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

1 files changed, 54 insertions, 62 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index db626282d424..1cae864f8dfc 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -13,6 +13,7 @@
 #include <linux/stat.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/blkdev.h>
 #include <linux/falloc.h>
 #include <linux/types.h>
 #include <linux/compat.h>
@@ -24,6 +25,7 @@
 #include "segment.h"
 #include "xattr.h"
 #include "acl.h"
+#include <trace/events/f2fs.h>
 
 static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 						struct vm_fault *vmf)
@@ -33,19 +35,18 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	block_t old_blk_addr;
 	struct dnode_of_data dn;
-	int err;
+	int err, ilock;
 
 	f2fs_balance_fs(sbi);
 
 	sb_start_pagefault(inode->i_sb);
 
-	mutex_lock_op(sbi, DATA_NEW);
-
 	/* block allocation */
+	ilock = mutex_lock_op(sbi);
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, page->index, 0);
+	err = get_dnode_of_data(&dn, page->index, ALLOC_NODE);
 	if (err) {
-		mutex_unlock_op(sbi, DATA_NEW);
+		mutex_unlock_op(sbi, ilock);
 		goto out;
 	}
 
@@ -55,13 +56,12 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 		err = reserve_new_block(&dn);
 		if (err) {
 			f2fs_put_dnode(&dn);
-			mutex_unlock_op(sbi, DATA_NEW);
+			mutex_unlock_op(sbi, ilock);
 			goto out;
 		}
 	}
 	f2fs_put_dnode(&dn);
-
-	mutex_unlock_op(sbi, DATA_NEW);
+	mutex_unlock_op(sbi, ilock);
 
 	lock_page(page);
 	if (page->mapping != inode->i_mapping ||
@@ -102,28 +102,10 @@ static const struct vm_operations_struct f2fs_file_vm_ops = {
 	.remap_pages	= generic_file_remap_pages,
 };
 
-static int need_to_sync_dir(struct f2fs_sb_info *sbi, struct inode *inode)
-{
-	struct dentry *dentry;
-	nid_t pino;
-
-	inode = igrab(inode);
-	dentry = d_find_any_alias(inode);
-	if (!dentry) {
-		iput(inode);
-		return 0;
-	}
-	pino = dentry->d_parent->d_inode->i_ino;
-	dput(dentry);
-	iput(inode);
-	return !is_checkpointed_node(sbi, pino);
-}
-
 int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	unsigned long long cur_version;
 	int ret = 0;
 	bool need_cp = false;
 	struct writeback_control wbc = {
@@ -135,9 +117,12 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (inode->i_sb->s_flags & MS_RDONLY)
 		return 0;
 
+	trace_f2fs_sync_file_enter(inode);
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (ret)
+	if (ret) {
+		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
 		return ret;
+	}
 
 	/* guarantee free sections for fsync */
 	f2fs_balance_fs(sbi);
@@ -147,28 +132,18 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
 		goto out;
 
-	mutex_lock(&sbi->cp_mutex);
-	cur_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver);
-	mutex_unlock(&sbi->cp_mutex);
-
-	if (F2FS_I(inode)->data_version != cur_version &&
-					!(inode->i_state & I_DIRTY))
-		goto out;
-	F2FS_I(inode)->data_version--;
-
 	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
 		need_cp = true;
-	else if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
+	else if (is_cp_file(inode))
 		need_cp = true;
 	else if (!space_for_roll_forward(sbi))
 		need_cp = true;
-	else if (need_to_sync_dir(sbi, inode))
+	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
 		need_cp = true;
 
 	if (need_cp) {
 		/* all the dirty node pages should be flushed for POR */
 		ret = f2fs_sync_fs(inode->i_sb, 1);
-		clear_inode_flag(F2FS_I(inode), FI_NEED_CP);
 	} else {
 		/* if there is no written node page, write its inode page */
 		while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
@@ -178,9 +153,11 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		}
 		filemap_fdatawait_range(sbi->node_inode->i_mapping,
 							0, LONG_MAX);
+		ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
 	}
 out:
 	mutex_unlock(&inode->i_mutex);
+	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
 	return ret;
 }
 
@@ -216,6 +193,9 @@ static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		sync_inode_page(dn);
 	}
 	dn->ofs_in_node = ofs;
+
+	trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
+					 dn->ofs_in_node, nr_free);
 	return nr_free;
 }
 
@@ -232,11 +212,15 @@ static void truncate_partial_data_page(struct inode *inode, u64 from)
 	if (!offset)
 		return;
 
-	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT);
+	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false);
 	if (IS_ERR(page))
 		return;
 
 	lock_page(page);
+	if (page->mapping != inode->i_mapping) {
+		f2fs_put_page(page, 1);
+		return;
+	}
 	wait_on_page_writeback(page);
 	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
 	set_page_dirty(page);
@@ -249,20 +233,22 @@ static int truncate_blocks(struct inode *inode, u64 from)
 	unsigned int blocksize = inode->i_sb->s_blocksize;
 	struct dnode_of_data dn;
 	pgoff_t free_from;
-	int count = 0;
+	int count = 0, ilock = -1;
 	int err;
 
+	trace_f2fs_truncate_blocks_enter(inode, from);
+
 	free_from = (pgoff_t)
 			((from + blocksize - 1) >> (sbi->log_blocksize));
 
-	mutex_lock_op(sbi, DATA_TRUNC);
-
+	ilock = mutex_lock_op(sbi);
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, free_from, RDONLY_NODE);
+	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
 	if (err) {
 		if (err == -ENOENT)
 			goto free_next;
-		mutex_unlock_op(sbi, DATA_TRUNC);
+		mutex_unlock_op(sbi, ilock);
+		trace_f2fs_truncate_blocks_exit(inode, err);
 		return err;
 	}
 
@@ -273,6 +259,7 @@ static int truncate_blocks(struct inode *inode, u64 from)
 
 	count -= dn.ofs_in_node;
 	BUG_ON(count < 0);
+
 	if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
 		truncate_data_blocks_range(&dn, count);
 		free_from += count;
@@ -281,11 +268,12 @@ static int truncate_blocks(struct inode *inode, u64 from)
 	f2fs_put_dnode(&dn);
 free_next:
 	err = truncate_inode_blocks(inode, free_from);
-	mutex_unlock_op(sbi, DATA_TRUNC);
+	mutex_unlock_op(sbi, ilock);
 
 	/* lastly zero out the first data page */
 	truncate_partial_data_page(inode, from);
 
+	trace_f2fs_truncate_blocks_exit(inode, err);
 	return err;
 }
 
@@ -295,6 +283,8 @@ void f2fs_truncate(struct inode *inode)
 				S_ISLNK(inode->i_mode)))
 		return;
 
+	trace_f2fs_truncate(inode);
+
 	if (!truncate_blocks(inode, i_size_read(inode))) {
 		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		mark_inode_dirty(inode);
@@ -389,15 +379,16 @@ static void fill_zero(struct inode *inode, pgoff_t index,
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	struct page *page;
+	int ilock;
 
 	if (!len)
 		return;
 
 	f2fs_balance_fs(sbi);
 
-	mutex_lock_op(sbi, DATA_NEW);
+	ilock = mutex_lock_op(sbi);
 	page = get_new_data_page(inode, index, false);
-	mutex_unlock_op(sbi, DATA_NEW);
+	mutex_unlock_op(sbi, ilock);
 
 	if (!IS_ERR(page)) {
 		wait_on_page_writeback(page);
@@ -414,15 +405,10 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 
 	for (index = pg_start; index < pg_end; index++) {
 		struct dnode_of_data dn;
-		struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-
-		f2fs_balance_fs(sbi);
 
-		mutex_lock_op(sbi, DATA_TRUNC);
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		err = get_dnode_of_data(&dn, index, RDONLY_NODE);
+		err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
 		if (err) {
-			mutex_unlock_op(sbi, DATA_TRUNC);
 			if (err == -ENOENT)
 				continue;
 			return err;
@@ -431,7 +417,6 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 		if (dn.data_blkaddr != NULL_ADDR)
 			truncate_data_blocks_range(&dn, 1);
 		f2fs_put_dnode(&dn);
-		mutex_unlock_op(sbi, DATA_TRUNC);
 	}
 	return 0;
 }
@@ -461,12 +446,19 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len, int mode)
 		if (pg_start < pg_end) {
 			struct address_space *mapping = inode->i_mapping;
 			loff_t blk_start, blk_end;
+			struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+			int ilock;
+
+			f2fs_balance_fs(sbi);
 
 			blk_start = pg_start << PAGE_CACHE_SHIFT;
 			blk_end = pg_end << PAGE_CACHE_SHIFT;
 			truncate_inode_pages_range(mapping, blk_start,
 					blk_end - 1);
+
+			ilock = mutex_lock_op(sbi);
 			ret = truncate_hole(inode, pg_start, pg_end);
+			mutex_unlock_op(sbi, ilock);
 		}
 	}
 
@@ -500,13 +492,13 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 
 	for (index = pg_start; index <= pg_end; index++) {
 		struct dnode_of_data dn;
+		int ilock;
 
-		mutex_lock_op(sbi, DATA_NEW);
-
+		ilock = mutex_lock_op(sbi);
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		ret = get_dnode_of_data(&dn, index, 0);
+		ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
 		if (ret) {
-			mutex_unlock_op(sbi, DATA_NEW);
+			mutex_unlock_op(sbi, ilock);
 			break;
 		}
 
@@ -514,13 +506,12 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 			ret = reserve_new_block(&dn);
 			if (ret) {
 				f2fs_put_dnode(&dn);
-				mutex_unlock_op(sbi, DATA_NEW);
+				mutex_unlock_op(sbi, ilock);
 				break;
 			}
 		}
 		f2fs_put_dnode(&dn);
-
-		mutex_unlock_op(sbi, DATA_NEW);
+		mutex_unlock_op(sbi, ilock);
 
 		if (pg_start == pg_end)
 			new_size = offset + len;
@@ -559,6 +550,7 @@ static long f2fs_fallocate(struct file *file, int mode,
 		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		mark_inode_dirty(inode);
 	}
+	trace_f2fs_fallocate(inode, mode, offset, len, ret);
 	return ret;
 }