f2fs: update from git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
Updated as of commit b3b06a14a26af368dd58f9265cf5a9927067b768
Change-Id: I3dfbbf52d069a397de662058bb72bf96c6393bc6
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 736a348..94e2d2f 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -71,3 +71,13 @@
Enables BUG_ONs which check the filesystem consistency in runtime.
If you want to improve the performance, say N.
+
+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.
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 2e35da1..d923977 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -5,3 +5,4 @@
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
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 2385ef8..df1a307 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -62,7 +62,7 @@
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);
@@ -108,7 +108,7 @@
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);
@@ -146,7 +146,8 @@
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)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT;
@@ -164,12 +165,13 @@
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)
@@ -186,6 +188,11 @@
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)
{
@@ -227,7 +234,7 @@
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);
}
}
@@ -238,11 +245,12 @@
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;
}
-int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage)
+int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
+ struct page *dpage)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
struct posix_acl *acl = NULL;
@@ -250,7 +258,7 @@
if (!S_ISLNK(inode->i_mode)) {
if (test_opt(sbi, POSIX_ACL)) {
- acl = f2fs_get_acl(dir, ACL_TYPE_DEFAULT);
+ acl = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage);
if (IS_ERR(acl))
return PTR_ERR(acl);
}
diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h
index 4963313..b4ba686 100644
--- a/fs/f2fs/acl.h
+++ b/fs/f2fs/acl.h
@@ -38,7 +38,8 @@
extern struct posix_acl *f2fs_get_acl(struct inode *, int);
extern int f2fs_acl_chmod(struct inode *);
-extern int f2fs_init_acl(struct inode *, struct inode *, struct page *);
+extern int f2fs_init_acl(struct inode *, struct inode *, struct page *,
+ struct page *);
#else
#define f2fs_check_acl NULL
#define f2fs_get_acl NULL
@@ -50,7 +51,7 @@
}
static inline int f2fs_init_acl(struct inode *inode, struct inode *dir,
- struct page *page)
+ struct page *ipage, struct page *dpage)
{
return 0;
}
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 0058028..ae2ab5f 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -20,10 +20,11 @@
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
static struct kmem_cache *ino_entry_slab;
-static struct kmem_cache *inode_entry_slab;
+struct kmem_cache *inode_entry_slab;
/*
* We guarantee no failure on the returned page.
@@ -50,6 +51,11 @@
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page;
+ struct f2fs_io_info fio = {
+ .type = META,
+ .rw = READ_SYNC | REQ_META | REQ_PRIO,
+ .blk_addr = index,
+ };
repeat:
page = grab_cache_page(mapping, index);
if (!page) {
@@ -59,8 +65,7 @@
if (PageUptodate(page))
goto out;
- if (f2fs_submit_page_bio(sbi, page, index,
- READ_SYNC | REQ_META | REQ_PRIO))
+ if (f2fs_submit_page_bio(sbi, page, &fio))
goto repeat;
lock_page(page);
@@ -69,70 +74,87 @@
goto repeat;
}
out:
+ mark_page_accessed(page);
return page;
}
-static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
+static inline bool is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type)
{
switch (type) {
case META_NAT:
- return NM_I(sbi)->max_nid / NAT_ENTRY_PER_BLOCK;
+ break;
case META_SIT:
- return SIT_BLK_CNT(sbi);
+ if (unlikely(blkaddr >= SIT_BLK_CNT(sbi)))
+ return false;
+ break;
case META_SSA:
+ if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) ||
+ blkaddr < SM_I(sbi)->ssa_blkaddr))
+ return false;
+ break;
case META_CP:
- return 0;
+ if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr ||
+ blkaddr < __start_cp_addr(sbi)))
+ return false;
+ break;
+ case META_POR:
+ if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
+ blkaddr < MAIN_BLKADDR(sbi)))
+ return false;
+ break;
default:
BUG();
}
+
+ return true;
}
/*
* Readahead CP/NAT/SIT/SSA pages
*/
-int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type)
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type)
{
block_t prev_blk_addr = 0;
struct page *page;
- int blkno = start;
- int max_blks = get_max_meta_blks(sbi, type);
-
+ block_t blkno = start;
struct f2fs_io_info fio = {
.type = META,
.rw = READ_SYNC | REQ_META | REQ_PRIO
};
for (; nrpages-- > 0; blkno++) {
- block_t blk_addr;
+
+ if (!is_valid_blkaddr(sbi, blkno, type))
+ goto out;
switch (type) {
case META_NAT:
- /* get nat block addr */
- if (unlikely(blkno >= max_blks))
+ if (unlikely(blkno >=
+ NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
blkno = 0;
- blk_addr = current_nat_addr(sbi,
+ /* get nat block addr */
+ fio.blk_addr = current_nat_addr(sbi,
blkno * NAT_ENTRY_PER_BLOCK);
break;
case META_SIT:
/* get sit block addr */
- if (unlikely(blkno >= max_blks))
- goto out;
- blk_addr = current_sit_addr(sbi,
+ fio.blk_addr = current_sit_addr(sbi,
blkno * SIT_ENTRY_PER_BLOCK);
- if (blkno != start && prev_blk_addr + 1 != blk_addr)
+ if (blkno != start && prev_blk_addr + 1 != fio.blk_addr)
goto out;
- prev_blk_addr = blk_addr;
+ prev_blk_addr = fio.blk_addr;
break;
case META_SSA:
case META_CP:
- /* get ssa/cp block addr */
- blk_addr = blkno;
+ case META_POR:
+ fio.blk_addr = blkno;
break;
default:
BUG();
}
- page = grab_cache_page(META_MAPPING(sbi), blk_addr);
+ page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr);
if (!page)
continue;
if (PageUptodate(page)) {
@@ -140,7 +162,7 @@
continue;
}
- f2fs_submit_page_mbio(sbi, page, blk_addr, &fio);
+ f2fs_submit_page_mbio(sbi, page, &fio);
f2fs_put_page(page, 0);
}
out:
@@ -148,17 +170,30 @@
return blkno - start;
}
+void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ struct page *page;
+ bool readahead = false;
+
+ page = find_get_page(META_MAPPING(sbi), index);
+ if (!page || (page && !PageUptodate(page)))
+ readahead = true;
+ f2fs_put_page(page, 0);
+
+ if (readahead)
+ ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR);
+}
+
static int f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc)
{
- struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
trace_f2fs_writepage(page, META);
- if (unlikely(sbi->por_doing))
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
- if (wbc->for_reclaim)
+ if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
@@ -167,6 +202,9 @@
write_meta_page(sbi, page);
dec_page_count(sbi, F2FS_DIRTY_META);
unlock_page(page);
+
+ if (wbc->for_reclaim)
+ f2fs_submit_merged_bio(sbi, META, WRITE);
return 0;
redirty_out:
@@ -177,7 +215,7 @@
static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff, written;
trace_f2fs_writepages(mapping->host, wbc, META);
@@ -259,15 +297,14 @@
static int f2fs_set_meta_page_dirty(struct page *page)
{
- struct address_space *mapping = page->mapping;
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
-
trace_f2fs_set_page_dirty(page, META);
SetPageUptodate(page);
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
- inc_page_count(sbi, F2FS_DIRTY_META);
+ inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
+ SetPagePrivate(page);
+ f2fs_trace_pid(page);
return 1;
}
return 0;
@@ -277,50 +314,63 @@
.writepage = f2fs_write_meta_page,
.writepages = f2fs_write_meta_pages,
.set_page_dirty = f2fs_set_meta_page_dirty,
+ .invalidatepage = f2fs_invalidate_page,
+ .releasepage = f2fs_release_page,
};
static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
+ struct inode_management *im = &sbi->im[type];
struct ino_entry *e;
retry:
- spin_lock(&sbi->ino_lock[type]);
+ if (radix_tree_preload(GFP_NOFS)) {
+ cond_resched();
+ goto retry;
+ }
- e = radix_tree_lookup(&sbi->ino_root[type], ino);
+ spin_lock(&im->ino_lock);
+
+ e = radix_tree_lookup(&im->ino_root, ino);
if (!e) {
e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC);
if (!e) {
- spin_unlock(&sbi->ino_lock[type]);
+ spin_unlock(&im->ino_lock);
+ radix_tree_preload_end();
goto retry;
}
- if (radix_tree_insert(&sbi->ino_root[type], ino, e)) {
- spin_unlock(&sbi->ino_lock[type]);
+ if (radix_tree_insert(&im->ino_root, ino, e)) {
+ spin_unlock(&im->ino_lock);
kmem_cache_free(ino_entry_slab, e);
+ radix_tree_preload_end();
goto retry;
}
memset(e, 0, sizeof(struct ino_entry));
e->ino = ino;
- list_add_tail(&e->list, &sbi->ino_list[type]);
+ list_add_tail(&e->list, &im->ino_list);
+ if (type != ORPHAN_INO)
+ im->ino_num++;
}
- spin_unlock(&sbi->ino_lock[type]);
+ spin_unlock(&im->ino_lock);
+ radix_tree_preload_end();
}
static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
+ struct inode_management *im = &sbi->im[type];
struct ino_entry *e;
- spin_lock(&sbi->ino_lock[type]);
- e = radix_tree_lookup(&sbi->ino_root[type], ino);
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
if (e) {
list_del(&e->list);
- radix_tree_delete(&sbi->ino_root[type], ino);
- if (type == ORPHAN_INO)
- sbi->n_orphans--;
- spin_unlock(&sbi->ino_lock[type]);
+ radix_tree_delete(&im->ino_root, ino);
+ im->ino_num--;
+ spin_unlock(&im->ino_lock);
kmem_cache_free(ino_entry_slab, e);
return;
}
- spin_unlock(&sbi->ino_lock[type]);
+ spin_unlock(&im->ino_lock);
}
void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -338,10 +388,12 @@
/* mode should be APPEND_INO or UPDATE_INO */
bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
+ struct inode_management *im = &sbi->im[mode];
struct ino_entry *e;
- spin_lock(&sbi->ino_lock[mode]);
- e = radix_tree_lookup(&sbi->ino_root[mode], ino);
- spin_unlock(&sbi->ino_lock[mode]);
+
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
+ spin_unlock(&im->ino_lock);
return e ? true : false;
}
@@ -351,36 +403,42 @@
int i;
for (i = APPEND_INO; i <= UPDATE_INO; i++) {
- spin_lock(&sbi->ino_lock[i]);
- list_for_each_entry_safe(e, tmp, &sbi->ino_list[i], list) {
+ struct inode_management *im = &sbi->im[i];
+
+ spin_lock(&im->ino_lock);
+ list_for_each_entry_safe(e, tmp, &im->ino_list, list) {
list_del(&e->list);
- radix_tree_delete(&sbi->ino_root[i], e->ino);
+ radix_tree_delete(&im->ino_root, e->ino);
kmem_cache_free(ino_entry_slab, e);
+ im->ino_num--;
}
- spin_unlock(&sbi->ino_lock[i]);
+ spin_unlock(&im->ino_lock);
}
}
int acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
int err = 0;
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- if (unlikely(sbi->n_orphans >= sbi->max_orphans))
+ spin_lock(&im->ino_lock);
+ if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
- sbi->n_orphans++;
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+ im->ino_num++;
+ spin_unlock(&im->ino_lock);
return err;
}
void release_orphan_inode(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- f2fs_bug_on(sbi->n_orphans == 0);
- sbi->n_orphans--;
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
+
+ spin_lock(&im->ino_lock);
+ f2fs_bug_on(sbi, im->ino_num == 0);
+ im->ino_num--;
+ spin_unlock(&im->ino_lock);
}
void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
@@ -398,7 +456,7 @@
static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode = f2fs_iget(sbi->sb, ino);
- f2fs_bug_on(IS_ERR(inode));
+ f2fs_bug_on(sbi, IS_ERR(inode));
clear_nlink(inode);
/* truncate all the data during iput */
@@ -412,7 +470,7 @@
if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
return;
- sbi->por_doing = true;
+ set_sbi_flag(sbi, SBI_POR_DOING);
start_blk = __start_cp_addr(sbi) + 1 +
le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
@@ -433,7 +491,7 @@
}
/* clear Orphan Flag */
clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
- sbi->por_doing = false;
+ clear_sbi_flag(sbi, SBI_POR_DOING);
return;
}
@@ -443,23 +501,25 @@
struct f2fs_orphan_block *orphan_blk = NULL;
unsigned int nentries = 0;
unsigned short index;
- unsigned short orphan_blocks =
- (unsigned short)GET_ORPHAN_BLOCKS(sbi->n_orphans);
+ unsigned short orphan_blocks;
struct page *page = NULL;
struct ino_entry *orphan = NULL;
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
+
+ orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num);
for (index = 0; index < orphan_blocks; index++)
grab_meta_page(sbi, start_blk + index);
index = 1;
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- head = &sbi->ino_list[ORPHAN_INO];
+ spin_lock(&im->ino_lock);
+ head = &im->ino_list;
/* loop for each orphan inode entry and write them in Jornal block */
list_for_each_entry(orphan, head, list) {
if (!page) {
page = find_get_page(META_MAPPING(sbi), start_blk++);
- f2fs_bug_on(!page);
+ f2fs_bug_on(sbi, !page);
orphan_blk =
(struct f2fs_orphan_block *)page_address(page);
memset(orphan_blk, 0, sizeof(*orphan_blk));
@@ -493,7 +553,7 @@
f2fs_put_page(page, 1);
}
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+ spin_unlock(&im->ino_lock);
}
static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
@@ -515,7 +575,7 @@
if (crc_offset >= blk_size)
goto invalid_cp1;
- crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
+ crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
if (!f2fs_crc_valid(crc, cp_block, crc_offset))
goto invalid_cp1;
@@ -530,7 +590,7 @@
if (crc_offset >= blk_size)
goto invalid_cp2;
- crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
+ crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
if (!f2fs_crc_valid(crc, cp_block, crc_offset))
goto invalid_cp2;
@@ -617,9 +677,9 @@
return -EINVAL;
}
-static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
+static int __add_dirty_inode(struct inode *inode, struct inode_entry *new)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
return -EEXIST;
@@ -631,33 +691,40 @@
return 0;
}
-void set_dirty_dir_page(struct inode *inode, struct page *page)
+void update_dirty_page(struct inode *inode, struct page *page)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct dir_inode_entry *new;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct inode_entry *new;
int ret = 0;
- if (!S_ISDIR(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
return;
+ if (!S_ISDIR(inode->i_mode)) {
+ inode_inc_dirty_pages(inode);
+ goto out;
+ }
+
new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
new->inode = inode;
INIT_LIST_HEAD(&new->list);
spin_lock(&sbi->dir_inode_lock);
ret = __add_dirty_inode(inode, new);
- inode_inc_dirty_dents(inode);
- SetPagePrivate(page);
+ inode_inc_dirty_pages(inode);
spin_unlock(&sbi->dir_inode_lock);
if (ret)
kmem_cache_free(inode_entry_slab, new);
+out:
+ SetPagePrivate(page);
+ f2fs_trace_pid(page);
}
void add_dirty_dir_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct dir_inode_entry *new =
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct inode_entry *new =
f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
int ret = 0;
@@ -674,14 +741,14 @@
void remove_dirty_dir_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct dir_inode_entry *entry;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct inode_entry *entry;
if (!S_ISDIR(inode->i_mode))
return;
spin_lock(&sbi->dir_inode_lock);
- if (get_dirty_dents(inode) ||
+ if (get_dirty_pages(inode) ||
!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
spin_unlock(&sbi->dir_inode_lock);
return;
@@ -705,9 +772,12 @@
void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
{
struct list_head *head;
- struct dir_inode_entry *entry;
+ struct inode_entry *entry;
struct inode *inode;
retry:
+ if (unlikely(f2fs_cp_error(sbi)))
+ return;
+
spin_lock(&sbi->dir_inode_lock);
head = &sbi->dir_inode_list;
@@ -715,7 +785,7 @@
spin_unlock(&sbi->dir_inode_lock);
return;
}
- entry = list_entry(head->next, struct dir_inode_entry, list);
+ entry = list_entry(head->next, struct inode_entry, list);
inode = igrab(entry->inode);
spin_unlock(&sbi->dir_inode_lock);
if (inode) {
@@ -802,10 +872,13 @@
finish_wait(&sbi->cp_wait, &wait);
}
-static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- nid_t last_nid = 0;
+ struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
+ nid_t last_nid = nm_i->next_scan_nid;
block_t start_blk;
struct page *cp_page;
unsigned int data_sum_blocks, orphan_blocks;
@@ -818,7 +891,7 @@
* This avoids to conduct wrong roll-forward operations and uses
* metapages, so should be called prior to sync_meta_pages below.
*/
- discard_next_dnode(sbi);
+ discard_next_dnode(sbi, NEXT_FREE_BLKADDR(sbi, curseg));
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
@@ -858,33 +931,43 @@
ckpt->next_free_nid = cpu_to_le32(last_nid);
/* 2 cp + n data seg summary + orphan inode blocks */
- data_sum_blocks = npages_for_summary_flush(sbi);
+ data_sum_blocks = npages_for_summary_flush(sbi, false);
if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
else
clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
- orphan_blocks = GET_ORPHAN_BLOCKS(sbi->n_orphans);
+ orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
orphan_blocks);
- if (is_umount) {
- set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+ if (__remain_node_summaries(cpc->reason))
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
cp_payload_blks + data_sum_blocks +
orphan_blocks + NR_CURSEG_NODE_TYPE);
- } else {
- clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+ else
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
cp_payload_blks + data_sum_blocks +
orphan_blocks);
- }
- if (sbi->n_orphans)
+ if (cpc->reason == CP_UMOUNT)
+ set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+ else
+ clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+
+ if (cpc->reason == CP_FASTBOOT)
+ set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+ else
+ clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+
+ if (orphan_num)
set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
else
clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+ if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
+ set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+
/* update SIT/NAT bitmap */
get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
@@ -899,27 +982,26 @@
/* write out checkpoint buffer at block 0 */
cp_page = grab_meta_page(sbi, start_blk++);
kaddr = page_address(cp_page);
- memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+ memcpy(kaddr, ckpt, F2FS_BLKSIZE);
set_page_dirty(cp_page);
f2fs_put_page(cp_page, 1);
for (i = 1; i < 1 + cp_payload_blks; i++) {
cp_page = grab_meta_page(sbi, start_blk++);
kaddr = page_address(cp_page);
- memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE,
- (1 << sbi->log_blocksize));
+ memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE, F2FS_BLKSIZE);
set_page_dirty(cp_page);
f2fs_put_page(cp_page, 1);
}
- if (sbi->n_orphans) {
+ if (orphan_num) {
write_orphan_inodes(sbi, start_blk);
start_blk += orphan_blocks;
}
write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
- if (is_umount) {
+ if (__remain_node_summaries(cpc->reason)) {
write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
@@ -927,7 +1009,7 @@
/* writeout checkpoint block */
cp_page = grab_meta_page(sbi, start_blk);
kaddr = page_address(cp_page);
- memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+ memcpy(kaddr, ckpt, F2FS_BLKSIZE);
set_page_dirty(cp_page);
f2fs_put_page(cp_page, 1);
@@ -947,35 +1029,41 @@
/* Here, we only have one bio having CP pack */
sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+ /* wait for previous submitted meta pages writeback */
+ wait_on_all_pages_writeback(sbi);
+
release_dirty_inode(sbi);
if (unlikely(f2fs_cp_error(sbi)))
return;
clear_prefree_segments(sbi);
- F2FS_RESET_SB_DIRT(sbi);
+ clear_sbi_flag(sbi, SBI_IS_DIRTY);
}
/*
* We guarantee that this checkpoint procedure will not fail.
*/
-void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
mutex_lock(&sbi->cp_mutex);
- if (!sbi->s_dirty)
+ if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
+ cpc->reason != CP_DISCARD && cpc->reason != CP_UMOUNT)
goto out;
if (unlikely(f2fs_cp_error(sbi)))
goto out;
+ if (f2fs_readonly(sbi->sb))
+ goto out;
if (block_operations(sbi))
goto out;
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
f2fs_submit_merged_bio(sbi, DATA, WRITE);
f2fs_submit_merged_bio(sbi, NODE, WRITE);
@@ -991,16 +1079,16 @@
/* write cached NAT/SIT entries to NAT/SIT area */
flush_nat_entries(sbi);
- flush_sit_entries(sbi);
+ flush_sit_entries(sbi, cpc);
/* unlock all the fs_lock[] in do_checkpoint() */
- do_checkpoint(sbi, is_umount);
+ do_checkpoint(sbi, cpc);
unblock_operations(sbi);
stat_inc_cp_count(sbi->stat_info);
out:
mutex_unlock(&sbi->cp_mutex);
- trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
}
void init_ino_entry_info(struct f2fs_sb_info *sbi)
@@ -1008,9 +1096,12 @@
int i;
for (i = 0; i < MAX_INO_ENTRY; i++) {
- INIT_RADIX_TREE(&sbi->ino_root[i], GFP_ATOMIC);
- spin_lock_init(&sbi->ino_lock[i]);
- INIT_LIST_HEAD(&sbi->ino_list[i]);
+ struct inode_management *im = &sbi->im[i];
+
+ INIT_RADIX_TREE(&im->ino_root, GFP_ATOMIC);
+ spin_lock_init(&im->ino_lock);
+ INIT_LIST_HEAD(&im->ino_list);
+ im->ino_num = 0;
}
/*
@@ -1019,7 +1110,6 @@
* orphan entries with the limitation one reserved segment
* for cp pack we can have max 1020*504 orphan entries
*/
- sbi->n_orphans = 0;
sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
NR_CURSEG_TYPE) * F2FS_ORPHANS_PER_BLOCK;
}
@@ -1030,8 +1120,8 @@
sizeof(struct ino_entry));
if (!ino_entry_slab)
return -ENOMEM;
- inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry",
- sizeof(struct dir_inode_entry));
+ inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
+ sizeof(struct inode_entry));
if (!inode_entry_slab) {
kmem_cache_destroy(ino_entry_slab);
return -ENOMEM;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0fdae6f..7c507bf 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -22,6 +22,7 @@
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
static void f2fs_read_end_io(struct bio *bio, int err)
@@ -55,18 +56,12 @@
if (unlikely(err)) {
set_page_dirty(page);
set_bit(AS_EIO, &page->mapping->flags);
- set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
- sbi->sb->s_flags |= MS_RDONLY;
+ f2fs_stop_checkpoint(sbi);
}
end_page_writeback(page);
dec_page_count(sbi, F2FS_WRITEBACK);
}
- if (sbi->wait_io) {
- complete(sbi->wait_io);
- sbi->wait_io = NULL;
- }
-
if (!get_pages(sbi, F2FS_WRITEBACK) &&
!list_empty(&sbi->cp_wait.task_list))
wake_up(&sbi->cp_wait);
@@ -86,7 +81,7 @@
bio = bio_alloc(GFP_NOIO, npages);
bio->bi_bdev = sbi->sb->s_bdev;
- bio->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+ bio->bi_sector = SECTOR_FROM_BLOCK(blk_addr);
bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
bio->bi_private = sbi;
@@ -96,34 +91,16 @@
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
- int rw;
if (!io->bio)
return;
- rw = fio->rw;
+ if (is_read_io(fio->rw))
+ trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
+ else
+ trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
- if (is_read_io(rw)) {
- trace_f2fs_submit_read_bio(io->sbi->sb, rw,
- fio->type, io->bio);
- submit_bio(rw, io->bio);
- } else {
- trace_f2fs_submit_write_bio(io->sbi->sb, rw,
- fio->type, io->bio);
- /*
- * META_FLUSH is only from the checkpoint procedure, and we
- * should wait this metadata bio for FS consistency.
- */
- if (fio->type == META_FLUSH) {
- DECLARE_COMPLETION_ONSTACK(wait);
- io->sbi->wait_io = &wait;
- submit_bio(rw, io->bio);
- wait_for_completion(&wait);
- } else {
- submit_bio(rw, io->bio);
- }
- }
-
+ submit_bio(fio->rw, io->bio);
io->bio = NULL;
}
@@ -154,14 +131,15 @@
* Return unlocked page.
*/
int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
- block_t blk_addr, int rw)
+ struct f2fs_io_info *fio)
{
struct bio *bio;
- trace_f2fs_submit_page_bio(page, blk_addr, rw);
+ trace_f2fs_submit_page_bio(page, fio);
+ f2fs_trace_ios(page, fio, 0);
/* Allocate a new bio */
- bio = __bio_alloc(sbi, blk_addr, 1, is_read_io(rw));
+ bio = __bio_alloc(sbi, fio->blk_addr, 1, is_read_io(fio->rw));
if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
bio_put(bio);
@@ -169,12 +147,12 @@
return -EFAULT;
}
- submit_bio(rw, bio);
+ submit_bio(fio->rw, bio);
return 0;
}
void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
- block_t blk_addr, struct f2fs_io_info *fio)
+ struct f2fs_io_info *fio)
{
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io;
@@ -182,21 +160,21 @@
io = is_read ? &sbi->read_io : &sbi->write_io[btype];
- verify_block_addr(sbi, blk_addr);
+ verify_block_addr(sbi, fio->blk_addr);
down_write(&io->io_rwsem);
if (!is_read)
inc_page_count(sbi, F2FS_WRITEBACK);
- if (io->bio && (io->last_block_in_bio != blk_addr - 1 ||
+ if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 ||
io->fio.rw != fio->rw))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
- int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ int bio_blocks = MAX_BIO_BLOCKS(sbi);
- io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read);
+ io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read);
io->fio = *fio;
}
@@ -206,10 +184,11 @@
goto alloc_new;
}
- io->last_block_in_bio = blk_addr;
+ io->last_block_in_bio = fio->blk_addr;
+ f2fs_trace_ios(page, fio, 0);
up_write(&io->io_rwsem);
- trace_f2fs_submit_page_mbio(page, fio->rw, fio->type, blk_addr);
+ trace_f2fs_submit_page_mbio(page, fio);
}
/*
@@ -218,7 +197,7 @@
* ->node_page
* update block addresses in the node page
*/
-static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
+static void __set_data_blkaddr(struct dnode_of_data *dn)
{
struct f2fs_node *rn;
__le32 *addr_array;
@@ -231,13 +210,13 @@
/* Get physical address of data block */
addr_array = blkaddr_in_node(rn);
- addr_array[ofs_in_node] = cpu_to_le32(new_addr);
+ addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
set_page_dirty(node_page);
}
int reserve_new_block(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return -EPERM;
@@ -246,8 +225,8 @@
trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
- __set_data_blkaddr(dn, NEW_ADDR);
dn->data_blkaddr = NEW_ADDR;
+ __set_data_blkaddr(dn);
mark_inode_dirty(dn->inode);
sync_inode_page(dn);
return 0;
@@ -258,9 +237,6 @@
bool need_put = dn->inode_page ? false : true;
int err;
- /* if inode_page exists, index should be zero */
- f2fs_bug_on(!need_put && index);
-
err = get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
@@ -298,7 +274,7 @@
unsigned int blkbits = inode->i_sb->s_blocksize_bits;
size_t count;
- clear_buffer_new(bh_result);
+ set_buffer_new(bh_result);
map_bh(bh_result, inode->i_sb,
start_blkaddr + pgofs - start_fofs);
count = end_fofs - pgofs + 1;
@@ -315,23 +291,24 @@
return 0;
}
-void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
+void update_extent_cache(struct dnode_of_data *dn)
{
struct f2fs_inode_info *fi = F2FS_I(dn->inode);
pgoff_t fofs, start_fofs, end_fofs;
block_t start_blkaddr, end_blkaddr;
int need_update = true;
- f2fs_bug_on(blk_addr == NEW_ADDR);
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
- dn->ofs_in_node;
+ f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
/* Update the page address in the parent node */
- __set_data_blkaddr(dn, blk_addr);
+ __set_data_blkaddr(dn);
if (is_inode_flag_set(fi, FI_NO_EXTENT))
return;
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+ dn->ofs_in_node;
+
write_lock(&fi->ext.ext_lock);
start_fofs = fi->ext.fofs;
@@ -345,16 +322,16 @@
/* Initial extent */
if (fi->ext.len == 0) {
- if (blk_addr != NULL_ADDR) {
+ if (dn->data_blkaddr != NULL_ADDR) {
fi->ext.fofs = fofs;
- fi->ext.blk_addr = blk_addr;
+ fi->ext.blk_addr = dn->data_blkaddr;
fi->ext.len = 1;
}
goto end_update;
}
/* Front merge */
- if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
+ if (fofs == start_fofs - 1 && dn->data_blkaddr == start_blkaddr - 1) {
fi->ext.fofs--;
fi->ext.blk_addr--;
fi->ext.len++;
@@ -362,7 +339,7 @@
}
/* Back merge */
- if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) {
+ if (fofs == end_fofs + 1 && dn->data_blkaddr == end_blkaddr + 1) {
fi->ext.len++;
goto end_update;
}
@@ -397,11 +374,14 @@
struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
int err;
+ struct f2fs_io_info fio = {
+ .type = DATA,
+ .rw = sync ? READ_SYNC : READA,
+ };
page = find_get_page(mapping, index);
if (page && PageUptodate(page))
@@ -430,8 +410,8 @@
return page;
}
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
- sync ? READ_SYNC : READA);
+ fio.blk_addr = dn.data_blkaddr;
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
if (err)
return ERR_PTR(err);
@@ -452,12 +432,14 @@
*/
struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
int err;
-
+ struct f2fs_io_info fio = {
+ .type = DATA,
+ .rw = READ_SYNC,
+ };
repeat:
page = grab_cache_page(mapping, index);
if (!page)
@@ -491,7 +473,8 @@
return page;
}
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, READ_SYNC);
+ fio.blk_addr = dn.data_blkaddr;
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
if (err)
return ERR_PTR(err);
@@ -518,7 +501,6 @@
struct page *get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
struct page *page;
struct dnode_of_data dn;
@@ -542,8 +524,12 @@
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
SetPageUptodate(page);
} else {
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
- READ_SYNC);
+ struct f2fs_io_info fio = {
+ .type = DATA,
+ .rw = READ_SYNC,
+ .blk_addr = dn.data_blkaddr,
+ };
+ err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
if (err)
goto put_err;
@@ -574,36 +560,88 @@
static int __allocate_data_block(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ struct f2fs_inode_info *fi = F2FS_I(dn->inode);
struct f2fs_summary sum;
- block_t new_blkaddr;
struct node_info ni;
- int type;
+ int seg = CURSEG_WARM_DATA;
+ pgoff_t fofs;
if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
return -EPERM;
if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
return -ENOSPC;
- __set_data_blkaddr(dn, NEW_ADDR);
- dn->data_blkaddr = NEW_ADDR;
-
get_node_info(sbi, dn->nid, &ni);
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
- type = CURSEG_WARM_DATA;
+ if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page)
+ seg = CURSEG_DIRECT_IO;
- allocate_data_block(sbi, NULL, NULL_ADDR, &new_blkaddr, &sum, type);
+ allocate_data_block(sbi, NULL, NULL_ADDR, &dn->data_blkaddr, &sum, seg);
/* direct IO doesn't use extent cache to maximize the performance */
- set_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
- update_extent_cache(new_blkaddr, dn);
- clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
+ __set_data_blkaddr(dn);
- dn->data_blkaddr = new_blkaddr;
+ /* update i_size */
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+ dn->ofs_in_node;
+ if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
+ i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
+
return 0;
}
+static void __allocate_data_blocks(struct inode *inode, loff_t offset,
+ size_t count)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct dnode_of_data dn;
+ u64 start = F2FS_BYTES_TO_BLK(offset);
+ u64 len = F2FS_BYTES_TO_BLK(count);
+ bool allocated;
+ u64 end_offset;
+
+ while (len) {
+ f2fs_balance_fs(sbi);
+ f2fs_lock_op(sbi);
+
+ /* When reading holes, we need its node page */
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ if (get_dnode_of_data(&dn, start, ALLOC_NODE))
+ goto out;
+
+ allocated = false;
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+
+ while (dn.ofs_in_node < end_offset && len) {
+ if (dn.data_blkaddr == NULL_ADDR) {
+ if (__allocate_data_block(&dn))
+ goto sync_out;
+ allocated = true;
+ }
+ len--;
+ start++;
+ dn.ofs_in_node++;
+ }
+
+ if (allocated)
+ sync_inode_page(&dn);
+
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
+ }
+ return;
+
+sync_out:
+ if (allocated)
+ sync_inode_page(&dn);
+ f2fs_put_dnode(&dn);
+out:
+ f2fs_unlock_op(sbi);
+ return;
+}
+
/*
* get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh.
* If original data blocks are allocated, then give them to blockdev.
@@ -615,7 +653,6 @@
static int __get_data_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create, bool fiemap)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
unsigned int blkbits = inode->i_sb->s_blocksize_bits;
unsigned maxblocks = bh_result->b_size >> blkbits;
struct dnode_of_data dn;
@@ -630,10 +667,8 @@
if (check_extent_cache(inode, pgofs, bh_result))
goto out;
- if (create) {
- f2fs_balance_fs(sbi);
- f2fs_lock_op(sbi);
- }
+ if (create)
+ f2fs_lock_op(F2FS_I_SB(inode));
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -647,12 +682,14 @@
goto put_out;
if (dn.data_blkaddr != NULL_ADDR) {
+ set_buffer_new(bh_result);
map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
} else if (create) {
err = __allocate_data_block(&dn);
if (err)
goto put_out;
allocated = true;
+ set_buffer_new(bh_result);
map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
} else {
goto put_out;
@@ -708,7 +745,7 @@
f2fs_put_dnode(&dn);
unlock_out:
if (create)
- f2fs_unlock_op(sbi);
+ f2fs_unlock_op(F2FS_I_SB(inode));
out:
trace_f2fs_get_data_block(inode, iblock, bh_result, err);
return err;
@@ -736,14 +773,14 @@
static int f2fs_read_data_page(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
- int ret;
+ int ret = -EAGAIN;
trace_f2fs_readpage(page, DATA);
/* If the file has inline data, try to read it directly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
- else
+ if (ret == -EAGAIN)
ret = mpage_readpage(page, get_data_block);
return ret;
@@ -765,7 +802,6 @@
int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
{
struct inode *inode = page->mapping->host;
- block_t old_blkaddr, new_blkaddr;
struct dnode_of_data dn;
int err = 0;
@@ -774,10 +810,10 @@
if (err)
return err;
- old_blkaddr = dn.data_blkaddr;
+ fio->blk_addr = dn.data_blkaddr;
/* This page is already truncated */
- if (old_blkaddr == NULL_ADDR)
+ if (fio->blk_addr == NULL_ADDR)
goto out_writepage;
set_page_writeback(page);
@@ -786,14 +822,14 @@
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
- if (unlikely(old_blkaddr != NEW_ADDR &&
+ if (unlikely(fio->blk_addr != NEW_ADDR &&
!is_cold_data(page) &&
need_inplace_update(inode))) {
- rewrite_data_page(page, old_blkaddr, fio);
+ rewrite_data_page(page, fio);
set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
} else {
- write_data_page(page, &dn, &new_blkaddr, fio);
- update_extent_cache(new_blkaddr, &dn);
+ write_data_page(page, &dn, fio);
+ update_extent_cache(&dn);
set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
}
out_writepage:
@@ -805,7 +841,7 @@
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
>> PAGE_CACHE_SHIFT;
@@ -832,7 +868,12 @@
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
write:
- if (unlikely(sbi->por_doing))
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto redirty_out;
+ if (f2fs_is_drop_cache(inode))
+ goto out;
+ if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
+ available_free_memory(sbi, BASE_CHECK))
goto redirty_out;
/* Dentry blocks are controlled by checkpoint */
@@ -846,8 +887,7 @@
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
SetPageError(page);
- unlock_page(page);
- return 0;
+ goto out;
}
if (!wbc->for_reclaim)
@@ -855,10 +895,11 @@
else if (has_not_enough_free_secs(sbi, 0))
goto redirty_out;
+ err = -EAGAIN;
f2fs_lock_op(sbi);
- if (f2fs_has_inline_data(inode) || f2fs_may_inline(inode))
- err = f2fs_write_inline_data(inode, page, offset);
- else
+ if (f2fs_has_inline_data(inode))
+ err = f2fs_write_inline_data(inode, page);
+ if (err == -EAGAIN)
err = do_write_data_page(page, &fio);
f2fs_unlock_op(sbi);
done:
@@ -867,7 +908,7 @@
clear_cold_data(page);
out:
- inode_dec_dirty_dents(inode);
+ inode_dec_dirty_pages(inode);
unlock_page(page);
if (need_balance_fs)
f2fs_balance_fs(sbi);
@@ -893,7 +934,7 @@
struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
bool locked = false;
int ret;
long diff;
@@ -905,7 +946,7 @@
return 0;
if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
- get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) &&
+ get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
@@ -927,7 +968,7 @@
return ret;
skip_write:
- wbc->pages_skipped += get_dirty_dents(inode);
+ wbc->pages_skipped += get_dirty_pages(inode);
return 0;
}
@@ -946,8 +987,8 @@
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct page *page;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct page *page, *ipage;
pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
struct dnode_of_data dn;
int err = 0;
@@ -955,45 +996,60 @@
trace_f2fs_write_begin(inode, pos, len, flags);
f2fs_balance_fs(sbi);
-repeat:
- err = f2fs_convert_inline_data(inode, pos + len, NULL);
- if (err)
- goto fail;
+ /*
+ * We should check this at this moment to avoid deadlock on inode page
+ * and #0 page. The locking rule for inline_data conversion should be:
+ * lock_page(page #0) -> lock_page(inode_page)
+ */
+ if (index != 0) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ goto fail;
+ }
+repeat:
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
err = -ENOMEM;
goto fail;
}
- /* to avoid latency during memory pressure */
- unlock_page(page);
-
*pagep = page;
- if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
- goto inline_data;
-
f2fs_lock_op(sbi);
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_reserve_block(&dn, index);
- f2fs_unlock_op(sbi);
- if (err) {
- f2fs_put_page(page, 0);
- goto fail;
- }
-inline_data:
- lock_page(page);
- if (unlikely(page->mapping != mapping)) {
- f2fs_put_page(page, 1);
- goto repeat;
+
+ /* check inline_data */
+ ipage = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto unlock_fail;
}
- f2fs_wait_on_page_writeback(page, DATA);
+ set_new_dnode(&dn, inode, ipage, ipage, 0);
+
+ if (f2fs_has_inline_data(inode)) {
+ if (pos + len <= MAX_INLINE_DATA) {
+ read_inline_data(page, ipage);
+ set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+ sync_inode_page(&dn);
+ goto put_next;
+ }
+ err = f2fs_convert_inline_page(&dn, page);
+ if (err)
+ goto put_fail;
+ }
+ err = f2fs_reserve_block(&dn, index);
+ if (err)
+ goto put_fail;
+put_next:
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
return 0;
+ f2fs_wait_on_page_writeback(page, DATA);
+
if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
unsigned start = pos & (PAGE_CACHE_SIZE - 1);
unsigned end = start + len;
@@ -1006,18 +1062,14 @@
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
} else {
- if (f2fs_has_inline_data(inode)) {
- err = f2fs_read_inline_data(inode, page);
- if (err) {
- page_cache_release(page);
- goto fail;
- }
- } else {
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
- READ_SYNC);
- if (err)
- goto fail;
- }
+ struct f2fs_io_info fio = {
+ .type = DATA,
+ .rw = READ_SYNC,
+ .blk_addr = dn.data_blkaddr,
+ };
+ err = f2fs_submit_page_bio(sbi, page, &fio);
+ if (err)
+ goto fail;
lock_page(page);
if (unlikely(!PageUptodate(page))) {
@@ -1034,6 +1086,12 @@
SetPageUptodate(page);
clear_cold_data(page);
return 0;
+
+put_fail:
+ f2fs_put_dnode(&dn);
+unlock_fail:
+ f2fs_unlock_op(sbi);
+ f2fs_put_page(page, 1);
fail:
f2fs_write_failed(mapping, pos + len);
return err;
@@ -1072,9 +1130,9 @@
if (offset & blocksize_mask)
return -EINVAL;
- for (i = 0; i < nr_segs; i++)
- if (iov[i].iov_len & blocksize_mask)
- return -EINVAL;
+ for (i = 0; i < nr_segs; i++)
+ if (iov[i].iov_len & blocksize_mask)
+ return -EINVAL;
return 0;
}
@@ -1089,21 +1147,23 @@
size_t count = iov_length(iov, nr_segs);
int err;
- /* Let buffer I/O handle the inline data case. */
- if (f2fs_has_inline_data(inode))
- return 0;
+ /* we don't need to use inline_data strictly */
+ if (f2fs_has_inline_data(inode)) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
if (check_direct_IO(inode, rw, iov, offset, nr_segs))
return 0;
- /* clear fsync mark to recover these blocks */
- fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino);
+ trace_f2fs_direct_IO_enter(inode, offset, count, rw);
+
+ if (rw & WRITE)
+ __allocate_data_blocks(inode, offset, count);
err = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
get_data_block);
-
- trace_f2fs_direct_IO_enter(inode, offset, count, rw);
-
if (err < 0 && (rw & WRITE))
f2fs_write_failed(mapping, offset + count);
@@ -1112,16 +1172,31 @@
return err;
}
-static void f2fs_invalidate_data_page(struct page *page, unsigned long offset)
+void f2fs_invalidate_page(struct page *page, unsigned long offset)
{
struct inode *inode = page->mapping->host;
- if (PageDirty(page))
- inode_dec_dirty_dents(inode);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ if (inode->i_ino >= F2FS_ROOT_INO(sbi) && (offset % PAGE_CACHE_SIZE))
+ return;
+
+ if (PageDirty(page)) {
+ if (inode->i_ino == F2FS_META_INO(sbi))
+ dec_page_count(sbi, F2FS_DIRTY_META);
+ else if (inode->i_ino == F2FS_NODE_INO(sbi))
+ dec_page_count(sbi, F2FS_DIRTY_NODES);
+ else
+ inode_dec_dirty_pages(inode);
+ }
ClearPagePrivate(page);
}
-static int f2fs_release_data_page(struct page *page, gfp_t wait)
+int f2fs_release_page(struct page *page, gfp_t wait)
{
+ /* If this is dirty page, keep PagePrivate */
+ if (PageDirty(page))
+ return 0;
+
ClearPagePrivate(page);
return 1;
}
@@ -1134,11 +1209,17 @@
trace_f2fs_set_page_dirty(page, DATA);
SetPageUptodate(page);
+
+ if (f2fs_is_atomic_file(inode)) {
+ register_inmem_page(inode, page);
+ return 1;
+ }
+
mark_inode_dirty(inode);
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
- set_dirty_dir_page(inode, page);
+ update_dirty_page(inode, page);
return 1;
}
return 0;
@@ -1148,9 +1229,12 @@
{
struct inode *inode = mapping->host;
- if (f2fs_has_inline_data(inode))
- return 0;
-
+ /* we don't need to use inline_data strictly */
+ if (f2fs_has_inline_data(inode)) {
+ int err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
return generic_block_bmap(mapping, block, get_data_block);
}
@@ -1162,8 +1246,8 @@
.write_begin = f2fs_write_begin,
.write_end = f2fs_write_end,
.set_page_dirty = f2fs_set_data_page_dirty,
- .invalidatepage = f2fs_invalidate_data_page,
- .releasepage = f2fs_release_data_page,
+ .invalidatepage = f2fs_invalidate_page,
+ .releasepage = f2fs_release_page,
.direct_IO = f2fs_direct_IO,
.bmap = f2fs_bmap,
};
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index fecebdb..e671373 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -39,13 +39,16 @@
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->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_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 +58,9 @@
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 +82,8 @@
si->segment_count[i] = sbi->segment_count[i];
si->block_count[i] = sbi->block_count[i];
}
+
+ si->inplace_count = atomic_read(&sbi->inplace_count);
}
/*
@@ -93,7 +100,7 @@
total_vblocks = 0;
blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg);
hblks_per_sec = blks_per_sec / 2;
- for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) {
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
dist = abs(vblocks - hblks_per_sec);
bimodal += dist * dist;
@@ -103,7 +110,7 @@
ndirty++;
}
}
- dist = TOTAL_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
+ dist = MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
si->bimodal = bimodal / dist;
if (si->dirty_count)
si->avg_vblocks = total_vblocks / ndirty;
@@ -118,6 +125,7 @@
{
struct f2fs_stat_info *si = F2FS_STAT(sbi);
unsigned npages;
+ int i;
if (si->base_mem)
goto get_cache;
@@ -131,17 +139,18 @@
/* build sit */
si->base_mem += sizeof(struct sit_info);
- si->base_mem += TOTAL_SEGS(sbi) * sizeof(struct seg_entry);
- si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * TOTAL_SEGS(sbi);
+ si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
+ si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+ si->base_mem += SIT_VBLOCK_MAP_SIZE;
if (sbi->segs_per_sec > 1)
- si->base_mem += TOTAL_SECS(sbi) * sizeof(struct sec_entry);
+ si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
/* build free segmap */
si->base_mem += sizeof(struct free_segmap_info);
- si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
/* build curseg */
si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
@@ -149,26 +158,39 @@
/* build dirty segmap */
si->base_mem += sizeof(struct dirty_seglist_info);
- si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(TOTAL_SEGS(sbi));
- si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
+ si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(MAIN_SEGS(sbi));
+ si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
/* build nm */
si->base_mem += sizeof(struct f2fs_nm_info);
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);
+ si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry);
+ for (i = 0; i <= UPDATE_INO; i++)
+ si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
+
+ si->page_mem = 0;
npages = NODE_MAPPING(sbi)->nrpages;
- si->cache_mem += npages << PAGE_CACHE_SHIFT;
+ si->page_mem += 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 += npages << PAGE_CACHE_SHIFT;
}
static int stat_show(struct seq_file *s, void *v)
@@ -200,6 +222,8 @@
si->valid_count - si->valid_node_count);
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);
@@ -244,14 +268,16 @@
seq_printf(s, "\nExtent Hit Ratio: %d / %d\n",
si->hit_ext, si->total_ext);
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, " - 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 +295,7 @@
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 +308,14 @@
/* 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: %u KB\n",
+ (si->base_mem + si->cache_mem + si->page_mem) >> 10);
+ seq_printf(s, " - static: %u KB\n",
+ si->base_mem >> 10);
+ seq_printf(s, " - cached: %u KB\n",
+ si->cache_mem >> 10);
+ seq_printf(s, " - paged : %u KB\n",
+ si->page_mem >> 10);
}
mutex_unlock(&f2fs_stat_mutex);
return 0;
@@ -321,6 +353,10 @@
si->sbi = sbi;
sbi->stat_info = si;
+ 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);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 8d16e45..1e65ced 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -37,7 +37,7 @@
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,
@@ -59,7 +59,7 @@
[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, struct inode *inode)
{
umode_t mode = inode->i_mode;
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
@@ -90,51 +90,70 @@
}
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 qstr *name, int *max_slots,
+ struct page **res_page)
+{
+ struct f2fs_dentry_block *dentry_blk;
+ struct f2fs_dir_entry *de;
+ struct f2fs_dentry_ptr d;
+
+ dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page);
+
+ make_dentry_ptr(&d, (void *)dentry_blk, 1);
+ de = find_target_dentry(name, 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;
+}
+
+struct f2fs_dir_entry *find_target_dentry(struct qstr *name, 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;
+ f2fs_hash_t namehash = f2fs_dentry_hash(name);
int max_len = 0;
- while (bit_pos < NR_DENTRY_IN_BLOCK) {
- if (!test_bit_le(bit_pos, dentry_bits)) {
+ if (max_slots)
+ *max_slots = 0;
+ while (bit_pos < d->max) {
+ if (!test_bit_le(bit_pos, d->bitmap)) {
if (bit_pos == 0)
max_len = 1;
- else if (!test_bit_le(bit_pos - 1, dentry_bits))
+ else if (!test_bit_le(bit_pos - 1, d->bitmap))
max_len++;
bit_pos++;
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) {
+ de = &d->dentry[bit_pos];
+ if (early_match_name(name->len, namehash, de) &&
+ !memcmp(d->filename[bit_pos], name->name, name->len))
+ goto found;
+
+ if (max_slots && *max_slots >= 0 && 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(!de->name_len);
+ /* 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;
}
@@ -149,9 +168,9 @@
struct page *dentry_page;
struct f2fs_dir_entry *de = NULL;
bool room = false;
- int max_slots = 0;
+ int max_slots;
- f2fs_bug_on(level > MAX_DIR_HASH_DEPTH);
+ f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
nblock = bucket_blocks(level);
@@ -168,8 +187,7 @@
continue;
}
- de = find_in_block(dentry_page, name, &max_slots,
- namehash, res_page);
+ de = find_in_block(dentry_page, name, &max_slots, res_page);
if (de)
break;
@@ -201,6 +219,9 @@
unsigned int max_depth;
unsigned int level;
+ if (f2fs_has_inline_dentry(dir))
+ return find_in_inline_dir(dir, child, res_page);
+
if (npages == 0)
return NULL;
@@ -227,6 +248,9 @@
struct f2fs_dir_entry *de;
struct f2fs_dentry_block *dentry_blk;
+ if (f2fs_has_inline_dentry(dir))
+ return f2fs_parent_inline_dir(dir, p);
+
page = get_lock_data_page(dir, 0);
if (IS_ERR(page))
return NULL;
@@ -247,7 +271,7 @@
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 +281,12 @@
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);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode);
- kunmap(page);
+ f2fs_dentry_kunmap(dir, page);
set_page_dirty(page);
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
mark_inode_dirty(dir);
@@ -284,10 +309,9 @@
int update_dent_inode(struct inode *inode, const struct qstr *name)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *page;
- page = get_node_page(sbi, inode->i_ino);
+ page = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(page))
return PTR_ERR(page);
@@ -297,36 +321,48 @@
return 0;
}
+void do_make_empty_dir(struct inode *inode, struct inode *parent,
+ struct f2fs_dentry_ptr *d)
+{
+ struct f2fs_dir_entry *de;
+
+ de = &d->dentry[0];
+ de->name_len = cpu_to_le16(1);
+ de->hash_code = 0;
+ de->ino = cpu_to_le32(inode->i_ino);
+ memcpy(d->filename[0], ".", 1);
+ set_de_type(de, inode);
+
+ de = &d->dentry[1];
+ de->hash_code = 0;
+ de->name_len = cpu_to_le16(2);
+ de->ino = cpu_to_le32(parent->i_ino);
+ memcpy(d->filename[1], "..", 2);
+ set_de_type(de, inode);
+
+ test_and_set_bit_le(0, (void *)d->bitmap);
+ test_and_set_bit_le(1, (void *)d->bitmap);
+}
+
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(&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);
@@ -334,10 +370,9 @@
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 f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
struct page *page;
int err;
@@ -352,7 +387,7 @@
goto error;
}
- err = f2fs_init_acl(inode, dir, page);
+ err = f2fs_init_acl(inode, dir, page, dpage);
if (err)
goto put_error;
@@ -360,7 +395,7 @@
if (err)
goto put_error;
} else {
- page = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
+ page = get_node_page(F2FS_I_SB(dir), inode->i_ino);
if (IS_ERR(page))
return page;
@@ -381,7 +416,7 @@
* we should remove this inode from orphan list.
*/
if (inode->i_nlink == 0)
- remove_orphan_inode(sbi, inode->i_ino);
+ remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
inc_nlink(inode);
}
return page;
@@ -397,7 +432,7 @@
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)) {
@@ -419,27 +454,23 @@
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;
}
@@ -465,6 +496,14 @@
int err = 0;
int i;
+ if (f2fs_has_inline_dentry(dir)) {
+ err = f2fs_add_inline_entry(dir, name, inode);
+ if (!err || err != -EAGAIN)
+ return err;
+ else
+ err = 0;
+ }
+
dentry_hash = f2fs_dentry_hash(name);
level = 0;
current_depth = F2FS_I(dir)->i_current_depth;
@@ -493,7 +532,8 @@
return PTR_ERR(dentry_page);
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;
@@ -508,7 +548,7 @@
f2fs_wait_on_page_writeback(dentry_page, DATA);
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, name);
+ page = init_inode_metadata(inode, dir, name, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -547,7 +587,7 @@
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;
@@ -562,20 +602,50 @@
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 address_space *mapping = page->mapping;
- struct inode *dir = mapping->host;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
int i;
+ 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);
@@ -593,35 +663,14 @@
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
- if (inode) {
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-
- 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 (inode)
+ f2fs_drop_nlink(dir, inode, NULL);
if (bit_pos == NR_DENTRY_IN_BLOCK) {
truncate_hole(dir, page->index, page->index + 1);
clear_page_dirty_for_io(page);
ClearPageUptodate(page);
- inode_dec_dirty_dents(dir);
+ inode_dec_dirty_pages(dir);
}
f2fs_put_page(page, 1);
}
@@ -631,9 +680,12 @@
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);
if (IS_ERR(dentry_page)) {
@@ -643,7 +695,6 @@
return false;
}
-
dentry_blk = kmap_atomic(dentry_page);
if (bidx == 0)
bit_pos = 2;
@@ -662,23 +713,54 @@
return true;
}
+bool f2fs_fill_dentries(struct file *file, void *dirent, filldir_t filldir,
+ struct f2fs_dentry_ptr *d, unsigned int n, unsigned int bit_pos)
+{
+ unsigned int start_bit_pos = bit_pos;
+ unsigned char d_type;
+ struct f2fs_dir_entry *de = NULL;
+ unsigned char *types = f2fs_filetype_table;
+ int over;
+
+ while (bit_pos < d->max) {
+ d_type = DT_UNKNOWN;
+ bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos);
+ if (bit_pos >= d->max)
+ break;
+
+ de = &d->dentry[bit_pos];
+ if (types && de->file_type < F2FS_FT_MAX)
+ d_type = types[de->file_type];
+
+ over = filldir(dirent, d->filename[bit_pos],
+ le16_to_cpu(de->name_len),
+ (n * d->max) + bit_pos,
+ le32_to_cpu(de->ino), d_type);
+ if (over) {
+ file->f_pos += bit_pos - start_bit_pos;
+ return true;
+ }
+
+ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+ }
+ return false;
+}
+
static int f2fs_readdir(struct file *file, void *dirent, filldir_t filldir)
{
unsigned long pos = file->f_pos;
- unsigned char *types = NULL;
- unsigned int bit_pos = 0, start_bit_pos = 0;
- int over = 0;
+ unsigned int bit_pos = 0;
struct inode *inode = file_inode(file);
unsigned long npages = dir_blocks(inode);
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;
+ struct f2fs_dentry_ptr d;
unsigned int n = 0;
- unsigned char d_type = DT_UNKNOWN;
- int slots;
- types = f2fs_filetype_table;
+ if (f2fs_has_inline_dentry(inode))
+ return f2fs_read_inline_dir(file, dirent, filldir);
+
bit_pos = (pos % NR_DENTRY_IN_BLOCK);
n = (pos / NR_DENTRY_IN_BLOCK);
@@ -692,32 +774,13 @@
if (IS_ERR(dentry_page))
continue;
- start_bit_pos = bit_pos;
dentry_blk = kmap(dentry_page);
- while (bit_pos < NR_DENTRY_IN_BLOCK) {
- d_type = DT_UNKNOWN;
- 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 (types && de->file_type < F2FS_FT_MAX)
- d_type = types[de->file_type];
+ make_dentry_ptr(&d, (void *)dentry_blk, 1);
- over = filldir(dirent,
- dentry_blk->filename[bit_pos],
- le16_to_cpu(de->name_len),
- (n * NR_DENTRY_IN_BLOCK) + bit_pos,
- le32_to_cpu(de->ino), d_type);
- if (over) {
- file->f_pos += bit_pos - start_bit_pos;
- goto stop;
- }
- slots = GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
- bit_pos += slots;
- }
+ if (f2fs_fill_dentries(file, dirent, filldir, &d, n, bit_pos))
+ goto stop;
+
bit_pos = 0;
file->f_pos = (n + 1) * NR_DENTRY_IN_BLOCK;
kunmap(dentry_page);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 90c7a39..686aad1 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -21,10 +21,16 @@
#include <linux/sched.h>
#ifdef CONFIG_F2FS_CHECK_FS
-#define f2fs_bug_on(condition) BUG_ON(condition)
+#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
#define f2fs_down_write(x, y) down_write(x)
#else
-#define f2fs_bug_on(condition) WARN_ON(condition)
+#define f2fs_bug_on(sbi, condition) \
+ do { \
+ if (unlikely(condition)) { \
+ WARN_ON(1); \
+ set_sbi_flag(sbi, SBI_NEED_FSCK); \
+ } \
+ } while (0)
#define f2fs_down_write(x, y) down_write(x)
#endif
@@ -41,8 +47,10 @@
#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040
#define F2FS_MOUNT_INLINE_XATTR 0x00000080
#define F2FS_MOUNT_INLINE_DATA 0x00000100
-#define F2FS_MOUNT_FLUSH_MERGE 0x00000200
-#define F2FS_MOUNT_NOBARRIER 0x00000400
+#define F2FS_MOUNT_INLINE_DENTRY 0x00000200
+#define F2FS_MOUNT_FLUSH_MERGE 0x00000400
+#define F2FS_MOUNT_NOBARRIER 0x00000800
+#define F2FS_MOUNT_FASTBOOT 0x00001000
#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -91,6 +99,25 @@
SIT_BITMAP
};
+enum {
+ CP_UMOUNT,
+ CP_FASTBOOT,
+ CP_SYNC,
+ CP_DISCARD,
+};
+
+#define DEF_BATCHED_TRIM_SECTIONS 32
+#define BATCHED_TRIM_SEGMENTS(sbi) \
+ (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
+
+struct cp_control {
+ int reason;
+ __u64 trim_start;
+ __u64 trim_end;
+ __u64 trim_minlen;
+ __u64 trimmed;
+};
+
/*
* For CP/NAT/SIT/SSA readahead
*/
@@ -98,7 +125,8 @@
META_CP,
META_NAT,
META_SIT,
- META_SSA
+ META_SSA,
+ META_POR,
};
/* for the list of ino */
@@ -114,8 +142,14 @@
nid_t ino; /* inode number */
};
-/* for the list of directory inodes */
-struct dir_inode_entry {
+/*
+ * for the list of directory inodes or gc inodes.
+ * NOTE: there are two slab users for this structure, if we add/modify/delete
+ * fields in structure for one of slab users, it may affect fields or size of
+ * other one, in this condition, it's better to split both of slab and related
+ * data structure.
+ */
+struct inode_entry {
struct list_head list; /* list head */
struct inode *inode; /* vfs inode pointer */
};
@@ -131,7 +165,9 @@
struct fsync_inode_entry {
struct list_head list; /* list head */
struct inode *inode; /* vfs inode pointer */
- block_t blkaddr; /* block address locating the last inode */
+ block_t blkaddr; /* block address locating the last fsync */
+ block_t last_dentry; /* block address locating the last dentry */
+ block_t last_inode; /* block address locating the last inode */
};
#define nats_in_cursum(sum) (le16_to_cpu(sum->n_nats))
@@ -142,6 +178,9 @@
#define sit_in_journal(sum, i) (sum->sit_j.entries[i].se)
#define segno_in_journal(sum, i) (sum->sit_j.entries[i].segno)
+#define MAX_NAT_JENTRIES(sum) (NAT_JOURNAL_ENTRIES - nats_in_cursum(sum))
+#define MAX_SIT_JENTRIES(sum) (SIT_JOURNAL_ENTRIES - sits_in_cursum(sum))
+
static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
{
int before = nats_in_cursum(rs);
@@ -156,11 +195,27 @@
return before;
}
+static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
+ int type)
+{
+ if (type == NAT_JOURNAL)
+ return size <= MAX_NAT_JENTRIES(sum);
+ return size <= MAX_SIT_JENTRIES(sum);
+}
+
/*
* ioctl commands
*/
-#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
+#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+#define F2FS_IOC_GETVERSION FS_IOC_GETVERSION
+
+#define F2FS_IOCTL_MAGIC 0xf5
+#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
+#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
+#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3)
+#define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4)
+#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5)
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
@@ -173,6 +228,32 @@
/*
* For INODE and NODE manager
*/
+/* for directory operations */
+struct f2fs_dentry_ptr {
+ const void *bitmap;
+ struct f2fs_dir_entry *dentry;
+ __u8 (*filename)[F2FS_SLOT_LEN];
+ int max;
+};
+
+static inline void make_dentry_ptr(struct f2fs_dentry_ptr *d,
+ void *src, int type)
+{
+ if (type == 1) {
+ struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src;
+ d->max = NR_DENTRY_IN_BLOCK;
+ d->bitmap = &t->dentry_bitmap;
+ d->dentry = t->dentry;
+ d->filename = t->filename;
+ } else {
+ struct f2fs_inline_dentry *t = (struct f2fs_inline_dentry *)src;
+ d->max = NR_INLINE_DENTRY;
+ d->bitmap = &t->dentry_bitmap;
+ d->dentry = t->dentry;
+ d->filename = t->filename;
+ }
+}
+
/*
* XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1
* as its node offset to distinguish from index node blocks.
@@ -223,13 +304,17 @@
/* Use below internally in f2fs*/
unsigned long flags; /* use to pass per-file flags */
struct rw_semaphore i_sem; /* protect fi info */
- atomic_t dirty_dents; /* # of dirty dentry pages */
+ atomic_t dirty_pages; /* # of dirty pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
nid_t i_xattr_nid; /* node id that contains xattrs */
unsigned long long xattr_ver; /* cp version of xattr modification */
struct extent_info ext; /* in-memory extent cache entry */
- struct dir_inode_entry *dirty_dir; /* the pointer of dirty dir */
+ struct inode_entry *dirty_dir; /* the pointer of dirty dir */
+
+ struct radix_tree_root inmem_root; /* radix tree for inmem pages */
+ struct list_head inmem_pages; /* inmemory pages managed by f2fs */
+ struct mutex inmem_lock; /* lock for inmemory pages */
};
static inline void get_extent_info(struct extent_info *ext,
@@ -261,11 +346,10 @@
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
- rwlock_t nat_tree_lock; /* protect nat_tree_lock */
- unsigned int nat_cnt; /* the # of cached nat entries */
+ struct radix_tree_root nat_set_root;/* root of the nat set cache */
+ struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
- struct list_head dirty_nat_entries; /* cached nat entry list (dirty) */
- struct list_head nat_entry_set; /* nat entry set list */
+ unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
/* free node ids management */
@@ -329,22 +413,21 @@
CURSEG_HOT_NODE, /* direct node blocks of directory files */
CURSEG_WARM_NODE, /* direct node blocks of normal files */
CURSEG_COLD_NODE, /* indirect node blocks */
- NO_CHECK_TYPE
+ NO_CHECK_TYPE,
+ CURSEG_DIRECT_IO, /* to use for the direct IO path */
};
struct flush_cmd {
- struct flush_cmd *next;
struct completion wait;
+ struct llist_node llnode;
int ret;
};
struct flush_cmd_control {
struct task_struct *f2fs_issue_flush; /* flush thread */
wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */
- struct flush_cmd *issue_list; /* list for command issue */
- struct flush_cmd *dispatch_list; /* list for command dispatch */
- spinlock_t issue_lock; /* for issue list lock */
- struct flush_cmd *issue_tail; /* list tail of issue list */
+ struct llist_head issue_list; /* list for command issue */
+ struct llist_node *dispatch_list; /* list for command dispatch */
};
struct f2fs_sm_info {
@@ -370,8 +453,14 @@
int nr_discards; /* # of discards in the list */
int max_discards; /* max. discards to be issued */
+ /* for batched trimming */
+ unsigned int trim_sections; /* # of sections to trim */
+
+ struct list_head sit_entry_set; /* sit entry set list */
+
unsigned int ipu_policy; /* in-place-update policy */
unsigned int min_ipu_util; /* in-place-update threshold */
+ unsigned int min_fsync_blocks; /* threshold for fsync */
/* for flush command control */
struct flush_cmd_control *cmd_control_info;
@@ -392,6 +481,7 @@
F2FS_DIRTY_DENTS,
F2FS_DIRTY_NODES,
F2FS_DIRTY_META,
+ F2FS_INMEM_PAGES,
NR_COUNT_TYPE,
};
@@ -418,6 +508,7 @@
struct f2fs_io_info {
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */
+ block_t blk_addr; /* block address to be written */
};
#define is_read_io(rw) (((rw) & 1) == READ)
@@ -429,12 +520,28 @@
struct rw_semaphore io_rwsem; /* blocking op for bio */
};
+/* for inner inode cache management */
+struct inode_management {
+ struct radix_tree_root ino_root; /* ino entry array */
+ spinlock_t ino_lock; /* for ino entry lock */
+ struct list_head ino_list; /* inode list head */
+ unsigned long ino_num; /* number of entries */
+};
+
+/* For s_flag in struct f2fs_sb_info */
+enum {
+ SBI_IS_DIRTY, /* dirty flag for checkpoint */
+ SBI_IS_CLOSE, /* specify unmounting */
+ SBI_NEED_FSCK, /* need fsck.f2fs to fix */
+ SBI_POR_DOING, /* recovery is doing or not */
+};
+
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
struct buffer_head *raw_super_buf; /* buffer head of raw sb */
struct f2fs_super_block *raw_super; /* raw super block pointer */
- int s_dirty; /* dirty flag for checkpoint */
+ int s_flag; /* flags for sbi */
/* for node-related operations */
struct f2fs_nm_info *nm_info; /* node manager */
@@ -446,7 +553,6 @@
/* for bio operations */
struct f2fs_bio_info read_io; /* for read bios */
struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */
- struct completion *wait_io; /* for completion bios */
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
@@ -455,16 +561,11 @@
struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
struct mutex writepages; /* mutex for writepages() */
- bool por_doing; /* recovery is doing or not */
wait_queue_head_t cp_wait;
- /* for inode management */
- struct radix_tree_root ino_root[MAX_INO_ENTRY]; /* ino entry array */
- spinlock_t ino_lock[MAX_INO_ENTRY]; /* for ino entry lock */
- struct list_head ino_list[MAX_INO_ENTRY]; /* inode list head */
+ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
/* for orphan inode, use 0'th array */
- unsigned int n_orphans; /* # of orphan inodes */
unsigned int max_orphans; /* max orphan inodes */
/* for directory inode management */
@@ -514,8 +615,10 @@
struct f2fs_stat_info *stat_info; /* FS status information */
unsigned int segment_count[2]; /* # of allocated segments */
unsigned int block_count[2]; /* # of allocated blocks */
+ atomic_t inplace_count; /* # of inplace update */
int total_hit_ext, read_hit_ext; /* extent cache hit ratio */
- int inline_inode; /* # of inline_data inodes */
+ atomic_t inline_inode; /* # of inline_data inodes */
+ atomic_t inline_dir; /* # of inline_dentry inodes */
int bg_gc; /* background gc calls */
unsigned int n_dirty_dirs; /* # of dir inodes */
#endif
@@ -540,6 +643,21 @@
return sb->s_fs_info;
}
+static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode)
+{
+ return F2FS_SB(inode->i_sb);
+}
+
+static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping)
+{
+ return F2FS_I_SB(mapping->host);
+}
+
+static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page)
+{
+ return F2FS_M_SB(page->mapping);
+}
+
static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
{
return (struct f2fs_super_block *)(sbi->raw_super);
@@ -595,14 +713,19 @@
return sbi->node_inode->i_mapping;
}
-static inline void F2FS_SET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
{
- sbi->s_dirty = 1;
+ return sbi->s_flag & (0x01 << type);
}
-static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
{
- sbi->s_dirty = 0;
+ sbi->s_flag |= (0x01 << type);
+}
+
+static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
+{
+ sbi->s_flag &= ~(0x01 << type);
}
static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
@@ -650,6 +773,28 @@
up_write(&sbi->cp_rwsem);
}
+static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
+{
+ int reason = CP_SYNC;
+
+ if (test_opt(sbi, FASTBOOT))
+ reason = CP_FASTBOOT;
+ if (is_sbi_flag_set(sbi, SBI_IS_CLOSE))
+ reason = CP_UMOUNT;
+ return reason;
+}
+
+static inline bool __remain_node_summaries(int reason)
+{
+ return (reason == CP_UMOUNT || reason == CP_FASTBOOT);
+}
+
+static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
+{
+ return (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) ||
+ is_set_ckpt_flags(F2FS_CKPT(sbi), CP_FASTBOOT_FLAG));
+}
+
/*
* Check whether the given nid is within node id range.
*/
@@ -704,8 +849,8 @@
blkcnt_t count)
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi->total_valid_block_count < (block_t) count);
- f2fs_bug_on(inode->i_blocks < count);
+ f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
+ f2fs_bug_on(sbi, inode->i_blocks < count);
inode->i_blocks -= count;
sbi->total_valid_block_count -= (block_t)count;
spin_unlock(&sbi->stat_lock);
@@ -714,13 +859,14 @@
static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
atomic_inc(&sbi->nr_pages[count_type]);
- F2FS_SET_SB_DIRT(sbi);
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
}
-static inline void inode_inc_dirty_dents(struct inode *inode)
+static inline void inode_inc_dirty_pages(struct inode *inode)
{
- inc_page_count(F2FS_SB(inode->i_sb), F2FS_DIRTY_DENTS);
- atomic_inc(&F2FS_I(inode)->dirty_dents);
+ atomic_inc(&F2FS_I(inode)->dirty_pages);
+ if (S_ISDIR(inode->i_mode))
+ inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
}
static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -728,13 +874,15 @@
atomic_dec(&sbi->nr_pages[count_type]);
}
-static inline void inode_dec_dirty_dents(struct inode *inode)
+static inline void inode_dec_dirty_pages(struct inode *inode)
{
- if (!S_ISDIR(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
return;
- dec_page_count(F2FS_SB(inode->i_sb), F2FS_DIRTY_DENTS);
- atomic_dec(&F2FS_I(inode)->dirty_dents);
+ atomic_dec(&F2FS_I(inode)->dirty_pages);
+
+ if (S_ISDIR(inode->i_mode))
+ dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
}
static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
@@ -742,9 +890,9 @@
return atomic_read(&sbi->nr_pages[count_type]);
}
-static inline int get_dirty_dents(struct inode *inode)
+static inline int get_dirty_pages(struct inode *inode)
{
- return atomic_read(&F2FS_I(inode)->dirty_dents);
+ return atomic_read(&F2FS_I(inode)->dirty_pages);
}
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
@@ -849,9 +997,9 @@
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(!sbi->total_valid_block_count);
- f2fs_bug_on(!sbi->total_valid_node_count);
- f2fs_bug_on(!inode->i_blocks);
+ f2fs_bug_on(sbi, !sbi->total_valid_block_count);
+ f2fs_bug_on(sbi, !sbi->total_valid_node_count);
+ f2fs_bug_on(sbi, !inode->i_blocks);
inode->i_blocks--;
sbi->total_valid_node_count--;
@@ -868,7 +1016,7 @@
static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi->total_valid_inode_count == sbi->total_node_count);
+ f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count);
sbi->total_valid_inode_count++;
spin_unlock(&sbi->stat_lock);
}
@@ -876,7 +1024,7 @@
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(!sbi->total_valid_inode_count);
+ f2fs_bug_on(sbi, !sbi->total_valid_inode_count);
sbi->total_valid_inode_count--;
spin_unlock(&sbi->stat_lock);
}
@@ -892,7 +1040,7 @@
return;
if (unlock) {
- f2fs_bug_on(!PageLocked(page));
+ f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
unlock_page(page);
}
page_cache_release(page);
@@ -928,6 +1076,13 @@
return entry;
}
+static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
+ unsigned long index, void *item)
+{
+ while (radix_tree_insert(root, index, item))
+ cond_resched();
+}
+
#define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino)
static inline bool IS_INODE(struct page *page)
@@ -960,7 +1115,7 @@
return mask & *addr;
}
-static inline int f2fs_set_bit(unsigned int nr, char *addr)
+static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
{
int mask;
int ret;
@@ -972,7 +1127,7 @@
return ret;
}
-static inline int f2fs_clear_bit(unsigned int nr, char *addr)
+static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr)
{
int mask;
int ret;
@@ -984,6 +1139,15 @@
return ret;
}
+static inline void f2fs_change_bit(unsigned int nr, char *addr)
+{
+ int mask;
+
+ addr += (nr >> 3);
+ mask = 1 << (7 - (nr & 0x07));
+ *addr ^= mask;
+}
+
/* used for f2fs_inode_info->flags */
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
@@ -997,9 +1161,14 @@
FI_NO_EXTENT, /* not to use the extent cache */
FI_INLINE_XATTR, /* used for inline xattr */
FI_INLINE_DATA, /* used for inline data*/
+ FI_INLINE_DENTRY, /* used for inline dentry */
FI_APPEND_WRITE, /* inode has appended data */
FI_UPDATE_WRITE, /* inode has in-place-update data */
- FI_NEED_IPU, /* used fo ipu for fdatasync */
+ FI_NEED_IPU, /* used for ipu per file */
+ FI_ATOMIC_FILE, /* indicate atomic file */
+ FI_VOLATILE_FILE, /* indicate volatile file */
+ FI_DROP_CACHE, /* drop dirty page cache */
+ FI_DATA_EXIST, /* indicate data exists */
};
static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
@@ -1025,15 +1194,6 @@
set_inode_flag(fi, FI_ACL_MODE);
}
-static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag)
-{
- if (is_inode_flag_set(fi, FI_ACL_MODE)) {
- clear_inode_flag(fi, FI_ACL_MODE);
- return 1;
- }
- return 0;
-}
-
static inline void get_inline_info(struct f2fs_inode_info *fi,
struct f2fs_inode *ri)
{
@@ -1041,6 +1201,10 @@
set_inode_flag(fi, FI_INLINE_XATTR);
if (ri->i_inline & F2FS_INLINE_DATA)
set_inode_flag(fi, FI_INLINE_DATA);
+ if (ri->i_inline & F2FS_INLINE_DENTRY)
+ set_inode_flag(fi, FI_INLINE_DENTRY);
+ if (ri->i_inline & F2FS_DATA_EXIST)
+ set_inode_flag(fi, FI_DATA_EXIST);
}
static inline void set_raw_inline(struct f2fs_inode_info *fi,
@@ -1052,6 +1216,10 @@
ri->i_inline |= F2FS_INLINE_XATTR;
if (is_inode_flag_set(fi, FI_INLINE_DATA))
ri->i_inline |= F2FS_INLINE_DATA;
+ if (is_inode_flag_set(fi, FI_INLINE_DENTRY))
+ ri->i_inline |= F2FS_INLINE_DENTRY;
+ if (is_inode_flag_set(fi, FI_DATA_EXIST))
+ ri->i_inline |= F2FS_DATA_EXIST;
}
static inline int f2fs_has_inline_xattr(struct inode *inode)
@@ -1086,12 +1254,55 @@
return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA);
}
+static inline void f2fs_clear_inline_inode(struct inode *inode)
+{
+ clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+ clear_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+}
+
+static inline int f2fs_exist_data(struct inode *inode)
+{
+ return is_inode_flag_set(F2FS_I(inode), FI_DATA_EXIST);
+}
+
+static inline bool f2fs_is_atomic_file(struct inode *inode)
+{
+ return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE);
+}
+
+static inline bool f2fs_is_volatile_file(struct inode *inode)
+{
+ return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
+}
+
+static inline bool f2fs_is_drop_cache(struct inode *inode)
+{
+ return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE);
+}
+
static inline void *inline_data_addr(struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
return (void *)&(ri->i_addr[1]);
}
+static inline int f2fs_has_inline_dentry(struct inode *inode)
+{
+ return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DENTRY);
+}
+
+static inline void *inline_dentry_addr(struct page *page)
+{
+ struct f2fs_inode *ri = F2FS_INODE(page);
+ return (void *)&(ri->i_addr[1]);
+}
+
+static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page)
+{
+ if (!f2fs_has_inline_dentry(dir))
+ kunmap(page);
+}
+
static inline int f2fs_readonly(struct super_block *sb)
{
return sb->s_flags & MS_RDONLY;
@@ -1144,9 +1355,10 @@
struct inode *f2fs_iget(struct super_block *, unsigned long);
int try_to_free_nats(struct f2fs_sb_info *, int);
void update_inode(struct inode *, struct page *);
-int update_inode_page(struct inode *);
+void update_inode_page(struct inode *);
int f2fs_write_inode(struct inode *, struct writeback_control *);
void f2fs_evict_inode(struct inode *);
+void handle_failed_inode(struct inode *);
/*
* namei.c
@@ -1156,6 +1368,19 @@
/*
* dir.c
*/
+extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
+void set_de_type(struct f2fs_dir_entry *, struct inode *);
+struct f2fs_dir_entry *find_target_dentry(struct qstr *, int *,
+ struct f2fs_dentry_ptr *);
+bool f2fs_fill_dentries(struct file *, void *, filldir_t,
+ struct f2fs_dentry_ptr *, unsigned int, unsigned int);
+void do_make_empty_dir(struct inode *, struct inode *,
+ struct f2fs_dentry_ptr *);
+struct page *init_inode_metadata(struct inode *, struct inode *,
+ const struct qstr *, struct page *);
+void update_parent_metadata(struct inode *, struct inode *, unsigned int);
+int room_for_filename(const void *, int, int);
+void f2fs_drop_nlink(struct inode *, struct inode *, struct page *);
struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *,
struct page **);
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
@@ -1164,7 +1389,8 @@
struct page *, struct inode *);
int update_dent_inode(struct inode *, const struct qstr *);
int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *);
-void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *);
+void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
+ struct inode *);
int f2fs_do_tmpfile(struct inode *, struct inode *);
int f2fs_make_empty(struct inode *, struct inode *);
bool f2fs_empty_dir(struct inode *);
@@ -1194,9 +1420,9 @@
struct node_info;
bool available_free_memory(struct f2fs_sb_info *, int);
-int is_checkpointed_node(struct f2fs_sb_info *, nid_t);
-bool fsync_mark_done(struct f2fs_sb_info *, nid_t);
-void fsync_mark_clear(struct f2fs_sb_info *, nid_t);
+bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
+bool has_fsynced_inode(struct f2fs_sb_info *, nid_t);
+bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
int truncate_inode_blocks(struct inode *, pgoff_t);
@@ -1227,6 +1453,8 @@
/*
* segment.c
*/
+void register_inmem_page(struct inode *, struct page *);
+void commit_inmem_pages(struct inode *, bool);
void f2fs_balance_fs(struct f2fs_sb_info *);
void f2fs_balance_fs_bg(struct f2fs_sb_info *);
int f2fs_issue_flush(struct f2fs_sb_info *);
@@ -1235,16 +1463,18 @@
void invalidate_blocks(struct f2fs_sb_info *, block_t);
void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
void clear_prefree_segments(struct f2fs_sb_info *);
-void discard_next_dnode(struct f2fs_sb_info *);
-int npages_for_summary_flush(struct f2fs_sb_info *);
+void release_discard_addrs(struct f2fs_sb_info *);
+void discard_next_dnode(struct f2fs_sb_info *, block_t);
+int npages_for_summary_flush(struct f2fs_sb_info *, bool);
void allocate_new_segments(struct f2fs_sb_info *);
+int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
void write_meta_page(struct f2fs_sb_info *, struct page *);
void write_node_page(struct f2fs_sb_info *, struct page *,
- struct f2fs_io_info *, unsigned int, block_t, block_t *);
-void write_data_page(struct page *, struct dnode_of_data *, block_t *,
- struct f2fs_io_info *);
-void rewrite_data_page(struct page *, block_t, struct f2fs_io_info *);
+ unsigned int, struct f2fs_io_info *);
+void write_data_page(struct page *, struct dnode_of_data *,
+ struct f2fs_io_info *);
+void rewrite_data_page(struct page *, struct f2fs_io_info *);
void recover_data_page(struct f2fs_sb_info *, struct page *,
struct f2fs_summary *, block_t, block_t);
void allocate_data_block(struct f2fs_sb_info *, struct page *,
@@ -1254,7 +1484,7 @@
void write_node_summaries(struct f2fs_sb_info *, block_t);
int lookup_journal_in_cursum(struct f2fs_summary_block *,
int, unsigned int, int);
-void flush_sit_entries(struct f2fs_sb_info *);
+void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
int build_segment_manager(struct f2fs_sb_info *);
void destroy_segment_manager(struct f2fs_sb_info *);
int __init create_segment_manager_caches(void);
@@ -1265,7 +1495,8 @@
*/
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
-int ra_meta_pages(struct f2fs_sb_info *, int, int, int);
+int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int);
+void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
@@ -1277,11 +1508,11 @@
void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
void recover_orphan_inodes(struct f2fs_sb_info *);
int get_valid_checkpoint(struct f2fs_sb_info *);
-void set_dirty_dir_page(struct inode *, struct page *);
+void update_dirty_page(struct inode *, struct page *);
void add_dirty_dir_inode(struct inode *);
void remove_dirty_dir_inode(struct inode *);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
-void write_checkpoint(struct f2fs_sb_info *, bool);
+void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
void init_ino_entry_info(struct f2fs_sb_info *);
int __init create_checkpoint_caches(void);
void destroy_checkpoint_caches(void);
@@ -1290,17 +1521,20 @@
* data.c
*/
void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, block_t, int);
-void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, block_t,
+int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *,
+ struct f2fs_io_info *);
+void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *,
struct f2fs_io_info *);
int reserve_new_block(struct dnode_of_data *);
int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-void update_extent_cache(block_t, struct dnode_of_data *);
+void update_extent_cache(struct dnode_of_data *);
struct page *find_data_page(struct inode *, pgoff_t, bool);
struct page *get_lock_data_page(struct inode *, pgoff_t);
struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
int do_write_data_page(struct page *, struct f2fs_io_info *);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void f2fs_invalidate_page(struct page *, unsigned long);
+int f2fs_release_page(struct page *, gfp_t);
/*
* gc.c
@@ -1310,8 +1544,6 @@
block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
int f2fs_gc(struct f2fs_sb_info *);
void build_gc_manager(struct f2fs_sb_info *);
-int __init create_gc_caches(void);
-void destroy_gc_caches(void);
/*
* recovery.c
@@ -1330,9 +1562,9 @@
int main_area_segs, main_area_sections, main_area_zones;
int hit_ext, total_ext;
int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
- int nats, sits, fnids;
+ int nats, dirty_nats, sits, dirty_sits, fnids;
int total_count, utilization;
- int bg_gc, inline_inode;
+ int bg_gc, inline_inode, inline_dir, inmem_pages, wb_pages;
unsigned int valid_count, valid_node_count, valid_inode_count;
unsigned int bimodal, avg_vblocks;
int util_free, util_valid, util_invalid;
@@ -1347,7 +1579,8 @@
unsigned int segment_count[2];
unsigned int block_count[2];
- unsigned base_mem, cache_mem;
+ unsigned int inplace_count;
+ unsigned base_mem, cache_mem, page_mem;
};
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
@@ -1365,19 +1598,29 @@
#define stat_inc_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
- ((F2FS_SB(inode->i_sb))->inline_inode++); \
+ (atomic_inc(&F2FS_I_SB(inode)->inline_inode)); \
} while (0)
#define stat_dec_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
- ((F2FS_SB(inode->i_sb))->inline_inode--); \
+ (atomic_dec(&F2FS_I_SB(inode)->inline_inode)); \
} while (0)
-
+#define stat_inc_inline_dir(inode) \
+ do { \
+ if (f2fs_has_inline_dentry(inode)) \
+ (atomic_inc(&F2FS_I_SB(inode)->inline_dir)); \
+ } while (0)
+#define stat_dec_inline_dir(inode) \
+ do { \
+ if (f2fs_has_inline_dentry(inode)) \
+ (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \
+ } while (0)
#define stat_inc_seg_type(sbi, curseg) \
((sbi)->segment_count[(curseg)->alloc_type]++)
#define stat_inc_block_count(sbi, curseg) \
((sbi)->block_count[(curseg)->alloc_type]++)
-
+#define stat_inc_inplace_blocks(sbi) \
+ (atomic_inc(&(sbi)->inplace_count))
#define stat_inc_seg_count(sbi, type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
@@ -1419,8 +1662,11 @@
#define stat_inc_read_hit(sb)
#define stat_inc_inline_inode(inode)
#define stat_dec_inline_inode(inode)
+#define stat_inc_inline_dir(inode)
+#define stat_dec_inline_dir(inode)
#define stat_inc_seg_type(sbi, curseg)
#define stat_inc_block_count(sbi, curseg)
+#define stat_inc_inplace_blocks(sbi)
#define stat_inc_seg_count(si, type)
#define stat_inc_tot_blk_count(si, blks)
#define stat_inc_data_blk_count(si, blks)
@@ -1441,14 +1687,25 @@
extern const struct inode_operations f2fs_dir_inode_operations;
extern const struct inode_operations f2fs_symlink_inode_operations;
extern const struct inode_operations f2fs_special_inode_operations;
+extern struct kmem_cache *inode_entry_slab;
/*
* inline.c
*/
bool f2fs_may_inline(struct inode *);
+void read_inline_data(struct page *, struct page *);
int f2fs_read_inline_data(struct inode *, struct page *);
-int f2fs_convert_inline_data(struct inode *, pgoff_t, struct page *);
-int f2fs_write_inline_data(struct inode *, struct page *, unsigned int);
-void truncate_inline_data(struct inode *, u64);
+int f2fs_convert_inline_page(struct dnode_of_data *, struct page *);
+int f2fs_convert_inline_inode(struct inode *);
+int f2fs_write_inline_data(struct inode *, struct page *);
bool recover_inline_data(struct inode *, struct page *);
+struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *,
+ struct page **);
+struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **);
+int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
+int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *);
+void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *,
+ struct inode *, struct inode *);
+bool f2fs_empty_inline_dir(struct inode *);
+int f2fs_read_inline_dir(struct file *, void *, filldir_t);
#endif
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index e3f2ebb..590651c 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -26,6 +26,7 @@
#include "segment.h"
#include "xattr.h"
#include "acl.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
@@ -33,7 +34,7 @@
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int err;
@@ -41,18 +42,18 @@
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
- /* force to convert with normal data indices */
- err = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, page);
- if (err)
- goto out;
+ f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
/* block allocation */
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_reserve_block(&dn, page->index);
- f2fs_unlock_op(sbi);
- if (err)
+ if (err) {
+ f2fs_unlock_op(sbi);
goto out;
+ }
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
file_update_time(vma->vm_file);
lock_page(page);
@@ -114,7 +115,7 @@
static inline bool need_do_checkpoint(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
bool need_cp = false;
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
@@ -127,15 +128,51 @@
need_cp = true;
else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
need_cp = true;
+ else if (test_opt(sbi, FASTBOOT))
+ need_cp = true;
+ else if (sbi->active_logs == 2)
+ need_cp = true;
return need_cp;
}
+static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
+{
+ struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
+ bool ret = false;
+ /* But we need to avoid that there are some inode updates */
+ if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino))
+ ret = true;
+ f2fs_put_page(i, 0);
+ return ret;
+}
+
+static void try_to_fix_pino(struct inode *inode)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ nid_t pino;
+
+ down_write(&fi->i_sem);
+ fi->xattr_ver = 0;
+ if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
+ get_parent_ino(inode, &pino)) {
+ fi->i_pino = pino;
+ file_got_pino(inode);
+ up_write(&fi->i_sem);
+
+ mark_inode_dirty_sync(inode);
+ f2fs_write_inode(inode, NULL);
+ } else {
+ up_write(&fi->i_sem);
+ }
+}
+
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct f2fs_inode_info *fi = F2FS_I(inode);
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ nid_t ino = inode->i_ino;
int ret = 0;
bool need_cp = false;
struct writeback_control wbc = {
@@ -150,28 +187,38 @@
trace_f2fs_sync_file_enter(inode);
/* if fdatasync is triggered, let's do in-place-update */
- if (datasync)
+ if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
set_inode_flag(fi, FI_NEED_IPU);
-
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- if (datasync)
- clear_inode_flag(fi, FI_NEED_IPU);
+ clear_inode_flag(fi, FI_NEED_IPU);
+
if (ret) {
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
return ret;
}
+ /* if the inode is dirty, let's recover all the time */
+ if (!datasync && is_inode_flag_set(fi, FI_DIRTY_INODE)) {
+ update_inode_page(inode);
+ goto go_write;
+ }
+
/*
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
- !exist_written_data(sbi, inode->i_ino, APPEND_INO)) {
+ !exist_written_data(sbi, ino, APPEND_INO)) {
+
+ /* it may call write_inode just prior to fsync */
+ if (need_inode_page_update(sbi, ino))
+ goto go_write;
+
if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
- exist_written_data(sbi, inode->i_ino, UPDATE_INO))
+ exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
-
+go_write:
/* guarantee free sections for fsync */
f2fs_balance_fs(sbi);
@@ -184,49 +231,43 @@
up_read(&fi->i_sem);
if (need_cp) {
- nid_t pino;
-
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
- down_write(&fi->i_sem);
- F2FS_I(inode)->xattr_ver = 0;
- if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
- get_parent_ino(inode, &pino)) {
- F2FS_I(inode)->i_pino = pino;
- file_got_pino(inode);
- up_write(&fi->i_sem);
- mark_inode_dirty_sync(inode);
- ret = f2fs_write_inode(inode, NULL);
- if (ret)
- goto out;
- } else {
- up_write(&fi->i_sem);
- }
- } else {
- /* if there is no written node page, write its inode page */
- while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
- if (fsync_mark_done(sbi, inode->i_ino))
- goto out;
- mark_inode_dirty_sync(inode);
- ret = f2fs_write_inode(inode, NULL);
- if (ret)
- goto out;
- }
- ret = wait_on_node_pages_writeback(sbi, inode->i_ino);
- if (ret)
- goto out;
-
- /* once recovery info is written, don't need to tack this */
- remove_dirty_inode(sbi, inode->i_ino, APPEND_INO);
- clear_inode_flag(fi, FI_APPEND_WRITE);
-flush_out:
- remove_dirty_inode(sbi, inode->i_ino, UPDATE_INO);
- clear_inode_flag(fi, FI_UPDATE_WRITE);
- ret = f2fs_issue_flush(F2FS_SB(inode->i_sb));
+ /*
+ * We've secured consistency through sync_fs. Following pino
+ * will be used only for fsynced inodes after checkpoint.
+ */
+ try_to_fix_pino(inode);
+ goto out;
}
+sync_nodes:
+ sync_node_pages(sbi, ino, &wbc);
+
+ /* if cp_error was enabled, we should avoid infinite loop */
+ if (unlikely(f2fs_cp_error(sbi)))
+ goto out;
+
+ if (need_inode_block_update(sbi, ino)) {
+ mark_inode_dirty_sync(inode);
+ f2fs_write_inode(inode, NULL);
+ goto sync_nodes;
+ }
+
+ ret = wait_on_node_pages_writeback(sbi, ino);
+ if (ret)
+ goto out;
+
+ /* once recovery info is written, don't need to tack this */
+ remove_dirty_inode(sbi, ino, APPEND_INO);
+ clear_inode_flag(fi, FI_APPEND_WRITE);
+flush_out:
+ remove_dirty_inode(sbi, ino, UPDATE_INO);
+ clear_inode_flag(fi, FI_UPDATE_WRITE);
+ ret = f2fs_issue_flush(sbi);
out:
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+ f2fs_trace_ios(NULL, NULL, 1);
return ret;
}
@@ -301,7 +342,7 @@
goto fail;
/* handle inline data case */
- if (f2fs_has_inline_data(inode)) {
+ if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
if (whence == SEEK_HOLE)
data_ofs = isize;
goto found;
@@ -332,7 +373,7 @@
/* find data/hole in dnode block */
for (; dn.ofs_in_node < end_offset;
dn.ofs_in_node++, pgofs++,
- data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+ data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
block_t blkaddr;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
@@ -369,6 +410,8 @@
maxbytes);
case SEEK_DATA:
case SEEK_HOLE:
+ if (offset < 0)
+ return -ENXIO;
return f2fs_seek_block(file, offset, whence);
}
@@ -377,6 +420,15 @@
static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
+ struct inode *inode = file_inode(file);
+
+ /* we don't need to use inline_data strictly */
+ if (f2fs_has_inline_data(inode)) {
+ int err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
+
file_accessed(file);
vma->vm_ops = &f2fs_file_vm_ops;
return 0;
@@ -385,7 +437,7 @@
int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
int nr_free = 0, ofs = dn->ofs_in_node;
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
__le32 *addr;
@@ -397,7 +449,8 @@
if (blkaddr == NULL_ADDR)
continue;
- update_extent_cache(NULL_ADDR, dn);
+ dn->data_blkaddr = NULL_ADDR;
+ update_extent_cache(dn);
invalidate_blocks(sbi, blkaddr);
nr_free++;
}
@@ -418,20 +471,17 @@
truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
}
-static void truncate_partial_data_page(struct inode *inode, u64 from)
+static int truncate_partial_data_page(struct inode *inode, u64 from)
{
unsigned offset = from & (PAGE_CACHE_SIZE - 1);
struct page *page;
- if (f2fs_has_inline_data(inode))
- return truncate_inline_data(inode, from);
-
if (!offset)
- return;
+ return 0;
page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false);
if (IS_ERR(page))
- return;
+ return 0;
lock_page(page);
if (unlikely(!PageUptodate(page) ||
@@ -441,45 +491,50 @@
f2fs_wait_on_page_writeback(page, DATA);
zero_user(page, offset, PAGE_CACHE_SIZE - offset);
set_page_dirty(page);
-
out:
f2fs_put_page(page, 1);
+ return 0;
}
int truncate_blocks(struct inode *inode, u64 from, bool lock)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int blocksize = inode->i_sb->s_blocksize;
struct dnode_of_data dn;
pgoff_t free_from;
int count = 0, err = 0;
+ struct page *ipage;
trace_f2fs_truncate_blocks_enter(inode, from);
- if (f2fs_has_inline_data(inode))
- goto done;
-
- free_from = (pgoff_t)
- ((from + blocksize - 1) >> (sbi->log_blocksize));
+ free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
if (lock)
f2fs_lock_op(sbi);
- set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ipage = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto out;
+ }
+
+ if (f2fs_has_inline_data(inode)) {
+ f2fs_put_page(ipage, 1);
+ goto out;
+ }
+
+ set_new_dnode(&dn, inode, ipage, NULL, 0);
err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
if (err) {
if (err == -ENOENT)
goto free_next;
- if (lock)
- f2fs_unlock_op(sbi);
- trace_f2fs_truncate_blocks_exit(inode, err);
- return err;
+ goto out;
}
count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
count -= dn.ofs_in_node;
- f2fs_bug_on(count < 0);
+ f2fs_bug_on(sbi, count < 0);
if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
truncate_data_blocks_range(&dn, count);
@@ -489,11 +544,13 @@
f2fs_put_dnode(&dn);
free_next:
err = truncate_inode_blocks(inode, free_from);
+out:
if (lock)
f2fs_unlock_op(sbi);
-done:
+
/* lastly zero out the first data page */
- truncate_partial_data_page(inode, from);
+ if (!err)
+ err = truncate_partial_data_page(inode, from);
trace_f2fs_truncate_blocks_exit(inode, err);
return err;
@@ -507,6 +564,12 @@
trace_f2fs_truncate(inode);
+ /* we should check inline_data size */
+ if (f2fs_has_inline_data(inode) && !f2fs_may_inline(inode)) {
+ if (f2fs_convert_inline_inode(inode))
+ return;
+ }
+
if (!truncate_blocks(inode, i_size_read(inode), true)) {
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
mark_inode_dirty(inode);
@@ -563,15 +626,18 @@
if (err)
return err;
- if ((attr->ia_valid & ATTR_SIZE) &&
- attr->ia_size != i_size_read(inode)) {
- err = f2fs_convert_inline_data(inode, attr->ia_size, NULL);
- if (err)
- return err;
-
- truncate_setsize(inode, attr->ia_size);
- f2fs_truncate(inode);
- f2fs_balance_fs(F2FS_SB(inode->i_sb));
+ if (attr->ia_valid & ATTR_SIZE) {
+ if (attr->ia_size != i_size_read(inode)) {
+ truncate_setsize(inode, attr->ia_size);
+ f2fs_truncate(inode);
+ f2fs_balance_fs(F2FS_I_SB(inode));
+ } else {
+ /*
+ * giving a chance to truncate blocks past EOF which
+ * are fallocated with FALLOC_FL_KEEP_SIZE.
+ */
+ f2fs_truncate(inode);
+ }
}
__setattr_copy(inode, attr);
@@ -604,7 +670,7 @@
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 f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
if (!len)
@@ -653,10 +719,19 @@
loff_t off_start, off_end;
int ret = 0;
- ret = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL);
- if (ret)
+ if (!S_ISREG(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ /* skip punching hole beyond i_size */
+ if (offset >= inode->i_size)
return ret;
+ if (f2fs_has_inline_data(inode)) {
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+ }
+
pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
@@ -676,7 +751,7 @@
if (pg_start < pg_end) {
struct address_space *mapping = inode->i_mapping;
loff_t blk_start, blk_end;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
f2fs_balance_fs(sbi);
@@ -697,7 +772,7 @@
static int expand_inode_data(struct inode *inode, loff_t offset,
loff_t len, int mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t index, pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_start, off_end;
@@ -709,9 +784,11 @@
if (ret)
return ret;
- ret = f2fs_convert_inline_data(inode, offset + len, NULL);
- if (ret)
- return ret;
+ if (f2fs_has_inline_data(inode)) {
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+ }
pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
@@ -780,6 +857,19 @@
return ret;
}
+static int f2fs_release_file(struct inode *inode, struct file *filp)
+{
+ /* some remained atomic pages should discarded */
+ if (f2fs_is_atomic_file(inode))
+ commit_inmem_pages(inode, true);
+ if (f2fs_is_volatile_file(inode)) {
+ set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+ filemap_fdatawrite(inode->i_mapping);
+ clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+ }
+ return 0;
+}
+
#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
@@ -793,61 +883,256 @@
return flags & F2FS_OTHER_FLMASK;
}
-long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
- unsigned int flags;
+ unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ return put_user(flags, (int __user *)arg);
+}
+
+static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ unsigned int oldflags;
int ret;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ if (!inode_owner_or_capable(inode)) {
+ ret = -EACCES;
+ goto out;
+ }
+
+ if (get_user(flags, (int __user *)arg)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ flags = f2fs_mask_flags(inode->i_mode, flags);
+
+ mutex_lock(&inode->i_mutex);
+
+ oldflags = fi->i_flags;
+
+ if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
+ if (!capable(CAP_LINUX_IMMUTABLE)) {
+ mutex_unlock(&inode->i_mutex);
+ ret = -EPERM;
+ goto out;
+ }
+ }
+
+ flags = flags & FS_FL_USER_MODIFIABLE;
+ flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
+ fi->i_flags = flags;
+ mutex_unlock(&inode->i_mutex);
+
+ f2fs_set_inode_flags(inode);
+ inode->i_ctime = CURRENT_TIME;
+ mark_inode_dirty(inode);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+
+ return put_user(inode->i_generation, (int __user *)arg);
+}
+
+static int f2fs_ioc_start_atomic_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ f2fs_balance_fs(F2FS_I_SB(inode));
+
+ if (f2fs_is_atomic_file(inode))
+ return 0;
+
+ set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+
+ return f2fs_convert_inline_inode(inode);
+}
+
+static int f2fs_ioc_commit_atomic_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+ int ret;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (f2fs_is_volatile_file(inode))
+ return 0;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ if (f2fs_is_atomic_file(inode))
+ commit_inmem_pages(inode, false);
+
+ ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
+ mnt_drop_write_file(filp);
+ clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ return ret;
+}
+
+static int f2fs_ioc_start_volatile_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (f2fs_is_volatile_file(inode))
+ return 0;
+
+ set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+
+ return f2fs_convert_inline_inode(inode);
+}
+
+static int f2fs_ioc_release_volatile_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (!f2fs_is_volatile_file(inode))
+ return 0;
+
+ punch_hole(inode, 0, F2FS_BLKSIZE);
+ return 0;
+}
+
+static int f2fs_ioc_abort_volatile_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+ int ret;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ f2fs_balance_fs(F2FS_I_SB(inode));
+
+ if (f2fs_is_atomic_file(inode)) {
+ commit_inmem_pages(inode, false);
+ clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ }
+
+ if (f2fs_is_volatile_file(inode)) {
+ clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+ filemap_fdatawrite(inode->i_mapping);
+ set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+ }
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct super_block *sb = sbi->sb;
+ __u32 in;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (get_user(in, (__u32 __user *)arg))
+ return -EFAULT;
+
+ switch (in) {
+ case FS_GOING_DOWN_FULLSYNC:
+ sb = freeze_bdev(sb->s_bdev);
+ if (sb && !IS_ERR(sb)) {
+ f2fs_stop_checkpoint(sbi);
+ thaw_bdev(sb->s_bdev, sb);
+ }
+ break;
+ case FS_GOING_DOWN_METASYNC:
+ /* do checkpoint only */
+ f2fs_sync_fs(sb, 1);
+ f2fs_stop_checkpoint(sbi);
+ break;
+ case FS_GOING_DOWN_NOSYNC:
+ f2fs_stop_checkpoint(sbi);
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct super_block *sb = inode->i_sb;
+ struct request_queue *q = bdev_get_queue(sb->s_bdev);
+ struct fstrim_range range;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&range, (struct fstrim_range __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ range.minlen = max((unsigned int)range.minlen,
+ q->limits.discard_granularity);
+ ret = f2fs_trim_fs(F2FS_SB(sb), &range);
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user((struct fstrim_range __user *)arg, &range,
+ sizeof(range)))
+ return -EFAULT;
+ return 0;
+}
+
+long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
switch (cmd) {
case F2FS_IOC_GETFLAGS:
- flags = fi->i_flags & FS_FL_USER_VISIBLE;
- return put_user(flags, (int __user *) arg);
+ return f2fs_ioc_getflags(filp, arg);
case F2FS_IOC_SETFLAGS:
- {
- unsigned int oldflags;
-
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out;
- }
-
- if (get_user(flags, (int __user *) arg)) {
- ret = -EFAULT;
- goto out;
- }
-
- flags = f2fs_mask_flags(inode->i_mode, flags);
-
- mutex_lock(&inode->i_mutex);
-
- oldflags = fi->i_flags;
-
- if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
- if (!capable(CAP_LINUX_IMMUTABLE)) {
- mutex_unlock(&inode->i_mutex);
- ret = -EPERM;
- goto out;
- }
- }
-
- flags = flags & FS_FL_USER_MODIFIABLE;
- flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
- fi->i_flags = flags;
- mutex_unlock(&inode->i_mutex);
-
- f2fs_set_inode_flags(inode);
- inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
-out:
- mnt_drop_write_file(filp);
- return ret;
- }
+ return f2fs_ioc_setflags(filp, arg);
+ case F2FS_IOC_GETVERSION:
+ return f2fs_ioc_getversion(filp, arg);
+ case F2FS_IOC_START_ATOMIC_WRITE:
+ return f2fs_ioc_start_atomic_write(filp);
+ case F2FS_IOC_COMMIT_ATOMIC_WRITE:
+ return f2fs_ioc_commit_atomic_write(filp);
+ case F2FS_IOC_START_VOLATILE_WRITE:
+ return f2fs_ioc_start_volatile_write(filp);
+ case F2FS_IOC_RELEASE_VOLATILE_WRITE:
+ return f2fs_ioc_release_volatile_write(filp);
+ case F2FS_IOC_ABORT_VOLATILE_WRITE:
+ return f2fs_ioc_abort_volatile_write(filp);
+ case FS_IOC_SHUTDOWN:
+ return f2fs_ioc_shutdown(filp, arg);
+ case FITRIM:
+ return f2fs_ioc_fitrim(filp, arg);
default:
return -ENOTTY;
}
@@ -877,6 +1162,7 @@
.aio_read = generic_file_aio_read,
.aio_write = generic_file_aio_write,
.open = generic_file_open,
+ .release = f2fs_release_file,
.mmap = f2fs_file_mmap,
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 81dc017..5d6af02 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -24,8 +24,6 @@
#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 +44,7 @@
break;
if (sbi->sb->s_frozen >= SB_FREEZE_WRITE) {
- wait_ms = increase_sleep_time(gc_th, wait_ms);
+ increase_sleep_time(gc_th, &wait_ms);
continue;
}
@@ -67,15 +65,15 @@
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);
@@ -96,8 +94,6 @@
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;
@@ -193,7 +189,7 @@
* selected by background GC before.
* Those segments guarantee they have small valid blocks.
*/
- for_each_set_bit(secno, dirty_i->victim_secmap, TOTAL_SECS(sbi)) {
+ for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) {
if (sec_usage_check(sbi, secno))
continue;
clear_bit(secno, dirty_i->victim_secmap);
@@ -263,14 +259,14 @@
unsigned int secno, max_cost;
int nsearched = 0;
+ mutex_lock(&dirty_i->seglist_lock);
+
p.alloc_mode = alloc_mode;
select_policy(sbi, gc_type, type, &p);
p.min_segno = NULL_SEGNO;
p.min_cost = max_cost = get_max_cost(sbi, &p);
- mutex_lock(&dirty_i->seglist_lock);
-
if (p.alloc_mode == LFS && gc_type == FG_GC) {
p.min_segno = check_bg_victims(sbi);
if (p.min_segno != NULL_SEGNO)
@@ -281,9 +277,8 @@
unsigned long cost;
unsigned int segno;
- segno = find_next_bit(p.dirty_segmap,
- TOTAL_SEGS(sbi), p.offset);
- if (segno >= TOTAL_SEGS(sbi)) {
+ segno = find_next_bit(p.dirty_segmap, MAIN_SEGS(sbi), p.offset);
+ if (segno >= MAIN_SEGS(sbi)) {
if (sbi->last_victim[p.gc_mode]) {
sbi->last_victim[p.gc_mode] = 0;
p.offset = 0;
@@ -341,37 +336,39 @@
.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);
}
}
@@ -423,6 +420,12 @@
if (IS_ERR(node_page))
continue;
+ /* block may become invalid during get_node_page */
+ if (check_valid_map(sbi, segno, off) == 0) {
+ 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);
@@ -531,7 +534,7 @@
f2fs_wait_on_page_writeback(page, DATA);
if (clear_page_dirty_for_io(page))
- inode_dec_dirty_dents(inode);
+ inode_dec_dirty_pages(inode);
set_cold_data(page);
do_write_data_page(page, &fio);
clear_cold_data(page);
@@ -548,7 +551,7 @@
* 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;
@@ -593,34 +596,34 @@
if (phase == 2) {
inode = f2fs_iget(sb, dni.ino);
- if (IS_ERR(inode))
+ if (IS_ERR(inode) || is_bad_inode(inode))
continue;
start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
data_page = find_data_page(inode,
start_bidx + ofs_in_node, false);
- if (IS_ERR(data_page))
- goto next_iput;
+ 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;
}
- continue;
-next_iput:
- iput(inode);
+
+ /* phase 3 */
+ inode = find_gc_inode(gc_list, dni.ino);
+ 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);
+ }
}
if (++phase < 4)
@@ -641,18 +644,20 @@
}
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)
+ struct gc_inode_list *gc_list, int gc_type)
{
struct page *sum_page;
struct f2fs_summary_block *sum;
@@ -670,7 +675,7 @@
gc_node_segment(sbi, sum->entries, segno, gc_type);
break;
case SUM_TYPE_DATA:
- gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
+ gc_data_segment(sbi, sum->entries, gc_list, segno, gc_type);
break;
}
blk_finish_plug(&plug);
@@ -683,13 +688,17 @@
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;
+ struct gc_inode_list gc_list = {
+ .ilist = LIST_HEAD_INIT(gc_list.ilist),
+ .iroot = RADIX_TREE_INIT(GFP_NOFS),
+ };
- INIT_LIST_HEAD(&ilist);
+ cpc.reason = __get_cp_reason(sbi);
gc_more:
if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
goto stop;
@@ -698,10 +707,10 @@
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) {
gc_type = FG_GC;
- write_checkpoint(sbi, false);
+ write_checkpoint(sbi, &cpc);
}
- if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
+ if (!__get_victim(sbi, &segno, gc_type))
goto stop;
ret = 0;
@@ -711,7 +720,7 @@
META_SSA);
for (i = 0; i < sbi->segs_per_sec; i++)
- do_garbage_collect(sbi, segno + i, &ilist, gc_type);
+ do_garbage_collect(sbi, segno + i, &gc_list, gc_type);
if (gc_type == FG_GC) {
sbi->cur_victim_sec = NULL_SEGNO;
@@ -723,11 +732,11 @@
goto gc_more;
if (gc_type == FG_GC)
- write_checkpoint(sbi, false);
+ write_checkpoint(sbi, &cpc);
stop:
mutex_unlock(&sbi->gc_mutex);
- put_gc_inode(&ilist);
+ put_gc_inode(&gc_list);
return ret;
}
@@ -735,17 +744,3 @@
{
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);
-}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index cc83aa2..9091e0c 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -35,9 +35,9 @@
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 @@
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)
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 3e8ecdf..42da76b 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -15,147 +15,166 @@
bool f2fs_may_inline(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- block_t nr_blocks;
- loff_t i_size;
-
- if (!test_opt(sbi, INLINE_DATA))
+ if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
return false;
- nr_blocks = F2FS_I(inode)->i_xattr_nid ? 3 : 2;
- if (inode->i_blocks > nr_blocks)
+ if (f2fs_is_atomic_file(inode))
return false;
- i_size = i_size_read(inode);
- if (i_size > MAX_INLINE_DATA)
+ if (!S_ISREG(inode->i_mode))
+ return false;
+
+ if (i_size_read(inode) > MAX_INLINE_DATA)
return false;
return true;
}
-int f2fs_read_inline_data(struct inode *inode, struct page *page)
+void read_inline_data(struct page *page, struct page *ipage)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct page *ipage;
void *src_addr, *dst_addr;
- if (page->index) {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
- goto out;
- }
+ if (PageUptodate(page))
+ return;
- ipage = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(ipage)) {
- unlock_page(page);
- return PTR_ERR(ipage);
- }
+ 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(page);
+ dst_addr = kmap_atomic(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
- kunmap(page);
- f2fs_put_page(ipage, 1);
-
-out:
+ flush_dcache_page(page);
+ kunmap_atomic(dst_addr);
SetPageUptodate(page);
- unlock_page(page);
+}
+static void truncate_inline_data(struct page *ipage)
+{
+ f2fs_wait_on_page_writeback(ipage, NODE);
+ memset(inline_data_addr(ipage), 0, MAX_INLINE_DATA);
+}
+
+int f2fs_read_inline_data(struct inode *inode, struct page *page)
+{
+ struct page *ipage;
+
+ ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ if (IS_ERR(ipage)) {
+ unlock_page(page);
+ return PTR_ERR(ipage);
+ }
+
+ if (!f2fs_has_inline_data(inode)) {
+ f2fs_put_page(ipage, 1);
+ return -EAGAIN;
+ }
+
+ if (page->index)
+ zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ else
+ read_inline_data(page, ipage);
+
+ 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_SB(inode->i_sb);
struct f2fs_io_info fio = {
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
};
+ int dirty, err;
+
+ f2fs_bug_on(F2FS_I_SB(dn->inode), page->index);
+
+ if (!f2fs_exist_data(dn->inode))
+ goto clear_out;
+
+ err = f2fs_reserve_block(dn, 0);
+ if (err)
+ return err;
+
+ f2fs_wait_on_page_writeback(page, DATA);
+
+ if (PageUptodate(page))
+ goto no_update;
+
+ zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+
+ /* Copy the whole inline data block */
+ src_addr = inline_data_addr(dn->inode_page);
+ dst_addr = kmap_atomic(page);
+ memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+ flush_dcache_page(page);
+ kunmap_atomic(dst_addr);
+ SetPageUptodate(page);
+no_update:
+ /* clear dirty state */
+ dirty = clear_page_dirty_for_io(page);
+
+ /* write data page to try to make data consistent */
+ set_page_writeback(page);
+ fio.blk_addr = dn->data_blkaddr;
+ write_data_page(page, dn, &fio);
+ update_extent_cache(dn);
+ f2fs_wait_on_page_writeback(page, DATA);
+ 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_data(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;
+
+ 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);
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;
@@ -163,53 +182,31 @@
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);
+ 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);
f2fs_put_dnode(&dn);
-
return 0;
}
-void truncate_inline_data(struct inode *inode, u64 from)
-{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct page *ipage;
-
- if (from >= MAX_INLINE_DATA)
- return;
-
- ipage = get_node_page(sbi, 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_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode *ri = NULL;
void *src_addr, *dst_addr;
struct page *ipage;
@@ -229,13 +226,17 @@
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
ipage = get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(IS_ERR(ipage));
+ f2fs_bug_on(sbi, IS_ERR(ipage));
f2fs_wait_on_page_writeback(ipage, NODE);
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;
@@ -243,17 +244,284 @@
if (f2fs_has_inline_data(inode)) {
ipage = get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(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);
+ f2fs_bug_on(sbi, IS_ERR(ipage));
+ truncate_inline_data(ipage);
+ 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);
goto process_inline;
}
return false;
}
+
+struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
+ struct qstr *name, struct page **res_page)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_inline_dentry *inline_dentry;
+ struct f2fs_dir_entry *de;
+ struct f2fs_dentry_ptr d;
+ struct page *ipage;
+
+ ipage = get_node_page(sbi, dir->i_ino);
+ if (IS_ERR(ipage))
+ return NULL;
+
+ inline_dentry = inline_data_addr(ipage);
+
+ make_dentry_ptr(&d, (void *)inline_dentry, 2);
+ de = find_target_dentry(name, 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(&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;
+}
+
+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)
+ 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);
+ zero_user_segment(page, 0, 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);
+ 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_data(ipage);
+
+ 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)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ struct page *ipage;
+ unsigned int bit_pos;
+ f2fs_hash_t name_hash;
+ struct f2fs_dir_entry *de;
+ size_t namelen = name->len;
+ struct f2fs_inline_dentry *dentry_blk = NULL;
+ int slots = GET_DENTRY_SLOTS(namelen);
+ struct page *page;
+ int err = 0;
+ int i;
+
+ name_hash = f2fs_dentry_hash(name);
+
+ 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)
+ err = -EAGAIN;
+ goto out;
+ }
+
+ 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);
+ de = &dentry_blk->dentry[bit_pos];
+ de->hash_code = name_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);
+ set_page_dirty(ipage);
+
+ /* 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, 0);
+fail:
+ 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);
+
+ 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, void *dirent, filldir_t filldir)
+{
+ unsigned long pos = file->f_pos;
+ unsigned int bit_pos = 0;
+ struct inode *inode = file_inode(file);
+ struct f2fs_inline_dentry *inline_dentry = NULL;
+ struct page *ipage = NULL;
+ struct f2fs_dentry_ptr d;
+
+ if (pos >= NR_INLINE_DENTRY)
+ return 0;
+
+ bit_pos = (pos % NR_INLINE_DENTRY);
+
+ 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(&d, (void *)inline_dentry, 2);
+
+ if (!f2fs_fill_dentries(file, dirent, filldir, &d, 0, bit_pos))
+ file->f_pos = NR_INLINE_DENTRY;
+
+ f2fs_put_page(ipage, 1);
+ return 0;
+}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 9ff9e75..8a75669 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -66,9 +66,28 @@
}
}
+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);
+
+ 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_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
@@ -113,10 +132,18 @@
get_extent_info(&fi->ext, ri->i_ext);
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);
f2fs_put_page(node_page, 1);
+
+ stat_inc_inline_inode(inode);
+ stat_inc_inline_dir(inode);
+
return 0;
}
@@ -155,7 +182,7 @@
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;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
@@ -215,24 +242,29 @@
clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
}
-int update_inode_page(struct inode *inode)
+void update_inode_page(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *node_page;
-
+retry:
node_page = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(node_page))
- return PTR_ERR(node_page);
-
+ if (IS_ERR(node_page)) {
+ int err = PTR_ERR(node_page);
+ if (err == -ENOMEM) {
+ cond_resched();
+ goto retry;
+ } else if (err != -ENOENT) {
+ f2fs_stop_checkpoint(sbi);
+ }
+ return;
+ }
update_inode(inode, node_page);
f2fs_put_page(node_page, 1);
- return 0;
}
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- int ret;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
@@ -246,13 +278,13 @@
* during the urgent cleaning time when runing out of free sections.
*/
f2fs_lock_op(sbi);
- ret = update_inode_page(inode);
+ update_inode_page(inode);
f2fs_unlock_op(sbi);
if (wbc)
f2fs_balance_fs(sbi);
- return ret;
+ return 0;
}
/*
@@ -260,17 +292,21 @@
*/
void f2fs_evict_inode(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ /* some remained atomic pages should discarded */
+ if (f2fs_is_atomic_file(inode))
+ commit_inmem_pages(inode, true);
+
trace_f2fs_evict_inode(inode);
truncate_inode_pages(&inode->i_data, 0);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
- goto no_delete;
+ goto out_clear;
- f2fs_bug_on(get_dirty_dents(inode));
+ f2fs_bug_on(sbi, get_dirty_pages(inode));
remove_dirty_dir_inode(inode);
if (inode->i_nlink || is_bad_inode(inode))
@@ -284,11 +320,11 @@
f2fs_lock_op(sbi);
remove_inode_page(inode);
- stat_dec_inline_inode(inode);
f2fs_unlock_op(sbi);
no_delete:
- end_writeback(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);
@@ -296,4 +332,30 @@
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);
+out_clear:
+ end_writeback(inode);
+}
+
+/* caller should call f2fs_lock_op() */
+void handle_failed_inode(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ clear_nlink(inode);
+ make_bad_inode(inode);
+ unlock_new_inode(inode);
+
+ i_size_write(inode, 0);
+ if (F2FS_HAS_BLOCKS(inode))
+ f2fs_truncate(inode);
+
+ remove_inode_page(inode);
+
+ clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+ clear_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
+ alloc_nid_failed(sbi, inode->i_ino);
+ f2fs_unlock_op(sbi);
+
+ /* iput will drop the inode object */
+ iput(inode);
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index ebba6ab..63094b3 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -23,7 +23,7 @@
static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
nid_t ino;
struct inode *inode;
bool nid_free = false;
@@ -54,6 +54,12 @@
nid_free = true;
goto out;
}
+
+ if (f2fs_may_inline(inode))
+ set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+ if (test_opt(sbi, INLINE_DENTRY) && S_ISDIR(inode->i_mode))
+ set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
+
trace_f2fs_new_inode(inode, 0);
mark_inode_dirty(inode);
return inode;
@@ -102,7 +108,7 @@
static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
struct nameidata *nd)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
nid_t ino = 0;
int err;
@@ -123,21 +129,21 @@
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out;
+ f2fs_unlock_op(sbi);
alloc_nid_done(sbi, ino);
+ stat_inc_inline_inode(inode);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
+
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
return 0;
out:
- clear_nlink(inode);
- unlock_new_inode(inode);
- make_bad_inode(inode);
- iput(inode);
- alloc_nid_failed(sbi, ino);
+ handle_failed_inode(inode);
return err;
}
@@ -145,7 +151,7 @@
struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
int err;
f2fs_balance_fs(sbi);
@@ -156,15 +162,19 @@
set_inode_flag(F2FS_I(inode), FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out;
+ 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);
iput(inode);
+ f2fs_unlock_op(sbi);
return err;
}
@@ -190,14 +200,12 @@
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (de) {
nid_t ino = le32_to_cpu(de->ino);
- kunmap(page);
+ f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
inode = f2fs_iget(dir->i_sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
-
- stat_inc_inline_inode(inode);
}
return d_splice_alias(inode, dentry);
@@ -205,7 +213,7 @@
static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode = dentry->d_inode;
struct f2fs_dir_entry *de;
struct page *page;
@@ -222,15 +230,18 @@
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;
@@ -239,7 +250,7 @@
static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
size_t symlen = strlen(symname) + 1;
int err;
@@ -255,28 +266,27 @@
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out;
+ f2fs_unlock_op(sbi);
err = page_symlink(inode, symname, symlen);
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 err;
out:
- clear_nlink(inode);
- unlock_new_inode(inode);
- make_bad_inode(inode);
- iput(inode);
- alloc_nid_failed(sbi, inode->i_ino);
+ handle_failed_inode(inode);
return err;
}
static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err;
@@ -289,29 +299,28 @@
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);
set_inode_flag(F2FS_I(inode), FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out_fail;
+ f2fs_unlock_op(sbi);
+ stat_inc_inline_dir(inode);
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_fail:
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
- clear_nlink(inode);
- unlock_new_inode(inode);
- make_bad_inode(inode);
- iput(inode);
- alloc_nid_failed(sbi, inode->i_ino);
+ handle_failed_inode(inode);
return err;
}
@@ -326,7 +335,7 @@
static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t rdev)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err = 0;
@@ -344,27 +353,27 @@
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
- f2fs_unlock_op(sbi);
if (err)
goto out;
+ 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:
- clear_nlink(inode);
- unlock_new_inode(inode);
- make_bad_inode(inode);
- iput(inode);
- alloc_nid_failed(sbi, inode->i_ino);
+ handle_failed_inode(inode);
return err;
}
static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
- struct f2fs_sb_info *sbi = F2FS_SB(old_dir->i_sb);
+ 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 page *old_dir_page;
@@ -450,7 +459,7 @@
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 (old_dir_entry) {
if (old_dir != new_dir) {
@@ -458,7 +467,7 @@
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);
@@ -467,19 +476,22 @@
}
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_dentry_kunmap(new_dir, new_page);
f2fs_put_page(new_page, 0);
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;
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 3e16e70..23c8fb5 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -19,6 +19,7 @@
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
#define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock)
@@ -31,22 +32,39 @@
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct sysinfo val;
+ unsigned long avail_ram;
unsigned long mem_size = 0;
bool res = false;
si_meminfo(&val);
- /* give 25%, 25%, 50% memory for each components respectively */
+
+ /* only uses low memory */
+ avail_ram = val.totalram - val.totalhigh;
+
+ /* give 25%, 25%, 50%, 50% memory for each components respectively */
if (type == FREE_NIDS) {
- mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> 12;
- res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+ mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >>
+ PAGE_CACHE_SHIFT;
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
} else if (type == NAT_ENTRIES) {
- mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12;
- res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+ mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
+ PAGE_CACHE_SHIFT;
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
} else if (type == DIRTY_DENTS) {
if (sbi->sb->s_bdi->dirty_exceeded)
return false;
mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
- res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1);
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+ } else if (type == INO_ENTRIES) {
+ int i;
+
+ for (i = 0; i <= UPDATE_INO; i++)
+ mem_size += (sbi->im[i].ino_num *
+ sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT;
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+ } else {
+ if (sbi->sb->s_bdi->dirty_exceeded)
+ return false;
}
return res;
}
@@ -54,7 +72,6 @@
static void clear_node_page_dirty(struct page *page)
{
struct address_space *mapping = page->mapping;
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
unsigned int long flags;
if (PageDirty(page)) {
@@ -65,7 +82,7 @@
spin_unlock_irqrestore(&mapping->tree_lock, flags);
clear_page_dirty_for_io(page);
- dec_page_count(sbi, F2FS_DIRTY_NODES);
+ dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES);
}
ClearPageUptodate(page);
}
@@ -92,7 +109,7 @@
/* get current nat block page with lock */
src_page = get_meta_page(sbi, src_off);
dst_page = grab_meta_page(sbi, dst_off);
- f2fs_bug_on(PageDirty(src_page));
+ f2fs_bug_on(sbi, PageDirty(src_page));
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
@@ -124,60 +141,106 @@
kmem_cache_free(nat_entry_slab, e);
}
-int is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
+static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
+ struct nat_entry *ne)
+{
+ nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
+ struct nat_entry_set *head;
+
+ if (get_nat_flag(ne, IS_DIRTY))
+ return;
+
+ head = radix_tree_lookup(&nm_i->nat_set_root, set);
+ if (!head) {
+ head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC);
+
+ INIT_LIST_HEAD(&head->entry_list);
+ INIT_LIST_HEAD(&head->set_list);
+ head->set = set;
+ head->entry_cnt = 0;
+ f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head);
+ }
+ list_move_tail(&ne->list, &head->entry_list);
+ nm_i->dirty_nat_cnt++;
+ head->entry_cnt++;
+ set_nat_flag(ne, IS_DIRTY, true);
+}
+
+static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
+ struct nat_entry *ne)
+{
+ nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
+ struct nat_entry_set *head;
+
+ head = radix_tree_lookup(&nm_i->nat_set_root, set);
+ if (head) {
+ list_move_tail(&ne->list, &nm_i->nat_entries);
+ set_nat_flag(ne, IS_DIRTY, false);
+ head->entry_cnt--;
+ nm_i->dirty_nat_cnt--;
+ }
+}
+
+static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
+ nid_t start, unsigned int nr, struct nat_entry_set **ep)
+{
+ return radix_tree_gang_lookup(&nm_i->nat_set_root, (void **)ep,
+ start, nr);
+}
+
+bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
- int is_cp = 1;
+ bool is_cp = true;
- read_lock(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
- if (e && !e->checkpointed)
- is_cp = 0;
- read_unlock(&nm_i->nat_tree_lock);
+ if (e && !get_nat_flag(e, IS_CHECKPOINTED))
+ is_cp = false;
+ up_read(&nm_i->nat_tree_lock);
return is_cp;
}
-bool fsync_mark_done(struct f2fs_sb_info *sbi, nid_t nid)
+bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
- bool fsync_done = false;
+ bool fsynced = false;
- read_lock(&nm_i->nat_tree_lock);
- e = __lookup_nat_cache(nm_i, nid);
- if (e)
- fsync_done = e->fsync_done;
- read_unlock(&nm_i->nat_tree_lock);
- return fsync_done;
+ down_read(&nm_i->nat_tree_lock);
+ e = __lookup_nat_cache(nm_i, ino);
+ if (e && get_nat_flag(e, HAS_FSYNCED_INODE))
+ fsynced = true;
+ up_read(&nm_i->nat_tree_lock);
+ return fsynced;
}
-void fsync_mark_clear(struct f2fs_sb_info *sbi, nid_t nid)
+bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
+ bool need_update = true;
- write_lock(&nm_i->nat_tree_lock);
- e = __lookup_nat_cache(nm_i, nid);
- if (e)
- e->fsync_done = false;
- write_unlock(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
+ e = __lookup_nat_cache(nm_i, ino);
+ if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
+ (get_nat_flag(e, IS_CHECKPOINTED) ||
+ get_nat_flag(e, HAS_FSYNCED_INODE)))
+ need_update = false;
+ up_read(&nm_i->nat_tree_lock);
+ return need_update;
}
static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
{
struct nat_entry *new;
- new = kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC);
- if (!new)
- return NULL;
- if (radix_tree_insert(&nm_i->nat_root, nid, new)) {
- kmem_cache_free(nat_entry_slab, new);
- return NULL;
- }
+ new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC);
+ f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
memset(new, 0, sizeof(struct nat_entry));
nat_set_nid(new, nid);
- new->checkpointed = true;
+ nat_reset_flag(new);
list_add_tail(&new->list, &nm_i->nat_entries);
nm_i->nat_cnt++;
return new;
@@ -187,18 +250,14 @@
struct f2fs_nat_entry *ne)
{
struct nat_entry *e;
-retry:
- write_lock(&nm_i->nat_tree_lock);
+
+ down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (!e) {
e = grab_nat_entry(nm_i, nid);
- if (!e) {
- write_unlock(&nm_i->nat_tree_lock);
- goto retry;
- }
node_info_from_raw_nat(&e->ni, ne);
}
- write_unlock(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
@@ -206,34 +265,30 @@
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
-retry:
- write_lock(&nm_i->nat_tree_lock);
+
+ down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ni->nid);
if (!e) {
e = grab_nat_entry(nm_i, ni->nid);
- if (!e) {
- write_unlock(&nm_i->nat_tree_lock);
- goto retry;
- }
- e->ni = *ni;
- f2fs_bug_on(ni->blk_addr == NEW_ADDR);
+ copy_node_info(&e->ni, ni);
+ f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
} else if (new_blkaddr == NEW_ADDR) {
/*
* when nid is reallocated,
* previous nat entry can be remained in nat cache.
* So, reinitialize it with new information.
*/
- e->ni = *ni;
- f2fs_bug_on(ni->blk_addr != NULL_ADDR);
+ copy_node_info(&e->ni, ni);
+ f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
}
/* sanity check */
- f2fs_bug_on(nat_get_blkaddr(e) != ni->blk_addr);
- f2fs_bug_on(nat_get_blkaddr(e) == NULL_ADDR &&
+ f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr);
+ f2fs_bug_on(sbi, nat_get_blkaddr(e) == NULL_ADDR &&
new_blkaddr == NULL_ADDR);
- f2fs_bug_on(nat_get_blkaddr(e) == NEW_ADDR &&
+ f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR &&
new_blkaddr == NEW_ADDR);
- f2fs_bug_on(nat_get_blkaddr(e) != NEW_ADDR &&
+ f2fs_bug_on(sbi, nat_get_blkaddr(e) != NEW_ADDR &&
nat_get_blkaddr(e) != NULL_ADDR &&
new_blkaddr == NEW_ADDR);
@@ -245,13 +300,18 @@
/* change address */
nat_set_blkaddr(e, new_blkaddr);
+ if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR)
+ set_nat_flag(e, IS_CHECKPOINTED, false);
__set_nat_cache_dirty(nm_i, e);
/* update fsync_mark if its inode nat entry is still alive */
e = __lookup_nat_cache(nm_i, ni->ino);
- if (e)
- e->fsync_done = fsync_done;
- write_unlock(&nm_i->nat_tree_lock);
+ if (e) {
+ if (fsync_done && ni->nid == ni->ino)
+ set_nat_flag(e, HAS_FSYNCED_INODE, true);
+ set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
+ }
+ up_write(&nm_i->nat_tree_lock);
}
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -261,7 +321,7 @@
if (available_free_memory(sbi, NAT_ENTRIES))
return 0;
- write_lock(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
struct nat_entry *ne;
ne = list_first_entry(&nm_i->nat_entries,
@@ -269,7 +329,7 @@
__del_from_nat_cache(nm_i, ne);
nr_shrink--;
}
- write_unlock(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
return nr_shrink;
}
@@ -288,21 +348,22 @@
struct nat_entry *e;
int i;
- memset(&ne, 0, sizeof(struct f2fs_nat_entry));
ni->nid = nid;
/* Check nat cache */
- read_lock(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
ni->ino = nat_get_ino(e);
ni->blk_addr = nat_get_blkaddr(e);
ni->version = nat_get_version(e);
}
- read_unlock(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
if (e)
return;
+ memset(&ne, 0, sizeof(struct f2fs_nat_entry));
+
/* Check current segment summary */
mutex_lock(&curseg->curseg_mutex);
i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
@@ -411,9 +472,9 @@
*/
int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct page *npage[4];
- struct page *parent;
+ struct page *parent = NULL;
int offset[4];
unsigned int noffset[4];
nid_t nids[4];
@@ -430,6 +491,14 @@
if (IS_ERR(npage[0]))
return PTR_ERR(npage[0]);
}
+
+ /* if inline_data is set, should not report any block indices */
+ if (f2fs_has_inline_data(dn->inode) && index) {
+ err = -EINVAL;
+ f2fs_put_page(npage[0], 1);
+ goto release_out;
+ }
+
parent = npage[0];
if (level != 0)
nids[1] = get_nid(parent, offset[0], true);
@@ -504,15 +573,15 @@
static void truncate_node(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info ni;
get_node_info(sbi, dn->nid, &ni);
if (dn->inode->i_blocks == 0) {
- f2fs_bug_on(ni.blk_addr != NULL_ADDR);
+ f2fs_bug_on(sbi, ni.blk_addr != NULL_ADDR);
goto invalidate;
}
- f2fs_bug_on(ni.blk_addr == NULL_ADDR);
+ f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
/* Deallocate node address */
invalidate_blocks(sbi, ni.blk_addr);
@@ -527,7 +596,7 @@
}
invalidate:
clear_node_page_dirty(dn->node_page);
- F2FS_SET_SB_DIRT(sbi);
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
f2fs_put_page(dn->node_page, 1);
@@ -540,14 +609,13 @@
static int truncate_dnode(struct dnode_of_data *dn)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
struct page *page;
if (dn->nid == 0)
return 1;
/* get direct node */
- page = get_node_page(sbi, dn->nid);
+ page = get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page) && PTR_ERR(page) == -ENOENT)
return 1;
else if (IS_ERR(page))
@@ -564,7 +632,6 @@
static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
int ofs, int depth)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
struct dnode_of_data rdn = *dn;
struct page *page;
struct f2fs_node *rn;
@@ -578,7 +645,7 @@
trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr);
- page = get_node_page(sbi, dn->nid);
+ page = get_node_page(F2FS_I_SB(dn->inode), dn->nid);
if (IS_ERR(page)) {
trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page));
return PTR_ERR(page);
@@ -636,7 +703,6 @@
static int truncate_partial_nodes(struct dnode_of_data *dn,
struct f2fs_inode *ri, int *offset, int depth)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
struct page *pages[2];
nid_t nid[3];
nid_t child_nid;
@@ -651,7 +717,7 @@
/* get indirect nodes in the path */
for (i = 0; i < idx + 1; i++) {
/* reference count'll be increased */
- pages[i] = get_node_page(sbi, nid[i]);
+ pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]);
if (IS_ERR(pages[i])) {
err = PTR_ERR(pages[i]);
idx = i - 1;
@@ -696,7 +762,7 @@
*/
int truncate_inode_blocks(struct inode *inode, pgoff_t from)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err = 0, cont = 1;
int level, offset[4], noffset[4];
unsigned int nofs = 0;
@@ -792,7 +858,7 @@
int truncate_xattr_node(struct inode *inode, struct page *page)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t nid = F2FS_I(inode)->i_xattr_nid;
struct dnode_of_data dn;
struct page *npage;
@@ -840,7 +906,8 @@
truncate_data_blocks_range(&dn, 1);
/* 0 is possible, after f2fs_new_inode() has failed */
- f2fs_bug_on(inode->i_blocks != 0 && inode->i_blocks != 1);
+ f2fs_bug_on(F2FS_I_SB(inode),
+ inode->i_blocks != 0 && inode->i_blocks != 1);
/* will put inode & node pages */
truncate_node(&dn);
@@ -860,7 +927,7 @@
struct page *new_node_page(struct dnode_of_data *dn,
unsigned int ofs, struct page *ipage)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info old_ni, new_ni;
struct page *page;
int err;
@@ -880,7 +947,7 @@
get_node_info(sbi, dn->nid, &old_ni);
/* Reinitialize old_ni with new node page */
- f2fs_bug_on(old_ni.blk_addr != NULL_ADDR);
+ f2fs_bug_on(sbi, old_ni.blk_addr != NULL_ADDR);
new_ni = old_ni;
new_ni.ino = dn->inode->i_ino;
set_node_addr(sbi, &new_ni, NEW_ADDR, false);
@@ -918,8 +985,12 @@
*/
static int read_node_page(struct page *page, int rw)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
struct node_info ni;
+ struct f2fs_io_info fio = {
+ .type = NODE,
+ .rw = rw,
+ };
get_node_info(sbi, page->index, &ni);
@@ -931,7 +1002,8 @@
if (PageUptodate(page))
return LOCKED_PAGE;
- return f2fs_submit_page_bio(sbi, page, ni.blk_addr, rw);
+ fio.blk_addr = ni.blk_addr;
+ return f2fs_submit_page_bio(sbi, page, &fio);
}
/*
@@ -972,11 +1044,11 @@
err = read_node_page(page, READ_SYNC);
if (err < 0)
return ERR_PTR(err);
- else if (err == LOCKED_PAGE)
- goto got_it;
+ else if (err != LOCKED_PAGE)
+ lock_page(page);
- lock_page(page);
if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) {
+ ClearPageUptodate(page);
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
@@ -984,7 +1056,7 @@
f2fs_put_page(page, 1);
goto repeat;
}
-got_it:
+ mark_page_accessed(page);
return page;
}
@@ -994,7 +1066,7 @@
*/
struct page *get_node_page_ra(struct page *parent, int start)
{
- struct f2fs_sb_info *sbi = F2FS_SB(parent->mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
struct blk_plug plug;
struct page *page;
int err, i, end;
@@ -1039,6 +1111,7 @@
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
+ mark_page_accessed(page);
return page;
}
@@ -1124,10 +1197,14 @@
/* called by fsync() */
if (ino && IS_DNODE(page)) {
- int mark = !is_checkpointed_node(sbi, ino);
set_fsync_mark(page, 1);
- if (IS_INODE(page))
- set_dentry_mark(page, mark);
+ if (IS_INODE(page)) {
+ if (!is_checkpointed_node(sbi, ino) &&
+ !has_fsynced_inode(sbi, ino))
+ set_dentry_mark(page, 1);
+ else
+ set_dentry_mark(page, 0);
+ }
nwritten++;
} else {
set_fsync_mark(page, 0);
@@ -1206,9 +1283,8 @@
static int f2fs_write_node_page(struct page *page,
struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
nid_t nid;
- block_t new_addr;
struct node_info ni;
struct f2fs_io_info fio = {
.type = NODE,
@@ -1217,7 +1293,7 @@
trace_f2fs_writepage(page, NODE);
- if (unlikely(sbi->por_doing))
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
@@ -1226,7 +1302,7 @@
/* get old block addr of this node page */
nid = nid_of_node(page);
- f2fs_bug_on(page->index != nid);
+ f2fs_bug_on(sbi, page->index != nid);
get_node_info(sbi, nid, &ni);
@@ -1237,16 +1313,24 @@
return 0;
}
- if (wbc->for_reclaim)
- goto redirty_out;
+ if (wbc->for_reclaim) {
+ if (!down_read_trylock(&sbi->node_write))
+ goto redirty_out;
+ } else {
+ down_read(&sbi->node_write);
+ }
- down_read(&sbi->node_write);
set_page_writeback(page);
- write_node_page(sbi, page, &fio, nid, ni.blk_addr, &new_addr);
- set_node_addr(sbi, &ni, new_addr, is_fsync_dnode(page));
+ fio.blk_addr = ni.blk_addr;
+ write_node_page(sbi, page, nid, &fio);
+ set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
dec_page_count(sbi, F2FS_DIRTY_NODES);
up_read(&sbi->node_write);
unlock_page(page);
+
+ if (wbc->for_reclaim)
+ f2fs_submit_merged_bio(sbi, NODE, WRITE);
+
return 0;
redirty_out:
@@ -1257,7 +1341,7 @@
static int f2fs_write_node_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff;
trace_f2fs_writepages(mapping->host, wbc, NODE);
@@ -1282,36 +1366,19 @@
static int f2fs_set_node_page_dirty(struct page *page)
{
- struct address_space *mapping = page->mapping;
- struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
-
trace_f2fs_set_page_dirty(page, NODE);
SetPageUptodate(page);
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
- inc_page_count(sbi, F2FS_DIRTY_NODES);
+ inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
SetPagePrivate(page);
+ f2fs_trace_pid(page);
return 1;
}
return 0;
}
-static void f2fs_invalidate_node_page(struct page *page, unsigned long offset)
-{
- struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- if (PageDirty(page))
- dec_page_count(sbi, F2FS_DIRTY_NODES);
- ClearPagePrivate(page);
-}
-
-static int f2fs_release_node_page(struct page *page, gfp_t wait)
-{
- ClearPagePrivate(page);
- return 1;
-}
-
/*
* Structure of the f2fs node operations
*/
@@ -1319,8 +1386,8 @@
.writepage = f2fs_write_node_page,
.writepages = f2fs_write_node_pages,
.set_page_dirty = f2fs_set_node_page_dirty,
- .invalidatepage = f2fs_invalidate_node_page,
- .releasepage = f2fs_release_node_page,
+ .invalidatepage = f2fs_invalidate_page,
+ .releasepage = f2fs_release_page,
};
static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
@@ -1352,12 +1419,13 @@
if (build) {
/* do not add allocated nids */
- read_lock(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
ne = __lookup_nat_cache(nm_i, nid);
if (ne &&
- (!ne->checkpointed || nat_get_blkaddr(ne) != NULL_ADDR))
+ (!get_nat_flag(ne, IS_CHECKPOINTED) ||
+ nat_get_blkaddr(ne) != NULL_ADDR))
allocated = true;
- read_unlock(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
if (allocated)
return 0;
}
@@ -1366,15 +1434,22 @@
i->nid = nid;
i->state = NID_NEW;
+ if (radix_tree_preload(GFP_NOFS)) {
+ kmem_cache_free(free_nid_slab, i);
+ return 0;
+ }
+
spin_lock(&nm_i->free_nid_list_lock);
if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) {
spin_unlock(&nm_i->free_nid_list_lock);
+ radix_tree_preload_end();
kmem_cache_free(free_nid_slab, i);
return 0;
}
list_add_tail(&i->list, &nm_i->free_nid_list);
nm_i->fcnt++;
spin_unlock(&nm_i->free_nid_list_lock);
+ radix_tree_preload_end();
return 1;
}
@@ -1412,7 +1487,7 @@
break;
blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
- f2fs_bug_on(blk_addr == NEW_ADDR);
+ f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
if (blk_addr == NULL_ADDR) {
if (add_free_nid(sbi, start_nid, true) < 0)
break;
@@ -1482,12 +1557,12 @@
/* We should not use stale free nids created by build_free_nids */
if (nm_i->fcnt && !on_build_free_nids(nm_i)) {
- f2fs_bug_on(list_empty(&nm_i->free_nid_list));
+ f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list));
list_for_each_entry(i, &nm_i->free_nid_list, list)
if (i->state == NID_NEW)
break;
- f2fs_bug_on(i->state != NID_NEW);
+ f2fs_bug_on(sbi, i->state != NID_NEW);
*nid = i->nid;
i->state = NID_ALLOC;
nm_i->fcnt--;
@@ -1513,7 +1588,7 @@
spin_lock(&nm_i->free_nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- f2fs_bug_on(!i || i->state != NID_ALLOC);
+ f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
__del_from_free_nid_list(nm_i, i);
spin_unlock(&nm_i->free_nid_list_lock);
@@ -1534,7 +1609,7 @@
spin_lock(&nm_i->free_nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- f2fs_bug_on(!i || i->state != NID_ALLOC);
+ f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
if (!available_free_memory(sbi, FREE_NIDS)) {
__del_from_free_nid_list(nm_i, i);
need_free = true;
@@ -1550,14 +1625,13 @@
void recover_inline_xattr(struct inode *inode, struct page *page)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
void *src_addr, *dst_addr;
size_t inline_size;
struct page *ipage;
struct f2fs_inode *ri;
- ipage = get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(IS_ERR(ipage));
+ ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage));
ri = F2FS_INODE(page);
if (!(ri->i_inline & F2FS_INLINE_XATTR)) {
@@ -1578,7 +1652,7 @@
void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid;
nid_t new_xnid = nid_of_node(page);
struct node_info ni;
@@ -1589,7 +1663,7 @@
/* Deallocate node address */
get_node_info(sbi, prev_xnid, &ni);
- f2fs_bug_on(ni.blk_addr == NULL_ADDR);
+ f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
invalidate_blocks(sbi, ni.blk_addr);
dec_valid_node_count(sbi, inode);
set_node_addr(sbi, &ni, NULL_ADDR, false);
@@ -1597,7 +1671,7 @@
recover_xnid:
/* 2: allocate new xattr nid */
if (unlikely(!inc_valid_node_count(sbi, inode)))
- f2fs_bug_on(1);
+ f2fs_bug_on(sbi, 1);
remove_free_nid(NM_I(sbi), new_xnid);
get_node_info(sbi, new_xnid, &ni);
@@ -1656,163 +1730,41 @@
return 0;
}
-/*
- * ra_sum_pages() merge contiguous pages into one bio and submit.
- * these pre-read pages are allocated in bd_inode's mapping tree.
- */
-static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages,
- int start, int nrpages)
-{
- struct inode *inode = sbi->sb->s_bdev->bd_inode;
- struct address_space *mapping = inode->i_mapping;
- int i, page_idx = start;
- struct f2fs_io_info fio = {
- .type = META,
- .rw = READ_SYNC | REQ_META | REQ_PRIO
- };
-
- for (i = 0; page_idx < start + nrpages; page_idx++, i++) {
- /* alloc page in bd_inode for reading node summary info */
- pages[i] = grab_cache_page(mapping, page_idx);
- if (!pages[i])
- break;
- f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio);
- }
-
- f2fs_submit_merged_bio(sbi, META, READ);
- return i;
-}
-
int restore_node_summary(struct f2fs_sb_info *sbi,
unsigned int segno, struct f2fs_summary_block *sum)
{
struct f2fs_node *rn;
struct f2fs_summary *sum_entry;
- struct inode *inode = sbi->sb->s_bdev->bd_inode;
block_t addr;
- int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
- struct page *pages[bio_blocks];
- int i, idx, last_offset, nrpages, err = 0;
+ int bio_blocks = MAX_BIO_BLOCKS(sbi);
+ int i, idx, last_offset, nrpages;
/* scan the node segment */
last_offset = sbi->blocks_per_seg;
addr = START_BLOCK(sbi, segno);
sum_entry = &sum->entries[0];
- for (i = 0; !err && i < last_offset; i += nrpages, addr += nrpages) {
+ for (i = 0; i < last_offset; i += nrpages, addr += nrpages) {
nrpages = min(last_offset - i, bio_blocks);
/* readahead node pages */
- nrpages = ra_sum_pages(sbi, pages, addr, nrpages);
- if (!nrpages)
- return -ENOMEM;
+ ra_meta_pages(sbi, addr, nrpages, META_POR);
- for (idx = 0; idx < nrpages; idx++) {
- if (err)
- goto skip;
+ for (idx = addr; idx < addr + nrpages; idx++) {
+ struct page *page = get_meta_page(sbi, idx);
- lock_page(pages[idx]);
- if (unlikely(!PageUptodate(pages[idx]))) {
- err = -EIO;
- } else {
- rn = F2FS_NODE(pages[idx]);
- sum_entry->nid = rn->footer.nid;
- sum_entry->version = 0;
- sum_entry->ofs_in_node = 0;
- sum_entry++;
- }
- unlock_page(pages[idx]);
-skip:
- page_cache_release(pages[idx]);
+ rn = F2FS_NODE(page);
+ sum_entry->nid = rn->footer.nid;
+ sum_entry->version = 0;
+ sum_entry->ofs_in_node = 0;
+ sum_entry++;
+ f2fs_put_page(page, 1);
}
- invalidate_mapping_pages(inode->i_mapping, addr,
+ invalidate_mapping_pages(META_MAPPING(sbi), addr,
addr + nrpages);
}
- return err;
-}
-
-static struct nat_entry_set *grab_nat_entry_set(void)
-{
- struct nat_entry_set *nes =
- f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC);
-
- nes->entry_cnt = 0;
- INIT_LIST_HEAD(&nes->set_list);
- INIT_LIST_HEAD(&nes->entry_list);
- return nes;
-}
-
-static void release_nat_entry_set(struct nat_entry_set *nes,
- struct f2fs_nm_info *nm_i)
-{
- f2fs_bug_on(!list_empty(&nes->entry_list));
-
- nm_i->dirty_nat_cnt -= nes->entry_cnt;
- list_del(&nes->set_list);
- kmem_cache_free(nat_entry_set_slab, nes);
-}
-
-static void adjust_nat_entry_set(struct nat_entry_set *nes,
- struct list_head *head)
-{
- struct nat_entry_set *next = nes;
-
- if (list_is_last(&nes->set_list, head))
- return;
-
- list_for_each_entry_continue(next, head, set_list)
- if (nes->entry_cnt <= next->entry_cnt)
- break;
-
- list_move_tail(&nes->set_list, &next->set_list);
-}
-
-static void add_nat_entry(struct nat_entry *ne, struct list_head *head)
-{
- struct nat_entry_set *nes;
- nid_t start_nid = START_NID(ne->ni.nid);
-
- list_for_each_entry(nes, head, set_list) {
- if (nes->start_nid == start_nid) {
- list_move_tail(&ne->list, &nes->entry_list);
- nes->entry_cnt++;
- adjust_nat_entry_set(nes, head);
- return;
- }
- }
-
- nes = grab_nat_entry_set();
-
- nes->start_nid = start_nid;
- list_move_tail(&ne->list, &nes->entry_list);
- nes->entry_cnt++;
- list_add(&nes->set_list, head);
-}
-
-static void merge_nats_in_set(struct f2fs_sb_info *sbi)
-{
- struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct list_head *dirty_list = &nm_i->dirty_nat_entries;
- struct list_head *set_list = &nm_i->nat_entry_set;
- struct nat_entry *ne, *tmp;
-
- write_lock(&nm_i->nat_tree_lock);
- list_for_each_entry_safe(ne, tmp, dirty_list, list) {
- if (nat_get_blkaddr(ne) == NEW_ADDR)
- continue;
- add_nat_entry(ne, set_list);
- nm_i->dirty_nat_cnt++;
- }
- write_unlock(&nm_i->nat_tree_lock);
-}
-
-static bool __has_cursum_space(struct f2fs_summary_block *sum, int size)
-{
- if (nats_in_cursum(sum) + size <= NAT_JOURNAL_ENTRIES)
- return true;
- else
- return false;
+ return 0;
}
static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
@@ -1829,26 +1781,105 @@
nid_t nid = le32_to_cpu(nid_in_journal(sum, i));
raw_ne = nat_in_journal(sum, i);
-retry:
- write_lock(&nm_i->nat_tree_lock);
- ne = __lookup_nat_cache(nm_i, nid);
- if (ne)
- goto found;
- ne = grab_nat_entry(nm_i, nid);
+ down_write(&nm_i->nat_tree_lock);
+ ne = __lookup_nat_cache(nm_i, nid);
if (!ne) {
- write_unlock(&nm_i->nat_tree_lock);
- goto retry;
+ ne = grab_nat_entry(nm_i, nid);
+ node_info_from_raw_nat(&ne->ni, &raw_ne);
}
- node_info_from_raw_nat(&ne->ni, &raw_ne);
-found:
__set_nat_cache_dirty(nm_i, ne);
- write_unlock(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
update_nats_in_cursum(sum, -i);
mutex_unlock(&curseg->curseg_mutex);
}
+static void __adjust_nat_entry_set(struct nat_entry_set *nes,
+ struct list_head *head, int max)
+{
+ struct nat_entry_set *cur;
+
+ if (nes->entry_cnt >= max)
+ goto add_out;
+
+ list_for_each_entry(cur, head, set_list) {
+ if (cur->entry_cnt >= nes->entry_cnt) {
+ list_add(&nes->set_list, cur->set_list.prev);
+ return;
+ }
+ }
+add_out:
+ list_add_tail(&nes->set_list, head);
+}
+
+static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
+ struct nat_entry_set *set)
+{
+ struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
+ struct f2fs_summary_block *sum = curseg->sum_blk;
+ nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK;
+ bool to_journal = true;
+ struct f2fs_nat_block *nat_blk;
+ struct nat_entry *ne, *cur;
+ struct page *page = NULL;
+
+ /*
+ * there are two steps to flush nat entries:
+ * #1, flush nat entries to journal in current hot data summary block.
+ * #2, flush nat entries to nat page.
+ */
+ if (!__has_cursum_space(sum, set->entry_cnt, NAT_JOURNAL))
+ to_journal = false;
+
+ if (to_journal) {
+ mutex_lock(&curseg->curseg_mutex);
+ } else {
+ page = get_next_nat_page(sbi, start_nid);
+ nat_blk = page_address(page);
+ f2fs_bug_on(sbi, !nat_blk);
+ }
+
+ /* flush dirty nats in nat entry set */
+ list_for_each_entry_safe(ne, cur, &set->entry_list, list) {
+ struct f2fs_nat_entry *raw_ne;
+ nid_t nid = nat_get_nid(ne);
+ int offset;
+
+ if (nat_get_blkaddr(ne) == NEW_ADDR)
+ continue;
+
+ if (to_journal) {
+ offset = lookup_journal_in_cursum(sum,
+ NAT_JOURNAL, nid, 1);
+ f2fs_bug_on(sbi, offset < 0);
+ raw_ne = &nat_in_journal(sum, offset);
+ nid_in_journal(sum, offset) = cpu_to_le32(nid);
+ } else {
+ raw_ne = &nat_blk->entries[nid - start_nid];
+ }
+ raw_nat_from_node_info(raw_ne, &ne->ni);
+
+ down_write(&NM_I(sbi)->nat_tree_lock);
+ nat_reset_flag(ne);
+ __clear_nat_cache_dirty(NM_I(sbi), ne);
+ up_write(&NM_I(sbi)->nat_tree_lock);
+
+ if (nat_get_blkaddr(ne) == NULL_ADDR)
+ add_free_nid(sbi, nid, false);
+ }
+
+ if (to_journal)
+ mutex_unlock(&curseg->curseg_mutex);
+ else
+ f2fs_put_page(page, 1);
+
+ f2fs_bug_on(sbi, set->entry_cnt);
+
+ radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
+ kmem_cache_free(nat_entry_set_slab, set);
+}
+
/*
* This function is called during the checkpointing process.
*/
@@ -1857,91 +1888,36 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
struct f2fs_summary_block *sum = curseg->sum_blk;
- struct nat_entry_set *nes, *tmp;
- struct list_head *head = &nm_i->nat_entry_set;
- bool to_journal = true;
+ struct nat_entry_set *setvec[SETVEC_SIZE];
+ struct nat_entry_set *set, *tmp;
+ unsigned int found;
+ nid_t set_idx = 0;
+ LIST_HEAD(sets);
- /* merge nat entries of dirty list to nat entry set temporarily */
- merge_nats_in_set(sbi);
-
+ if (!nm_i->dirty_nat_cnt)
+ return;
/*
* if there are no enough space in journal to store dirty nat
* entries, remove all entries from journal and merge them
* into nat entry set.
*/
- if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt)) {
+ if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
remove_nats_in_journal(sbi);
- /*
- * merge nat entries of dirty list to nat entry set temporarily
- */
- merge_nats_in_set(sbi);
+ while ((found = __gang_lookup_nat_set(nm_i,
+ set_idx, SETVEC_SIZE, setvec))) {
+ unsigned idx;
+ set_idx = setvec[found - 1]->set + 1;
+ for (idx = 0; idx < found; idx++)
+ __adjust_nat_entry_set(setvec[idx], &sets,
+ MAX_NAT_JENTRIES(sum));
}
- if (!nm_i->dirty_nat_cnt)
- return;
+ /* flush dirty nats in nat entry set */
+ list_for_each_entry_safe(set, tmp, &sets, set_list)
+ __flush_nat_entry_set(sbi, set);
- /*
- * there are two steps to flush nat entries:
- * #1, flush nat entries to journal in current hot data summary block.
- * #2, flush nat entries to nat page.
- */
- list_for_each_entry_safe(nes, tmp, head, set_list) {
- struct f2fs_nat_block *nat_blk;
- struct nat_entry *ne, *cur;
- struct page *page;
- nid_t start_nid = nes->start_nid;
-
- if (to_journal && !__has_cursum_space(sum, nes->entry_cnt))
- to_journal = false;
-
- if (to_journal) {
- mutex_lock(&curseg->curseg_mutex);
- } else {
- page = get_next_nat_page(sbi, start_nid);
- nat_blk = page_address(page);
- f2fs_bug_on(!nat_blk);
- }
-
- /* flush dirty nats in nat entry set */
- list_for_each_entry_safe(ne, cur, &nes->entry_list, list) {
- struct f2fs_nat_entry *raw_ne;
- nid_t nid = nat_get_nid(ne);
- int offset;
-
- if (to_journal) {
- offset = lookup_journal_in_cursum(sum,
- NAT_JOURNAL, nid, 1);
- f2fs_bug_on(offset < 0);
- raw_ne = &nat_in_journal(sum, offset);
- nid_in_journal(sum, offset) = cpu_to_le32(nid);
- } else {
- raw_ne = &nat_blk->entries[nid - start_nid];
- }
- raw_nat_from_node_info(raw_ne, &ne->ni);
-
- if (nat_get_blkaddr(ne) == NULL_ADDR &&
- add_free_nid(sbi, nid, false) <= 0) {
- write_lock(&nm_i->nat_tree_lock);
- __del_from_nat_cache(nm_i, ne);
- write_unlock(&nm_i->nat_tree_lock);
- } else {
- write_lock(&nm_i->nat_tree_lock);
- __clear_nat_cache_dirty(nm_i, ne);
- write_unlock(&nm_i->nat_tree_lock);
- }
- }
-
- if (to_journal)
- mutex_unlock(&curseg->curseg_mutex);
- else
- f2fs_put_page(page, 1);
-
- release_nat_entry_set(nes, nm_i);
- }
-
- f2fs_bug_on(!list_empty(head));
- f2fs_bug_on(nm_i->dirty_nat_cnt);
+ f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
}
static int init_node_manager(struct f2fs_sb_info *sbi)
@@ -1967,14 +1943,13 @@
INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
INIT_LIST_HEAD(&nm_i->free_nid_list);
- INIT_RADIX_TREE(&nm_i->nat_root, GFP_ATOMIC);
+ INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO);
+ INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO);
INIT_LIST_HEAD(&nm_i->nat_entries);
- INIT_LIST_HEAD(&nm_i->dirty_nat_entries);
- INIT_LIST_HEAD(&nm_i->nat_entry_set);
mutex_init(&nm_i->build_lock);
spin_lock_init(&nm_i->free_nid_list_lock);
- rwlock_init(&nm_i->nat_tree_lock);
+ init_rwsem(&nm_i->nat_tree_lock);
nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
@@ -2010,6 +1985,7 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i, *next_i;
struct nat_entry *natvec[NATVEC_SIZE];
+ struct nat_entry_set *setvec[SETVEC_SIZE];
nid_t nid = 0;
unsigned int found;
@@ -2019,27 +1995,43 @@
/* destroy free nid list */
spin_lock(&nm_i->free_nid_list_lock);
list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) {
- f2fs_bug_on(i->state == NID_ALLOC);
+ f2fs_bug_on(sbi, i->state == NID_ALLOC);
__del_from_free_nid_list(nm_i, i);
nm_i->fcnt--;
spin_unlock(&nm_i->free_nid_list_lock);
kmem_cache_free(free_nid_slab, i);
spin_lock(&nm_i->free_nid_list_lock);
}
- f2fs_bug_on(nm_i->fcnt);
+ f2fs_bug_on(sbi, nm_i->fcnt);
spin_unlock(&nm_i->free_nid_list_lock);
/* destroy nat cache */
- write_lock(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_cache(nm_i,
nid, NATVEC_SIZE, natvec))) {
unsigned idx;
+
nid = nat_get_nid(natvec[found - 1]) + 1;
for (idx = 0; idx < found; idx++)
__del_from_nat_cache(nm_i, natvec[idx]);
}
- f2fs_bug_on(nm_i->nat_cnt);
- write_unlock(&nm_i->nat_tree_lock);
+ f2fs_bug_on(sbi, nm_i->nat_cnt);
+
+ /* destroy nat set cache */
+ nid = 0;
+ while ((found = __gang_lookup_nat_set(nm_i,
+ nid, SETVEC_SIZE, setvec))) {
+ unsigned idx;
+
+ nid = setvec[found - 1]->set + 1;
+ for (idx = 0; idx < found; idx++) {
+ /* entry_cnt is not zero, when cp_error was occurred */
+ f2fs_bug_on(sbi, !list_empty(&setvec[idx]->entry_list));
+ radix_tree_delete(&nm_i->nat_set_root, setvec[idx]->set);
+ kmem_cache_free(nat_entry_set_slab, setvec[idx]);
+ }
+ }
+ up_write(&nm_i->nat_tree_lock);
kfree(nm_i->nat_bitmap);
sbi->nm_info = NULL;
@@ -2056,17 +2048,17 @@
free_nid_slab = f2fs_kmem_cache_create("free_nid",
sizeof(struct free_nid));
if (!free_nid_slab)
- goto destory_nat_entry;
+ goto destroy_nat_entry;
nat_entry_set_slab = f2fs_kmem_cache_create("nat_entry_set",
sizeof(struct nat_entry_set));
if (!nat_entry_set_slab)
- goto destory_free_nid;
+ goto destroy_free_nid;
return 0;
-destory_free_nid:
+destroy_free_nid:
kmem_cache_destroy(free_nid_slab);
-destory_nat_entry:
+destroy_nat_entry:
kmem_cache_destroy(nat_entry_slab);
fail:
return -ENOMEM;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 8a116a4..f405bbf 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -25,10 +25,19 @@
/* 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
*/
@@ -37,12 +46,11 @@
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 */
+ unsigned char flag; /* for node information bits */
};
struct nat_entry {
struct list_head list; /* for clean or dirty nat list */
- bool checkpointed; /* whether it is checkpointed or not */
- bool fsync_done; /* whether the latest node has fsync mark */
struct node_info ni; /* in-memory node information */
};
@@ -55,18 +63,42 @@
#define nat_get_version(nat) (nat->ni.version)
#define nat_set_version(nat, v) (nat->ni.version = v)
-#define __set_nat_cache_dirty(nm_i, ne) \
- do { \
- ne->checkpointed = false; \
- list_move_tail(&ne->list, &nm_i->dirty_nat_entries); \
- } while (0)
-#define __clear_nat_cache_dirty(nm_i, ne) \
- do { \
- ne->checkpointed = true; \
- list_move_tail(&ne->list, &nm_i->nat_entries); \
- } while (0)
#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->ni.flag |= mask;
+ else
+ ne->ni.flag &= ~mask;
+}
+
+static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
+{
+ unsigned char mask = 0x01 << type;
+ return ne->ni.flag & mask;
+}
+
+static inline void nat_reset_flag(struct nat_entry *ne)
+{
+ /* these states can be set only after checkpoint was done */
+ set_nat_flag(ne, IS_CHECKPOINTED, true);
+ set_nat_flag(ne, HAS_FSYNCED_INODE, false);
+ set_nat_flag(ne, HAS_LAST_FSYNC, true);
+}
+
static inline void node_info_from_raw_nat(struct node_info *ni,
struct f2fs_nat_entry *raw_ne)
{
@@ -86,13 +118,15 @@
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 */
+ BASE_CHECK, /* check kernel status */
};
struct nat_entry_set {
- struct list_head set_list; /* link with all nat sets */
+ struct list_head set_list; /* link with other nat sets */
struct list_head entry_list; /* link with dirty nat entries */
- nid_t start_nid; /* start nid of nats in set */
+ nid_t set; /* set number*/
unsigned int entry_cnt; /* the # of nat entries in set */
};
@@ -110,18 +144,19 @@
int state; /* in use or not: NID_NEW or NID_ALLOC */
};
-static inline int next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
+static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *fnid;
- if (nm_i->fcnt <= 0)
- return -1;
spin_lock(&nm_i->free_nid_list_lock);
+ if (nm_i->fcnt <= 0) {
+ spin_unlock(&nm_i->free_nid_list_lock);
+ return;
+ }
fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
*nid = fnid->nid;
spin_unlock(&nm_i->free_nid_list_lock);
- return 0;
}
/*
@@ -171,21 +206,26 @@
{
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)
@@ -197,8 +237,7 @@
static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
struct f2fs_node *rn = F2FS_NODE(page);
rn->footer.cp_ver = ckpt->checkpoint_ver;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index c23d131..01a4e0b 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -14,6 +14,37 @@
#include "node.h"
#include "segment.h"
+/*
+ * Roll forward recovery scenarios.
+ *
+ * [Term] F: fsync_mark, D: dentry_mark
+ *
+ * 1. inode(x) | CP | inode(x) | dnode(F)
+ * -> Update the latest inode(x).
+ *
+ * 2. inode(x) | CP | inode(F) | dnode(F)
+ * -> No problem.
+ *
+ * 3. inode(x) | CP | dnode(F) | inode(x)
+ * -> Recover to the latest dnode(F), and drop the last inode(x)
+ *
+ * 4. inode(x) | CP | dnode(F) | inode(F)
+ * -> No problem.
+ *
+ * 5. CP | inode(x) | dnode(F)
+ * -> The inode(DF) was missing. Should drop this dnode(F).
+ *
+ * 6. CP | inode(DF) | dnode(F)
+ * -> No problem.
+ *
+ * 7. CP | dnode(F) | inode(DF)
+ * -> If f2fs_iget fails, then goto next to find inode(DF).
+ *
+ * 8. CP | dnode(F) | inode(x)
+ * -> If f2fs_iget fails, then goto next to find inode(DF).
+ * But it will fail due to no inode(DF).
+ */
+
static struct kmem_cache *fsync_entry_slab;
bool space_for_roll_forward(struct f2fs_sb_info *sbi)
@@ -36,7 +67,7 @@
return NULL;
}
-static int recover_dentry(struct page *ipage, struct inode *inode)
+static int recover_dentry(struct inode *inode, struct page *ipage)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
@@ -75,12 +106,12 @@
err = -EEXIST;
goto out_unmap_put;
}
- err = acquire_orphan_inode(F2FS_SB(inode->i_sb));
+ err = acquire_orphan_inode(F2FS_I_SB(inode));
if (err) {
iput(einode);
goto out_unmap_put;
}
- f2fs_delete_entry(de, page, einode);
+ f2fs_delete_entry(de, page, dir, einode);
iput(einode);
goto retry;
}
@@ -98,7 +129,7 @@
goto out;
out_unmap_put:
- kunmap(page);
+ f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
out_err:
iput(dir);
@@ -110,35 +141,28 @@
return err;
}
-static int recover_inode(struct inode *inode, struct page *node_page)
+static void recover_inode(struct inode *inode, struct page *page)
{
- struct f2fs_inode *raw_inode = F2FS_INODE(node_page);
+ struct f2fs_inode *raw = F2FS_INODE(page);
- if (!IS_INODE(node_page))
- return 0;
-
- inode->i_mode = le16_to_cpu(raw_inode->i_mode);
- i_size_write(inode, le64_to_cpu(raw_inode->i_size));
- inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
- inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
- inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
- inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
- inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
- inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
-
- if (is_dent_dnode(node_page))
- return recover_dentry(node_page, inode);
+ inode->i_mode = le16_to_cpu(raw->i_mode);
+ i_size_write(inode, le64_to_cpu(raw->i_size));
+ inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
+ inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
+ inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
+ inode->i_atime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+ inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
+ inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
- ino_of_node(node_page), raw_inode->i_name);
- return 0;
+ ino_of_node(page), F2FS_INODE(page)->i_name);
}
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
- struct page *page;
+ struct page *page = NULL;
block_t blkaddr;
int err = 0;
@@ -146,20 +170,15 @@
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- /* read node page */
- page = alloc_page(GFP_F2FS_ZERO);
- if (!page)
- return -ENOMEM;
- lock_page(page);
+ ra_meta_pages(sbi, blkaddr, 1, META_POR);
while (1) {
struct fsync_inode_entry *entry;
- err = f2fs_submit_page_bio(sbi, page, blkaddr, READ_SYNC);
- if (err)
- return err;
+ if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi))
+ return 0;
- lock_page(page);
+ page = get_meta_page(sbi, blkaddr);
if (cp_ver != cpver_of_node(page))
break;
@@ -180,33 +199,40 @@
}
/* add this fsync inode to the list */
- entry = kmem_cache_alloc(fsync_entry_slab, GFP_NOFS);
+ entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
if (!entry) {
err = -ENOMEM;
break;
}
-
+ /*
+ * CP | dnode(F) | inode(DF)
+ * For this case, we should not give up now.
+ */
entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
if (IS_ERR(entry->inode)) {
err = PTR_ERR(entry->inode);
kmem_cache_free(fsync_entry_slab, entry);
+ if (err == -ENOENT)
+ goto next;
break;
}
list_add_tail(&entry->list, head);
}
entry->blkaddr = blkaddr;
- err = recover_inode(entry->inode, page);
- if (err && err != -ENOENT)
- break;
+ if (IS_INODE(page)) {
+ entry->last_inode = blkaddr;
+ if (is_dent_dnode(page))
+ entry->last_dentry = blkaddr;
+ }
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
+ f2fs_put_page(page, 1);
+
+ ra_meta_pages_cond(sbi, blkaddr);
}
-
- unlock_page(page);
- __free_pages(page, 0);
-
+ f2fs_put_page(page, 1);
return err;
}
@@ -279,16 +305,30 @@
ino = ino_of_node(node_page);
f2fs_put_page(node_page, 1);
- /* Deallocate previous index in the node page */
- inode = f2fs_iget(sbi->sb, ino);
- if (IS_ERR(inode))
- return PTR_ERR(inode);
+ if (ino != dn->inode->i_ino) {
+ /* Deallocate previous index in the node page */
+ inode = f2fs_iget(sbi->sb, ino);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+ } else {
+ inode = dn->inode;
+ }
bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
- le16_to_cpu(sum.ofs_in_node);
+ le16_to_cpu(sum.ofs_in_node);
- truncate_hole(inode, bidx, bidx + 1);
- iput(inode);
+ if (ino != dn->inode->i_ino) {
+ truncate_hole(inode, bidx, bidx + 1);
+ 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);
+ }
return 0;
}
@@ -306,6 +346,10 @@
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;
}
@@ -331,8 +375,8 @@
f2fs_wait_on_page_writeback(dn.node_page, NODE);
get_node_info(sbi, dn.nid, &ni);
- f2fs_bug_on(ni.ino != ino_of_node(page));
- f2fs_bug_on(ofs_of_node(dn.node_page) != ofs_of_node(page));
+ 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++) {
block_t src, dest;
@@ -344,7 +388,7 @@
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
/* We should not get -ENOSPC */
- f2fs_bug_on(err);
+ f2fs_bug_on(sbi, err);
}
/* Check the previous node page having this index */
@@ -356,7 +400,8 @@
/* write dummy data page */
recover_data_page(sbi, NULL, &sum, src, dest);
- update_extent_cache(dest, &dn);
+ dn.data_blkaddr = dest;
+ update_extent_cache(&dn);
recovered++;
}
dn.ofs_in_node++;
@@ -386,7 +431,7 @@
{
unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
- struct page *page;
+ struct page *page = NULL;
int err = 0;
block_t blkaddr;
@@ -394,32 +439,43 @@
curseg = CURSEG_I(sbi, type);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- /* read node page */
- page = alloc_page(GFP_F2FS_ZERO);
- if (!page)
- return -ENOMEM;
-
- lock_page(page);
-
while (1) {
struct fsync_inode_entry *entry;
- err = f2fs_submit_page_bio(sbi, page, blkaddr, READ_SYNC);
- if (err)
- return err;
-
- lock_page(page);
-
- if (cp_ver != cpver_of_node(page))
+ if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi))
break;
+ ra_meta_pages_cond(sbi, blkaddr);
+
+ page = get_meta_page(sbi, blkaddr);
+
+ if (cp_ver != cpver_of_node(page)) {
+ f2fs_put_page(page, 1);
+ break;
+ }
+
entry = get_fsync_inode(head, ino_of_node(page));
if (!entry)
goto next;
-
+ /*
+ * inode(x) | CP | inode(x) | dnode(F)
+ * In this case, we can lose the latest inode(x).
+ * So, call recover_inode for the inode update.
+ */
+ if (entry->last_inode == blkaddr)
+ recover_inode(entry->inode, page);
+ if (entry->last_dentry == blkaddr) {
+ err = recover_dentry(entry->inode, page);
+ if (err) {
+ f2fs_put_page(page, 1);
+ break;
+ }
+ }
err = do_recover_data(sbi, entry->inode, page, blkaddr);
- if (err)
+ if (err) {
+ f2fs_put_page(page, 1);
break;
+ }
if (entry->blkaddr == blkaddr) {
iput(entry->inode);
@@ -429,11 +485,8 @@
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
+ f2fs_put_page(page, 1);
}
-
- unlock_page(page);
- __free_pages(page, 0);
-
if (!err)
allocate_new_segments(sbi);
return err;
@@ -441,7 +494,9 @@
int recover_fsync_data(struct f2fs_sb_info *sbi)
{
+ struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct list_head inode_list;
+ block_t blkaddr;
int err;
bool need_writecp = false;
@@ -453,7 +508,13 @@
INIT_LIST_HEAD(&inode_list);
/* step #1: find fsynced inode numbers */
- sbi->por_doing = true;
+ set_sbi_flag(sbi, SBI_POR_DOING);
+
+ /* prevent checkpoint */
+ mutex_lock(&sbi->cp_mutex);
+
+ blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+
err = find_fsync_dnodes(sbi, &inode_list);
if (err)
goto out;
@@ -466,12 +527,37 @@
/* step #2: recover data */
err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
if (!err)
- f2fs_bug_on(!list_empty(&inode_list));
+ f2fs_bug_on(sbi, !list_empty(&inode_list));
out:
destroy_fsync_dnodes(&inode_list);
kmem_cache_destroy(fsync_entry_slab);
- sbi->por_doing = false;
- if (!err && need_writecp)
- write_checkpoint(sbi, false);
+
+ /* truncate meta pages to be used by the recovery */
+ truncate_inode_pages_range(META_MAPPING(sbi),
+ MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
+
+ if (err) {
+ truncate_inode_pages(NODE_MAPPING(sbi), 0);
+ truncate_inode_pages(META_MAPPING(sbi), 0);
+ }
+
+ clear_sbi_flag(sbi, SBI_POR_DOING);
+ if (err) {
+ discard_next_dnode(sbi, blkaddr);
+
+ /* Flush all the NAT/SIT pages */
+ while (get_pages(sbi, F2FS_DIRTY_META))
+ sync_meta_pages(sbi, META, LONG_MAX);
+ set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
+ mutex_unlock(&sbi->cp_mutex);
+ } else if (need_writecp) {
+ struct cp_control cpc = {
+ .reason = CP_SYNC,
+ };
+ mutex_unlock(&sbi->cp_mutex);
+ write_checkpoint(sbi, &cpc);
+ } else {
+ mutex_unlock(&sbi->cp_mutex);
+ }
return err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index ed6a6ec..0dc8ee8 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -20,11 +20,73 @@
#include "f2fs.h"
#include "segment.h"
#include "node.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
#define __reverse_ffz(x) __reverse_ffs(~(x))
static struct kmem_cache *discard_entry_slab;
+static struct kmem_cache *sit_entry_set_slab;
+static struct kmem_cache *inmem_entry_slab;
+
+/**
+ * Copied from latest lib/llist.c
+ * llist_for_each_entry_safe - iterate over some deleted entries of
+ * lock-less list of given type
+ * safe against removal of list entry
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @node: the first entry of deleted list entries.
+ * @member: the name of the llist_node with the struct.
+ *
+ * In general, some entries of the lock-less list can be traversed
+ * safely only after being removed from list, so start with an entry
+ * instead of list head.
+ *
+ * If being used on entries deleted from lock-less list directly, the
+ * traverse order is from the newest to the oldest added entry. If
+ * you want to traverse from the oldest to the newest, you must
+ * reverse the order by yourself before traversing.
+ */
+#define llist_for_each_entry_safe(pos, n, node, member) \
+ for (pos = llist_entry((node), typeof(*pos), member); \
+ &pos->member != NULL && \
+ (n = llist_entry(pos->member.next, typeof(*n), member), true); \
+ pos = n)
+
+/**
+ * Copied from latest lib/llist.c
+ * llist_reverse_order - reverse order of a llist chain
+ * @head: first item of the list to be reversed
+ *
+ * Reverse the order of a chain of llist entries and return the
+ * new first entry.
+ */
+struct llist_node *llist_reverse_order(struct llist_node *head)
+{
+ struct llist_node *new_head = NULL;
+
+ while (head) {
+ struct llist_node *tmp = head;
+ head = head->next;
+ tmp->next = new_head;
+ new_head = tmp;
+ }
+
+ return new_head;
+}
+
+/**
+ * Copied from latest linux/list.h
+ * list_last_entry - get the last element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
/*
* __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
@@ -172,6 +234,90 @@
return result + __reverse_ffz(tmp);
}
+void register_inmem_page(struct inode *inode, struct page *page)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct inmem_pages *new;
+ int err;
+
+ SetPagePrivate(page);
+ f2fs_trace_pid(page);
+
+ new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
+
+ /* add atomic page indices to the list */
+ new->page = page;
+ INIT_LIST_HEAD(&new->list);
+retry:
+ /* increase reference count with clean state */
+ mutex_lock(&fi->inmem_lock);
+ err = radix_tree_insert(&fi->inmem_root, page->index, new);
+ if (err == -EEXIST) {
+ mutex_unlock(&fi->inmem_lock);
+ kmem_cache_free(inmem_entry_slab, new);
+ return;
+ } else if (err) {
+ mutex_unlock(&fi->inmem_lock);
+ goto retry;
+ }
+ get_page(page);
+ list_add_tail(&new->list, &fi->inmem_pages);
+ inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+ mutex_unlock(&fi->inmem_lock);
+}
+
+void commit_inmem_pages(struct inode *inode, bool abort)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct inmem_pages *cur, *tmp;
+ bool submit_bio = false;
+ struct f2fs_io_info fio = {
+ .type = DATA,
+ .rw = WRITE_SYNC | REQ_PRIO,
+ };
+
+ /*
+ * The abort is true only when f2fs_evict_inode is called.
+ * Basically, the f2fs_evict_inode doesn't produce any data writes, so
+ * that we don't need to call f2fs_balance_fs.
+ * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this
+ * inode becomes free by iget_locked in f2fs_iget.
+ */
+ if (!abort) {
+ f2fs_balance_fs(sbi);
+ f2fs_lock_op(sbi);
+ }
+
+ mutex_lock(&fi->inmem_lock);
+ list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
+ if (!abort) {
+ lock_page(cur->page);
+ if (cur->page->mapping == inode->i_mapping) {
+ f2fs_wait_on_page_writeback(cur->page, DATA);
+ if (clear_page_dirty_for_io(cur->page))
+ inode_dec_dirty_pages(inode);
+ do_write_data_page(cur->page, &fio);
+ submit_bio = true;
+ }
+ f2fs_put_page(cur->page, 1);
+ } else {
+ put_page(cur->page);
+ }
+ radix_tree_delete(&fi->inmem_root, cur->page->index);
+ list_del(&cur->list);
+ kmem_cache_free(inmem_entry_slab, cur);
+ dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+ }
+ mutex_unlock(&fi->inmem_lock);
+
+ if (!abort) {
+ f2fs_unlock_op(sbi);
+ if (submit_bio)
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ }
+}
+
/*
* This function balances dirty node and dentry pages.
* In addition, it controls garbage collection.
@@ -192,7 +338,8 @@
{
/* check the # of cached NAT entries and prefree segments */
if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) ||
- excess_prefree_segs(sbi))
+ excess_prefree_segs(sbi) ||
+ !available_free_memory(sbi, INO_ENTRIES))
f2fs_sync_fs(sbi->sb, true);
}
@@ -232,24 +379,20 @@
if (kthread_should_stop())
return 0;
- spin_lock(&fcc->issue_lock);
- if (fcc->issue_list) {
- fcc->dispatch_list = fcc->issue_list;
- fcc->issue_list = fcc->issue_tail = NULL;
- }
- spin_unlock(&fcc->issue_lock);
-
- if (fcc->dispatch_list) {
+ if (!llist_empty(&fcc->issue_list)) {
struct bio *bio = bio_alloc(GFP_NOIO, 0);
struct flush_cmd *cmd, *next;
int ret;
+ fcc->dispatch_list = llist_del_all(&fcc->issue_list);
+ fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
+
bio->bi_bdev = sbi->sb->s_bdev;
ret = __submit_bio_wait(WRITE_FLUSH, bio);
- for (cmd = fcc->dispatch_list; cmd; cmd = next) {
+ llist_for_each_entry_safe(cmd, next,
+ fcc->dispatch_list, llnode) {
cmd->ret = ret;
- next = cmd->next;
complete(&cmd->wait);
}
bio_put(bio);
@@ -257,7 +400,7 @@
}
wait_event_interruptible(*q,
- kthread_should_stop() || fcc->issue_list);
+ kthread_should_stop() || !llist_empty(&fcc->issue_list));
goto repeat;
}
@@ -276,15 +419,8 @@
return blkdev_issue_flush(sbi->sb->s_bdev, GFP_KERNEL, NULL);
init_completion(&cmd.wait);
- cmd.next = NULL;
- spin_lock(&fcc->issue_lock);
- if (fcc->issue_list)
- fcc->issue_tail->next = &cmd;
- else
- fcc->issue_list = &cmd;
- fcc->issue_tail = &cmd;
- spin_unlock(&fcc->issue_lock);
+ llist_add(&cmd.llnode, &fcc->issue_list);
if (!fcc->dispatch_list)
wake_up(&fcc->flush_wait_queue);
@@ -303,8 +439,8 @@
fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
if (!fcc)
return -ENOMEM;
- spin_lock_init(&fcc->issue_lock);
init_waitqueue_head(&fcc->flush_wait_queue);
+ init_llist_head(&fcc->issue_list);
SM_I(sbi)->cmd_control_info = fcc;
fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
@@ -344,6 +480,10 @@
struct seg_entry *sentry = get_seg_entry(sbi, segno);
enum dirty_type t = sentry->type;
+ if (unlikely(t >= DIRTY)) {
+ f2fs_bug_on(sbi, 1);
+ return;
+ }
if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]++;
}
@@ -403,17 +543,14 @@
static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
block_t blkstart, block_t blklen)
{
- sector_t start = SECTOR_FROM_BLOCK(sbi, blkstart);
- sector_t len = SECTOR_FROM_BLOCK(sbi, blklen);
+ sector_t start = SECTOR_FROM_BLOCK(blkstart);
+ sector_t len = SECTOR_FROM_BLOCK(blklen);
trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
}
-void discard_next_dnode(struct f2fs_sb_info *sbi)
+void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
{
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
- block_t blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
-
if (f2fs_issue_discard(sbi, blkaddr, 1)) {
struct page *page = grab_meta_page(sbi, blkaddr);
/* zero-filled page */
@@ -422,44 +559,98 @@
}
}
-static void add_discard_addrs(struct f2fs_sb_info *sbi,
- unsigned int segno, struct seg_entry *se)
+static void __add_discard_entry(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc, unsigned int start, unsigned int end)
{
struct list_head *head = &SM_I(sbi)->discard_list;
- struct discard_entry *new;
+ struct discard_entry *new, *last;
+
+ if (!list_empty(head)) {
+ last = list_last_entry(head, struct discard_entry, list);
+ if (START_BLOCK(sbi, cpc->trim_start) + start ==
+ last->blkaddr + last->len) {
+ last->len += end - start;
+ goto done;
+ }
+ }
+
+ new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
+ INIT_LIST_HEAD(&new->list);
+ new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start;
+ new->len = end - start;
+ list_add_tail(&new->list, head);
+done:
+ SM_I(sbi)->nr_discards += end - start;
+ cpc->trimmed += end - start;
+}
+
+static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+{
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
int max_blocks = sbi->blocks_per_seg;
+ struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
- unsigned long dmap[entries];
+ unsigned long *dmap = SIT_I(sbi)->tmp_map;
unsigned int start = 0, end = -1;
+ bool force = (cpc->reason == CP_DISCARD);
int i;
- if (!test_opt(sbi, DISCARD))
+ if (!force && (!test_opt(sbi, DISCARD) ||
+ SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards))
return;
+ if (force && !se->valid_blocks) {
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ /*
+ * if this segment is registered in the prefree list, then
+ * we should skip adding a discard candidate, and let the
+ * checkpoint do that later.
+ */
+ mutex_lock(&dirty_i->seglist_lock);
+ if (test_bit(cpc->trim_start, dirty_i->dirty_segmap[PRE])) {
+ mutex_unlock(&dirty_i->seglist_lock);
+ cpc->trimmed += sbi->blocks_per_seg;
+ return;
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
+
+ __add_discard_entry(sbi, cpc, 0, sbi->blocks_per_seg);
+ return;
+ }
+
/* zero block will be discarded through the prefree list */
if (!se->valid_blocks || se->valid_blocks == max_blocks)
return;
/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
for (i = 0; i < entries; i++)
- dmap[i] = (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
+ dmap[i] = force ? ~ckpt_map[i] :
+ (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
- while (SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
+ while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
start = __find_rev_next_bit(dmap, max_blocks, end + 1);
if (start >= max_blocks)
break;
end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
- new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
- INIT_LIST_HEAD(&new->list);
- new->blkaddr = START_BLOCK(sbi, segno) + start;
- new->len = end - start;
+ if (end - start < cpc->trim_minlen)
+ continue;
- list_add_tail(&new->list, head);
- SM_I(sbi)->nr_discards += end - start;
+ __add_discard_entry(sbi, cpc, start, end);
+ }
+}
+
+void release_discard_addrs(struct f2fs_sb_info *sbi)
+{
+ struct list_head *head = &(SM_I(sbi)->discard_list);
+ struct discard_entry *entry, *this;
+
+ /* drop caches */
+ list_for_each_entry_safe(entry, this, head, list) {
+ list_del(&entry->list);
+ kmem_cache_free(discard_entry_slab, entry);
}
}
@@ -470,10 +661,9 @@
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned int segno;
- unsigned int total_segs = TOTAL_SEGS(sbi);
mutex_lock(&dirty_i->seglist_lock);
- for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], total_segs)
+ for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], MAIN_SEGS(sbi))
__set_test_and_free(sbi, segno);
mutex_unlock(&dirty_i->seglist_lock);
}
@@ -484,17 +674,17 @@
struct discard_entry *entry, *this;
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
- unsigned int total_segs = TOTAL_SEGS(sbi);
unsigned int start = 0, end = -1;
mutex_lock(&dirty_i->seglist_lock);
while (1) {
int i;
- start = find_next_bit(prefree_map, total_segs, end + 1);
- if (start >= total_segs)
+ start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1);
+ if (start >= MAIN_SEGS(sbi))
break;
- end = find_next_zero_bit(prefree_map, total_segs, start + 1);
+ end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi),
+ start + 1);
for (i = start; i < end; i++)
clear_bit(i, prefree_map);
@@ -518,11 +708,16 @@
}
}
-static void __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
+static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap))
+
+ if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap)) {
sit_i->dirty_sentries++;
+ return false;
+ }
+
+ return true;
}
static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type,
@@ -546,7 +741,7 @@
new_vblocks = se->valid_blocks + del;
offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
- f2fs_bug_on((new_vblocks >> (sizeof(unsigned short) << 3) ||
+ f2fs_bug_on(sbi, (new_vblocks >> (sizeof(unsigned short) << 3) ||
(new_vblocks > sbi->blocks_per_seg)));
se->valid_blocks = new_vblocks;
@@ -555,11 +750,11 @@
/* Update valid block bitmap */
if (del > 0) {
- if (f2fs_set_bit(offset, se->cur_valid_map))
- BUG();
+ if (f2fs_test_and_set_bit(offset, se->cur_valid_map))
+ f2fs_bug_on(sbi, 1);
} else {
- if (!f2fs_clear_bit(offset, se->cur_valid_map))
- BUG();
+ if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map))
+ f2fs_bug_on(sbi, 1);
}
if (!f2fs_test_bit(offset, se->ckpt_valid_map))
se->ckpt_valid_blocks += del;
@@ -588,7 +783,7 @@
unsigned int segno = GET_SEGNO(sbi, addr);
struct sit_info *sit_i = SIT_I(sbi);
- f2fs_bug_on(addr == NULL_ADDR);
+ f2fs_bug_on(sbi, addr == NULL_ADDR);
if (addr == NEW_ADDR)
return;
@@ -618,7 +813,7 @@
/*
* Calculate the number of current summary pages for writing
*/
-int npages_for_summary_flush(struct f2fs_sb_info *sbi)
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
{
int valid_sum_count = 0;
int i, sum_in_page;
@@ -626,8 +821,13 @@
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
if (sbi->ckpt->alloc_type[i] == SSR)
valid_sum_count += sbi->blocks_per_seg;
- else
- valid_sum_count += curseg_blkoff(sbi, i);
+ else {
+ if (for_ra)
+ valid_sum_count += le16_to_cpu(
+ F2FS_CKPT(sbi)->cur_data_blkoff[i]);
+ else
+ valid_sum_count += curseg_blkoff(sbi, i);
+ }
}
sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
@@ -664,7 +864,7 @@
unsigned int segno = curseg->segno + 1;
struct free_segmap_info *free_i = FREE_I(sbi);
- if (segno < TOTAL_SEGS(sbi) && segno % sbi->segs_per_sec)
+ if (segno < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec)
return !test_bit(segno, free_i->free_segmap);
return 0;
}
@@ -678,7 +878,7 @@
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int segno, secno, zoneno;
- unsigned int total_zones = TOTAL_SECS(sbi) / sbi->secs_per_zone;
+ unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone;
unsigned int hint = *newseg / sbi->segs_per_sec;
unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg);
unsigned int left_start = hint;
@@ -686,22 +886,22 @@
int go_left = 0;
int i;
- write_lock(&free_i->segmap_lock);
+ spin_lock(&free_i->segmap_lock);
if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
segno = find_next_zero_bit(free_i->free_segmap,
- TOTAL_SEGS(sbi), *newseg + 1);
+ MAIN_SEGS(sbi), *newseg + 1);
if (segno - *newseg < sbi->segs_per_sec -
(*newseg % sbi->segs_per_sec))
goto got_it;
}
find_other_zone:
- secno = find_next_zero_bit(free_i->free_secmap, TOTAL_SECS(sbi), hint);
- if (secno >= TOTAL_SECS(sbi)) {
+ secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
+ if (secno >= MAIN_SECS(sbi)) {
if (dir == ALLOC_RIGHT) {
secno = find_next_zero_bit(free_i->free_secmap,
- TOTAL_SECS(sbi), 0);
- f2fs_bug_on(secno >= TOTAL_SECS(sbi));
+ MAIN_SECS(sbi), 0);
+ f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi));
} else {
go_left = 1;
left_start = hint - 1;
@@ -716,8 +916,8 @@
continue;
}
left_start = find_next_zero_bit(free_i->free_secmap,
- TOTAL_SECS(sbi), 0);
- f2fs_bug_on(left_start >= TOTAL_SECS(sbi));
+ MAIN_SECS(sbi), 0);
+ f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi));
break;
}
secno = left_start;
@@ -756,10 +956,10 @@
}
got_it:
/* set it as dirty segment in free segmap */
- f2fs_bug_on(test_bit(segno, free_i->free_segmap));
+ f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
__set_inuse(sbi, segno);
*newseg = segno;
- write_unlock(&free_i->segmap_lock);
+ spin_unlock(&free_i->segmap_lock);
}
static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
@@ -810,7 +1010,7 @@
{
struct seg_entry *se = get_seg_entry(sbi, seg->segno);
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
- unsigned long target_map[entries];
+ unsigned long *target_map = SIT_I(sbi)->tmp_map;
unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
int i, pos;
@@ -910,24 +1110,66 @@
stat_inc_seg_type(sbi, curseg);
}
+static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type)
+{
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
+ unsigned int old_segno;
+
+ old_segno = curseg->segno;
+ SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
+ locate_dirty_segment(sbi, old_segno);
+}
+
void allocate_new_segments(struct f2fs_sb_info *sbi)
{
- struct curseg_info *curseg;
- unsigned int old_curseg;
int i;
- for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
- curseg = CURSEG_I(sbi, i);
- old_curseg = curseg->segno;
- SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
- locate_dirty_segment(sbi, old_curseg);
- }
+ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
+ __allocate_new_segments(sbi, i);
}
static const struct segment_allocation default_salloc_ops = {
.allocate_segment = allocate_segment_by_default,
};
+int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
+{
+ __u64 start = F2FS_BYTES_TO_BLK(range->start);
+ __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
+ unsigned int start_segno, end_segno;
+ struct cp_control cpc;
+
+ if (range->minlen > SEGMENT_SIZE(sbi) || start >= MAX_BLKADDR(sbi) ||
+ range->len < sbi->blocksize)
+ return -EINVAL;
+
+ cpc.trimmed = 0;
+ if (end <= MAIN_BLKADDR(sbi))
+ goto out;
+
+ /* start/end segment number in main_area */
+ start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
+ end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
+ GET_SEGNO(sbi, end);
+ cpc.reason = CP_DISCARD;
+ cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen);
+
+ /* do checkpoint to issue discard commands safely */
+ for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
+ cpc.trim_start = start_segno;
+ cpc.trim_end = min_t(unsigned int, rounddown(start_segno +
+ BATCHED_TRIM_SEGMENTS(sbi),
+ sbi->segs_per_sec) - 1, end_segno);
+
+ mutex_lock(&sbi->gc_mutex);
+ write_checkpoint(sbi, &cpc);
+ mutex_unlock(&sbi->gc_mutex);
+ }
+out:
+ range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
+ return 0;
+}
+
static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -954,8 +1196,8 @@
else
return CURSEG_COLD_DATA;
} else {
- if (IS_DNODE(page) && !is_cold_node(page))
- return CURSEG_HOT_NODE;
+ if (IS_DNODE(page) && is_cold_node(page))
+ return CURSEG_WARM_NODE;
else
return CURSEG_COLD_NODE;
}
@@ -983,15 +1225,15 @@
static int __get_segment_type(struct page *page, enum page_type p_type)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
- switch (sbi->active_logs) {
+ switch (F2FS_P_SB(page)->active_logs) {
case 2:
return __get_segment_type_2(page, p_type);
case 4:
return __get_segment_type_4(page, p_type);
}
/* NR_CURSEG_TYPE(6) logs by default */
- f2fs_bug_on(sbi->active_logs != NR_CURSEG_TYPE);
+ f2fs_bug_on(F2FS_P_SB(page),
+ F2FS_P_SB(page)->active_logs != NR_CURSEG_TYPE);
return __get_segment_type_6(page, p_type);
}
@@ -1001,11 +1243,18 @@
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg;
+ bool direct_io = (type == CURSEG_DIRECT_IO);
+
+ type = direct_io ? CURSEG_WARM_DATA : type;
curseg = CURSEG_I(sbi, type);
mutex_lock(&curseg->curseg_mutex);
+ /* direct_io'ed data is aligned to the segment for better performance */
+ if (direct_io && curseg->next_blkoff)
+ __allocate_new_segments(sbi, type);
+
*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
/*
@@ -1037,57 +1286,55 @@
}
static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
- block_t old_blkaddr, block_t *new_blkaddr,
- struct f2fs_summary *sum, struct f2fs_io_info *fio)
+ struct f2fs_summary *sum,
+ struct f2fs_io_info *fio)
{
int type = __get_segment_type(page, fio->type);
- allocate_data_block(sbi, page, old_blkaddr, new_blkaddr, sum, type);
+ allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type);
/* writeout dirty page into bdev */
- f2fs_submit_page_mbio(sbi, page, *new_blkaddr, fio);
+ f2fs_submit_page_mbio(sbi, page, fio);
}
void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_io_info fio = {
.type = META,
- .rw = WRITE_SYNC | REQ_META | REQ_PRIO
+ .rw = WRITE_SYNC | REQ_META | REQ_PRIO,
+ .blk_addr = page->index,
};
set_page_writeback(page);
- f2fs_submit_page_mbio(sbi, page, page->index, &fio);
+ f2fs_submit_page_mbio(sbi, page, &fio);
}
void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
- struct f2fs_io_info *fio,
- unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr)
+ unsigned int nid, struct f2fs_io_info *fio)
{
struct f2fs_summary sum;
set_summary(&sum, nid, 0, 0);
- do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, fio);
+ do_write_page(sbi, page, &sum, fio);
}
void write_data_page(struct page *page, struct dnode_of_data *dn,
- block_t *new_blkaddr, struct f2fs_io_info *fio)
+ struct f2fs_io_info *fio)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
- f2fs_bug_on(dn->data_blkaddr == NULL_ADDR);
+ f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
get_node_info(sbi, dn->nid, &ni);
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
-
- do_write_page(sbi, page, dn->data_blkaddr, new_blkaddr, &sum, fio);
+ do_write_page(sbi, page, &sum, fio);
+ dn->data_blkaddr = fio->blk_addr;
}
-void rewrite_data_page(struct page *page, block_t old_blkaddr,
- struct f2fs_io_info *fio)
+void rewrite_data_page(struct page *page, struct f2fs_io_info *fio)
{
- struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- f2fs_submit_page_mbio(sbi, page, old_blkaddr, fio);
+ stat_inc_inplace_blocks(F2FS_P_SB(page));
+ f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio);
}
void recover_data_page(struct f2fs_sb_info *sbi,
@@ -1160,8 +1407,9 @@
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type)
{
- struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
if (PageWriteback(page)) {
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+
if (is_merged_page(sbi, page, type))
f2fs_submit_merged_bio(sbi, type, WRITE);
wait_on_page_writeback(page);
@@ -1244,7 +1492,7 @@
segno = le32_to_cpu(ckpt->cur_data_segno[type]);
blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
CURSEG_HOT_DATA]);
- if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+ if (__exist_node_summaries(sbi))
blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
else
blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
@@ -1253,7 +1501,7 @@
CURSEG_HOT_NODE]);
blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
CURSEG_HOT_NODE]);
- if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+ if (__exist_node_summaries(sbi))
blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
type - CURSEG_HOT_NODE);
else
@@ -1264,7 +1512,7 @@
sum = (struct f2fs_summary_block *)page_address(new);
if (IS_NODESEG(type)) {
- if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) {
+ if (__exist_node_summaries(sbi)) {
struct f2fs_summary *ns = &sum->entries[0];
int i;
for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
@@ -1301,12 +1549,22 @@
int err;
if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
+ int npages = npages_for_summary_flush(sbi, true);
+
+ if (npages >= 2)
+ ra_meta_pages(sbi, start_sum_block(sbi), npages,
+ META_CP);
+
/* restore for compacted data summary */
if (read_compacted_summaries(sbi))
return -EINVAL;
type = CURSEG_HOT_NODE;
}
+ if (__exist_node_summaries(sbi))
+ ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
+ NR_CURSEG_TYPE - type, META_CP);
+
for (; type <= CURSEG_COLD_NODE; type++) {
err = read_normal_summaries(sbi, type);
if (err)
@@ -1400,8 +1658,7 @@
void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
- if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
- write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
+ write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
}
int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
@@ -1429,17 +1686,7 @@
static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
unsigned int segno)
{
- struct sit_info *sit_i = SIT_I(sbi);
- unsigned int offset = SIT_BLOCK_OFFSET(sit_i, segno);
- block_t blk_addr = sit_i->sit_base_addr + offset;
-
- check_seg_range(sbi, segno);
-
- /* calculate sit block address */
- if (f2fs_test_bit(offset, sit_i->sit_bitmap))
- blk_addr += sit_i->sit_blocks;
-
- return get_meta_page(sbi, blk_addr);
+ return get_meta_page(sbi, current_sit_addr(sbi, segno));
}
static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
@@ -1456,7 +1703,7 @@
/* get current sit block page without lock */
src_page = get_meta_page(sbi, src_off);
dst_page = grab_meta_page(sbi, dst_off);
- f2fs_bug_on(PageDirty(src_page));
+ f2fs_bug_on(sbi, PageDirty(src_page));
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
@@ -1470,101 +1717,192 @@
return dst_page;
}
-static bool flush_sits_in_journal(struct f2fs_sb_info *sbi)
+static struct sit_entry_set *grab_sit_entry_set(void)
+{
+ struct sit_entry_set *ses =
+ f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_ATOMIC);
+
+ ses->entry_cnt = 0;
+ INIT_LIST_HEAD(&ses->set_list);
+ return ses;
+}
+
+static void release_sit_entry_set(struct sit_entry_set *ses)
+{
+ list_del(&ses->set_list);
+ kmem_cache_free(sit_entry_set_slab, ses);
+}
+
+static void adjust_sit_entry_set(struct sit_entry_set *ses,
+ struct list_head *head)
+{
+ struct sit_entry_set *next = ses;
+
+ if (list_is_last(&ses->set_list, head))
+ return;
+
+ list_for_each_entry_continue(next, head, set_list)
+ if (ses->entry_cnt <= next->entry_cnt)
+ break;
+
+ list_move_tail(&ses->set_list, &next->set_list);
+}
+
+static void add_sit_entry(unsigned int segno, struct list_head *head)
+{
+ struct sit_entry_set *ses;
+ unsigned int start_segno = START_SEGNO(segno);
+
+ list_for_each_entry(ses, head, set_list) {
+ if (ses->start_segno == start_segno) {
+ ses->entry_cnt++;
+ adjust_sit_entry_set(ses, head);
+ return;
+ }
+ }
+
+ ses = grab_sit_entry_set();
+
+ ses->start_segno = start_segno;
+ ses->entry_cnt++;
+ list_add(&ses->set_list, head);
+}
+
+static void add_sits_in_set(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_sm_info *sm_info = SM_I(sbi);
+ struct list_head *set_list = &sm_info->sit_entry_set;
+ unsigned long *bitmap = SIT_I(sbi)->dirty_sentries_bitmap;
+ unsigned int segno;
+
+ for_each_set_bit(segno, bitmap, MAIN_SEGS(sbi))
+ add_sit_entry(segno, set_list);
+}
+
+static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
struct f2fs_summary_block *sum = curseg->sum_blk;
int i;
- /*
- * If the journal area in the current summary is full of sit entries,
- * all the sit entries will be flushed. Otherwise the sit entries
- * are not able to replace with newly hot sit entries.
- */
- if (sits_in_cursum(sum) >= SIT_JOURNAL_ENTRIES) {
- for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
- unsigned int segno;
- segno = le32_to_cpu(segno_in_journal(sum, i));
- __mark_sit_entry_dirty(sbi, segno);
- }
- update_sits_in_cursum(sum, -sits_in_cursum(sum));
- return true;
+ for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
+ unsigned int segno;
+ bool dirtied;
+
+ segno = le32_to_cpu(segno_in_journal(sum, i));
+ dirtied = __mark_sit_entry_dirty(sbi, segno);
+
+ if (!dirtied)
+ add_sit_entry(segno, &SM_I(sbi)->sit_entry_set);
}
- return false;
+ update_sits_in_cursum(sum, -sits_in_cursum(sum));
}
/*
* CP calls this function, which flushes SIT entries including sit_journal,
* and moves prefree segs to free segs.
*/
-void flush_sit_entries(struct f2fs_sb_info *sbi)
+void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
struct f2fs_summary_block *sum = curseg->sum_blk;
- unsigned long nsegs = TOTAL_SEGS(sbi);
- struct page *page = NULL;
- struct f2fs_sit_block *raw_sit = NULL;
- unsigned int start = 0, end = 0;
- unsigned int segno;
- bool flushed;
+ struct sit_entry_set *ses, *tmp;
+ struct list_head *head = &SM_I(sbi)->sit_entry_set;
+ bool to_journal = true;
+ struct seg_entry *se;
mutex_lock(&curseg->curseg_mutex);
mutex_lock(&sit_i->sentry_lock);
/*
- * "flushed" indicates whether sit entries in journal are flushed
- * to the SIT area or not.
+ * add and account sit entries of dirty bitmap in sit entry
+ * set temporarily
*/
- flushed = flush_sits_in_journal(sbi);
+ add_sits_in_set(sbi);
- for_each_set_bit(segno, bitmap, nsegs) {
- struct seg_entry *se = get_seg_entry(sbi, segno);
- int sit_offset, offset;
+ /*
+ * if there are no enough space in journal to store dirty sit
+ * entries, remove all entries from journal and add and account
+ * them in sit entry set.
+ */
+ if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL))
+ remove_sits_in_journal(sbi);
- sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
+ if (!sit_i->dirty_sentries)
+ goto out;
- /* add discard candidates */
- if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards)
- add_discard_addrs(sbi, segno, se);
+ /*
+ * there are two steps to flush sit entries:
+ * #1, flush sit entries to journal in current cold data summary block.
+ * #2, flush sit entries to sit page.
+ */
+ list_for_each_entry_safe(ses, tmp, head, set_list) {
+ struct page *page = NULL;
+ struct f2fs_sit_block *raw_sit = NULL;
+ unsigned int start_segno = ses->start_segno;
+ unsigned int end = min(start_segno + SIT_ENTRY_PER_BLOCK,
+ (unsigned long)MAIN_SEGS(sbi));
+ unsigned int segno = start_segno;
- if (flushed)
- goto to_sit_page;
+ if (to_journal &&
+ !__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL))
+ to_journal = false;
- offset = lookup_journal_in_cursum(sum, SIT_JOURNAL, segno, 1);
- if (offset >= 0) {
- segno_in_journal(sum, offset) = cpu_to_le32(segno);
- seg_info_to_raw_sit(se, &sit_in_journal(sum, offset));
- goto flush_done;
- }
-to_sit_page:
- if (!page || (start > segno) || (segno > end)) {
- if (page) {
- f2fs_put_page(page, 1);
- page = NULL;
- }
-
- start = START_SEGNO(sit_i, segno);
- end = start + SIT_ENTRY_PER_BLOCK - 1;
-
- /* read sit block that will be updated */
- page = get_next_sit_page(sbi, start);
+ if (!to_journal) {
+ page = get_next_sit_page(sbi, start_segno);
raw_sit = page_address(page);
}
- /* udpate entry in SIT block */
- seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]);
-flush_done:
- __clear_bit(segno, bitmap);
- sit_i->dirty_sentries--;
+ /* flush dirty sit entries in region of current sit set */
+ for_each_set_bit_from(segno, bitmap, end) {
+ int offset, sit_offset;
+
+ se = get_seg_entry(sbi, segno);
+
+ /* add discard candidates */
+ if (cpc->reason != CP_DISCARD) {
+ cpc->trim_start = segno;
+ add_discard_addrs(sbi, cpc);
+ }
+
+ if (to_journal) {
+ offset = lookup_journal_in_cursum(sum,
+ SIT_JOURNAL, segno, 1);
+ f2fs_bug_on(sbi, offset < 0);
+ segno_in_journal(sum, offset) =
+ cpu_to_le32(segno);
+ seg_info_to_raw_sit(se,
+ &sit_in_journal(sum, offset));
+ } else {
+ sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
+ seg_info_to_raw_sit(se,
+ &raw_sit->entries[sit_offset]);
+ }
+
+ __clear_bit(segno, bitmap);
+ sit_i->dirty_sentries--;
+ ses->entry_cnt--;
+ }
+
+ if (!to_journal)
+ f2fs_put_page(page, 1);
+
+ f2fs_bug_on(sbi, ses->entry_cnt);
+ release_sit_entry_set(ses);
+ }
+
+ f2fs_bug_on(sbi, !list_empty(head));
+ f2fs_bug_on(sbi, sit_i->dirty_sentries);
+out:
+ if (cpc->reason == CP_DISCARD) {
+ for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++)
+ add_discard_addrs(sbi, cpc);
}
mutex_unlock(&sit_i->sentry_lock);
mutex_unlock(&curseg->curseg_mutex);
- /* writeout last modified SIT block */
- f2fs_put_page(page, 1);
-
set_prefree_as_free_segments(sbi);
}
@@ -1584,16 +1922,16 @@
SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries = vzalloc(TOTAL_SEGS(sbi) * sizeof(struct seg_entry));
+ sit_i->sentries = vzalloc(MAIN_SEGS(sbi) * sizeof(struct seg_entry));
if (!sit_i->sentries)
return -ENOMEM;
- bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+ bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL);
if (!sit_i->dirty_sentries_bitmap)
return -ENOMEM;
- for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+ for (start = 0; start < MAIN_SEGS(sbi); start++) {
sit_i->sentries[start].cur_valid_map
= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
sit_i->sentries[start].ckpt_valid_map
@@ -1603,8 +1941,12 @@
return -ENOMEM;
}
+ sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ if (!sit_i->tmp_map)
+ return -ENOMEM;
+
if (sbi->segs_per_sec > 1) {
- sit_i->sec_entries = vzalloc(TOTAL_SECS(sbi) *
+ sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) *
sizeof(struct sec_entry));
if (!sit_i->sec_entries)
return -ENOMEM;
@@ -1639,7 +1981,6 @@
static int build_free_segmap(struct f2fs_sb_info *sbi)
{
- struct f2fs_sm_info *sm_info = SM_I(sbi);
struct free_segmap_info *free_i;
unsigned int bitmap_size, sec_bitmap_size;
@@ -1650,12 +1991,12 @@
SM_I(sbi)->free_info = free_i;
- bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+ bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL);
if (!free_i->free_segmap)
return -ENOMEM;
- sec_bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
+ sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL);
if (!free_i->free_secmap)
return -ENOMEM;
@@ -1665,11 +2006,10 @@
memset(free_i->free_secmap, 0xff, sec_bitmap_size);
/* init free segmap information */
- free_i->start_segno =
- (unsigned int) GET_SEGNO_FROM_SEG0(sbi, sm_info->main_blkaddr);
+ free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi));
free_i->free_segments = 0;
free_i->free_sections = 0;
- rwlock_init(&free_i->segmap_lock);
+ spin_lock_init(&free_i->segmap_lock);
return 0;
}
@@ -1703,7 +2043,7 @@
int sit_blk_cnt = SIT_BLK_CNT(sbi);
unsigned int i, start, end;
unsigned int readed, start_blk = 0;
- int nrpages = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ int nrpages = MAX_BIO_BLOCKS(sbi);
do {
readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT);
@@ -1711,7 +2051,7 @@
start = start_blk * sit_i->sents_per_block;
end = (start_blk + readed) * sit_i->sents_per_block;
- for (; start < end && start < TOTAL_SEGS(sbi); start++) {
+ for (; start < end && start < MAIN_SEGS(sbi); start++) {
struct seg_entry *se = &sit_i->sentries[start];
struct f2fs_sit_block *sit_blk;
struct f2fs_sit_entry sit;
@@ -1749,7 +2089,7 @@
unsigned int start;
int type;
- for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+ for (start = 0; start < MAIN_SEGS(sbi); start++) {
struct seg_entry *sentry = get_seg_entry(sbi, start);
if (!sentry->valid_blocks)
__set_free(sbi, start);
@@ -1766,18 +2106,22 @@
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int segno = 0, offset = 0, total_segs = TOTAL_SEGS(sbi);
+ unsigned int segno = 0, offset = 0;
unsigned short valid_blocks;
while (1) {
/* find dirty segment based on free segmap */
- segno = find_next_inuse(free_i, total_segs, offset);
- if (segno >= total_segs)
+ segno = find_next_inuse(free_i, MAIN_SEGS(sbi), offset);
+ if (segno >= MAIN_SEGS(sbi))
break;
offset = segno + 1;
valid_blocks = get_valid_blocks(sbi, segno, 0);
- if (valid_blocks >= sbi->blocks_per_seg || !valid_blocks)
+ if (valid_blocks == sbi->blocks_per_seg || !valid_blocks)
continue;
+ if (valid_blocks > sbi->blocks_per_seg) {
+ f2fs_bug_on(sbi, 1);
+ continue;
+ }
mutex_lock(&dirty_i->seglist_lock);
__locate_dirty_segment(sbi, segno, DIRTY);
mutex_unlock(&dirty_i->seglist_lock);
@@ -1787,7 +2131,7 @@
static int init_victim_secmap(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
+ unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL);
if (!dirty_i->victim_secmap)
@@ -1808,7 +2152,7 @@
SM_I(sbi)->dirty_info = dirty_i;
mutex_init(&dirty_i->seglist_lock);
- bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+ bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
for (i = 0; i < NR_DIRTY_TYPE; i++) {
dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL);
@@ -1832,7 +2176,7 @@
sit_i->min_mtime = LLONG_MAX;
- for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) {
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
unsigned int i;
unsigned long long mtime = 0;
@@ -1870,13 +2214,18 @@
sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
sm_info->rec_prefree_segments = sm_info->main_segments *
DEF_RECLAIM_PREFREE_SEGMENTS / 100;
- sm_info->ipu_policy = F2FS_IPU_DISABLE;
+ sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
+ sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
INIT_LIST_HEAD(&sm_info->discard_list);
sm_info->nr_discards = 0;
sm_info->max_discards = 0;
+ sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
+
+ INIT_LIST_HEAD(&sm_info->sit_entry_set);
+
if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
err = create_flush_cmd_control(sbi);
if (err)
@@ -1972,11 +2321,13 @@
return;
if (sit_i->sentries) {
- for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+ for (start = 0; start < MAIN_SEGS(sbi); start++) {
kfree(sit_i->sentries[start].cur_valid_map);
kfree(sit_i->sentries[start].ckpt_valid_map);
}
}
+ kfree(sit_i->tmp_map);
+
vfree(sit_i->sentries);
vfree(sit_i->sec_entries);
kfree(sit_i->dirty_sentries_bitmap);
@@ -2006,11 +2357,30 @@
discard_entry_slab = f2fs_kmem_cache_create("discard_entry",
sizeof(struct discard_entry));
if (!discard_entry_slab)
- return -ENOMEM;
+ goto fail;
+
+ sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set",
+ sizeof(struct sit_entry_set));
+ if (!sit_entry_set_slab)
+ goto destory_discard_entry;
+
+ inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry",
+ sizeof(struct inmem_pages));
+ if (!inmem_entry_slab)
+ goto destroy_sit_entry_set;
return 0;
+
+destroy_sit_entry_set:
+ kmem_cache_destroy(sit_entry_set_slab);
+destory_discard_entry:
+ kmem_cache_destroy(discard_entry_slab);
+fail:
+ return -ENOMEM;
}
void destroy_segment_manager_caches(void)
{
+ kmem_cache_destroy(sit_entry_set_slab);
kmem_cache_destroy(discard_entry_slab);
+ kmem_cache_destroy(inmem_entry_slab);
}
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index ff48325..7fd3511 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -45,16 +45,26 @@
(secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
sbi->segs_per_sec)) \
-#define START_BLOCK(sbi, segno) \
- (SM_I(sbi)->seg0_blkaddr + \
+#define MAIN_BLKADDR(sbi) (SM_I(sbi)->main_blkaddr)
+#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr)
+
+#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
+#define MAIN_SECS(sbi) (sbi->total_sections)
+
+#define TOTAL_SEGS(sbi) (SM_I(sbi)->segment_count)
+#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)
+
+#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
+#define SEGMENT_SIZE(sbi) (1ULL << (sbi->log_blocksize + \
+ sbi->log_blocks_per_seg))
+
+#define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \
(GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg))
+
#define NEXT_FREE_BLKADDR(sbi, curseg) \
(START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff)
-#define MAIN_BASE_BLOCK(sbi) (SM_I(sbi)->main_blkaddr)
-
-#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) \
- ((blk_addr) - SM_I(sbi)->seg0_blkaddr)
+#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi))
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \
(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \
@@ -77,23 +87,21 @@
#define SIT_ENTRY_OFFSET(sit_i, segno) \
(segno % sit_i->sents_per_block)
-#define SIT_BLOCK_OFFSET(sit_i, segno) \
+#define SIT_BLOCK_OFFSET(segno) \
(segno / SIT_ENTRY_PER_BLOCK)
-#define START_SEGNO(sit_i, segno) \
- (SIT_BLOCK_OFFSET(sit_i, segno) * SIT_ENTRY_PER_BLOCK)
+#define START_SEGNO(segno) \
+ (SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
#define SIT_BLK_CNT(sbi) \
- ((TOTAL_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
+ ((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
#define f2fs_bitmap_size(nr) \
(BITS_TO_LONGS(nr) * sizeof(unsigned long))
-#define TOTAL_SEGS(sbi) (SM_I(sbi)->main_segments)
-#define TOTAL_SECS(sbi) (sbi->total_sections)
-#define SECTOR_FROM_BLOCK(sbi, blk_addr) \
- (((sector_t)blk_addr) << (sbi)->log_sectors_per_block)
-#define SECTOR_TO_BLOCK(sbi, sectors) \
- (sectors >> (sbi)->log_sectors_per_block)
-#define MAX_BIO_BLOCKS(max_hw_blocks) \
- (min((int)max_hw_blocks, BIO_MAX_PAGES))
+#define SECTOR_FROM_BLOCK(blk_addr) \
+ (((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
+#define SECTOR_TO_BLOCK(sectors) \
+ (sectors >> F2FS_LOG_SECTORS_PER_BLOCK)
+#define MAX_BIO_BLOCKS(sbi) \
+ ((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES))
/*
* indicate a block allocation direction: RIGHT and LEFT.
@@ -167,6 +175,11 @@
void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
};
+struct inmem_pages {
+ struct list_head list;
+ struct page *page;
+};
+
struct sit_info {
const struct segment_allocation *s_ops;
@@ -176,6 +189,7 @@
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 */
@@ -194,7 +208,7 @@
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 */
};
@@ -237,6 +251,12 @@
unsigned int next_segno; /* preallocated segment */
};
+struct sit_entry_set {
+ struct list_head set_list; /* link with all sit sets */
+ unsigned int start_segno; /* start segno of sits in set */
+ unsigned int entry_cnt; /* the # of sit entries in set */
+};
+
/*
* inline functions
*/
@@ -299,9 +319,9 @@
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;
}
@@ -312,16 +332,16 @@
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, TOTAL_SEGS(sbi), start_segno);
+ next = find_next_bit(free_i->free_segmap, MAIN_SEGS(sbi), 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,
@@ -343,7 +363,7 @@
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++;
@@ -354,7 +374,7 @@
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,
@@ -362,13 +382,13 @@
{
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,
@@ -430,8 +450,10 @@
static inline bool need_SSR(struct f2fs_sb_info *sbi)
{
- return (prefree_segments(sbi) / sbi->segs_per_sec)
- + free_sections(sbi) < overprovision_sections(sbi);
+ int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
+ int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+ return free_sections(sbi) <= (node_secs + 2 * dent_secs +
+ reserved_sections(sbi) + 1);
}
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
@@ -439,7 +461,7 @@
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 +
@@ -466,48 +488,47 @@
* F2FS_IPU_UTIL - if FS utilization is over threashold,
* F2FS_IPU_SSR_UTIL - if SSR mode is activated and FS utilization is over
* threashold,
+ * F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
+ * storages. IPU will be triggered only if the # of dirty
+ * pages over min_fsync_blocks.
* F2FS_IPUT_DISABLE - disable IPU. (=default option)
*/
#define DEF_MIN_IPU_UTIL 70
+#define DEF_MIN_FSYNC_BLOCKS 8
enum {
F2FS_IPU_FORCE,
F2FS_IPU_SSR,
F2FS_IPU_UTIL,
F2FS_IPU_SSR_UTIL,
- F2FS_IPU_DISABLE,
+ F2FS_IPU_FSYNC,
};
static inline bool need_inplace_update(struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ unsigned int policy = SM_I(sbi)->ipu_policy;
/* IPU can be done only for the user data */
- if (S_ISDIR(inode->i_mode))
+ if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
return false;
- /* this is only set during fdatasync */
- if (is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
+ if (policy & (0x1 << F2FS_IPU_FORCE))
+ return true;
+ if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
+ return true;
+ if (policy & (0x1 << F2FS_IPU_UTIL) &&
+ utilization(sbi) > SM_I(sbi)->min_ipu_util)
+ return true;
+ if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) &&
+ utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
- switch (SM_I(sbi)->ipu_policy) {
- case F2FS_IPU_FORCE:
+ /* this is only set during fdatasync */
+ if (policy & (0x1 << F2FS_IPU_FSYNC) &&
+ is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
return true;
- case F2FS_IPU_SSR:
- if (need_SSR(sbi))
- return true;
- break;
- case F2FS_IPU_UTIL:
- if (utilization(sbi) > SM_I(sbi)->min_ipu_util)
- return true;
- break;
- case F2FS_IPU_SSR_UTIL:
- if (need_SSR(sbi) && utilization(sbi) > SM_I(sbi)->min_ipu_util)
- return true;
- break;
- case F2FS_IPU_DISABLE:
- break;
- }
+
return false;
}
@@ -534,18 +555,13 @@
#ifdef CONFIG_F2FS_CHECK_FS
static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
{
- unsigned int end_segno = SM_I(sbi)->segment_count - 1;
- BUG_ON(segno > end_segno);
+ BUG_ON(segno > TOTAL_SEGS(sbi) - 1);
}
static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
{
- struct f2fs_sm_info *sm_info = SM_I(sbi);
- block_t total_blks = sm_info->segment_count << sbi->log_blocks_per_seg;
- block_t start_addr = sm_info->seg0_blkaddr;
- block_t end_addr = start_addr + total_blks - 1;
- BUG_ON(blk_addr < start_addr);
- BUG_ON(blk_addr > end_addr);
+ BUG_ON(blk_addr < SEG0_BLKADDR(sbi));
+ BUG_ON(blk_addr >= MAX_BLKADDR(sbi));
}
/*
@@ -554,8 +570,6 @@
static inline void check_block_count(struct f2fs_sb_info *sbi,
int segno, struct f2fs_sit_entry *raw_sit)
{
- struct f2fs_sm_info *sm_info = SM_I(sbi);
- unsigned int end_segno = sm_info->segment_count - 1;
bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false;
int valid_blocks = 0;
int cur_pos = 0, next_pos;
@@ -564,7 +578,7 @@
BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg);
/* check boundary of a given segment number */
- BUG_ON(segno > end_segno);
+ BUG_ON(segno > TOTAL_SEGS(sbi) - 1);
/* check bitmap with valid block count */
do {
@@ -583,16 +597,39 @@
BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
}
#else
-#define check_seg_range(sbi, segno)
-#define verify_block_addr(sbi, blk_addr)
-#define check_block_count(sbi, segno, raw_sit)
+static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+ if (segno > TOTAL_SEGS(sbi) - 1)
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+}
+
+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))
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+}
+
+/*
+ * 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)
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+
+ /* check boundary of a given segment number */
+ if (segno > TOTAL_SEGS(sbi) - 1)
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+}
#endif
static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
unsigned int start)
{
struct sit_info *sit_i = SIT_I(sbi);
- unsigned int offset = SIT_BLOCK_OFFSET(sit_i, start);
+ unsigned int offset = SIT_BLOCK_OFFSET(start);
block_t blk_addr = sit_i->sit_base_addr + offset;
check_seg_range(sbi, start);
@@ -619,12 +656,9 @@
static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
{
- unsigned int block_off = SIT_BLOCK_OFFSET(sit_i, 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)
@@ -666,7 +700,7 @@
{
struct block_device *bdev = sbi->sb->s_bdev;
struct request_queue *q = bdev_get_queue(bdev);
- return SECTOR_TO_BLOCK(sbi, queue_max_sectors(q));
+ return SECTOR_TO_BLOCK(queue_max_sectors(q));
}
/*
@@ -678,12 +712,15 @@
*/
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)
return 3 * sbi->blocks_per_seg;
else if (type == META)
- return MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ return MAX_BIO_BLOCKS(sbi);
else
return 0;
}
@@ -706,7 +743,7 @@
else if (type == NODE)
desired = 3 * max_hw_blocks(sbi);
else
- desired = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+ desired = MAX_BIO_BLOCKS(sbi);
wbc->nr_to_write = desired;
return desired - nr_to_write;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index d7802be..4ab9c76 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -30,6 +30,7 @@
#include "segment.h"
#include "xattr.h"
#include "gc.h"
+#include "trace.h"
#define CREATE_TRACE_POINTS
#include <trace/events/f2fs.h>
@@ -41,6 +42,7 @@
enum {
Opt_gc_background,
Opt_disable_roll_forward,
+ Opt_norecovery,
Opt_discard,
Opt_noheap,
Opt_user_xattr,
@@ -51,14 +53,17 @@
Opt_disable_ext_identify,
Opt_inline_xattr,
Opt_inline_data,
+ Opt_inline_dentry,
Opt_flush_merge,
Opt_nobarrier,
+ Opt_fastboot,
Opt_err,
};
static match_table_t f2fs_tokens = {
{Opt_gc_background, "background_gc=%s"},
{Opt_disable_roll_forward, "disable_roll_forward"},
+ {Opt_norecovery, "norecovery"},
{Opt_discard, "discard"},
{Opt_noheap, "no_heap"},
{Opt_user_xattr, "user_xattr"},
@@ -69,8 +74,10 @@
{Opt_disable_ext_identify, "disable_ext_identify"},
{Opt_inline_xattr, "inline_xattr"},
{Opt_inline_data, "inline_data"},
+ {Opt_inline_dentry, "inline_dentry"},
{Opt_flush_merge, "flush_merge"},
{Opt_nobarrier, "nobarrier"},
+ {Opt_fastboot, "fastboot"},
{Opt_err, NULL},
};
@@ -188,8 +195,10 @@
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
@@ -202,8 +211,10 @@
ATTR_LIST(gc_idle),
ATTR_LIST(reclaim_segments),
ATTR_LIST(max_small_discards),
+ ATTR_LIST(batched_trim_sections),
ATTR_LIST(ipu_policy),
ATTR_LIST(min_ipu_util),
+ ATTR_LIST(min_fsync_blocks),
ATTR_LIST(max_victim_search),
ATTR_LIST(dir_level),
ATTR_LIST(ram_thresh),
@@ -280,6 +291,12 @@
case Opt_disable_roll_forward:
set_opt(sbi, DISABLE_ROLL_FORWARD);
break;
+ case Opt_norecovery:
+ /* this option mounts f2fs with ro */
+ set_opt(sbi, DISABLE_ROLL_FORWARD);
+ if (!f2fs_readonly(sb))
+ return -EINVAL;
+ break;
case Opt_discard:
set_opt(sbi, DISCARD);
break;
@@ -338,12 +355,18 @@
case Opt_inline_data:
set_opt(sbi, INLINE_DATA);
break;
+ case Opt_inline_dentry:
+ set_opt(sbi, INLINE_DENTRY);
+ break;
case Opt_flush_merge:
set_opt(sbi, FLUSH_MERGE);
break;
case Opt_nobarrier:
set_opt(sbi, NOBARRIER);
break;
+ case Opt_fastboot:
+ set_opt(sbi, FASTBOOT);
+ break;
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
@@ -366,11 +389,14 @@
/* Initialize f2fs-specific inode info */
fi->vfs_inode.i_version = 1;
- atomic_set(&fi->dirty_dents, 0);
+ atomic_set(&fi->dirty_pages, 0);
fi->i_current_depth = 1;
fi->i_advise = 0;
rwlock_init(&fi->ext.ext_lock);
init_rwsem(&fi->i_sem);
+ INIT_RADIX_TREE(&fi->inmem_root, GFP_NOFS);
+ INIT_LIST_HEAD(&fi->inmem_pages);
+ mutex_init(&fi->inmem_lock);
set_inode_flag(fi, FI_NEW_INODE);
@@ -431,15 +457,25 @@
f2fs_destroy_stats(sbi);
stop_gc_thread(sbi);
- /* We don't need to do checkpoint when it's clean */
- if (sbi->s_dirty)
- write_checkpoint(sbi, true);
+ /*
+ * We don't need to do checkpoint when superblock is clean.
+ * But, the previous checkpoint was not done by umount, it needs to do
+ * clean checkpoint again.
+ */
+ if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
+ !is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) {
+ struct cp_control cpc = {
+ .reason = CP_UMOUNT,
+ };
+ write_checkpoint(sbi, &cpc);
+ }
/*
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
*/
release_dirty_inode(sbi);
+ release_discard_addrs(sbi);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -464,12 +500,17 @@
trace_f2fs_sync_fs(sb, sync);
if (sync) {
+ struct cp_control cpc;
+
+ cpc.reason = __get_cp_reason(sbi);
+
mutex_lock(&sbi->gc_mutex);
- write_checkpoint(sbi, false);
+ write_checkpoint(sbi, &cpc);
mutex_unlock(&sbi->gc_mutex);
} else {
f2fs_balance_fs(sbi);
}
+ f2fs_trace_ios(NULL, NULL, 1);
return 0;
}
@@ -550,10 +591,14 @@
seq_puts(seq, ",disable_ext_identify");
if (test_opt(sbi, INLINE_DATA))
seq_puts(seq, ",inline_data");
+ if (test_opt(sbi, INLINE_DENTRY))
+ seq_puts(seq, ",inline_dentry");
if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE))
seq_puts(seq, ",flush_merge");
if (test_opt(sbi, NOBARRIER))
seq_puts(seq, ",nobarrier");
+ if (test_opt(sbi, FASTBOOT))
+ seq_puts(seq, ",fastboot");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
return 0;
@@ -616,6 +661,9 @@
org_mount_opt = sbi->mount_opt;
active_logs = sbi->active_logs;
+ sbi->mount_opt.opt = 0;
+ sbi->active_logs = NR_CURSEG_TYPE;
+
/* parse mount options */
err = parse_options(sb, data);
if (err)
@@ -639,7 +687,7 @@
f2fs_sync_fs(sb, 1);
need_restart_gc = true;
}
- } else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) {
+ } else if (!sbi->gc_thread) {
err = start_gc_thread(sbi);
if (err)
goto restore_opts;
@@ -652,7 +700,7 @@
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
destroy_flush_cmd_control(sbi);
- } else if (test_opt(sbi, FLUSH_MERGE) && !SM_I(sbi)->cmd_control_info) {
+ } else if (!SM_I(sbi)->cmd_control_info) {
err = create_flush_cmd_control(sbi);
if (err)
goto restore_gc;
@@ -786,14 +834,22 @@
return 1;
}
- if (le32_to_cpu(raw_super->log_sectorsize) !=
- F2FS_LOG_SECTOR_SIZE) {
- f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
+ /* Currently, support 512/1024/2048/4096 bytes sector size */
+ if (le32_to_cpu(raw_super->log_sectorsize) >
+ F2FS_MAX_LOG_SECTOR_SIZE ||
+ le32_to_cpu(raw_super->log_sectorsize) <
+ F2FS_MIN_LOG_SECTOR_SIZE) {
+ f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize (%u)",
+ le32_to_cpu(raw_super->log_sectorsize));
return 1;
}
- if (le32_to_cpu(raw_super->log_sectors_per_block) !=
- F2FS_LOG_SECTORS_PER_BLOCK) {
- f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block");
+ if (le32_to_cpu(raw_super->log_sectors_per_block) +
+ le32_to_cpu(raw_super->log_sectorsize) !=
+ F2FS_MAX_LOG_SECTOR_SIZE) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid log sectors per block(%u) log sectorsize(%u)",
+ le32_to_cpu(raw_super->log_sectors_per_block),
+ le32_to_cpu(raw_super->log_sectorsize));
return 1;
}
return 0;
@@ -849,6 +905,7 @@
atomic_set(&sbi->nr_pages[i], 0);
sbi->dir_level = DEF_DIR_LEVEL;
+ clear_sbi_flag(sbi, SBI_NEED_FSCK);
}
/*
@@ -898,11 +955,12 @@
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
- struct f2fs_super_block *raw_super;
+ struct f2fs_super_block *raw_super = NULL;
struct buffer_head *raw_super_buf;
struct inode *root;
long err = -EINVAL;
bool retry = true;
+ char *options = NULL;
int i;
try_onemore:
@@ -934,9 +992,15 @@
set_opt(sbi, POSIX_ACL);
#endif
/* parse mount options */
- err = parse_options(sb, (char *)data);
- if (err)
+ options = kstrdup((const char *)data, GFP_KERNEL);
+ if (data && !options) {
+ err = -ENOMEM;
goto free_sb_buf;
+ }
+
+ err = parse_options(sb, options);
+ if (err)
+ goto free_options;
sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
sb->s_max_links = F2FS_LINK_MAX;
@@ -959,7 +1023,7 @@
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
- sbi->por_doing = false;
+ clear_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
init_rwsem(&sbi->read_io.io_rwsem);
@@ -980,7 +1044,7 @@
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;
+ goto free_options;
}
err = get_valid_checkpoint(sbi);
@@ -1082,8 +1146,20 @@
if (err)
goto free_proc;
+ if (!retry)
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+ /*
+ * mount should be failed, when device has readonly mode, and
+ * previous checkpoint was not done by clean system shutdown.
+ */
+ if (bdev_read_only(sb->s_bdev) &&
+ !is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) {
+ err = -EROFS;
+ goto free_kobj;
+ }
err = recover_fsync_data(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
@@ -1096,12 +1172,13 @@
* If filesystem is not mounted as read-only then
* do start the gc_thread.
*/
- if (!f2fs_readonly(sb)) {
+ if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
/* After POR, we can run background GC thread.*/
err = start_gc_thread(sbi);
if (err)
goto free_kobj;
}
+ kfree(options);
return 0;
free_kobj:
@@ -1126,6 +1203,8 @@
free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
+free_options:
+ kfree(options);
free_sb_buf:
brelse(raw_super_buf);
free_sbi:
@@ -1146,11 +1225,18 @@
return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
}
+static void kill_f2fs_super(struct super_block *sb)
+{
+ if (sb->s_root)
+ set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+ kill_block_super(sb);
+}
+
static struct file_system_type f2fs_fs_type = {
.owner = THIS_MODULE,
.name = "f2fs",
.mount = f2fs_mount,
- .kill_sb = kill_block_super,
+ .kill_sb = kill_f2fs_super,
.fs_flags = FS_REQUIRES_DEV,
};
@@ -1177,6 +1263,8 @@
{
int err;
+ f2fs_build_trace_ios();
+
err = init_inodecache();
if (err)
goto fail;
@@ -1186,12 +1274,9 @@
err = create_segment_manager_caches();
if (err)
goto free_node_manager_caches;
- err = create_gc_caches();
- if (err)
- goto free_segment_manager_caches;
err = create_checkpoint_caches();
if (err)
- goto free_gc_caches;
+ goto free_segment_manager_caches;
f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
if (!f2fs_kset) {
err = -ENOMEM;
@@ -1208,8 +1293,6 @@
kset_unregister(f2fs_kset);
free_checkpoint_caches:
destroy_checkpoint_caches();
-free_gc_caches:
- destroy_gc_caches();
free_segment_manager_caches:
destroy_segment_manager_caches();
free_node_manager_caches:
@@ -1226,11 +1309,11 @@
f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
destroy_checkpoint_caches();
- destroy_gc_caches();
destroy_segment_manager_caches();
destroy_node_manager_caches();
destroy_inodecache();
kset_unregister(f2fs_kset);
+ f2fs_destroy_trace_ios();
}
module_init(init_f2fs_fs)
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
new file mode 100644
index 0000000..875aa81
--- /dev/null
+++ b/fs/f2fs/trace.c
@@ -0,0 +1,159 @@
+/*
+ * 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.blk_addr,
+ 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 page *page, struct f2fs_io_info *fio, int flush)
+{
+ struct inode *inode;
+ pid_t pid;
+ int major, minor;
+
+ if (flush) {
+ __print_last_io();
+ return;
+ }
+
+ inode = page->mapping->host;
+ pid = page_private(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.blk_addr + last_io.len == fio->blk_addr) {
+ 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);
+}
diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h
new file mode 100644
index 0000000..1041dbe
--- /dev/null
+++ b/fs/f2fs/trace.h
@@ -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 page *, 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(p, i, n)
+#define f2fs_build_trace_ios()
+#define f2fs_destroy_trace_ios()
+
+#endif
+#endif /* __F2FS_TRACE_H__ */
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 06e1679..2f49a58 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -82,7 +82,7 @@
}
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,
@@ -265,7 +265,7 @@
static void *read_all_xattrs(struct inode *inode, struct page *ipage)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_xattr_header *header;
size_t size = PAGE_SIZE, inline_size = 0;
void *txattr_addr;
@@ -324,7 +324,7 @@
static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
void *txattr_addr, struct page *ipage)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
size_t inline_size = 0;
void *xattr_addr;
struct page *xpage;
@@ -372,7 +372,7 @@
alloc_nid_failed(sbi, new_nid);
return PTR_ERR(xpage);
}
- f2fs_bug_on(new_nid);
+ f2fs_bug_on(sbi, new_nid);
f2fs_wait_on_page_writeback(xpage, NODE);
} else {
struct dnode_of_data dn;
@@ -397,7 +397,7 @@
}
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;
@@ -411,7 +411,7 @@
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;
@@ -595,7 +595,7 @@
const void *value, size_t size,
struct page *ipage, int flags)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err;
/* this case is only from init_inode_metadata */
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index 9b18c07..95b55a0 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -117,7 +117,8 @@
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
@@ -128,7 +129,8 @@
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;
}
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 08ed2b0..a23556c 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -15,15 +15,20 @@
#include <linux/types.h>
#define F2FS_SUPER_OFFSET 1024 /* byte-size offset */
-#define F2FS_LOG_SECTOR_SIZE 9 /* 9 bits for 512 byte */
-#define F2FS_LOG_SECTORS_PER_BLOCK 3 /* 4KB: F2FS_BLKSIZE */
+#define F2FS_MIN_LOG_SECTOR_SIZE 9 /* 9 bits for 512 bytes */
+#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 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
@@ -32,7 +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
@@ -85,6 +91,8 @@
/*
* For checkpoint
*/
+#define CP_FASTBOOT_FLAG 0x00000020
+#define CP_FSCK_FLAG 0x00000010
#define CP_ERROR_FLAG 0x00000008
#define CP_COMPACT_SUM_FLAG 0x00000004
#define CP_ORPHAN_PRESENT_FLAG 0x00000002
@@ -168,14 +176,12 @@
#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 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 */
@@ -223,6 +229,8 @@
OFFSET_BIT_SHIFT
};
+#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */
+
struct node_footer {
__le32 nid; /* node id */
__le32 ino; /* inode nunmber */
@@ -433,6 +441,24 @@
__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,
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 72664b8..b83cc02 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -69,6 +69,13 @@
{ GC_GREEDY, "Greedy" }, \
{ GC_CB, "Cost-Benefit" })
+#define show_cpreason(type) \
+ __print_symbolic(type, \
+ { CP_UMOUNT, "Umount" }, \
+ { CP_FASTBOOT, "Fastboot" }, \
+ { CP_SYNC, "Sync" }, \
+ { CP_DISCARD, "Discard" })
+
struct victim_sel_policy;
DECLARE_EVENT_CLASS(f2fs__inode,
@@ -142,14 +149,14 @@
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)
),
@@ -184,7 +191,7 @@
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;
),
@@ -434,38 +441,6 @@
__entry->err)
);
-TRACE_EVENT_CONDITION(f2fs_submit_page_bio,
-
- TP_PROTO(struct page *page, sector_t blkaddr, int type),
-
- TP_ARGS(page, blkaddr, type),
-
- TP_CONDITION(page->mapping),
-
- 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),
@@ -674,11 +649,63 @@
__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, 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->blkaddr = fio->blk_addr;
+ __entry->rw = fio->rw;
+ __entry->type = fio->type;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
+ "blkaddr = 0x%llx, rw = %s%s, type = %s",
+ show_dev_ino(__entry),
+ (unsigned long)__entry->index,
+ (unsigned long long)__entry->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)
@@ -690,8 +717,8 @@
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_sector;
__entry->size = bio->bi_size;
),
@@ -706,18 +733,20 @@
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)
);
@@ -907,59 +936,27 @@
__entry->range_cyclic)
);
-TRACE_EVENT(f2fs_submit_page_mbio,
-
- TP_PROTO(struct page *page, int rw, int type, block_t blk_addr),
-
- TP_ARGS(page, rw, type, blk_addr),
-
- 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)
- ),
-
- 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;
- ),
-
- TP_printk("dev = (%d,%d), ino = %lu, %s%s, %s, index = %lu, blkaddr = 0x%llx",
- show_dev_ino(__entry),
- show_bio_type(__entry->rw),
- show_block_type(__entry->type),
- (unsigned long)__entry->index,
- (unsigned long long)__entry->block)
-);
-
TRACE_EVENT(f2fs_write_checkpoint,
- TP_PROTO(struct super_block *sb, bool is_umount, char *msg),
+ TP_PROTO(struct super_block *sb, int reason, char *msg),
- TP_ARGS(sb, is_umount, msg),
+ TP_ARGS(sb, reason, msg),
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(bool, is_umount)
+ __field(int, reason)
__field(char *, msg)
),
TP_fast_assign(
__entry->dev = sb->s_dev;
- __entry->is_umount = is_umount;
+ __entry->reason = reason;
__entry->msg = msg;
),
TP_printk("dev = (%d,%d), checkpoint for %s, state = %s",
show_dev(__entry),
- __entry->is_umount ? "clean umount" : "consistency",
+ show_cpreason(__entry->reason),
__entry->msg)
);
@@ -989,14 +986,15 @@
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(