Merge tag 'for-f2fs-3.20' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "Major changes are to:
   - add f2fs_io_tracer and F2FS_IOC_GETVERSION
   - fix wrong acl assignment from parent
   - fix accessing wrong data blocks
   - fix wrong condition check for f2fs_sync_fs
   - align start block address for direct_io
   - add and refactor the readahead flows of FS metadata
   - refactor atomic and volatile write policies

  But most of patches are for clean-ups and minor bug fixes.  Some of
  them refactor old code too"

* tag 'for-f2fs-3.20' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (64 commits)
  f2fs: use spinlock for segmap_lock instead of rwlock
  f2fs: fix accessing wrong indexed data blocks
  f2fs: avoid variable length array
  f2fs: fix sparse warnings
  f2fs: allocate data blocks in advance for f2fs_direct_IO
  f2fs: introduce macros to convert bytes and blocks in f2fs
  f2fs: call set_buffer_new for get_block
  f2fs: check node page contents all the time
  f2fs: avoid data offset overflow when lseeking huge file
  f2fs: fix to use highmem for pages of newly created directory
  f2fs: introduce a batched trim
  f2fs: merge {invalidate,release}page for meta/node/data pages
  f2fs: show the number of writeback pages in stat
  f2fs: keep PagePrivate during releasepage
  f2fs: should fail mount when trying to recover data on read-only dev
  f2fs: split UMOUNT and FASTBOOT flags
  f2fs: avoid write_checkpoint if f2fs is mounted readonly
  f2fs: support norecovery mount option
  f2fs: fix not to drop mount options when retrying fill_super
  f2fs: merge flags in struct f2fs_sb_info
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -74,3 +74,9 @@ Date:		March 2014
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
 Description:
 		 Controls the memory footprint used by f2fs.
+
+What:		/sys/fs/f2fs/<disk>/trim_sections
+Date:		February 2015
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the trimming rate in batch mode.

Documentation/filesystems/f2fs.txt

@@ -106,6 +106,8 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
                        Default value for this option is on. So garbage
                        collection is on by default.
 disable_roll_forward   Disable the roll-forward recovery routine
+norecovery             Disable the roll-forward recovery routine, mounted read-
+                       only (i.e., -o ro,disable_roll_forward)
 discard                Issue discard/TRIM commands when a segment is cleaned.
 no_heap                Disable heap-style segment allocation which finds free
                        segments for data from the beginning of main area, while
@@ -197,6 +199,10 @@ Files in /sys/fs/f2fs/<devname>
 			      checkpoint is triggered, and issued during the
 			      checkpoint. By default, it is disabled with 0.
 
+ trim_sections                This parameter controls the number of sections
+                              to be trimmed out in batch mode when FITRIM
+                              conducts. 32 sections is set by default.
+
  ipu_policy                   This parameter controls the policy of in-place
                               updates in f2fs. There are five policies:
                                0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,

fs/f2fs/Kconfig

@@ -71,3 +71,13 @@ config F2FS_CHECK_FS
 	  Enables BUG_ONs which check the filesystem consistency in runtime.
 
 	  If you want to improve the performance, say N.
+
+config F2FS_IO_TRACE
+	bool "F2FS IO tracer"
+	depends on F2FS_FS
+	depends on FUNCTION_TRACER
+	help
+	  F2FS IO trace is based on a function trace, which gathers process
+	  information and block IO patterns in the filesystem level.
+
+	  If unsure, say N.

fs/f2fs/Makefile

@@ -5,3 +5,4 @@ f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
 f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
 f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
+f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o

fs/f2fs/acl.c

@@ -62,7 +62,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
 	if (count == 0)
 		return NULL;
 
-	acl = posix_acl_alloc(count, GFP_KERNEL);
+	acl = posix_acl_alloc(count, GFP_NOFS);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -116,7 +116,7 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
 	int i;
 
 	f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
-			sizeof(struct f2fs_acl_entry), GFP_KERNEL);
+			sizeof(struct f2fs_acl_entry), GFP_NOFS);
 	if (!f2fs_acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -396,7 +396,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
 		posix_acl_release(default_acl);
 	}
 	if (acl) {
-		if (error)
+		if (!error)
 			error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl,
 					       ipage);
 		posix_acl_release(acl);

fs/f2fs/debug.c

@@ -40,6 +40,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_dirs = sbi->n_dirty_dirs;
 	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
+	si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
@@ -57,7 +58,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->node_pages = NODE_MAPPING(sbi)->nrpages;
 	si->meta_pages = META_MAPPING(sbi)->nrpages;
 	si->nats = NM_I(sbi)->nat_cnt;
-	si->sits = SIT_I(sbi)->dirty_sentries;
+	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
+	si->sits = MAIN_SEGS(sbi);
+	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
 	si->fnids = NM_I(sbi)->fcnt;
 	si->bg_gc = sbi->bg_gc;
 	si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
@@ -79,6 +82,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->segment_count[i] = sbi->segment_count[i];
 		si->block_count[i] = sbi->block_count[i];
 	}
+
+	si->inplace_count = atomic_read(&sbi->inplace_count);
 }
 
 /*
@@ -137,6 +142,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
 	si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
 	si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	si->base_mem += SIT_VBLOCK_MAP_SIZE;
 	if (sbi->segs_per_sec > 1)
 		si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
 	si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
@@ -159,20 +165,32 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += sizeof(struct f2fs_nm_info);
 	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
 
+get_cache:
+	si->cache_mem = 0;
+
 	/* build gc */
-	si->base_mem += sizeof(struct f2fs_gc_kthread);
+	if (sbi->gc_thread)
+		si->cache_mem += sizeof(struct f2fs_gc_kthread);
+
+	/* build merge flush thread */
+	if (SM_I(sbi)->cmd_control_info)
+		si->cache_mem += sizeof(struct flush_cmd_control);
 
-get_cache:
 	/* free nids */
-	si->cache_mem = NM_I(sbi)->fcnt;
-	si->cache_mem += NM_I(sbi)->nat_cnt;
-	npages = NODE_MAPPING(sbi)->nrpages;
-	si->cache_mem += npages << PAGE_CACHE_SHIFT;
-	npages = META_MAPPING(sbi)->nrpages;
-	si->cache_mem += npages << PAGE_CACHE_SHIFT;
-	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry);
+	si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid);
+	si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
+	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
+					sizeof(struct nat_entry_set);
+	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
+	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry);
 	for (i = 0; i <= UPDATE_INO; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
+
+	si->page_mem = 0;
+	npages = NODE_MAPPING(sbi)->nrpages;
+	si->page_mem += npages << PAGE_CACHE_SHIFT;
+	npages = META_MAPPING(sbi)->nrpages;
+	si->page_mem += npages << PAGE_CACHE_SHIFT;
 }
 
 static int stat_show(struct seq_file *s, void *v)
@@ -250,16 +268,16 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "\nExtent Hit Ratio: %d / %d\n",
 			   si->hit_ext, si->total_ext);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - inmem: %4d\n",
-			   si->inmem_pages);
+		seq_printf(s, "  - inmem: %4d, wb: %4d\n",
+			   si->inmem_pages, si->wb_pages);
 		seq_printf(s, "  - nodes: %4d in %4d\n",
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d\n",
 			   si->ndirty_dent, si->ndirty_dirs);
 		seq_printf(s, "  - meta: %4d in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
-		seq_printf(s, "  - NATs: %9d\n  - SITs: %9d\n",
-			   si->nats, si->sits);
+		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
+			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);
 		seq_printf(s, "  - free_nids: %9d\n",
 			   si->fnids);
 		seq_puts(s, "\nDistribution of User Blocks:");
@@ -277,6 +295,7 @@ static int stat_show(struct seq_file *s, void *v)
 		for (j = 0; j < si->util_free; j++)
 			seq_putc(s, '-');
 		seq_puts(s, "]\n\n");
+		seq_printf(s, "IPU: %u blocks\n", si->inplace_count);
 		seq_printf(s, "SSR: %u blocks in %u segments\n",
 			   si->block_count[SSR], si->segment_count[SSR]);
 		seq_printf(s, "LFS: %u blocks in %u segments\n",
@@ -289,9 +308,14 @@ static int stat_show(struct seq_file *s, void *v)
 
 		/* memory footprint */
 		update_mem_info(si->sbi);
-		seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
-				(si->base_mem + si->cache_mem) >> 10,
-				si->base_mem >> 10, si->cache_mem >> 10);
+		seq_printf(s, "\nMemory: %u KB\n",
+			(si->base_mem + si->cache_mem + si->page_mem) >> 10);
+		seq_printf(s, "  - static: %u KB\n",
+				si->base_mem >> 10);
+		seq_printf(s, "  - cached: %u KB\n",
+				si->cache_mem >> 10);
+		seq_printf(s, "  - paged : %u KB\n",
+				si->page_mem >> 10);
 	}
 	mutex_unlock(&f2fs_stat_mutex);
 	return 0;
@@ -331,6 +355,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 
 	atomic_set(&sbi->inline_inode, 0);
 	atomic_set(&sbi->inline_dir, 0);
+	atomic_set(&sbi->inplace_count, 0);
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_add_tail(&si->stat_list, &f2fs_stat_list);

fs/f2fs/dir.c

@@ -286,8 +286,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	f2fs_wait_on_page_writeback(page, type);
 	de->ino = cpu_to_le32(inode->i_ino);
 	set_de_type(de, inode);
-	if (!f2fs_has_inline_dentry(dir))
-		kunmap(page);
+	f2fs_dentry_kunmap(dir, page);
 	set_page_dirty(page);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 	mark_inode_dirty(dir);

fs/f2fs/file.c

@@ -26,6 +26,7 @@
 #include "segment.h"
 #include "xattr.h"
 #include "acl.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
@@ -245,6 +246,10 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 sync_nodes:
 	sync_node_pages(sbi, ino, &wbc);
 
+	/* if cp_error was enabled, we should avoid infinite loop */
+	if (unlikely(f2fs_cp_error(sbi)))
+		goto out;
+
 	if (need_inode_block_update(sbi, ino)) {
 		mark_inode_dirty_sync(inode);
 		f2fs_write_inode(inode, NULL);
@@ -264,6 +269,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	ret = f2fs_issue_flush(sbi);
 out:
 	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+	f2fs_trace_ios(NULL, NULL, 1);
 	return ret;
 }
 
@@ -350,7 +356,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 		/* find data/hole in dnode block */
 		for (; dn.ofs_in_node < end_offset;
 				dn.ofs_in_node++, pgofs++,
-				data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+				data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
 			block_t blkaddr;
 			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
 
@@ -426,7 +432,8 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		if (blkaddr == NULL_ADDR)
 			continue;
 
-		update_extent_cache(NULL_ADDR, dn);
+		dn->data_blkaddr = NULL_ADDR;
+		update_extent_cache(dn);
 		invalidate_blocks(sbi, blkaddr);
 		nr_free++;
 	}
@@ -483,8 +490,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 
 	trace_f2fs_truncate_blocks_enter(inode, from);
 
-	free_from = (pgoff_t)
-		((from + blocksize - 1) >> (sbi->log_blocksize));
+	free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
 
 	if (lock)
 		f2fs_lock_op(sbi);
@@ -835,6 +841,19 @@ static long f2fs_fallocate(struct file *file, int mode,
 	return ret;
 }
 
+static int f2fs_release_file(struct inode *inode, struct file *filp)
+{
+	/* some remained atomic pages should discarded */
+	if (f2fs_is_atomic_file(inode))
+		commit_inmem_pages(inode, true);
+	if (f2fs_is_volatile_file(inode)) {
+		set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+		filemap_fdatawrite(inode->i_mapping);
+		clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
+	}
+	return 0;
+}
+
 #define F2FS_REG_FLMASK		(~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
 #define F2FS_OTHER_FLMASK	(FS_NODUMP_FL | FS_NOATIME_FL)
 
@@ -905,29 +924,30 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 	return ret;
 }
 
+static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+
+	return put_user(inode->i_generation, (int __user *)arg);
+}
+
 static int f2fs_ioc_start_atomic_write(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(F2FS_I_SB(inode));
+
+	if (f2fs_is_atomic_file(inode))
+		return 0;
 
 	set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 
 	return f2fs_convert_inline_inode(inode);
 }
 
-static int f2fs_release_file(struct inode *inode, struct file *filp)
-{
-	/* some remained atomic pages should discarded */
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
-		commit_inmem_pages(inode, true);
-	return 0;
-}
-
 static int f2fs_ioc_commit_atomic_write(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
@@ -948,6 +968,7 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 
 	ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
 	mnt_drop_write_file(filp);
+	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 	return ret;
 }
 
@@ -958,11 +979,56 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	if (f2fs_is_volatile_file(inode))
+		return 0;
+
 	set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
 
 	return f2fs_convert_inline_inode(inode);
 }
 
+static int f2fs_ioc_release_volatile_write(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (!f2fs_is_volatile_file(inode))
+		return 0;
+
+	punch_hole(inode, 0, F2FS_BLKSIZE);
+	return 0;
+}
+
+static int f2fs_ioc_abort_volatile_write(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+	int ret;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	f2fs_balance_fs(F2FS_I_SB(inode));
+
+	if (f2fs_is_atomic_file(inode)) {
+		commit_inmem_pages(inode, false);
+		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+	}
+
+	if (f2fs_is_volatile_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+		filemap_fdatawrite(inode->i_mapping);
+		set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+	}
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
 static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -1000,12 +1066,18 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_getflags(filp, arg);
 	case F2FS_IOC_SETFLAGS:
 		return f2fs_ioc_setflags(filp, arg);
+	case F2FS_IOC_GETVERSION:
+		return f2fs_ioc_getversion(filp, arg);
 	case F2FS_IOC_START_ATOMIC_WRITE:
 		return f2fs_ioc_start_atomic_write(filp);
 	case F2FS_IOC_COMMIT_ATOMIC_WRITE:
 		return f2fs_ioc_commit_atomic_write(filp);
 	case F2FS_IOC_START_VOLATILE_WRITE:
 		return f2fs_ioc_start_volatile_write(filp);
+	case F2FS_IOC_RELEASE_VOLATILE_WRITE:
+		return f2fs_ioc_release_volatile_write(filp);
+	case F2FS_IOC_ABORT_VOLATILE_WRITE:
+		return f2fs_ioc_abort_volatile_write(filp);
 	case FITRIM:
 		return f2fs_ioc_fitrim(filp, arg);
 	default:

fs/f2fs/gc.c

@@ -24,8 +24,6 @@
 #include "gc.h"
 #include <trace/events/f2fs.h>
 
-static struct kmem_cache *winode_slab;
-
 static int gc_thread_func(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
@@ -46,7 +44,7 @@ static int gc_thread_func(void *data)
 			break;
 
 		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 			continue;
 		}
 
@@ -67,15 +65,15 @@ static int gc_thread_func(void *data)
 			continue;
 
 		if (!is_idle(sbi)) {
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 			mutex_unlock(&sbi->gc_mutex);
 			continue;
 		}
 
 		if (has_enough_invalid_blocks(sbi))
-			wait_ms = decrease_sleep_time(gc_th, wait_ms);
+			decrease_sleep_time(gc_th, &wait_ms);
 		else
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 
 		stat_inc_bggc_count(sbi);
 
@@ -356,13 +354,10 @@ static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
 		iput(inode);
 		return;
 	}
-	new_ie = f2fs_kmem_cache_alloc(winode_slab, GFP_NOFS);
+	new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
 	new_ie->inode = inode;
-retry:
-	if (radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie)) {
-		cond_resched();
-		goto retry;
-	}
+
+	f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie);
 	list_add_tail(&new_ie->list, &gc_list->ilist);
 }
 
@@ -373,7 +368,7 @@ static void put_gc_inode(struct gc_inode_list *gc_list)
 		radix_tree_delete(&gc_list->iroot, ie->inode->i_ino);
 		iput(ie->inode);
 		list_del(&ie->list);
-		kmem_cache_free(winode_slab, ie);
+		kmem_cache_free(inode_entry_slab, ie);
 	}
 }
 
@@ -703,8 +698,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi)
 		.iroot = RADIX_TREE_INIT(GFP_NOFS),
 	};
 
-	cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC;
-
+	cpc.reason = __get_cp_reason(sbi);
 gc_more:
 	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
 		goto stop;
@@ -750,17 +744,3 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
 {
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
 }
-
-int __init create_gc_caches(void)
-{
-	winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
-			sizeof(struct inode_entry));
-	if (!winode_slab)
-		return -ENOMEM;
-	return 0;
-}
-
-void destroy_gc_caches(void)
-{
-	kmem_cache_destroy(winode_slab);
-}

fs/f2fs/gc.h

@@ -35,11 +35,6 @@ struct f2fs_gc_kthread {
 	unsigned int gc_idle;
 };
 
-struct inode_entry {
-	struct list_head list;
-	struct inode *inode;
-};
-
 struct gc_inode_list {
 	struct list_head ilist;
 	struct radix_tree_root iroot;
@@ -69,26 +64,26 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
 	return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
 }
 
-static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
+static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th,
+								long *wait)
 {
-	if (wait == gc_th->no_gc_sleep_time)
-		return wait;
+	if (*wait == gc_th->no_gc_sleep_time)
+		return;
 
-	wait += gc_th->min_sleep_time;
-	if (wait > gc_th->max_sleep_time)
-		wait = gc_th->max_sleep_time;
-	return wait;
+	*wait += gc_th->min_sleep_time;
+	if (*wait > gc_th->max_sleep_time)
+		*wait = gc_th->max_sleep_time;
 }
 
-static inline long decrease_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
+static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
+								long *wait)
 {
-	if (wait == gc_th->no_gc_sleep_time)
-		wait = gc_th->max_sleep_time;
+	if (*wait == gc_th->no_gc_sleep_time)
+		*wait = gc_th->max_sleep_time;
 
-	wait -= gc_th->min_sleep_time;
-	if (wait <= gc_th->min_sleep_time)
-		wait = gc_th->min_sleep_time;
-	return wait;
+	*wait -= gc_th->min_sleep_time;
+	if (*wait <= gc_th->min_sleep_time)
+		*wait = gc_th->min_sleep_time;
 }
 
 static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)

fs/f2fs/inline.c

@@ -50,6 +50,12 @@ void read_inline_data(struct page *page, struct page *ipage)
 	SetPageUptodate(page);
 }
 
+static void truncate_inline_data(struct page *ipage)
+{
+	f2fs_wait_on_page_writeback(ipage, NODE);
+	memset(inline_data_addr(ipage), 0, MAX_INLINE_DATA);
+}
+
 int f2fs_read_inline_data(struct inode *inode, struct page *page)
 {
 	struct page *ipage;
@@ -79,7 +85,6 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
 	void *src_addr, *dst_addr;
-	block_t new_blk_addr;
 	struct f2fs_io_info fio = {
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
@@ -115,9 +120,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
-
-	write_data_page(page, dn, &new_blk_addr, &fio);
-	update_extent_cache(new_blk_addr, dn);
+	fio.blk_addr = dn->data_blkaddr;
+	write_data_page(page, dn, &fio);
+	update_extent_cache(dn);
 	f2fs_wait_on_page_writeback(page, DATA);
 	if (dirty)
 		inode_dec_dirty_pages(dn->inode);
@@ -126,7 +131,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
 
 	/* clear inline data and flag after data writeback */
-	truncate_inline_data(dn->inode_page, 0);
+	truncate_inline_data(dn->inode_page);
 clear_out:
 	stat_dec_inline_inode(dn->inode);
 	f2fs_clear_inline_inode(dn->inode);
@@ -199,19 +204,6 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 	return 0;
 }
 
-void truncate_inline_data(struct page *ipage, u64 from)
-{
-	void *addr;
-
-	if (from >= MAX_INLINE_DATA)
-		return;
-
-	f2fs_wait_on_page_writeback(ipage, NODE);
-
-	addr = inline_data_addr(ipage);
-	memset(addr + from, 0, MAX_INLINE_DATA - from);
-}
-
 bool recover_inline_data(struct inode *inode, struct page *npage)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -253,7 +245,7 @@ bool recover_inline_data(struct inode *inode, struct page *npage)
 	if (f2fs_has_inline_data(inode)) {
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
-		truncate_inline_data(ipage, 0);
+		truncate_inline_data(ipage);
 		f2fs_clear_inline_inode(inode);
 		update_inode(inode, ipage);
 		f2fs_put_page(ipage, 1);
@@ -371,7 +363,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	set_page_dirty(page);
 
 	/* clear inline dir and flag after data writeback */
-	truncate_inline_data(ipage, 0);
+	truncate_inline_data(ipage);
 
 	stat_dec_inline_dir(dir);
 	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);

fs/f2fs/inode.c

@@ -67,29 +67,23 @@ static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }
 
-static int __recover_inline_status(struct inode *inode, struct page *ipage)
+static void __recover_inline_status(struct inode *inode, struct page *ipage)
 {
 	void *inline_data = inline_data_addr(ipage);
-	struct f2fs_inode *ri;
-	void *zbuf;
-
-	zbuf = kzalloc(MAX_INLINE_DATA, GFP_NOFS);
-	if (!zbuf)
-		return -ENOMEM;
-
-	if (!memcmp(zbuf, inline_data, MAX_INLINE_DATA)) {
-		kfree(zbuf);
-		return 0;
-	}
-	kfree(zbuf);
+	__le32 *start = inline_data;
+	__le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
 
+	while (start < end) {
+		if (*start++) {
 			f2fs_wait_on_page_writeback(ipage, NODE);
-	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
 
-	ri = F2FS_INODE(ipage);
-	set_raw_inline(F2FS_I(inode), ri);
+			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+			set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
 			set_page_dirty(ipage);
-	return 0;
+			return;
+		}
+	}
+	return;
 }
 
 static int do_read_inode(struct inode *inode)
@@ -98,7 +92,6 @@ static int do_read_inode(struct inode *inode)
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct page *node_page;
 	struct f2fs_inode *ri;
-	int err = 0;
 
 	/* Check if ino is within scope */
 	if (check_nid_range(sbi, inode->i_ino)) {
@@ -142,7 +135,7 @@ static int do_read_inode(struct inode *inode)
 
 	/* check data exist */
 	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
-		err = __recover_inline_status(inode, node_page);
+		__recover_inline_status(inode, node_page);
 
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);
@@ -152,7 +145,7 @@ static int do_read_inode(struct inode *inode)
 	stat_inc_inline_inode(inode);
 	stat_inc_inline_dir(inode);
 
-	return err;
+	return 0;
 }
 
 struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
@@ -304,7 +297,7 @@ void f2fs_evict_inode(struct inode *inode)
 	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 
 	/* some remained atomic pages should discarded */
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
+	if (f2fs_is_atomic_file(inode))
 		commit_inmem_pages(inode, true);
 
 	trace_f2fs_evict_inode(inode);

fs/f2fs/namei.c

@@ -299,7 +299,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_op = &f2fs_dir_inode_operations;
 	inode->i_fop = &f2fs_dir_operations;
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 
 	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
 	f2fs_lock_op(sbi);

fs/f2fs/node.h

@@ -25,10 +25,19 @@
 
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
+#define SETVEC_SIZE	32
 
 /* return value for read_node_page */
 #define LOCKED_PAGE	1
 
+/* For flag in struct node_info */
+enum {
+	IS_CHECKPOINTED,	/* is it checkpointed before? */
+	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
+	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
+	IS_DIRTY,		/* this nat entry is dirty? */
+};
+
 /*
  * For node information
  */
@@ -37,18 +46,11 @@ struct node_info {
 	nid_t ino;		/* inode number of the node's owner */
 	block_t	blk_addr;	/* block address of the node */
 	unsigned char version;	/* version of the node */
-};
-
-enum {
-	IS_CHECKPOINTED,	/* is it checkpointed before? */
-	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
-	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
-	IS_DIRTY,		/* this nat entry is dirty? */
+	unsigned char flag;	/* for node information bits */
 };
 
 struct nat_entry {
 	struct list_head list;	/* for clean or dirty nat list */
-	unsigned char flag;	/* for node information bits */
 	struct node_info ni;	/* in-memory node information */
 };
 
@@ -63,20 +65,30 @@ struct nat_entry {
 
 #define inc_node_version(version)	(++version)
 
+static inline void copy_node_info(struct node_info *dst,
+						struct node_info *src)
+{
+	dst->nid = src->nid;
+	dst->ino = src->ino;
+	dst->blk_addr = src->blk_addr;
+	dst->version = src->version;
+	/* should not copy flag here */
+}
+
 static inline void set_nat_flag(struct nat_entry *ne,
 				unsigned int type, bool set)
 {
 	unsigned char mask = 0x01 << type;
 	if (set)
-		ne->flag |= mask;
+		ne->ni.flag |= mask;
 	else
-		ne->flag &= ~mask;
+		ne->ni.flag &= ~mask;
 }
 
 static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
 {
 	unsigned char mask = 0x01 << type;
-	return ne->flag & mask;
+	return ne->ni.flag & mask;
 }
 
 static inline void nat_reset_flag(struct nat_entry *ne)
@@ -108,6 +120,7 @@ enum mem_type {
 	NAT_ENTRIES,	/* indicates the cached nat entry */
 	DIRTY_DENTS,	/* indicates dirty dentry pages */
 	INO_ENTRIES,	/* indicates inode entries */
+	BASE_CHECK,	/* check kernel status */
 };
 
 struct nat_entry_set {
@@ -200,11 +213,19 @@ static inline void fill_node_footer(struct page *page, nid_t nid,
 				nid_t ino, unsigned int ofs, bool reset)
 {
 	struct f2fs_node *rn = F2FS_NODE(page);
+	unsigned int old_flag = 0;
+
 	if (reset)
 		memset(rn, 0, sizeof(*rn));
+	else
+		old_flag = le32_to_cpu(rn->footer.flag);
+
 	rn->footer.nid = cpu_to_le32(nid);
 	rn->footer.ino = cpu_to_le32(ino);
-	rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
+
+	/* should remain old flag bits such as COLD_BIT_SHIFT */
+	rn->footer.flag = cpu_to_le32((ofs << OFFSET_BIT_SHIFT) |
+					(old_flag & OFFSET_BIT_MASK));
 }
 
 static inline void copy_node_footer(struct page *dst, struct page *src)

fs/f2fs/recovery.c

@@ -346,6 +346,10 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (IS_INODE(page)) {
 		recover_inline_xattr(inode, page);
 	} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
+		/*
+		 * Deprecated; xattr blocks should be found from cold log.
+		 * But, we should remain this for backward compatibility.
+		 */
 		recover_xattr_data(inode, page, blkaddr);
 		goto out;
 	}
@@ -396,7 +400,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 			/* write dummy data page */
 			recover_data_page(sbi, NULL, &sum, src, dest);
-			update_extent_cache(dest, &dn);
+			dn.data_blkaddr = dest;
+			update_extent_cache(&dn);
 			recovered++;
 		}
 		dn.ofs_in_node++;
@@ -503,7 +508,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 	INIT_LIST_HEAD(&inode_list);
 
 	/* step #1: find fsynced inode numbers */
-	sbi->por_doing = true;
+	set_sbi_flag(sbi, SBI_POR_DOING);
 
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
@@ -536,7 +541,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 		truncate_inode_pages_final(META_MAPPING(sbi));
 	}
 
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	if (err) {
 		discard_next_dnode(sbi, blkaddr);
 

fs/f2fs/segment.h

@@ -189,6 +189,7 @@ struct sit_info {
 	char *sit_bitmap;		/* SIT bitmap pointer */
 	unsigned int bitmap_size;	/* SIT bitmap size */
 
+	unsigned long *tmp_map;			/* bitmap for temporal use */
 	unsigned long *dirty_sentries_bitmap;	/* bitmap for dirty sentries */
 	unsigned int dirty_sentries;		/* # of dirty sentries */
 	unsigned int sents_per_block;		/* # of SIT entries per block */
@@ -207,7 +208,7 @@ struct free_segmap_info {
 	unsigned int start_segno;	/* start segment number logically */
 	unsigned int free_segments;	/* # of free segments */
 	unsigned int free_sections;	/* # of free sections */
-	rwlock_t segmap_lock;		/* free segmap lock */
+	spinlock_t segmap_lock;		/* free segmap lock */
 	unsigned long *free_segmap;	/* free segment bitmap */
 	unsigned long *free_secmap;	/* free section bitmap */
 };
@@ -318,9 +319,9 @@ static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
 		unsigned int max, unsigned int segno)
 {
 	unsigned int ret;
-	read_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	ret = find_next_bit(free_i->free_segmap, max, segno);
-	read_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 	return ret;
 }
 
@@ -331,7 +332,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned int start_segno = secno * sbi->segs_per_sec;
 	unsigned int next;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	clear_bit(segno, free_i->free_segmap);
 	free_i->free_segments++;
 
@@ -340,7 +341,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 		clear_bit(secno, free_i->free_secmap);
 		free_i->free_sections++;
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void __set_inuse(struct f2fs_sb_info *sbi,
@@ -362,7 +363,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 	unsigned int start_segno = secno * sbi->segs_per_sec;
 	unsigned int next;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	if (test_and_clear_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments++;
 
@@ -373,7 +374,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 				free_i->free_sections++;
 		}
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
@@ -381,13 +382,13 @@ static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int secno = segno / sbi->segs_per_sec;
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	if (!test_and_set_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments--;
 		if (!test_and_set_bit(secno, free_i->free_secmap))
 			free_i->free_sections--;
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
@@ -460,7 +461,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
 	return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
@@ -599,13 +600,13 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
 {
 	if (segno > TOTAL_SEGS(sbi) - 1)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
 {
 	if (blk_addr < SEG0_BLKADDR(sbi) || blk_addr >= MAX_BLKADDR(sbi))
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 /*
@@ -616,11 +617,11 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 {
 	/* check segment usage */
 	if (GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	/* check boundary of a given segment number */
 	if (segno > TOTAL_SEGS(sbi) - 1)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 #endif
 

fs/f2fs/super.c

@@ -30,6 +30,7 @@
 #include "segment.h"
 #include "xattr.h"
 #include "gc.h"
+#include "trace.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/f2fs.h>
@@ -41,6 +42,7 @@ static struct kset *f2fs_kset;
 enum {
 	Opt_gc_background,
 	Opt_disable_roll_forward,
+	Opt_norecovery,
 	Opt_discard,
 	Opt_noheap,
 	Opt_user_xattr,
@@ -61,6 +63,7 @@ enum {
 static match_table_t f2fs_tokens = {
 	{Opt_gc_background, "background_gc=%s"},
 	{Opt_disable_roll_forward, "disable_roll_forward"},
+	{Opt_norecovery, "norecovery"},
 	{Opt_discard, "discard"},
 	{Opt_noheap, "no_heap"},
 	{Opt_user_xattr, "user_xattr"},
@@ -192,6 +195,7 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
@@ -207,6 +211,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(gc_idle),
 	ATTR_LIST(reclaim_segments),
 	ATTR_LIST(max_small_discards),
+	ATTR_LIST(batched_trim_sections),
 	ATTR_LIST(ipu_policy),
 	ATTR_LIST(min_ipu_util),
 	ATTR_LIST(min_fsync_blocks),
@@ -286,6 +291,12 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_disable_roll_forward:
 			set_opt(sbi, DISABLE_ROLL_FORWARD);
 			break;
+		case Opt_norecovery:
+			/* this option mounts f2fs with ro */
+			set_opt(sbi, DISABLE_ROLL_FORWARD);
+			if (!f2fs_readonly(sb))
+				return -EINVAL;
+			break;
 		case Opt_discard:
 			set_opt(sbi, DISCARD);
 			break;
@@ -446,8 +457,13 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_destroy_stats(sbi);
 	stop_gc_thread(sbi);
 
-	/* We don't need to do checkpoint when it's clean */
-	if (sbi->s_dirty) {
+	/*
+	 * We don't need to do checkpoint when superblock is clean.
+	 * But, the previous checkpoint was not done by umount, it needs to do
+	 * clean checkpoint again.
+	 */
+	if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
+			!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) {
 		struct cp_control cpc = {
 			.reason = CP_UMOUNT,
 		};
@@ -486,13 +502,15 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 	if (sync) {
 		struct cp_control cpc;
 
-		cpc.reason = test_opt(sbi, FASTBOOT) ? CP_UMOUNT : CP_SYNC;
+		cpc.reason = __get_cp_reason(sbi);
+
 		mutex_lock(&sbi->gc_mutex);
 		write_checkpoint(sbi, &cpc);
 		mutex_unlock(&sbi->gc_mutex);
 	} else {
 		f2fs_balance_fs(sbi);
 	}
+	f2fs_trace_ios(NULL, NULL, 1);
 
 	return 0;
 }
@@ -887,7 +905,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 		atomic_set(&sbi->nr_pages[i], 0);
 
 	sbi->dir_level = DEF_DIR_LEVEL;
-	sbi->need_fsck = false;
+	clear_sbi_flag(sbi, SBI_NEED_FSCK);
 }
 
 /*
@@ -942,6 +960,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *root;
 	long err = -EINVAL;
 	bool retry = true;
+	char *options = NULL;
 	int i;
 
 try_onemore:
@@ -973,9 +992,15 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	set_opt(sbi, POSIX_ACL);
 #endif
 	/* parse mount options */
-	err = parse_options(sb, (char *)data);
-	if (err)
+	options = kstrdup((const char *)data, GFP_KERNEL);
+	if (data && !options) {
+		err = -ENOMEM;
 		goto free_sb_buf;
+	}
+
+	err = parse_options(sb, options);
+	if (err)
+		goto free_options;
 
 	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
 	sb->s_max_links = F2FS_LINK_MAX;
@@ -998,7 +1023,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
 	init_rwsem(&sbi->node_write);
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	spin_lock_init(&sbi->stat_lock);
 
 	init_rwsem(&sbi->read_io.io_rwsem);
@@ -1019,7 +1044,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	if (IS_ERR(sbi->meta_inode)) {
 		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
 		err = PTR_ERR(sbi->meta_inode);
-		goto free_sb_buf;
+		goto free_options;
 	}
 
 	err = get_valid_checkpoint(sbi);
@@ -1122,10 +1147,19 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_proc;
 
 	if (!retry)
-		sbi->need_fsck = true;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	/* recover fsynced data */
 	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+		/*
+		 * mount should be failed, when device has readonly mode, and
+		 * previous checkpoint was not done by clean system shutdown.
+		 */
+		if (bdev_read_only(sb->s_bdev) &&
+				!is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) {
+			err = -EROFS;
+			goto free_kobj;
+		}
 		err = recover_fsync_data(sbi);
 		if (err) {
 			f2fs_msg(sb, KERN_ERR,
@@ -1144,6 +1178,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		if (err)
 			goto free_kobj;
 	}
+	kfree(options);
 	return 0;
 
 free_kobj:
@@ -1168,6 +1203,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
 	iput(sbi->meta_inode);
+free_options:
+	kfree(options);
 free_sb_buf:
 	brelse(raw_super_buf);
 free_sbi:
@@ -1188,11 +1225,18 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
 	return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
 }
 
+static void kill_f2fs_super(struct super_block *sb)
+{
+	if (sb->s_root)
+		set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+	kill_block_super(sb);
+}
+
 static struct file_system_type f2fs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "f2fs",
 	.mount		= f2fs_mount,
-	.kill_sb	= kill_block_super,
+	.kill_sb	= kill_f2fs_super,
 	.fs_flags	= FS_REQUIRES_DEV,
 };
 MODULE_ALIAS_FS("f2fs");
@@ -1220,6 +1264,8 @@ static int __init init_f2fs_fs(void)
 {
 	int err;
 
+	f2fs_build_trace_ios();
+
 	err = init_inodecache();
 	if (err)
 		goto fail;
@@ -1229,12 +1275,9 @@ static int __init init_f2fs_fs(void)
 	err = create_segment_manager_caches();
 	if (err)
 		goto free_node_manager_caches;
-	err = create_gc_caches();
-	if (err)
-		goto free_segment_manager_caches;
 	err = create_checkpoint_caches();
 	if (err)
-		goto free_gc_caches;
+		goto free_segment_manager_caches;
 	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
 	if (!f2fs_kset) {
 		err = -ENOMEM;
@@ -1251,8 +1294,6 @@ static int __init init_f2fs_fs(void)
 	kset_unregister(f2fs_kset);
 free_checkpoint_caches:
 	destroy_checkpoint_caches();
-free_gc_caches:
-	destroy_gc_caches();
 free_segment_manager_caches:
 	destroy_segment_manager_caches();
 free_node_manager_caches:
@@ -1269,11 +1310,11 @@ static void __exit exit_f2fs_fs(void)
 	f2fs_destroy_root_stats();
 	unregister_filesystem(&f2fs_fs_type);
 	destroy_checkpoint_caches();
-	destroy_gc_caches();
 	destroy_segment_manager_caches();
 	destroy_node_manager_caches();
 	destroy_inodecache();
 	kset_unregister(f2fs_kset);
+	f2fs_destroy_trace_ios();
 }
 
 module_init(init_f2fs_fs)

fs/f2fs/trace.c

+/*
+ * f2fs IO tracer
+ *
+ * Copyright (c) 2014 Motorola Mobility
+ * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/sched.h>
+#include <linux/radix-tree.h>
+
+#include "f2fs.h"
+#include "trace.h"
+
+static RADIX_TREE(pids, GFP_ATOMIC);
+static spinlock_t pids_lock;
+static struct last_io_info last_io;
+
+static inline void __print_last_io(void)
+{
+	if (!last_io.len)
+		return;
+
+	trace_printk("%3x:%3x %4x %-16s %2x %5x %12x %4x\n",
+			last_io.major, last_io.minor,
+			last_io.pid, "----------------",
+			last_io.type,
+			last_io.fio.rw, last_io.fio.blk_addr,
+			last_io.len);
+	memset(&last_io, 0, sizeof(last_io));
+}
+
+static int __file_type(struct inode *inode, pid_t pid)
+{
+	if (f2fs_is_atomic_file(inode))
+		return __ATOMIC_FILE;
+	else if (f2fs_is_volatile_file(inode))
+		return __VOLATILE_FILE;
+	else if (S_ISDIR(inode->i_mode))
+		return __DIR_FILE;
+	else if (inode->i_ino == F2FS_NODE_INO(F2FS_I_SB(inode)))
+		return __NODE_FILE;
+	else if (inode->i_ino == F2FS_META_INO(F2FS_I_SB(inode)))
+		return __META_FILE;
+	else if (pid)
+		return __NORMAL_FILE;
+	else
+		return __MISC_FILE;
+}
+
+void f2fs_trace_pid(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	pid_t pid = task_pid_nr(current);
+	void *p;
+
+	page->private = pid;
+
+	if (radix_tree_preload(GFP_NOFS))
+		return;
+
+	spin_lock(&pids_lock);
+	p = radix_tree_lookup(&pids, pid);
+	if (p == current)
+		goto out;
+	if (p)
+		radix_tree_delete(&pids, pid);
+
+	f2fs_radix_tree_insert(&pids, pid, current);
+
+	trace_printk("%3x:%3x %4x %-16s\n",
+			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
+			pid, current->comm);
+out:
+	spin_unlock(&pids_lock);
+	radix_tree_preload_end();
+}
+
+void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush)
+{
+	struct inode *inode;
+	pid_t pid;
+	int major, minor;
+
+	if (flush) {
+		__print_last_io();
+		return;
+	}
+
+	inode = page->mapping->host;
+	pid = page_private(page);
+
+	major = MAJOR(inode->i_sb->s_dev);
+	minor = MINOR(inode->i_sb->s_dev);
+
+	if (last_io.major == major && last_io.minor == minor &&
+			last_io.pid == pid &&
+			last_io.type == __file_type(inode, pid) &&
+			last_io.fio.rw == fio->rw &&
+			last_io.fio.blk_addr + last_io.len == fio->blk_addr) {
+		last_io.len++;
+		return;
+	}
+
+	__print_last_io();
+
+	last_io.major = major;
+	last_io.minor = minor;
+	last_io.pid = pid;
+	last_io.type = __file_type(inode, pid);
+	last_io.fio = *fio;
+	last_io.len = 1;
+	return;
+}
+
+void f2fs_build_trace_ios(void)
+{
+	spin_lock_init(&pids_lock);
+}
+
+#define PIDVEC_SIZE	128
+static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index,
+							unsigned int max_items)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
+
+	if (unlikely(!max_items))
+		return 0;
+
+	radix_tree_for_each_slot(slot, &pids, &iter, first_index) {
+		results[ret] = iter.index;
+		if (++ret == PIDVEC_SIZE)
+			break;
+	}
+	return ret;
+}
+
+void f2fs_destroy_trace_ios(void)
+{
+	pid_t pid[PIDVEC_SIZE];
+	pid_t next_pid = 0;
+	unsigned int found;
+
+	spin_lock(&pids_lock);
+	while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) {
+		unsigned idx;
+
+		next_pid = pid[found - 1] + 1;
+		for (idx = 0; idx < found; idx++)
+			radix_tree_delete(&pids, pid[idx]);
+	}
+	spin_unlock(&pids_lock);
+}

fs/f2fs/trace.h

+/*
+ * f2fs IO tracer
+ *
+ * Copyright (c) 2014 Motorola Mobility
+ * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __F2FS_TRACE_H__
+#define __F2FS_TRACE_H__
+
+#ifdef CONFIG_F2FS_IO_TRACE
+#include <trace/events/f2fs.h>
+
+enum file_type {
+	__NORMAL_FILE,
+	__DIR_FILE,
+	__NODE_FILE,
+	__META_FILE,
+	__ATOMIC_FILE,
+	__VOLATILE_FILE,
+	__MISC_FILE,
+};
+
+struct last_io_info {
+	int major, minor;
+	pid_t pid;
+	enum file_type type;
+	struct f2fs_io_info fio;
+	block_t len;
+};
+
+extern void f2fs_trace_pid(struct page *);
+extern void f2fs_trace_ios(struct page *, struct f2fs_io_info *, int);
+extern void f2fs_build_trace_ios(void);
+extern void f2fs_destroy_trace_ios(void);
+#else
+#define f2fs_trace_pid(p)
+#define f2fs_trace_ios(p, i, n)
+#define f2fs_build_trace_ios()
+#define f2fs_destroy_trace_ios()
+
+#endif
+#endif /* __F2FS_TRACE_H__ */

include/linux/f2fs_fs.h

@@ -19,12 +19,16 @@
 #define F2FS_MAX_LOG_SECTOR_SIZE	12	/* 12 bits for 4096 bytes */
 #define F2FS_LOG_SECTORS_PER_BLOCK	3	/* log number for sector/blk */
 #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 NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
 
+#define F2FS_BYTES_TO_BLK(bytes)	((bytes) >> F2FS_BLKSIZE_BITS)
+#define F2FS_BLK_TO_BYTES(blk)		((blk) << F2FS_BLKSIZE_BITS)
+
 /* 0, 1(node nid), 2(meta nid) are reserved node id */
 #define F2FS_RESERVED_NODE_NUM		3
 
@@ -87,6 +91,7 @@ struct f2fs_super_block {
 /*
  * For checkpoint
  */
+#define CP_FASTBOOT_FLAG	0x00000020
 #define CP_FSCK_FLAG		0x00000010
 #define CP_ERROR_FLAG		0x00000008
 #define CP_COMPACT_SUM_FLAG	0x00000004
@@ -224,6 +229,8 @@ enum {
 	OFFSET_BIT_SHIFT
 };
 
+#define OFFSET_BIT_MASK		(0x07)	/* (0x01 << OFFSET_BIT_SHIFT) - 1 */
+
 struct node_footer {
 	__le32 nid;		/* node id */
 	__le32 ino;		/* inode nunmber */

include/trace/events/f2fs.h

@@ -72,6 +72,7 @@
 #define show_cpreason(type)						\
 	__print_symbolic(type,						\
 		{ CP_UMOUNT,	"Umount" },				\
+		{ CP_FASTBOOT,	"Fastboot" },				\
 		{ CP_SYNC,	"Sync" },				\
 		{ CP_DISCARD,	"Discard" })
 
@@ -148,14 +149,14 @@ DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter,
 
 TRACE_EVENT(f2fs_sync_file_exit,
 
-	TP_PROTO(struct inode *inode, bool need_cp, int datasync, int ret),
+	TP_PROTO(struct inode *inode, int need_cp, int datasync, int ret),
 
 	TP_ARGS(inode, need_cp, datasync, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(bool,	need_cp)
+		__field(int,	need_cp)
 		__field(int,	datasync)
 		__field(int,	ret)
 	),
@@ -190,7 +191,7 @@ TRACE_EVENT(f2fs_sync_fs,
 
 	TP_fast_assign(
 		__entry->dev	= sb->s_dev;
-		__entry->dirty	= F2FS_SB(sb)->s_dirty;
+		__entry->dirty	= is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY);
 		__entry->wait	= wait;
 	),
 
@@ -440,38 +441,6 @@ TRACE_EVENT(f2fs_truncate_partial_nodes,
 		__entry->err)
 );
 
-TRACE_EVENT_CONDITION(f2fs_submit_page_bio,
-
-	TP_PROTO(struct page *page, sector_t blkaddr, int type),
-
-	TP_ARGS(page, blkaddr, type),
-
-	TP_CONDITION(page->mapping),
-
-	TP_STRUCT__entry(
-		__field(dev_t,	dev)
-		__field(ino_t,	ino)
-		__field(pgoff_t,	index)
-		__field(sector_t,	blkaddr)
-		__field(int,	type)
-	),
-
-	TP_fast_assign(
-		__entry->dev		= page->mapping->host->i_sb->s_dev;
-		__entry->ino		= page->mapping->host->i_ino;
-		__entry->index		= page->index;
-		__entry->blkaddr	= blkaddr;
-		__entry->type		= type;
-	),
-
-	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
-		"blkaddr = 0x%llx, bio_type = %s%s",
-		show_dev_ino(__entry),
-		(unsigned long)__entry->index,
-		(unsigned long long)__entry->blkaddr,
-		show_bio_type(__entry->type))
-);
-
 TRACE_EVENT(f2fs_get_data_block,
 	TP_PROTO(struct inode *inode, sector_t iblock,
 				struct buffer_head *bh, int ret),
@@ -680,11 +649,63 @@ TRACE_EVENT(f2fs_reserve_new_block,
 		__entry->ofs_in_node)
 );
 
+DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(ino_t, ino)
+		__field(pgoff_t, index)
+		__field(block_t, blkaddr)
+		__field(int, rw)
+		__field(int, type)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= page->mapping->host->i_sb->s_dev;
+		__entry->ino		= page->mapping->host->i_ino;
+		__entry->index		= page->index;
+		__entry->blkaddr	= fio->blk_addr;
+		__entry->rw		= fio->rw;
+		__entry->type		= fio->type;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
+		"blkaddr = 0x%llx, rw = %s%s, type = %s",
+		show_dev_ino(__entry),
+		(unsigned long)__entry->index,
+		(unsigned long long)__entry->blkaddr,
+		show_bio_type(__entry->rw),
+		show_block_type(__entry->type))
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_CONDITION(page->mapping)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_CONDITION(page->mapping)
+);
+
 DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+						struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
@@ -696,8 +717,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
-		__entry->rw		= rw;
-		__entry->type		= type;
+		__entry->rw		= fio->rw;
+		__entry->type		= fio->type;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->size		= bio->bi_iter.bi_size;
 	),
@@ -712,18 +733,20 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
 DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_write_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+							struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_CONDITION(bio)
 );
 
 DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+							struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_CONDITION(bio)
 );
@@ -916,38 +939,6 @@ TRACE_EVENT(f2fs_writepages,
 		__entry->for_sync)
 );
 
-TRACE_EVENT(f2fs_submit_page_mbio,
-
-	TP_PROTO(struct page *page, int rw, int type, block_t blk_addr),
-
-	TP_ARGS(page, rw, type, blk_addr),
-
-	TP_STRUCT__entry(
-		__field(dev_t,	dev)
-		__field(ino_t,	ino)
-		__field(int, rw)
-		__field(int, type)
-		__field(pgoff_t, index)
-		__field(block_t, block)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= page->mapping->host->i_sb->s_dev;
-		__entry->ino	= page->mapping->host->i_ino;
-		__entry->rw	= rw;
-		__entry->type	= type;
-		__entry->index	= page->index;
-		__entry->block	= blk_addr;
-	),
-
-	TP_printk("dev = (%d,%d), ino = %lu, %s%s, %s, index = %lu, blkaddr = 0x%llx",
-		show_dev_ino(__entry),
-		show_bio_type(__entry->rw),
-		show_block_type(__entry->type),
-		(unsigned long)__entry->index,
-		(unsigned long long)__entry->block)
-);
-
 TRACE_EVENT(f2fs_write_checkpoint,
 
 	TP_PROTO(struct super_block *sb, int reason, char *msg),
@@ -998,14 +989,15 @@ TRACE_EVENT(f2fs_issue_discard,
 
 TRACE_EVENT(f2fs_issue_flush,
 
-	TP_PROTO(struct super_block *sb, bool nobarrier, bool flush_merge),
+	TP_PROTO(struct super_block *sb, unsigned int nobarrier,
+					unsigned int flush_merge),
 
 	TP_ARGS(sb, nobarrier, flush_merge),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
-		__field(bool, nobarrier)
-		__field(bool, flush_merge)
+		__field(unsigned int, nobarrier)
+		__field(unsigned int, flush_merge)
 	),
 
 	TP_fast_assign(