,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
struct inode *inode;
int err;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, S_IFDIR | mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@ -282,7 +489,9 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
f2fs_balance_fs(sbi, true);
set_inode_flag(F2FS_I(inode), FI_INC_LINK);
f2fs_lock_op(sbi);
@ -296,6 +505,8 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
d_instantiate(dentry, inode);
unlock_new_inode(inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
out_fail:
@ -322,8 +533,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
if (!new_valid_dev(rdev))
return -EINVAL;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@ -331,6 +540,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &f2fs_special_inode_operations;
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
@ -338,28 +549,111 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
f2fs_unlock_op(sbi);
alloc_nid_done(sbi, inode->i_ino);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
out:
handle_failed_inode(inode);
return err;
}
static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
umode_t mode, struct inode **whiteout)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err;
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
if (whiteout) {
init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
inode->i_op = &f2fs_special_inode_operations;
} else {
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
}
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
if (err)
goto out;
err = f2fs_do_tmpfile(inode, dir);
if (err)
goto release_out;
/*
* 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);
alloc_nid_done(sbi, inode->i_ino);
if (whiteout) {
inode_dec_link_count(inode);
*whiteout = inode;
} else {
d_tmpfile(dentry, inode);
}
unlock_new_inode(inode);
return 0;
release_out:
release_orphan_inode(sbi);
out:
handle_failed_inode(inode);
return err;
}
static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
{
if (f2fs_encrypted_inode(dir)) {
int err = fscrypt_get_encryption_info(dir);
if (err)
return err;
}
return __f2fs_tmpfile(dir, dentry, mode, NULL);
}
static int f2fs_create_whiteout(struct inode *dir, struct inode **whiteout)
{
return __f2fs_tmpfile(dir, NULL, S_IFCHR | WHITEOUT_MODE, whiteout);
}
static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct inode *whiteout = NULL;
struct page *old_dir_page;
struct page *old_page, *new_page;
struct page *old_page, *new_page = NULL;
struct f2fs_dir_entry *old_dir_entry = NULL;
struct f2fs_dir_entry *old_entry;
struct f2fs_dir_entry *new_entry;
bool is_old_inline = f2fs_has_inline_dentry(old_dir);
int err = -ENOENT;
f2fs_balance_fs(sbi);
if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
!fscrypt_has_permitted_context(new_dir, old_inode)) {
err = -EPERM;
goto out;
}
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry)
@ -372,17 +666,25 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out_old;
}
if (flags & RENAME_WHITEOUT) {
err = f2fs_create_whiteout(old_dir, &whiteout);
if (err)
goto out_dir;
}
if (new_inode) {
err = -ENOTEMPTY;
if (old_dir_entry && !f2fs_empty_dir(new_inode))
goto out_dir;
goto out_whiteout;
err = -ENOENT;
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
&new_page);
if (!new_entry)
goto out_dir;
goto out_whiteout;
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
@ -390,7 +692,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (err)
goto put_out_dir;
if (update_dent_inode(old_inode, &new_dentry->d_name)) {
err = update_dent_inode(old_inode, new_inode,
&new_dentry->d_name);
if (err) {
release_orphan_inode(sbi);
goto put_out_dir;
}
@ -414,36 +718,70 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
update_inode_page(old_inode);
update_inode_page(new_inode);
} else {
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = f2fs_add_link(new_dentry, old_inode);
if (err) {
f2fs_unlock_op(sbi);
goto out_dir;
goto out_whiteout;
}
if (old_dir_entry) {
inc_nlink(new_dir);
update_inode_page(new_dir);
}
/*
* old entry and new entry can locate in the same inline
* dentry in inode, when attaching new entry in inline dentry,
* it could force inline dentry conversion, after that,
* old_entry and old_page will point to wrong address, in
* order to avoid this, let's do the check and update here.
*/
if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) {
f2fs_put_page(old_page, 0);
old_page = NULL;
old_entry = f2fs_find_entry(old_dir,
&old_dentry->d_name, &old_page);
if (!old_entry) {
err = -EIO;
f2fs_unlock_op(sbi);
goto out_dir;
}
}
}
down_write(&F2FS_I(old_inode)->i_sem);
file_lost_pino(old_inode);
if (new_inode && file_enc_name(new_inode))
file_set_enc_name(old_inode);
up_write(&F2FS_I(old_inode)->i_sem);
old_inode->i_ctime = CURRENT_TIME;
mark_inode_dirty(old_inode);
f2fs_delete_entry(old_entry, old_page, NULL);
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);
err = f2fs_add_link(old_dentry, whiteout);
if (err)
goto put_out_dir;
whiteout->i_state &= ~I_LINKABLE;
iput(whiteout);
}
if (old_dir_entry) {
if (old_dir != new_dir) {
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 {
kunmap(old_dir_page);
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
drop_nlink(old_dir);
@ -452,19 +790,27 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
f2fs_unlock_op(sbi);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
put_out_dir:
f2fs_unlock_op(sbi);
kunmap(new_page);
f2fs_put_page(new_page, 0);
if (new_page) {
f2fs_dentry_kunmap(new_dir, new_page);
f2fs_put_page(new_page, 0);
}
out_whiteout:
if (whiteout)
iput(whiteout);
out_dir:
if (old_dir_entry) {
kunmap(old_dir_page);
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
out_old:
kunmap(old_page);
f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
@ -483,7 +829,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
int old_nlink = 0, new_nlink = 0;
int err = -ENOENT;
f2fs_balance_fs(sbi);
if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
(old_dir != new_dir) &&
(!fscrypt_has_permitted_context(new_dir, old_inode) ||
!fscrypt_has_permitted_context(old_dir, new_inode)))
return -EPERM;
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry)
@ -527,15 +877,21 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out_new_dir;
}
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = update_dent_inode(old_inode, &new_dentry->d_name);
err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name);
if (err)
goto out_unlock;
if (file_enc_name(new_inode))
file_set_enc_name(old_inode);
err = update_dent_inode(new_inode, &old_dentry->d_name);
err = update_dent_inode(new_inode, old_inode, &old_dentry->d_name);
if (err)
goto out_undo;
if (file_enc_name(old_inode))
file_set_enc_name(new_inode);
/* update ".." directory entry info of old dentry */
if (old_dir_entry)
@ -588,27 +944,33 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
update_inode_page(new_dir);
f2fs_unlock_op(sbi);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
out_undo:
/* Still we may fail to recover name info of f2fs_inode here */
update_dent_inode(old_inode, &old_dentry->d_name);
/*
* Still we may fail to recover name info of f2fs_inode here
* Drop it, once its name is set as encrypted
*/
update_dent_inode(old_inode, old_inode, &old_dentry->d_name);
out_unlock:
f2fs_unlock_op(sbi);
out_new_dir:
if (new_dir_entry) {
kunmap(new_dir_page);
f2fs_dentry_kunmap(new_inode, new_dir_page);
f2fs_put_page(new_dir_page, 0);
}
out_old_dir:
if (old_dir_entry) {
kunmap(old_dir_page);
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
out_new:
kunmap(new_page);
f2fs_dentry_kunmap(new_dir, new_page);
f2fs_put_page(new_page, 0);
out_old:
kunmap(old_page);
f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
@ -618,7 +980,7 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
if (flags & RENAME_EXCHANGE) {
@ -629,51 +991,100 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
* VFS has already handled the new dentry existence case,
* here, we just deal with "RENAME_NOREPLACE" as regular rename.
*/
return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry);
return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
static void *f2fs_encrypted_follow_link(struct dentry *dentry,
struct nameidata *nd)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err;
struct page *cpage = NULL;
char *caddr, *paddr = NULL;
struct fscrypt_str cstr = FSTR_INIT(NULL, 0);
struct fscrypt_str pstr = FSTR_INIT(NULL, 0);
struct fscrypt_symlink_data *sd;
struct inode *inode = dentry->d_inode;
loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
u32 max_size = inode->i_sb->s_blocksize;
int res;
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
res = fscrypt_get_encryption_info(inode);
if (res)
return ERR_PTR(res);
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
cpage = read_mapping_page(inode->i_mapping, 0, NULL);
if (IS_ERR(cpage))
return cpage;
caddr = kmap(cpage);
caddr[size] = 0;
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
if (err)
goto out;
/* Symlink is encrypted */
sd = (struct fscrypt_symlink_data *)caddr;
cstr.name = sd->encrypted_path;
cstr.len = le16_to_cpu(sd->len);
err = f2fs_do_tmpfile(inode, dir);
if (err)
goto release_out;
/* this is broken symlink case */
if (unlikely(cstr.len == 0)) {
res = -ENOENT;
goto errout;
}
/*
* 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);
/* this is broken symlink case */
if (unlikely(cstr.name[0] == 0)) {
res = -ENOENT;
goto errout;
}
alloc_nid_done(sbi, inode->i_ino);
d_tmpfile(dentry, inode);
unlock_new_inode(inode);
return 0;
if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
/* Symlink data on the disk is corrupted */
res = -EIO;
goto errout;
}
res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
if (res)
goto errout;
release_out:
release_orphan_inode(sbi);
out:
handle_failed_inode(inode);
return err;
res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
if (res < 0)
goto errout;
paddr = pstr.name;
/* Null-terminate the name */
paddr[res] = '\0';
nd_set_link(nd, paddr);
kunmap(cpage);
page_cache_release(cpage);
return NULL;
errout:
fscrypt_fname_free_buffer(&pstr);
kunmap(cpage);
page_cache_release(cpage);
return ERR_PTR(res);
}
void kfree_put_link(struct dentry *dentry, struct nameidata *nd,
void *cookie)
{
char *s = nd_get_link(nd);
if (!IS_ERR(s))
kfree(s);
}
const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = f2fs_encrypted_follow_link,
.put_link = kfree_put_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
#ifdef CONFIG_F2FS_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
};
const struct inode_operations f2fs_dir_inode_operations = {
.create = f2fs_create,
.lookup = f2fs_lookup,
@ -699,7 +1110,7 @@ const struct inode_operations f2fs_dir_inode_operations = {
const struct inode_operations f2fs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
.follow_link = f2fs_follow_link,
.put_link = page_put_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,

776
fs/f2fs/node.c
View file

File diff suppressed because it is too large Load diff

112
fs/f2fs/node.h
View file

@ -14,21 +14,35 @@
/* node block offset on the NAT area dedicated to the given start node id */
#define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
/* # of pages to perform readahead before building free nids */
/* # of pages to perform synchronous readahead before building free nids */
#define FREE_NID_PAGES 4
#define DEF_RA_NID_PAGES 4 /* # 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
/* control dirty nats ratio threshold (default: 10% over max nid count) */
#define DEF_DIRTY_NAT_RATIO_THRESHOLD 10
/* vector size for gang look-up from nat cache that consists of radix tree */
#define NATVEC_SIZE 64
#define SETVEC_SIZE 32
/* return value for read_node_page */
#define LOCKED_PAGE 1
/* For flag in struct node_info */
enum {
IS_CHECKPOINTED, /* is it checkpointed before? */
HAS_FSYNCED_INODE, /* is the inode fsynced before? */
HAS_LAST_FSYNC, /* has the latest node fsync mark? */
IS_DIRTY, /* this nat entry is dirty? */
};
/*
* For node information
*/
@ -37,18 +51,11 @@ struct node_info {
nid_t ino; /* inode number of the node's owner */
block_t blk_addr; /* block address of the node */
unsigned char version; /* version of the node */
};
enum {
IS_CHECKPOINTED, /* is it checkpointed before? */
HAS_FSYNCED_INODE, /* is the inode fsynced before? */
HAS_LAST_FSYNC, /* has the latest node fsync mark? */
IS_DIRTY, /* this nat entry is dirty? */
unsigned char flag; /* for node information bits */
};
struct nat_entry {
struct list_head list; /* for clean or dirty nat list */
unsigned char flag; /* for node information bits */
struct node_info ni; /* in-memory node information */
};
@ -63,20 +70,30 @@ struct nat_entry {
#define inc_node_version(version) (++version)
static inline void copy_node_info(struct node_info *dst,
struct node_info *src)
{
dst->nid = src->nid;
dst->ino = src->ino;
dst->blk_addr = src->blk_addr;
dst->version = src->version;
/* should not copy flag here */
}
static inline void set_nat_flag(struct nat_entry *ne,
unsigned int type, bool set)
{
unsigned char mask = 0x01 << type;
if (set)
ne->flag |= mask;
ne->ni.flag |= mask;
else
ne->flag &= ~mask;
ne->ni.flag &= ~mask;
}
static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
{
unsigned char mask = 0x01 << type;
return ne->flag & mask;
return ne->ni.flag & mask;
}
static inline void nat_reset_flag(struct nat_entry *ne)
@ -103,10 +120,19 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
raw_ne->version = ni->version;
}
static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
{
return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid *
NM_I(sbi)->dirty_nats_ratio / 100;
}
enum mem_type {
FREE_NIDS, /* indicates the free nid list */
NAT_ENTRIES, /* indicates the cached nat entry */
DIRTY_DENTS /* indicates dirty dentry pages */
DIRTY_DENTS, /* indicates dirty dentry pages */
INO_ENTRIES, /* indicates inode entries */
EXTENT_CACHE, /* indicates extent cache */
BASE_CHECK, /* check kernel status */
};
struct nat_entry_set {
@ -166,7 +192,7 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
block_addr = (pgoff_t)(nm_i->nat_blkaddr +
(seg_off << sbi->log_blocks_per_seg << 1) +
(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));
(block_off & (sbi->blocks_per_seg - 1)));
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
block_addr += sbi->blocks_per_seg;
@ -192,21 +218,26 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
{
unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
f2fs_clear_bit(block_off, nm_i->nat_bitmap);
else
f2fs_set_bit(block_off, nm_i->nat_bitmap);
f2fs_change_bit(block_off, nm_i->nat_bitmap);
}
static inline void fill_node_footer(struct page *page, nid_t nid,
nid_t ino, unsigned int ofs, bool reset)
{
struct f2fs_node *rn = F2FS_NODE(page);
unsigned int old_flag = 0;
if (reset)
memset(rn, 0, sizeof(*rn));
else
old_flag = le32_to_cpu(rn->footer.flag);
rn->footer.nid = cpu_to_le32(nid);
rn->footer.ino = cpu_to_le32(ino);
rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
/* should remain old flag bits such as COLD_BIT_SHIFT */
rn->footer.flag = cpu_to_le32((ofs << OFFSET_BIT_SHIFT) |
(old_flag & OFFSET_BIT_MASK));
}
static inline void copy_node_footer(struct page *dst, struct page *src)
@ -295,17 +326,17 @@ static inline bool IS_DNODE(struct page *node_page)
return true;
}
static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
static inline int set_nid(struct page *p, int off, nid_t nid, bool i)
{
struct f2fs_node *rn = F2FS_NODE(p);
f2fs_wait_on_page_writeback(p, NODE);
f2fs_wait_on_page_writeback(p, NODE, true);
if (i)
rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
else
rn->in.nid[off] = cpu_to_le32(nid);
set_page_dirty(p);
return set_page_dirty(p);
}
static inline nid_t get_nid(struct page *p, int off, bool i)
@ -323,28 +354,6 @@ static inline nid_t get_nid(struct page *p, int off, bool i)
* - Mark cold node blocks in their node footer
* - Mark cold data pages in page cache
*/
static inline int is_file(struct inode *inode, int type)
{
return F2FS_I(inode)->i_advise & type;
}
static inline void set_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise |= type;
}
static inline void clear_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise &= ~type;
}
#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT)
#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT)
#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT)
#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT)
static inline int is_cold_data(struct page *page)
{
return PageChecked(page);
@ -370,6 +379,21 @@ static inline int is_node(struct page *page, int type)
#define is_fsync_dnode(page) is_node(page, FSYNC_BIT_SHIFT)
#define is_dent_dnode(page) is_node(page, DENT_BIT_SHIFT)
static inline int is_inline_node(struct page *page)
{
return PageChecked(page);
}
static inline void set_inline_node(struct page *page)
{
SetPageChecked(page);
}
static inline void clear_inline_node(struct page *page)
{
ClearPageChecked(page);
}
static inline void set_cold_node(struct inode *inode, struct page *page)
{
struct f2fs_node *rn = F2FS_NODE(page);

215
fs/f2fs/recovery.c
View file

@ -83,6 +83,11 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
goto out;
}
if (file_enc_name(inode)) {
iput(dir);
return 0;
}
name.len = le32_to_cpu(raw_inode->i_namelen);
name.name = raw_inode->i_name;
@ -93,10 +98,9 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
}
retry:
de = f2fs_find_entry(dir, &name, &page);
if (de && inode->i_ino == le32_to_cpu(de->ino)) {
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
if (de && inode->i_ino == le32_to_cpu(de->ino))
goto out_unmap_put;
}
if (de) {
einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino));
if (IS_ERR(einode)) {
@ -111,11 +115,11 @@ retry:
iput(einode);
goto out_unmap_put;
}
f2fs_delete_entry(de, page, einode);
f2fs_delete_entry(de, page, dir, einode);
iput(einode);
goto retry;
}
err = __f2fs_add_link(dir, &name, inode);
err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
if (err)
goto out_err;
@ -129,7 +133,7 @@ retry:
goto out;
out_unmap_put:
kunmap(page);
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
out_err:
iput(dir);
@ -144,6 +148,7 @@ out:
static void recover_inode(struct inode *inode, struct page *page)
{
struct f2fs_inode *raw = F2FS_INODE(page);
char *name;
inode->i_mode = le16_to_cpu(raw->i_mode);
i_size_write(inode, le64_to_cpu(raw->i_size));
@ -154,8 +159,39 @@ static void recover_inode(struct inode *inode, struct page *page)
inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
if (file_enc_name(inode))
name = "<encrypted>";
else
name = F2FS_INODE(page)->i_name;
f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
ino_of_node(page), F2FS_INODE(page)->i_name);
ino_of_node(page), name);
}
static bool is_same_inode(struct inode *inode, struct page *ipage)
{
struct f2fs_inode *ri = F2FS_INODE(ipage);
struct timespec disk;
if (!IS_INODE(ipage))
return true;
disk.tv_sec = le64_to_cpu(ri->i_ctime);
disk.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
if (timespec_compare(&inode->i_ctime, &disk) > 0)
return false;
disk.tv_sec = le64_to_cpu(ri->i_atime);
disk.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
if (timespec_compare(&inode->i_atime, &disk) > 0)
return false;
disk.tv_sec = le64_to_cpu(ri->i_mtime);
disk.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
if (timespec_compare(&inode->i_mtime, &disk) > 0)
return false;
return true;
}
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
@ -170,13 +206,15 @@ 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;
if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi))
if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
page = get_meta_page_ra(sbi, blkaddr);
page = get_tmp_page(sbi, blkaddr);
if (cp_ver != cpver_of_node(page))
break;
@ -186,9 +224,8 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
entry = get_fsync_inode(head, ino_of_node(page));
if (entry) {
if (IS_INODE(page) && is_dent_dnode(page))
set_inode_flag(F2FS_I(entry->inode),
FI_INC_LINK);
if (!is_same_inode(entry->inode, page))
goto next;
} else {
if (IS_INODE(page) && is_dent_dnode(page)) {
err = recover_inode_page(sbi, page);
@ -210,8 +247,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
if (IS_ERR(entry->inode)) {
err = PTR_ERR(entry->inode);
kmem_cache_free(fsync_entry_slab, entry);
if (err == -ENOENT)
if (err == -ENOENT) {
err = 0;
goto next;
}
break;
}
list_add_tail(&entry->list, head);
@ -227,6 +266,8 @@ next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
ra_meta_pages_cond(sbi, blkaddr);
}
f2fs_put_page(page, 1);
return err;
@ -252,6 +293,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
struct f2fs_summary_block *sum_node;
struct f2fs_summary sum;
struct page *sum_page, *node_page;
struct dnode_of_data tdn = *dn;
nid_t ino, nid;
struct inode *inode;
unsigned int offset;
@ -279,17 +321,15 @@ got_it:
/* Use the locked dnode page and inode */
nid = le32_to_cpu(sum.nid);
if (dn->inode->i_ino == nid) {
struct dnode_of_data tdn = *dn;
tdn.nid = nid;
if (!dn->inode_page_locked)
lock_page(dn->inode_page);
tdn.node_page = dn->inode_page;
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
truncate_data_blocks_range(&tdn, 1);
return 0;
goto truncate_out;
} else if (dn->nid == nid) {
struct dnode_of_data tdn = *dn;
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
truncate_data_blocks_range(&tdn, 1);
return 0;
goto truncate_out;
}
/* Get the node page */
@ -310,38 +350,54 @@ got_it:
inode = dn->inode;
}
bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
le16_to_cpu(sum.ofs_in_node);
bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
if (ino != dn->inode->i_ino) {
truncate_hole(inode, bidx, bidx + 1);
/*
* if inode page is locked, unlock temporarily, but its reference
* count keeps alive.
*/
if (ino == dn->inode->i_ino && dn->inode_page_locked)
unlock_page(dn->inode_page);
set_new_dnode(&tdn, inode, NULL, NULL, 0);
if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
goto out;
if (tdn.data_blkaddr == blkaddr)
truncate_data_blocks_range(&tdn, 1);
f2fs_put_dnode(&tdn);
out:
if (ino != dn->inode->i_ino)
iput(inode);
} else {
struct dnode_of_data tdn;
set_new_dnode(&tdn, inode, dn->inode_page, NULL, 0);
if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
return 0;
if (tdn.data_blkaddr != NULL_ADDR)
truncate_data_blocks_range(&tdn, 1);
f2fs_put_page(tdn.node_page, 1);
}
else if (dn->inode_page_locked)
lock_page(dn->inode_page);
return 0;
truncate_out:
if (datablock_addr(tdn.node_page, tdn.ofs_in_node) == blkaddr)
truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
return 0;
}
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct page *page, block_t blkaddr)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned int start, end;
struct dnode_of_data dn;
struct f2fs_summary sum;
struct node_info ni;
unsigned int start, end;
int err = 0, recovered = 0;
/* step 1: recover xattr */
if (IS_INODE(page)) {
recover_inline_xattr(inode, page);
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
/*
* Deprecated; xattr blocks should be found from cold log.
* But, we should remain this for backward compatibility.
*/
recover_xattr_data(inode, page, blkaddr);
goto out;
}
@ -351,32 +407,51 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
goto out;
/* step 3: recover data indices */
start = start_bidx_of_node(ofs_of_node(page), fi);
end = start + ADDRS_PER_PAGE(page, fi);
f2fs_lock_op(sbi);
start = start_bidx_of_node(ofs_of_node(page), inode);
end = start + ADDRS_PER_PAGE(page, inode);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, start, ALLOC_NODE);
if (err) {
f2fs_unlock_op(sbi);
if (err)
goto out;
}
f2fs_wait_on_page_writeback(dn.node_page, NODE);
f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
get_node_info(sbi, dn.nid, &ni);
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page));
for (; start < end; start++) {
for (; start < end; start++, dn.ofs_in_node++) {
block_t src, dest;
src = datablock_addr(dn.node_page, dn.ofs_in_node);
dest = datablock_addr(page, dn.ofs_in_node);
if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR) {
/* skip recovering if dest is the same as src */
if (src == dest)
continue;
/* dest is invalid, just invalidate src block */
if (dest == NULL_ADDR) {
truncate_data_blocks_range(&dn, 1);
continue;
}
/*
* 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);
continue;
}
/* dest is valid block, try to recover from src to dest */
if (is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
/* We should not get -ENOSPC */
@ -388,18 +463,13 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
if (err)
goto err;
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
/* write dummy data page */
recover_data_page(sbi, NULL, &sum, src, dest);
update_extent_cache(dest, &dn);
f2fs_replace_block(sbi, &dn, src, dest,
ni.version, false, false);
recovered++;
}
dn.ofs_in_node++;
}
/* write node page in place */
set_summary(&sum, dn.nid, 0, 0);
if (IS_INODE(dn.node_page))
sync_inode_page(&dn);
@ -409,7 +479,6 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
set_page_dirty(dn.node_page);
err:
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
out:
f2fs_msg(sbi->sb, KERN_NOTICE,
"recover_data: ino = %lx, recovered = %d blocks, err = %d",
@ -417,8 +486,7 @@ out:
return err;
}
static int recover_data(struct f2fs_sb_info *sbi,
struct list_head *head, int type)
static int recover_data(struct f2fs_sb_info *sbi, struct list_head *head)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
@ -427,16 +495,18 @@ static int recover_data(struct f2fs_sb_info *sbi,
block_t blkaddr;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, type);
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi))
if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
page = get_meta_page_ra(sbi, blkaddr);
ra_meta_pages_cond(sbi, blkaddr);
page = get_tmp_page(sbi, blkaddr);
if (cp_ver != cpver_of_node(page)) {
f2fs_put_page(page, 1);
@ -496,14 +566,12 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
INIT_LIST_HEAD(&inode_list);
/* step #1: find fsynced inode numbers */
sbi->por_doing = true;
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
/* step #1: find fsynced inode numbers */
err = find_fsync_dnodes(sbi, &inode_list);
if (err)
goto out;
@ -514,7 +582,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
need_writecp = true;
/* step #2: recover data */
err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
err = recover_data(sbi, &inode_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
out:
@ -523,28 +591,37 @@ out:
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
(loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
truncate_inode_pages_final(META_MAPPING(sbi));
truncate_inode_pages(NODE_MAPPING(sbi), 0);
truncate_inode_pages(META_MAPPING(sbi), 0);
}
sbi->por_doing = false;
clear_sbi_flag(sbi, SBI_POR_DOING);
if (err) {
discard_next_dnode(sbi, blkaddr);
bool invalidate = false;
if (discard_next_dnode(sbi, blkaddr))
invalidate = true;
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META))
sync_meta_pages(sbi, META, LONG_MAX);
/* invalidate temporary meta page */
if (invalidate)
invalidate_mapping_pages(META_MAPPING(sbi),
blkaddr, blkaddr);
set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
mutex_unlock(&sbi->cp_mutex);
} else if (need_writecp) {
struct cp_control cpc = {
.reason = CP_SYNC,
.reason = CP_RECOVERY,
};
mutex_unlock(&sbi->cp_mutex);
write_checkpoint(sbi, &cpc);
err = write_checkpoint(sbi, &cpc);
} else {
mutex_unlock(&sbi->cp_mutex);
}

974
fs/f2fs/segment.c
View file

File diff suppressed because it is too large Load diff

95
fs/f2fs/segment.h
View file

@ -136,10 +136,12 @@ enum {
/*
* BG_GC means the background cleaning job.
* FG_GC means the on-demand cleaning job.
* FORCE_FG_GC means on-demand cleaning job in background.
*/
enum {
BG_GC = 0,
FG_GC
FG_GC,
FORCE_FG_GC,
};
/* for a function parameter to select a victim segment */
@ -163,6 +165,7 @@ struct seg_entry {
*/
unsigned short ckpt_valid_blocks;
unsigned char *ckpt_valid_map;
unsigned char *discard_map;
unsigned char type; /* segment type like CURSEG_XXX_TYPE */
unsigned long long mtime; /* modification time of the segment */
};
@ -175,9 +178,19 @@ struct segment_allocation {
void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
};
/*
* this value is set in page as a private data which indicate that
* the page is atomically written, and it is in inmem_pages list.
*/
#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1)
#define IS_ATOMIC_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
struct inmem_pages {
struct list_head list;
struct page *page;
block_t old_addr; /* for revoking when fail to commit */
};
struct sit_info {
@ -189,6 +202,7 @@ struct sit_info {
char *sit_bitmap; /* SIT bitmap pointer */
unsigned int bitmap_size; /* SIT bitmap size */
unsigned long *tmp_map; /* bitmap for temporal use */
unsigned long *dirty_sentries_bitmap; /* bitmap for dirty sentries */
unsigned int dirty_sentries; /* # of dirty sentries */
unsigned int sents_per_block; /* # of SIT entries per block */
@ -207,7 +221,7 @@ struct free_segmap_info {
unsigned int start_segno; /* start segment number logically */
unsigned int free_segments; /* # of free segments */
unsigned int free_sections; /* # of free sections */
rwlock_t segmap_lock; /* free segmap lock */
spinlock_t segmap_lock; /* free segmap lock */
unsigned long *free_segmap; /* free segment bitmap */
unsigned long *free_secmap; /* free section bitmap */
};
@ -243,6 +257,8 @@ struct victim_selection {
struct curseg_info {
struct mutex curseg_mutex; /* lock for consistency */
struct f2fs_summary_block *sum_blk; /* cached summary block */
struct rw_semaphore journal_rwsem; /* protect journal area */
struct f2fs_journal *journal; /* cached journal info */
unsigned char alloc_type; /* current allocation type */
unsigned int segno; /* current segment number */
unsigned short next_blkoff; /* next block offset to write */
@ -318,9 +334,9 @@ static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
unsigned int max, unsigned int segno)
{
unsigned int ret;
read_lock(&free_i->segmap_lock);
spin_lock(&free_i->segmap_lock);
ret = find_next_bit(free_i->free_segmap, max, segno);
read_unlock(&free_i->segmap_lock);
spin_unlock(&free_i->segmap_lock);
return ret;
}
@ -331,16 +347,17 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
unsigned int start_segno = secno * sbi->segs_per_sec;
unsigned int next;
write_lock(&free_i->segmap_lock);
spin_lock(&free_i->segmap_lock);
clear_bit(segno, free_i->free_segmap);
free_i->free_segments++;
next = find_next_bit(free_i->free_segmap, MAIN_SEGS(sbi), start_segno);
next = find_next_bit(free_i->free_segmap,
start_segno + sbi->segs_per_sec, start_segno);
if (next >= start_segno + sbi->segs_per_sec) {
clear_bit(secno, free_i->free_secmap);
free_i->free_sections++;
}
write_unlock(&free_i->segmap_lock);
spin_unlock(&free_i->segmap_lock);
}
static inline void __set_inuse(struct f2fs_sb_info *sbi,
@ -362,7 +379,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
unsigned int start_segno = secno * sbi->segs_per_sec;
unsigned int next;
write_lock(&free_i->segmap_lock);
spin_lock(&free_i->segmap_lock);
if (test_and_clear_bit(segno, free_i->free_segmap)) {
free_i->free_segments++;
@ -373,7 +390,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
free_i->free_sections++;
}
}
write_unlock(&free_i->segmap_lock);
spin_unlock(&free_i->segmap_lock);
}
static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
@ -381,13 +398,13 @@ static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int secno = segno / sbi->segs_per_sec;
write_lock(&free_i->segmap_lock);
spin_lock(&free_i->segmap_lock);
if (!test_and_set_bit(segno, free_i->free_segmap)) {
free_i->free_segments--;
if (!test_and_set_bit(secno, free_i->free_secmap))
free_i->free_sections--;
}
write_unlock(&free_i->segmap_lock);
spin_unlock(&free_i->segmap_lock);
}
static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
@ -460,7 +477,7 @@ 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);
if (unlikely(sbi->por_doing))
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
return false;
return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
@ -551,16 +568,15 @@ static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
return curseg->next_blkoff;
}
#ifdef CONFIG_F2FS_CHECK_FS
static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
{
BUG_ON(segno > TOTAL_SEGS(sbi) - 1);
f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
}
static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
{
BUG_ON(blk_addr < SEG0_BLKADDR(sbi));
BUG_ON(blk_addr >= MAX_BLKADDR(sbi));
f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi)
|| blk_addr >= MAX_BLKADDR(sbi));
}
/*
@ -569,16 +585,11 @@ static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
static inline void check_block_count(struct f2fs_sb_info *sbi,
int segno, struct f2fs_sit_entry *raw_sit)
{
#ifdef CONFIG_F2FS_CHECK_FS
bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false;
int valid_blocks = 0;
int cur_pos = 0, next_pos;
/* check segment usage */
BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg);
/* check boundary of a given segment number */
BUG_ON(segno > TOTAL_SEGS(sbi) - 1);
/* check bitmap with valid block count */
do {
if (is_valid) {
@ -594,35 +605,11 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
is_valid = !is_valid;
} while (cur_pos < sbi->blocks_per_seg);
BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
}
#else
static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
{
if (segno > TOTAL_SEGS(sbi) - 1)
sbi->need_fsck = true;
}
static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
{
if (blk_addr < SEG0_BLKADDR(sbi) || blk_addr >= MAX_BLKADDR(sbi))
sbi->need_fsck = true;
}
/*
* Summary block is always treated as an invalid block
*/
static inline void check_block_count(struct f2fs_sb_info *sbi,
int segno, struct f2fs_sit_entry *raw_sit)
{
/* check segment usage */
if (GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg)
sbi->need_fsck = true;
/* check boundary of a given segment number */
if (segno > TOTAL_SEGS(sbi) - 1)
sbi->need_fsck = true;
}
#endif
/* check segment usage, and check boundary of a given segment number */
f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
|| segno > TOTAL_SEGS(sbi) - 1);
}
static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
unsigned int start)
@ -657,10 +644,7 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
{
unsigned int block_off = SIT_BLOCK_OFFSET(start);
if (f2fs_test_bit(block_off, sit_i->sit_bitmap))
f2fs_clear_bit(block_off, sit_i->sit_bitmap);
else
f2fs_set_bit(block_off, sit_i->sit_bitmap);
f2fs_change_bit(block_off, sit_i->sit_bitmap);
}
static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
@ -714,6 +698,9 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
*/
static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
{
if (sbi->sb->s_bdi->dirty_exceeded)
return 0;
if (type == DATA)
return sbi->blocks_per_seg;
else if (type == NODE)

140
fs/f2fs/shrinker.c Normal file
View file

@ -0,0 +1,140 @@
/*
* f2fs shrinker support
* the basic infra was copied from fs/ubifs/shrinker.c
*
* Copyright (c) 2015 Motorola Mobility
* Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include "f2fs.h"
static LIST_HEAD(f2fs_list);
static DEFINE_SPINLOCK(f2fs_list_lock);
static unsigned int shrinker_run_no;
static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
{
return NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
}
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;
return 0;
}
static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi)
{
return atomic_read(&sbi->total_zombie_tree) +
atomic_read(&sbi->total_ext_node);
}
unsigned long f2fs_shrink_count(struct shrinker *shrink,
struct shrink_control *sc)
{
struct f2fs_sb_info *sbi;
struct list_head *p;
unsigned long count = 0;
spin_lock(&f2fs_list_lock);
p = f2fs_list.next;
while (p != &f2fs_list) {
sbi = list_entry(p, struct f2fs_sb_info, s_list);
/* stop f2fs_put_super */
if (!mutex_trylock(&sbi->umount_mutex)) {
p = p->next;
continue;
}
spin_unlock(&f2fs_list_lock);
/* count extent cache entries */
count += __count_extent_cache(sbi);
/* shrink clean nat cache entries */
count += __count_nat_entries(sbi);
/* count free nids cache entries */
count += __count_free_nids(sbi);
spin_lock(&f2fs_list_lock);
p = p->next;
mutex_unlock(&sbi->umount_mutex);
}
spin_unlock(&f2fs_list_lock);
return count;
}
unsigned long f2fs_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
unsigned long nr = sc->nr_to_scan;
struct f2fs_sb_info *sbi;
struct list_head *p;
unsigned int run_no;
unsigned long freed = 0;
spin_lock(&f2fs_list_lock);
do {
run_no = ++shrinker_run_no;
} while (run_no == 0);
p = f2fs_list.next;
while (p != &f2fs_list) {
sbi = list_entry(p, struct f2fs_sb_info, s_list);
if (sbi->shrinker_run_no == run_no)
break;
/* stop f2fs_put_super */
if (!mutex_trylock(&sbi->umount_mutex)) {
p = p->next;
continue;
}
spin_unlock(&f2fs_list_lock);
sbi->shrinker_run_no = run_no;
/* shrink extent cache entries */
freed += f2fs_shrink_extent_tree(sbi, nr >> 1);
/* shrink clean nat cache entries */
if (freed < nr)
freed += try_to_free_nats(sbi, nr - freed);
/* shrink free nids cache entries */
if (freed < nr)
freed += try_to_free_nids(sbi, nr - freed);
spin_lock(&f2fs_list_lock);
p = p->next;
list_move_tail(&sbi->s_list, &f2fs_list);
mutex_unlock(&sbi->umount_mutex);
if (freed >= nr)
break;
}
spin_unlock(&f2fs_list_lock);
return freed;
}
void f2fs_join_shrinker(struct f2fs_sb_info *sbi)
{
spin_lock(&f2fs_list_lock);
list_add_tail(&sbi->s_list, &f2fs_list);
spin_unlock(&f2fs_list_lock);
}
void f2fs_leave_shrinker(struct f2fs_sb_info *sbi)
{
f2fs_shrink_extent_tree(sbi, __count_extent_cache(sbi));
spin_lock(&f2fs_list_lock);
list_del(&sbi->s_list);
spin_unlock(&f2fs_list_lock);
}

690
fs/f2fs/super.c
View file

File diff suppressed because it is too large Load diff

161
fs/f2fs/trace.c Normal file
View file

@ -0,0 +1,161 @@
/*
* f2fs IO tracer
*
* Copyright (c) 2014 Motorola Mobility
* Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/sched.h>
#include <linux/radix-tree.h>
#include "f2fs.h"
#include "trace.h"
static RADIX_TREE(pids, GFP_ATOMIC);
static spinlock_t pids_lock;
static struct last_io_info last_io;
static inline void __print_last_io(void)
{
if (!last_io.len)
return;
trace_printk("%3x:%3x %4x %-16s %2x %5x %12x %4x\n",
last_io.major, last_io.minor,
last_io.pid, "----------------",
last_io.type,
last_io.fio.rw,
last_io.fio.new_blkaddr,
last_io.len);
memset(&last_io, 0, sizeof(last_io));
}
static int __file_type(struct inode *inode, pid_t pid)
{
if (f2fs_is_atomic_file(inode))
return __ATOMIC_FILE;
else if (f2fs_is_volatile_file(inode))
return __VOLATILE_FILE;
else if (S_ISDIR(inode->i_mode))
return __DIR_FILE;
else if (inode->i_ino == F2FS_NODE_INO(F2FS_I_SB(inode)))
return __NODE_FILE;
else if (inode->i_ino == F2FS_META_INO(F2FS_I_SB(inode)))
return __META_FILE;
else if (pid)
return __NORMAL_FILE;
else
return __MISC_FILE;
}
void f2fs_trace_pid(struct page *page)
{
struct inode *inode = page->mapping->host;
pid_t pid = task_pid_nr(current);
void *p;
page->private = pid;
if (radix_tree_preload(GFP_NOFS))
return;
spin_lock(&pids_lock);
p = radix_tree_lookup(&pids, pid);
if (p == current)
goto out;
if (p)
radix_tree_delete(&pids, pid);
f2fs_radix_tree_insert(&pids, pid, current);
trace_printk("%3x:%3x %4x %-16s\n",
MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
pid, current->comm);
out:
spin_unlock(&pids_lock);
radix_tree_preload_end();
}
void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
{
struct inode *inode;
pid_t pid;
int major, minor;
if (flush) {
__print_last_io();
return;
}
inode = fio->page->mapping->host;
pid = page_private(fio->page);
major = MAJOR(inode->i_sb->s_dev);
minor = MINOR(inode->i_sb->s_dev);
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.new_blkaddr + last_io.len ==
fio->new_blkaddr) {
last_io.len++;
return;
}
__print_last_io();
last_io.major = major;
last_io.minor = minor;
last_io.pid = pid;
last_io.type = __file_type(inode, pid);
last_io.fio = *fio;
last_io.len = 1;
return;
}
void f2fs_build_trace_ios(void)
{
spin_lock_init(&pids_lock);
}
#define PIDVEC_SIZE 128
static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index,
unsigned int max_items)
{
struct radix_tree_iter iter;
void **slot;
unsigned int ret = 0;
if (unlikely(!max_items))
return 0;
radix_tree_for_each_slot(slot, &pids, &iter, first_index) {
results[ret] = iter.index;
if (++ret == PIDVEC_SIZE)
break;
}
return ret;
}
void f2fs_destroy_trace_ios(void)
{
pid_t pid[PIDVEC_SIZE];
pid_t next_pid = 0;
unsigned int found;
spin_lock(&pids_lock);
while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) {
unsigned idx;
next_pid = pid[found - 1] + 1;
for (idx = 0; idx < found; idx++)
radix_tree_delete(&pids, pid[idx]);
}
spin_unlock(&pids_lock);
}

46
fs/f2fs/trace.h Normal file
View file

@ -0,0 +1,46 @@
/*
* f2fs IO tracer
*
* Copyright (c) 2014 Motorola Mobility
* Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#ifndef __F2FS_TRACE_H__
#define __F2FS_TRACE_H__
#ifdef CONFIG_F2FS_IO_TRACE
#include <trace/events/f2fs.h>
enum file_type {
__NORMAL_FILE,
__DIR_FILE,
__NODE_FILE,
__META_FILE,
__ATOMIC_FILE,
__VOLATILE_FILE,
__MISC_FILE,
};
struct last_io_info {
int major, minor;
pid_t pid;
enum file_type type;
struct f2fs_io_info fio;
block_t len;
};
extern void f2fs_trace_pid(struct page *);
extern void f2fs_trace_ios(struct f2fs_io_info *, int);
extern void f2fs_build_trace_ios(void);
extern void f2fs_destroy_trace_ios(void);
#else
#define f2fs_trace_pid(p)
#define f2fs_trace_ios(i, n)
#define f2fs_build_trace_ios()
#define f2fs_destroy_trace_ios()
#endif
#endif /* __F2FS_TRACE_H__ */

27
fs/f2fs/xattr.c
View file

@ -83,7 +83,7 @@ static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name,
}
if (strcmp(name, "") == 0)
return -EINVAL;
return f2fs_getxattr(dentry->d_inode, type, name, buffer, size);
return f2fs_getxattr(dentry->d_inode, type, name, buffer, size, NULL);
}
static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
@ -135,7 +135,8 @@ static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name,
if (strcmp(name, "") != 0)
return -EINVAL;
*((char *)buffer) = F2FS_I(inode)->i_advise;
if (buffer)
*((char *)buffer) = F2FS_I(inode)->i_advise;
return sizeof(char);
}
@ -152,6 +153,7 @@ static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
return -EINVAL;
F2FS_I(inode)->i_advise |= *(char *)value;
mark_inode_dirty(inode);
return 0;
}
@ -345,7 +347,7 @@ 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);
f2fs_wait_on_page_writeback(ipage, NODE, true);
} else {
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
@ -353,7 +355,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
return PTR_ERR(page);
}
inline_addr = inline_xattr_addr(page);
f2fs_wait_on_page_writeback(page, NODE);
f2fs_wait_on_page_writeback(page, NODE, true);
}
memcpy(inline_addr, txattr_addr, inline_size);
f2fs_put_page(page, 1);
@ -374,7 +376,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
return PTR_ERR(xpage);
}
f2fs_bug_on(sbi, new_nid);
f2fs_wait_on_page_writeback(xpage, NODE);
f2fs_wait_on_page_writeback(xpage, NODE, true);
} else {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, new_nid);
@ -398,7 +400,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
}
int f2fs_getxattr(struct inode *inode, int index, const char *name,
void *buffer, size_t buffer_size)
void *buffer, size_t buffer_size, struct page *ipage)
{
struct f2fs_xattr_entry *entry;
void *base_addr;
@ -412,7 +414,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
if (len > F2FS_NAME_LEN)
return -ERANGE;
base_addr = read_all_xattrs(inode, NULL);
base_addr = read_all_xattrs(inode, ipage);
if (!base_addr)
return -ENOMEM;
@ -497,9 +499,12 @@ static int __f2fs_setxattr(struct inode *inode, int index,
len = strlen(name);
if (len > F2FS_NAME_LEN || size > MAX_VALUE_LEN(inode))
if (len > F2FS_NAME_LEN)
return -ERANGE;
if (size > MAX_VALUE_LEN(inode))
return -E2BIG;
base_addr = read_all_xattrs(inode, ipage);
if (!base_addr)
goto exit;
@ -582,6 +587,9 @@ static int __f2fs_setxattr(struct inode *inode, int index,
inode->i_ctime = CURRENT_TIME;
clear_inode_flag(fi, 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);
@ -603,7 +611,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
if (ipage)
return __f2fs_setxattr(inode, index, name, value,
size, ipage, flags);
f2fs_balance_fs(sbi);
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
/* protect xattr_ver */
@ -612,5 +620,6 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
up_write(&F2FS_I(inode)->i_sem);
f2fs_unlock_op(sbi);
f2fs_update_time(sbi, REQ_TIME);
return err;
}

13
fs/f2fs/xattr.h
View file

@ -35,6 +35,10 @@
#define F2FS_XATTR_INDEX_LUSTRE 5
#define F2FS_XATTR_INDEX_SECURITY 6
#define F2FS_XATTR_INDEX_ADVISE 7
/* Should be same as EXT4_XATTR_INDEX_ENCRYPTION */
#define F2FS_XATTR_INDEX_ENCRYPTION 9
#define F2FS_XATTR_NAME_ENCRYPTION_CONTEXT "c"
struct f2fs_xattr_header {
__le32 h_magic; /* magic number for identification */
@ -115,18 +119,21 @@ extern const struct xattr_handler *f2fs_xattr_handlers[];
extern int f2fs_setxattr(struct inode *, int, const char *,
const void *, size_t, struct page *, int);
extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t);
extern int f2fs_getxattr(struct inode *, int, const char *, void *,
size_t, struct page *);
extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
#else
#define f2fs_xattr_handlers NULL
static inline int f2fs_setxattr(struct inode *inode, int index,
const char *name, const void *value, size_t size, int flags)
const char *name, const void *value, size_t size,
struct page *page, int flags)
{
return -EOPNOTSUPP;
}
static inline int f2fs_getxattr(struct inode *inode, int index,
const char *name, void *buffer, size_t buffer_size)
const char *name, void *buffer,
size_t buffer_size, struct page *dpage)
{
return -EOPNOTSUPP;
}

98
include/linux/f2fs_fs.h
View file

@ -19,12 +19,16 @@
#define F2FS_MAX_LOG_SECTOR_SIZE 12 /* 12 bits for 4096 bytes */
#define F2FS_LOG_SECTORS_PER_BLOCK 3 /* log number for sector/blk */
#define F2FS_BLKSIZE 4096 /* support only 4KB block */
#define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */
#define F2FS_MAX_EXTENSION 64 /* # of extension entries */
#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE)
#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS)
#define NULL_ADDR ((block_t)0) /* used as block_t addresses */
#define NEW_ADDR ((block_t)-1) /* used as block_t addresses */
#define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS)
#define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS)
/* 0, 1(node nid), 2(meta nid) are reserved node id */
#define F2FS_RESERVED_NODE_NUM 3
@ -33,7 +37,8 @@
#define F2FS_META_INO(sbi) (sbi->meta_ino_num)
/* This flag is used by node and meta inodes, and by recovery */
#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO)
#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO)
#define GFP_F2FS_HIGH_ZERO (GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM)
/*
* For further optimization on multi-head logs, on-disk layout supports maximum
@ -45,6 +50,9 @@
#define MAX_ACTIVE_NODE_LOGS 8
#define MAX_ACTIVE_DATA_LOGS 8
#define VERSION_LEN 256
#define MAX_VOLUME_NAME 512
/*
* For superblock
*/
@ -77,15 +85,22 @@ struct f2fs_super_block {
__le32 node_ino; /* node inode number */
__le32 meta_ino; /* meta inode number */
__u8 uuid[16]; /* 128-bit uuid for volume */
__le16 volume_name[512]; /* volume name */
__le16 volume_name[MAX_VOLUME_NAME]; /* volume name */
__le32 extension_count; /* # of extensions below */
__u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */
__le32 cp_payload;
__u8 version[VERSION_LEN]; /* the kernel version */
__u8 init_version[VERSION_LEN]; /* the initial kernel version */
__le32 feature; /* defined features */
__u8 encryption_level; /* versioning level for encryption */
__u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */
__u8 reserved[871]; /* valid reserved region */
} __packed;
/*
* For checkpoint
*/
#define CP_FASTBOOT_FLAG 0x00000020
#define CP_FSCK_FLAG 0x00000010
#define CP_ERROR_FLAG 0x00000008
#define CP_COMPACT_SUM_FLAG 0x00000004
@ -147,7 +162,7 @@ struct f2fs_orphan_block {
*/
struct f2fs_extent {
__le32 fofs; /* start file offset of the extent */
__le32 blk_addr; /* start block address of the extent */
__le32 blk; /* start block address of the extent */
__le32 len; /* lengh of the extent */
} __packed;
@ -155,12 +170,12 @@ struct f2fs_extent {
#define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */
#define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */
#define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */
#define ADDRS_PER_INODE(fi) addrs_per_inode(fi)
#define ADDRS_PER_INODE(inode) addrs_per_inode(inode)
#define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */
#define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */
#define ADDRS_PER_PAGE(page, fi) \
(IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK)
#define ADDRS_PER_PAGE(page, inode) \
(IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK)
#define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1)
#define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2)
@ -170,14 +185,13 @@ struct f2fs_extent {
#define F2FS_INLINE_XATTR 0x01 /* file inline xattr flag */
#define F2FS_INLINE_DATA 0x02 /* file inline data flag */
#define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */
#define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */
#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */
#define MAX_INLINE_DATA (sizeof(__le32) * (DEF_ADDRS_PER_INODE - \
F2FS_INLINE_XATTR_ADDRS - 1))
#define INLINE_DATA_OFFSET (PAGE_CACHE_SIZE - sizeof(struct node_footer) -\
sizeof(__le32) * (DEF_ADDRS_PER_INODE + \
DEF_NIDS_PER_INODE - 1))
struct f2fs_inode {
__le16 i_mode; /* file mode */
__u8 i_advise; /* file hints */
@ -225,6 +239,8 @@ enum {
OFFSET_BIT_SHIFT
};
#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */
struct node_footer {
__le32 nid; /* node id */
__le32 ino; /* inode nunmber */
@ -329,7 +345,7 @@ struct f2fs_summary {
struct summary_footer {
unsigned char entry_type; /* SUM_TYPE_XXX */
__u32 check_sum; /* summary checksum */
__le32 check_sum; /* summary checksum */
} __packed;
#define SUM_JOURNAL_SIZE (F2FS_BLKSIZE - SUM_FOOTER_SIZE -\
@ -342,6 +358,12 @@ struct summary_footer {
sizeof(struct sit_journal_entry))
#define SIT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\
sizeof(struct sit_journal_entry))
/* Reserved area should make size of f2fs_extra_info equals to
* that of nat_journal and sit_journal.
*/
#define EXTRA_INFO_RESERVED (SUM_JOURNAL_SIZE - 2 - 8)
/*
* frequently updated NAT/SIT entries can be stored in the spare area in
* summary blocks
@ -371,18 +393,28 @@ struct sit_journal {
__u8 reserved[SIT_JOURNAL_RESERVED];
} __packed;
/* 4KB-sized summary block structure */
struct f2fs_summary_block {
struct f2fs_summary entries[ENTRIES_IN_SUM];
struct f2fs_extra_info {
__le64 kbytes_written;
__u8 reserved[EXTRA_INFO_RESERVED];
} __packed;
struct f2fs_journal {
union {
__le16 n_nats;
__le16 n_sits;
};
/* spare area is used by NAT or SIT journals */
/* spare area is used by NAT or SIT journals or extra info */
union {
struct nat_journal nat_j;
struct sit_journal sit_j;
struct f2fs_extra_info info;
};
} __packed;
/* 4KB-sized summary block structure */
struct f2fs_summary_block {
struct f2fs_summary entries[ENTRIES_IN_SUM];
struct f2fs_journal journal;
struct summary_footer footer;
} __packed;
@ -402,15 +434,25 @@ typedef __le32 f2fs_hash_t;
#define GET_DENTRY_SLOTS(x) ((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS)
/* the number of dentry in a block */
#define NR_DENTRY_IN_BLOCK 214
/* MAX level for dir lookup */
#define MAX_DIR_HASH_DEPTH 63
/* MAX buckets in one level of dir */
#define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1))
/*
* space utilization of regular dentry and inline dentry
* regular dentry inline dentry
* bitmap 1 * 27 = 27 1 * 23 = 23
* reserved 1 * 3 = 3 1 * 7 = 7
* dentry 11 * 214 = 2354 11 * 182 = 2002
* filename 8 * 214 = 1712 8 * 182 = 1456
* total 4096 3488
*
* Note: there are more reserved space in inline dentry than in regular
* dentry, when converting inline dentry we should handle this carefully.
*/
#define NR_DENTRY_IN_BLOCK 214 /* the number of dentry in a block */
#define SIZE_OF_DIR_ENTRY 11 /* by byte */
#define SIZE_OF_DENTRY_BITMAP ((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
BITS_PER_BYTE)
@ -435,6 +477,24 @@ struct f2fs_dentry_block {
__u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN];
} __packed;
/* for inline dir */
#define NR_INLINE_DENTRY (MAX_INLINE_DATA * BITS_PER_BYTE / \
((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
BITS_PER_BYTE + 1))
#define INLINE_DENTRY_BITMAP_SIZE ((NR_INLINE_DENTRY + \
BITS_PER_BYTE - 1) / BITS_PER_BYTE)
#define INLINE_RESERVED_SIZE (MAX_INLINE_DATA - \
((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE))
/* inline directory entry structure */
struct f2fs_inline_dentry {
__u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE];
__u8 reserved[INLINE_RESERVED_SIZE];
struct f2fs_dir_entry dentry[NR_INLINE_DENTRY];
__u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN];
} __packed;
/* file types used in inode_info->flags */
enum {
F2FS_FT_UNKNOWN,

411
include/trace/events/f2fs.h
View file

@ -14,7 +14,12 @@
{ NODE, "NODE" }, \
{ DATA, "DATA" }, \
{ META, "META" }, \
{ META_FLUSH, "META_FLUSH" })
{ META_FLUSH, "META_FLUSH" }, \
{ INMEM, "INMEM" }, \
{ INMEM_DROP, "INMEM_DROP" }, \
{ INMEM_REVOKE, "INMEM_REVOKE" }, \
{ IPU, "IN-PLACE" }, \
{ OPU, "OUT-OF-PLACE" })
#define F2FS_BIO_MASK(t) (t & (READA | WRITE_FLUSH_FUA))
#define F2FS_BIO_EXTRA_MASK(t) (t & (REQ_META | REQ_PRIO))
@ -72,10 +77,13 @@
#define show_cpreason(type) \
__print_symbolic(type, \
{ CP_UMOUNT, "Umount" }, \
{ CP_FASTBOOT, "Fastboot" }, \
{ CP_SYNC, "Sync" }, \
{ CP_RECOVERY, "Recovery" }, \
{ CP_DISCARD, "Discard" })
struct victim_sel_policy;
struct f2fs_map_blocks;
DECLARE_EVENT_CLASS(f2fs__inode,
@ -148,14 +156,14 @@ DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter,
TRACE_EVENT(f2fs_sync_file_exit,
TP_PROTO(struct inode *inode, bool need_cp, int datasync, int ret),
TP_PROTO(struct inode *inode, int need_cp, int datasync, int ret),
TP_ARGS(inode, need_cp, datasync, ret),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(bool, need_cp)
__field(int, need_cp)
__field(int, datasync)
__field(int, ret)
),
@ -190,7 +198,7 @@ TRACE_EVENT(f2fs_sync_fs,
TP_fast_assign(
__entry->dev = sb->s_dev;
__entry->dirty = F2FS_SB(sb)->s_dirty;
__entry->dirty = is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY);
__entry->wait = wait;
),
@ -440,71 +448,66 @@ TRACE_EVENT(f2fs_truncate_partial_nodes,
__entry->err)
);
TRACE_EVENT_CONDITION(f2fs_submit_page_bio,
TRACE_EVENT(f2fs_map_blocks,
TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret),
TP_PROTO(struct page *page, sector_t blkaddr, int type),
TP_ARGS(page, blkaddr, type),
TP_CONDITION(page->mapping),
TP_ARGS(inode, map, ret),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(pgoff_t, index)
__field(sector_t, blkaddr)
__field(int, type)
),
TP_fast_assign(
__entry->dev = page->mapping->host->i_sb->s_dev;
__entry->ino = page->mapping->host->i_ino;
__entry->index = page->index;
__entry->blkaddr = blkaddr;
__entry->type = type;
),
TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
"blkaddr = 0x%llx, bio_type = %s%s",
show_dev_ino(__entry),
(unsigned long)__entry->index,
(unsigned long long)__entry->blkaddr,
show_bio_type(__entry->type))
);
TRACE_EVENT(f2fs_get_data_block,
TP_PROTO(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int ret),
TP_ARGS(inode, iblock, bh, ret),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(sector_t, iblock)
__field(sector_t, bh_start)
__field(size_t, bh_size)
__field(block_t, m_lblk)
__field(block_t, m_pblk)
__field(unsigned int, m_len)
__field(int, ret)
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->iblock = iblock;
__entry->bh_start = bh->b_blocknr;
__entry->bh_size = bh->b_size;
__entry->m_lblk = map->m_lblk;
__entry->m_pblk = map->m_pblk;
__entry->m_len = map->m_len;
__entry->ret = ret;
),
TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, "
"start blkaddr = 0x%llx, len = 0x%llx bytes, err = %d",
"start blkaddr = 0x%llx, len = 0x%llx, err = %d",
show_dev_ino(__entry),
(unsigned long long)__entry->iblock,
(unsigned long long)__entry->bh_start,
(unsigned long long)__entry->bh_size,
(unsigned long long)__entry->m_lblk,
(unsigned long long)__entry->m_pblk,
(unsigned long long)__entry->m_len,
__entry->ret)
);
TRACE_EVENT(f2fs_background_gc,
TP_PROTO(struct super_block *sb, long wait_ms,
unsigned int prefree, unsigned int free),
TP_ARGS(sb, wait_ms, prefree, free),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(long, wait_ms)
__field(unsigned int, prefree)
__field(unsigned int, free)
),
TP_fast_assign(
__entry->dev = sb->s_dev;
__entry->wait_ms = wait_ms;
__entry->prefree = prefree;
__entry->free = free;
),
TP_printk("dev = (%d,%d), wait_ms = %ld, prefree = %u, free = %u",
show_dev(__entry),
__entry->wait_ms,
__entry->prefree,
__entry->free)
);
TRACE_EVENT(f2fs_get_victim,
TP_PROTO(struct super_block *sb, int type, int gc_type,
@ -680,11 +683,66 @@ TRACE_EVENT(f2fs_reserve_new_block,
__entry->ofs_in_node)
);
DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
TP_PROTO(struct page *page, struct f2fs_io_info *fio),
TP_ARGS(page, fio),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(pgoff_t, index)
__field(block_t, old_blkaddr)
__field(block_t, new_blkaddr)
__field(int, rw)
__field(int, type)
),
TP_fast_assign(
__entry->dev = page->mapping->host->i_sb->s_dev;
__entry->ino = page->mapping->host->i_ino;
__entry->index = page->index;
__entry->old_blkaddr = fio->old_blkaddr;
__entry->new_blkaddr = fio->new_blkaddr;
__entry->rw = fio->rw;
__entry->type = fio->type;
),
TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
"oldaddr = 0x%llx, newaddr = 0x%llx rw = %s%s, type = %s",
show_dev_ino(__entry),
(unsigned long)__entry->index,
(unsigned long long)__entry->old_blkaddr,
(unsigned long long)__entry->new_blkaddr,
show_bio_type(__entry->rw),
show_block_type(__entry->type))
);
DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
TP_PROTO(struct page *page, struct f2fs_io_info *fio),
TP_ARGS(page, fio),
TP_CONDITION(page->mapping)
);
DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
TP_PROTO(struct page *page, struct f2fs_io_info *fio),
TP_ARGS(page, fio),
TP_CONDITION(page->mapping)
);
DECLARE_EVENT_CLASS(f2fs__submit_bio,
TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
struct bio *bio),
TP_ARGS(sb, rw, type, bio),
TP_ARGS(sb, fio, bio),
TP_STRUCT__entry(
__field(dev_t, dev)
@ -696,8 +754,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
TP_fast_assign(
__entry->dev = sb->s_dev;
__entry->rw = rw;
__entry->type = type;
__entry->rw = fio->rw;
__entry->type = fio->type;
__entry->sector = bio->bi_iter.bi_sector;
__entry->size = bio->bi_iter.bi_size;
),
@ -712,18 +770,20 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_write_bio,
TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
struct bio *bio),
TP_ARGS(sb, rw, type, bio),
TP_ARGS(sb, fio, bio),
TP_CONDITION(bio)
);
DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
struct bio *bio),
TP_ARGS(sb, rw, type, bio),
TP_ARGS(sb, fio, bio),
TP_CONDITION(bio)
);
@ -831,6 +891,13 @@ DEFINE_EVENT(f2fs__page, f2fs_writepage,
TP_ARGS(page, type)
);
DEFINE_EVENT(f2fs__page, f2fs_do_write_data_page,
TP_PROTO(struct page *page, int type),
TP_ARGS(page, type)
);
DEFINE_EVENT(f2fs__page, f2fs_readpage,
TP_PROTO(struct page *page, int type),
@ -852,6 +919,20 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite,
TP_ARGS(page, type)
);
DEFINE_EVENT(f2fs__page, f2fs_register_inmem_page,
TP_PROTO(struct page *page, int type),
TP_ARGS(page, type)
);
DEFINE_EVENT(f2fs__page, f2fs_commit_inmem_page,
TP_PROTO(struct page *page, int type),
TP_ARGS(page, type)
);
TRACE_EVENT(f2fs_writepages,
TP_PROTO(struct inode *inode, struct writeback_control *wbc, int type),
@ -916,36 +997,30 @@ TRACE_EVENT(f2fs_writepages,
__entry->for_sync)
);
TRACE_EVENT(f2fs_submit_page_mbio,
TRACE_EVENT(f2fs_readpages,
TP_PROTO(struct page *page, int rw, int type, block_t blk_addr),
TP_PROTO(struct inode *inode, struct page *page, unsigned int nrpage),
TP_ARGS(page, rw, type, blk_addr),
TP_ARGS(inode, page, nrpage),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(int, rw)
__field(int, type)
__field(pgoff_t, index)
__field(block_t, block)
__field(pgoff_t, start)
__field(unsigned int, nrpage)
),
TP_fast_assign(
__entry->dev = page->mapping->host->i_sb->s_dev;
__entry->ino = page->mapping->host->i_ino;
__entry->rw = rw;
__entry->type = type;
__entry->index = page->index;
__entry->block = blk_addr;
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->start = page->index;
__entry->nrpage = nrpage;
),
TP_printk("dev = (%d,%d), ino = %lu, %s%s, %s, index = %lu, blkaddr = 0x%llx",
TP_printk("dev = (%d,%d), ino = %lu, start = %lu nrpage = %u",
show_dev_ino(__entry),
show_bio_type(__entry->rw),
show_block_type(__entry->type),
(unsigned long)__entry->index,
(unsigned long long)__entry->block)
(unsigned long)__entry->start,
__entry->nrpage)
);
TRACE_EVENT(f2fs_write_checkpoint,
@ -998,14 +1073,15 @@ TRACE_EVENT(f2fs_issue_discard,
TRACE_EVENT(f2fs_issue_flush,
TP_PROTO(struct super_block *sb, bool nobarrier, bool flush_merge),
TP_PROTO(struct super_block *sb, unsigned int nobarrier,
unsigned int flush_merge),
TP_ARGS(sb, nobarrier, flush_merge),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(bool, nobarrier)
__field(bool, flush_merge)
__field(unsigned int, nobarrier)
__field(unsigned int, flush_merge)
),
TP_fast_assign(
@ -1019,6 +1095,183 @@ TRACE_EVENT(f2fs_issue_flush,
__entry->nobarrier ? "skip (nobarrier)" : "issue",
__entry->flush_merge ? " with flush_merge" : "")
);
TRACE_EVENT(f2fs_lookup_extent_tree_start,
TP_PROTO(struct inode *inode, unsigned int pgofs),
TP_ARGS(inode, pgofs),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(unsigned int, pgofs)
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->pgofs = pgofs;
),
TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u",
show_dev_ino(__entry),
__entry->pgofs)
);
TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end,
TP_PROTO(struct inode *inode, unsigned int pgofs,
struct extent_info *ei),
TP_ARGS(inode, pgofs, ei),
TP_CONDITION(ei),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(unsigned int, pgofs)
__field(unsigned int, fofs)
__field(u32, blk)
__field(unsigned int, len)
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->pgofs = pgofs;
__entry->fofs = ei->fofs;
__entry->blk = ei->blk;
__entry->len = ei->len;
),
TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
"ext_info(fofs: %u, blk: %u, len: %u)",
show_dev_ino(__entry),
__entry->pgofs,
__entry->fofs,
__entry->blk,
__entry->len)
);
TRACE_EVENT(f2fs_update_extent_tree_range,
TP_PROTO(struct inode *inode, unsigned int pgofs, block_t blkaddr,
unsigned int len),
TP_ARGS(inode, pgofs, blkaddr, len),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(unsigned int, pgofs)
__field(u32, blk)
__field(unsigned int, len)
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->pgofs = pgofs;
__entry->blk = blkaddr;
__entry->len = len;
),
TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
"blkaddr = %u, len = %u",
show_dev_ino(__entry),
__entry->pgofs,
__entry->blk,
__entry->len)
);
TRACE_EVENT(f2fs_shrink_extent_tree,
TP_PROTO(struct f2fs_sb_info *sbi, unsigned int node_cnt,
unsigned int tree_cnt),
TP_ARGS(sbi, node_cnt, tree_cnt),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(unsigned int, node_cnt)
__field(unsigned int, tree_cnt)
),
TP_fast_assign(
__entry->dev = sbi->sb->s_dev;
__entry->node_cnt = node_cnt;
__entry->tree_cnt = tree_cnt;
),
TP_printk("dev = (%d,%d), shrunk: node_cnt = %u, tree_cnt = %u",
show_dev(__entry),
__entry->node_cnt,
__entry->tree_cnt)
);
TRACE_EVENT(f2fs_destroy_extent_tree,
TP_PROTO(struct inode *inode, unsigned int node_cnt),
TP_ARGS(inode, node_cnt),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(unsigned int, node_cnt)
),
TP_fast_assign(
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->node_cnt = node_cnt;
),
TP_printk("dev = (%d,%d), ino = %lu, destroyed: node_cnt = %u",
show_dev_ino(__entry),
__entry->node_cnt)
);
DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
TP_PROTO(struct super_block *sb, int type, int count),
TP_ARGS(sb, type, count),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(int, type)
__field(int, count)
),
TP_fast_assign(
__entry->dev = sb->s_dev;
__entry->type = type;
__entry->count = count;
),
TP_printk("dev = (%d,%d), %s, dirty count = %d",
show_dev(__entry),
show_file_type(__entry->type),
__entry->count)
);
DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_enter,
TP_PROTO(struct super_block *sb, int type, int count),
TP_ARGS(sb, type, count)
);
DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_exit,
TP_PROTO(struct super_block *sb, int type, int count),
TP_ARGS(sb, type, count)
);
#endif /* _TRACE_F2FS_H */
/* This part must be outside protection */