summaryrefslogtreecommitdiffstats
path: root/fs/f2fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/f2fs')
-rw-r--r--fs/f2fs/acl.c13
-rw-r--r--fs/f2fs/checkpoint.c66
-rw-r--r--fs/f2fs/data.c17
-rw-r--r--fs/f2fs/debug.c54
-rw-r--r--fs/f2fs/dir.c2
-rw-r--r--fs/f2fs/f2fs.h50
-rw-r--r--fs/f2fs/file.c51
-rw-r--r--fs/f2fs/gc.c158
-rw-r--r--fs/f2fs/gc.h21
-rw-r--r--fs/f2fs/inode.c56
-rw-r--r--fs/f2fs/node.c33
-rw-r--r--fs/f2fs/recovery.c14
-rw-r--r--fs/f2fs/segment.c31
-rw-r--r--fs/f2fs/segment.h23
-rw-r--r--fs/f2fs/super.c177
-rw-r--r--fs/f2fs/xattr.c2
16 files changed, 428 insertions, 340 deletions
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index e95b949..137af42 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -191,15 +191,14 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
retval = f2fs_getxattr(inode, name_index, "", value, retval);
}
- if (retval < 0) {
- if (retval == -ENODATA)
- acl = NULL;
- else
- acl = ERR_PTR(retval);
- } else {
+ if (retval > 0)
acl = f2fs_acl_from_disk(value, retval);
- }
+ else if (retval == -ENODATA)
+ acl = NULL;
+ else
+ acl = ERR_PTR(retval);
kfree(value);
+
if (!IS_ERR(acl))
set_cached_acl(inode, type, acl);
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 6ef36c3..2b6fc13 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -72,22 +72,22 @@ static int f2fs_write_meta_page(struct page *page,
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- int err;
- wait_on_page_writeback(page);
-
- err = write_meta_page(sbi, page, wbc);
- if (err) {
+ /* Should not write any meta pages, if any IO error was occurred */
+ if (wbc->for_reclaim ||
+ is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ERROR_FLAG)) {
+ dec_page_count(sbi, F2FS_DIRTY_META);
wbc->pages_skipped++;
set_page_dirty(page);
+ return AOP_WRITEPAGE_ACTIVATE;
}
- dec_page_count(sbi, F2FS_DIRTY_META);
+ wait_on_page_writeback(page);
- /* In this case, we should not unlock this page */
- if (err != AOP_WRITEPAGE_ACTIVATE)
- unlock_page(page);
- return err;
+ write_meta_page(sbi, page);
+ dec_page_count(sbi, F2FS_DIRTY_META);
+ unlock_page(page);
+ return 0;
}
static int f2fs_write_meta_pages(struct address_space *mapping,
@@ -138,7 +138,10 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
BUG_ON(page->mapping != mapping);
BUG_ON(!PageDirty(page));
clear_page_dirty_for_io(page);
- f2fs_write_meta_page(page, &wbc);
+ if (f2fs_write_meta_page(page, &wbc)) {
+ unlock_page(page);
+ break;
+ }
if (nwritten++ >= nr_to_write)
break;
}
@@ -161,7 +164,6 @@ static int f2fs_set_meta_page_dirty(struct page *page)
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
inc_page_count(sbi, F2FS_DIRTY_META);
- F2FS_SET_SB_DIRT(sbi);
return 1;
}
return 0;
@@ -214,22 +216,13 @@ retry:
goto retry;
}
new->ino = ino;
- INIT_LIST_HEAD(&new->list);
/* add new_oentry into list which is sorted by inode number */
- if (orphan) {
- struct orphan_inode_entry *prev;
-
- /* get previous entry */
- prev = list_entry(orphan->list.prev, typeof(*prev), list);
- if (&prev->list != head)
- /* insert new orphan inode entry */
- list_add(&new->list, &prev->list);
- else
- list_add(&new->list, head);
- } else {
+ if (orphan)
+ list_add(&new->list, this->prev);
+ else
list_add_tail(&new->list, head);
- }
+
sbi->n_orphans++;
out:
mutex_unlock(&sbi->orphan_inode_mutex);
@@ -546,7 +539,7 @@ retry:
/*
* Freeze all the FS-operations for checkpoint.
*/
-void block_operations(struct f2fs_sb_info *sbi)
+static void block_operations(struct f2fs_sb_info *sbi)
{
int t;
struct writeback_control wbc = {
@@ -718,27 +711,24 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
sbi->alloc_valid_block_count = 0;
/* Here, we only have one bio having CP pack */
- if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG))
- sbi->sb->s_flags |= MS_RDONLY;
- else
- sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+ sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
- clear_prefree_segments(sbi);
- F2FS_RESET_SB_DIRT(sbi);
+ if (!is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+ clear_prefree_segments(sbi);
+ F2FS_RESET_SB_DIRT(sbi);
+ }
}
/*
* We guarantee that this checkpoint procedure should not fail.
*/
-void write_checkpoint(struct f2fs_sb_info *sbi, bool blocked, bool is_umount)
+void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
- if (!blocked) {
- mutex_lock(&sbi->cp_mutex);
- block_operations(sbi);
- }
+ mutex_lock(&sbi->cp_mutex);
+ block_operations(sbi);
f2fs_submit_bio(sbi, DATA, true);
f2fs_submit_bio(sbi, NODE, true);
@@ -772,7 +762,7 @@ void init_orphan_info(struct f2fs_sb_info *sbi)
sbi->n_orphans = 0;
}
-int create_checkpoint_caches(void)
+int __init create_checkpoint_caches(void)
{
orphan_entry_slab = f2fs_kmem_cache_create("f2fs_orphan_entry",
sizeof(struct orphan_inode_entry), NULL);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 3aa5ce7..7bd22a2 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -547,6 +547,15 @@ redirty_out:
#define MAX_DESIRED_PAGES_WP 4096
+static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
+ void *data)
+{
+ struct address_space *mapping = data;
+ int ret = mapping->a_ops->writepage(page, wbc);
+ mapping_set_error(mapping, ret);
+ return ret;
+}
+
static int f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
@@ -563,7 +572,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
if (!S_ISDIR(inode->i_mode))
mutex_lock(&sbi->writepages);
- ret = generic_writepages(mapping, wbc);
+ ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
if (!S_ISDIR(inode->i_mode))
mutex_unlock(&sbi->writepages);
f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL));
@@ -689,6 +698,11 @@ static int f2fs_set_data_page_dirty(struct page *page)
return 0;
}
+static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
+{
+ return generic_block_bmap(mapping, block, get_data_block_ro);
+}
+
const struct address_space_operations f2fs_dblock_aops = {
.readpage = f2fs_read_data_page,
.readpages = f2fs_read_data_pages,
@@ -700,4 +714,5 @@ const struct address_space_operations f2fs_dblock_aops = {
.invalidatepage = f2fs_invalidate_data_page,
.releasepage = f2fs_release_data_page,
.direct_IO = f2fs_direct_IO,
+ .bmap = f2fs_bmap,
};
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 0e0380a..025b9e2 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -26,6 +26,7 @@
static LIST_HEAD(f2fs_stat_list);
static struct dentry *debugfs_root;
+static DEFINE_MUTEX(f2fs_stat_mutex);
static void update_general_status(struct f2fs_sb_info *sbi)
{
@@ -180,18 +181,16 @@ static int stat_show(struct seq_file *s, void *v)
int i = 0;
int j;
+ mutex_lock(&f2fs_stat_mutex);
list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
+ char devname[BDEVNAME_SIZE];
- mutex_lock(&si->stat_lock);
- if (!si->sbi) {
- mutex_unlock(&si->stat_lock);
- continue;
- }
update_general_status(si->sbi);
- seq_printf(s, "\n=====[ partition info. #%d ]=====\n", i++);
- seq_printf(s, "[SB: 1] [CP: 2] [NAT: %d] [SIT: %d] ",
- si->nat_area_segs, si->sit_area_segs);
+ seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n",
+ bdevname(si->sbi->sb->s_bdev, devname), i++);
+ seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
+ si->sit_area_segs, si->nat_area_segs);
seq_printf(s, "[SSA: %d] [MAIN: %d",
si->ssa_area_segs, si->main_area_segs);
seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
@@ -286,8 +285,8 @@ static int stat_show(struct seq_file *s, void *v)
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);
- mutex_unlock(&si->stat_lock);
}
+ mutex_unlock(&f2fs_stat_mutex);
return 0;
}
@@ -303,7 +302,7 @@ static const struct file_operations stat_fops = {
.release = single_release,
};
-static int init_stats(struct f2fs_sb_info *sbi)
+int f2fs_build_stats(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_stat_info *si;
@@ -313,9 +312,6 @@ static int init_stats(struct f2fs_sb_info *sbi)
return -ENOMEM;
si = sbi->stat_info;
- mutex_init(&si->stat_lock);
- list_add_tail(&si->stat_list, &f2fs_stat_list);
-
si->all_area_segs = le32_to_cpu(raw_super->segment_count);
si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
@@ -325,21 +321,11 @@ static int init_stats(struct f2fs_sb_info *sbi)
si->main_area_zones = si->main_area_sections /
le32_to_cpu(raw_super->secs_per_zone);
si->sbi = sbi;
- return 0;
-}
-int f2fs_build_stats(struct f2fs_sb_info *sbi)
-{
- int retval;
-
- retval = init_stats(sbi);
- if (retval)
- return retval;
-
- if (!debugfs_root)
- debugfs_root = debugfs_create_dir("f2fs", NULL);
+ mutex_lock(&f2fs_stat_mutex);
+ list_add_tail(&si->stat_list, &f2fs_stat_list);
+ mutex_unlock(&f2fs_stat_mutex);
- debugfs_create_file("status", S_IRUGO, debugfs_root, NULL, &stat_fops);
return 0;
}
@@ -347,14 +333,22 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
{
struct f2fs_stat_info *si = sbi->stat_info;
+ mutex_lock(&f2fs_stat_mutex);
list_del(&si->stat_list);
- mutex_lock(&si->stat_lock);
- si->sbi = NULL;
- mutex_unlock(&si->stat_lock);
+ mutex_unlock(&f2fs_stat_mutex);
+
kfree(sbi->stat_info);
}
-void destroy_root_stats(void)
+void __init f2fs_create_root_stats(void)
+{
+ debugfs_root = debugfs_create_dir("f2fs", NULL);
+ if (debugfs_root)
+ debugfs_create_file("status", S_IRUGO, debugfs_root,
+ NULL, &stat_fops);
+}
+
+void f2fs_destroy_root_stats(void)
{
debugfs_remove_recursive(debugfs_root);
debugfs_root = NULL;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 47df925..c395c50 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -500,7 +500,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
}
if (inode) {
- inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+ inode->i_ctime = CURRENT_TIME;
drop_nlink(inode);
if (S_ISDIR(inode->i_mode)) {
drop_nlink(inode);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 6895ecc..cc2213a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -104,6 +104,20 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
}
/*
+ * ioctl commands
+ */
+#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
+#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
+#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
+#endif
+
+/*
* For INODE and NODE manager
*/
#define XATTR_NODE_OFFSET (-1) /*
@@ -141,7 +155,7 @@ struct f2fs_inode_info {
/* Use below internally in f2fs*/
unsigned long flags; /* use to pass per-file flags */
- unsigned long long data_version;/* lastes version of data for fsync */
+ unsigned long long data_version;/* latest version of data for fsync */
atomic_t dirty_dents; /* # of dirty dentry pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
@@ -211,11 +225,11 @@ struct dnode_of_data {
static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
struct page *ipage, struct page *npage, nid_t nid)
{
+ memset(dn, 0, sizeof(*dn));
dn->inode = inode;
dn->inode_page = ipage;
dn->node_page = npage;
dn->nid = nid;
- dn->inode_page_locked = 0;
}
/*
@@ -573,6 +587,14 @@ static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
return atomic_read(&sbi->nr_pages[count_type]);
}
+static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
+{
+ unsigned int pages_per_sec = sbi->segs_per_sec *
+ (1 << sbi->log_blocks_per_seg);
+ return ((get_pages(sbi, block_type) + pages_per_sec - 1)
+ >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+}
+
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
{
block_t ret;
@@ -842,12 +864,12 @@ void f2fs_truncate(struct inode *);
int f2fs_setattr(struct dentry *, struct iattr *);
int truncate_hole(struct inode *, pgoff_t, pgoff_t);
long f2fs_ioctl(struct file *, unsigned int, unsigned long);
+long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
/*
* inode.c
*/
void f2fs_set_inode_flags(struct inode *);
-struct inode *f2fs_iget_nowait(struct super_block *, unsigned long);
struct inode *f2fs_iget(struct super_block *, unsigned long);
void update_inode(struct inode *, struct page *);
int f2fs_write_inode(struct inode *, struct writeback_control *);
@@ -883,6 +905,8 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
* super.c
*/
int f2fs_sync_fs(struct super_block *, int);
+extern __printf(3, 4)
+void f2fs_msg(struct super_block *, const char *, const char *, ...);
/*
* hash.c
@@ -918,7 +942,7 @@ int restore_node_summary(struct f2fs_sb_info *, unsigned int,
void flush_nat_entries(struct f2fs_sb_info *);
int build_node_manager(struct f2fs_sb_info *);
void destroy_node_manager(struct f2fs_sb_info *);
-int create_node_manager_caches(void);
+int __init create_node_manager_caches(void);
void destroy_node_manager_caches(void);
/*
@@ -933,8 +957,7 @@ void allocate_new_segments(struct f2fs_sb_info *);
struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
struct bio *f2fs_bio_alloc(struct block_device *, int);
void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool sync);
-int write_meta_page(struct f2fs_sb_info *, struct page *,
- struct writeback_control *);
+void write_meta_page(struct f2fs_sb_info *, struct page *);
void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int,
block_t, block_t *);
void write_data_page(struct inode *, struct page *, struct dnode_of_data*,
@@ -967,10 +990,9 @@ int get_valid_checkpoint(struct f2fs_sb_info *);
void set_dirty_dir_page(struct inode *, struct page *);
void remove_dirty_dir_inode(struct inode *);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
-void block_operations(struct f2fs_sb_info *);
-void write_checkpoint(struct f2fs_sb_info *, bool, bool);
+void write_checkpoint(struct f2fs_sb_info *, bool);
void init_orphan_info(struct f2fs_sb_info *);
-int create_checkpoint_caches(void);
+int __init create_checkpoint_caches(void);
void destroy_checkpoint_caches(void);
/*
@@ -990,9 +1012,9 @@ int do_write_data_page(struct page *);
int start_gc_thread(struct f2fs_sb_info *);
void stop_gc_thread(struct f2fs_sb_info *);
block_t start_bidx_of_node(unsigned int);
-int f2fs_gc(struct f2fs_sb_info *, int);
+int f2fs_gc(struct f2fs_sb_info *);
void build_gc_manager(struct f2fs_sb_info *);
-int create_gc_caches(void);
+int __init create_gc_caches(void);
void destroy_gc_caches(void);
/*
@@ -1064,7 +1086,8 @@ struct f2fs_stat_info {
int f2fs_build_stats(struct f2fs_sb_info *);
void f2fs_destroy_stats(struct f2fs_sb_info *);
-void destroy_root_stats(void);
+void __init f2fs_create_root_stats(void);
+void f2fs_destroy_root_stats(void);
#else
#define stat_inc_call_count(si)
#define stat_inc_seg_count(si, type)
@@ -1074,7 +1097,8 @@ void destroy_root_stats(void);
static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
-static inline void destroy_root_stats(void) { }
+static inline void __init f2fs_create_root_stats(void) { }
+static inline void f2fs_destroy_root_stats(void) { }
#endif
extern const struct file_operations f2fs_dir_operations;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 7f9ea92..b7a053d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -15,6 +15,7 @@
#include <linux/writeback.h>
#include <linux/falloc.h>
#include <linux/types.h>
+#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/mount.h>
@@ -96,8 +97,9 @@ out:
}
static const struct vm_operations_struct f2fs_file_vm_ops = {
- .fault = filemap_fault,
- .page_mkwrite = f2fs_vm_page_mkwrite,
+ .fault = filemap_fault,
+ .page_mkwrite = f2fs_vm_page_mkwrite,
+ .remap_pages = generic_file_remap_pages,
};
static int need_to_sync_dir(struct f2fs_sb_info *sbi, struct inode *inode)
@@ -137,6 +139,9 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (ret)
return ret;
+ /* guarantee free sections for fsync */
+ f2fs_balance_fs(sbi);
+
mutex_lock(&inode->i_mutex);
if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
@@ -153,11 +158,11 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
need_cp = true;
- if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
+ else if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
need_cp = true;
- if (!space_for_roll_forward(sbi))
+ else if (!space_for_roll_forward(sbi))
need_cp = true;
- if (need_to_sync_dir(sbi, inode))
+ else if (need_to_sync_dir(sbi, inode))
need_cp = true;
if (need_cp) {
@@ -294,8 +299,6 @@ void f2fs_truncate(struct inode *inode)
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
mark_inode_dirty(inode);
}
-
- f2fs_balance_fs(F2FS_SB(inode->i_sb));
}
static int f2fs_getattr(struct vfsmount *mnt,
@@ -352,6 +355,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
attr->ia_size != i_size_read(inode)) {
truncate_setsize(inode, attr->ia_size);
f2fs_truncate(inode);
+ f2fs_balance_fs(F2FS_SB(inode->i_sb));
}
__setattr_copy(inode, attr);
@@ -383,12 +387,17 @@ const struct inode_operations f2fs_file_inode_operations = {
static void fill_zero(struct inode *inode, pgoff_t index,
loff_t start, loff_t len)
{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *page;
if (!len)
return;
+ f2fs_balance_fs(sbi);
+
+ mutex_lock_op(sbi, DATA_NEW);
page = get_new_data_page(inode, index, false);
+ mutex_unlock_op(sbi, DATA_NEW);
if (!IS_ERR(page)) {
wait_on_page_writeback(page);
@@ -407,6 +416,8 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
struct dnode_of_data dn;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ f2fs_balance_fs(sbi);
+
mutex_lock_op(sbi, DATA_TRUNC);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, index, RDONLY_NODE);
@@ -534,7 +545,6 @@ static long f2fs_fallocate(struct file *file, int mode,
loff_t offset, loff_t len)
{
struct inode *inode = file->f_path.dentry->d_inode;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
long ret;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
@@ -545,7 +555,10 @@ static long f2fs_fallocate(struct file *file, int mode,
else
ret = expand_inode_data(inode, offset, len, mode);
- f2fs_balance_fs(sbi);
+ if (!ret) {
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ mark_inode_dirty(inode);
+ }
return ret;
}
@@ -622,6 +635,23 @@ out:
}
}
+#ifdef CONFIG_COMPAT
+long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case F2FS_IOC32_GETFLAGS:
+ cmd = F2FS_IOC_GETFLAGS;
+ break;
+ case F2FS_IOC32_SETFLAGS:
+ cmd = F2FS_IOC_SETFLAGS;
+ break;
+ default:
+ return -ENOIOCTLCMD;
+ }
+ return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif
+
const struct file_operations f2fs_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
@@ -633,6 +663,9 @@ const struct file_operations f2fs_file_operations = {
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
.unlocked_ioctl = f2fs_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = f2fs_compat_ioctl,
+#endif
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
};
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index b0ec721..94b8a0c 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -44,10 +44,10 @@ static int gc_thread_func(void *data)
if (kthread_should_stop())
break;
- f2fs_balance_fs(sbi);
-
- if (!test_opt(sbi, BG_GC))
+ if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
+ wait_ms = GC_THREAD_MAX_SLEEP_TIME;
continue;
+ }
/*
* [GC triggering condition]
@@ -78,7 +78,8 @@ static int gc_thread_func(void *data)
sbi->bg_gc++;
- if (f2fs_gc(sbi, 1) == GC_NONE)
+ /* if return value is not zero, no victim was selected */
+ if (f2fs_gc(sbi))
wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
else if (wait_ms == GC_THREAD_NOGC_SLEEP_TIME)
wait_ms = GC_THREAD_MAX_SLEEP_TIME;
@@ -90,7 +91,10 @@ static int gc_thread_func(void *data)
int start_gc_thread(struct f2fs_sb_info *sbi)
{
struct f2fs_gc_kthread *gc_th;
+ dev_t dev = sbi->sb->s_bdev->bd_dev;
+ if (!test_opt(sbi, BG_GC))
+ return 0;
gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
if (!gc_th)
return -ENOMEM;
@@ -98,9 +102,10 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
sbi->gc_thread = gc_th;
init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
- GC_THREAD_NAME);
+ "f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(gc_th->f2fs_gc_task)) {
kfree(gc_th);
+ sbi->gc_thread = NULL;
return -ENOMEM;
}
return 0;
@@ -141,6 +146,9 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
struct victim_sel_policy *p)
{
+ /* SSR allocates in a segment unit */
+ if (p->alloc_mode == SSR)
+ return 1 << sbi->log_blocks_per_seg;
if (p->gc_mode == GC_GREEDY)
return (1 << sbi->log_blocks_per_seg) * p->ofs_unit;
else if (p->gc_mode == GC_CB)
@@ -356,7 +364,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
sentry = get_seg_entry(sbi, segno);
ret = f2fs_test_bit(offset, sentry->cur_valid_map);
mutex_unlock(&sit_i->sentry_lock);
- return ret ? GC_OK : GC_NEXT;
+ return ret;
}
/*
@@ -364,7 +372,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
* On validity, copy that node with cold status, otherwise (invalid node)
* ignore that.
*/
-static int gc_node_segment(struct f2fs_sb_info *sbi,
+static void gc_node_segment(struct f2fs_sb_info *sbi,
struct f2fs_summary *sum, unsigned int segno, int gc_type)
{
bool initial = true;
@@ -376,21 +384,12 @@ next_step:
for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
nid_t nid = le32_to_cpu(entry->nid);
struct page *node_page;
- int err;
- /*
- * It makes sure that free segments are able to write
- * all the dirty node pages before CP after this CP.
- * So let's check the space of dirty node pages.
- */
- if (should_do_checkpoint(sbi)) {
- mutex_lock(&sbi->cp_mutex);
- block_operations(sbi);
- return GC_BLOCKED;
- }
+ /* stop BG_GC if there is not enough free sections. */
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+ return;
- err = check_valid_map(sbi, segno, off);
- if (err == GC_NEXT)
+ if (check_valid_map(sbi, segno, off) == 0)
continue;
if (initial) {
@@ -420,11 +419,14 @@ next_step:
};
sync_node_pages(sbi, 0, &wbc);
}
- return GC_DONE;
}
/*
- * Calculate start block index that this node page contains
+ * Calculate start block index indicating the given node offset.
+ * Be careful, caller should give this node offset only indicating direct node
+ * blocks. If any node offsets, which point the other types of node blocks such
+ * 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)
{
@@ -459,13 +461,13 @@ 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 GC_NEXT;
+ return 0;
get_node_info(sbi, nid, dni);
if (sum->version != dni->version) {
f2fs_put_page(node_page, 1);
- return GC_NEXT;
+ return 0;
}
*nofs = ofs_of_node(node_page);
@@ -473,8 +475,8 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
f2fs_put_page(node_page, 1);
if (source_blkaddr != blkaddr)
- return GC_NEXT;
- return GC_OK;
+ return 0;
+ return 1;
}
static void move_data_page(struct inode *inode, struct page *page, int gc_type)
@@ -515,13 +517,13 @@ out:
* If the parent node is not valid or the data block address is different,
* the victim data block is ignored.
*/
-static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+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 super_block *sb = sbi->sb;
struct f2fs_summary *entry;
block_t start_addr;
- int err, off;
+ int off;
int phase = 0;
start_addr = START_BLOCK(sbi, segno);
@@ -535,20 +537,11 @@ next_step:
unsigned int ofs_in_node, nofs;
block_t start_bidx;
- /*
- * It makes sure that free segments are able to write
- * all the dirty node pages before CP after this CP.
- * So let's check the space of dirty node pages.
- */
- if (should_do_checkpoint(sbi)) {
- mutex_lock(&sbi->cp_mutex);
- block_operations(sbi);
- err = GC_BLOCKED;
- goto stop;
- }
+ /* stop BG_GC if there is not enough free sections. */
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+ return;
- err = check_valid_map(sbi, segno, off);
- if (err == GC_NEXT)
+ if (check_valid_map(sbi, segno, off) == 0)
continue;
if (phase == 0) {
@@ -557,8 +550,7 @@ next_step:
}
/* Get an inode by ino with checking validity */
- err = check_dnode(sbi, entry, &dni, start_addr + off, &nofs);
- if (err == GC_NEXT)
+ if (check_dnode(sbi, entry, &dni, start_addr + off, &nofs) == 0)
continue;
if (phase == 1) {
@@ -570,7 +562,7 @@ next_step:
ofs_in_node = le16_to_cpu(entry->ofs_in_node);
if (phase == 2) {
- inode = f2fs_iget_nowait(sb, dni.ino);
+ inode = f2fs_iget(sb, dni.ino);
if (IS_ERR(inode))
continue;
@@ -598,11 +590,9 @@ next_iput:
}
if (++phase < 4)
goto next_step;
- err = GC_DONE;
-stop:
+
if (gc_type == FG_GC)
f2fs_submit_bio(sbi, DATA, true);
- return err;
}
static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
@@ -616,17 +606,16 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
return ret;
}
-static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
+static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
struct list_head *ilist, int gc_type)
{
struct page *sum_page;
struct f2fs_summary_block *sum;
- int ret = GC_DONE;
/* read segment summary of victim */
sum_page = get_sum_page(sbi, segno);
if (IS_ERR(sum_page))
- return GC_ERROR;
+ return;
/*
* CP needs to lock sum_page. In this time, we don't need
@@ -638,76 +627,55 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
switch (GET_SUM_TYPE((&sum->footer))) {
case SUM_TYPE_NODE:
- ret = gc_node_segment(sbi, sum->entries, segno, gc_type);
+ gc_node_segment(sbi, sum->entries, segno, gc_type);
break;
case SUM_TYPE_DATA:
- ret = gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
+ gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
break;
}
stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)));
stat_inc_call_count(sbi->stat_info);
f2fs_put_page(sum_page, 0);
- return ret;
}
-int f2fs_gc(struct f2fs_sb_info *sbi, int nGC)
+int f2fs_gc(struct f2fs_sb_info *sbi)
{
- unsigned int segno;
- int old_free_secs, cur_free_secs;
- int gc_status, nfree;
struct list_head ilist;
+ unsigned int segno, i;
int gc_type = BG_GC;
+ int nfree = 0;
+ int ret = -1;
INIT_LIST_HEAD(&ilist);
gc_more:
- nfree = 0;
- gc_status = GC_NONE;
+ if (!(sbi->sb->s_flags & MS_ACTIVE))
+ goto stop;
- if (has_not_enough_free_secs(sbi))
- old_free_secs = reserved_sections(sbi);
- else
- old_free_secs = free_sections(sbi);
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree))
+ gc_type = FG_GC;
- while (sbi->sb->s_flags & MS_ACTIVE) {
- int i;
- if (has_not_enough_free_secs(sbi))
- gc_type = FG_GC;
+ if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
+ goto stop;
+ ret = 0;
- cur_free_secs = free_sections(sbi) + nfree;
+ for (i = 0; i < sbi->segs_per_sec; i++)
+ do_garbage_collect(sbi, segno + i, &ilist, gc_type);
- /* We got free space successfully. */
- if (nGC < cur_free_secs - old_free_secs)
- break;
+ if (gc_type == FG_GC &&
+ get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
+ nfree++;
- if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
- break;
+ if (has_not_enough_free_secs(sbi, nfree))
+ goto gc_more;
- for (i = 0; i < sbi->segs_per_sec; i++) {
- /*
- * do_garbage_collect will give us three gc_status:
- * GC_ERROR, GC_DONE, and GC_BLOCKED.
- * If GC is finished uncleanly, we have to return
- * the victim to dirty segment list.
- */
- gc_status = do_garbage_collect(sbi, segno + i,
- &ilist, gc_type);
- if (gc_status != GC_DONE)
- goto stop;
- nfree++;
- }
- }
+ if (gc_type == FG_GC)
+ write_checkpoint(sbi, false);
stop:
- if (has_not_enough_free_secs(sbi) || gc_status == GC_BLOCKED) {
- write_checkpoint(sbi, (gc_status == GC_BLOCKED), false);
- if (nfree)
- goto gc_more;
- }
mutex_unlock(&sbi->gc_mutex);
put_gc_inode(&ilist);
- BUG_ON(!list_empty(&ilist));
- return gc_status;
+ return ret;
}
void build_gc_manager(struct f2fs_sb_info *sbi)
@@ -715,7 +683,7 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
DIRTY_I(sbi)->v_ops = &default_v_ops;
}
-int create_gc_caches(void)
+int __init create_gc_caches(void)
{
winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
sizeof(struct inode_entry), NULL);
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index b026d93..30b2db0 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -8,7 +8,6 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
-#define GC_THREAD_NAME "f2fs_gc_task"
#define GC_THREAD_MIN_WB_PAGES 1 /*
* a threshold to determine
* whether IO subsystem is idle
@@ -23,15 +22,6 @@
/* Search max. number of dirty segments to select a victim segment */
#define MAX_VICTIM_SEARCH 20
-enum {
- GC_NONE = 0,
- GC_ERROR,
- GC_OK,
- GC_NEXT,
- GC_BLOCKED,
- GC_DONE,
-};
-
struct f2fs_gc_kthread {
struct task_struct *f2fs_gc_task;
wait_queue_head_t gc_wait_queue_head;
@@ -104,14 +94,3 @@ static inline int is_idle(struct f2fs_sb_info *sbi)
struct request_list *rl = &q->root_rl;
return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
}
-
-static inline bool should_do_checkpoint(struct f2fs_sb_info *sbi)
-{
- unsigned int pages_per_sec = sbi->segs_per_sec *
- (1 << sbi->log_blocks_per_seg);
- int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
- int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
- return free_sections(sbi) <= (node_secs + 2 * dent_secs + 2);
-}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index bf20b4d..ddae412 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -16,11 +16,6 @@
#include "f2fs.h"
#include "node.h"
-struct f2fs_iget_args {
- u64 ino;
- int on_free;
-};
-
void f2fs_set_inode_flags(struct inode *inode)
{
unsigned int flags = F2FS_I(inode)->i_flags;
@@ -40,34 +35,6 @@ void f2fs_set_inode_flags(struct inode *inode)
inode->i_flags |= S_DIRSYNC;
}
-static int f2fs_iget_test(struct inode *inode, void *data)
-{
- struct f2fs_iget_args *args = data;
-
- if (inode->i_ino != args->ino)
- return 0;
- if (inode->i_state & (I_FREEING | I_WILL_FREE)) {
- args->on_free = 1;
- return 0;
- }
- return 1;
-}
-
-struct inode *f2fs_iget_nowait(struct super_block *sb, unsigned long ino)
-{
- struct f2fs_iget_args args = {
- .ino = ino,
- .on_free = 0
- };
- struct inode *inode = ilookup5(sb, ino, f2fs_iget_test, &args);
-
- if (inode)
- return inode;
- if (!args.on_free)
- return f2fs_iget(sb, ino);
- return ERR_PTR(-ENOENT);
-}
-
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
@@ -100,6 +67,10 @@ static int do_read_inode(struct inode *inode)
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
inode->i_generation = le32_to_cpu(ri->i_generation);
+ if (ri->i_addr[0])
+ inode->i_rdev = old_decode_dev(le32_to_cpu(ri->i_addr[0]));
+ else
+ inode->i_rdev = new_decode_dev(le32_to_cpu(ri->i_addr[1]));
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
@@ -203,6 +174,20 @@ void update_inode(struct inode *inode, struct page *node_page)
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
ri->i_generation = cpu_to_le32(inode->i_generation);
+
+ if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
+ if (old_valid_dev(inode->i_rdev)) {
+ ri->i_addr[0] =
+ cpu_to_le32(old_encode_dev(inode->i_rdev));
+ ri->i_addr[1] = 0;
+ } else {
+ ri->i_addr[0] = 0;
+ ri->i_addr[1] =
+ cpu_to_le32(new_encode_dev(inode->i_rdev));
+ ri->i_addr[2] = 0;
+ }
+ }
+
set_cold_node(inode, node_page);
set_page_dirty(node_page);
}
@@ -217,6 +202,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
inode->i_ino == F2FS_META_INO(sbi))
return 0;
+ if (wbc)
+ f2fs_balance_fs(sbi);
+
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
@@ -257,6 +245,7 @@ void f2fs_evict_inode(struct inode *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);
i_size_write(inode, 0);
@@ -264,6 +253,7 @@ void f2fs_evict_inode(struct inode *inode)
f2fs_truncate(inode);
remove_inode_page(inode);
+ sb_end_intwrite(inode->i_sb);
no_delete:
clear_inode(inode);
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 6625ca8..0da252c 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -104,7 +104,7 @@ static void ra_nat_pages(struct f2fs_sb_info *sbi, int nid)
f2fs_put_page(page, 1);
continue;
}
- page_cache_release(page);
+ f2fs_put_page(page, 0);
}
}
@@ -874,15 +874,11 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
return;
if (read_node_page(apage, READA))
- goto unlock_out;
+ unlock_page(apage);
- page_cache_release(apage);
- return;
-
-unlock_out:
- unlock_page(apage);
release_out:
- page_cache_release(apage);
+ f2fs_put_page(apage, 0);
+ return;
}
struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
@@ -1124,6 +1120,12 @@ static int f2fs_write_node_page(struct page *page,
return 0;
}
+/*
+ * It is very important to gather dirty pages and write at once, so that we can
+ * submit a big bio without interfering other data writes.
+ * Be default, 512 pages (2MB), a segment size, is quite reasonable.
+ */
+#define COLLECT_DIRTY_NODES 512
static int f2fs_write_node_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
@@ -1131,17 +1133,16 @@ static int f2fs_write_node_pages(struct address_space *mapping,
struct block_device *bdev = sbi->sb->s_bdev;
long nr_to_write = wbc->nr_to_write;
- if (wbc->for_kupdate)
- return 0;
-
- if (get_pages(sbi, F2FS_DIRTY_NODES) == 0)
- return 0;
-
+ /* First check balancing cached NAT entries */
if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK)) {
- write_checkpoint(sbi, false, false);
+ write_checkpoint(sbi, false);
return 0;
}
+ /* collect a number of dirty node pages and write together */
+ if (get_pages(sbi, F2FS_DIRTY_NODES) < COLLECT_DIRTY_NODES)
+ return 0;
+
/* if mounting is failed, skip writing node pages */
wbc->nr_to_write = bio_get_nr_vecs(bdev);
sync_node_pages(sbi, 0, wbc);
@@ -1732,7 +1733,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
kfree(nm_i);
}
-int create_node_manager_caches(void)
+int __init create_node_manager_caches(void)
{
nat_entry_slab = f2fs_kmem_cache_create("nat_entry",
sizeof(struct nat_entry), NULL);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 6200042..b235215 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -65,7 +65,7 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
kunmap(page);
f2fs_put_page(page, 0);
} else {
- __f2fs_add_link(dir, &name, inode);
+ err = __f2fs_add_link(dir, &name, inode);
}
iput(dir);
out:
@@ -149,7 +149,6 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
goto out;
}
- INIT_LIST_HEAD(&entry->list);
list_add_tail(&entry->list, head);
entry->blkaddr = blkaddr;
}
@@ -172,10 +171,9 @@ out:
static void destroy_fsync_dnodes(struct f2fs_sb_info *sbi,
struct list_head *head)
{
- struct list_head *this;
- struct fsync_inode_entry *entry;
- list_for_each(this, head) {
- entry = list_entry(this, struct fsync_inode_entry, list);
+ struct fsync_inode_entry *entry, *tmp;
+
+ list_for_each_entry_safe(entry, tmp, head, list) {
iput(entry->inode);
list_del(&entry->list);
kmem_cache_free(fsync_entry_slab, entry);
@@ -226,7 +224,7 @@ static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
f2fs_put_page(node_page, 1);
/* Deallocate previous index in the node page */
- inode = f2fs_iget_nowait(sbi->sb, ino);
+ inode = f2fs_iget(sbi->sb, ino);
if (IS_ERR(inode))
return;
@@ -373,5 +371,5 @@ void recover_fsync_data(struct f2fs_sb_info *sbi)
out:
destroy_fsync_dnodes(sbi, &inode_list);
kmem_cache_destroy(fsync_entry_slab);
- write_checkpoint(sbi, false, false);
+ write_checkpoint(sbi, false);
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index de62409..777f17e 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -29,9 +29,9 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi)
* We should do GC or end up with checkpoint, if there are so many dirty
* dir/node pages without enough free segments.
*/
- if (has_not_enough_free_secs(sbi)) {
+ if (has_not_enough_free_secs(sbi, 0)) {
mutex_lock(&sbi->gc_mutex);
- f2fs_gc(sbi, 1);
+ f2fs_gc(sbi);
}
}
@@ -308,7 +308,7 @@ static unsigned int check_prefree_segments(struct f2fs_sb_info *sbi,
* If there is not enough reserved sections,
* we should not reuse prefree segments.
*/
- if (has_not_enough_free_secs(sbi))
+ if (has_not_enough_free_secs(sbi, 0))
return NULL_SEGNO;
/*
@@ -536,6 +536,23 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse)
}
}
+static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+{
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
+ const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
+
+ if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0))
+ return v_ops->get_victim(sbi,
+ &(curseg)->next_segno, BG_GC, type, SSR);
+
+ /* For data segments, let's do SSR more intensively */
+ for (; type >= CURSEG_HOT_DATA; type--)
+ if (v_ops->get_victim(sbi, &(curseg)->next_segno,
+ BG_GC, type, SSR))
+ return 1;
+ return 0;
+}
+
/*
* flush out current segment and replace it with new segment
* This function should be returned with success, otherwise BUG
@@ -600,6 +617,7 @@ static void f2fs_end_io_write(struct bio *bio, int err)
if (page->mapping)
set_bit(AS_EIO, &page->mapping->flags);
set_ckpt_flags(p->sbi->ckpt, CP_ERROR_FLAG);
+ p->sbi->sb->s_flags |= MS_RDONLY;
}
end_page_writeback(page);
dec_page_count(p->sbi, F2FS_WRITEBACK);
@@ -815,15 +833,10 @@ static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
mutex_unlock(&curseg->curseg_mutex);
}
-int write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
- struct writeback_control *wbc)
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
{
- if (wbc->for_reclaim)
- return AOP_WRITEPAGE_ACTIVATE;
-
set_page_writeback(page);
submit_write_page(sbi, page, page->index, META);
- return 0;
}
void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 66a288a..552dadb 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -450,29 +450,16 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi)
return (free_sections(sbi) < overprovision_sections(sbi));
}
-static inline int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
{
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- return DIRTY_I(sbi)->v_ops->get_victim(sbi,
- &(curseg)->next_segno, BG_GC, type, SSR);
-}
-
-static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi)
-{
- unsigned int pages_per_sec = (1 << sbi->log_blocks_per_seg) *
- sbi->segs_per_sec;
- int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
- int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+ int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
+ int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
if (sbi->por_doing)
return false;
- if (free_sections(sbi) <= (node_secs + 2 * dent_secs +
- reserved_sections(sbi)))
- return true;
- return false;
+ return ((free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
+ reserved_sections(sbi)));
}
static inline int utilization(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 08a94c8..8c11764 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -53,6 +53,18 @@ static match_table_t f2fs_tokens = {
{Opt_err, NULL},
};
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
+{
+ struct va_format vaf;
+ va_list args;
+
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
+ va_end(args);
+}
+
static void init_once(void *foo)
{
struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;
@@ -100,7 +112,7 @@ static void f2fs_put_super(struct super_block *sb)
f2fs_destroy_stats(sbi);
stop_gc_thread(sbi);
- write_checkpoint(sbi, false, true);
+ write_checkpoint(sbi, true);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -124,11 +136,29 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
return 0;
if (sync)
- write_checkpoint(sbi, false, false);
+ write_checkpoint(sbi, false);
+ else
+ f2fs_balance_fs(sbi);
return 0;
}
+static int f2fs_freeze(struct super_block *sb)
+{
+ int err;
+
+ if (sb->s_flags & MS_RDONLY)
+ return 0;
+
+ err = f2fs_sync_fs(sb, 1);
+ return err;
+}
+
+static int f2fs_unfreeze(struct super_block *sb)
+{
+ return 0;
+}
+
static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
@@ -184,7 +214,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",noacl");
#endif
if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
- seq_puts(seq, ",disable_ext_indentify");
+ seq_puts(seq, ",disable_ext_identify");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
@@ -199,6 +229,8 @@ static struct super_operations f2fs_sops = {
.evict_inode = f2fs_evict_inode,
.put_super = f2fs_put_super,
.sync_fs = f2fs_sync_fs,
+ .freeze_fs = f2fs_freeze,
+ .unfreeze_fs = f2fs_unfreeze,
.statfs = f2fs_statfs,
};
@@ -247,7 +279,8 @@ static const struct export_operations f2fs_export_ops = {
.get_parent = f2fs_get_parent,
};
-static int parse_options(struct f2fs_sb_info *sbi, char *options)
+static int parse_options(struct super_block *sb, struct f2fs_sb_info *sbi,
+ char *options)
{
substring_t args[MAX_OPT_ARGS];
char *p;
@@ -286,7 +319,8 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
break;
#else
case Opt_nouser_xattr:
- pr_info("nouser_xattr options not supported\n");
+ f2fs_msg(sb, KERN_INFO,
+ "nouser_xattr options not supported");
break;
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
@@ -295,7 +329,7 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
break;
#else
case Opt_noacl:
- pr_info("noacl options not supported\n");
+ f2fs_msg(sb, KERN_INFO, "noacl options not supported");
break;
#endif
case Opt_active_logs:
@@ -309,8 +343,9 @@ static int parse_options(struct f2fs_sb_info *sbi, char *options)
set_opt(sbi, DISABLE_EXT_IDENTIFY);
break;
default:
- pr_err("Unrecognized mount option \"%s\" or missing value\n",
- p);
+ f2fs_msg(sb, KERN_ERR,
+ "Unrecognized mount option \"%s\" or missing value",
+ p);
return -EINVAL;
}
}
@@ -337,30 +372,53 @@ static loff_t max_file_size(unsigned bits)
return result;
}
-static int sanity_check_raw_super(struct f2fs_super_block *raw_super)
+static int sanity_check_raw_super(struct super_block *sb,
+ struct f2fs_super_block *raw_super)
{
unsigned int blocksize;
- if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic))
+ if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Magic Mismatch, valid(0x%x) - read(0x%x)",
+ F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
return 1;
+ }
+
+ /* Currently, support only 4KB page cache size */
+ if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid page_cache_size (%lu), supports only 4KB\n",
+ PAGE_CACHE_SIZE);
+ return 1;
+ }
/* Currently, support only 4KB block size */
blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
- if (blocksize != PAGE_CACHE_SIZE)
+ if (blocksize != F2FS_BLKSIZE) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid blocksize (%u), supports only 4KB\n",
+ blocksize);
return 1;
+ }
+
if (le32_to_cpu(raw_super->log_sectorsize) !=
- F2FS_LOG_SECTOR_SIZE)
+ F2FS_LOG_SECTOR_SIZE) {
+ f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
return 1;
+ }
if (le32_to_cpu(raw_super->log_sectors_per_block) !=
- F2FS_LOG_SECTORS_PER_BLOCK)
+ F2FS_LOG_SECTORS_PER_BLOCK) {
+ f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block");
return 1;
+ }
return 0;
}
-static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
- struct f2fs_checkpoint *ckpt)
+static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
{
unsigned int total, fsmeta;
+ struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
total = le32_to_cpu(raw_super->segment_count);
fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -371,6 +429,11 @@ static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
if (fsmeta >= total)
return 1;
+
+ if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
+ return 1;
+ }
return 0;
}
@@ -399,6 +462,32 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
atomic_set(&sbi->nr_pages[i], 0);
}
+static int validate_superblock(struct super_block *sb,
+ struct f2fs_super_block **raw_super,
+ struct buffer_head **raw_super_buf, sector_t block)
+{
+ const char *super = (block == 0 ? "first" : "second");
+
+ /* read f2fs raw super block */
+ *raw_super_buf = sb_bread(sb, block);
+ if (!*raw_super_buf) {
+ f2fs_msg(sb, KERN_ERR, "unable to read %s superblock",
+ super);
+ return 1;
+ }
+
+ *raw_super = (struct f2fs_super_block *)
+ ((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET);
+
+ /* sanity checking of raw super */
+ if (!sanity_check_raw_super(sb, *raw_super))
+ return 0;
+
+ f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem "
+ "in %s superblock", super);
+ return 1;
+}
+
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
@@ -413,19 +502,17 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
if (!sbi)
return -ENOMEM;
- /* set a temporary block size */
- if (!sb_set_blocksize(sb, F2FS_BLKSIZE))
- goto free_sbi;
-
- /* read f2fs raw super block */
- raw_super_buf = sb_bread(sb, 0);
- if (!raw_super_buf) {
- err = -EIO;
+ /* set a block size */
+ if (!sb_set_blocksize(sb, F2FS_BLKSIZE)) {
+ f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
goto free_sbi;
}
- raw_super = (struct f2fs_super_block *)
- ((char *)raw_super_buf->b_data + F2FS_SUPER_OFFSET);
+ if (validate_superblock(sb, &raw_super, &raw_super_buf, 0)) {
+ brelse(raw_super_buf);
+ if (validate_superblock(sb, &raw_super, &raw_super_buf, 1))
+ goto free_sb_buf;
+ }
/* init some FS parameters */
sbi->active_logs = NR_CURSEG_TYPE;
@@ -438,11 +525,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
set_opt(sbi, POSIX_ACL);
#endif
/* parse mount options */
- if (parse_options(sbi, (char *)data))
- goto free_sb_buf;
-
- /* sanity checking of raw super */
- if (sanity_check_raw_super(raw_super))
+ if (parse_options(sb, sbi, (char *)data))
goto free_sb_buf;
sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
@@ -477,18 +560,23 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
/* get an inode for meta space */
sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
if (IS_ERR(sbi->meta_inode)) {
+ f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
err = PTR_ERR(sbi->meta_inode);
goto free_sb_buf;
}
err = get_valid_checkpoint(sbi);
- if (err)
+ if (err) {
+ f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
goto free_meta_inode;
+ }
/* sanity checking of checkpoint */
err = -EINVAL;
- if (sanity_check_ckpt(raw_super, sbi->ckpt))
+ if (sanity_check_ckpt(sbi)) {
+ f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
goto free_cp;
+ }
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
@@ -502,25 +590,28 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
INIT_LIST_HEAD(&sbi->dir_inode_list);
spin_lock_init(&sbi->dir_inode_lock);
- /* init super block */
- if (!sb_set_blocksize(sb, sbi->blocksize))
- goto free_cp;
-
init_orphan_info(sbi);
/* setup f2fs internal modules */
err = build_segment_manager(sbi);
- if (err)
+ if (err) {
+ f2fs_msg(sb, KERN_ERR,
+ "Failed to initialize F2FS segment manager");
goto free_sm;
+ }
err = build_node_manager(sbi);
- if (err)
+ if (err) {
+ f2fs_msg(sb, KERN_ERR,
+ "Failed to initialize F2FS node manager");
goto free_nm;
+ }
build_gc_manager(sbi);
/* get an inode for node space */
sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
if (IS_ERR(sbi->node_inode)) {
+ f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
err = PTR_ERR(sbi->node_inode);
goto free_nm;
}
@@ -533,6 +624,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
if (IS_ERR(root)) {
+ f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
err = PTR_ERR(root);
goto free_node_inode;
}
@@ -596,7 +688,7 @@ static struct file_system_type f2fs_fs_type = {
.fs_flags = FS_REQUIRES_DEV,
};
-static int init_inodecache(void)
+static int __init init_inodecache(void)
{
f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
sizeof(struct f2fs_inode_info), NULL);
@@ -631,14 +723,17 @@ static int __init init_f2fs_fs(void)
err = create_checkpoint_caches();
if (err)
goto fail;
- return register_filesystem(&f2fs_fs_type);
+ err = register_filesystem(&f2fs_fs_type);
+ if (err)
+ goto fail;
+ f2fs_create_root_stats();
fail:
return err;
}
static void __exit exit_f2fs_fs(void)
{
- destroy_root_stats();
+ f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
destroy_checkpoint_caches();
destroy_gc_caches();
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 940136a..8038c04 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -318,6 +318,8 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
if (name_len > 255 || value_len > MAX_VALUE_LEN)
return -ERANGE;
+ f2fs_balance_fs(sbi);
+
mutex_lock_op(sbi, NODE_NEW);
if (!fi->i_xattr_nid) {
/* Allocate new attribute block */
OpenPOWER on IntegriCloud