Merge tag 'f2fs-for-v3.10' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch-set includes the following major enhancement patches.
   - introduce a new gloabl lock scheme
   - add tracepoints on several major functions
   - fix the overall cleaning process focused on victim selection
   - apply the block plugging to merge IOs as much as possible
   - enhance management of free nids and its list
   - enhance the readahead mode for node pages
   - address several cretical deadlock conditions
   - reduce lock_page calls

  The other minor bug fixes and enhancements are as follows.
   - calculation mistakes: overflow
   - bio types: READ, READA, and READ_SYNC
   - fix the recovery flow, data races, and null pointer errors"

* tag 'f2fs-for-v3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits)
  f2fs: cover free_nid management with spin_lock
  f2fs: optimize scan_nat_page()
  f2fs: code cleanup for scan_nat_page() and build_free_nids()
  f2fs: bugfix for alloc_nid_failed()
  f2fs: recover when journal contains deleted files
  f2fs: continue to mount after failing recovery
  f2fs: avoid deadlock during evict after f2fs_gc
  f2fs: modify the number of issued pages to merge IOs
  f2fs: remove useless #include <linux/proc_fs.h> as we're now using sysfs as debug entry.
  f2fs: fix inconsistent using of NM_WOUT_THRESHOLD
  f2fs: check truncation of mapping after lock_page
  f2fs: enhance alloc_nid and build_free_nids flows
  f2fs: add a tracepoint on f2fs_new_inode
  f2fs: check nid == 0 in add_free_nid
  f2fs: add REQ_META about metadata requests for submit
  f2fs: give a chance to merge IOs by IO scheduler
  f2fs: avoid frequent background GC
  f2fs: add tracepoints to debug checkpoint request
  f2fs: add tracepoints for write page operations
  f2fs: add tracepoints to debug the block allocation
  ...

Documentation/filesystems/f2fs.txt

@@ -146,7 +146,7 @@ USAGE
 
 Format options
 --------------
--l [label]   : Give a volume label, up to 256 unicode name.
+-l [label]   : Give a volume label, up to 512 unicode name.
 -a [0 or 1]  : Split start location of each area for heap-based allocation.
                1 is set by default, which performs this.
 -o [int]     : Set overprovision ratio in percent over volume size.
@@ -156,6 +156,8 @@ Format options
 -z [int]     : Set the number of sections per zone.
                1 is set by default.
 -e [str]     : Set basic extension list. e.g. "mp3,gif,mov"
+-t [0 or 1]  : Disable discard command or not.
+               1 is set by default, which conducts discard.
 
 ================================================================================
 DESIGN

fs/f2fs/checkpoint.c

@@ -20,6 +20,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include <trace/events/f2fs.h>
 
 static struct kmem_cache *orphan_entry_slab;
 static struct kmem_cache *inode_entry_slab;
@@ -57,13 +58,19 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 		cond_resched();
 		goto repeat;
 	}
-	if (f2fs_readpage(sbi, page, index, READ_SYNC)) {
+	if (PageUptodate(page))
+		goto out;
+
+	if (f2fs_readpage(sbi, page, index, READ_SYNC))
+		goto repeat;
+
+	lock_page(page);
+	if (page->mapping != mapping) {
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
+out:
 	mark_page_accessed(page);
-
-	/* We do not allow returning an errorneous page */
 	return page;
 }
 
@@ -541,54 +548,44 @@ void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
  */
 static void block_operations(struct f2fs_sb_info *sbi)
 {
-	int t;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,
 		.nr_to_write = LONG_MAX,
 		.for_reclaim = 0,
 	};
+	struct blk_plug plug;
 
-	/* Stop renaming operation */
-	mutex_lock_op(sbi, RENAME);
-	mutex_lock_op(sbi, DENTRY_OPS);
+	blk_start_plug(&plug);
 
-retry_dents:
-	/* write all the dirty dentry pages */
-	sync_dirty_dir_inodes(sbi);
+retry_flush_dents:
+	mutex_lock_all(sbi);
 
-	mutex_lock_op(sbi, DATA_WRITE);
+	/* write all the dirty dentry pages */
 	if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
-		mutex_unlock_op(sbi, DATA_WRITE);
-		goto retry_dents;
+		mutex_unlock_all(sbi);
+		sync_dirty_dir_inodes(sbi);
+		goto retry_flush_dents;
 	}
 
-	/* block all the operations */
-	for (t = DATA_NEW; t <= NODE_TRUNC; t++)
-		mutex_lock_op(sbi, t);
-
-	mutex_lock(&sbi->write_inode);
-
 	/*
 	 * POR: we should ensure that there is no dirty node pages
 	 * until finishing nat/sit flush.
 	 */
-retry:
-	sync_node_pages(sbi, 0, &wbc);
-
-	mutex_lock_op(sbi, NODE_WRITE);
+retry_flush_nodes:
+	mutex_lock(&sbi->node_write);
 
 	if (get_pages(sbi, F2FS_DIRTY_NODES)) {
-		mutex_unlock_op(sbi, NODE_WRITE);
-		goto retry;
+		mutex_unlock(&sbi->node_write);
+		sync_node_pages(sbi, 0, &wbc);
+		goto retry_flush_nodes;
 	}
-	mutex_unlock(&sbi->write_inode);
+	blk_finish_plug(&plug);
 }
 
 static void unblock_operations(struct f2fs_sb_info *sbi)
 {
-	int t;
-	for (t = NODE_WRITE; t >= RENAME; t--)
-		mutex_unlock_op(sbi, t);
+	mutex_unlock(&sbi->node_write);
+	mutex_unlock_all(sbi);
 }
 
 static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
@@ -727,9 +724,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned long long ckpt_ver;
 
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");
+
 	mutex_lock(&sbi->cp_mutex);
 	block_operations(sbi);
 
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");
+
 	f2fs_submit_bio(sbi, DATA, true);
 	f2fs_submit_bio(sbi, NODE, true);
 	f2fs_submit_bio(sbi, META, true);
@@ -746,13 +747,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	flush_nat_entries(sbi);
 	flush_sit_entries(sbi);
 
-	reset_victim_segmap(sbi);
-
 	/* unlock all the fs_lock[] in do_checkpoint() */
 	do_checkpoint(sbi, is_umount);
 
 	unblock_operations(sbi);
 	mutex_unlock(&sbi->cp_mutex);
+
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
 }
 
 void init_orphan_info(struct f2fs_sb_info *sbi)