Contact: "Chao Yu" <chao2.yu@samsung.com>
Description:
Controls the count of nid pages to be readaheaded.
+
+What: /sys/fs/f2fs/<disk>/dirty_nats_ratio
+Date: January 2016
+Contact: "Chao Yu" <chao2.yu@samsung.com>
+Description:
+ Controls dirty nat entries ratio threshold, if current
+ ratio exceeds configured threshold, checkpoint will
+ be triggered for flushing dirty nat entries.
+
+What: /sys/fs/f2fs/<disk>/lifetime_write_kbytes
+Date: January 2016
+Contact: "Shuoran Liu" <liushuoran@huawei.com>
+Description:
+ Shows total written kbytes issued to disk.
cond_resched();
goto repeat;
}
- f2fs_wait_on_page_writeback(page, META);
+ f2fs_wait_on_page_writeback(page, META, true);
SetPageUptodate(page);
return page;
}
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
- f2fs_wait_on_page_writeback(page, META);
write_meta_page(sbi, page);
dec_page_count(sbi, F2FS_DIRTY_META);
+
+ if (wbc->for_reclaim)
+ f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+
unlock_page(page);
- if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi)))
+ if (unlikely(f2fs_cp_error(sbi)))
f2fs_submit_merged_bio(sbi, META, WRITE);
+
return 0;
redirty_out:
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff, written;
- trace_f2fs_writepages(mapping->host, wbc, META);
-
/* collect a number of dirty meta pages and write together */
if (wbc->for_kupdate ||
get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
goto skip_write;
+ trace_f2fs_writepages(mapping->host, wbc, META);
+
/* if mounting is failed, skip writing node pages */
mutex_lock(&sbi->cp_mutex);
diff = nr_pages_to_write(sbi, META, wbc);
skip_write:
wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META);
+ trace_f2fs_writepages(mapping->host, wbc, META);
return 0;
}
goto continue_unlock;
}
+ f2fs_wait_on_page_writeback(page, META, true);
+
+ BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
int cp_payload_blks = __cp_payload(sbi);
block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
bool invalidate = false;
+ struct super_block *sb = sbi->sb;
+ struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+ u64 kbytes_written;
/*
* This avoids to conduct wrong roll-forward operations and uses
write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
+
+ /* Record write statistics in the hot node summary */
+ kbytes_written = sbi->kbytes_written;
+ if (sb->s_bdev->bd_part)
+ kbytes_written += BD_PART_WRITTEN(sbi);
+
+ seg_i->sum_blk->info.kbytes_written = cpu_to_le64(kbytes_written);
+
if (__remain_node_summaries(cpc->reason)) {
write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
f2fs_restore_and_release_control_page(&page);
if (unlikely(bio->bi_error)) {
- set_page_dirty(page);
set_bit(AS_EIO, &page->mapping->flags);
f2fs_stop_checkpoint(sbi);
}
dec_page_count(sbi, F2FS_WRITEBACK);
}
- if (!get_pages(sbi, F2FS_WRITEBACK) &&
- !list_empty(&sbi->cp_wait.task_list))
+ if (!get_pages(sbi, F2FS_WRITEBACK) && wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
bio_put(bio);
io->bio = NULL;
}
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
- enum page_type type, int rw)
+static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
+ struct page *page, nid_t ino)
+{
+ struct bio_vec *bvec;
+ struct page *target;
+ int i;
+
+ if (!io->bio)
+ return false;
+
+ if (!inode && !page && !ino)
+ return true;
+
+ bio_for_each_segment_all(bvec, io->bio, i) {
+
+ if (bvec->bv_page->mapping) {
+ target = bvec->bv_page;
+ } else {
+ struct f2fs_crypto_ctx *ctx;
+
+ /* encrypted page */
+ ctx = (struct f2fs_crypto_ctx *)page_private(
+ bvec->bv_page);
+ target = ctx->w.control_page;
+ }
+
+ if (inode && inode == target->mapping->host)
+ return true;
+ if (page && page == target)
+ return true;
+ if (ino && ino == ino_of_node(target))
+ return true;
+ }
+
+ return false;
+}
+
+static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
+ struct page *page, nid_t ino,
+ enum page_type type)
+{
+ enum page_type btype = PAGE_TYPE_OF_BIO(type);
+ struct f2fs_bio_info *io = &sbi->write_io[btype];
+ bool ret;
+
+ down_read(&io->io_rwsem);
+ ret = __has_merged_page(io, inode, page, ino);
+ up_read(&io->io_rwsem);
+ return ret;
+}
+
+static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
+ struct inode *inode, struct page *page,
+ nid_t ino, enum page_type type, int rw)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
struct f2fs_bio_info *io;
down_write(&io->io_rwsem);
+ if (!__has_merged_page(io, inode, page, ino))
+ goto out;
+
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO;
}
__submit_merged_bio(io);
+out:
up_write(&io->io_rwsem);
}
+void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
+ int rw)
+{
+ __f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw);
+}
+
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+ struct inode *inode, struct page *page,
+ nid_t ino, enum page_type type, int rw)
+{
+ if (has_merged_page(sbi, inode, page, ino, type))
+ __f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw);
+}
+
/*
* Fill the locked page with data located in the block address.
* Return unlocked page.
struct page *node_page = dn->node_page;
unsigned int ofs_in_node = dn->ofs_in_node;
- f2fs_wait_on_page_writeback(node_page, NODE);
+ f2fs_wait_on_page_writeback(node_page, NODE, true);
rn = F2FS_NODE(node_page);
static int __allocate_data_block(struct dnode_of_data *dn)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
- struct f2fs_inode_info *fi = F2FS_I(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
int seg = CURSEG_WARM_DATA;
set_data_blkaddr(dn);
/* update i_size */
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
dn->ofs_in_node;
if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT))
i_size_write(dn->inode,
return 0;
}
-static int __allocate_data_blocks(struct inode *inode, loff_t offset,
- size_t count)
+ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dnode_of_data dn;
- u64 start = F2FS_BYTES_TO_BLK(offset);
- u64 len = F2FS_BYTES_TO_BLK(count);
- bool allocated;
- u64 end_offset;
- int err = 0;
-
- while (len) {
- f2fs_lock_op(sbi);
-
- /* When reading holes, we need its node page */
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, start, ALLOC_NODE);
- if (err)
- goto out;
-
- allocated = false;
- end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
-
- while (dn.ofs_in_node < end_offset && len) {
- block_t blkaddr;
-
- if (unlikely(f2fs_cp_error(sbi))) {
- err = -EIO;
- goto sync_out;
- }
-
- blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
- if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) {
- err = __allocate_data_block(&dn);
- if (err)
- goto sync_out;
- allocated = true;
- }
- len--;
- start++;
- dn.ofs_in_node++;
- }
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct f2fs_map_blocks map;
+ ssize_t ret = 0;
- if (allocated)
- sync_inode_page(&dn);
+ map.m_lblk = F2FS_BYTES_TO_BLK(iocb->ki_pos);
+ map.m_len = F2FS_BLK_ALIGN(iov_iter_count(from));
+ map.m_next_pgofs = NULL;
- f2fs_put_dnode(&dn);
- f2fs_unlock_op(sbi);
+ if (f2fs_encrypted_inode(inode))
+ return 0;
- f2fs_balance_fs(sbi, dn.node_changed);
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+ return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
}
- return err;
-
-sync_out:
- if (allocated)
- sync_inode_page(&dn);
- f2fs_put_dnode(&dn);
-out:
- f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, dn.node_changed);
- return err;
+ if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+ }
+ if (!f2fs_has_inline_data(inode))
+ return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+ return ret;
}
/*
/* it only supports block size == page size */
pgofs = (pgoff_t)map->m_lblk;
- if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
+ if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
map->m_pblk = ei.blk + pgofs - ei.fofs;
map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
map->m_flags = F2FS_MAP_MAPPED;
goto out;
}
+next_dnode:
if (create)
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, mode);
if (err) {
- if (err == -ENOENT)
+ if (err == -ENOENT) {
err = 0;
+ if (map->m_next_pgofs)
+ *map->m_next_pgofs =
+ get_next_page_offset(&dn, pgofs);
+ }
goto unlock_out;
}
- if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) {
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+
+next_block:
+ blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
if (create) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
- goto put_out;
+ goto sync_out;
+ }
+ if (flag == F2FS_GET_BLOCK_PRE_AIO) {
+ if (blkaddr == NULL_ADDR)
+ err = reserve_new_block(&dn);
+ } else {
+ err = __allocate_data_block(&dn);
}
- err = __allocate_data_block(&dn);
if (err)
- goto put_out;
+ goto sync_out;
allocated = true;
map->m_flags = F2FS_MAP_NEW;
+ blkaddr = dn.data_blkaddr;
} else {
+ if (flag == F2FS_GET_BLOCK_FIEMAP &&
+ blkaddr == NULL_ADDR) {
+ if (map->m_next_pgofs)
+ *map->m_next_pgofs = pgofs + 1;
+ }
if (flag != F2FS_GET_BLOCK_FIEMAP ||
- dn.data_blkaddr != NEW_ADDR) {
+ blkaddr != NEW_ADDR) {
if (flag == F2FS_GET_BLOCK_BMAP)
err = -ENOENT;
- goto put_out;
+ goto sync_out;
}
-
- /*
- * preallocated unwritten block should be mapped
- * for fiemap.
- */
- if (dn.data_blkaddr == NEW_ADDR)
- map->m_flags = F2FS_MAP_UNWRITTEN;
}
}
- map->m_flags |= F2FS_MAP_MAPPED;
- map->m_pblk = dn.data_blkaddr;
- map->m_len = 1;
+ if (map->m_len == 0) {
+ /* preallocated unwritten block should be mapped for fiemap. */
+ if (blkaddr == NEW_ADDR)
+ map->m_flags |= F2FS_MAP_UNWRITTEN;
+ map->m_flags |= F2FS_MAP_MAPPED;
+
+ map->m_pblk = blkaddr;
+ map->m_len = 1;
+ } else if ((map->m_pblk != NEW_ADDR &&
+ blkaddr == (map->m_pblk + ofs)) ||
+ (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
+ flag == F2FS_GET_BLOCK_PRE_DIO ||
+ flag == F2FS_GET_BLOCK_PRE_AIO) {
+ ofs++;
+ map->m_len++;
+ } else {
+ goto sync_out;
+ }
- end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
dn.ofs_in_node++;
pgofs++;
-get_next:
- if (map->m_len >= maxblocks)
- goto sync_out;
+ if (map->m_len < maxblocks) {
+ if (dn.ofs_in_node < end_offset)
+ goto next_block;
- if (dn.ofs_in_node >= end_offset) {
if (allocated)
sync_inode_page(&dn);
- allocated = false;
f2fs_put_dnode(&dn);
if (create) {
f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, dn.node_changed);
- f2fs_lock_op(sbi);
- }
-
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, pgofs, mode);
- if (err) {
- if (err == -ENOENT)
- err = 0;
- goto unlock_out;
+ f2fs_balance_fs(sbi, allocated);
}
-
- end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
- }
-
- blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
-
- 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)) ||
- (map->m_pblk == NEW_ADDR &&
- blkaddr == NEW_ADDR)) {
- ofs++;
- dn.ofs_in_node++;
- pgofs++;
- map->m_len++;
- goto get_next;
+ allocated = false;
+ goto next_dnode;
}
sync_out:
if (allocated)
sync_inode_page(&dn);
-put_out:
f2fs_put_dnode(&dn);
unlock_out:
if (create) {
f2fs_unlock_op(sbi);
- f2fs_balance_fs(sbi, dn.node_changed);
+ f2fs_balance_fs(sbi, allocated);
}
out:
trace_f2fs_map_blocks(inode, map, err);
}
static int __get_data_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh, int create, int flag)
+ struct buffer_head *bh, int create, int flag,
+ pgoff_t *next_pgofs)
{
struct f2fs_map_blocks map;
int ret;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
+ map.m_next_pgofs = next_pgofs;
ret = f2fs_map_blocks(inode, &map, create, flag);
if (!ret) {
}
static int get_data_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create, int flag)
+ struct buffer_head *bh_result, int create, int flag,
+ pgoff_t *next_pgofs)
{
- return __get_data_block(inode, iblock, bh_result, create, flag);
+ return __get_data_block(inode, iblock, bh_result, create,
+ flag, next_pgofs);
}
static int get_data_block_dio(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
return __get_data_block(inode, iblock, bh_result, create,
- F2FS_GET_BLOCK_DIO);
+ F2FS_GET_BLOCK_DIO, NULL);
}
static int get_data_block_bmap(struct inode *inode, sector_t iblock,
return -EFBIG;
return __get_data_block(inode, iblock, bh_result, create,
- F2FS_GET_BLOCK_BMAP);
+ F2FS_GET_BLOCK_BMAP, NULL);
}
static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
{
struct buffer_head map_bh;
sector_t start_blk, last_blk;
+ pgoff_t next_pgofs;
loff_t isize;
u64 logical = 0, phys = 0, size = 0;
u32 flags = 0;
map_bh.b_size = len;
ret = get_data_block(inode, start_blk, &map_bh, 0,
- F2FS_GET_BLOCK_FIEMAP);
+ F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
if (ret)
goto out;
/* HOLE */
if (!buffer_mapped(&map_bh)) {
+ start_blk = next_pgofs;
/* Go through holes util pass the EOF */
- if (blk_to_logical(inode, start_blk++) < isize)
+ if (blk_to_logical(inode, start_blk) < isize)
goto prep_next;
/* Found a hole beyond isize means no more extents.
* Note that the premise is that filesystems don't
map.m_lblk = 0;
map.m_len = 0;
map.m_flags = 0;
+ map.m_next_pgofs = NULL;
for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
map.m_len = last_block - block_in_file;
if (f2fs_map_blocks(inode, &map, 0,
- F2FS_GET_BLOCK_READ))
+ F2FS_GET_BLOCK_READ))
goto set_error_page;
}
got_it:
inode_dec_dirty_pages(inode);
if (err)
ClearPageUptodate(page);
+
+ if (wbc->for_reclaim) {
+ f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE);
+ remove_dirty_inode(inode);
+ }
+
unlock_page(page);
f2fs_balance_fs(sbi, need_balance_fs);
- if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi))) {
+
+ if (unlikely(f2fs_cp_error(sbi)))
f2fs_submit_merged_bio(sbi, DATA, WRITE);
- remove_dirty_inode(inode);
- }
+
return 0;
redirty_out:
if (PageWriteback(page)) {
if (wbc->sync_mode != WB_SYNC_NONE)
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page,
+ DATA, true);
else
goto continue_unlock;
}
int ret;
long diff;
- trace_f2fs_writepages(mapping->host, wbc, DATA);
-
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto skip_write;
+ trace_f2fs_writepages(mapping->host, wbc, DATA);
+
diff = nr_pages_to_write(sbi, DATA, wbc);
- if (!S_ISDIR(inode->i_mode)) {
+ if (!S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_ALL) {
mutex_lock(&sbi->writepages);
locked = true;
}
ret = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
if (locked)
mutex_unlock(&sbi->writepages);
skip_write:
wbc->pages_skipped += get_dirty_pages(inode);
+ trace_f2fs_writepages(mapping->host, wbc, DATA);
return 0;
}
struct extent_info ei;
int err = 0;
+ /*
+ * we already allocated all the blocks, so we don't need to get
+ * the block addresses when there is no need to fill the page.
+ */
+ if (!f2fs_has_inline_data(inode) && !f2fs_encrypted_inode(inode) &&
+ len == PAGE_CACHE_SIZE)
+ return 0;
+
if (f2fs_has_inline_data(inode) ||
(pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
f2fs_lock_op(sbi);
if (pos + len <= MAX_INLINE_DATA) {
read_inline_data(page, ipage);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
- sync_inode_page(&dn);
+ set_inline_node(ipage);
} else {
err = f2fs_convert_inline_page(&dn, page);
if (err)
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn.data_blkaddr = ei.blk + index - ei.fofs;
} else {
- bool restart = false;
-
/* hole case */
err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
- if (err || (!err && dn.data_blkaddr == NULL_ADDR))
- restart = true;
- if (restart) {
+ if (err || (!err && dn.data_blkaddr == NULL_ADDR)) {
f2fs_put_dnode(&dn);
f2fs_lock_op(sbi);
locked = true;
}
}
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, false);
/* wait for GCed encrypted page writeback */
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
if (pos + copied > i_size_read(inode)) {
i_size_write(inode, pos + copied);
mark_inode_dirty(inode);
- update_inode_page(inode);
}
f2fs_put_page(page, 1);
static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
loff_t offset)
{
- struct file *file = iocb->ki_filp;
- struct address_space *mapping = file->f_mapping;
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
int err;
- /* we don't need to use inline_data strictly */
- err = f2fs_convert_inline_inode(inode);
+ err = check_direct_IO(inode, iter, offset);
if (err)
return err;
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
return 0;
- err = check_direct_IO(inode, iter, offset);
- if (err)
- return err;
-
trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- if (iov_iter_rw(iter) == WRITE) {
- err = __allocate_data_blocks(inode, offset, count);
- if (err)
- 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);
{
enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
lock_page(page);
- f2fs_wait_on_page_writeback(page, type);
+ f2fs_wait_on_page_writeback(page, type, true);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode->i_mode);
f2fs_dentry_kunmap(dir, page);
{
struct f2fs_inode *ri;
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
/* copy name info. to this inode page */
ri = F2FS_INODE(ipage);
++level;
goto start;
add_dentry:
- f2fs_wait_on_page_writeback(dentry_page, DATA);
+ f2fs_wait_on_page_writeback(dentry_page, DATA, true);
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
return f2fs_delete_inline_entry(dentry, page, dir, inode);
lock_page(page);
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, true);
dentry_blk = page_address(page);
bit_pos = dentry - dentry_blk->dentry;
en->ei = *ei;
INIT_LIST_HEAD(&en->list);
+ en->et = et;
rb_link_node(&en->rb_node, parent, p);
rb_insert_color(&en->rb_node, &et->root);
if (et->cached_en == en)
et->cached_en = NULL;
+ kmem_cache_free(extent_node_slab, en);
+}
+
+/*
+ * Flow to release an extent_node:
+ * 1. list_del_init
+ * 2. __detach_extent_node
+ * 3. kmem_cache_free.
+ */
+static void __release_extent_node(struct f2fs_sb_info *sbi,
+ struct extent_tree *et, struct extent_node *en)
+{
+ spin_lock(&sbi->extent_lock);
+ f2fs_bug_on(sbi, list_empty(&en->list));
+ list_del_init(&en->list);
+ spin_unlock(&sbi->extent_lock);
+
+ __detach_extent_node(sbi, et, en);
}
static struct extent_tree *__grab_extent_tree(struct inode *inode)
}
static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
- struct extent_tree *et, bool free_all)
+ struct extent_tree *et)
{
struct rb_node *node, *next;
struct extent_node *en;
while (node) {
next = rb_next(node);
en = rb_entry(node, struct extent_node, rb_node);
-
- if (free_all) {
- spin_lock(&sbi->extent_lock);
- if (!list_empty(&en->list))
- list_del_init(&en->list);
- spin_unlock(&sbi->extent_lock);
- }
-
- if (free_all || list_empty(&en->list)) {
- __detach_extent_node(sbi, et, en);
- kmem_cache_free(extent_node_slab, en);
- }
+ __release_extent_node(sbi, et, en);
node = next;
}
if (en) {
*ei = en->ei;
spin_lock(&sbi->extent_lock);
- if (!list_empty(&en->list))
+ if (!list_empty(&en->list)) {
list_move_tail(&en->list, &sbi->extent_list);
- et->cached_en = en;
+ et->cached_en = en;
+ }
spin_unlock(&sbi->extent_lock);
ret = true;
}
static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
struct extent_tree *et, struct extent_info *ei,
- struct extent_node **den,
struct extent_node *prev_ex,
struct extent_node *next_ex)
{
}
if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
- if (en) {
- __detach_extent_node(sbi, et, prev_ex);
- *den = prev_ex;
- }
+ if (en)
+ __release_extent_node(sbi, et, prev_ex);
next_ex->ei.fofs = ei->fofs;
next_ex->ei.blk = ei->blk;
next_ex->ei.len += ei->len;
en = next_ex;
}
- if (en) {
- __try_update_largest_extent(et, en);
+ if (!en)
+ return NULL;
+
+ __try_update_largest_extent(et, en);
+
+ spin_lock(&sbi->extent_lock);
+ if (!list_empty(&en->list)) {
+ list_move_tail(&en->list, &sbi->extent_list);
et->cached_en = en;
}
+ spin_unlock(&sbi->extent_lock);
return en;
}
return NULL;
__try_update_largest_extent(et, en);
+
+ /* update in global extent list */
+ spin_lock(&sbi->extent_lock);
+ list_add_tail(&en->list, &sbi->extent_list);
et->cached_en = en;
+ spin_unlock(&sbi->extent_lock);
return en;
}
if (parts)
__try_update_largest_extent(et, en);
else
- __detach_extent_node(sbi, et, en);
+ __release_extent_node(sbi, et, en);
/*
* if original extent is split into zero or two parts, extent
insert_p = NULL;
insert_parent = NULL;
}
-
- /* update in global extent list */
- spin_lock(&sbi->extent_lock);
- if (!parts && !list_empty(&en->list))
- list_del(&en->list);
- if (en1)
- list_add_tail(&en1->list, &sbi->extent_list);
- spin_unlock(&sbi->extent_lock);
-
- /* release extent node */
- if (!parts)
- kmem_cache_free(extent_node_slab, en);
-
en = next_en;
}
/* 3. update extent in extent cache */
if (blkaddr) {
- struct extent_node *den = NULL;
set_extent_info(&ei, fofs, blkaddr, len);
- en1 = __try_merge_extent_node(sbi, et, &ei, &den,
- prev_en, next_en);
- if (!en1)
- en1 = __insert_extent_tree(sbi, et, &ei,
+ if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
+ __insert_extent_tree(sbi, et, &ei,
insert_p, insert_parent);
/* give up extent_cache, if split and small updates happen */
et->largest.len = 0;
set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
}
-
- spin_lock(&sbi->extent_lock);
- if (en1) {
- if (list_empty(&en1->list))
- list_add_tail(&en1->list, &sbi->extent_list);
- else
- list_move_tail(&en1->list, &sbi->extent_list);
- }
- if (den && !list_empty(&den->list))
- list_del(&den->list);
- spin_unlock(&sbi->extent_lock);
-
- if (den)
- kmem_cache_free(extent_node_slab, den);
}
if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
- __free_extent_tree(sbi, et, true);
+ __free_extent_tree(sbi, et);
write_unlock(&et->lock);
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
{
- struct extent_tree *treevec[EXT_TREE_VEC_SIZE];
struct extent_tree *et, *next;
- struct extent_node *en, *tmp;
- unsigned long ino = F2FS_ROOT_INO(sbi);
- unsigned int found;
+ struct extent_node *en;
unsigned int node_cnt = 0, tree_cnt = 0;
int remained;
- bool do_free = false;
if (!test_opt(sbi, EXTENT_CACHE))
return 0;
list_for_each_entry_safe(et, next, &sbi->zombie_list, list) {
if (atomic_read(&et->node_cnt)) {
write_lock(&et->lock);
- node_cnt += __free_extent_tree(sbi, et, true);
+ node_cnt += __free_extent_tree(sbi, et);
write_unlock(&et->lock);
}
-
+ f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
list_del_init(&et->list);
radix_tree_delete(&sbi->extent_tree_root, et->ino);
kmem_cache_free(extent_tree_slab, et);
if (node_cnt + tree_cnt >= nr_shrink)
goto unlock_out;
+ cond_resched();
}
up_write(&sbi->extent_tree_lock);
remained = nr_shrink - (node_cnt + tree_cnt);
spin_lock(&sbi->extent_lock);
- list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) {
- if (!remained--)
+ for (; remained > 0; remained--) {
+ if (list_empty(&sbi->extent_list))
break;
- list_del_init(&en->list);
- do_free = true;
- }
- spin_unlock(&sbi->extent_lock);
-
- if (do_free == false)
- goto unlock_out;
-
- /*
- * reset ino for searching victims from beginning of global extent tree.
- */
- ino = F2FS_ROOT_INO(sbi);
-
- while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root,
- (void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
- unsigned i;
-
- ino = treevec[found - 1]->ino + 1;
- for (i = 0; i < found; i++) {
- struct extent_tree *et = treevec[i];
+ en = list_first_entry(&sbi->extent_list,
+ struct extent_node, list);
+ et = en->et;
+ if (!write_trylock(&et->lock)) {
+ /* refresh this extent node's position in extent list */
+ list_move_tail(&en->list, &sbi->extent_list);
+ continue;
+ }
- if (!atomic_read(&et->node_cnt))
- continue;
+ list_del_init(&en->list);
+ spin_unlock(&sbi->extent_lock);
- if (write_trylock(&et->lock)) {
- node_cnt += __free_extent_tree(sbi, et, false);
- write_unlock(&et->lock);
- }
+ __detach_extent_node(sbi, et, en);
- if (node_cnt + tree_cnt >= nr_shrink)
- goto unlock_out;
- }
+ write_unlock(&et->lock);
+ node_cnt++;
+ spin_lock(&sbi->extent_lock);
}
+ spin_unlock(&sbi->extent_lock);
+
unlock_out:
up_write(&sbi->extent_tree_lock);
out:
return 0;
write_lock(&et->lock);
- node_cnt = __free_extent_tree(sbi, et, true);
+ node_cnt = __free_extent_tree(sbi, et);
write_unlock(&et->lock);
return node_cnt;
void f2fs_update_extent_cache(struct dnode_of_data *dn)
{
- struct f2fs_inode_info *fi = F2FS_I(dn->inode);
pgoff_t fofs;
if (!f2fs_may_extent_tree(dn->inode))
f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
- dn->ofs_in_node;
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+ dn->ofs_in_node;
if (f2fs_update_extent_tree_range(dn->inode, fofs, dn->data_blkaddr, 1))
sync_inode_page(dn);
struct rb_node rb_node; /* rb node located in rb-tree */
struct list_head list; /* node in global extent list of sbi */
struct extent_info ei; /* extent info */
+ struct extent_tree *et; /* extent tree pointer */
};
struct extent_tree {
block_t m_lblk;
unsigned int m_len;
unsigned int m_flags;
+ pgoff_t *m_next_pgofs; /* point next possible non-hole pgofs */
};
/* for flag in get_data_block */
#define F2FS_GET_BLOCK_DIO 1
#define F2FS_GET_BLOCK_FIEMAP 2
#define F2FS_GET_BLOCK_BMAP 3
+#define F2FS_GET_BLOCK_PRE_DIO 4
+#define F2FS_GET_BLOCK_PRE_AIO 5
/*
* i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
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 */
+ unsigned int dirty_nats_ratio; /* control dirty nats ratio threshold */
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
unsigned int ofs_in_node; /* data offset in the node page */
bool inode_page_locked; /* inode page is locked or not */
bool node_changed; /* is node block changed */
+ char cur_level; /* level of hole node page */
+ char max_level; /* level of current page located */
block_t data_blkaddr; /* block address of the node block */
};
struct list_head s_list;
struct mutex umount_mutex;
unsigned int shrinker_run_no;
+
+ /* For write statistics */
+ u64 sectors_written_start;
+ u64 kbytes_written;
};
+/* For write statistics. Suppose sector size is 512 bytes,
+ * and the return value is in kbytes. s is of struct f2fs_sb_info.
+ */
+#define BD_PART_WRITTEN(s) \
+(((u64)part_stat_read(s->sb->s_bdev->bd_part, sectors[1]) - \
+ s->sectors_written_start) >> 1)
+
static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
sbi->last_time[type] = jiffies;
return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR);
}
-static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi)
+static inline unsigned int addrs_per_inode(struct inode *inode)
{
- if (f2fs_has_inline_xattr(&fi->vfs_inode))
+ if (f2fs_has_inline_xattr(inode))
return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
return DEF_ADDRS_PER_INODE;
}
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
/* get offset of first page in next direct node */
-#define PGOFS_OF_NEXT_DNODE(pgofs, fi) \
- ((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) : \
- (pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \
- ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+#define PGOFS_OF_NEXT_DNODE(pgofs, inode) \
+ ((pgofs < ADDRS_PER_INODE(inode)) ? ADDRS_PER_INODE(inode) : \
+ (pgofs - ADDRS_PER_INODE(inode) + ADDRS_PER_BLOCK) / \
+ ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode))
/*
* file.c
bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
+pgoff_t get_next_page_offset(struct dnode_of_data *, pgoff_t);
int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
int truncate_inode_blocks(struct inode *, pgoff_t);
int truncate_xattr_node(struct inode *, struct page *);
block_t, block_t, unsigned char, bool);
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_page_writeback(struct page *, enum page_type, bool);
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);
* data.c
*/
void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *,
+ struct page *, nid_t, enum page_type, int);
int f2fs_submit_page_bio(struct f2fs_io_info *);
void f2fs_submit_page_mbio(struct f2fs_io_info *);
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);
+ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
struct page *find_data_page(struct inode *, pgoff_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 *);
+block_t start_bidx_of_node(unsigned int, struct inode *);
int f2fs_gc(struct f2fs_sb_info *, bool);
void build_gc_manager(struct f2fs_sb_info *);
trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
/* fill the page */
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, false);
/* wait for GCed encrypted page writeback */
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
- pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
- F2FS_I(inode));
+ pgofs = get_next_page_offset(&dn, pgofs);
continue;
} else {
goto found;
}
}
- end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
/* find data/hole in dnode block */
for (; dn.ofs_in_node < end_offset;
* we will invalidate all blkaddr in the whole range.
*/
fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
- F2FS_I(dn->inode)) + ofs;
+ dn->inode) + ofs;
f2fs_update_extent_cache_range(dn, fofs, 0, len);
dec_valid_block_count(sbi, dn->inode, nr_free);
sync_inode_page(dn);
if (IS_ERR(page))
return 0;
truncate_out:
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, true);
zero_user(page, offset, PAGE_CACHE_SIZE - offset);
if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode))
set_page_dirty(page);
goto out;
}
- count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ count = ADDRS_PER_PAGE(dn.node_page, inode);
count -= dn.ofs_in_node;
f2fs_bug_on(sbi, count < 0);
if (IS_ERR(page))
return PTR_ERR(page);
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, true);
zero_user(page, start, len);
set_page_dirty(page);
f2fs_put_page(page, 1);
return err;
}
- end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ end_offset = ADDRS_PER_PAGE(dn.node_page, 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);
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);
+ pdst = get_new_data_page(inode, NULL, dst, true);
if (IS_ERR(pdst)) {
f2fs_put_page(psrc, 1);
return PTR_ERR(pdst);
struct f2fs_defragment *range)
{
struct inode *inode = file_inode(filp);
- struct f2fs_map_blocks map;
+ struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
struct extent_info ei;
pgoff_t pg_start, pg_end;
unsigned int blk_per_seg = sbi->blocks_per_seg;
static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- struct inode *inode = file_inode(iocb->ki_filp);
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ ssize_t ret;
if (f2fs_encrypted_inode(inode) &&
!f2fs_has_encryption_key(inode) &&
f2fs_get_encryption_info(inode))
return -EACCES;
- return generic_file_write_iter(iocb, from);
+ inode_lock(inode);
+ ret = generic_write_checks(iocb, from);
+ if (ret > 0) {
+ ret = f2fs_preallocate_blocks(iocb, from);
+ if (!ret)
+ ret = __generic_file_write_iter(iocb, from);
+ }
+ inode_unlock(inode);
+
+ if (ret > 0) {
+ ssize_t err;
+
+ err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+ if (err < 0)
+ ret = err;
+ }
+ return ret;
}
#ifdef CONFIG_COMPAT
return get_cb_cost(sbi, segno);
}
+static unsigned int count_bits(const unsigned long *addr,
+ unsigned int offset, unsigned int len)
+{
+ unsigned int end = offset + len, sum = 0;
+
+ while (offset < end) {
+ if (test_bit(offset++, addr))
+ ++sum;
+ }
+ return sum;
+}
+
/*
* This function is called from two paths.
* One is garbage collection and the other is SSR segment selection.
struct victim_sel_policy p;
unsigned int secno, max_cost;
unsigned int last_segment = MAIN_SEGS(sbi);
- int nsearched = 0;
+ unsigned int nsearched = 0;
mutex_lock(&dirty_i->seglist_lock);
}
p.offset = segno + p.ofs_unit;
- if (p.ofs_unit > 1)
+ 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++;
+ }
+
secno = GET_SECNO(sbi, segno);
if (sec_usage_check(sbi, secno))
- continue;
+ goto next;
if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
- continue;
+ goto next;
cost = get_gc_cost(sbi, segno, &p);
if (p.min_cost > cost) {
p.min_segno = segno;
p.min_cost = cost;
- } else if (unlikely(cost == max_cost)) {
- continue;
}
-
- if (nsearched++ >= p.max_search) {
+next:
+ if (nsearched >= p.max_search) {
sbi->last_victim[p.gc_mode] = segno;
break;
}
* On validity, copy that node with cold status, otherwise (invalid node)
* ignore that.
*/
-static int gc_node_segment(struct f2fs_sb_info *sbi,
+static void gc_node_segment(struct f2fs_sb_info *sbi,
struct f2fs_summary *sum, unsigned int segno, int gc_type)
{
bool initial = true;
/* stop BG_GC if there is not enough free sections. */
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
- return 0;
+ return;
if (check_valid_map(sbi, segno, off) == 0)
continue;
/* set page dirty and write it */
if (gc_type == FG_GC) {
- f2fs_wait_on_page_writeback(node_page, NODE);
+ f2fs_wait_on_page_writeback(node_page, NODE, true);
set_page_dirty(node_page);
} else {
if (!PageWriteback(node_page))
initial = false;
goto next_step;
}
-
- if (gc_type == FG_GC) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .nr_to_write = LONG_MAX,
- .for_reclaim = 0,
- };
- sync_node_pages(sbi, 0, &wbc);
-
- /* return 1 only if FG_GC succefully reclaimed one */
- if (get_valid_blocks(sbi, segno, 1) == 0)
- return 1;
- }
- return 0;
}
/*
* as indirect or double indirect node blocks, are given, it must be a caller's
* bug.
*/
-block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
+block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
{
unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
unsigned int bidx;
int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
bidx = node_ofs - 5 - dec;
}
- return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi);
+ return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode);
}
static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
* 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);
+ f2fs_wait_on_page_writeback(page, DATA, true);
get_node_info(fio.sbi, dn.nid, &ni);
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
goto put_page_out;
set_page_dirty(fio.encrypted_page);
- f2fs_wait_on_page_writeback(fio.encrypted_page, DATA);
+ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true);
if (clear_page_dirty_for_io(fio.encrypted_page))
dec_page_count(fio.sbi, F2FS_DIRTY_META);
set_page_writeback(fio.encrypted_page);
/* allocate block address */
- f2fs_wait_on_page_writeback(dn.node_page, NODE);
+ f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
allocate_data_block(fio.sbi, NULL, fio.blk_addr,
&fio.blk_addr, &sum, CURSEG_COLD_DATA);
fio.rw = WRITE_SYNC;
.encrypted_page = NULL,
};
set_page_dirty(page);
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, true);
if (clear_page_dirty_for_io(page))
inode_dec_dirty_pages(inode);
set_cold_data(page);
* If the parent node is not valid or the data block address is different,
* the victim data block is ignored.
*/
-static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
struct gc_inode_list *gc_list, unsigned int segno, int gc_type)
{
struct super_block *sb = sbi->sb;
/* stop BG_GC if there is not enough free sections. */
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
- return 0;
+ return;
if (check_valid_map(sbi, segno, off) == 0)
continue;
continue;
}
- start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
+ start_bidx = start_bidx_of_node(nofs, inode);
data_page = get_read_data_page(inode,
start_bidx + ofs_in_node, READA, true);
if (IS_ERR(data_page)) {
/* phase 3 */
inode = find_gc_inode(gc_list, dni.ino);
if (inode) {
- start_bidx = start_bidx_of_node(nofs, F2FS_I(inode))
+ start_bidx = start_bidx_of_node(nofs, inode)
+ ofs_in_node;
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
move_encrypted_block(inode, start_bidx);
if (++phase < 4)
goto next_step;
-
- if (gc_type == FG_GC) {
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
-
- /* return 1 only if FG_GC succefully reclaimed one */
- if (get_valid_blocks(sbi, segno, 1) == 0)
- return 1;
- }
- return 0;
}
static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
return ret;
}
-static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
+static int do_garbage_collect(struct f2fs_sb_info *sbi,
+ unsigned int start_segno,
struct gc_inode_list *gc_list, int gc_type)
{
struct page *sum_page;
struct f2fs_summary_block *sum;
struct blk_plug plug;
- int nfree = 0;
+ unsigned int segno = start_segno;
+ unsigned int end_segno = start_segno + sbi->segs_per_sec;
+ int seg_freed = 0;
+ unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+ SUM_TYPE_DATA : SUM_TYPE_NODE;
- /* read segment summary of victim */
- sum_page = get_sum_page(sbi, segno);
+ /* 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, true);
+
+ /* reference all summary page */
+ while (segno < end_segno) {
+ sum_page = get_sum_page(sbi, segno++);
+ unlock_page(sum_page);
+ }
blk_start_plug(&plug);
- sum = page_address(sum_page);
+ for (segno = start_segno; segno < end_segno; segno++) {
+ /* find segment summary of victim */
+ sum_page = find_get_page(META_MAPPING(sbi),
+ GET_SUM_BLOCK(sbi, segno));
+ f2fs_bug_on(sbi, !PageUptodate(sum_page));
+ f2fs_put_page(sum_page, 0);
- /*
- * this is to avoid deadlock:
- * - lock_page(sum_page) - f2fs_replace_block
- * - check_valid_map() - mutex_lock(sentry_lock)
- * - mutex_lock(sentry_lock) - change_curseg()
- * - lock_page(sum_page)
- */
- unlock_page(sum_page);
-
- switch (GET_SUM_TYPE((&sum->footer))) {
- case SUM_TYPE_NODE:
- nfree = gc_node_segment(sbi, sum->entries, segno, gc_type);
- break;
- case SUM_TYPE_DATA:
- nfree = gc_data_segment(sbi, sum->entries, gc_list,
- segno, gc_type);
- break;
+ sum = page_address(sum_page);
+ f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
+
+ /*
+ * this is to avoid deadlock:
+ * - lock_page(sum_page) - f2fs_replace_block
+ * - check_valid_map() - mutex_lock(sentry_lock)
+ * - mutex_lock(sentry_lock) - change_curseg()
+ * - lock_page(sum_page)
+ */
+
+ if (type == SUM_TYPE_NODE)
+ gc_node_segment(sbi, sum->entries, segno, gc_type);
+ else
+ gc_data_segment(sbi, sum->entries, gc_list, segno,
+ gc_type);
+
+ stat_inc_seg_count(sbi, type, gc_type);
+ stat_inc_call_count(sbi->stat_info);
+
+ f2fs_put_page(sum_page, 0);
}
- blk_finish_plug(&plug);
- stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type);
- stat_inc_call_count(sbi->stat_info);
+ if (gc_type == FG_GC) {
+ if (type == SUM_TYPE_NODE) {
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = LONG_MAX,
+ .for_reclaim = 0,
+ };
+ sync_node_pages(sbi, 0, &wbc);
+ } else {
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ }
+ }
- f2fs_put_page(sum_page, 0);
- return nfree;
+ blk_finish_plug(&plug);
+
+ if (gc_type == FG_GC) {
+ while (start_segno < end_segno)
+ if (get_valid_blocks(sbi, start_segno++, 1) == 0)
+ seg_freed++;
+ }
+ return seg_freed;
}
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
{
- unsigned int segno, i;
+ unsigned int segno;
int gc_type = sync ? FG_GC : BG_GC;
- int sec_freed = 0;
+ int sec_freed = 0, seg_freed;
int ret = -EINVAL;
struct cp_control cpc;
struct gc_inode_list gc_list = {
if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
gc_type = FG_GC;
+ /*
+ * If there is no victim and no prefree segment but still not
+ * enough free sections, we should flush dent/node blocks and do
+ * garbage collections.
+ */
if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
write_checkpoint(sbi, &cpc);
+ else if (has_not_enough_free_secs(sbi, 0))
+ write_checkpoint(sbi, &cpc);
}
if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
goto stop;
ret = 0;
- /* 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, true);
-
- 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;
- }
+ seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
- if (i == sbi->segs_per_sec && gc_type == FG_GC)
+ if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
sec_freed++;
if (gc_type == FG_GC)
addr = inline_data_addr(ipage);
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
memset(addr + from, 0, MAX_INLINE_DATA - from);
return true;
if (err)
return err;
- f2fs_wait_on_page_writeback(page, DATA);
-
+ f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
if (PageUptodate(page))
goto no_update;
write_data_page(dn, &fio);
set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, true);
if (dirty)
inode_dec_dirty_pages(dn->inode);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode_page, 0);
+ clear_inline_node(dn->inode_page);
clear_out:
stat_dec_inline_inode(dn->inode);
f2fs_clear_inline_inode(dn->inode);
f2fs_bug_on(F2FS_I_SB(inode), page->index);
- f2fs_wait_on_page_writeback(dn.inode_page, NODE);
+ f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
src_addr = kmap_atomic(page);
dst_addr = inline_data_addr(dn.inode_page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
sync_inode_page(&dn);
+ clear_inline_node(dn.inode_page);
f2fs_put_dnode(&dn);
return 0;
}
ipage = get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
src_addr = inline_data_addr(npage);
dst_addr = inline_data_addr(ipage);
if (err)
goto out;
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, true);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
dentry_blk = kmap_atomic(page);
}
}
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
name_hash = f2fs_dentry_hash(name);
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
int i;
lock_page(page);
- f2fs_wait_on_page_writeback(page, NODE);
+ f2fs_wait_on_page_writeback(page, NODE, true);
inline_dentry = inline_data_addr(page);
bit_pos = dentry - inline_dentry->dentry;
while (start < end) {
if (*start++) {
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
{
struct f2fs_inode *ri;
- f2fs_wait_on_page_writeback(node_page, NODE);
+ f2fs_wait_on_page_writeback(node_page, NODE, true);
ri = F2FS_INODE(node_page);
set_cold_node(inode, node_page);
clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
+ /* deleted inode */
+ if (inode->i_nlink == 0)
+ clear_inline_node(node_page);
+
return set_page_dirty(node_page);
}
up_write(&nm_i->nat_tree_lock);
}
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
+{
+ const long direct_index = ADDRS_PER_INODE(dn->inode);
+ const long direct_blks = ADDRS_PER_BLOCK;
+ const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
+ unsigned int skipped_unit = ADDRS_PER_BLOCK;
+ int cur_level = dn->cur_level;
+ int max_level = dn->max_level;
+ pgoff_t base = 0;
+
+ if (!dn->max_level)
+ return pgofs + 1;
+
+ while (max_level-- > cur_level)
+ skipped_unit *= NIDS_PER_BLOCK;
+
+ switch (dn->max_level) {
+ case 3:
+ base += 2 * indirect_blks;
+ case 2:
+ base += 2 * direct_blks;
+ case 1:
+ base += direct_index;
+ break;
+ default:
+ f2fs_bug_on(F2FS_I_SB(dn->inode), 1);
+ }
+
+ return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base;
+}
+
/*
* The maximum depth is four.
* Offset[0] will have raw inode offset.
*/
-static int get_node_path(struct f2fs_inode_info *fi, long block,
+static int get_node_path(struct inode *inode, long block,
int offset[4], unsigned int noffset[4])
{
- const long direct_index = ADDRS_PER_INODE(fi);
+ const long direct_index = ADDRS_PER_INODE(inode);
const long direct_blks = ADDRS_PER_BLOCK;
const long dptrs_per_blk = NIDS_PER_BLOCK;
const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
int offset[4];
unsigned int noffset[4];
nid_t nids[4];
- int level, i;
+ int level, i = 0;
int err = 0;
- level = get_node_path(F2FS_I(dn->inode), index, offset, noffset);
+ level = get_node_path(dn->inode, index, offset, noffset);
nids[0] = dn->inode->i_ino;
npage[0] = dn->inode_page;
release_out:
dn->inode_page = NULL;
dn->node_page = NULL;
+ if (err == -ENOENT) {
+ dn->cur_level = i;
+ dn->max_level = level;
+ }
return err;
}
trace_f2fs_truncate_inode_blocks_enter(inode, from);
- level = get_node_path(F2FS_I(inode), from, offset, noffset);
+ level = get_node_path(inode, from, offset, noffset);
restart:
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
f2fs_put_page(page, 1);
goto restart;
}
- f2fs_wait_on_page_writeback(page, NODE);
+ f2fs_wait_on_page_writeback(page, NODE, true);
ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
set_page_dirty(page);
unlock_page(page);
new_ni.ino = dn->inode->i_ino;
set_node_addr(sbi, &new_ni, NEW_ADDR, false);
- f2fs_wait_on_page_writeback(page, NODE);
+ f2fs_wait_on_page_writeback(page, NODE, true);
fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
set_cold_node(dn->inode, page);
SetPageUptodate(page);
dn->node_changed = ret ? true: false;
}
+static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
+{
+ struct inode *inode;
+ struct page *page;
+
+ /* should flush inline_data before evict_inode */
+ inode = ilookup(sbi->sb, ino);
+ if (!inode)
+ return;
+
+ page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0);
+ if (!page)
+ goto iput_out;
+
+ if (!PageUptodate(page))
+ goto page_out;
+
+ if (!PageDirty(page))
+ goto page_out;
+
+ if (!clear_page_dirty_for_io(page))
+ goto page_out;
+
+ if (!f2fs_write_inline_data(inode, page))
+ inode_dec_dirty_pages(inode);
+ else
+ set_page_dirty(page);
+page_out:
+ f2fs_put_page(page, 1);
+iput_out:
+ iput(inode);
+}
+
int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
struct writeback_control *wbc)
{
goto continue_unlock;
}
+ /* flush inline_data */
+ if (!ino && is_inline_node(page)) {
+ clear_inline_node(page);
+ unlock_page(page);
+ flush_inline_data(sbi, ino_of_node(page));
+ continue;
+ }
+
+ f2fs_wait_on_page_writeback(page, NODE, true);
+
+ BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
goto next_step;
}
- if (wrote)
- f2fs_submit_merged_bio(sbi, NODE, WRITE);
+ if (wrote) {
+ if (ino)
+ f2fs_submit_merged_bio_cond(sbi, NULL, NULL,
+ ino, NODE, WRITE);
+ else
+ f2fs_submit_merged_bio(sbi, NODE, WRITE);
+ }
return nwritten;
}
continue;
if (ino && ino_of_node(page) == ino) {
- f2fs_wait_on_page_writeback(page, NODE);
+ f2fs_wait_on_page_writeback(page, NODE, true);
if (TestClearPageError(page))
ret = -EIO;
}
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
- f2fs_wait_on_page_writeback(page, NODE);
-
/* get old block addr of this node page */
nid = nid_of_node(page);
f2fs_bug_on(sbi, page->index != nid);
set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
dec_page_count(sbi, F2FS_DIRTY_NODES);
up_read(&sbi->node_write);
+
+ if (wbc->for_reclaim)
+ f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE);
+
unlock_page(page);
- if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi)))
+ if (unlikely(f2fs_cp_error(sbi)))
f2fs_submit_merged_bio(sbi, NODE, WRITE);
return 0;
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff;
- trace_f2fs_writepages(mapping->host, wbc, NODE);
-
/* balancing f2fs's metadata in background */
f2fs_balance_fs_bg(sbi);
if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE))
goto skip_write;
+ trace_f2fs_writepages(mapping->host, wbc, NODE);
+
diff = nr_pages_to_write(sbi, NODE, wbc);
wbc->sync_mode = WB_SYNC_NONE;
sync_node_pages(sbi, 0, wbc);
skip_write:
wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES);
+ trace_f2fs_writepages(mapping->host, wbc, NODE);
return 0;
}
src_addr = inline_xattr_addr(page);
inline_size = inline_xattr_size(inode);
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
memcpy(dst_addr, src_addr, inline_size);
update_inode:
update_inode(inode, ipage);
nm_i->nat_cnt = 0;
nm_i->ram_thresh = DEF_RAM_THRESHOLD;
nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
+ nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
INIT_LIST_HEAD(&nm_i->free_nid_list);
/* control the memory footprint threshold (10MB per 1GB ram) */
#define DEF_RAM_THRESHOLD 10
+/* control dirty nats ratio threshold (default: 10% over max nid count) */
+#define DEF_DIRTY_NAT_RATIO_THRESHOLD 10
+
/* vector size for gang look-up from nat cache that consists of radix tree */
#define NATVEC_SIZE 64
#define SETVEC_SIZE 32
raw_ne->version = ni->version;
}
+static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
+{
+ return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid *
+ NM_I(sbi)->dirty_nats_ratio / 100;
+}
+
enum mem_type {
FREE_NIDS, /* indicates the free nid list */
NAT_ENTRIES, /* indicates the cached nat entry */
{
struct f2fs_node *rn = F2FS_NODE(p);
- f2fs_wait_on_page_writeback(p, NODE);
+ f2fs_wait_on_page_writeback(p, NODE, true);
if (i)
rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
#define is_fsync_dnode(page) is_node(page, FSYNC_BIT_SHIFT)
#define is_dent_dnode(page) is_node(page, DENT_BIT_SHIFT)
+static inline int is_inline_node(struct page *page)
+{
+ return PageChecked(page);
+}
+
+static inline void set_inline_node(struct page *page)
+{
+ SetPageChecked(page);
+}
+
+static inline void clear_inline_node(struct page *page)
+{
+ ClearPageChecked(page);
+}
+
static inline void set_cold_node(struct inode *inode, struct page *page)
{
struct f2fs_node *rn = F2FS_NODE(page);
inode = dn->inode;
}
- bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
- le16_to_cpu(sum.ofs_in_node);
+ bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
/*
* if inode page is locked, unlock temporarily, but its reference
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct page *page, block_t blkaddr)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
- unsigned int start, end;
struct dnode_of_data dn;
struct node_info ni;
+ unsigned int start, end;
int err = 0, recovered = 0;
/* step 1: recover xattr */
goto out;
/* step 3: recover data indices */
- start = start_bidx_of_node(ofs_of_node(page), fi);
- end = start + ADDRS_PER_PAGE(page, fi);
+ start = start_bidx_of_node(ofs_of_node(page), inode);
+ end = start + ADDRS_PER_PAGE(page, inode);
set_new_dnode(&dn, inode, NULL, NULL, 0);
if (err)
goto out;
- f2fs_wait_on_page_writeback(dn.node_page, NODE);
+ f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
get_node_info(sbi, dn.nid, &ni);
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
if (!abort) {
if (cur->page->mapping == inode->i_mapping) {
set_page_dirty(cur->page);
- f2fs_wait_on_page_writeback(cur->page, DATA);
+ f2fs_wait_on_page_writeback(cur->page, DATA,
+ true);
if (clear_page_dirty_for_io(cur->page))
inode_dec_dirty_pages(inode);
trace_f2fs_commit_inmem_page(cur->page, INMEM);
if (!abort) {
f2fs_unlock_op(sbi);
if (submit_bio)
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0,
+ DATA, WRITE);
}
return err;
}
/* 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) ||
+ excess_prefree_segs(sbi) ||
+ excess_dirty_nats(sbi) ||
(is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
if (test_opt(sbi, DATA_FLUSH))
sync_dirty_inodes(sbi, FILE_INODE);
if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
segno = find_next_zero_bit(free_i->free_segmap,
- MAIN_SEGS(sbi), *newseg + 1);
- if (segno - *newseg < sbi->segs_per_sec -
- (*newseg % sbi->segs_per_sec))
+ (hint + 1) * sbi->segs_per_sec, *newseg + 1);
+ if (segno < (hint + 1) * sbi->segs_per_sec)
goto got_it;
}
find_other_zone:
f2fs_update_extent_cache(dn);
}
-static inline bool is_merged_page(struct f2fs_sb_info *sbi,
- struct page *page, enum page_type type)
-{
- enum page_type btype = PAGE_TYPE_OF_BIO(type);
- struct f2fs_bio_info *io = &sbi->write_io[btype];
- struct bio_vec *bvec;
- struct page *target;
- int i;
-
- down_read(&io->io_rwsem);
- if (!io->bio) {
- up_read(&io->io_rwsem);
- return false;
- }
-
- bio_for_each_segment_all(bvec, io->bio, i) {
-
- if (bvec->bv_page->mapping) {
- target = bvec->bv_page;
- } else {
- struct f2fs_crypto_ctx *ctx;
-
- /* encrypted page */
- ctx = (struct f2fs_crypto_ctx *)page_private(
- bvec->bv_page);
- target = ctx->w.control_page;
- }
-
- if (page == target) {
- up_read(&io->io_rwsem);
- return true;
- }
- }
-
- up_read(&io->io_rwsem);
- return false;
-}
-
void f2fs_wait_on_page_writeback(struct page *page,
- enum page_type type)
+ enum page_type type, bool ordered)
{
if (PageWriteback(page)) {
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- if (is_merged_page(sbi, page, type))
- f2fs_submit_merged_bio(sbi, type, WRITE);
- wait_on_page_writeback(page);
+ f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
+ if (ordered)
+ wait_on_page_writeback(page);
+ else
+ wait_for_stable_page(page);
}
}
cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
if (cpage) {
- f2fs_wait_on_page_writeback(cpage, DATA);
+ f2fs_wait_on_page_writeback(cpage, DATA, true);
f2fs_put_page(cpage, 1);
}
}
* this value is set in page as a private data which indicate that
* the page is atomically written, and it is in inmem_pages list.
*/
-#define ATOMIC_WRITTEN_PAGE 0x0000ffff
+#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1)
#define IS_ATOMIC_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
return NULL;
}
+static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct super_block *sb = sbi->sb;
+
+ if (!sb->s_bdev->bd_part)
+ return snprintf(buf, PAGE_SIZE, "0\n");
+
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ (unsigned long long)(sbi->kbytes_written +
+ BD_PART_WRITTEN(sbi)));
+}
+
static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
f2fs_sbi_show, f2fs_sbi_store, \
offsetof(struct struct_name, elname))
+#define F2FS_GENERAL_RO_ATTR(name) \
+static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
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(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
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, interval_time[CP_TIME]);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
ATTR_LIST(dir_level),
ATTR_LIST(ram_thresh),
ATTR_LIST(ra_nid_pages),
+ ATTR_LIST(dirty_nats_ratio),
ATTR_LIST(cp_interval),
ATTR_LIST(idle_interval),
+ ATTR_LIST(lifetime_write_kbytes),
NULL,
};
f2fs_leave_shrinker(sbi);
mutex_unlock(&sbi->umount_mutex);
+ /* our cp_error case, we can wait for any writeback page */
+ if (get_pages(sbi, F2FS_WRITEBACK)) {
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ f2fs_submit_merged_bio(sbi, NODE, WRITE);
+ f2fs_submit_merged_bio(sbi, META, WRITE);
+ }
+
iput(sbi->node_inode);
iput(sbi->meta_inode);
bool need_stop_gc = false;
bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
- sync_filesystem(sb);
-
/*
* Save the old mount options in case we
* need to restore them.
org_mount_opt = sbi->mount_opt;
active_logs = sbi->active_logs;
+ if (*flags & MS_RDONLY) {
+ set_opt(sbi, FASTBOOT);
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+ }
+
+ sync_filesystem(sb);
+
sbi->mount_opt.opt = 0;
default_options(sbi);
bool retry = true, need_fsck = false;
char *options = NULL;
int recovery, i, valid_super_block;
+ struct curseg_info *seg_i;
try_onemore:
err = -EINVAL;
goto free_nm;
}
+ /* For write statistics */
+ if (sb->s_bdev->bd_part)
+ sbi->sectors_written_start =
+ (u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+
+ /* Read accumulated write IO statistics if exists */
+ seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+ if (__exist_node_summaries(sbi))
+ sbi->kbytes_written =
+ le64_to_cpu(seg_i->sum_blk->info.kbytes_written);
+
build_gc_manager(sbi);
/* get an inode for node space */
if (ipage) {
inline_addr = inline_xattr_addr(ipage);
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
} else {
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
return PTR_ERR(page);
}
inline_addr = inline_xattr_addr(page);
- f2fs_wait_on_page_writeback(page, NODE);
+ f2fs_wait_on_page_writeback(page, NODE, true);
}
memcpy(inline_addr, txattr_addr, inline_size);
f2fs_put_page(page, 1);
return PTR_ERR(xpage);
}
f2fs_bug_on(sbi, new_nid);
- f2fs_wait_on_page_writeback(xpage, NODE);
+ f2fs_wait_on_page_writeback(xpage, NODE, true);
} else {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, new_nid);
#define F2FS_BLKSIZE 4096 /* support only 4KB block */
#define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */
#define F2FS_MAX_EXTENSION 64 /* # of extension entries */
-#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE)
+#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS)
#define NULL_ADDR ((block_t)0) /* used as block_t addresses */
#define NEW_ADDR ((block_t)-1) /* used as block_t addresses */
#define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */
#define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */
#define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */
-#define ADDRS_PER_INODE(fi) addrs_per_inode(fi)
+#define ADDRS_PER_INODE(inode) addrs_per_inode(inode)
#define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */
#define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */
-#define ADDRS_PER_PAGE(page, fi) \
- (IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK)
+#define ADDRS_PER_PAGE(page, inode) \
+ (IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK)
#define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1)
#define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2)
struct summary_footer {
unsigned char entry_type; /* SUM_TYPE_XXX */
- __u32 check_sum; /* summary checksum */
+ __le32 check_sum; /* summary checksum */
} __packed;
#define SUM_JOURNAL_SIZE (F2FS_BLKSIZE - SUM_FOOTER_SIZE -\
sizeof(struct sit_journal_entry))
#define SIT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\
sizeof(struct sit_journal_entry))
+
+/* Reserved area should make size of f2fs_extra_info equals to
+ * that of nat_journal and sit_journal.
+ */
+#define EXTRA_INFO_RESERVED (SUM_JOURNAL_SIZE - 2 - 8)
+
/*
* frequently updated NAT/SIT entries can be stored in the spare area in
* summary blocks
__u8 reserved[SIT_JOURNAL_RESERVED];
} __packed;
+struct f2fs_extra_info {
+ __le64 kbytes_written;
+ __u8 reserved[EXTRA_INFO_RESERVED];
+} __packed;
+
/* 4KB-sized summary block structure */
struct f2fs_summary_block {
struct f2fs_summary entries[ENTRIES_IN_SUM];
__le16 n_nats;
__le16 n_sits;
};
- /* spare area is used by NAT or SIT journals */
+ /* spare area is used by NAT or SIT journals or extra info */
union {
struct nat_journal nat_j;
struct sit_journal sit_j;
+ struct f2fs_extra_info info;
};
struct summary_footer footer;
} __packed;