aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/filesystems/f2fs.txt4
-rw-r--r--fs/f2fs/checkpoint.c63
-rw-r--r--fs/f2fs/data.c202
-rw-r--r--fs/f2fs/debug.c10
-rw-r--r--fs/f2fs/dir.c110
-rw-r--r--fs/f2fs/f2fs.h93
-rw-r--r--fs/f2fs/file.c116
-rw-r--r--fs/f2fs/gc.c123
-rw-r--r--fs/f2fs/gc.h12
-rw-r--r--fs/f2fs/inode.c68
-rw-r--r--fs/f2fs/namei.c80
-rw-r--r--fs/f2fs/node.c411
-rw-r--r--fs/f2fs/node.h20
-rw-r--r--fs/f2fs/recovery.c83
-rw-r--r--fs/f2fs/segment.c137
-rw-r--r--fs/f2fs/segment.h41
-rw-r--r--fs/f2fs/super.c67
-rw-r--r--fs/f2fs/xattr.c28
-rw-r--r--include/linux/f2fs_fs.h17
-rw-r--r--include/trace/events/f2fs.h682
20 files changed, 1676 insertions, 691 deletions
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index dcf338e62b7..bd3c56c6738 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -146,7 +146,7 @@ USAGE
Format options
--------------
--l [label] : Give a volume label, up to 256 unicode name.
+-l [label] : Give a volume label, up to 512 unicode name.
-a [0 or 1] : Split start location of each area for heap-based allocation.
1 is set by default, which performs this.
-o [int] : Set overprovision ratio in percent over volume size.
@@ -156,6 +156,8 @@ Format options
-z [int] : Set the number of sections per zone.
1 is set by default.
-e [str] : Set basic extension list. e.g. "mp3,gif,mov"
+-t [0 or 1] : Disable discard command or not.
+ 1 is set by default, which conducts discard.
================================================================================
DESIGN
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 2b6fc131e2c..b1de01da1a4 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -20,6 +20,7 @@
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include <trace/events/f2fs.h>
static struct kmem_cache *orphan_entry_slab;
static struct kmem_cache *inode_entry_slab;
@@ -57,13 +58,19 @@ repeat:
cond_resched();
goto repeat;
}
- if (f2fs_readpage(sbi, page, index, READ_SYNC)) {
+ if (PageUptodate(page))
+ goto out;
+
+ if (f2fs_readpage(sbi, page, index, READ_SYNC))
+ goto repeat;
+
+ lock_page(page);
+ if (page->mapping != mapping) {
f2fs_put_page(page, 1);
goto repeat;
}
+out:
mark_page_accessed(page);
-
- /* We do not allow returning an errorneous page */
return page;
}
@@ -541,54 +548,44 @@ retry:
*/
static void block_operations(struct f2fs_sb_info *sbi)
{
- int t;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
+ struct blk_plug plug;
- /* Stop renaming operation */
- mutex_lock_op(sbi, RENAME);
- mutex_lock_op(sbi, DENTRY_OPS);
+ blk_start_plug(&plug);
-retry_dents:
- /* write all the dirty dentry pages */
- sync_dirty_dir_inodes(sbi);
+retry_flush_dents:
+ mutex_lock_all(sbi);
- mutex_lock_op(sbi, DATA_WRITE);
+ /* write all the dirty dentry pages */
if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
- mutex_unlock_op(sbi, DATA_WRITE);
- goto retry_dents;
+ mutex_unlock_all(sbi);
+ sync_dirty_dir_inodes(sbi);
+ goto retry_flush_dents;
}
- /* block all the operations */
- for (t = DATA_NEW; t <= NODE_TRUNC; t++)
- mutex_lock_op(sbi, t);
-
- mutex_lock(&sbi->write_inode);
-
/*
* POR: we should ensure that there is no dirty node pages
* until finishing nat/sit flush.
*/
-retry:
- sync_node_pages(sbi, 0, &wbc);
-
- mutex_lock_op(sbi, NODE_WRITE);
+retry_flush_nodes:
+ mutex_lock(&sbi->node_write);
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
- mutex_unlock_op(sbi, NODE_WRITE);
- goto retry;
+ mutex_unlock(&sbi->node_write);
+ sync_node_pages(sbi, 0, &wbc);
+ goto retry_flush_nodes;
}
- mutex_unlock(&sbi->write_inode);
+ blk_finish_plug(&plug);
}
static void unblock_operations(struct f2fs_sb_info *sbi)
{
- int t;
- for (t = NODE_WRITE; t >= RENAME; t--)
- mutex_unlock_op(sbi, t);
+ mutex_unlock(&sbi->node_write);
+ mutex_unlock_all(sbi);
}
static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
@@ -727,9 +724,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
+ trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");
+
mutex_lock(&sbi->cp_mutex);
block_operations(sbi);
+ trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");
+
f2fs_submit_bio(sbi, DATA, true);
f2fs_submit_bio(sbi, NODE, true);
f2fs_submit_bio(sbi, META, true);
@@ -746,13 +747,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
flush_nat_entries(sbi);
flush_sit_entries(sbi);
- reset_victim_segmap(sbi);
-
/* unlock all the fs_lock[] in do_checkpoint() */
do_checkpoint(sbi, is_umount);
unblock_operations(sbi);
mutex_unlock(&sbi->cp_mutex);
+
+ trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
}
void init_orphan_info(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index d0ed4ba4b61..91ff93b0b0f 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/events/f2fs.h>
/*
* Lock ordering for the change of data block address:
@@ -55,6 +56,8 @@ int reserve_new_block(struct dnode_of_data *dn)
if (!inc_valid_block_count(sbi, dn->inode, 1))
return -ENOSPC;
+ trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
+
__set_data_blkaddr(dn, NEW_ADDR);
dn->data_blkaddr = NEW_ADDR;
sync_inode_page(dn);
@@ -134,7 +137,7 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
goto end_update;
}
- /* Frone merge */
+ /* Front merge */
if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
fi->ext.fofs--;
fi->ext.blk_addr--;
@@ -170,7 +173,7 @@ end_update:
return;
}
-struct page *find_data_page(struct inode *inode, pgoff_t index)
+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;
@@ -184,7 +187,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
f2fs_put_page(page, 0);
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, RDONLY_NODE);
+ err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err)
return ERR_PTR(err);
f2fs_put_dnode(&dn);
@@ -200,12 +203,20 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
if (!page)
return ERR_PTR(-ENOMEM);
- err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
- if (err) {
- f2fs_put_page(page, 1);
- return ERR_PTR(err);
+ if (PageUptodate(page)) {
+ unlock_page(page);
+ return page;
+ }
+
+ err = f2fs_readpage(sbi, page, dn.data_blkaddr,
+ sync ? READ_SYNC : READA);
+ if (sync) {
+ wait_on_page_locked(page);
+ if (!PageUptodate(page)) {
+ f2fs_put_page(page, 0);
+ return ERR_PTR(-EIO);
+ }
}
- unlock_page(page);
return page;
}
@@ -223,14 +234,14 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, RDONLY_NODE);
+ err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err)
return ERR_PTR(err);
f2fs_put_dnode(&dn);
if (dn.data_blkaddr == NULL_ADDR)
return ERR_PTR(-ENOENT);
-
+repeat:
page = grab_cache_page(mapping, index);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -242,9 +253,17 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
BUG_ON(dn.data_blkaddr == NULL_ADDR);
err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
- if (err) {
- f2fs_put_page(page, 1);
+ if (err)
return ERR_PTR(err);
+
+ lock_page(page);
+ if (!PageUptodate(page)) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(-EIO);
+ }
+ if (page->mapping != mapping) {
+ f2fs_put_page(page, 1);
+ goto repeat;
}
return page;
}
@@ -252,6 +271,9 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
/*
* Caller ensures that this data page is never allocated.
* A new zero-filled data page is allocated in the page cache.
+ *
+ * Also, caller should grab and release a mutex by calling mutex_lock_op() and
+ * mutex_unlock_op().
*/
struct page *get_new_data_page(struct inode *inode, pgoff_t index,
bool new_i_size)
@@ -263,7 +285,7 @@ struct page *get_new_data_page(struct inode *inode, pgoff_t index,
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, 0);
+ err = get_dnode_of_data(&dn, index, ALLOC_NODE);
if (err)
return ERR_PTR(err);
@@ -274,7 +296,7 @@ struct page *get_new_data_page(struct inode *inode, pgoff_t index,
}
}
f2fs_put_dnode(&dn);
-
+repeat:
page = grab_cache_page(mapping, index);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -284,14 +306,21 @@ struct page *get_new_data_page(struct inode *inode, pgoff_t index,
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ SetPageUptodate(page);
} else {
err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
- if (err) {
- f2fs_put_page(page, 1);
+ if (err)
return ERR_PTR(err);
+ lock_page(page);
+ if (!PageUptodate(page)) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(-EIO);
+ }
+ if (page->mapping != mapping) {
+ f2fs_put_page(page, 1);
+ goto repeat;
}
}
- SetPageUptodate(page);
if (new_i_size &&
i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
@@ -326,21 +355,15 @@ static void read_end_io(struct bio *bio, int err)
/*
* Fill the locked page with data located in the block address.
- * Read operation is synchronous, and caller must unlock the page.
+ * Return unlocked page.
*/
int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page,
block_t blk_addr, int type)
{
struct block_device *bdev = sbi->sb->s_bdev;
- bool sync = (type == READ_SYNC);
struct bio *bio;
- /* This page can be already read by other threads */
- if (PageUptodate(page)) {
- if (!sync)
- unlock_page(page);
- return 0;
- }
+ trace_f2fs_readpage(page, blk_addr, type);
down_read(&sbi->bio_sem);
@@ -355,18 +378,12 @@ int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page,
kfree(bio->bi_private);
bio_put(bio);
up_read(&sbi->bio_sem);
+ f2fs_put_page(page, 1);
return -EFAULT;
}
submit_bio(type, bio);
up_read(&sbi->bio_sem);
-
- /* wait for read completion if sync */
- if (sync) {
- lock_page(page);
- if (PageError(page))
- return -EIO;
- }
return 0;
}
@@ -388,14 +405,18 @@ static int get_data_block_ro(struct inode *inode, sector_t iblock,
/* Get the page offset from the block offset(iblock) */
pgofs = (pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits));
- if (check_extent_cache(inode, pgofs, bh_result))
+ if (check_extent_cache(inode, pgofs, bh_result)) {
+ trace_f2fs_get_data_block(inode, iblock, bh_result, 0);
return 0;
+ }
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, pgofs, RDONLY_NODE);
- if (err)
+ err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+ if (err) {
+ trace_f2fs_get_data_block(inode, iblock, bh_result, err);
return (err == -ENOENT) ? 0 : err;
+ }
/* It does not support data allocation */
BUG_ON(create);
@@ -420,6 +441,7 @@ static int get_data_block_ro(struct inode *inode, sector_t iblock,
bh_result->b_size = (i << blkbits);
}
f2fs_put_dnode(&dn);
+ trace_f2fs_get_data_block(inode, iblock, bh_result, 0);
return 0;
}
@@ -438,13 +460,12 @@ static int f2fs_read_data_pages(struct file *file,
int do_write_data_page(struct page *page)
{
struct inode *inode = page->mapping->host;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
block_t old_blk_addr, new_blk_addr;
struct dnode_of_data dn;
int err = 0;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, page->index, RDONLY_NODE);
+ err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
return err;
@@ -468,8 +489,6 @@ int do_write_data_page(struct page *page)
write_data_page(inode, page, &dn,
old_blk_addr, &new_blk_addr);
update_extent_cache(new_blk_addr, &dn);
- F2FS_I(inode)->data_version =
- le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver);
}
out_writepage:
f2fs_put_dnode(&dn);
@@ -485,10 +504,11 @@ static int f2fs_write_data_page(struct page *page,
const pgoff_t end_index = ((unsigned long long) i_size)
>> PAGE_CACHE_SHIFT;
unsigned offset;
+ bool need_balance_fs = false;
int err = 0;
if (page->index < end_index)
- goto out;
+ goto write;
/*
* If the offset is out-of-range of file size,
@@ -500,50 +520,46 @@ static int f2fs_write_data_page(struct page *page,
dec_page_count(sbi, F2FS_DIRTY_DENTS);
inode_dec_dirty_dents(inode);
}
- goto unlock_out;
+ goto out;
}
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
-out:
- if (sbi->por_doing)
- goto redirty_out;
-
- if (wbc->for_reclaim && !S_ISDIR(inode->i_mode) && !is_cold_data(page))
+write:
+ if (sbi->por_doing) {
+ err = AOP_WRITEPAGE_ACTIVATE;
goto redirty_out;
+ }
- mutex_lock_op(sbi, DATA_WRITE);
+ /* Dentry blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode)) {
dec_page_count(sbi, F2FS_DIRTY_DENTS);
inode_dec_dirty_dents(inode);
+ err = do_write_data_page(page);
+ } else {
+ int ilock = mutex_lock_op(sbi);
+ err = do_write_data_page(page);
+ mutex_unlock_op(sbi, ilock);
+ need_balance_fs = true;
}
- err = do_write_data_page(page);
- if (err && err != -ENOENT) {
- wbc->pages_skipped++;
- set_page_dirty(page);
- }
- mutex_unlock_op(sbi, DATA_WRITE);
+ if (err == -ENOENT)
+ goto out;
+ else if (err)
+ goto redirty_out;
if (wbc->for_reclaim)
f2fs_submit_bio(sbi, DATA, true);
- if (err == -ENOENT)
- goto unlock_out;
-
clear_cold_data(page);
+out:
unlock_page(page);
-
- if (!wbc->for_reclaim && !S_ISDIR(inode->i_mode))
+ if (need_balance_fs)
f2fs_balance_fs(sbi);
return 0;
-unlock_out:
- unlock_page(page);
- return (err == -ENOENT) ? 0 : err;
-
redirty_out:
wbc->pages_skipped++;
set_page_dirty(page);
- return AOP_WRITEPAGE_ACTIVATE;
+ return err;
}
#define MAX_DESIRED_PAGES_WP 4096
@@ -562,19 +578,26 @@ static int f2fs_write_data_pages(struct address_space *mapping,
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ bool locked = false;
int ret;
long excess_nrtw = 0, desired_nrtw;
+ /* deal with chardevs and other special file */
+ if (!mapping->a_ops->writepage)
+ return 0;
+
if (wbc->nr_to_write < MAX_DESIRED_PAGES_WP) {
desired_nrtw = MAX_DESIRED_PAGES_WP;
excess_nrtw = desired_nrtw - wbc->nr_to_write;
wbc->nr_to_write = desired_nrtw;
}
- if (!S_ISDIR(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode)) {
mutex_lock(&sbi->writepages);
+ locked = true;
+ }
ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
- if (!S_ISDIR(inode->i_mode))
+ if (locked)
mutex_unlock(&sbi->writepages);
f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL));
@@ -594,39 +617,33 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
struct dnode_of_data dn;
int err = 0;
+ int ilock;
/* for nobh_write_end */
*fsdata = NULL;
f2fs_balance_fs(sbi);
-
+repeat:
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
*pagep = page;
- mutex_lock_op(sbi, DATA_NEW);
+ ilock = mutex_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, 0);
- if (err) {
- mutex_unlock_op(sbi, DATA_NEW);
- f2fs_put_page(page, 1);
- return err;
- }
+ err = get_dnode_of_data(&dn, index, ALLOC_NODE);
+ if (err)
+ goto err;
- if (dn.data_blkaddr == NULL_ADDR) {
+ if (dn.data_blkaddr == NULL_ADDR)
err = reserve_new_block(&dn);
- if (err) {
- f2fs_put_dnode(&dn);
- mutex_unlock_op(sbi, DATA_NEW);
- f2fs_put_page(page, 1);
- return err;
- }
- }
+
f2fs_put_dnode(&dn);
+ if (err)
+ goto err;
- mutex_unlock_op(sbi, DATA_NEW);
+ mutex_unlock_op(sbi, ilock);
if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
return 0;
@@ -637,21 +654,34 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
/* Reading beyond i_size is simple: memset to zero */
zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
- return 0;
+ goto out;
}
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
} else {
err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
- if (err) {
- f2fs_put_page(page, 1);
+ if (err)
return err;
+ lock_page(page);
+ if (!PageUptodate(page)) {
+ f2fs_put_page(page, 1);
+ return -EIO;
+ }
+ if (page->mapping != mapping) {
+ f2fs_put_page(page, 1);
+ goto repeat;
}
}
+out:
SetPageUptodate(page);
clear_cold_data(page);
return 0;
+
+err:
+ mutex_unlock_op(sbi, ilock);
+ f2fs_put_page(page, 1);
+ return err;
}
static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
@@ -682,7 +712,7 @@ static void f2fs_invalidate_data_page(struct page *page, unsigned long offset)
static int f2fs_release_data_page(struct page *page, gfp_t wait)
{
ClearPagePrivate(page);
- return 0;
+ return 1;
}
static int f2fs_set_data_page_dirty(struct page *page)
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 025b9e2f935..8d9943786c3 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -13,7 +13,6 @@
#include <linux/fs.h>
#include <linux/backing-dev.h>
-#include <linux/proc_fs.h>
#include <linux/f2fs_fs.h>
#include <linux/blkdev.h>
#include <linux/debugfs.h>
@@ -106,7 +105,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
}
}
mutex_unlock(&sit_i->sentry_lock);
- dist = sbi->total_sections * hblks_per_sec * hblks_per_sec / 100;
+ dist = TOTAL_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
si->bimodal = bimodal / dist;
if (si->dirty_count)
si->avg_vblocks = total_vblocks / ndirty;
@@ -138,14 +137,13 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * TOTAL_SEGS(sbi);
if (sbi->segs_per_sec > 1)
- si->base_mem += sbi->total_sections *
- sizeof(struct sec_entry);
+ si->base_mem += TOTAL_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(sbi->total_sections);
+ si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
/* build curseg */
si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
@@ -154,7 +152,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
/* 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 += 2 * f2fs_bitmap_size(TOTAL_SEGS(sbi));
+ si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
/* buld nm */
si->base_mem += sizeof(struct f2fs_nm_info);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 1be948768e2..1ac6b93036b 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -148,7 +148,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
for (; bidx < end_block; bidx++) {
/* no need to allocate new dentry pages to all the indices */
- dentry_page = find_data_page(dir, bidx);
+ dentry_page = find_data_page(dir, bidx, true);
if (IS_ERR(dentry_page)) {
room = true;
continue;
@@ -189,6 +189,9 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
unsigned int max_depth;
unsigned int level;
+ if (namelen > F2FS_NAME_LEN)
+ return NULL;
+
if (npages == 0)
return NULL;
@@ -246,9 +249,6 @@ ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
struct page *page, struct inode *inode)
{
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-
- mutex_lock_op(sbi, DENTRY_OPS);
lock_page(page);
wait_on_page_writeback(page);
de->ino = cpu_to_le32(inode->i_ino);
@@ -262,7 +262,6 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
F2FS_I(inode)->i_pino = dir->i_ino;
f2fs_put_page(page, 1);
- mutex_unlock_op(sbi, DENTRY_OPS);
}
void init_dent_inode(const struct qstr *name, struct page *ipage)
@@ -281,6 +280,43 @@ void init_dent_inode(const struct qstr *name, struct page *ipage)
set_page_dirty(ipage);
}
+static int make_empty_dir(struct inode *inode, struct inode *parent)
+{
+ struct page *dentry_page;
+ struct f2fs_dentry_block *dentry_blk;
+ struct f2fs_dir_entry *de;
+ void *kaddr;
+
+ dentry_page = get_new_data_page(inode, 0, true);
+ if (IS_ERR(dentry_page))
+ return PTR_ERR(dentry_page);
+
+ kaddr = kmap_atomic(dentry_page);
+ dentry_blk = (struct f2fs_dentry_block *)kaddr;
+
+ 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);
+
+ 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(kaddr);
+
+ set_page_dirty(dentry_page);
+ f2fs_put_page(dentry_page, 1);
+ return 0;
+}
+
static int init_inode_metadata(struct inode *inode,
struct inode *dir, const struct qstr *name)
{
@@ -291,7 +327,7 @@ static int init_inode_metadata(struct inode *inode,
return err;
if (S_ISDIR(inode->i_mode)) {
- err = f2fs_make_empty(inode, dir);
+ err = make_empty_dir(inode, dir);
if (err) {
remove_inode_page(inode);
return err;
@@ -314,7 +350,7 @@ static int init_inode_metadata(struct inode *inode,
}
if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
inc_nlink(inode);
- f2fs_write_inode(inode, NULL);
+ update_inode_page(inode);
}
return 0;
}
@@ -338,7 +374,7 @@ static void update_parent_metadata(struct inode *dir, struct inode *inode,
}
if (need_dir_update)
- f2fs_write_inode(dir, NULL);
+ update_inode_page(dir);
else
mark_inode_dirty(dir);
@@ -370,6 +406,10 @@ next:
goto next;
}
+/*
+ * Caller should grab and release a mutex by calling mutex_lock_op() and
+ * mutex_unlock_op().
+ */
int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *inode)
{
unsigned int bit_pos;
@@ -379,7 +419,6 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *in
f2fs_hash_t dentry_hash;
struct f2fs_dir_entry *de;
unsigned int nbucket, nblock;
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
size_t namelen = name->len;
struct page *dentry_page = NULL;
struct f2fs_dentry_block *dentry_blk = NULL;
@@ -409,12 +448,9 @@ start:
bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket));
for (block = bidx; block <= (bidx + nblock - 1); block++) {
- mutex_lock_op(sbi, DENTRY_OPS);
dentry_page = get_new_data_page(dir, block, true);
- if (IS_ERR(dentry_page)) {
- mutex_unlock_op(sbi, DENTRY_OPS);
+ if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
- }
dentry_blk = kmap(dentry_page);
bit_pos = room_for_filename(dentry_blk, slots);
@@ -423,7 +459,6 @@ start:
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
- mutex_unlock_op(sbi, DENTRY_OPS);
}
/* Move to next level to find the empty slot for new dentry */
@@ -453,7 +488,6 @@ add_dentry:
fail:
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
- mutex_unlock_op(sbi, DENTRY_OPS);
return err;
}
@@ -473,8 +507,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
void *kaddr = page_address(page);
int i;
- mutex_lock_op(sbi, DENTRY_OPS);
-
lock_page(page);
wait_on_page_writeback(page);
@@ -494,7 +526,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
if (inode && S_ISDIR(inode->i_mode)) {
drop_nlink(dir);
- f2fs_write_inode(dir, NULL);
+ update_inode_page(dir);
} else {
mark_inode_dirty(dir);
}
@@ -506,7 +538,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
drop_nlink(inode);
i_size_write(inode, 0);
}
- f2fs_write_inode(inode, NULL);
+ update_inode_page(inode);
+
if (inode->i_nlink == 0)
add_orphan_inode(sbi, inode->i_ino);
}
@@ -519,45 +552,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
inode_dec_dirty_dents(dir);
}
f2fs_put_page(page, 1);
-
- mutex_unlock_op(sbi, DENTRY_OPS);
-}
-
-int f2fs_make_empty(struct inode *inode, struct inode *parent)
-{
- struct page *dentry_page;
- struct f2fs_dentry_block *dentry_blk;
- struct f2fs_dir_entry *de;
- void *kaddr;
-
- dentry_page = get_new_data_page(inode, 0, true);
- if (IS_ERR(dentry_page))
- return PTR_ERR(dentry_page);
-
- kaddr = kmap_atomic(dentry_page);
- dentry_blk = (struct f2fs_dentry_block *)kaddr;
-
- de = &dentry_blk->dentry[0];
- de->name_len = cpu_to_le16(1);
- de->hash_code = f2fs_dentry_hash(".", 1);
- de->ino = cpu_to_le32(inode->i_ino);
- memcpy(dentry_blk->filename[0], ".", 1);
- set_de_type(de, inode);
-
- de = &dentry_blk->dentry[1];
- de->hash_code = f2fs_dentry_hash("..", 2);
- 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(kaddr);
-
- set_page_dirty(dentry_page);
- f2fs_put_page(dentry_page, 1);
- return 0;
}
bool f2fs_empty_dir(struct inode *dir)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 201c8d3b0f8..20aab02f2a4 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -125,11 +125,15 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
* file keeping -1 as its node offset to
* distinguish from index node blocks.
*/
-#define RDONLY_NODE 1 /*
- * specify a read-only mode when getting
- * a node block. 0 is read-write mode.
- * used by get_dnode_of_data().
+enum {
+ ALLOC_NODE, /* allocate a new node page if needed */
+ LOOKUP_NODE, /* look up a node without readahead */
+ LOOKUP_NODE_RA, /*
+ * look up a node with readahead called
+ * by get_datablock_ro.
*/
+};
+
#define F2FS_LINK_MAX 32000 /* maximum link count per file */
/* for in-memory extent cache entry */
@@ -144,6 +148,7 @@ struct extent_info {
* i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
*/
#define FADVISE_COLD_BIT 0x01
+#define FADVISE_CP_BIT 0x02
struct f2fs_inode_info {
struct inode vfs_inode; /* serve a vfs inode */
@@ -155,7 +160,6 @@ struct f2fs_inode_info {
/* Use below internally in f2fs*/
unsigned long flags; /* use to pass per-file flags */
- unsigned long long data_version;/* latest version of data for fsync */
atomic_t dirty_dents; /* # of dirty dentry pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
@@ -186,7 +190,6 @@ static inline void set_raw_extent(struct extent_info *ext,
struct f2fs_nm_info {
block_t nat_blkaddr; /* base disk address of NAT */
nid_t max_nid; /* maximum possible node ids */
- nid_t init_scan_nid; /* the first nid to be scanned */
nid_t next_scan_nid; /* the next nid to be scanned */
/* NAT cache management */
@@ -305,23 +308,12 @@ enum count_type {
};
/*
- * FS_LOCK nesting subclasses for the lock validator:
- *
- * The locking order between these classes is
- * RENAME -> DENTRY_OPS -> DATA_WRITE -> DATA_NEW
- * -> DATA_TRUNC -> NODE_WRITE -> NODE_NEW -> NODE_TRUNC
+ * Uses as sbi->fs_lock[NR_GLOBAL_LOCKS].
+ * The checkpoint procedure blocks all the locks in this fs_lock array.
+ * Some FS operations grab free locks, and if there is no free lock,
+ * then wait to grab a lock in a round-robin manner.
*/
-enum lock_type {
- RENAME, /* for renaming operations */
- DENTRY_OPS, /* for directory operations */
- DATA_WRITE, /* for data write */
- DATA_NEW, /* for data allocation */
- DATA_TRUNC, /* for data truncate */
- NODE_NEW, /* for node allocation */
- NODE_TRUNC, /* for node truncate */
- NODE_WRITE, /* for node write */
- NR_LOCK_TYPE,
-};
+#define NR_GLOBAL_LOCKS 8
/*
* The below are the page types of bios used in submti_bio().
@@ -361,11 +353,13 @@ struct f2fs_sb_info {
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
struct inode *meta_inode; /* cache meta blocks */
- struct mutex cp_mutex; /* for checkpoint procedure */
- struct mutex fs_lock[NR_LOCK_TYPE]; /* for blocking FS operations */
- struct mutex write_inode; /* mutex for write inode */
+ struct mutex cp_mutex; /* checkpoint procedure lock */
+ struct mutex fs_lock[NR_GLOBAL_LOCKS]; /* blocking FS operations */
+ struct mutex node_write; /* locking node writes */
struct mutex writepages; /* mutex for writepages() */
+ unsigned char next_lock_num; /* round-robin global locks */
int por_doing; /* recovery is doing or not */
+ int on_build_free_nids; /* build_free_nids is doing */
/* for orphan inode management */
struct list_head orphan_inode_list; /* orphan inode list */
@@ -406,6 +400,7 @@ struct f2fs_sb_info {
/* for cleaning operations */
struct mutex gc_mutex; /* mutex for GC */
struct f2fs_gc_kthread *gc_thread; /* GC thread