summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-11-05 22:22:07 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2015-11-05 22:22:07 +0300
commit0fcb9d21b4e18ede3727b8905e74acd0d1daef56 (patch)
treef8181c110c8bed5b6322122ba086f34bbfb269f9
parentd000f8d67f2bb464c9cf4fb5103f78d8cb406c05 (diff)
parentbeaa57dd986d4f398728c060692fc2452895cfd8 (diff)
downloadlinux-0fcb9d21b4e18ede3727b8905e74acd0d1daef56.tar.xz
Merge tag 'for-f2fs-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
Pull f2fs updates from Jaegeuk Kim: "Most part of the patches include enhancing the stability and performance of in-memory extent caches feature. In addition, it introduces several new features and configurable points: - F2FS_GOING_DOWN_METAFLUSH ioctl to test power failures - F2FS_IOC_WRITE_CHECKPOINT ioctl to trigger checkpoint by users - background_gc=sync mount option to do gc synchronously - periodic checkpoints - sysfs entry to control readahead blocks for free nids And the following bug fixes have been merged. - fix SSA corruption by collapse/insert_range - correct a couple of gc behaviors - fix the results of f2fs_map_blocks - fix error case handling of volatile/atomic writes" * tag 'for-f2fs-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (54 commits) f2fs: fix to skip shrinking extent nodes f2fs: fix error path of ->symlink f2fs: fix to clear GCed flag for atomic written page f2fs: don't need to submit bio on error case f2fs: fix leakage of inmemory atomic pages f2fs: refactor __find_rev_next_{zero}_bit f2fs: support fiemap for inline_data f2fs: flush dirty data for bmap f2fs: relocate the tracepoint for background_gc f2fs crypto: fix racing of accessing encrypted page among f2fs: export ra_nid_pages to sysfs f2fs: readahead for free nids building f2fs: support lower priority asynchronous readahead in ra_meta_pages f2fs: don't tag REQ_META for temporary non-meta pages f2fs: add a tracepoint for f2fs_read_data_pages f2fs: set GFP_NOFS for grab_cache_page f2fs: fix SSA updates resulting in corruption Revert "f2fs: do not skip dentry block writes" f2fs: add F2FS_GOING_DOWN_METAFLUSH to test power-failure f2fs: merge meta writes as many possible ...
Diffstat
-rw-r--r--Documentation/ABI/testing/sysfs-fs-f2fs12
-rw-r--r--Documentation/filesystems/f2fs.txt3
-rw-r--r--fs/f2fs/checkpoint.c49
-rw-r--r--fs/f2fs/data.c176
-rw-r--r--fs/f2fs/debug.c36
-rw-r--r--fs/f2fs/dir.c19
-rw-r--r--fs/f2fs/extent_cache.c195
-rw-r--r--fs/f2fs/f2fs.h86
-rw-r--r--fs/f2fs/file.c327
-rw-r--r--fs/f2fs/gc.c77
-rw-r--r--fs/f2fs/gc.h6
-rw-r--r--fs/f2fs/inline.c42
-rw-r--r--fs/f2fs/inode.c8
-rw-r--r--fs/f2fs/namei.c19
-rw-r--r--fs/f2fs/node.c26
-rw-r--r--fs/f2fs/node.h4
-rw-r--r--fs/f2fs/recovery.c15
-rw-r--r--fs/f2fs/segment.c206
-rw-r--r--fs/f2fs/segment.h4
-rw-r--r--fs/f2fs/super.c37
-rw-r--r--include/trace/events/f2fs.h69
21 files changed, 869 insertions, 547 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 2c4cc42006e8..0345f2d1c727 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -80,3 +80,15 @@ Date: February 2015
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the trimming rate in batch mode.
+
+What: /sys/fs/f2fs/<disk>/cp_interval
+Date: October 2015
+Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+ Controls the checkpoint timing.
+
+What: /sys/fs/f2fs/<disk>/ra_nid_pages
+Date: October 2015
+Contact: "Chao Yu" <chao2.yu@samsung.com>
+Description:
+ Controls the count of nid pages to be readaheaded.
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index e2d5105b7214..b102b436563e 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -102,7 +102,8 @@ background_gc=%s Turn on/off cleaning operations, namely garbage
collection, triggered in background when I/O subsystem is
idle. If background_gc=on, it will turn on the garbage
collection and if background_gc=off, garbage collection
- will be truned off.
+ will be truned off. If background_gc=sync, it will turn
+ on synchronous garbage collection running in background.
Default value for this option is on. So garbage
collection is on by default.
disable_roll_forward Disable the roll-forward recovery routine
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index c5a38e352a80..f661d80474be 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -47,7 +47,8 @@ repeat:
/*
* We guarantee no failure on the returned page.
*/
-struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
+static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
+ bool is_meta)
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page;
@@ -58,6 +59,9 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
.blk_addr = index,
.encrypted_page = NULL,
};
+
+ if (unlikely(!is_meta))
+ fio.rw &= ~REQ_META;
repeat:
page = grab_cache_page(mapping, index);
if (!page) {
@@ -91,6 +95,17 @@ out:
return page;
}
+struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ return __get_meta_page(sbi, index, true);
+}
+
+/* for POR only */
+struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ return __get_meta_page(sbi, index, false);
+}
+
bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
{
switch (type) {
@@ -125,7 +140,8 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
/*
* Readahead CP/NAT/SIT/SSA pages
*/
-int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type)
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
+ int type, bool sync)
{
block_t prev_blk_addr = 0;
struct page *page;
@@ -133,10 +149,13 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
- .rw = READ_SYNC | REQ_META | REQ_PRIO,
+ .rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
.encrypted_page = NULL,
};
+ if (unlikely(type == META_POR))
+ fio.rw &= ~REQ_META;
+
for (; nrpages-- > 0; blkno++) {
if (!is_valid_blkaddr(sbi, blkno, type))
@@ -196,7 +215,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
f2fs_put_page(page, 0);
if (readahead)
- ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR);
+ ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR, true);
}
static int f2fs_write_meta_page(struct page *page,
@@ -257,7 +276,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
long nr_to_write)
{
struct address_space *mapping = META_MAPPING(sbi);
- pgoff_t index = 0, end = LONG_MAX;
+ pgoff_t index = 0, end = LONG_MAX, prev = LONG_MAX;
struct pagevec pvec;
long nwritten = 0;
struct writeback_control wbc = {
@@ -277,6 +296,13 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ if (prev == LONG_MAX)
+ prev = page->index - 1;
+ if (nr_to_write != LONG_MAX && page->index != prev + 1) {
+ pagevec_release(&pvec);
+ goto stop;
+ }
+
lock_page(page);
if (unlikely(page->mapping != mapping)) {
@@ -297,13 +323,14 @@ continue_unlock:
break;
}
nwritten++;
+ prev = page->index;
if (unlikely(nwritten >= nr_to_write))
break;
}
pagevec_release(&pvec);
cond_resched();
}
-
+stop:
if (nwritten)
f2fs_submit_merged_bio(sbi, type, WRITE);
@@ -495,7 +522,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
- ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP);
+ ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
for (i = 0; i < orphan_blocks; i++) {
struct page *page = get_meta_page(sbi, start_blk + i);
@@ -1000,6 +1027,11 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
start_blk = __start_cp_addr(sbi);
+ /* need to wait for end_io results */
+ wait_on_all_pages_writeback(sbi);
+ if (unlikely(f2fs_cp_error(sbi)))
+ return;
+
/* write out checkpoint buffer at block 0 */
update_meta_page(sbi, ckpt, start_blk++);
@@ -1109,6 +1141,9 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
if (cpc->reason == CP_RECOVERY)
f2fs_msg(sbi->sb, KERN_NOTICE,
"checkpoint: version = %llx", ckpt_ver);
+
+ /* do checkpoint periodically */
+ sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval);
out:
mutex_unlock(&sbi->cp_mutex);
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a82abe921b89..972eab7ac071 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -275,7 +275,8 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
return f2fs_reserve_block(dn, index);
}
-struct page *get_read_data_page(struct inode *inode, pgoff_t index, int rw)
+struct page *get_read_data_page(struct inode *inode, pgoff_t index,
+ int rw, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
@@ -292,7 +293,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index, int rw)
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
return read_mapping_page(mapping, index, NULL);
- page = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, for_write);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -352,7 +353,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
return page;
f2fs_put_page(page, 0);
- page = get_read_data_page(inode, index, READ_SYNC);
+ page = get_read_data_page(inode, index, READ_SYNC, false);
if (IS_ERR(page))
return page;
@@ -372,12 +373,13 @@ struct page *find_data_page(struct inode *inode, pgoff_t index)
* Because, the callers, functions in dir.c and GC, should be able to know
* whether this page exists or not.
*/
-struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
+struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
+ bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
repeat:
- page = get_read_data_page(inode, index, READ_SYNC);
+ page = get_read_data_page(inode, index, READ_SYNC, for_write);
if (IS_ERR(page))
return page;
@@ -411,7 +413,7 @@ struct page *get_new_data_page(struct inode *inode,
struct dnode_of_data dn;
int err;
repeat:
- page = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, true);
if (!page) {
/*
* before exiting, we should make sure ipage will be released
@@ -439,7 +441,7 @@ repeat:
} else {
f2fs_put_page(page, 1);
- page = get_read_data_page(inode, index, READ_SYNC);
+ page = get_read_data_page(inode, index, READ_SYNC, true);
if (IS_ERR(page))
goto repeat;
@@ -447,9 +449,9 @@ repeat:
lock_page(page);
}
got_it:
- if (new_i_size &&
- i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
- i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT));
+ if (new_i_size && i_size_read(inode) <
+ ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)) {
+ i_size_write(inode, ((loff_t)(index + 1) << PAGE_CACHE_SHIFT));
/* Only the directory inode sets new_i_size */
set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
}
@@ -489,8 +491,9 @@ alloc:
/* 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));
+ if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT))
+ i_size_write(dn->inode,
+ ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT));
/* direct IO doesn't use extent cache to maximize the performance */
f2fs_drop_largest_extent(dn->inode, fofs);
@@ -523,6 +526,9 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset,
while (dn.ofs_in_node < end_offset && len) {
block_t blkaddr;
+ if (unlikely(f2fs_cp_error(sbi)))
+ goto sync_out;
+
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) {
if (__allocate_data_block(&dn))
@@ -565,6 +571,7 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
{
unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
pgoff_t pgofs, end_offset;
int err = 0, ofs = 1;
@@ -595,40 +602,40 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
err = 0;
goto unlock_out;
}
- if (dn.data_blkaddr == NEW_ADDR) {
- if (flag == F2FS_GET_BLOCK_BMAP) {
- err = -ENOENT;
- goto put_out;
- } else if (flag == F2FS_GET_BLOCK_READ ||
- flag == F2FS_GET_BLOCK_DIO) {
- goto put_out;
+
+ if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) {
+ if (create) {
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto put_out;
+ }
+ err = __allocate_data_block(&dn);
+ if (err)
+ goto put_out;
+ allocated = true;
+ map->m_flags = F2FS_MAP_NEW;
+ } else {
+ if (flag != F2FS_GET_BLOCK_FIEMAP ||
+ dn.data_blkaddr != NEW_ADDR) {
+ if (flag == F2FS_GET_BLOCK_BMAP)
+ err = -ENOENT;
+ goto put_out;
+ }
+
+ /*
+ * preallocated unwritten block should be mapped
+ * for fiemap.
+ */
+ if (dn.data_blkaddr == NEW_ADDR)
+ map->m_flags = F2FS_MAP_UNWRITTEN;
}
- /*
- * if it is in fiemap call path (flag = F2FS_GET_BLOCK_FIEMAP),
- * mark it as mapped and unwritten block.
- */
}
- if (dn.data_blkaddr != NULL_ADDR) {
- map->m_flags = F2FS_MAP_MAPPED;
- map->m_pblk = dn.data_blkaddr;
- if (dn.data_blkaddr == NEW_ADDR)
- map->m_flags |= F2FS_MAP_UNWRITTEN;
- } else if (create) {
- err = __allocate_data_block(&dn);
- if (err)
- goto put_out;
- allocated = true;
- map->m_flags = F2FS_MAP_NEW | F2FS_MAP_MAPPED;
- map->m_pblk = dn.data_blkaddr;
- } else {
- if (flag == F2FS_GET_BLOCK_BMAP)
- err = -ENOENT;
- goto put_out;
- }
+ map->m_flags |= F2FS_MAP_MAPPED;
+ map->m_pblk = dn.data_blkaddr;
+ map->m_len = 1;
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
- map->m_len = 1;
dn.ofs_in_node++;
pgofs++;
@@ -647,23 +654,35 @@ get_next:
goto unlock_out;
}
- if (dn.data_blkaddr == NEW_ADDR &&
- flag != F2FS_GET_BLOCK_FIEMAP)
- goto put_out;
-
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
}
if (maxblocks > map->m_len) {
block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
- if (blkaddr == NULL_ADDR && create) {
- err = __allocate_data_block(&dn);
- if (err)
- goto sync_out;
- allocated = true;
- map->m_flags |= F2FS_MAP_NEW;
- blkaddr = dn.data_blkaddr;
+
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
+ if (create) {
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto sync_out;
+ }
+ err = __allocate_data_block(&dn);
+ if (err)
+ goto sync_out;
+ allocated = true;
+ map->m_flags |= F2FS_MAP_NEW;
+ blkaddr = dn.data_blkaddr;
+ } else {
+ /*
+ * we only merge preallocated unwritten blocks
+ * for fiemap.
+ */
+ if (flag != F2FS_GET_BLOCK_FIEMAP ||
+ blkaddr != NEW_ADDR)
+ goto sync_out;
+ }
}
+
/* Give more consecutive addresses for the readahead */
if ((map->m_pblk != NEW_ADDR &&
blkaddr == (map->m_pblk + ofs)) ||
@@ -752,6 +771,12 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
if (ret)
return ret;
+ if (f2fs_has_inline_data(inode)) {
+ ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
+ if (ret != -EAGAIN)
+ return ret;
+ }
+
mutex_lock(&inode->i_mutex);
if (len >= isize) {
@@ -903,7 +928,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
map.m_lblk = block_in_file;
map.m_len = last_block - block_in_file;
- if (f2fs_map_blocks(inode, &map, 0, false))
+ if (f2fs_map_blocks(inode, &map, 0,
+ F2FS_GET_BLOCK_READ))
goto set_error_page;
}
got_it:
@@ -936,21 +962,14 @@ submit_and_realloc:
if (f2fs_encrypted_inode(inode) &&
S_ISREG(inode->i_mode)) {
- struct page *cpage;
ctx = f2fs_get_crypto_ctx(inode);
if (IS_ERR(ctx))
goto set_error_page;
/* wait the page to be moved by cleaning */
- cpage = find_lock_page(
- META_MAPPING(F2FS_I_SB(inode)),
- block_nr);
- if (cpage) {
- f2fs_wait_on_page_writeback(cpage,
- DATA);
- f2fs_put_page(cpage, 1);
- }
+ f2fs_wait_on_encrypted_page_writeback(
+ F2FS_I_SB(inode), block_nr);
}
bio = bio_alloc(GFP_KERNEL,
@@ -1012,6 +1031,9 @@ static int f2fs_read_data_pages(struct file *file,
struct list_head *pages, unsigned nr_pages)
{
struct inode *inode = file->f_mapping->host;
+ struct page *page = list_entry(pages->prev, struct page, lru);
+
+ trace_f2fs_readpages(inode, page, nr_pages);
/* If the file has inline data, skip readpages */
if (f2fs_has_inline_data(inode))
@@ -1041,6 +1063,11 @@ int do_write_data_page(struct f2fs_io_info *fio)
}
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+
+ /* wait for GCed encrypted page writeback */
+ f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
+ fio->blk_addr);
+
fio->encrypted_page = f2fs_encrypt(inode, fio->page);
if (IS_ERR(fio->encrypted_page)) {
err = PTR_ERR(fio->encrypted_page);
@@ -1429,6 +1456,10 @@ put_next:
f2fs_wait_on_page_writeback(page, DATA);
+ /* wait for GCed encrypted page writeback */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+
if (len == PAGE_CACHE_SIZE)
goto out_update;
if (PageUptodate(page))
@@ -1551,10 +1582,16 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- if (iov_iter_rw(iter) == WRITE)
+ if (iov_iter_rw(iter) == WRITE) {
__allocate_data_blocks(inode, offset, count);
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
+ err = -EIO;
+ goto out;
+ }
+ }
err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);
+out:
if (err < 0 && iov_iter_rw(iter) == WRITE)
f2fs_write_failed(mapping, offset + count);
@@ -1636,12 +1673,13 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
- /* 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;
- }
+ if (f2fs_has_inline_data(inode))
+ return 0;
+
+ /* make sure allocating whole blocks */
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+ filemap_write_and_wait(mapping);
+
return generic_block_bmap(mapping, block, get_data_block_bmap);
}
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index d013d8479753..478e5d54154f 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -33,11 +33,11 @@ static void update_general_status(struct f2fs_sb_info *sbi)
int i;
/* validation check of the segment numbers */
- si->hit_largest = atomic_read(&sbi->read_hit_largest);
- si->hit_cached = atomic_read(&sbi->read_hit_cached);
- si->hit_rbtree = atomic_read(&sbi->read_hit_rbtree);
+ si->hit_largest = atomic64_read(&sbi->read_hit_largest);
+ si->hit_cached = atomic64_read(&sbi->read_hit_cached);
+ si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree);
si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree;
- si->total_ext = atomic_read(&sbi->total_hit_ext);
+ si->total_ext = atomic64_read(&sbi->total_hit_ext);
si->ext_tree = sbi->total_ext_tree;
si->ext_node = atomic_read(&sbi->total_ext_node);
si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
@@ -118,7 +118,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
}
}
dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
- si->bimodal = div_u64(bimodal, dist);
+ si->bimodal = div64_u64(bimodal, dist);
if (si->dirty_count)
si->avg_vblocks = div_u64(total_vblocks, ndirty);
else
@@ -198,9 +198,9 @@ get_cache:
si->page_mem = 0;
npages = NODE_MAPPING(sbi)->nrpages;
- si->page_mem += npages << PAGE_CACHE_SHIFT;
+ si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
npages = META_MAPPING(sbi)->nrpages;
- si->page_mem += npages << PAGE_CACHE_SHIFT;
+ si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
}
static int stat_show(struct seq_file *s, void *v)
@@ -283,12 +283,12 @@ static int stat_show(struct seq_file *s, void *v)
seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks,
si->bg_node_blks);
seq_puts(s, "\nExtent Cache:\n");
- seq_printf(s, " - Hit Count: L1-1:%d L1-2:%d L2:%d\n",
+ seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n",
si->hit_largest, si->hit_cached,
si->hit_rbtree);
- seq_printf(s, " - Hit Ratio: %d%% (%d / %d)\n",
+ seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n",
!si->total_ext ? 0 :
- (si->hit_total * 100) / si->total_ext,
+ div64_u64(si->hit_total * 100, si->total_ext),
si->hit_total, si->total_ext);
seq_printf(s, " - Inner Struct Count: tree: %d, node: %d\n",
si->ext_tree, si->ext_node);
@@ -333,13 +333,13 @@ static int stat_show(struct seq_file *s, void *v)
/* memory footprint */
update_mem_info(si->sbi);
- seq_printf(s, "\nMemory: %u KB\n",
+ seq_printf(s, "\nMemory: %llu KB\n",
(si->base_mem + si->cache_mem + si->page_mem) >> 10);
- seq_printf(s, " - static: %u KB\n",
+ seq_printf(s, " - static: %llu KB\n",
si->base_mem >> 10);
- seq_printf(s, " - cached: %u KB\n",
+ seq_printf(s, " - cached: %llu KB\n",
si->cache_mem >> 10);
- seq_printf(s, " - paged : %u KB\n",
+ seq_printf(s, " - paged : %llu KB\n",
si->page_mem >> 10);
}
mutex_unlock(&f2fs_stat_mutex);
@@ -378,10 +378,10 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
si->sbi = sbi;
sbi->stat_info = si;
- atomic_set(&sbi->total_hit_ext, 0);
- atomic_set(&sbi->read_hit_rbtree, 0);
- atomic_set(&sbi->read_hit_largest, 0);
- atomic_set(&sbi->read_hit_cached, 0);
+ atomic64_set(&sbi->total_hit_ext, 0);
+ atomic64_set(&sbi->read_hit_rbtree, 0);
+ atomic64_set(&sbi->read_hit_largest, 0);
+ atomic64_set(&sbi->read_hit_cached, 0);
atomic_set(&sbi->inline_xattr, 0);
atomic_set(&sbi->inline_inode, 0);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 8f15fc134040..7c1678ba8f92 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -258,7 +258,7 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
if (f2fs_has_inline_dentry(dir))
return f2fs_parent_inline_dir(dir, p);
- page = get_lock_data_page(dir, 0);
+ page = get_lock_data_page(dir, 0, false);
if (IS_ERR(page))
return NULL;
@@ -740,7 +740,7 @@ bool f2fs_empty_dir(struct inode *dir)
return f2fs_empty_inline_dir(dir);
for (bidx = 0; bidx < nblock; bidx++) {
- dentry_page = get_lock_data_page(dir, bidx);
+ dentry_page = get_lock_data_page(dir, bidx, false);
if (IS_ERR(dentry_page)) {
if (PTR_ERR(dentry_page) == -ENOENT)
continue;
@@ -787,7 +787,6 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
else
d_type = DT_UNKNOWN;
- /* encrypted case */
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
@@ -795,12 +794,20 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
int save_len = fstr->len;
int ret;
+ de_name.name = kmalloc(de_name.len, GFP_NOFS);
+ if (!de_name.name)
+ return false;
+
+ memcpy(de_name.name, d->filename[bit_pos], de_name.len);
+
ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code,
&de_name, fstr);
- de_name = *fstr;
- fstr->len = save_len;
+ kfree(de_name.name);
if (ret < 0)
return true;
+
+ de_name = *fstr;
+ fstr->len = save_len;
}
if (!dir_emit(ctx, de_name.name, de_name.len,
@@ -847,7 +854,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
for (; n < npages; n++) {
- dentry_page = get_lock_data_page(inode, n);
+ dentry_page = get_lock_data_page(inode, n, false);
if (IS_ERR(dentry_page))
continue;
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 997ac86f2a1d..7ddba812e11b 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -155,11 +155,12 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
return count - et->count;
}
-static void __drop_largest_extent(struct inode *inode, pgoff_t fofs)
+static void __drop_largest_extent(struct inode *inode,
+ pgoff_t fofs, unsigned int len)
{
struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
- if (largest->fofs <= fofs && largest->fofs + largest->len > fofs)
+ if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs)
largest->len = 0;
}
@@ -168,7 +169,7 @@ void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs)
if (!f2fs_may_extent_tree(inode))
return;
- __drop_largest_extent(inode, fofs);
+ __drop_largest_extent(inode, fofs, 1);
}
void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
@@ -350,8 +351,7 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
}
if (en) {
- if (en->ei.len > et->largest.len)
- et->largest = en->ei;
+ __try_update_largest_extent(et, en);
et->cached_en = en;
}
return en;
@@ -388,18 +388,17 @@ do_insert:
if (!en)
return NULL;
- if (en->ei.len > et->largest.len)
- et->largest = en->ei;
+ __try_update_largest_extent(et, en);
et->cached_en = en;
return en;
}
-unsigned int f2fs_update_extent_tree_range(struct inode *inode,
+static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
pgoff_t fofs, block_t blkaddr, unsigned int len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et = F2FS_I(inode)->extent_tree;
- struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL;
+ struct extent_node *en = NULL, *en1 = NULL;
struct extent_node *prev_en = NULL, *next_en = NULL;
struct extent_info ei, dei, prev;
struct rb_node **insert_p = NULL, *insert_parent = NULL;
@@ -409,6 +408,8 @@ unsigned int f2fs_update_extent_tree_range(struct inode *inode,
if (!et)
return false;
+ trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
+
write_lock(&et->lock);
if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) {
@@ -419,148 +420,99 @@ unsigned int f2fs_update_extent_tree_range(struct inode *inode,
prev = et->largest;
dei.len = 0;
- /* we do not guarantee that the largest extent is cached all the time */
- __drop_largest_extent(inode, fofs);
+ /*
+ * drop largest extent before lookup, in case it's already
+ * been shrunk from extent tree
+ */
+ __drop_largest_extent(inode, fofs, len);
/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
en = __lookup_extent_tree_ret(et, fofs, &prev_en, &next_en,
&insert_p, &insert_parent);
- if (!en) {
- if (next_en) {
- en = next_en;
- f2fs_bug_on(sbi, en->ei.fofs <= pos);
- pos = en->ei.fofs;
- } else {
- /*
- * skip searching in the tree since there is no
- * larger extent node in the cache.
- */
- goto update_extent;
- }
- }
+ if (!en)
+ en = next_en;
/* 2. invlidate all extent nodes in range [fofs, fofs + len - 1] */
- while (en) {
- struct rb_node *node;
+ while (en && en->ei.fofs < end) {
+ unsigned int org_end;
+ int parts = 0; /* # of parts current extent split into */
- if (pos >= end)
- break;
+ next_en = en1 = NULL;
dei = en->ei;
- en1 = en2 = NULL;
+ org_end = dei.fofs + dei.len;
+ f2fs_bug_on(sbi, pos >= org_end);
- node = rb_next(&en->rb_node);
+ if (pos > dei.fofs && pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
+ en->ei.len = pos - en->ei.fofs;
+ prev_en = en;
+ parts = 1;
+ }
- /*
- * 2.1 there are four cases when we invalidate blkaddr in extent
- * node, |V: valid address, X: will be invalidated|
- */
- /* case#1, invalidate right part of extent node |VVVVVXXXXX| */
- if (pos > dei.fofs && end >= dei.fofs + dei.len) {
- en->ei.len = pos - dei.fofs;
-
- if (en->ei.len < F2FS_MIN_EXTENT_LEN) {
- __detach_extent_node(sbi, et, en);
- insert_p = NULL;
- insert_parent = NULL;
- goto update;
+ if (end < org_end && org_end - end >= F2FS_MIN_EXTENT_LEN) {
+ if (parts) {
+ set_extent_info(&ei, end,
+ end - dei.fofs + dei.blk,
+ org_end - end);
+ en1 = __insert_extent_tree(sbi, et, &ei,
+ NULL, NULL);
+ next_en = en1;
+ } else {
+ en->ei.fofs = end;
+ en->ei.blk += end - dei.fofs;
+ en->ei.len -= end - dei.fofs;
+ next_en = en;
}
-
- if (__is_extent_same(&dei, &et->largest))
- et->largest = en->ei;
- goto next;
+ parts++;
}
- /* case#2, invalidate left part of extent node |XXXXXVVVVV| */
- if (pos <= dei.fofs && end < dei.fofs + dei.len) {
- en->ei.fofs = end;
- en->ei.blk += end - dei.fofs;
- en->ei.len -= end - dei.fofs;
-
- if (en->ei.len < F2FS_MIN_EXTENT_LEN) {
- __detach_extent_node(sbi, et, en);
- insert_p = NULL;
- insert_parent = NULL;
- goto update;
- }
+ if (!next_en) {
+ struct rb_node *node = rb_next(&en->rb_node);
- if (__is_extent_same(&dei, &et->largest))
- et->largest = en->ei;
- goto next;
+ next_en = node ?
+ rb_entry(node, struct extent_node, rb_node)
+ : NULL;
}
- __detach_extent_node(sbi, et, en);
+ if (parts)
+ __try_update_largest_extent(et, en);
+ else
+ __detach_extent_node(sbi, et, en);
/*
- * if we remove node in rb-tree, our parent node pointer may
- * point the wrong place, discard them.
+ * if original extent is split into zero or two parts, extent
+ * tree has been altered by deletion or insertion, therefore
+ * invalidate pointers regard to tree.
*/
- insert_p = NULL;
- insert_parent = NULL;
-
- /* case#3, invalidate entire extent node |XXXXXXXXXX| */
- if (pos <= dei.fofs && end >= dei.fofs + dei.len) {
- if (__is_extent_same(&dei, &et->largest))
- et->largest.len = 0;
- goto update;
+ if (parts != 1) {
+ insert_p = NULL;
+ insert_parent = NULL;
}
- /*
- * case#4, invalidate data in the middle of extent node
- * |VVVXXXXVVV|
- */
- if (dei.len > F2FS_MIN_EXTENT_LEN) {
- unsigned int endofs;
-
- /* insert left part of split extent into cache */
- if (pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
- set_extent_info(&ei, dei.fofs, dei.blk,
- pos - dei.fofs);
- en1 = __insert_extent_tree(sbi, et, &ei,
- NULL, NULL);
- }
-
- /* insert right part of split extent into cache */
- endofs = dei.fofs + dei.len;
- if (endofs - end >= F2FS_MIN_EXTENT_LEN) {
- set_extent_info(&ei, end,
- end - dei.fofs + dei.blk,
- endofs - end);
- en2 = __insert_extent_tree(sbi, et, &ei,
- NULL, NULL);
- }
- }
-update:
- /* 2.2 update in global extent list */
+ /* update in global extent list */
spin_lock(&sbi->extent_lock);
- if (en && !list_empty(&en->list))
+ if (!parts && !list_empty(&en->list))
list_del(&en->list);
if (en1)
list_add_tail(&en1->list, &sbi->extent_list);
- if (en2)
- list_add_tail(&en2->list, &sbi->extent_list);
spin_unlock(&sbi->extent_lock);
- /* 2.3 release extent node */
- if (en)
+ /* release extent node */
+ if (!parts)
kmem_cache_free(extent_node_slab, en);
-next:
- en = node ? rb_entry(node, struct extent_node, rb_node) : NULL;
- next_en = en;
- if (en)
- pos = en->ei.fofs;
+
+ en = next_en;
}
-update_extent:
/* 3. update extent in extent cache */
if (blkaddr) {
struct extent_node *den = NULL;
set_extent_info(&ei, fofs, blkaddr, len);
- en3 = __try_merge_extent_node(sbi, et, &ei, &den,
+ en1 = __try_merge_extent_node(sbi, et, &ei, &den,
prev_en, next_en);
- if (!en3)
- en3 = __insert_extent_tree(sbi, et, &ei,
+ if (!en1)
+ en1 = __insert_extent_tree(sbi, et, &ei,
insert_p, insert_parent);
/* give up extent_cache, if split and small updates happen */
@@ -572,11 +524,11 @@ update_extent:
}
spin_lock(&sbi->extent_lock);
- if (en3) {
- if (list_empty(&en3->list))
- list_add_tail(&en3->list, &sbi->extent_list);
+ if (en1) {
+ if (list_empty(&en1->list))
+ list_add_tail(&en1->list, &sbi->extent_list);
else
- list_move_tail(&en3->list, &sbi->extent_list);
+ list_move_tail(&en1->list, &sbi->extent_list);
}
if (den && !list_empty(&den->list))
list_del(&den->list);
@@ -650,6 +602,11 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
}
spin_unlock(&sbi->extent_lock);
+ /*
+ * reset ino for searching victims from beginning of global extent tree.
+ */
+ ino = F2FS_ROOT_INO(sbi);
+
while ((found = radix_tree_gang_lookup(root,
(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
unsigned i;
@@ -663,7 +620,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
write_unlock(&et->lock);
if (node_cnt + tree_cnt >= nr_shrink)
- break;
+ goto unlock_out;
}
}
unlock_out:
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index f1a90ffd7cad..9db5500d63d9 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -19,6 +19,7 @@
#include <linux/magic.h>
#include <linux/kobject.h>
#include <linux/sched.h>
+#include <linux/vmalloc.h>
#include <linux/bio.h>
#ifdef CONFIG_F2FS_CHECK_FS
@@ -52,6 +53,7 @@
#define F2FS_MOUNT_NOBARRIER 0x00000800
#define F2FS_MOUNT_FASTBOOT 0x00001000
#define F2FS_MOUNT_EXTENT_CACHE 0x00002000
+#define F2FS_MOUNT_FORCE_FG_GC 0x00004000
#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -122,6 +124,7 @@ enum {
(SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
#define BATCHED_TRIM_BLOCKS(sbi) \
(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
+#define DEF_CP_INTERVAL 60 /* 60 secs */
struct cp_control {
int reason;
@@ -230,6 +233,7 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
#define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4)
#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5)
#define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6)
+#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7)
#define F2FS_IOC_SET_ENCRYPTION_POLICY \
_IOR('f', 19, struct f2fs_encryption_policy)
@@ -246,6 +250,7 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
#define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */
#define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */
#define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */
+#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
@@ -492,12 +497,20 @@ static inline bool __is_front_mergeable(struct extent_info *cur,
return __is_extent_mergeable(cur, front);
}
+static inline void __try_update_largest_extent(struct extent_tree *et,
+ struct extent_node *en)
+{
+ if (en->ei.len > et->largest.len)
+ et->largest = en->ei;
+}
+
struct f2fs_nm_info {
block_t nat_blkaddr; /* base disk address of NAT */
nid_t max_nid; /* maximum possible node ids */
nid_t available_nids; /* maximum available node ids */
nid_t next_scan_nid; /* the next nid to be scanned */
unsigned int ram_thresh; /* control the memory footprint */
+ unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
@@ -724,6 +737,7 @@ struct f2fs_sb_info {
struct rw_semaphore node_write; /* locking node writes */
struct mutex writepages; /* mutex for writepages() */
wait_queue_head_t cp_wait;
+ long cp_expires, cp_interval; /* next expected periodic cp */
struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
@@ -787,10 +801,10 @@ struct f2fs_sb_info {
unsigned int segment_count[2]; /* # of allocated segments */
unsigned int block_count[2]; /* # of allocated blocks */
atomic_t inplace_count; /* # of inplace update */
- atomic_t total_hit_ext; /* # of lookup extent cache */
- atomic_t read_hit_rbtree; /* # of hit rbtree extent node */
- atomic_t read_hit_largest; /* # of hit largest extent node */
- atomic_t read_hit_cached; /* # of hit cached extent node */
+ atomic64_t total_hit_ext; /* # of lookup extent cache */
+ atomic64_t read_hit_rbtree; /* # of hit rbtree extent node */
+ atomic64_t read_hit_largest; /* # of hit largest extent node */
+ atomic64_t read_hit_cached; /* # of hit cached extent node */
atomic_t inline_xattr; /* # of inline_xattr inodes */
atomic_t inline_inode; /* # of inline_data inodes */
atomic_t inline_dir; /* # of inline_dentry inodes */
@@ -1220,6 +1234,24 @@ static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi)
return sbi->total_valid_inode_count;
}
+static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
+ pgoff_t index, bool for_write)
+{
+ if (!for_write)
+ return grab_cache_page(mapping, index);
+ return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+}
+
+static inline void f2fs_copy_page(struct page *src, struct page *dst)
+{
+ char *src_kaddr = kmap(src);
+ char *dst_kaddr = kmap(dst);
+
+ memcpy(dst_kaddr, src_kaddr, PAGE_SIZE);
+ kunmap(dst);
+ kunmap(src);
+}
+
static inline void f2fs_put_page(struct page *page, int unlock)
{
if (!page)
@@ -1579,6 +1611,26 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
return S_ISREG(mode);
}
+static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kmalloc(size, flags | __GFP_NOWARN);
+ if (!ret)
+ ret = __vmalloc(size, flags, PAGE_KERNEL);
+ return ret;
+}
+
+static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kzalloc(size, flags | __GFP_NOWARN);
+ if (!ret)
+ ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
+ return ret;
+}
+
#define get_inode_mode(i) \
((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
@@ -1721,6 +1773,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *);
int create_flush_cmd_control(struct f2fs_sb_info *);
void destroy_flush_cmd_control(struct f2fs_sb_info *);
void invalidate_blocks(struct f2fs_sb_info *, block_t);
+bool is_checkpointed_data(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 *, struct cp_control *);
void release_discard_addrs(struct f2fs_sb_info *);
@@ -1739,6 +1792,7 @@ void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *,
void allocate_data_block(struct f2fs_sb_info *, struct page *,
block_t, block_t *, struct f2fs_summary *, int);
void f2fs_wait_on_page_writeback(struct page *, enum page_type);
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
void write_data_summaries(struct f2fs_sb_info *, block_t);
void write_node_summaries(struct f2fs_sb_info *, block_t);
int lookup_journal_in_cursum(struct f2fs_summary_block *,
@@ -1754,8 +1808,9 @@ void destroy_segment_manager_caches(void);
*/
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
+struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
-int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int);
+int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
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);
@@ -1787,9 +1842,9 @@ void set_data_blkaddr(struct dnode_of_data *);
int reserve_new_block(struct dnode_of_data *);
int f2fs_get_block(struct dnode_of_data *, pgoff_t);
int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-struct page *get_read_data_page(struct inode *, pgoff_t, int);
+struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
struct page *find_data_page(struct inode *, pgoff_t);
-struct page *get_lock_data_page(struct inode *, pgoff_t);
+struct page *get_lock_data_page(struct inode *, pgoff_t, bool);
struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
int do_write_data_page(struct f2fs_io_info *);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
@@ -1802,7 +1857,7 @@ int f2fs_release_page(struct page *, gfp_t);
int start_gc_thread(struct f2fs_sb_info *);
void stop_gc_thread(struct f2fs_sb_info *);
block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
-int f2fs_gc(struct f2fs_sb_info *);
+int f2fs_gc(struct f2fs_sb_info *, bool);
void build_gc_manager(struct f2fs_sb_info *);
/*
@@ -1820,7 +1875,8 @@ struct f2fs_stat_info {
struct f2fs_sb_info *sbi;
int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs;
int main_area_segs, main_area_sections, main_area_zones;
- int hit_largest, hit_cached, hit_rbtree, hit_total, total_ext;
+ unsigned long long hit_largest, hit_cached, hit_rbtree;
+ unsigned long long hit_total, total_ext;
int ext_tree, ext_node;
int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
int nats, dirty_nats, sits, dirty_sits, fnids;
@@ -1844,7 +1900,7 @@ struct f2fs_stat_info {
unsigned int segment_count[2];
unsigned int block_count[2];
unsigned int inplace_count;
- unsigned base_mem, cache_mem, page_mem;
+ unsigned long long base_mem, cache_mem, page_mem;
};
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
@@ -1857,10 +1913,10 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
#define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++)
#define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++)
#define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--)
-#define stat_inc_total_hit(sbi) (atomic_inc(&(sbi)->total_hit_ext))
-#define stat_inc_rbtree_node_hit(sbi) (atomic_inc(&(sbi)->read_hit_rbtree))
-#define stat_inc_largest_node_hit(sbi) (atomic_inc(&(sbi)->read_hit_largest))
-#define stat_inc_cached_node_hit(sbi) (atomic_inc(&(sbi)->read_hit_cached))
+#define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext))
+#define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree))
+#define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest))
+#define stat_inc_cached_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_cached))
#define stat_inc_inline_xattr(inode) \
do { \
if (f2fs_has_inline_xattr(inode)) \
@@ -1998,6 +2054,8 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *,
bool f2fs_empty_inline_dir(struct inode *);
int f2fs_read_inline_dir(struct file *, struct dir_context *,
struct f2fs_str *);
+int f2fs_inline_data_fiemap(struct inode *,
+ struct fiemap_extent_info *, __u64, __u64);
/*
* shrinker.c
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 8120f8685141..a197215ad52b 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -74,7 +74,8 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
goto mapped;
/* page is wholly or partially inside EOF */
- if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
+ if (((loff_t)(page->index + 1) << PAGE_CACHE_SHIFT) >
+ i_size_read(inode)) {
unsigned offset;
offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
@@ -86,6 +87,11 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
mapped:
/* fill the page */
f2fs_wait_on_page_writeback(page, DATA);
+
+ /* wait for GCed encrypted page writeback */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+
/* if gced page is attached, don't write to cold segment */
clear_cold_data(page);
out:
@@ -343,7 +349,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
- for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+ for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
if (err && err != -ENOENT) {
@@ -504,14 +510,14 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
return 0;
if (cache_only) {
- page = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, false);
if (page && PageUptodate(page))
goto truncate_out;
f2fs_put_page(page, 1);
return 0;
}
- page = get_lock_data_page(inode, index);
+ page = get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return 0;
truncate_out:
@@ -680,6 +686,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
* larger than i_size.
*/
truncate_setsize(inode, attr->ia_size);
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
}
}
@@ -738,23 +745,31 @@ static int fill_zero(struct inode *inode, pgoff_t index,
int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
- pgoff_t index;
int err;
- for (index = pg_start; index < pg_end; index++) {
+ while (pg_start < pg_end) {
struct dnode_of_data dn;
+ pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
if (err) {
- if (err == -ENOENT)
+ if (err == -ENOENT) {
+ pg_start++;
continue;
+ }
return err;
}
- if (dn.data_blkaddr != NULL_ADDR)
- truncate_data_blocks_range(&dn, 1);
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
+
+ f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
+
+ truncate_data_blocks_range(&dn, count);
f2fs_put_dnode(&dn);
+
+ pg_start += count;
}
return 0;
}
@@ -765,9 +780,6 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
loff_t off_start, off_end;
int ret = 0;
- if (!S_ISREG(inode->i_mode))
- return -EOPNOTSUPP;
-
if (f2fs_has_inline_data(inode)) {
ret = f2fs_convert_inline_inode(inode);
if (ret)
@@ -805,8 +817,8 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
f2fs_balance_fs(sbi);
- blk_start = pg_start << PAGE_CACHE_SHIFT;
- blk_end = pg_end << PAGE_CACHE_SHIFT;
+ blk_start = (loff_t)pg_start << PAGE_CACHE_SHIFT;
+ blk_end = (loff_t)pg_end << PAGE_CACHE_SHIFT;
truncate_inode_pages_range(mapping, blk_start,
blk_end - 1);
@@ -819,86 +831,100 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
return ret;
}
-static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
+static int __exchange_data_block(struct inode *inode, pgoff_t src,
+ pgoff_t dst, bool full)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
- pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
- int ret = 0;
-
- for (; end < nrpages; start++, end++) {
- block_t new_addr, old_addr;
-
- f2fs_lock_op(sbi);
+ block_t new_addr;
+ bool do_replace = false;
+ int ret;
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = get_dnode_of_data(&dn, end, LOOKUP_NODE_RA);
- if (ret && ret != -ENOENT) {
- goto out;
- } else if (ret == -ENOENT) {
- new_addr = NULL_ADDR;
- } else {
- new_addr = dn.data_blkaddr;
- truncate_data_blocks_range(&dn, 1);
- f2fs_put_dnode(&dn);
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, src, LOOKUP_NODE_RA);
+ if (ret && ret != -ENOENT) {
+ return ret;
+ } else if (ret == -ENOENT) {
+ new_addr = NULL_ADDR;
+ } else {
+ new_addr = dn.data_blkaddr;
+ if (!is_checkpointed_data(sbi, new_addr)) {
+ dn.data_blkaddr = NULL_ADDR;
+ /* do not invalidate this block address */
+ set_data_blkaddr(&dn);
+ f2fs_update_extent_cache(&dn);
+ do_replace = true;
}
+ f2fs_put_dnode(&dn);
+ }
- if (new_addr == NULL_ADDR) {
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = get_dnode_of_data(&dn, start, LOOKUP_NODE_RA);
- if (ret && ret != -ENOENT) {
- goto out;
- } else if (ret == -ENOENT) {
- f2fs_unlock_op(sbi);
- continue;
- }
+ if (new_addr == NULL_ADDR)
+ return full ? truncate_hole(inode, dst, dst + 1) : 0;
- if (dn.data_blkaddr == NULL_ADDR) {
- f2fs_put_dnode(&dn);
- f2fs_unlock_op(sbi);
- continue;
- } else {
- truncate_data_blocks_range(&dn, 1);
- }
+ if (do_replace) {
+ struct page *ipage = get_node_page(sbi, inode->i_ino);
+ struct node_info ni;
- f2fs_put_dnode(&dn);
- } else {
- struct page *ipage;
+ if (IS_ERR(ipage)) {
+ ret = PTR_ERR(ipage);
+ goto err_out;
+ }
- ipage = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(ipage)) {
- ret = PTR_ERR(ipage);
- goto out;
- }
+ set_new_dnode(&dn, inode, ipage, NULL, 0);
+ ret = f2fs_reserve_block(&dn, dst);
+ if (ret)
+ goto err_out;
- set_new_dnode(&dn, inode, ipage, NULL, 0);
- ret = f2fs_reserve_block(&dn, start);
- if (ret)
- goto out;
+ truncate_data_blocks_range(&dn, 1);
- old_addr = dn.data_blkaddr;
- if (old_addr != NEW_ADDR && new_addr == NEW_ADDR) {
- dn.data_blkaddr = NULL_ADDR;
- f2fs_update_extent_cache(&dn);
- invalidate_blocks(sbi, old_addr);
+ get_node_info(sbi, dn.nid, &ni);
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
+ ni.version, true);
+ f2fs_put_dnode(&dn);
+ } else {
+ struct page *psrc, *pdst;
+
+ psrc = get_lock_data_page(inode, src, true);
+ if (IS_ERR(psrc))
+ return PTR_ERR(psrc);
+ pdst = get_new_data_page(inode, NULL, dst, false);
+ if (IS_ERR(pdst)) {
+ f2fs_put_page(psrc, 1);
+ return PTR_ERR(pdst);
+ }
+ f2fs_copy_page(psrc, pdst);
+ set_page_dirty(pdst);
+ f2fs_put_page(pdst, 1);
+ f2fs_put_page(psrc, 1);
- dn.data_blkaddr = new_addr;
- set_data_blkaddr(&dn);
- } else if (new_addr != NEW_ADDR) {
- struct node_info ni;
+ return truncate_hole(inode, src, src + 1);
+ }
+ return 0;
- get_node_info(sbi, dn.nid, &ni);
- f2fs_replace_block(sbi, &dn, old_addr, new_addr,
- ni.version, true);
- }
+err_out:
+ if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) {
+ dn.data_blkaddr = new_addr;
+ set_data_blkaddr(&dn);
+ f2fs_update_extent_cache(&dn);
+ f2fs_put_dnode(&dn);
+ }
+ return ret;
+}
- f2fs_put_dnode(&dn);
- }
+static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+ int ret = 0;
+
+ for (; end < nrpages; start++, end++) {
+ f2fs_balance_fs(sbi);
+ f2fs_lock_op(sbi);
+ ret = __exchange_data_block(inode, end, start, true);
f2fs_unlock_op(sbi);
+ if (ret)
+ break;
}
- return 0;
-out:
- f2fs_unlock_op(sbi);
return ret;
}
@@ -908,9 +934,6 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
loff_t new_size;
int ret;
- if (!S_ISREG(inode->i_mode))
- return -EINVAL;
-
if (offset + len >= i_size_read(inode))
return -EINVAL;
@@ -940,7 +963,12 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
+ /* write out all moved pages, if possible */
+ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ truncate_pagecache(inode, offset);
+
new_size = i_size_read(inode) - len;
+ truncate_pagecache(inode, new_size);
ret = truncate_blocks(inode, new_size, true);
if (!ret)
@@ -959,9 +987,6 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
loff_t off_start, off_end;
int ret = 0;
- if (!S_ISREG(inode->i_mode))
- return -EINVAL;
-
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
return ret;
@@ -1003,7 +1028,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
return ret;
new_size = max_t(loff_t, new_size,
- pg_start << PAGE_CACHE_SHIFT);
+ (loff_t)pg_start << PAGE_CACHE_SHIFT);
}
for (index = pg_start; index < pg_end; index++) {
@@ -1039,7 +1064,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
f2fs_unlock_op(sbi);
new_size = max_t(loff_t, new_size,
- (index + 1) << PAGE_CACHE_SHIFT);
+ (loff_t)(index + 1) << PAGE_CACHE_SHIFT);
}
if (off_end) {
@@ -1066,10 +1091,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t pg_start, pg_end, delta, nrpages, idx;
loff_t new_size;
- int ret;
-
- if (!S_ISREG(inode->i_mode))
- return -EINVAL;
+ int ret = 0;
new_size = i_size_read(inode) + len;
if (new_size > inode->i_sb->s_maxbytes)
@@ -1107,57 +1129,19 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) {
- struct dnode_of_data dn;
- struct page *ipage;
- block_t new_addr, old_addr;
-
f2fs_lock_op(sbi);
-
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = get_dnode_of_data(&dn, idx, LOOKUP_NODE_RA);
- if (ret && ret != -ENOENT) {
- goto out;
- } else if (ret == -ENOENT) {
- goto next;
- } else if (dn.data_blkaddr == NULL_ADDR) {
- f2fs_put_dnode(&dn);
- goto next;
- } else {
- new_addr = dn.data_blkaddr;
- truncate_data_blocks_range(&dn, 1);
- f2fs_put_dnode(&dn);
- }
-
- ipage = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(ipage)) {
- ret = PTR_ERR(ipage);
- goto out;
- }
-
- set_new_dnode(&dn, inode, ipage, NULL, 0);
- ret = f2fs_reserve_block(&dn, idx + delta);
- if (ret)
- goto out;
-
- old_addr = dn.data_blkaddr;
- f2fs_bug_on(sbi, old_addr != NEW_ADDR);
-
- if (new_addr != NEW_ADDR) {
- struct node_info ni;
-
- get_node_info(sbi, dn.nid, &ni);
- f2fs_replace_block(sbi, &dn, old_addr, new_addr,
- ni.version, true);
- }
- f2fs_put_dnode(&dn);
-next:
+ ret = __exchange_data_block(inode, idx, idx + delta, false);
f2fs_unlock_op(sbi);
+ if (ret)
+ break;
}
- i_size_write(inode, new_size);
- return 0;
-out:
- f2fs_unlock_op(sbi);
+ /* write out all moved pages, if possible */
+ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ truncate_pagecache(inode, offset);
+
+ if (!ret)
+ i_size_write(inode, new_size);
return ret;
}
@@ -1204,9 +1188,10 @@ noalloc:
if (pg_start == pg_end)
new_size = offset + len;
else if (index == pg_start && off_start)
- new_size = (index + 1) << PAGE_CACHE_SHIFT;
+ new_size = (loff_t)(index + 1) << PAGE_CACHE_SHIFT;
else if (index == pg_end)
- new_size = (index << PAGE_CACHE_SHIFT) + off_end;
+ new_size = ((loff_t)index << PAGE_CACHE_SHIFT) +
+ off_end;
else
new_size += PAGE_CACHE_SIZE;
}
@@ -1228,6 +1213,10 @@ static long f2fs_fallocate(struct file *file, int mode,
struct inode *inode = file_inode(file);
long ret = 0;
+ /* f2fs only support ->fallocate for regular file */
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
if (f2fs_encrypted_inode(inode) &&
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
@@ -1437,8 +1426,7 @@ static int f2fs_ioc_release_volatile_write(struct file *filp)
if (!f2fs_is_first_block_written(inode))
return truncate_partial_data_page(inode, 0, true);
- punch_hole(inode, 0, F2FS_BLKSIZE);
- return 0;
+ return punch_hole(inode, 0, F2FS_BLKSIZE);
}
static int f2fs_ioc_abort_volatile_write(struct file *filp)
@@ -1455,13 +1443,9 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
f2fs_balance_fs(F2FS_I_SB(inode));
- if (f2fs_is_atomic_file(inode)) {
- clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
- commit_inmem_pages(inode, true);
- }
-
- if (f2fs_is_volatile_file(inode))
- clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+ clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+ commit_inmem_pages(inode, true);
mnt_drop_write_file(filp);
return ret;
@@ -1496,6 +1480,10 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
case F2FS_GOING_DOWN_NOSYNC:
f2fs_stop_checkpoint(sbi);
break;
+ case F2FS_GOING_DOWN_METAFLUSH:
+ sync_meta_pages(sbi, META, LONG_MAX);
+ f2fs_stop_checkpoint(sbi);
+ break;
default:
return -EINVAL;
}
@@ -1616,27 +1604,44 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- __u32 i, count;
+ __u32 sync;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (get_user(count, (__u32 __user *)arg))
+ if (get_user(sync, (__u32 __user *)arg))
return -EFAULT;
- if (!count || count > F2FS_BATCH_GC_MAX_NUM)
- return -EINVAL;
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
- for (i = 0; i < count; i++) {
+ if (!sync) {
if (!mutex_trylock(&sbi->gc_mutex))
- break;
-
- if (f2fs_gc(sbi))
- break;
+ return -EBUSY;
+ } else {
+ mutex_lock(&sbi->gc_mutex);
}
- if (put_user(i, (__u32 __user *)arg))
- return -EFAULT;
+ return f2fs_gc(sbi, sync);
+}
+
+static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct cp_control cpc;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ cpc.reason = __get_cp_reason(sbi);
+
+ mutex_lock(&sbi->gc_mutex);
+ write_checkpoint(sbi, &cpc);
+ mutex_unlock(&sbi->gc_mutex);
return 0;
}
@@ -1672,6 +1677,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_get_encryption_pwsalt(filp, arg);
case F2FS_IOC_GARBAGE_COLLECT:
return f2fs_ioc_gc(filp, arg);
+ case F2FS_IOC_WRITE_CHECKPOINT:
+ return f2fs_ioc_write_checkpoint(filp, arg);
default:
return -ENOTTY;
}
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 782b8e72c094..fedbf67a0842 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -78,9 +78,12 @@ static int gc_thread_func(void *data)
stat_inc_bggc_count(sbi);
/* if return value is not zero, no victim was selected */
- if (f2fs_gc(sbi))
+ if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC)))
wait_ms = gc_th->no_gc_sleep_time;
+ trace_f2fs_background_gc(sbi->sb, wait_ms,
+ prefree_segments(sbi), free_segments(sbi));
+
/* balancing f2fs's metadata periodically */
f2fs_balance_fs_bg(sbi);
@@ -257,6 +260,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct victim_sel_policy p;
unsigned int secno, max_cost;
+ unsigned int last_segment = MAIN_SEGS(sbi);
int nsearched = 0;
mutex_lock(&dirty_i->seglist_lock);
@@ -267,6 +271,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
p.min_segno = NULL_SEGNO;
p.min_cost = max_cost = get_max_cost(sbi, &p);
+ if (p.max_search == 0)
+ goto out;
+
if (p.alloc_mode == LFS && gc_type == FG_GC) {
p.min_segno = check_bg_victims(sbi);
if (p.min_segno != NULL_SEGNO)
@@ -277,9 +284,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
unsigned long cost;
unsigned int segno;
- segno = find_next_bit(p.dirty_segmap, MAIN_SEGS(sbi), p.offset);
- if (segno >= MAIN_SEGS(sbi)) {
+ segno = find_next_bit(p.dirty_segmap, last_segment, p.offset);
+ if (segno >= last_segment) {
if (sbi->last_victim[p.gc_mode]) {
+ last_segment = sbi->last_victim[p.gc_mode];
sbi->last_victim[p.gc_mode] = 0;
p.offset = 0;
continue;
@@ -327,6 +335,7 @@ got_it:
sbi->cur_victim_sec,
prefree_segments(sbi), free_segments(sbi));
}
+out:
mutex_unlock(&dirty_i->seglist_lock);
return (p.min_segno == NULL_SEGNO) ? 0 : 1;
@@ -541,7 +550,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
int err;
/* do not read out */
- page = grab_cache_page(inode->i_mapping, bidx);
+ page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
if (!page)
return;
@@ -550,8 +559,16 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
if (err)
goto out;
- if (unlikely(dn.data_blkaddr == NULL_ADDR))
+ if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
+ ClearPageUptodate(page);
goto put_out;
+ }
+
+ /*
+ * don't cache encrypted data into meta inode until previous dirty
+ * data were writebacked to avoid racing between GC and flush.
+ */
+ f2fs_wait_on_page_writeback(page, DATA);
get_node_info(fio.sbi, dn.nid, &ni);
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
@@ -580,7 +597,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
goto put_page_out;
set_page_dirty(fio.encrypted_page);
- f2fs_wait_on_page_writeback(fio.encrypted_page, META);
+ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA);
if (clear_page_dirty_for_io(fio.encrypted_page))
dec_page_count(fio.sbi, F2FS_DIRTY_META);
@@ -611,7 +628,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
{
struct page *page;
- page = get_lock_data_page(inode, bidx);
+ page = get_lock_data_page(inode, bidx, true);
if (IS_ERR(page))
return;
@@ -705,7 +722,7 @@ next_step:
start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
data_page = get_read_data_page(inode,
- start_bidx + ofs_in_node, READA);
+ start_bidx + ofs_in_node, READA, true);
if (IS_ERR(data_page)) {
iput(inode);
continue;
@@ -797,13 +814,12 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
return nfree;
}
-int f2fs_gc(struct f2fs_sb_info *sbi)
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
{
- unsigned int segno = NULL_SEGNO;
- unsigned int i;
- int gc_type = BG_GC;
- int nfree = 0;
- int ret = -1;
+ unsigned int segno, i;
+ int gc_type = sync ? FG_GC : BG_GC;
+ int sec_freed = 0;
+ int ret = -EINVAL;
struct cp_control cpc;
struct gc_inode_list gc_list = {
.ilist = LIST_HEAD_INIT(gc_list.ilist),
@@ -812,12 +828,14 @@ int f2fs_gc(struct f2fs_sb_info *sbi)
cpc.reason = __get_cp_reason(sbi);
gc_more:
+ segno = NULL_SEGNO;
+
if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
goto stop;
if (unlikely(f2fs_cp_error(sbi)))
goto stop;
- if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) {
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
gc_type = FG_GC;
if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
write_checkpoint(sbi, &cpc);
@@ -830,23 +848,38 @@ gc_more:
/* readahead multi ssa blocks those have contiguous address */
if (sbi->segs_per_sec > 1)
ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec,
- META_SSA);
+ META_SSA, true);
- for (i = 0; i < sbi->segs_per_sec; i++)
- nfree += do_garbage_collect(sbi, segno + i, &gc_list, gc_type);
+ for (i = 0; i < sbi->segs_per_sec; i++) {
+ /*
+ * for FG_GC case, halt gcing left segments once failed one
+ * of segments in selected section to avoid long latency.
+ */
+ if (!do_garbage_collect(sbi, segno + i, &gc_list, gc_type) &&
+ gc_type == FG_GC)
+ break;
+ }
+
+ if (i == sbi->segs_per_sec && gc_type == FG_GC)
+ sec_freed++;
if (gc_type == FG_GC)
sbi->cur_victim_sec = NULL_SEGNO;
- if (has_not_enough_free_secs(sbi, nfree))
- goto gc_more;
+ if (!sync) {
+ if (has_not_enough_free_secs(sbi, sec_freed))
+ goto gc_more;
- if (gc_type == FG_GC)
- write_checkpoint(sbi, &cpc);
+ if (gc_type == FG_GC)
+ write_checkpoint(sbi, &cpc);
+ }
stop:
mutex_unlock(&sbi->gc_mutex);
put_gc_inode(&gc_list);
+
+ if (sync)
+ ret = sec_freed ? 0 : -EAGAIN;
return ret;
}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index c5a055b3376e..b4a65be9f7d3 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -19,12 +19,6 @@
#define LIMIT_INVALID_BLOCK 40 /* percentage over total user space */
#define LIMIT_FREE_BLOCK 40 /* percentage over invalid + free space */
-/*
- * with this macro, we can control the max time we do garbage collection,
- * when user triggers batch mode gc by ioctl.
- */
-#define F2FS_BATCH_GC_MAX_NUM 16
-
/* Search max. number of dirty segments to select a victim segment */
#define DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 3d143be42895..bda7126466c0 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -12,6 +12,7 @@
#include <linux/f2fs_fs.h>
#include "f2fs.h"
+#include "node.h"
bool f2fs_may_inline_data(struct inode *inode)
{
@@ -274,12 +275,14 @@ process_inline:
if (f2fs_has_inline_data(inode)) {
ipage = get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
- truncate_inline_inode(ipage, 0);
+ if (!truncate_inline_inode(ipage, 0))
+ return false;
f2fs_clear_inline_inode(inode);
update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
- truncate_blocks(inode, 0, false);
+ if (truncate_blocks(inode, 0, false))
+ return false;
goto process_inline;
}
return false;
@@ -568,3 +571,38 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
f2fs_put_page(ipage, 1);
return 0;
}
+
+int f2fs_inline_data_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, __u64 start, __u64 len)
+{
+ __u64 byteaddr, ilen;
+ __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED |
+ FIEMAP_EXTENT_LAST;
+ struct node_info ni;
+ struct page *ipage;
+ int err = 0;
+
+ ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
+
+ if (!f2fs_has_inline_data(inode)) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode));
+ if (start >= ilen)
+ goto out;
+ if (start + len < ilen)
+ ilen = start + len;
+ ilen -= start;
+
+ get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
+ byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
+ byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage);
+ err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
+out:
+ f2fs_put_page(ipage, 1);
+ return err;
+}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 35aae65b3e5d..97e20decacb4 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -296,16 +296,12 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
return 0;
/*
- * We need to lock here to prevent from producing dirty node pages
+ * We need to balance fs here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
*/
- f2fs_lock_op(sbi);
update_inode_page(inode);
- f2fs_unlock_op(sbi);
-
- if (wbc)
- f2fs_balance_fs(sbi);
+ f2fs_balance_fs(sbi);
return 0;
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a680bf38e4f0..e48b80c49090 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -410,11 +410,14 @@ err_out:
* If the symlink path is stored into inline_data, there is no
* performance regression.
*/
- if (!err)
+ if (!err) {
filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1);
- if (IS_DIRSYNC(dir))
- f2fs_sync_fs(sbi->sb, 1);
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
+ } else {
+ f2fs_unlink(dir, dentry);
+ }
kfree(sd);
f2fs_fname_crypto_free_buffer(&disk_link);
@@ -947,8 +950,13 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook
/* Symlink is encrypted */
sd = (struct f2fs_encrypted_symlink_data *)caddr;
- cstr.name = sd->encrypted_path;
cstr.len = le16_to_cpu(sd->len);
+ cstr.name = kmalloc(cstr.len, GFP_NOFS);
+ if (!cstr.name) {
+ res = -ENOMEM;
+ goto errout;
+ }
+ memcpy(cstr.name, sd->encrypted_path, cstr.len);
/* this is broken symlink case */
if (cstr.name[0] == 0 && cstr.len == 0) {
@@ -970,6 +978,8 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook
if (res < 0)
goto errout;
+ kfree(cstr.name);
+
paddr = pstr.name;
/* Null-terminate the name */
@@ -979,6 +989,7 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook
page_cache_release(cpage);
return *cookie = paddr;
errout:
+ kfree(cstr.name);
f2fs_fname_crypto_free_buffer(&pstr);
kunmap(cpage);
page_cache_release(cpage);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 27d1a74dd6f3..7bcbc6e9c40d 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1323,23 +1323,24 @@ static int f2fs_write_node_page(struct page *page,
nid = nid_of_node(page);
f2fs_bug_on(sbi, page->index != nid);
+ if (wbc->for_reclaim) {
+ if (!down_read_trylock(&sbi->node_write))
+ goto redirty_out;
+ } else {
+ down_read(&sbi->node_write);
+ }
+
get_node_info(sbi, nid, &ni);
/* This page is already truncated */
if (unlikely(ni.blk_addr == NULL_ADDR)) {
ClearPageUptodate(page);
dec_page_count(sbi, F2FS_DIRTY_NODES);
+ up_read(&sbi->node_write);
unlock_page(page);
return 0;
}
- if (wbc->for_reclaim) {
- if (!down_read_trylock(&sbi->node_write))
- goto redirty_out;
- } else {
- down_read(&sbi->node_write);
- }
-
set_page_writeback(page);
fio.blk_addr = ni.blk_addr;
write_node_page(nid, &fio);
@@ -1528,7 +1529,8 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
return;
/* readahead nat pages to be scanned */
- ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT);
+ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
+ META_NAT, true);
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
@@ -1558,6 +1560,9 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
remove_free_nid(nm_i, nid);
}
mutex_unlock(&curseg->curseg_mutex);
+
+ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
+ nm_i->ra_nid_pages, META_NAT, false);
}
/*
@@ -1803,10 +1808,10 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
nrpages = min(last_offset - i, bio_blocks);
/* readahead node pages */
- ra_meta_pages(sbi, addr, nrpages, META_POR);
+ ra_meta_pages(sbi, addr, nrpages, META_POR, true);
for (idx = addr; idx < addr + nrpages; idx++) {
- struct page *page = get_meta_page(sbi, idx);
+ struct page *page = get_tmp_page(sbi, idx);
rn = F2FS_NODE(page);
sum_entry->nid = rn->footer.nid;
@@ -2000,6 +2005,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
nm_i->fcnt = 0;
nm_i->nat_cnt = 0;
nm_i->ram_thresh = DEF_RAM_THRESHOLD;
+ nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
INIT_LIST_HEAD(&nm_i->free_nid_list);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 7427e956ad81..e4fffd2d98c4 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -14,9 +14,11 @@
/* node block offset on the NAT area dedicated to the given start node id */
#define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
-/* # of pages to perform readahead before building free nids */
+/* # of pages to perform synchronous readahead before building free nids */
#define FREE_NID_PAGES 4
+#define DEF_RA_NID_PAGES 4 /* # of nid pages to be readaheaded */
+
/* maximum readahead size for node during getting data blocks */
#define MAX_RA_NODE 128
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index faec2ca004b9..cbf74f47cce8 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -180,7 +180,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- ra_meta_pages(sbi, blkaddr, 1, META_POR);
+ ra_meta_pages(sbi, blkaddr, 1, META_POR, true);
while (1) {
struct fsync_inode_entry *entry;
@@ -188,7 +188,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
- page = get_meta_page(sbi, blkaddr);
+ page = get_tmp_page(sbi, blkaddr);
if (cp_ver != cpver_of_node(page))
break;
@@ -383,15 +383,11 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
start = start_bidx_of_node(ofs_of_node(page), fi);
end = start + ADDRS_PER_PAGE(page, fi);
- f2fs_lock_op(sbi);
-
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, start, ALLOC_NODE);
- if (err) {
- f2fs_unlock_op(sbi);
+ if (err)
goto out;
- }
f2fs_wait_on_page_writeback(dn.node_page, NODE);
@@ -456,7 +452,6 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
set_page_dirty(dn.node_page);
err:
f2fs_put_dnode(&dn);
- f2fs_unlock_op(sbi);
out:
f2fs_msg(sbi->sb, KERN_NOTICE,
"recover_data: ino = %lx, recovered = %d blocks, err = %d",
@@ -485,7 +480,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
ra_meta_pages_cond(sbi, blkaddr);
- page = get_meta_page(sbi, blkaddr);
+ page = get_tmp_page(sbi, blkaddr);
if (cp_ver != cpver_of_node(page)) {
f2fs_put_page(page, 1);
@@ -570,7 +565,7 @@ out:
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
- MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
+ (loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 78e6d0696847..f77b3258454a 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -14,8 +14,8 @@
#include <linux/blkdev.h>
#include <linux/prefetch.h>
#include <linux/kthread.h>
-#include <linux/vmalloc.h>
#include <linux/swap.h>
+#include <linux/timer.h>
#include "f2fs.h"
#include "segment.h"
@@ -29,6 +29,21 @@ static struct kmem_cache *discard_entry_slab;
static struct kmem_cache *sit_entry_set_slab;
static struct kmem_cache *inmem_entry_slab;
+static unsigned long __reverse_ulong(unsigned char *str)
+{
+ unsigned long tmp = 0;
+ int shift = 24, idx = 0;
+
+#if BITS_PER_LONG == 64
+ shift = 56;
+#endif
+ while (shift >= 0) {
+ tmp |= (unsigned long)str[idx++] << shift;
+ shift -= BITS_PER_BYTE;
+ }
+ return tmp;
+}
+
/*
* __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
* MSB and LSB are reversed in a byte by f2fs_set_bit.
@@ -38,27 +53,31 @@ static inline unsigned long __reverse_ffs(unsigned long word)
int num = 0;
#if BITS_PER_LONG == 64
- if ((word & 0xffffffff) == 0) {
+ if ((word & 0xffffffff00000000UL) == 0)
num += 32;
+ else
word >>= 32;
- }
#endif
- if ((word & 0xffff) == 0) {
+ if ((word & 0xffff0000) == 0)
num += 16;
+ else
word >>= 16;
- }
- if ((word & 0xff) == 0) {
+
+ if ((word & 0xff00) == 0)
num += 8;
+ else
word >>= 8;
- }
+
if ((word & 0xf0) == 0)
num += 4;
else
word >>= 4;
+
if ((word & 0xc) == 0)
num += 2;
else
word >>= 2;
+
if ((word & 0x2) == 0)
num += 1;
return num;
@@ -68,26 +87,16 @@ static inline unsigned long __reverse_ffs(unsigned long word)
* __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because
* f2fs_set_bit makes MSB and LSB reversed in a byte.
* Example:
- * LSB <--> MSB
- * f2fs_set_bit(0, bitmap) => 0000 0001
- * f2fs_set_bit(7, bitmap) => 1000 0000
+ * MSB <--> LSB
+ * f2fs_set_bit(0, bitmap) => 1000 0000
+ * f2fs_set_bit(7, bitmap) => 0000 0001
*/
static unsigned long __find_rev_next_bit(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
- while (!f2fs_test_bit(offset, (unsigned char *)addr))
- offset++;
-
- if (offset > size)
- offset = size;
-
- return offset;
-#if 0
const unsigned long *p = addr + BIT_WORD(offset);
unsigned long result = offset & ~(BITS_PER_LONG - 1);
unsigned long tmp;
- unsigned long mask, submask;
- unsigned long quot, rest;
if (offset >= size)
return size;
@@ -97,14 +106,9 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr,
if (!offset)
goto aligned;
- tmp = *(p++);
- quot = (offset >> 3) << 3;
- rest = offset & 0x7;
- mask = ~0UL << quot;
- submask = (unsigned char)(0xff << rest) >> rest;
- submask <<= quot;
- mask &= submask;
- tmp &= mask;
+ tmp = __reverse_ulong((unsigned char *)p);
+ tmp &= ~0UL >> offset;
+
if (size < BITS_PER_LONG)
goto found_first;
if (tmp)
@@ -112,42 +116,34 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr,
size -= BITS_PER_LONG;
result += BITS_PER_LONG;
+ p++;
aligned:
while (size & ~(BITS_PER_LONG-1)) {
- tmp = *(p++);
+ tmp = __reverse_ulong((unsigned char *)p);
if (tmp)
goto found_middle;
result += BITS_PER_LONG;
size -= BITS_PER_LONG;
+ p++;
}
if (!size)
return result;
- tmp = *p;
+
+ tmp = __reverse_ulong((unsigned char *)p);
found_first:
- tmp &= (~0UL >> (BITS_PER_LONG - size));
- if (tmp == 0UL) /* Are any bits set? */
+ tmp &= (~0UL << (BITS_PER_LONG - size));
+ if (!tmp) /* Are any bits set? */
return result + size; /* Nope. */
found_middle:
return result + __reverse_ffs(tmp);
-#endif
}
static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
- while (f2fs_test_bit(offset, (unsigned char *)addr))
- offset++;
-
- if (offset > size)
- offset = size;
-
- return offset;
-#if 0
const unsigned long *p = addr + BIT_WORD(offset);
unsigned long result = offset & ~(BITS_PER_LONG - 1);
unsigned long tmp;
- unsigned long mask, submask;
- unsigned long quot, rest;
if (offset >= size)
return size;
@@ -157,40 +153,36 @@ static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
if (!offset)
goto aligned;
- tmp = *(p++);
- quot = (offset >> 3) << 3;
- rest = offset & 0x7;
- mask = ~(~0UL << quot);
- submask = (unsigned char)~((unsigned char)(0xff << rest) >> rest);
- submask <<= quot;
- mask += submask;
- tmp |= mask;
+ tmp = __reverse_ulong((unsigned char *)p);
+ tmp |= ~((~0UL << offset) >> offset);
+
if (size < BITS_PER_LONG)
goto found_first;
- if (~tmp)
+ if (tmp != ~0UL)
goto found_middle;
size -= BITS_PER_LONG;
result += BITS_PER_LONG;
+ p++;
aligned:
while (size & ~(BITS_PER_LONG - 1)) {
- tmp = *(p++);
- if (~tmp)
+ tmp = __reverse_ulong((unsigned char *)p);
+ if (tmp != ~0UL)
goto found_middle;
result += BITS_PER_LONG;
size -= BITS_PER_LONG;
+ p++;
}
if (!size)
return result;
- tmp = *p;
+ tmp = __reverse_ulong((unsigned char *)p);
found_first:
- tmp |= ~0UL << size;
- if (tmp == ~0UL) /* Are any bits zero? */
+ tmp |= ~(~0UL << (BITS_PER_LONG - size));
+ if (tmp == ~0UL) /* Are any bits zero? */
return result + size; /* Nope. */
found_middle:
return result + __reverse_ffz(tmp);
-#endif
}
void register_inmem_page(struct inode *inode, struct page *page)
@@ -257,11 +249,12 @@ int commit_inmem_pages(struct inode *inode, bool abort)
trace_f2fs_commit_inmem_page(cur->page, INMEM);
fio.page = cur->page;
err = do_write_data_page(&fio);
- submit_bio = true;
if (err) {
unlock_page(cur->page);
break;
}
+ clear_cold_data(cur->page);
+ submit_bio = true;
}
} else {
trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP);
@@ -296,7 +289,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi)
*/
if (has_not_enough_free_secs(sbi, 0)) {
mutex_lock(&sbi->gc_mutex);
- f2fs_gc(sbi);
+ f2fs_gc(sbi, false);
}
}
@@ -316,7 +309,8 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
/* checkpoint is the only way to shrink partial cached entries */
if (!available_free_memory(sbi, NAT_ENTRIES) ||
excess_prefree_segs(sbi) ||
- !available_free_memory(sbi, INO_ENTRIES))
+ !available_free_memory(sbi, INO_ENTRIES) ||
+ jiffies > sbi->cp_expires)
f2fs_sync_fs(sbi->sb, true);
}
@@ -767,6 +761,30 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
mutex_unlock(&sit_i->sentry_lock);
}
+bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+ struct sit_info *sit_i = SIT_I(sbi);
+ unsigned int segno, offset;
+ struct seg_entry *se;
+ bool is_cp = false;
+
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ return true;
+
+ mutex_lock(&sit_i->sentry_lock);
+
+ segno = GET_SEGNO(sbi, blkaddr);
+ se = get_seg_entry(sbi, segno);
+ offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+
+ if (f2fs_test_bit(offset, se->ckpt_valid_map))
+ is_cp = true;
+
+ mutex_unlock(&sit_i->sentry_lock);
+
+ return is_cp;
+}
+
/*
* This function should be resided under the curseg_mutex lock
*/
@@ -1292,6 +1310,9 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
.encrypted_page = NULL,
};
+ if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
+ fio.rw &= ~REQ_META;
+
set_page_writeback(page);
f2fs_submit_page_mbio(&fio);
}
@@ -1369,7 +1390,14 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
__add_sum_entry(sbi, type, sum);
- refresh_sit_entry(sbi, old_blkaddr, new_blkaddr);
+ if (!recover_curseg)
+ update_sit_entry(sbi, new_blkaddr, 1);
+ if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+ update_sit_entry(sbi, old_blkaddr, -1);
+
+ locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
+ locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr));
+
locate_dirty_segment(sbi, old_cursegno);
if (recover_curseg) {
@@ -1449,6 +1477,23 @@ void f2fs_wait_on_page_writeback(struct page *page,
}
}
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
+ block_t blkaddr)
+{
+ struct page *cpage;
+
+ if (blkaddr == NEW_ADDR)
+ return;
+
+ f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
+
+ cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
+ if (cpage) {
+ f2fs_wait_on_page_writeback(cpage, DATA);
+ f2fs_put_page(cpage, 1);
+ }
+}
+
static int read_compacted_summaries(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
@@ -1586,7 +1631,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
if (npages >= 2)
ra_meta_pages(sbi, start_sum_block(sbi), npages,
- META_CP);
+ META_CP, true);
/* restore for compacted data summary */
if (read_compacted_summaries(sbi))
@@ -1596,7 +1641,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
if (__exist_node_summaries(sbi))
ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
- NR_CURSEG_TYPE - type, META_CP);
+ NR_CURSEG_TYPE - type, META_CP, true);
for (; type <= CURSEG_COLD_NODE; type++) {
err = read_normal_summaries(sbi, type);
@@ -1955,12 +2000,13 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries = vzalloc(MAIN_SEGS(sbi) * sizeof(struct seg_entry));
+ sit_i->sentries = f2fs_kvzalloc(MAIN_SEGS(sbi) *
+ sizeof(struct seg_entry), GFP_KERNEL);
if (!sit_i->sentries)
return -ENOMEM;
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+ sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
if (!sit_i->dirty_sentries_bitmap)
return -ENOMEM;
@@ -1982,8 +2028,8 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
return -ENOMEM;
if (sbi->segs_per_sec > 1) {
- sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) *
- sizeof(struct sec_entry));
+ sit_i->sec_entries = f2fs_kvzalloc(MAIN_SECS(sbi) *
+ sizeof(struct sec_entry), GFP_KERNEL);
if (!sit_i->sec_entries)
return -ENOMEM;
}
@@ -2028,12 +2074,12 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
SM_I(sbi)->free_info = free_i;
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL);
+ free_i->free_segmap = f2fs_kvmalloc(bitmap_size, GFP_KERNEL);
if (!free_i->free_segmap)
return -ENOMEM;
sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL);
+ free_i->free_secmap = f2fs_kvmalloc(sec_bitmap_size, GFP_KERNEL);
if (!free_i->free_secmap)
return -ENOMEM;
@@ -2082,7 +2128,7 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
int nrpages = MAX_BIO_BLOCKS(sbi);
do {
- readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT);
+ readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
start = start_blk * sit_i->sents_per_block;
end = (start_blk + readed) * sit_i->sents_per_block;
@@ -2174,7 +2220,7 @@ 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(MAIN_SECS(sbi));
- dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL);
+ dirty_i->victim_secmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
if (!dirty_i->victim_secmap)
return -ENOMEM;
return 0;
@@ -2196,7 +2242,7 @@ static int build_dirty_segmap(struct f2fs_sb_info *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);
+ dirty_i->dirty_segmap[i] = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
if (!dirty_i->dirty_segmap[i])
return -ENOMEM;
}
@@ -2301,7 +2347,7 @@ static void discard_dirty_segmap(struct f2fs_sb_info *sbi,
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
mutex_lock(&dirty_i->seglist_lock);
- kfree(dirty_i->dirty_segmap[dirty_type]);
+ kvfree(dirty_i->dirty_segmap[dirty_type]);
dirty_i->nr_dirty[dirty_type] = 0;
mutex_unlock(&dirty_i->seglist_lock);
}
@@ -2309,7 +2355,7 @@ static void discard_dirty_segmap(struct f2fs_sb_info *sbi,
static void destroy_victim_secmap(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- kfree(dirty_i->victim_secmap);
+ kvfree(dirty_i->victim_secmap);
}
static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
@@ -2348,8 +2394,8 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi)
if (!free_i)
return;
SM_I(sbi)->free_info = NULL;
- kfree(free_i->free_segmap);
- kfree(free_i->free_secmap);
+ kvfree(free_i->free_segmap);
+ kvfree(free_i->free_secmap);
kfree(free_i);
}
@@ -2370,9 +2416,9 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
}
kfree(sit_i->tmp_map);
- vfree(sit_i->sentries);
- vfree(sit_i->sec_entries);
- kfree(sit_i->dirty_sentries_bitmap);
+ kvfree(sit_i->sentries);
+ kvfree(sit_i->sec_entries);
+ kvfree(sit_i->dirty_sentries_bitmap);
SM_I(sbi)->sit_info = NULL;
kfree(sit_i->sit_bitmap);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index b6e4ed15c698..ee44d346ea44 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -137,10 +137,12 @@ enum {
/*
* BG_GC means the background cleaning job.
* FG_GC means the on-demand cleaning job.
+ * FORCE_FG_GC means on-demand cleaning job in background.
*/
enum {
BG_GC = 0,
- FG_GC
+ FG_GC,
+ FORCE_FG_GC,
};
/* for a function parameter to select a victim segment */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f79478115d37..3a65e0132352 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -213,8 +213,10 @@ 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(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
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);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, cp_interval);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
@@ -231,6 +233,8 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(max_victim_search),
ATTR_LIST(dir_level),
ATTR_LIST(ram_thresh),
+ ATTR_LIST(ra_nid_pages),
+ ATTR_LIST(cp_interval),
NULL,
};
@@ -292,11 +296,16 @@ static int parse_options(struct super_block *sb, char *options)
if (!name)
return -ENOMEM;
- if (strlen(name) == 2 && !strncmp(name, "on", 2))
+ if (strlen(name) == 2 && !strncmp(name, "on", 2)) {
set_opt(sbi, BG_GC);
- else if (strlen(name) == 3 && !strncmp(name, "off", 3))
+ clear_opt(sbi, FORCE_FG_GC);
+ } else if (strlen(name) == 3 && !strncmp(name, "off", 3)) {
clear_opt(sbi, BG_GC);
- else {
+ clear_opt(sbi, FORCE_FG_GC);
+ } else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) {
+ set_opt(sbi, BG_GC);
+ set_opt(sbi, FORCE_FG_GC);
+ } else {
kfree(name);
return -EINVAL;
}
@@ -631,10 +640,14 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
- if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC))
- seq_printf(seq, ",background_gc=%s", "on");
- else
+ if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) {
+ if (test_opt(sbi, FORCE_FG_GC))
+ seq_printf(seq, ",background_gc=%s", "sync");
+ else
+ seq_printf(seq, ",background_gc=%s", "on");
+ } else {
seq_printf(seq, ",background_gc=%s", "off");
+ }
if (test_opt(sbi, DISABLE_ROLL_FORWARD))
seq_puts(seq, ",disable_roll_forward");
if (test_opt(sbi, DISCARD))
@@ -742,6 +755,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
int err, active_logs;
bool need_restart_gc = false;
bool need_stop_gc = false;
+ bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
sync_filesystem(sb);
@@ -767,6 +781,14 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
goto skip;
+ /* disallow enable/disable extent_cache dynamically */
+ if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
+ err = -EINVAL;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "switch extent_cache option is not allowed");
+ goto restore_opts;
+ }
+
/*
* We stop the GC thread if FS is mounted as RO
* or if background_gc = off is passed in mount
@@ -996,6 +1018,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
atomic_set(&sbi->nr_pages[i], 0);
sbi->dir_level = DEF_DIR_LEVEL;
+ sbi->cp_interval = DEF_CP_INTERVAL;
clear_sbi_flag(sbi, SBI_NEED_FSCK);
INIT_LIST_HEAD(&sbi->s_list);
@@ -1332,6 +1355,8 @@ try_onemore:
f2fs_commit_super(sbi, true);
}
+ sbi->cp_expires = round_jiffies_up(jiffies);
+
return 0;
free_kobj:
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index a01946514b5a..00b4a6308249 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -514,6 +514,34 @@ TRACE_EVENT(f2fs_map_blocks,
__entry->ret)
);
+TRACE_EVENT(f2fs_background_gc,
+
+ TP_PROTO(struct super_block *sb, long wait_ms,
+ unsigned int prefree, unsigned int free),
+
+ TP_ARGS(sb, wait_ms, prefree, free),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(long, wait_ms)
+ __field(unsigned int, prefree)
+ __field(unsigned int, free)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->wait_ms = wait_ms;
+ __entry->prefree = prefree;
+ __entry->free = free;
+ ),
+
+ TP_printk("dev = (%d,%d), wait_ms = %ld, prefree = %u, free = %u",
+ show_dev(__entry),
+ __entry->wait_ms,
+ __entry->prefree,
+ __entry->free)
+);
+
TRACE_EVENT(f2fs_get_victim,
TP_PROTO(struct super_block *sb, int type, int gc_type,
@@ -1000,6 +1028,32 @@ TRACE_EVENT(f2fs_writepages,
__entry->for_sync)
);
+TRACE_EVENT(f2fs_readpages,
+
+ TP_PROTO(struct inode *inode, struct page *page, unsigned int nrpage),
+
+ TP_ARGS(inode, page, nrpage),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(pgoff_t, start)
+ __field(unsigned int, nrpage)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->start = page->index;
+ __entry->nrpage = nrpage;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, start = %lu nrpage = %u",
+ show_dev_ino(__entry),
+ (unsigned long)__entry->start,
+ __entry->nrpage)
+);
+
TRACE_EVENT(f2fs_write_checkpoint,
TP_PROTO(struct super_block *sb, int reason, char *msg),
@@ -1132,17 +1186,19 @@ TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end,
__entry->len)
);
-TRACE_EVENT(f2fs_update_extent_tree,
+TRACE_EVENT(f2fs_update_extent_tree_range,
- TP_PROTO(struct inode *inode, unsigned int pgofs, block_t blkaddr),
+ TP_PROTO(struct inode *inode, unsigned int pgofs, block_t blkaddr,
+ unsigned int len),
- TP_ARGS(inode, pgofs, blkaddr),
+ TP_ARGS(inode, pgofs, blkaddr, len),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
__field(unsigned int, pgofs)
__field(u32, blk)
+ __field(unsigned int, len)
),
TP_fast_assign(
@@ -1150,12 +1206,15 @@ TRACE_EVENT(f2fs_update_extent_tree,
__entry->ino = inode->i_ino;
__entry->pgofs = pgofs;
__entry->blk = blkaddr;
+ __entry->len = len;
),
- TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, blkaddr = %u",
+ TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+ "blkaddr = %u, len = %u",
show_dev_ino(__entry),
__entry->pgofs,
- __entry->blk)
+ __entry->blk,
+ __entry->len)
);
TRACE_EVENT(f2fs_shrink_extent_tree,
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-30 10:51:13 +0300