summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/ABI/testing/sysfs-fs-f2fs6
-rw-r--r--Documentation/filesystems/f2fs.txt6
-rw-r--r--fs/f2fs/Kconfig10
-rw-r--r--fs/f2fs/Makefile1
-rw-r--r--fs/f2fs/acl.c6
-rw-r--r--fs/f2fs/checkpoint.c95
-rw-r--r--fs/f2fs/data.c218
-rw-r--r--fs/f2fs/debug.c59
-rw-r--r--fs/f2fs/dir.c3
-rw-r--r--fs/f2fs/f2fs.h120
-rw-r--r--fs/f2fs/file.c100
-rw-r--r--fs/f2fs/gc.c38
-rw-r--r--fs/f2fs/gc.h33
-rw-r--r--fs/f2fs/inline.c32
-rw-r--r--fs/f2fs/inode.c37
-rw-r--r--fs/f2fs/namei.c2
-rw-r--r--fs/f2fs/node.c154
-rw-r--r--fs/f2fs/node.h45
-rw-r--r--fs/f2fs/recovery.c11
-rw-r--r--fs/f2fs/segment.c194
-rw-r--r--fs/f2fs/segment.h29
-rw-r--r--fs/f2fs/super.c75
-rw-r--r--fs/f2fs/trace.c159
-rw-r--r--fs/f2fs/trace.h46
-rw-r--r--include/linux/f2fs_fs.h7
-rw-r--r--include/trace/events/f2fs.h148
26 files changed, 1075 insertions, 559 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 6f9157f16725..2c4cc42006e8 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -74,3 +74,9 @@ Date: March 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the memory footprint used by f2fs.
+
+What: /sys/fs/f2fs/<disk>/trim_sections
+Date: February 2015
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Controls the trimming rate in batch mode.
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index e0950c483c22..dac11d7fef27 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -106,6 +106,8 @@ background_gc=%s Turn on/off cleaning operations, namely garbage
Default value for this option is on. So garbage
collection is on by default.
disable_roll_forward Disable the roll-forward recovery routine
+norecovery Disable the roll-forward recovery routine, mounted read-
+ only (i.e., -o ro,disable_roll_forward)
discard Issue discard/TRIM commands when a segment is cleaned.
no_heap Disable heap-style segment allocation which finds free
segments for data from the beginning of main area, while
@@ -197,6 +199,10 @@ Files in /sys/fs/f2fs/<devname>
checkpoint is triggered, and issued during the
checkpoint. By default, it is disabled with 0.
+ trim_sections This parameter controls the number of sections
+ to be trimmed out in batch mode when FITRIM
+ conducts. 32 sections is set by default.
+
ipu_policy This parameter controls the policy of in-place
updates in f2fs. There are five policies:
0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 736a348509f7..94e2d2ffabe1 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -71,3 +71,13 @@ config F2FS_CHECK_FS
Enables BUG_ONs which check the filesystem consistency in runtime.
If you want to improve the performance, say N.
+
+config F2FS_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 2e35da12d292..d92397731db8 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -5,3 +5,4 @@ f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o
f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
+f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 1ccb26bc2a0b..742202779bd5 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -62,7 +62,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
if (count == 0)
return NULL;
- acl = posix_acl_alloc(count, GFP_KERNEL);
+ acl = posix_acl_alloc(count, GFP_NOFS);
if (!acl)
return ERR_PTR(-ENOMEM);
@@ -116,7 +116,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
int i;
f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
- sizeof(struct f2fs_acl_entry), GFP_KERNEL);
+ sizeof(struct f2fs_acl_entry), GFP_NOFS);
if (!f2fs_acl)
return ERR_PTR(-ENOMEM);
@@ -396,7 +396,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
posix_acl_release(default_acl);
}
if (acl) {
- if (error)
+ if (!error)
error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl,
ipage);
posix_acl_release(acl);
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index e6c271fefaca..7f794b72b3b7 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 page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
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 @@ repeat:
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);
@@ -112,14 +117,12 @@ 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;
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;
@@ -130,27 +133,27 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
blkno = 0;
/* get nat block addr */
- blk_addr = current_nat_addr(sbi,
+ fio.blk_addr = current_nat_addr(sbi,
blkno * NAT_ENTRY_PER_BLOCK);
break;
case META_SIT:
/* get sit block addr */
- 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:
case META_POR:
- blk_addr = blkno;
+ 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)) {
@@ -158,7 +161,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
continue;
}
- f2fs_submit_page_mbio(sbi, page, blk_addr, &fio);
+ f2fs_submit_page_mbio(sbi, page, &fio);
f2fs_put_page(page, 0);
}
out:
@@ -187,7 +190,7 @@ static int f2fs_write_meta_page(struct page *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 && page->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
@@ -299,6 +302,8 @@ static int f2fs_set_meta_page_dirty(struct page *page)
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
+ SetPagePrivate(page);
+ f2fs_trace_pid(page);
return 1;
}
return 0;
@@ -308,6 +313,8 @@ const struct address_space_operations f2fs_meta_aops = {
.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)
@@ -462,7 +469,7 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
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);
@@ -483,7 +490,7 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
}
/* 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;
}
@@ -567,7 +574,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
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;
@@ -582,7 +589,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
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;
@@ -669,7 +676,7 @@ fail_no_cp:
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_I_SB(inode);
@@ -686,7 +693,7 @@ static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
void update_dirty_page(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dir_inode_entry *new;
+ struct inode_entry *new;
int ret = 0;
if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
@@ -710,12 +717,13 @@ void update_dirty_page(struct inode *inode, struct page *page)
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_I_SB(inode);
- struct dir_inode_entry *new =
+ struct inode_entry *new =
f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
int ret = 0;
@@ -733,7 +741,7 @@ void add_dirty_dir_inode(struct inode *inode)
void remove_dirty_dir_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dir_inode_entry *entry;
+ struct inode_entry *entry;
if (!S_ISDIR(inode->i_mode))
return;
@@ -763,7 +771,7 @@ void remove_dirty_dir_inode(struct inode *inode)
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)))
@@ -776,7 +784,7 @@ retry:
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) {
@@ -922,7 +930,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
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
@@ -932,24 +940,31 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
orphan_blocks);
- if (cpc->reason == CP_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 (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 (sbi->need_fsck)
+ if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
set_ckpt_flags(ckpt, CP_FSCK_FLAG);
/* update SIT/NAT bitmap */
@@ -966,15 +981,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* 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);
}
@@ -986,7 +1000,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
- if (cpc->reason == CP_UMOUNT) {
+ if (__remain_node_summaries(cpc->reason)) {
write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
@@ -994,7 +1008,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* 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);
@@ -1023,7 +1037,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
return;
clear_prefree_segments(sbi);
- F2FS_RESET_SB_DIRT(sbi);
+ clear_sbi_flag(sbi, SBI_IS_DIRTY);
}
/*
@@ -1038,10 +1052,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
mutex_lock(&sbi->cp_mutex);
- if (!sbi->s_dirty && cpc->reason != CP_DISCARD)
+ 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;
@@ -1102,8 +1119,8 @@ int __init create_checkpoint_caches(void)
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 7ec697b37f19..985ed023a750 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)
@@ -95,11 +96,9 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
return;
if (is_read_io(fio->rw))
- trace_f2fs_submit_read_bio(io->sbi->sb, fio->rw,
- fio->type, io->bio);
+ trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
else
- trace_f2fs_submit_write_bio(io->sbi->sb, fio->rw,
- fio->type, io->bio);
+ trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
submit_bio(fio->rw, io->bio);
io->bio = NULL;
@@ -132,14 +131,15 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
* 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);
@@ -147,12 +147,12 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
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;
@@ -160,21 +160,21 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
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(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;
}
@@ -184,10 +184,11 @@ alloc_new:
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);
}
/*
@@ -196,7 +197,7 @@ alloc_new:
* ->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;
@@ -209,7 +210,7 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
/* 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);
}
@@ -224,8 +225,8 @@ int reserve_new_block(struct dnode_of_data *dn)
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;
@@ -273,7 +274,7 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
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;
@@ -290,23 +291,24 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
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(F2FS_I_SB(dn->inode), blk_addr == NEW_ADDR);
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
- dn->ofs_in_node;
+ 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;
@@ -320,16 +322,16 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
/* 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++;
@@ -337,7 +339,7 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
}
/* 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;
}
@@ -376,6 +378,10 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
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))
@@ -404,8 +410,8 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
return page;
}
- err = f2fs_submit_page_bio(F2FS_I_SB(inode), 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);
@@ -430,7 +436,10 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
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)
@@ -464,8 +473,8 @@ repeat:
return page;
}
- err = f2fs_submit_page_bio(F2FS_I_SB(inode), 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);
@@ -515,8 +524,12 @@ repeat:
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
SetPageUptodate(page);
} else {
- err = f2fs_submit_page_bio(F2FS_I_SB(inode), 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;
@@ -550,30 +563,25 @@ static int __allocate_data_block(struct dnode_of_data *dn)
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 seg = CURSEG_WARM_DATA;
pgoff_t fofs;
- int type;
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);
/* update i_size */
fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
@@ -581,10 +589,59 @@ static int __allocate_data_block(struct dnode_of_data *dn)
if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
- dn->data_blkaddr = new_blkaddr;
return 0;
}
+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.
@@ -610,10 +667,8 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
if (check_extent_cache(inode, pgofs, bh_result))
goto out;
- if (create) {
- f2fs_balance_fs(F2FS_I_SB(inode));
+ 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);
@@ -627,12 +682,14 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
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;
@@ -745,7 +802,6 @@ static int f2fs_read_data_pages(struct file *file,
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;
@@ -754,10 +810,10 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
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);
@@ -766,14 +822,14 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
* 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:
@@ -812,7 +868,12 @@ static int f2fs_write_data_page(struct page *page,
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 */
@@ -826,7 +887,6 @@ write:
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
SetPageError(page);
- unlock_page(page);
goto out;
}
@@ -1002,8 +1062,12 @@ put_next:
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
} 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(sbi, page, &fio);
if (err)
goto fail;
@@ -1092,6 +1156,9 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
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, iter, offset, get_data_block);
if (err < 0 && (rw & WRITE))
f2fs_write_failed(mapping, offset + count);
@@ -1101,24 +1168,33 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
return err;
}
-static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
- unsigned int length)
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct inode *inode = page->mapping->host;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- if (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)
+ if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
+ (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE))<