Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description: Do background GC agressively when set. When gc_urgent = 1,
background thread starts to do GC by given gc_urgent_sleep_time
- interval. It is set to 0 by default.
+ interval. When gc_urgent = 2, F2FS will lower the bar of
+ checking idle in order to process outstanding discard commands
+ and GC a little bit aggressively. It is set to 0 by default.
What: /sys/fs/f2fs/<disk>/gc_urgent_sleep_time
Date: August 2017
on compression extension list and enable compression on
these file by default rather than to enable it via ioctl.
For other files, we can still enable compression via ioctl.
+ Note that, there is one reserved special extension '*', it
+ can be set to enable compression for all files.
inlinecrypt When possible, encrypt/decrypt the contents of encrypted
files using the blk-crypto framework rather than
filesystem-layer encryption. This allows the use of
- In order to eliminate write amplification during overwrite, F2FS only
support compression on write-once file, data can be compressed only when
- all logical blocks in file are valid and cluster compress ratio is lower
- than specified threshold.
+ all logical blocks in cluster contain valid data and compress ratio of
+ cluster data is lower than specified threshold.
- To enable compression on regular inode, there are three ways:
__remove_ino_entry(sbi, ino, type);
}
-/* mode should be APPEND_INO or UPDATE_INO */
+/* mode should be APPEND_INO, UPDATE_INO or TRANS_DIR_INO */
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
struct inode_management *im = &sbi->im[mode];
DEFINE_WAIT(wait);
for (;;) {
- prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
-
if (!get_pages(sbi, type))
break;
if (type == F2FS_DIRTY_META)
f2fs_sync_meta_pages(sbi, META, LONG_MAX,
FS_CP_META_IO);
+ else if (type == F2FS_WB_CP_DATA)
+ f2fs_submit_merged_write(sbi, DATA);
+
+ prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
io_schedule_timeout(DEFAULT_IO_TIMEOUT);
}
finish_wait(&sbi->cp_wait, &wait);
curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
}
- /* 2 cp + n data seg summary + orphan inode blocks */
+ /* 2 cp + n data seg summary + orphan inode blocks */
data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false);
spin_lock_irqsave(&sbi->cp_lock, flags);
if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
/*
* invalidate intermediate page cache borrowed from meta inode which are
- * used for migration of encrypted or verity inode's blocks.
+ * used for migration of encrypted, verity or compressed inode's blocks.
*/
- if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi))
+ if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi) ||
+ f2fs_sb_has_compression(sbi))
invalidate_mapping_pages(META_MAPPING(sbi),
MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
return false;
if (IS_ATOMIC_WRITTEN_PAGE(page) || IS_DUMMY_WRITTEN_PAGE(page))
return false;
+ /*
+ * page->private may be set with pid.
+ * pid_max is enough to check if it is traced.
+ */
+ if (IS_IO_TRACED_PAGE(page))
+ return false;
+
f2fs_bug_on(F2FS_M_SB(page->mapping),
*((u32 *)page_private(page)) != F2FS_COMPRESSED_PAGE_MAGIC);
return true;
return f2fs_cops[F2FS_I(inode)->i_compress_algorithm];
}
-static mempool_t *compress_page_pool = NULL;
+static mempool_t *compress_page_pool;
static int num_compress_pages = 512;
module_param(num_compress_pages, uint, 0444);
MODULE_PARM_DESC(num_compress_pages,
const struct f2fs_compress_ops *cops =
f2fs_cops[fi->i_compress_algorithm];
int ret;
+ int i;
dec_page_count(sbi, F2FS_RD_DATA);
goto out_free_dic;
}
+ dic->tpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
+ dic->cluster_size, GFP_NOFS);
+ if (!dic->tpages) {
+ ret = -ENOMEM;
+ goto out_free_dic;
+ }
+
+ for (i = 0; i < dic->cluster_size; i++) {
+ if (dic->rpages[i]) {
+ dic->tpages[i] = dic->rpages[i];
+ continue;
+ }
+
+ dic->tpages[i] = f2fs_compress_alloc_page();
+ if (!dic->tpages[i]) {
+ ret = -ENOMEM;
+ goto out_free_dic;
+ }
+ }
+
if (cops->init_decompress_ctx) {
ret = cops->init_decompress_ctx(dic);
if (ret)
}
/* return # of valid blocks in compressed cluster */
-static int f2fs_cluster_blocks(struct compress_ctx *cc, bool compr)
+static int f2fs_cluster_blocks(struct compress_ctx *cc)
{
return __f2fs_cluster_blocks(cc, false);
}
.cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size,
};
- return f2fs_cluster_blocks(&cc, false);
+ return f2fs_cluster_blocks(&cc);
}
static bool cluster_may_compress(struct compress_ctx *cc)
bool prealloc;
retry:
- ret = f2fs_cluster_blocks(cc, false);
+ ret = f2fs_cluster_blocks(cc);
if (ret <= 0)
return ret;
}
if (prealloc) {
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
break;
}
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
}
if (likely(!ret)) {
loff_t psize;
int i, err;
- if (!IS_NOQUOTA(inode) && !f2fs_trylock_op(sbi))
+ if (IS_NOQUOTA(inode)) {
+ /*
+ * We need to wait for node_write to avoid block allocation during
+ * checkpoint. This can only happen to quota writes which can cause
+ * the below discard race condition.
+ */
+ down_read(&sbi->node_write);
+ } else if (!f2fs_trylock_op(sbi)) {
return -EAGAIN;
+ }
set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
f2fs_set_compressed_page(cc->cpages[i], inode,
cc->rpages[i + 1]->index, cic);
fio.compressed_page = cc->cpages[i];
+
+ fio.old_blkaddr = data_blkaddr(dn.inode, dn.node_page,
+ dn.ofs_in_node + i + 1);
+
+ /* wait for GCed page writeback via META_MAPPING */
+ f2fs_wait_on_block_writeback(inode, fio.old_blkaddr);
+
if (fio.encrypted) {
fio.page = cc->rpages[i + 1];
err = f2fs_encrypt_one_page(&fio);
set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
f2fs_put_dnode(&dn);
- if (!IS_NOQUOTA(inode))
+ if (IS_NOQUOTA(inode))
+ up_read(&sbi->node_write);
+ else
f2fs_unlock_op(sbi);
spin_lock(&fi->i_size_lock);
out_put_dnode:
f2fs_put_dnode(&dn);
out_unlock_op:
- if (!IS_NOQUOTA(inode))
+ if (IS_NOQUOTA(inode))
+ up_read(&sbi->node_write);
+ else
f2fs_unlock_op(sbi);
return -EAGAIN;
}
congestion_wait(BLK_RW_ASYNC,
DEFAULT_IO_TIMEOUT);
lock_page(cc->rpages[i]);
+
+ if (!PageDirty(cc->rpages[i])) {
+ unlock_page(cc->rpages[i]);
+ continue;
+ }
+
clear_page_dirty_for_io(cc->rpages[i]);
goto retry_write;
}
err = f2fs_write_compressed_pages(cc, submitted,
wbc, io_type);
cops->destroy_compress_ctx(cc);
+ kfree(cc->cpages);
+ cc->cpages = NULL;
if (!err)
return 0;
f2fs_bug_on(F2FS_I_SB(cc->inode), err != -EAGAIN);
dic->cpages[i] = page;
}
- dic->tpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
- dic->cluster_size, GFP_NOFS);
- if (!dic->tpages)
- goto out_free;
-
- for (i = 0; i < dic->cluster_size; i++) {
- if (cc->rpages[i]) {
- dic->tpages[i] = cc->rpages[i];
- continue;
- }
-
- dic->tpages[i] = f2fs_compress_alloc_page();
- if (!dic->tpages[i])
- goto out_free;
- }
-
return dic;
out_free:
sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi) ||
- inode->i_ino == F2FS_NODE_INO(sbi) ||
+ inode->i_ino == F2FS_NODE_INO(sbi) ||
S_ISDIR(inode->i_mode) ||
(S_ISREG(inode->i_mode) &&
(f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) ||
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
- block_t blkaddr, bool for_write)
+ block_t blkaddr, int op_flags, bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
- bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index, for_write);
+ bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags,
+ page->index, for_write);
if (IS_ERR(bio))
return PTR_ERR(bio);
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
{
- struct extent_info ei = {0,0,0};
+ struct extent_info ei = {0, 0, 0};
struct inode *inode = dn->inode;
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
return page;
}
- err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, for_write);
+ err = f2fs_submit_page_read(inode, page, dn.data_blkaddr,
+ op_flags, for_write);
if (err)
goto put_err;
return page;
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
old_blkaddr = dn->data_blkaddr;
f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
- &sum, seg_type, NULL, false);
+ &sum, seg_type, NULL);
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
invalidate_mapping_pages(META_MAPPING(sbi),
old_blkaddr, old_blkaddr);
return err;
}
-void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
+void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
if (lock)
next_dnode:
if (map->m_may_create)
- __do_map_lock(sbi, flag, true);
+ f2fs_do_map_lock(sbi, flag, true);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
f2fs_put_dnode(&dn);
if (map->m_may_create) {
- __do_map_lock(sbi, flag, false);
+ f2fs_do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
goto next_dnode;
f2fs_put_dnode(&dn);
unlock_out:
if (map->m_may_create) {
- __do_map_lock(sbi, flag, false);
+ f2fs_do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
out:
flags |= FIEMAP_EXTENT_LAST;
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+ trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
if (err || err == 1)
return err;
}
flags = FIEMAP_EXTENT_LAST;
}
- if (phys)
+ if (phys) {
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+ trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
+ }
return (err < 0 ? err : 0);
}
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size, flags);
+ trace_f2fs_fiemap(inode, logical, phys, size, flags, ret);
if (ret)
goto out;
size = 0;
if (ret)
goto out;
- /* cluster was overwritten as normal cluster */
- if (dn.data_blkaddr != COMPRESS_ADDR)
- goto out;
+ f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR);
for (i = 1; i < cc->cluster_size; i++) {
block_t blkaddr;
unsigned nr_pages = rac ? readahead_count(rac) : 1;
unsigned max_nr_pages = nr_pages;
int ret = 0;
+ bool drop_ra = false;
map.m_pblk = 0;
map.m_lblk = 0;
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = false;
+ /*
+ * Two readahead threads for same address range can cause race condition
+ * which fragments sequential read IOs. So let's avoid each other.
+ */
+ if (rac && readahead_count(rac)) {
+ if (READ_ONCE(F2FS_I(inode)->ra_offset) == readahead_index(rac))
+ drop_ra = true;
+ else
+ WRITE_ONCE(F2FS_I(inode)->ra_offset,
+ readahead_index(rac));
+ }
+
for (; nr_pages; nr_pages--) {
if (rac) {
page = readahead_page(rac);
prefetchw(&page->flags);
+ if (drop_ra) {
+ f2fs_put_page(page, 1);
+ continue;
+ }
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
}
if (bio)
__submit_bio(F2FS_I_SB(inode), bio, DATA);
+
+ if (rac && readahead_count(rac) && !drop_ra)
+ WRITE_ONCE(F2FS_I(inode)->ra_offset, -1);
return ret;
}
/* Dentry/quota blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) {
+ /*
+ * We need to wait for node_write to avoid block allocation during
+ * checkpoint. This can only happen to quota writes which can cause
+ * the below discard race condition.
+ */
+ if (IS_NOQUOTA(inode))
+ down_read(&sbi->node_write);
+
fio.need_lock = LOCK_DONE;
err = f2fs_do_write_data_page(&fio);
+
+ if (IS_NOQUOTA(inode))
+ up_read(&sbi->node_write);
+
goto done;
}
if (f2fs_has_inline_data(inode) ||
(pos & PAGE_MASK) >= i_size_read(inode)) {
- __do_map_lock(sbi, flag, true);
+ f2fs_do_map_lock(sbi, flag, true);
locked = true;
}
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err || dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
true);
WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO);
locked = true;
f2fs_put_dnode(&dn);
unlock_out:
if (locked)
- __do_map_lock(sbi, flag, false);
+ f2fs_do_map_lock(sbi, flag, false);
return err;
}
err = -EFSCORRUPTED;
goto fail;
}
- err = f2fs_submit_page_read(inode, page, blkaddr, true);
+ err = f2fs_submit_page_read(inode, page, blkaddr, 0, true);
if (err)
goto fail;
if (f2fs_compressed_file(inode) && fsdata) {
f2fs_compress_write_end(inode, fsdata, page->index, copied);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+
+ if (pos + copied > i_size_read(inode) &&
+ !f2fs_verity_in_progress(inode))
+ f2fs_i_size_write(inode, pos + copied);
return copied;
}
#endif
}
f2fs_put_dnode(&dn);
-
return blknr;
#else
- return -EOPNOTSUPP;
+ return 0;
#endif
}
static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
+ struct buffer_head tmp = {
+ .b_size = i_blocksize(inode),
+ };
+ sector_t blknr = 0;
if (f2fs_has_inline_data(inode))
- return 0;
+ goto out;
/* make sure allocating whole blocks */
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
filemap_write_and_wait(mapping);
if (f2fs_compressed_file(inode))
- return f2fs_bmap_compress(inode, block);
+ blknr = f2fs_bmap_compress(inode, block);
- return generic_block_bmap(mapping, block, get_data_block_bmap);
+ if (!get_data_block_bmap(inode, block, &tmp, 0))
+ blknr = tmp.b_blocknr;
+out:
+ trace_f2fs_bmap(inode, block, blknr);
+ return blknr;
}
#ifdef CONFIG_MIGRATION
for (i = META_CP; i < META_MAX; i++)
si->meta_count[i] = atomic_read(&sbi->meta_count[i]);
+ for (i = 0; i < NO_CHECK_TYPE; i++) {
+ si->dirty_seg[i] = 0;
+ si->full_seg[i] = 0;
+ si->valid_blks[i] = 0;
+ }
+
+ for (i = 0; i < MAIN_SEGS(sbi); i++) {
+ int blks = get_seg_entry(sbi, i)->valid_blocks;
+ int type = get_seg_entry(sbi, i)->type;
+
+ if (!blks)
+ continue;
+
+ if (blks == sbi->blocks_per_seg)
+ si->full_seg[type]++;
+ else
+ si->dirty_seg[type]++;
+ si->valid_blks[type] += blks;
+ }
+
for (i = 0; i < 2; i++) {
si->segment_count[i] = sbi->segment_count[i];
si->block_count[i] = sbi->block_count[i];
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
si->main_area_segs, si->main_area_sections,
si->main_area_zones);
- seq_printf(s, " - COLD data: %d, %d, %d\n",
+ seq_printf(s, " TYPE %8s %8s %8s %10s %10s %10s\n",
+ "segno", "secno", "zoneno", "dirty_seg", "full_seg", "valid_blk");
+ seq_printf(s, " - COLD data: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_COLD_DATA],
si->cursec[CURSEG_COLD_DATA],
- si->curzone[CURSEG_COLD_DATA]);
- seq_printf(s, " - WARM data: %d, %d, %d\n",
+ si->curzone[CURSEG_COLD_DATA],
+ si->dirty_seg[CURSEG_COLD_DATA],
+ si->full_seg[CURSEG_COLD_DATA],
+ si->valid_blks[CURSEG_COLD_DATA]);
+ seq_printf(s, " - WARM data: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_WARM_DATA],
si->cursec[CURSEG_WARM_DATA],
- si->curzone[CURSEG_WARM_DATA]);
- seq_printf(s, " - HOT data: %d, %d, %d\n",
+ si->curzone[CURSEG_WARM_DATA],
+ si->dirty_seg[CURSEG_WARM_DATA],
+ si->full_seg[CURSEG_WARM_DATA],
+ si->valid_blks[CURSEG_WARM_DATA]);
+ seq_printf(s, " - HOT data: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_HOT_DATA],
si->cursec[CURSEG_HOT_DATA],
- si->curzone[CURSEG_HOT_DATA]);
- seq_printf(s, " - Dir dnode: %d, %d, %d\n",
+ si->curzone[CURSEG_HOT_DATA],
+ si->dirty_seg[CURSEG_HOT_DATA],
+ si->full_seg[CURSEG_HOT_DATA],
+ si->valid_blks[CURSEG_HOT_DATA]);
+ seq_printf(s, " - Dir dnode: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_HOT_NODE],
si->cursec[CURSEG_HOT_NODE],
- si->curzone[CURSEG_HOT_NODE]);
- seq_printf(s, " - File dnode: %d, %d, %d\n",
+ si->curzone[CURSEG_HOT_NODE],
+ si->dirty_seg[CURSEG_HOT_NODE],
+ si->full_seg[CURSEG_HOT_NODE],
+ si->valid_blks[CURSEG_HOT_NODE]);
+ seq_printf(s, " - File dnode: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_WARM_NODE],
si->cursec[CURSEG_WARM_NODE],
- si->curzone[CURSEG_WARM_NODE]);
- seq_printf(s, " - Indir nodes: %d, %d, %d\n",
+ si->curzone[CURSEG_WARM_NODE],
+ si->dirty_seg[CURSEG_WARM_NODE],
+ si->full_seg[CURSEG_WARM_NODE],
+ si->valid_blks[CURSEG_WARM_NODE]);
+ seq_printf(s, " - Indir nodes: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_COLD_NODE],
si->cursec[CURSEG_COLD_NODE],
- si->curzone[CURSEG_COLD_NODE]);
+ si->curzone[CURSEG_COLD_NODE],
+ si->dirty_seg[CURSEG_COLD_NODE],
+ si->full_seg[CURSEG_COLD_NODE],
+ si->valid_blks[CURSEG_COLD_NODE]);
seq_printf(s, "\n - Valid: %d\n - Dirty: %d\n",
si->main_area_segs - si->dirty_count -
si->prefree_count - si->free_segs,
return err;
/*
- * An immature stakable filesystem shows a race condition between lookup
+ * An immature stackable filesystem shows a race condition between lookup
* and create. If we have same task when doing lookup and create, it's
* definitely fine as expected by VFS normally. Otherwise, let's just
* verify on-disk dentry one more time, which guarantees filesystem
}
/* return true, if inode page is changed */
-static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+static void __f2fs_init_extent_tree(struct inode *inode, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_extent *i_ext = ipage ? &F2FS_INODE(ipage)->i_ext : NULL;
struct extent_tree *et;
struct extent_node *en;
struct extent_info ei;
if (!f2fs_may_extent_tree(inode)) {
/* drop largest extent */
if (i_ext && i_ext->len) {
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
i_ext->len = 0;
- return true;
+ set_page_dirty(ipage);
+ return;
}
- return false;
+ return;
}
et = __grab_extent_tree(inode);
if (!i_ext || !i_ext->len)
- return false;
+ return;
get_extent_info(&ei, i_ext);
}
out:
write_unlock(&et->lock);
- return false;
}
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+void f2fs_init_extent_tree(struct inode *inode, struct page *ipage)
{
- bool ret = __f2fs_init_extent_tree(inode, i_ext);
+ __f2fs_init_extent_tree(inode, ipage);
if (!F2FS_I(inode)->extent_tree)
set_inode_flag(inode, FI_NO_EXTENT);
-
- return ret;
}
static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
}
/*
- * ioctl commands
+ * f2fs-specific ioctl commands
*/
-#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
-#define F2FS_IOC_GETVERSION FS_IOC_GETVERSION
-
#define F2FS_IOCTL_MAGIC 0xf5
#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
_IOR(F2FS_IOCTL_MAGIC, 18, __u64)
#define F2FS_IOC_RESERVE_COMPRESS_BLOCKS \
_IOR(F2FS_IOCTL_MAGIC, 19, __u64)
-
-#define F2FS_IOC_GET_VOLUME_NAME FS_IOC_GETFSLABEL
-#define F2FS_IOC_SET_VOLUME_NAME FS_IOC_SETFSLABEL
-
-#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
-#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
-#define F2FS_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT
+#define F2FS_IOC_SEC_TRIM_FILE _IOW(F2FS_IOCTL_MAGIC, 20, \
+ struct f2fs_sectrim_range)
/*
* should be same as XFS_IOC_GOINGDOWN.
#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */
#define F2FS_GOING_DOWN_NEED_FSCK 0x4 /* going down to trigger fsck */
-#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
- * ioctl commands in 32 bit emulation
+ * Flags used by F2FS_IOC_SEC_TRIM_FILE
*/
-#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
-#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
-#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION
-#endif
-
-#define F2FS_IOC_FSGETXATTR FS_IOC_FSGETXATTR
-#define F2FS_IOC_FSSETXATTR FS_IOC_FSSETXATTR
+#define F2FS_TRIM_FILE_DISCARD 0x1 /* send discard command */
+#define F2FS_TRIM_FILE_ZEROOUT 0x2 /* zero out */
+#define F2FS_TRIM_FILE_MASK 0x3
struct f2fs_gc_range {
u32 sync;
u32 segments; /* # of segments to flush */
};
+struct f2fs_sectrim_range {
+ u64 start;
+ u64 len;
+ u64 flags;
+};
+
/* for inline stuff */
#define DEF_INLINE_RESERVED_SIZE 1
static inline int get_extra_isize(struct inode *inode);
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
struct task_struct *inmem_task; /* store inmemory task */
struct mutex inmem_lock; /* lock for inmemory pages */
+ pgoff_t ra_offset; /* ongoing readahead offset */
struct extent_tree *extent_tree; /* cached extent_tree entry */
/* avoid racing between foreground op and gc */
GC_NORMAL,
GC_IDLE_CB,
GC_IDLE_GREEDY,
- GC_URGENT,
+ GC_URGENT_HIGH,
+ GC_URGENT_LOW,
};
enum {
#define IS_DUMMY_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
+#ifdef CONFIG_F2FS_IO_TRACE
+#define IS_IO_TRACED_PAGE(page) \
+ (page_private(page) > 0 && \
+ page_private(page) < (unsigned long)PID_MAX_LIMIT)
+#else
+#define IS_IO_TRACED_PAGE(page) (0)
+#endif
+
#ifdef CONFIG_FS_ENCRYPTION
#define DUMMY_ENCRYPTION_ENABLED(sbi) \
(unlikely(F2FS_OPTION(sbi).dummy_enc_ctx.ctx != NULL))
unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
long interval_time[MAX_TIME]; /* to store thresholds */
- struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
+ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
spinlock_t fsync_node_lock; /* for node entry lock */
struct list_head fsync_node_list; /* node list head */
unsigned int cur_victim_sec; /* current victim section num */
unsigned int gc_mode; /* current GC state */
unsigned int next_victim_seg[2]; /* next segment in victim section */
+
/* for skip statistic */
- unsigned int atomic_files; /* # of opened atomic file */
+ unsigned int atomic_files; /* # of opened atomic file */
unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */
unsigned long long skipped_gc_rwsem; /* FG_GC only */
static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
- if (sbi->gc_mode == GC_URGENT)
+ if (sbi->gc_mode == GC_URGENT_HIGH)
return true;
if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
return false;
+ if (sbi->gc_mode == GC_URGENT_LOW &&
+ (type == DISCARD_TIME || type == GC_TIME))
+ return true;
+
return f2fs_time_over(sbi, type);
}
static inline void set_inode_flag(struct inode *inode, int flag)
{
- test_and_set_bit(flag, F2FS_I(inode)->flags);
+ set_bit(flag, F2FS_I(inode)->flags);
__mark_inode_dirty_flag(inode, flag, true);
}
static inline void clear_inode_flag(struct inode *inode, int flag)
{
- test_and_clear_bit(flag, F2FS_I(inode)->flags);
+ clear_bit(flag, F2FS_I(inode)->flags);
__mark_inode_dirty_flag(inode, flag, false);
}
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
struct page *f2fs_get_node_page_ra(struct page *parent, int start);
int f2fs_move_node_page(struct page *node_page, int gc_type);
-int f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
+void f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic,
unsigned int *seq_id);
void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
-void f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
+int f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
-void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
+void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
unsigned int start, unsigned int end);
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type);
+void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type);
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
struct cp_control *cpc);
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
- struct f2fs_io_info *fio, bool add_list);
+ struct f2fs_io_info *fio);
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type, bool ordered, bool locked);
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size);
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
-void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
+void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
int curseg[NR_CURSEG_TYPE];
int cursec[NR_CURSEG_TYPE];
int curzone[NR_CURSEG_TYPE];
+ unsigned int dirty_seg[NR_CURSEG_TYPE];
+ unsigned int full_seg[NR_CURSEG_TYPE];
+ unsigned int valid_blks[NR_CURSEG_TYPE];
unsigned int meta_count[META_MAX];
unsigned int segment_count[2];
int f2fs_convert_inline_inode(struct inode *inode);
int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
int f2fs_write_inline_data(struct inode *inode, struct page *page);
-bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
+int f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
const struct f2fs_filename *fname,
struct page **res_page);
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
struct rb_root_cached *root);
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
+void f2fs_init_extent_tree(struct inode *inode, struct page *ipage);
void f2fs_drop_extent_tree(struct inode *inode);
unsigned int f2fs_destroy_extent_node(struct inode *inode);
void f2fs_destroy_extent_tree(struct inode *inode);
#include <linux/uuid.h>
#include <linux/file.h>
#include <linux/nls.h>
+#include <linux/sched/signal.h>
#include "f2fs.h"
#include "node.h"
if (need_alloc) {
/* block allocation */
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_block(&dn, page->index);
f2fs_put_dnode(&dn);
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
truncate_pagecache(inode, offset);
new_size = i_size_read(inode) - len;
- truncate_pagecache(inode, new_size);
-
ret = f2fs_truncate_blocks(inode, new_size, true);
up_write(&F2FS_I(inode)->i_mmap_sem);
if (!ret)
map.m_seg_type = CURSEG_COLD_DATA_PINNED;
f2fs_lock_op(sbi);
- f2fs_allocate_new_segments(sbi, CURSEG_COLD_DATA);
+ f2fs_allocate_new_segment(sbi, CURSEG_COLD_DATA);
f2fs_unlock_op(sbi);
err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
}
ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start));
+ if (ret) {
+ if (ret == -EBUSY)
+ ret = -EAGAIN;
+ goto out;
+ }
range.start += BLKS_PER_SEC(sbi);
if (range.start <= end)
goto do_more;
return fsverity_ioctl_measure(filp, (void __user *)arg);
}
-static int f2fs_get_volume_name(struct file *filp, unsigned long arg)
+static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
return err;
}
-static int f2fs_set_volume_name(struct file *filp, unsigned long arg)
+static int f2fs_ioc_setfslabel(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (ret)
goto out;
- if (!F2FS_I(inode)->i_compr_blocks)
- goto out;
-
F2FS_I(inode)->i_flags |= F2FS_IMMUTABLE_FL;
f2fs_set_inode_flags(inode);
inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, true);
+ if (!F2FS_I(inode)->i_compr_blocks)
+ goto out;
+
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
return ret;
}
+static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode,
+ pgoff_t off, block_t block, block_t len, u32 flags)
+{
+ struct request_queue *q = bdev_get_queue(bdev);
+ sector_t sector = SECTOR_FROM_BLOCK(block);
+ sector_t nr_sects = SECTOR_FROM_BLOCK(len);
+ int ret = 0;
+
+ if (!q)
+ return -ENXIO;
+
+ if (flags & F2FS_TRIM_FILE_DISCARD)
+ ret = blkdev_issue_discard(bdev, sector, nr_sects, GFP_NOFS,
+ blk_queue_secure_erase(q) ?
+ BLKDEV_DISCARD_SECURE : 0);
+
+ if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) {
+ if (IS_ENCRYPTED(inode))
+ ret = fscrypt_zeroout_range(inode, off, block, len);
+ else
+ ret = blkdev_issue_zeroout(bdev, sector, nr_sects,
+ GFP_NOFS, 0);
+ }
+
+ return ret;
+}
+
+static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct address_space *mapping = inode->i_mapping;
+ struct block_device *prev_bdev = NULL;
+ struct f2fs_sectrim_range range;
+ pgoff_t index, pg_end, prev_index = 0;
+ block_t prev_block = 0, len = 0;
+ loff_t end_addr;
+ bool to_end = false;
+ int ret = 0;
+
+ if (!(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(&range, (struct f2fs_sectrim_range __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ if (range.flags == 0 || (range.flags & ~F2FS_TRIM_FILE_MASK) ||
+ !S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ if (((range.flags & F2FS_TRIM_FILE_DISCARD) &&
+ !f2fs_hw_support_discard(sbi)) ||
+ ((range.flags & F2FS_TRIM_FILE_ZEROOUT) &&
+ IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi)))
+ return -EOPNOTSUPP;
+
+ file_start_write(filp);
+ inode_lock(inode);
+
+ if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) ||
+ range.start >= inode->i_size) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ if (range.len == 0)
+ goto err;
+
+ if (inode->i_size - range.start > range.len) {
+ end_addr = range.start + range.len;
+ } else {
+ end_addr = range.len == (u64)-1 ?
+ sbi->sb->s_maxbytes : inode->i_size;
+ to_end = true;
+ }
+
+ if (!IS_ALIGNED(range.start, F2FS_BLKSIZE) ||
+ (!to_end && !IS_ALIGNED(end_addr, F2FS_BLKSIZE))) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ index = F2FS_BYTES_TO_BLK(range.start);
+ pg_end = DIV_ROUND_UP(end_addr, F2FS_BLKSIZE);
+
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ goto err;
+
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
+ ret = filemap_write_and_wait_range(mapping, range.start,
+ to_end ? LLONG_MAX : end_addr - 1);
+ if (ret)
+ goto out;
+
+ truncate_inode_pages_range(mapping, range.start,
+ to_end ? -1 : end_addr - 1);
+
+ while (index < pg_end) {
+ struct dnode_of_data dn;
+ pgoff_t end_offset, count;
+ int i;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ if (ret) {
+ if (ret == -ENOENT) {
+ index = f2fs_get_next_page_offset(&dn, index);
+ continue;
+ }
+ goto out;
+ }
+
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+ count = min(end_offset - dn.ofs_in_node, pg_end - index);
+ for (i = 0; i < count; i++, index++, dn.ofs_in_node++) {
+ struct block_device *cur_bdev;
+ block_t blkaddr = f2fs_data_blkaddr(&dn);
+
+ if (!__is_valid_data_blkaddr(blkaddr))
+ continue;
+
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
+ DATA_GENERIC_ENHANCE)) {
+ ret = -EFSCORRUPTED;
+ f2fs_put_dnode(&dn);
+ goto out;
+ }
+
+ cur_bdev = f2fs_target_device(sbi, blkaddr, NULL);
+ if (f2fs_is_multi_device(sbi)) {
+ int di = f2fs_target_device_index(sbi, blkaddr);
+
+ blkaddr -= FDEV(di).start_blk;
+ }
+
+ if (len) {
+ if (prev_bdev == cur_bdev &&
+ index == prev_index + len &&
+ blkaddr == prev_block + len) {
+ len++;
+ } else {
+ ret = f2fs_secure_erase(prev_bdev,
+ inode, prev_index, prev_block,
+ len, range.flags);
+ if (ret) {
+ f2fs_put_dnode(&dn);
+ goto out;
+ }
+
+ len = 0;
+ }
+ }
+
+ if (!len) {
+ prev_bdev = cur_bdev;
+ prev_index = index;
+ prev_block = blkaddr;
+ len = 1;
+ }
+ }
+
+ f2fs_put_dnode(&dn);
+
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+ goto out;
+ }
+ cond_resched();
+ }
+
+ if (len)
+ ret = f2fs_secure_erase(prev_bdev, inode, prev_index,
+ prev_block, len, range.flags);
+out:
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+err:
+ inode_unlock(inode);
+ file_end_write(filp);
+
+ return ret;
+}
+
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp)))))
return -ENOSPC;
switch (cmd) {
- case F2FS_IOC_GETFLAGS:
+ case FS_IOC_GETFLAGS:
return f2fs_ioc_getflags(filp, arg);
- case F2FS_IOC_SETFLAGS:
+ case FS_IOC_SETFLAGS:
return f2fs_ioc_setflags(filp, arg);
- case F2FS_IOC_GETVERSION:
+ case FS_IOC_GETVERSION:
return f2fs_ioc_getversion(filp, arg);
case F2FS_IOC_START_ATOMIC_WRITE:
return f2fs_ioc_start_atomic_write(filp);
return f2fs_ioc_shutdown(filp, arg);
case FITRIM:
return f2fs_ioc_fitrim(filp, arg);
- case F2FS_IOC_SET_ENCRYPTION_POLICY:
+ case FS_IOC_SET_ENCRYPTION_POLICY:
return f2fs_ioc_set_encryption_policy(filp, arg);
- case F2FS_IOC_GET_ENCRYPTION_POLICY:
+ case FS_IOC_GET_ENCRYPTION_POLICY:
return f2fs_ioc_get_encryption_policy(filp, arg);
- case F2FS_IOC_GET_ENCRYPTION_PWSALT:
+ case FS_IOC_GET_ENCRYPTION_PWSALT:
return f2fs_ioc_get_encryption_pwsalt(filp, arg);
case FS_IOC_GET_ENCRYPTION_POLICY_EX:
return f2fs_ioc_get_encryption_policy_ex(filp, arg);
return f2fs_ioc_flush_device(filp, arg);
case F2FS_IOC_GET_FEATURES:
return f2fs_ioc_get_features(filp, arg);
- case F2FS_IOC_FSGETXATTR:
+ case FS_IOC_FSGETXATTR:
return f2fs_ioc_fsgetxattr(filp, arg);
- case F2FS_IOC_FSSETXATTR:
+ case FS_IOC_FSSETXATTR:
return f2fs_ioc_fssetxattr(filp, arg);
case F2FS_IOC_GET_PIN_FILE:
return f2fs_ioc_get_pin_file(filp, arg);
return f2fs_ioc_enable_verity(filp, arg);
case FS_IOC_MEASURE_VERITY:
return f2fs_ioc_measure_verity(filp, arg);
- case F2FS_IOC_GET_VOLUME_NAME:
- return f2fs_get_volume_name(filp, arg);
- case F2FS_IOC_SET_VOLUME_NAME:
- return f2fs_set_volume_name(filp, arg);
+ case FS_IOC_GETFSLABEL:
+ return f2fs_ioc_getfslabel(filp, arg);
+ case FS_IOC_SETFSLABEL:
+ return f2fs_ioc_setfslabel(filp, arg);
case F2FS_IOC_GET_COMPRESS_BLOCKS:
return f2fs_get_compress_blocks(filp, arg);
case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
return f2fs_release_compress_blocks(filp, arg);
case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
return f2fs_reserve_compress_blocks(filp, arg);
+ case F2FS_IOC_SEC_TRIM_FILE:
+ return f2fs_sec_trim_file(filp, arg);
default:
return -ENOTTY;
}
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
- case F2FS_IOC32_GETFLAGS:
- cmd = F2FS_IOC_GETFLAGS;
+ case FS_IOC32_GETFLAGS:
+ cmd = FS_IOC_GETFLAGS;
break;
- case F2FS_IOC32_SETFLAGS:
- cmd = F2FS_IOC_SETFLAGS;
+ case FS_IOC32_SETFLAGS:
+ cmd = FS_IOC_SETFLAGS;
break;
- case F2FS_IOC32_GETVERSION:
- cmd = F2FS_IOC_GETVERSION;
+ case FS_IOC32_GETVERSION:
+ cmd = FS_IOC_GETVERSION;
break;
case F2FS_IOC_START_ATOMIC_WRITE:
case F2FS_IOC_COMMIT_ATOMIC_WRITE:
case F2FS_IOC_ABORT_VOLATILE_WRITE:
case F2FS_IOC_SHUTDOWN:
case FITRIM:
- case F2FS_IOC_SET_ENCRYPTION_POLICY:
- case F2FS_IOC_GET_ENCRYPTION_PWSALT:
- case F2FS_IOC_GET_ENCRYPTION_POLICY:
+ case FS_IOC_SET_ENCRYPTION_POLICY:
+ case FS_IOC_GET_ENCRYPTION_PWSALT:
+ case FS_IOC_GET_ENCRYPTION_POLICY:
case FS_IOC_GET_ENCRYPTION_POLICY_EX:
case FS_IOC_ADD_ENCRYPTION_KEY:
case FS_IOC_REMOVE_ENCRYPTION_KEY:
case F2FS_IOC_MOVE_RANGE:
case F2FS_IOC_FLUSH_DEVICE:
case F2FS_IOC_GET_FEATURES:
- case F2FS_IOC_FSGETXATTR:
- case F2FS_IOC_FSSETXATTR:
+ case FS_IOC_FSGETXATTR:
+ case FS_IOC_FSSETXATTR:
case F2FS_IOC_GET_PIN_FILE:
case F2FS_IOC_SET_PIN_FILE:
case F2FS_IOC_PRECACHE_EXTENTS:
case F2FS_IOC_RESIZE_FS:
case FS_IOC_ENABLE_VERITY:
case FS_IOC_MEASURE_VERITY:
- case F2FS_IOC_GET_VOLUME_NAME:
- case F2FS_IOC_SET_VOLUME_NAME:
+ case FS_IOC_GETFSLABEL:
+ case FS_IOC_SETFSLABEL:
case F2FS_IOC_GET_COMPRESS_BLOCKS:
case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
+ case F2FS_IOC_SEC_TRIM_FILE:
break;
default:
return -ENOIOCTLCMD;
#include "gc.h"
#include <trace/events/f2fs.h>
+static unsigned int count_bits(const unsigned long *addr,
+ unsigned int offset, unsigned int len);
+
static int gc_thread_func(void *data)
{
struct f2fs_sb_info *sbi = data;
* invalidated soon after by user update or deletion.
* So, I'd like to wait some time to collect dirty segments.
*/
- if (sbi->gc_mode == GC_URGENT) {
+ if (sbi->gc_mode == GC_URGENT_HIGH) {
wait_ms = gc_th->urgent_sleep_time;
down_write(&sbi->gc_lock);
goto do_gc;
gc_mode = GC_CB;
break;
case GC_IDLE_GREEDY:
- case GC_URGENT:
+ case GC_URGENT_HIGH:
gc_mode = GC_GREEDY;
break;
}
if (p->alloc_mode == SSR) {
p->gc_mode = GC_GREEDY;
- p->dirty_segmap = dirty_i->dirty_segmap[type];
+ p->dirty_bitmap = dirty_i->dirty_segmap[type];
p->max_search = dirty_i->nr_dirty[type];
p->ofs_unit = 1;
} else {
p->gc_mode = select_gc_type(sbi, gc_type);
- p->dirty_segmap = dirty_i->dirty_segmap[DIRTY];
- p->max_search = dirty_i->nr_dirty[DIRTY];
p->ofs_unit = sbi->segs_per_sec;
+ if (__is_large_section(sbi)) {
+ p->dirty_bitmap = dirty_i->dirty_secmap;
+ p->max_search = count_bits(p->dirty_bitmap,
+ 0, MAIN_SECS(sbi));
+ } else {
+ p->dirty_bitmap = dirty_i->dirty_segmap[DIRTY];
+ p->max_search = dirty_i->nr_dirty[DIRTY];
+ }
}
/*
* foreground GC and urgent GC cases.
*/
if (gc_type != FG_GC &&
- (sbi->gc_mode != GC_URGENT) &&
+ (sbi->gc_mode != GC_URGENT_HIGH) &&
p->max_search > sbi->max_victim_search)
p->max_search = sbi->max_victim_search;
unsigned int secno, last_victim;
unsigned int last_segment;
unsigned int nsearched = 0;
+ int ret = 0;
mutex_lock(&dirty_i->seglist_lock);
last_segment = MAIN_SECS(sbi) * sbi->segs_per_sec;
p.min_cost = get_max_cost(sbi, &p);
if (*result != NULL_SEGNO) {
- if (get_valid_blocks(sbi, *result, false) &&
- !sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+ if (!get_valid_blocks(sbi, *result, false)) {
+ ret = -ENODATA;
+ goto out;
+ }
+
+ if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+ ret = -EBUSY;
+ else
p.min_segno = *result;
goto out;
}
+ ret = -ENODATA;
if (p.max_search == 0)
goto out;
}
while (1) {
- unsigned long cost;
- unsigned int segno;
-
- segno = find_next_bit(p.dirty_segmap, last_segment, p.offset);
+ unsigned long cost, *dirty_bitmap;
+ unsigned int unit_no, segno;
+
+ dirty_bitmap = p.dirty_bitmap;
+ unit_no = find_next_bit(dirty_bitmap,
+ last_segment / p.ofs_unit,
+ p.offset / p.ofs_unit);
+ segno = unit_no * p.ofs_unit;
if (segno >= last_segment) {
if (sm->last_victim[p.gc_mode]) {
last_segment =
}
p.offset = segno + p.ofs_unit;
- if (p.ofs_unit > 1) {
- p.offset -= segno % p.ofs_unit;
- nsearched += count_bits(p.dirty_segmap,
- p.offset - p.ofs_unit,
- p.ofs_unit);
- } else {
- nsearched++;
- }
+ nsearched++;
#ifdef CONFIG_F2FS_CHECK_FS
/*
next:
if (nsearched >= p.max_search) {
if (!sm->last_victim[p.gc_mode] && segno <= last_victim)
- sm->last_victim[p.gc_mode] = last_victim + 1;
+ sm->last_victim[p.gc_mode] =
+ last_victim + p.ofs_unit;
else
- sm->last_victim[p.gc_mode] = segno + 1;
+ sm->last_victim[p.gc_mode] = segno + p.ofs_unit;
sm->last_victim[p.gc_mode] %=
(MAIN_SECS(sbi) * sbi->segs_per_sec);
break;
else
set_bit(secno, dirty_i->victim_secmap);
}
+ ret = 0;
}
out:
prefree_segments(sbi), free_segments(sbi));
mutex_unlock(&dirty_i->seglist_lock);
- return (p.min_segno == NULL_SEGNO) ? 0 : 1;
+ return ret;
}
static const struct victim_selection default_v_ops = {
mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi),
fio.old_blkaddr, false);
- if (!mpage)
+ if (!mpage) {
+ err = -ENOMEM;
goto up_out;
+ }
fio.encrypted_page = mpage;
}
f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
- &sum, CURSEG_COLD_DATA, NULL, false);
+ &sum, CURSEG_COLD_DATA, NULL);
fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS);
ret = -EINVAL;
goto stop;
}
- if (!__get_victim(sbi, &segno, gc_type)) {
- ret = -ENODATA;
+ ret = __get_victim(sbi, &segno, gc_type);
+ if (ret)
goto stop;
- }
seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
/* Move out cursegs from the target range */
for (type = CURSEG_HOT_DATA; type < NR_CURSEG_TYPE; type++)
- allocate_segment_for_resize(sbi, type, start, end);
+ f2fs_allocate_segment_for_resize(sbi, type, start, end);
/* do GC to move out valid blocks in the range */
for (segno = start; segno <= end; segno += sbi->segs_per_sec) {
#include "f2fs.h"
#include "node.h"
+#include <trace/events/f2fs.h>
bool f2fs_may_inline_data(struct inode *inode)
{
return 0;
}
-bool f2fs_recover_inline_data(struct inode *inode, struct page *npage)
+int f2fs_recover_inline_data(struct inode *inode, struct page *npage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode *ri = NULL;
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
ipage = f2fs_get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(sbi, IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true, true);
set_page_dirty(ipage);
f2fs_put_page(ipage, 1);
- return true;
+ return 1;
}
if (f2fs_has_inline_data(inode)) {
ipage = f2fs_get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(sbi, IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
f2fs_truncate_inline_inode(inode, ipage, 0);
clear_inode_flag(inode, FI_INLINE_DATA);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
- if (f2fs_truncate_blocks(inode, 0, false))
- return false;
+ int ret;
+
+ ret = f2fs_truncate_blocks(inode, 0, false);
+ if (ret)
+ return ret;
goto process_inline;
}
- return false;
+ return 0;
}
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
byteaddr += (char *)inline_data_addr(inode, ipage) -
(char *)F2FS_INODE(ipage);
err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
+ trace_f2fs_fiemap(inode, start, byteaddr, ilen, flags, err);
out:
f2fs_put_page(ipage, 1);
return err;
fi->i_pino = le32_to_cpu(ri->i_pino);
fi->i_dir_level = ri->i_dir_level;
- if (f2fs_init_extent_tree(inode, &ri->i_ext))
- set_page_dirty(node_page);
+ f2fs_init_extent_tree(inode, node_page);
get_inline_info(inode, ri);
/* try to recover cold bit for non-dir inode */
if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) {
+ f2fs_wait_on_page_writeback(node_page, NODE, true, true);
set_cold_node(node_page, false);
set_page_dirty(node_page);
}
trace_f2fs_unlink_enter(dir, dentry);
- if (unlikely(f2fs_cp_error(sbi)))
- return -EIO;
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto fail;
+ }
err = dquot_initialize(dir);
if (err)
- return err;
+ goto fail;
err = dquot_initialize(inode);
if (err)
- return err;
+ goto fail;
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (!de) {
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
- * negative dentries at f2fs_lookup(), when it is better
+ * negative dentries at f2fs_lookup(), when it is better
* supported by the VFS for the CI case.
*/
if (IS_CASEFOLDED(dir))
}
const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
- .get_link = f2fs_encrypted_get_link,
+ .get_link = f2fs_encrypted_get_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.listxattr = f2fs_listxattr,
};
const struct inode_operations f2fs_symlink_inode_operations = {
- .get_link = f2fs_get_link,
+ .get_link = f2fs_get_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.listxattr = f2fs_listxattr,
const struct inode_operations f2fs_special_inode_operations = {
.getattr = f2fs_getattr,
- .setattr = f2fs_setattr,
+ .setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
.listxattr = f2fs_listxattr,
trace_f2fs_truncate_inode_blocks_enter(inode, from);
level = get_node_path(inode, from, offset, noffset);
- if (level < 0)
+ if (level < 0) {
+ trace_f2fs_truncate_inode_blocks_exit(inode, level);
return level;
+ }
page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
set_dentry_mark(page,
f2fs_need_dentry_mark(sbi, ino));
}
- /* may be written by other thread */
+ /* may be written by other thread */
if (!PageDirty(page))
set_page_dirty(page);
}
return true;
}
-int f2fs_flush_inline_data(struct f2fs_sb_info *sbi)
+void f2fs_flush_inline_data(struct f2fs_sb_info *sbi)
{
pgoff_t index = 0;
struct pagevec pvec;
int nr_pages;
- int ret = 0;
pagevec_init(&pvec);
pagevec_release(&pvec);
cond_resched();
}
- return ret;
}
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
goto continue_unlock;
}
- /* flush inline_data, if it's async context. */
- if (do_balance && is_inline_node(page)) {
+ /* flush inline_data/inode, if it's async context. */
+ if (!do_balance)
+ goto write_node;
+
+ /* flush inline_data */
+ if (is_inline_node(page)) {
clear_inline_node(page);
unlock_page(page);
flush_inline_data(sbi, ino_of_node(page));
if (flush_dirty_inode(page))
goto lock_node;
}
-
+write_node:
f2fs_wait_on_page_writeback(page, NODE, true, true);
if (!clear_page_dirty_for_io(page))
.invalidatepage = f2fs_invalidate_page,
.releasepage = f2fs_release_page,
#ifdef CONFIG_MIGRATION
- .migratepage = f2fs_migrate_page,
+ .migratepage = f2fs_migrate_page,
#endif
};
}
static int __insert_free_nid(struct f2fs_sb_info *sbi,
- struct free_nid *i, enum nid_state state)
+ struct free_nid *i)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
if (err)
return err;
- f2fs_bug_on(sbi, state != i->state);
- nm_i->nid_cnt[state]++;
- if (state == FREE_NID)
- list_add_tail(&i->list, &nm_i->free_nid_list);
+ nm_i->nid_cnt[FREE_NID]++;
+ list_add_tail(&i->list, &nm_i->free_nid_list);
return 0;
}
}
}
ret = true;
- err = __insert_free_nid(sbi, i, FREE_NID);
+ err = __insert_free_nid(sbi, i);
err_out:
if (update) {
update_free_nid_bitmap(sbi, nid, ret, build);
return nr - nr_shrink;
}
-void f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
+int f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
size_t inline_size;
struct f2fs_inode *ri;
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
- f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
ri = F2FS_INODE(page);
if (ri->i_inline & F2FS_INLINE_XATTR) {
update_inode:
f2fs_update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
+ return 0;
}
int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
/* step 1: recover xattr */
if (IS_INODE(page)) {
- f2fs_recover_inline_xattr(inode, page);
+ err = f2fs_recover_inline_xattr(inode, page);
+ if (err)
+ goto out;
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
err = f2fs_recover_xattr_data(inode, page);
if (!err)
}
/* step 2: recover inline data */
- if (f2fs_recover_inline_data(inode, page))
+ err = f2fs_recover_inline_data(inode, page);
+ if (err) {
+ if (err == 1)
+ err = 0;
goto out;
+ }
/* step 3: recover data indices */
start = f2fs_start_bidx_of_node(ofs_of_node(page), inode);
f2fs_put_page(page, 1);
}
if (!err)
- f2fs_allocate_new_segments(sbi, NO_CHECK_TYPE);
+ f2fs_allocate_new_segments(sbi);
return err;
}
if (f2fs_lfs_mode(sbi))
return false;
- if (sbi->gc_mode == GC_URGENT)
+ if (sbi->gc_mode == GC_URGENT_HIGH)
return true;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return true;
}
if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]++;
+
+ if (__is_large_section(sbi)) {
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ unsigned short valid_blocks =
+ get_valid_blocks(sbi, segno, true);
+
+ f2fs_bug_on(sbi, unlikely(!valid_blocks ||
+ valid_blocks == BLKS_PER_SEC(sbi)));
+
+ if (!IS_CURSEC(sbi, secno))
+ set_bit(secno, dirty_i->dirty_secmap);
+ }
}
}
enum dirty_type dirty_type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ unsigned short valid_blocks;
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
dirty_i->nr_dirty[dirty_type]--;
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]--;
- if (get_valid_blocks(sbi, segno, true) == 0) {
+ valid_blocks = get_valid_blocks(sbi, segno, true);
+ if (valid_blocks == 0) {
clear_bit(GET_SEC_FROM_SEG(sbi, segno),
dirty_i->victim_secmap);
#ifdef CONFIG_F2FS_CHECK_FS
clear_bit(segno, SIT_I(sbi)->invalid_segmap);
#endif
}
+ if (__is_large_section(sbi)) {
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
+ if (!valid_blocks ||
+ valid_blocks == BLKS_PER_SEC(sbi)) {
+ clear_bit(secno, dirty_i->dirty_secmap);
+ return;
+ }
+
+ if (!IS_CURSEC(sbi, secno))
+ set_bit(secno, dirty_i->dirty_secmap);
+ }
}
}
continue;
}
- if (sbi->gc_mode == GC_URGENT)
+ if (sbi->gc_mode == GC_URGENT_HIGH)
__init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);
sb_start_intwrite(sbi->sb);
new_vblocks = se->valid_blocks + del;
offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
- f2fs_bug_on(sbi, (new_vblocks >> (sizeof(unsigned short) << 3) ||
+ f2fs_bug_on(sbi, (new_vblocks < 0 ||
(new_vblocks > sbi->blocks_per_seg)));
se->valid_blocks = new_vblocks;
bool reversed = false;
/* f2fs_need_SSR() already forces to do this */
- if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
+ if (!v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
curseg->next_segno = segno;
return 1;
}
for (; cnt-- > 0; reversed ? i-- : i++) {
if (i == type)
continue;
- if (v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
+ if (!v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
curseg->next_segno = segno;
return 1;
}
stat_inc_seg_type(sbi, curseg);
}
-void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
+void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
unsigned int start, unsigned int end)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
up_read(&SM_I(sbi)->curseg_lock);
}
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type)
+static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type)
{
- struct curseg_info *curseg;
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
unsigned int old_segno;
- int i;
- down_write(&SIT_I(sbi)->sentry_lock);
+ if (!curseg->next_blkoff &&
+ !get_valid_blocks(sbi, curseg->segno, false) &&
+ !get_ckpt_valid_blocks(sbi, curseg->segno))
+ return;
- for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
- if (type != NO_CHECK_TYPE && i != type)
- continue;
+ old_segno = curseg->segno;
+ SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
+ locate_dirty_segment(sbi, old_segno);
+}
- curseg = CURSEG_I(sbi, i);
- if (type == NO_CHECK_TYPE || curseg->next_blkoff ||
- get_valid_blocks(sbi, curseg->segno, false) ||
- get_ckpt_valid_blocks(sbi, curseg->segno)) {
- old_segno = curseg->segno;
- SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
- locate_dirty_segment(sbi, old_segno);
- }
- }
+void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type)
+{
+ down_write(&SIT_I(sbi)->sentry_lock);
+ __allocate_new_segment(sbi, type);
+ up_write(&SIT_I(sbi)->sentry_lock);
+}
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
+{
+ int i;
+
+ down_write(&SIT_I(sbi)->sentry_lock);
+ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
+ __allocate_new_segment(sbi, i);
up_write(&SIT_I(sbi)->sentry_lock);
}
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
- struct f2fs_io_info *fio, bool add_list)
+ struct f2fs_io_info *fio)
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, type);
type = CURSEG_COLD_DATA;
}
- /*
- * We need to wait for node_write to avoid block allocation during
- * checkpoint. This can only happen to quota writes which can cause
- * the below discard race condition.
- */
- if (IS_DATASEG(type))
- down_write(&sbi->node_write);
-
down_read(&SM_I(sbi)->curseg_lock);
mutex_lock(&curseg->curseg_mutex);
if (F2FS_IO_ALIGNED(sbi))
fio->retry = false;
- if (add_list) {
+ if (fio) {
struct f2fs_bio_info *io;
INIT_LIST_HEAD(&fio->list);
up_read(&SM_I(sbi)->curseg_lock);
- if (IS_DATASEG(type))
- up_write(&sbi->node_write);
-
if (put_pin_sem)
up_read(&sbi->pin_sem);
}
down_read(&fio->sbi->io_order_lock);
reallocate:
f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
- &fio->new_blkaddr, sum, type, fio, true);
+ &fio->new_blkaddr, sum, type, fio);
if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
invalidate_mapping_pages(META_MAPPING(fio->sbi),
fio->old_blkaddr, fio->old_blkaddr);
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int segno = 0, offset = 0;
+ unsigned int segno = 0, offset = 0, secno;
unsigned short valid_blocks;
+ unsigned short blks_per_sec = BLKS_PER_SEC(sbi);
while (1) {
/* find dirty segment based on free segmap */
__locate_dirty_segment(sbi, segno, DIRTY);
mutex_unlock(&dirty_i->seglist_lock);
}
+
+ if (!__is_large_section(sbi))
+ return;
+
+ mutex_lock(&dirty_i->seglist_lock);
+ for (segno = 0; segno < MAIN_SECS(sbi); segno += blks_per_sec) {
+ valid_blocks = get_valid_blocks(sbi, segno, true);
+ secno = GET_SEC_FROM_SEG(sbi, segno);
+
+ if (!valid_blocks || valid_blocks == blks_per_sec)
+ continue;
+ if (IS_CURSEC(sbi, secno))
+ continue;
+ set_bit(secno, dirty_i->dirty_secmap);
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
}
static int init_victim_secmap(struct f2fs_sb_info *sbi)
return -ENOMEM;
}
+ if (__is_large_section(sbi)) {
+ bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
+ dirty_i->dirty_secmap = f2fs_kvzalloc(sbi,
+ bitmap_size, GFP_KERNEL);
+ if (!dirty_i->dirty_secmap)
+ return -ENOMEM;
+ }
+
init_dirty_segmap(sbi);
return init_victim_secmap(sbi);
}
for (i = 0; i < NR_DIRTY_TYPE; i++)
discard_dirty_segmap(sbi, i);
+ if (__is_large_section(sbi)) {
+ mutex_lock(&dirty_i->seglist_lock);
+ kvfree(dirty_i->dirty_secmap);
+ mutex_unlock(&dirty_i->seglist_lock);
+ }
+
destroy_victim_secmap(sbi);
SM_I(sbi)->dirty_info = NULL;
kvfree(dirty_i);
struct victim_sel_policy {
int alloc_mode; /* LFS or SSR */
int gc_mode; /* GC_CB or GC_GREEDY */
- unsigned long *dirty_segmap; /* dirty segment bitmap */
- unsigned int max_search; /* maximum # of segments to search */
+ unsigned long *dirty_bitmap; /* dirty segment/section bitmap */
+ unsigned int max_search; /*
+ * maximum # of segments/sections
+ * to search
+ */
unsigned int offset; /* last scanned bitmap offset */
unsigned int ofs_unit; /* bitmap search unit */
unsigned int min_cost; /* minimum cost */
unsigned char *cur_valid_map_mir; /* mirror of current valid bitmap */
#endif
/*
- * # of valid blocks and the validity bitmap stored in the the last
+ * # of valid blocks and the validity bitmap stored in the last
* checkpoint pack. This information is used by the SSR mode.
*/
unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */
struct dirty_seglist_info {
const struct victim_selection *v_ops; /* victim selction operation */
unsigned long *dirty_segmap[NR_DIRTY_TYPE];
+ unsigned long *dirty_secmap;
struct mutex seglist_lock; /* lock for segment bitmaps */
int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */
unsigned long *victim_secmap; /* background GC victims */
set_opt(sbi, QUOTA);
return 0;
errout:
- kvfree(qname);
+ kfree(qname);
return ret;
}
f2fs_err(sbi, "Cannot change journaled quota options when quota turned on");
return -EINVAL;
}
- kvfree(F2FS_OPTION(sbi).s_qf_names[qtype]);
+ kfree(F2FS_OPTION(sbi).s_qf_names[qtype]);
F2FS_OPTION(sbi).s_qf_names[qtype] = NULL;
return 0;
}
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
substring_t args[MAX_OPT_ARGS];
+#ifdef CONFIG_F2FS_FS_COMPRESSION
unsigned char (*ext)[F2FS_EXTENSION_LEN];
+ int ext_cnt;
+#endif
char *p, *name;
- int arg = 0, ext_cnt;
+ int arg = 0;
kuid_t uid;
kgid_t gid;
int ret;
} else if (!strcmp(name, "sync")) {
F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_SYNC;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_disable_roll_forward:
set_opt(sbi, DISABLE_ROLL_FORWARD);
if (!strcmp(name, "adaptive")) {
if (f2fs_sb_has_blkzoned(sbi)) {
f2fs_warn(sbi, "adaptive mode is not allowed with zoned block device feature");
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE;
} else if (!strcmp(name, "lfs")) {
F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_io_size_bits:
if (args->from && match_int(args, &arg))
} else if (!strcmp(name, "fs-based")) {
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_alloc:
name = match_strdup(&args[0]);
} else if (!strcmp(name, "reuse")) {
F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_fsync:
name = match_strdup(&args[0]);
F2FS_OPTION(sbi).fsync_mode =
FSYNC_MODE_NOBARRIER;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_test_dummy_encryption:
ret = f2fs_set_test_dummy_encryption(sb, p, &args[0],
case Opt_checkpoint_enable:
clear_opt(sbi, DISABLE_CHECKPOINT);
break;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
case Opt_compress_algorithm:
if (!f2fs_sb_has_compression(sbi)) {
f2fs_err(sbi, "Compression feature if off");
F2FS_OPTION(sbi).compress_ext_cnt++;
kfree(name);
break;
+#else
+ case Opt_compress_algorithm:
+ case Opt_compress_log_size:
+ case Opt_compress_extension:
+ f2fs_info(sbi, "compression options not supported");
+ break;
+#endif
default:
f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
p);
/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
+ fi->ra_offset = -1;
+
return &fi->vfs_inode;
}
int i;
bool dropped;
+ /* unregister procfs/sysfs entries in advance to avoid race case */
+ f2fs_unregister_sysfs(sbi);
+
f2fs_quota_off_umount(sb);
/* prevent remaining shrinker jobs */
kvfree(sbi->ckpt);
- f2fs_unregister_sysfs(sbi);
-
sb->s_fs_info = NULL;
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
- kvfree(sbi->raw_super);
+ kfree(sbi->raw_super);
destroy_device_list(sbi);
f2fs_destroy_xattr_caches(sbi);
mempool_destroy(sbi->write_io_dummy);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
- kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+ kfree(F2FS_OPTION(sbi).s_qf_names[i]);
#endif
fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
destroy_percpu_info(sbi);
#ifdef CONFIG_UNICODE
utf8_unload(sbi->s_encoding);
#endif
- kvfree(sbi);
+ kfree(sbi);
}
int f2fs_sync_fs(struct super_block *sb, int sync)
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER)
seq_printf(seq, ",fsync_mode=%s", "nobarrier");
+#ifdef CONFIG_F2FS_FS_COMPRESSION
f2fs_show_compress_options(seq, sbi->sb);
+#endif
return 0;
}
GFP_KERNEL);
if (!org_mount_opt.s_qf_names[i]) {
for (j = 0; j < i; j++)
- kvfree(org_mount_opt.s_qf_names[j]);
+ kfree(org_mount_opt.s_qf_names[j]);
return -ENOMEM;
}
} else {
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
- kvfree(org_mount_opt.s_qf_names[i]);
+ kfree(org_mount_opt.s_qf_names[i]);
#endif
/* Update the POSIXACL Flag */
sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
#ifdef CONFIG_QUOTA
F2FS_OPTION(sbi).s_jquota_fmt = org_mount_opt.s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
- kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+ kfree(F2FS_OPTION(sbi).s_qf_names[i]);
F2FS_OPTION(sbi).s_qf_names[i] = org_mount_opt.s_qf_names[i];
}
#endif
/* No valid superblock */
if (!*raw_super)
- kvfree(super);
+ kfree(super);
else
err = 0;
free_options:
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
- kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+ kfree(F2FS_OPTION(sbi).s_qf_names[i]);
#endif
fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
kvfree(options);
free_sb_buf:
- kvfree(raw_super);
+ kfree(raw_super);
free_sbi:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
- kvfree(sbi);
+ kfree(sbi);
/* give only one another chance */
if (retry_cnt > 0 && skip_recovery) {
NM_INFO, /* struct f2fs_nm_info */
F2FS_SBI, /* struct f2fs_sb_info */
#ifdef CONFIG_F2FS_STAT_FS
- STAT_INFO, /* struct f2fs_stat_info */
+ STAT_INFO, /* struct f2fs_stat_info */
#endif
#ifdef CONFIG_F2FS_FAULT_INJECTION
FAULT_INFO_RATE, /* struct f2fs_fault_info */
}
#endif
+static ssize_t main_blkaddr_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ (unsigned long long)MAIN_BLKADDR(sbi));
+}
+
static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
return -EINVAL;
if (!strcmp(a->attr.name, "gc_urgent")) {
- if (t >= 1) {
- sbi->gc_mode = GC_URGENT;
+ if (t == 0) {
+ sbi->gc_mode = GC_NORMAL;
+ } else if (t == 1) {
+ sbi->gc_mode = GC_URGENT_HIGH;
if (sbi->gc_thread) {
sbi->gc_thread->gc_wake = 1;
wake_up_interruptible_all(
&sbi->gc_thread->gc_wait_queue_head);
wake_up_discard_thread(sbi, true);
}
+ } else if (t == 2) {
+ sbi->gc_mode = GC_URGENT_LOW;
} else {
- sbi->gc_mode = GC_NORMAL;
+ return -EINVAL;
}
return count;
}
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, main_blkaddr, main_blkaddr);
F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity);
F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks);
F2FS_GENERAL_RO_ATTR(unusable);
F2FS_GENERAL_RO_ATTR(encoding);
F2FS_GENERAL_RO_ATTR(mounted_time_sec);
+F2FS_GENERAL_RO_ATTR(main_blkaddr);
#ifdef CONFIG_F2FS_STAT_FS
F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count);
F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count);
};
static struct kset f2fs_kset = {
- .kobj = {.ktype = &f2fs_ktype},
+ .kobj = {.ktype = &f2fs_ktype},
};
static struct kobj_type f2fs_feat_ktype = {
#include "f2fs.h"
#include "xattr.h"
+#define F2FS_VERIFY_VER (1)
+
static inline loff_t f2fs_verity_metadata_pos(const struct inode *inode)
{
return round_up(inode->i_size, 65536);
struct inode *inode = file_inode(filp);
u64 desc_pos = f2fs_verity_metadata_pos(inode) + merkle_tree_size;
struct fsverity_descriptor_location dloc = {
- .version = cpu_to_le32(1),
+ .version = cpu_to_le32(F2FS_VERIFY_VER),
.size = cpu_to_le32(desc_size),
.pos = cpu_to_le64(desc_pos),
};
F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc), NULL);
if (res < 0 && res != -ERANGE)
return res;
- if (res != sizeof(dloc) || dloc.version != cpu_to_le32(1)) {
+ if (res != sizeof(dloc) || dloc.version != cpu_to_le32(F2FS_VERIFY_VER)) {
f2fs_warn(F2FS_I_SB(inode), "unknown verity xattr format");
return -EINVAL;
}
const struct xattr_handler f2fs_xattr_advise_handler = {
.name = F2FS_SYSTEM_ADVISE_NAME,
.flags = F2FS_XATTR_INDEX_ADVISE,
- .get = f2fs_xattr_advise_get,
- .set = f2fs_xattr_advise_set,
+ .get = f2fs_xattr_advise_get,
+ .set = f2fs_xattr_advise_set,
};
const struct xattr_handler f2fs_xattr_security_handler = {
__entry->fs_cdrio, __entry->fs_nrio, __entry->fs_mrio)
);
+TRACE_EVENT(f2fs_bmap,
+
+ TP_PROTO(struct inode *inode, sector_t lblock, sector_t pblock),
+
+ TP_ARGS(inode, lblock, pblock),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(sector_t, lblock)
+ __field(sector_t, pblock)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->lblock = lblock;
+ __entry->pblock = pblock;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, lblock:%lld, pblock:%lld",
+ show_dev_ino(__entry),
+ (unsigned long long)__entry->lblock,
+ (unsigned long long)__entry->pblock)
+);
+
+TRACE_EVENT(f2fs_fiemap,
+
+ TP_PROTO(struct inode *inode, sector_t lblock, sector_t pblock,
+ unsigned long long len, unsigned int flags, int ret),
+
+ TP_ARGS(inode, lblock, pblock, len, flags, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(sector_t, lblock)
+ __field(sector_t, pblock)
+ __field(unsigned long long, len)
+ __field(unsigned int, flags)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->lblock = lblock;
+ __entry->pblock = pblock;
+ __entry->len = len;
+ __entry->flags = flags;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, lblock:%lld, pblock:%lld, "
+ "len:%llu, flags:%u, ret:%d",
+ show_dev_ino(__entry),
+ (unsigned long long)__entry->lblock,
+ (unsigned long long)__entry->pblock,
+ __entry->len,
+ __entry->flags,
+ __entry->ret)
+);
+
#endif /* _TRACE_F2FS_H */
/* This part must be outside protection */
projects / linux-block.git / commitdiff