Merge tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "The major change in this version is mitigating cpu overheads on write
  paths by replacing redundant inode page updates with mark_inode_dirty
  calls.  And we tried to reduce lock contentions as well to improve
  filesystem scalability.  Other feature is setting F2FS automatically
  when detecting host-managed SMR.

  Enhancements:
   - ioctl to move a range of data between files
   - inject orphan inode errors
   - avoid flush commands congestion
   - support lazytime

  Bug fixes:
   - return proper results for some dentry operations
   - fix deadlock in add_link failure
   - disable extent_cache for fcollapse/finsert"

* tag 'for-f2fs-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits)
  f2fs: clean up coding style and redundancy
  f2fs: get victim segment again after new cp
  f2fs: handle error case with f2fs_bug_on
  f2fs: avoid data race when deciding checkpoin in f2fs_sync_file
  f2fs: support an ioctl to move a range of data blocks
  f2fs: fix to report error number of f2fs_find_entry
  f2fs: avoid memory allocation failure due to a long length
  f2fs: reset default idle interval value
  f2fs: use blk_plug in all the possible paths
  f2fs: fix to avoid data update racing between GC and DIO
  f2fs: add maximum prefree segments
  f2fs: disable extent_cache for fcollapse/finsert inodes
  f2fs: refactor __exchange_data_block for speed up
  f2fs: fix ERR_PTR returned by bio
  f2fs: avoid mark_inode_dirty
  f2fs: move i_size_write in f2fs_write_end
  f2fs: fix to avoid redundant discard during fstrim
  f2fs: avoid mismatching block range for discard
  f2fs: fix incorrect f_bfree calculation in ->statfs
  f2fs: use percpu_rw_semaphore
  ...

1 files changed, 52 insertions, 7 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4c2d1fa1e0e2..a46296f57b02 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -241,7 +241,7 @@ void drop_inmem_pages(struct inode *inode)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
-	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+	clear_inode_flag(inode, FI_ATOMIC_FILE);
 
 	mutex_lock(&fi->inmem_lock);
 	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
@@ -346,6 +346,11 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 {
 	if (!need)
 		return;
+
+	/* balance_fs_bg is able to be pending */
+	if (excess_cached_nats(sbi))
+		f2fs_balance_fs_bg(sbi);
+
 	/*
 	 * We should do GC or end up with checkpoint, if there are so many dirty
 	 * dir/node pages without enough free segments.
@@ -367,7 +372,9 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 		try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
 
 	if (!available_free_memory(sbi, FREE_NIDS))
-		try_to_free_nids(sbi, NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES);
+		try_to_free_nids(sbi, MAX_FREE_NIDS);
+	else
+		build_free_nids(sbi);
 
 	/* checkpoint is the only way to shrink partial cached entries */
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
@@ -435,25 +442,29 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 	if (test_opt(sbi, NOBARRIER))
 		return 0;
 
-	if (!test_opt(sbi, FLUSH_MERGE)) {
+	if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
 		struct bio *bio = f2fs_bio_alloc(0);
 		int ret;
 
+		atomic_inc(&fcc->submit_flush);
 		bio->bi_bdev = sbi->sb->s_bdev;
 		bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
 		ret = submit_bio_wait(bio);
+		atomic_dec(&fcc->submit_flush);
 		bio_put(bio);
 		return ret;
 	}
 
 	init_completion(&cmd.wait);
 
+	atomic_inc(&fcc->submit_flush);
 	llist_add(&cmd.llnode, &fcc->issue_list);
 
 	if (!fcc->dispatch_list)
 		wake_up(&fcc->flush_wait_queue);
 
 	wait_for_completion(&cmd.wait);
+	atomic_dec(&fcc->submit_flush);
 
 	return cmd.ret;
 }
@@ -467,6 +478,7 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
 	if (!fcc)
 		return -ENOMEM;
+	atomic_set(&fcc->submit_flush, 0);
 	init_waitqueue_head(&fcc->flush_wait_queue);
 	init_llist_head(&fcc->issue_list);
 	SM_I(sbi)->cmd_control_info = fcc;
@@ -668,6 +680,10 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			break;
 
 		end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
+		if (force && start && end != max_blocks
+					&& (end - start) < cpc->trim_minlen)
+			continue;
+
 		__add_discard_entry(sbi, cpc, se, start, end);
 	}
 }
@@ -705,6 +721,8 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
 	unsigned int start = 0, end = -1;
+	unsigned int secno, start_segno;
+	bool force = (cpc->reason == CP_DISCARD);
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -721,17 +739,31 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 		dirty_i->nr_dirty[PRE] -= end - start;
 
-		if (!test_opt(sbi, DISCARD))
+		if (force || !test_opt(sbi, DISCARD))
 			continue;
 
-		f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
+		if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
+			f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
 				(end - start) << sbi->log_blocks_per_seg);
+			continue;
+		}
+next:
+		secno = GET_SECNO(sbi, start);
+		start_segno = secno * sbi->segs_per_sec;
+		if (!IS_CURSEC(sbi, secno) &&
+			!get_valid_blocks(sbi, start, sbi->segs_per_sec))
+			f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
+				sbi->segs_per_sec << sbi->log_blocks_per_seg);
+
+		start = start_segno + sbi->segs_per_sec;
+		if (start < end)
+			goto next;
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
 	/* send small discards */
 	list_for_each_entry_safe(entry, this, head, list) {
-		if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen)
+		if (force && entry->len < cpc->trim_minlen)
 			goto skip;
 		f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
 		cpc->trimmed += entry->len;
@@ -1219,6 +1251,9 @@ void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
 	int i;
 
+	if (test_opt(sbi, LFS))
+		return;
+
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
 		__allocate_new_segments(sbi, i);
 }
@@ -1392,11 +1427,17 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(fio->page, fio->type);
 
+	if (fio->type == NODE || fio->type == DATA)
+		mutex_lock(&fio->sbi->wio_mutex[fio->type]);
+
 	allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
 					&fio->new_blkaddr, sum, type);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_mbio(fio);
+
+	if (fio->type == NODE || fio->type == DATA)
+		mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -2377,7 +2418,11 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
 	sm_info->rec_prefree_segments = sm_info->main_segments *
 					DEF_RECLAIM_PREFREE_SEGMENTS / 100;
-	sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
+	if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS)
+		sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS;
+
+	if (!test_opt(sbi, LFS))
+		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;