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/checkpoint.c

@@ -20,10 +20,11 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static struct kmem_cache *ino_entry_slab;
-static struct kmem_cache *inode_entry_slab;
+struct kmem_cache *inode_entry_slab;
 
 /*
  * We guarantee no failure on the returned page.
@@ -50,6 +51,11 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
 	struct page *page;
+	struct f2fs_io_info fio = {
+		.type = META,
+		.rw = READ_SYNC | REQ_META | REQ_PRIO,
+		.blk_addr = index,
+	};
 repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page) {
@@ -59,8 +65,7 @@ repeat:
 	if (PageUptodate(page))
 		goto out;
 
-	if (f2fs_submit_page_bio(sbi, page, index,
-				READ_SYNC | REQ_META | REQ_PRIO))
+	if (f2fs_submit_page_bio(sbi, page, &fio))
 		goto repeat;
 
 	lock_page(page);
@@ -112,14 +117,12 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 	block_t prev_blk_addr = 0;
 	struct page *page;
 	block_t blkno = start;
-
 	struct f2fs_io_info fio = {
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO
 	};
 
 	for (; nrpages-- > 0; blkno++) {
-		block_t blk_addr;
 
 		if (!is_valid_blkaddr(sbi, blkno, type))
 			goto out;
@@ -130,27 +133,27 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 					NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
 				blkno = 0;
 			/* get nat block addr */
-			blk_addr = current_nat_addr(sbi,
+			fio.blk_addr = current_nat_addr(sbi,
 					blkno * NAT_ENTRY_PER_BLOCK);
 			break;
 		case META_SIT:
 			/* get sit block addr */
-			blk_addr = current_sit_addr(sbi,
+			fio.blk_addr = current_sit_addr(sbi,
 					blkno * SIT_ENTRY_PER_BLOCK);
-			if (blkno != start && prev_blk_addr + 1 != blk_addr)
+			if (blkno != start && prev_blk_addr + 1 != fio.blk_addr)
 				goto out;
-			prev_blk_addr = blk_addr;
+			prev_blk_addr = fio.blk_addr;
 			break;
 		case META_SSA:
 		case META_CP:
 		case META_POR:
-			blk_addr = blkno;
+			fio.blk_addr = blkno;
 			break;
 		default:
 			BUG();
 		}
 
-		page = grab_cache_page(META_MAPPING(sbi), blk_addr);
+		page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr);
 		if (!page)
 			continue;
 		if (PageUptodate(page)) {
@@ -158,7 +161,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 			continue;
 		}
 
-		f2fs_submit_page_mbio(sbi, page, blk_addr, &fio);
+		f2fs_submit_page_mbio(sbi, page, &fio);
 		f2fs_put_page(page, 0);
 	}
 out:
@@ -187,7 +190,7 @@ static int f2fs_write_meta_page(struct page *page,
 
 	trace_f2fs_writepage(page, META);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
 		goto redirty_out;
@@ -299,6 +302,8 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
+		SetPagePrivate(page);
+		f2fs_trace_pid(page);
 		return 1;
 	}
 	return 0;
@@ -308,6 +313,8 @@ const struct address_space_operations f2fs_meta_aops = {
 	.writepage	= f2fs_write_meta_page,
 	.writepages	= f2fs_write_meta_pages,
 	.set_page_dirty	= f2fs_set_meta_page_dirty,
+	.invalidatepage = f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 };
 
 static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -462,7 +469,7 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
 		return;
 
-	sbi->por_doing = true;
+	set_sbi_flag(sbi, SBI_POR_DOING);
 
 	start_blk = __start_cp_addr(sbi) + 1 +
 		le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
@@ -483,7 +490,7 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	}
 	/* clear Orphan Flag */
 	clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	return;
 }
 
@@ -567,7 +574,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (crc_offset >= blk_size)
 		goto invalid_cp1;
 
-	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp1;
 
@@ -582,7 +589,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	if (crc_offset >= blk_size)
 		goto invalid_cp2;
 
-	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
 	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
 		goto invalid_cp2;
 
@@ -669,7 +676,7 @@ fail_no_cp:
 	return -EINVAL;
 }
 
-static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
+static int __add_dirty_inode(struct inode *inode, struct inode_entry *new)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
@@ -686,7 +693,7 @@ static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
 void update_dirty_page(struct inode *inode, struct page *page)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *new;
+	struct inode_entry *new;
 	int ret = 0;
 
 	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
@@ -710,12 +717,13 @@ void update_dirty_page(struct inode *inode, struct page *page)
 		kmem_cache_free(inode_entry_slab, new);
 out:
 	SetPagePrivate(page);
+	f2fs_trace_pid(page);
 }
 
 void add_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *new =
+	struct inode_entry *new =
 			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
 	int ret = 0;
 
@@ -733,7 +741,7 @@ void add_dirty_dir_inode(struct inode *inode)
 void remove_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dir_inode_entry *entry;
+	struct inode_entry *entry;
 
 	if (!S_ISDIR(inode->i_mode))
 		return;
@@ -763,7 +771,7 @@ void remove_dirty_dir_inode(struct inode *inode)
 void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
 {
 	struct list_head *head;
-	struct dir_inode_entry *entry;
+	struct inode_entry *entry;
 	struct inode *inode;
 retry:
 	if (unlikely(f2fs_cp_error(sbi)))
@@ -776,7 +784,7 @@ retry:
 		spin_unlock(&sbi->dir_inode_lock);
 		return;
 	}
-	entry = list_entry(head->next, struct dir_inode_entry, list);
+	entry = list_entry(head->next, struct inode_entry, list);
 	inode = igrab(entry->inode);
 	spin_unlock(&sbi->dir_inode_lock);
 	if (inode) {
@@ -922,7 +930,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	ckpt->next_free_nid = cpu_to_le32(last_nid);
 
 	/* 2 cp  + n data seg summary + orphan inode blocks */
-	data_sum_blocks = npages_for_summary_flush(sbi);
+	data_sum_blocks = npages_for_summary_flush(sbi, false);
 	if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
 		set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 	else
@@ -932,24 +940,31 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
 			orphan_blocks);
 
-	if (cpc->reason == CP_UMOUNT) {
-		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	if (__remain_node_summaries(cpc->reason))
 		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks + NR_CURSEG_NODE_TYPE);
-	} else {
-		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	else
 		ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks);
-	}
+
+	if (cpc->reason == CP_UMOUNT)
+		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	else
+		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+
+	if (cpc->reason == CP_FASTBOOT)
+		set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+	else
+		clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
 
 	if (orphan_num)
 		set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 	else
 		clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
 
-	if (sbi->need_fsck)
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
 		set_ckpt_flags(ckpt, CP_FSCK_FLAG);
 
 	/* update SIT/NAT bitmap */
@@ -966,15 +981,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* write out checkpoint buffer at block 0 */
 	cp_page = grab_meta_page(sbi, start_blk++);
 	kaddr = page_address(cp_page);
-	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+	memcpy(kaddr, ckpt, F2FS_BLKSIZE);
 	set_page_dirty(cp_page);
 	f2fs_put_page(cp_page, 1);
 
 	for (i = 1; i < 1 + cp_payload_blks; i++) {
 		cp_page = grab_meta_page(sbi, start_blk++);
 		kaddr = page_address(cp_page);
-		memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE,
-				(1 << sbi->log_blocksize));
+		memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE, F2FS_BLKSIZE);
 		set_page_dirty(cp_page);
 		f2fs_put_page(cp_page, 1);
 	}
@@ -986,7 +1000,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	write_data_summaries(sbi, start_blk);
 	start_blk += data_sum_blocks;
-	if (cpc->reason == CP_UMOUNT) {
+	if (__remain_node_summaries(cpc->reason)) {
 		write_node_summaries(sbi, start_blk);
 		start_blk += NR_CURSEG_NODE_TYPE;
 	}
@@ -994,7 +1008,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* writeout checkpoint block */
 	cp_page = grab_meta_page(sbi, start_blk);
 	kaddr = page_address(cp_page);
-	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+	memcpy(kaddr, ckpt, F2FS_BLKSIZE);
 	set_page_dirty(cp_page);
 	f2fs_put_page(cp_page, 1);
 
@@ -1023,7 +1037,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		return;
 
 	clear_prefree_segments(sbi);
-	F2FS_RESET_SB_DIRT(sbi);
+	clear_sbi_flag(sbi, SBI_IS_DIRTY);
 }
 
 /*
@@ -1038,10 +1052,13 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	mutex_lock(&sbi->cp_mutex);
 
-	if (!sbi->s_dirty && cpc->reason != CP_DISCARD)
+	if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
+			cpc->reason != CP_DISCARD && cpc->reason != CP_UMOUNT)
 		goto out;
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto out;
+	if (f2fs_readonly(sbi->sb))
+		goto out;
 	if (block_operations(sbi))
 		goto out;
 
@@ -1102,8 +1119,8 @@ int __init create_checkpoint_caches(void)
 			sizeof(struct ino_entry));
 	if (!ino_entry_slab)
 		return -ENOMEM;
-	inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry",
-			sizeof(struct dir_inode_entry));
+	inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
+			sizeof(struct inode_entry));
 	if (!inode_entry_slab) {
 		kmem_cache_destroy(ino_entry_slab);
 		return -ENOMEM;

fs/f2fs/data.c

@@ -22,6 +22,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 static void f2fs_read_end_io(struct bio *bio, int err)
@@ -95,11 +96,9 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 		return;
 
 	if (is_read_io(fio->rw))
-		trace_f2fs_submit_read_bio(io->sbi->sb, fio->rw,
-							fio->type, io->bio);
+		trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
 	else
-		trace_f2fs_submit_write_bio(io->sbi->sb, fio->rw,
-							fio->type, io->bio);
+		trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
 
 	submit_bio(fio->rw, io->bio);
 	io->bio = NULL;
@@ -132,14 +131,15 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
  * Return unlocked page.
  */
 int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
-					block_t blk_addr, int rw)
+					struct f2fs_io_info *fio)
 {
 	struct bio *bio;
 
-	trace_f2fs_submit_page_bio(page, blk_addr, rw);
+	trace_f2fs_submit_page_bio(page, fio);
+	f2fs_trace_ios(page, fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(sbi, blk_addr, 1, is_read_io(rw));
+	bio = __bio_alloc(sbi, fio->blk_addr, 1, is_read_io(fio->rw));
 
 	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
 		bio_put(bio);
@@ -147,12 +147,12 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
 		return -EFAULT;
 	}
 
-	submit_bio(rw, bio);
+	submit_bio(fio->rw, bio);
 	return 0;
 }
 
 void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
-			block_t blk_addr, struct f2fs_io_info *fio)
+					struct f2fs_io_info *fio)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
 	struct f2fs_bio_info *io;
@@ -160,21 +160,21 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
 
-	verify_block_addr(sbi, blk_addr);
+	verify_block_addr(sbi, fio->blk_addr);
 
 	down_write(&io->io_rwsem);
 
 	if (!is_read)
 		inc_page_count(sbi, F2FS_WRITEBACK);
 
-	if (io->bio && (io->last_block_in_bio != blk_addr - 1 ||
+	if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 ||
 						io->fio.rw != fio->rw))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
 		int bio_blocks = MAX_BIO_BLOCKS(sbi);
 
-		io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read);
+		io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read);
 		io->fio = *fio;
 	}
 
@@ -184,10 +184,11 @@ alloc_new:
 		goto alloc_new;
 	}
 
-	io->last_block_in_bio = blk_addr;
+	io->last_block_in_bio = fio->blk_addr;
+	f2fs_trace_ios(page, fio, 0);
 
 	up_write(&io->io_rwsem);
-	trace_f2fs_submit_page_mbio(page, fio->rw, fio->type, blk_addr);
+	trace_f2fs_submit_page_mbio(page, fio);
 }
 
 /*
@@ -196,7 +197,7 @@ alloc_new:
  *  ->node_page
  *    update block addresses in the node page
  */
-static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
+static void __set_data_blkaddr(struct dnode_of_data *dn)
 {
 	struct f2fs_node *rn;
 	__le32 *addr_array;
@@ -209,7 +210,7 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
 
 	/* Get physical address of data block */
 	addr_array = blkaddr_in_node(rn);
-	addr_array[ofs_in_node] = cpu_to_le32(new_addr);
+	addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
 	set_page_dirty(node_page);
 }
 
@@ -224,8 +225,8 @@ int reserve_new_block(struct dnode_of_data *dn)
 
 	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
 
-	__set_data_blkaddr(dn, NEW_ADDR);
 	dn->data_blkaddr = NEW_ADDR;
+	__set_data_blkaddr(dn);
 	mark_inode_dirty(dn->inode);
 	sync_inode_page(dn);
 	return 0;
@@ -273,7 +274,7 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 		unsigned int blkbits = inode->i_sb->s_blocksize_bits;
 		size_t count;
 
-		clear_buffer_new(bh_result);
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb,
 				start_blkaddr + pgofs - start_fofs);
 		count = end_fofs - pgofs + 1;
@@ -290,23 +291,24 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 	return 0;
 }
 
-void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
+void update_extent_cache(struct dnode_of_data *dn)
 {
 	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	pgoff_t fofs, start_fofs, end_fofs;
 	block_t start_blkaddr, end_blkaddr;
 	int need_update = true;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), blk_addr == NEW_ADDR);
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
-							dn->ofs_in_node;
+	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
 
 	/* Update the page address in the parent node */
-	__set_data_blkaddr(dn, blk_addr);
+	__set_data_blkaddr(dn);
 
 	if (is_inode_flag_set(fi, FI_NO_EXTENT))
 		return;
 
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+							dn->ofs_in_node;
+
 	write_lock(&fi->ext.ext_lock);
 
 	start_fofs = fi->ext.fofs;
@@ -320,16 +322,16 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 
 	/* Initial extent */
 	if (fi->ext.len == 0) {
-		if (blk_addr != NULL_ADDR) {
+		if (dn->data_blkaddr != NULL_ADDR) {
 			fi->ext.fofs = fofs;
-			fi->ext.blk_addr = blk_addr;
+			fi->ext.blk_addr = dn->data_blkaddr;
 			fi->ext.len = 1;
 		}
 		goto end_update;
 	}
 
 	/* Front merge */
-	if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
+	if (fofs == start_fofs - 1 && dn->data_blkaddr == start_blkaddr - 1) {
 		fi->ext.fofs--;
 		fi->ext.blk_addr--;
 		fi->ext.len++;
@@ -337,7 +339,7 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
 	}
 
 	/* Back merge */
-	if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) {
+	if (fofs == end_fofs + 1 && dn->data_blkaddr == end_blkaddr + 1) {
 		fi->ext.len++;
 		goto end_update;
 	}
@@ -376,6 +378,10 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	struct dnode_of_data dn;
 	struct page *page;
 	int err;
+	struct f2fs_io_info fio = {
+		.type = DATA,
+		.rw = sync ? READ_SYNC : READA,
+	};
 
 	page = find_get_page(mapping, index);
 	if (page && PageUptodate(page))
@@ -404,8 +410,8 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 		return page;
 	}
 
-	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, dn.data_blkaddr,
-					sync ? READ_SYNC : READA);
+	fio.blk_addr = dn.data_blkaddr;
+	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 	if (err)
 		return ERR_PTR(err);
 
@@ -430,7 +436,10 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	struct dnode_of_data dn;
 	struct page *page;
 	int err;
-
+	struct f2fs_io_info fio = {
+		.type = DATA,
+		.rw = READ_SYNC,
+	};
 repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page)
@@ -464,8 +473,8 @@ repeat:
 		return page;
 	}
 
-	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
-					dn.data_blkaddr, READ_SYNC);
+	fio.blk_addr = dn.data_blkaddr;
+	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 	if (err)
 		return ERR_PTR(err);
 
@@ -515,8 +524,12 @@ repeat:
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 		SetPageUptodate(page);
 	} else {
-		err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
-						dn.data_blkaddr, READ_SYNC);
+		struct f2fs_io_info fio = {
+			.type = DATA,
+			.rw = READ_SYNC,
+			.blk_addr = dn.data_blkaddr,
+		};
+		err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
 		if (err)
 			goto put_err;
 
@@ -550,30 +563,25 @@ 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;
-	block_t new_blkaddr;
 	struct node_info ni;
+	int seg = CURSEG_WARM_DATA;
 	pgoff_t fofs;
-	int type;
 
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return -EPERM;
 	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
 		return -ENOSPC;
 
-	__set_data_blkaddr(dn, NEW_ADDR);
-	dn->data_blkaddr = NEW_ADDR;
-
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
-	type = CURSEG_WARM_DATA;
+	if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page)
+		seg = CURSEG_DIRECT_IO;
 
-	allocate_data_block(sbi, NULL, NULL_ADDR, &new_blkaddr, &sum, type);
+	allocate_data_block(sbi, NULL, NULL_ADDR, &dn->data_blkaddr, &sum, seg);
 
 	/* direct IO doesn't use extent cache to maximize the performance */
-	set_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
-	update_extent_cache(new_blkaddr, dn);
-	clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
+	__set_data_blkaddr(dn);
 
 	/* update i_size */
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
@@ -581,10 +589,59 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
 		i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
 
-	dn->data_blkaddr = new_blkaddr;
 	return 0;
 }
 
+static void __allocate_data_blocks(struct inode *inode, loff_t offset,
+							size_t count)
+{
+	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;
+
+	while (len) {
+		f2fs_balance_fs(sbi);
+		f2fs_lock_op(sbi);
+
+		/* When reading holes, we need its node page */
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		if (get_dnode_of_data(&dn, start, ALLOC_NODE))
+			goto out;
+
+		allocated = false;
+		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+
+		while (dn.ofs_in_node < end_offset && len) {
+			if (dn.data_blkaddr == NULL_ADDR) {
+				if (__allocate_data_block(&dn))
+					goto sync_out;
+				allocated = true;
+			}
+			len--;
+			start++;
+			dn.ofs_in_node++;
+		}
+
+		if (allocated)
+			sync_inode_page(&dn);
+
+		f2fs_put_dnode(&dn);
+		f2fs_unlock_op(sbi);
+	}
+	return;
+
+sync_out:
+	if (allocated)
+		sync_inode_page(&dn);
+	f2fs_put_dnode(&dn);
+out:
+	f2fs_unlock_op(sbi);
+	return;
+}
+
 /*
  * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh.
  * If original data blocks are allocated, then give them to blockdev.
@@ -610,10 +667,8 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	if (check_extent_cache(inode, pgofs, bh_result))
 		goto out;
 
-	if (create) {
-		f2fs_balance_fs(F2FS_I_SB(inode));
+	if (create)
 		f2fs_lock_op(F2FS_I_SB(inode));
-	}
 
 	/* When reading holes, we need its node page */
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -627,12 +682,14 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 		goto put_out;
 
 	if (dn.data_blkaddr != NULL_ADDR) {
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
 	} else if (create) {
 		err = __allocate_data_block(&dn);
 		if (err)
 			goto put_out;
 		allocated = true;
+		set_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
 	} else {
 		goto put_out;
@@ -745,7 +802,6 @@ static int f2fs_read_data_pages(struct file *file,
 int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 {
 	struct inode *inode = page->mapping->host;
-	block_t old_blkaddr, new_blkaddr;
 	struct dnode_of_data dn;
 	int err = 0;
 
@@ -754,10 +810,10 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 	if (err)
 		return err;
 
-	old_blkaddr = dn.data_blkaddr;
+	fio->blk_addr = dn.data_blkaddr;
 
 	/* This page is already truncated */
-	if (old_blkaddr == NULL_ADDR)
+	if (fio->blk_addr == NULL_ADDR)
 		goto out_writepage;
 
 	set_page_writeback(page);
@@ -766,14 +822,14 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (unlikely(old_blkaddr != NEW_ADDR &&
+	if (unlikely(fio->blk_addr != NEW_ADDR &&
 			!is_cold_data(page) &&
 			need_inplace_update(inode))) {
-		rewrite_data_page(page, old_blkaddr, fio);
+		rewrite_data_page(page, fio);
 		set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
 	} else {
-		write_data_page(page, &dn, &new_blkaddr, fio);
-		update_extent_cache(new_blkaddr, &dn);
+		write_data_page(page, &dn, fio);
+		update_extent_cache(&dn);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	}
 out_writepage:
@@ -812,7 +868,12 @@ static int f2fs_write_data_page(struct page *page,
 
 	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
 write:
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto redirty_out;
+	if (f2fs_is_drop_cache(inode))
+		goto out;
+	if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim &&
+			available_free_memory(sbi, BASE_CHECK))
 		goto redirty_out;
 
 	/* Dentry blocks are controlled by checkpoint */
@@ -826,7 +887,6 @@ write:
 	/* we should bypass data pages to proceed the kworkder jobs */
 	if (unlikely(f2fs_cp_error(sbi))) {
 		SetPageError(page);
-		unlock_page(page);
 		goto out;
 	}
 
@@ -1002,8 +1062,12 @@ put_next:
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 	} else {
-		err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
-					   READ_SYNC);
+		struct f2fs_io_info fio = {
+			.type = DATA,
+			.rw = READ_SYNC,
+			.blk_addr = dn.data_blkaddr,
+		};
+		err = f2fs_submit_page_bio(sbi, page, &fio);
 		if (err)
 			goto fail;
 
@@ -1092,6 +1156,9 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 
 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
 
+	if (rw & WRITE)
+		__allocate_data_blocks(inode, offset, count);
+
 	err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block);
 	if (err < 0 && (rw & WRITE))
 		f2fs_write_failed(mapping, offset + count);
@@ -1101,24 +1168,33 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 	return err;
 }
 
-static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
-				      unsigned int length)
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+							unsigned int length)
 {
 	struct inode *inode = page->mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
-	if (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)
+	if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
+		(offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE))
 		return;
 
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
-		invalidate_inmem_page(inode, page);
-
-	if (PageDirty(page))
-		inode_dec_dirty_pages(inode);
+	if (PageDirty(page)) {
+		if (inode->i_ino == F2FS_META_INO(sbi))
+			dec_page_count(sbi, F2FS_DIRTY_META);
+		else if (inode->i_ino == F2FS_NODE_INO(sbi))
+			dec_page_count(sbi, F2FS_DIRTY_NODES);
+		else
+			inode_dec_dirty_pages(inode);
+	}
 	ClearPagePrivate(page);
 }
 
-static int f2fs_release_data_page(struct page *page, gfp_t wait)
+int f2fs_release_page(struct page *page, gfp_t wait)
 {
+	/* If this is dirty page, keep PagePrivate */
+	if (PageDirty(page))
+		return 0;
+
 	ClearPagePrivate(page);
 	return 1;
 }
@@ -1132,7 +1208,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
 
 	SetPageUptodate(page);
 
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode)) {
+	if (f2fs_is_atomic_file(inode)) {
 		register_inmem_page(inode, page);
 		return 1;
 	}
@@ -1168,8 +1244,8 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.write_begin	= f2fs_write_begin,
 	.write_end	= f2fs_write_end,
 	.set_page_dirty	= f2fs_set_data_page_dirty,
-	.invalidatepage	= f2fs_invalidate_data_page,
-	.releasepage	= f2fs_release_data_page,
+	.invalidatepage	= f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 	.direct_IO	= f2fs_direct_IO,
 	.bmap		= f2fs_bmap,
 };

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/f2fs.h

@@ -28,7 +28,7 @@
 	do {								\
 		if (unlikely(condition)) {				\
 			WARN_ON(1);					\
-			sbi->need_fsck = true;				\
+			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
 		}							\
 	} while (0)
 #define f2fs_down_write(x, y)	down_write(x)
@@ -100,10 +100,15 @@ enum {
 
 enum {
 	CP_UMOUNT,
+	CP_FASTBOOT,
 	CP_SYNC,
 	CP_DISCARD,
 };
 
+#define DEF_BATCHED_TRIM_SECTIONS	32
+#define BATCHED_TRIM_SEGMENTS(sbi)	\
+		(SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
+
 struct cp_control {
 	int reason;
 	__u64 trim_start;
@@ -136,8 +141,14 @@ struct ino_entry {
 	nid_t ino;		/* inode number */
 };
 
-/* for the list of directory inodes */
-struct dir_inode_entry {
+/*
+ * for the list of directory inodes or gc inodes.
+ * NOTE: there are two slab users for this structure, if we add/modify/delete
+ * fields in structure for one of slab users, it may affect fields or size of
+ * other one, in this condition, it's better to split both of slab and related
+ * data structure.
+ */
+struct inode_entry {
 	struct list_head list;	/* list head */
 	struct inode *inode;	/* vfs inode pointer */
 };
@@ -196,11 +207,14 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
  */
 #define F2FS_IOC_GETFLAGS		FS_IOC_GETFLAGS
 #define F2FS_IOC_SETFLAGS		FS_IOC_SETFLAGS
+#define F2FS_IOC_GETVERSION		FS_IOC_GETVERSION
 
 #define F2FS_IOCTL_MAGIC		0xf5
 #define F2FS_IOC_START_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 1)
 #define F2FS_IOC_COMMIT_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 2)
 #define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
+#define F2FS_IOC_RELEASE_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 4)
+#define F2FS_IOC_ABORT_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 5)
 
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
@@ -295,7 +309,7 @@ struct f2fs_inode_info {
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	unsigned long long xattr_ver;	/* cp version of xattr modification */
 	struct extent_info ext;		/* in-memory extent cache entry */
-	struct dir_inode_entry *dirty_dir;	/* the pointer of dirty dir */
+	struct inode_entry *dirty_dir;	/* the pointer of dirty dir */
 
 	struct radix_tree_root inmem_root;	/* radix tree for inmem pages */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
@@ -398,7 +412,8 @@ enum {
 	CURSEG_HOT_NODE,	/* direct node blocks of directory files */
 	CURSEG_WARM_NODE,	/* direct node blocks of normal files */
 	CURSEG_COLD_NODE,	/* indirect node blocks */
-	NO_CHECK_TYPE
+	NO_CHECK_TYPE,
+	CURSEG_DIRECT_IO,	/* to use for the direct IO path */
 };
 
 struct flush_cmd {
@@ -437,6 +452,9 @@ struct f2fs_sm_info {
 	int nr_discards;			/* # of discards in the list */
 	int max_discards;			/* max. discards to be issued */
 
+	/* for batched trimming */
+	unsigned int trim_sections;		/* # of sections to trim */
+
 	struct list_head sit_entry_set;	/* sit entry set list */
 
 	unsigned int ipu_policy;	/* in-place-update policy */
@@ -489,6 +507,7 @@ enum page_type {
 struct f2fs_io_info {
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	int rw;			/* contains R/RS/W/WS with REQ_META/REQ_PRIO */
+	block_t blk_addr;	/* block address to be written */
 };
 
 #define is_read_io(rw)	(((rw) & 1) == READ)
@@ -508,13 +527,20 @@ struct inode_management {
 	unsigned long ino_num;			/* number of entries */
 };
 
+/* For s_flag in struct f2fs_sb_info */
+enum {
+	SBI_IS_DIRTY,				/* dirty flag for checkpoint */
+	SBI_IS_CLOSE,				/* specify unmounting */
+	SBI_NEED_FSCK,				/* need fsck.f2fs to fix */
+	SBI_POR_DOING,				/* recovery is doing or not */
+};
+
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
 	struct buffer_head *raw_super_buf;	/* buffer head of raw sb */
 	struct f2fs_super_block *raw_super;	/* raw super block pointer */
-	int s_dirty;				/* dirty flag for checkpoint */
-	bool need_fsck;				/* need fsck.f2fs to fix */
+	int s_flag;				/* flags for sbi */
 
 	/* for node-related operations */
 	struct f2fs_nm_info *nm_info;		/* node manager */
@@ -534,7 +560,6 @@ struct f2fs_sb_info {
 	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
 	struct mutex writepages;		/* mutex for writepages() */
-	bool por_doing;				/* recovery is doing or not */
 	wait_queue_head_t cp_wait;
 
 	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
@@ -589,6 +614,7 @@ struct f2fs_sb_info {
 	struct f2fs_stat_info *stat_info;	/* FS status information */
 	unsigned int segment_count[2];		/* # of allocated segments */
 	unsigned int block_count[2];		/* # of allocated blocks */
+	atomic_t inplace_count;		/* # of inplace update */
 	int total_hit_ext, read_hit_ext;	/* extent cache hit ratio */
 	atomic_t inline_inode;			/* # of inline_data inodes */
 	atomic_t inline_dir;			/* # of inline_dentry inodes */
@@ -686,14 +712,19 @@ static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
 	return sbi->node_inode->i_mapping;
 }
 
-static inline void F2FS_SET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
 {
-	sbi->s_dirty = 1;
+	return sbi->s_flag & (0x01 << type);
 }
 
-static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
 {
-	sbi->s_dirty = 0;
+	sbi->s_flag |= (0x01 << type);
+}
+
+static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
+{
+	sbi->s_flag &= ~(0x01 << type);
 }
 
 static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
@@ -741,6 +772,28 @@ static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
 	up_write(&sbi->cp_rwsem);
 }
 
+static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
+{
+	int reason = CP_SYNC;
+
+	if (test_opt(sbi, FASTBOOT))
+		reason = CP_FASTBOOT;
+	if (is_sbi_flag_set(sbi, SBI_IS_CLOSE))
+		reason = CP_UMOUNT;
+	return reason;
+}
+
+static inline bool __remain_node_summaries(int reason)
+{
+	return (reason == CP_UMOUNT || reason == CP_FASTBOOT);
+}
+
+static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
+{
+	return (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) ||
+			is_set_ckpt_flags(F2FS_CKPT(sbi), CP_FASTBOOT_FLAG));
+}
+
 /*
  * Check whether the given nid is within node id range.
  */
@@ -805,7 +858,7 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
 {
 	atomic_inc(&sbi->nr_pages[count_type]);
-	F2FS_SET_SB_DIRT(sbi);
+	set_sbi_flag(sbi, SBI_IS_DIRTY);
 }
 
 static inline void inode_inc_dirty_pages(struct inode *inode)
@@ -1113,6 +1166,7 @@ enum {
 	FI_NEED_IPU,		/* used for ipu per file */
 	FI_ATOMIC_FILE,		/* indicate atomic file */
 	FI_VOLATILE_FILE,	/* indicate volatile file */
+	FI_DROP_CACHE,		/* drop dirty page cache */
 	FI_DATA_EXIST,		/* indicate data exists */
 };
 
@@ -1220,6 +1274,11 @@ static inline bool f2fs_is_volatile_file(struct inode *inode)
 	return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
 }
 
+static inline bool f2fs_is_drop_cache(struct inode *inode)
+{
+	return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE);
+}
+
 static inline void *inline_data_addr(struct page *page)
 {
 	struct f2fs_inode *ri = F2FS_INODE(page);
@@ -1389,7 +1448,6 @@ void destroy_node_manager_caches(void);
  * segment.c
  */
 void register_inmem_page(struct inode *, struct page *);
-void invalidate_inmem_page(struct inode *, struct page *);
 void commit_inmem_pages(struct inode *, bool);
 void f2fs_balance_fs(struct f2fs_sb_info *);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
@@ -1401,16 +1459,16 @@ void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
 void clear_prefree_segments(struct f2fs_sb_info *);
 void release_discard_addrs(struct f2fs_sb_info *);
 void discard_next_dnode(struct f2fs_sb_info *, block_t);
-int npages_for_summary_flush(struct f2fs_sb_info *);
+int npages_for_summary_flush(struct f2fs_sb_info *, bool);
 void allocate_new_segments(struct f2fs_sb_info *);
 int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
 void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(struct f2fs_sb_info *, struct page *,
-		struct f2fs_io_info *, unsigned int, block_t, block_t *);
-void write_data_page(struct page *, struct dnode_of_data *, block_t *,
-					struct f2fs_io_info *);
-void rewrite_data_page(struct page *, block_t, struct f2fs_io_info *);
+				unsigned int, struct f2fs_io_info *);
+void write_data_page(struct page *, struct dnode_of_data *,
+			struct f2fs_io_info *);
+void rewrite_data_page(struct page *, struct f2fs_io_info *);
 void recover_data_page(struct f2fs_sb_info *, struct page *,
 				struct f2fs_summary *, block_t, block_t);
 void allocate_data_block(struct f2fs_sb_info *, struct page *,
@@ -1457,17 +1515,20 @@ void destroy_checkpoint_caches(void);
  * data.c
  */
 void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, block_t, int);
-void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, block_t,
+int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *,
+						struct f2fs_io_info *);
+void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *,
 						struct f2fs_io_info *);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-void update_extent_cache(block_t, struct dnode_of_data *);
+void update_extent_cache(struct dnode_of_data *);
 struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int do_write_data_page(struct page *, struct f2fs_io_info *);
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
+int f2fs_release_page(struct page *, gfp_t);
 
 /*
  * gc.c
@@ -1477,8 +1538,6 @@ void stop_gc_thread(struct f2fs_sb_info *);
 block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
 int f2fs_gc(struct f2fs_sb_info *);
 void build_gc_manager(struct f2fs_sb_info *);
-int __init create_gc_caches(void);
-void destroy_gc_caches(void);
 
 /*
  * recovery.c
@@ -1497,9 +1556,9 @@ struct f2fs_stat_info {
 	int main_area_segs, main_area_sections, main_area_zones;
 	int hit_ext, total_ext;
 	int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
-	int nats, sits, fnids;
+	int nats, dirty_nats, sits, dirty_sits, fnids;
 	int total_count, utilization;
-	int bg_gc, inline_inode, inline_dir, inmem_pages;
+	int bg_gc, inline_inode, inline_dir, inmem_pages, wb_pages;
 	unsigned int valid_count, valid_node_count, valid_inode_count;
 	unsigned int bimodal, avg_vblocks;
 	int util_free, util_valid, util_invalid;
@@ -1514,7 +1573,8 @@ struct f2fs_stat_info {
 
 	unsigned int segment_count[2];
 	unsigned int block_count[2];
-	unsigned base_mem, cache_mem;
+	unsigned int inplace_count;
+	unsigned base_mem, cache_mem, page_mem;
 };
 
 static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
@@ -1553,7 +1613,8 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 		((sbi)->segment_count[(curseg)->alloc_type]++)
 #define stat_inc_block_count(sbi, curseg)				\
 		((sbi)->block_count[(curseg)->alloc_type]++)
-
+#define stat_inc_inplace_blocks(sbi)					\
+		(atomic_inc(&(sbi)->inplace_count))
 #define stat_inc_seg_count(sbi, type)					\
 	do {								\
 		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
@@ -1599,6 +1660,7 @@ void f2fs_destroy_root_stats(void);
 #define stat_dec_inline_dir(inode)
 #define stat_inc_seg_type(sbi, curseg)
 #define stat_inc_block_count(sbi, curseg)
+#define stat_inc_inplace_blocks(sbi)
 #define stat_inc_seg_count(si, type)
 #define stat_inc_tot_blk_count(si, blks)
 #define stat_inc_data_blk_count(si, blks)
@@ -1619,6 +1681,7 @@ extern const struct address_space_operations f2fs_meta_aops;
 extern const struct inode_operations f2fs_dir_inode_operations;
 extern const struct inode_operations f2fs_symlink_inode_operations;
 extern const struct inode_operations f2fs_special_inode_operations;
+extern struct kmem_cache *inode_entry_slab;
 
 /*
  * inline.c
@@ -1629,7 +1692,6 @@ int f2fs_read_inline_data(struct inode *, struct page *);
 int f2fs_convert_inline_page(struct dnode_of_data *, struct page *);
 int f2fs_convert_inline_inode(struct inode *);
 int f2fs_write_inline_data(struct inode *, struct page *);
-void truncate_inline_data(struct page *, u64);
 bool recover_inline_data(struct inode *, struct page *);
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *,
 							struct page **);

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 @@ go_write:
 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 @@ flush_out:
 	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 @@ out:
 	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 @@ no_update:
 
 	/* 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 @@ no_update:
 	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 @@ process_inline:
 	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;
+	__le32 *start = inline_data;
+	__le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
 
-	zbuf = kzalloc(MAX_INLINE_DATA, GFP_NOFS);
-	if (!zbuf)
-		return -ENOMEM;
+	while (start < end) {
+		if (*start++) {
+			f2fs_wait_on_page_writeback(ipage, NODE);
 
-	if (!memcmp(zbuf, inline_data, MAX_INLINE_DATA)) {
-		kfree(zbuf);
-		return 0;
+			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+			set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
+			set_page_dirty(ipage);
+			return;
+		}
 	}
-	kfree(zbuf);
-
-	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_page_dirty(ipage);
-	return 0;
+	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.c

@@ -19,6 +19,7 @@
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 #define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock)
@@ -57,12 +58,13 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 	} else if (type == INO_ENTRIES) {
 		int i;
 
-		if (sbi->sb->s_bdi->dirty_exceeded)
-			return false;
 		for (i = 0; i <= UPDATE_INO; i++)
 			mem_size += (sbi->im[i].ino_num *
 				sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+	} else {
+		if (sbi->sb->s_bdi->dirty_exceeded)
+			return false;
 	}
 	return res;
 }
@@ -268,7 +270,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 	e = __lookup_nat_cache(nm_i, ni->nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, ni->nid);
-		e->ni = *ni;
+		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
 	} else if (new_blkaddr == NEW_ADDR) {
 		/*
@@ -276,7 +278,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 		 * previous nat entry can be remained in nat cache.
 		 * So, reinitialize it with new information.
 		 */
-		e->ni = *ni;
+		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
 	}
 
@@ -346,7 +348,6 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	struct nat_entry *e;
 	int i;
 
-	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
 	ni->nid = nid;
 
 	/* Check nat cache */
@@ -361,6 +362,8 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	if (e)
 		return;
 
+	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
+
 	/* Check current segment summary */
 	mutex_lock(&curseg->curseg_mutex);
 	i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
@@ -471,7 +474,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct page *npage[4];
-	struct page *parent;
+	struct page *parent = NULL;
 	int offset[4];
 	unsigned int noffset[4];
 	nid_t nids[4];
@@ -488,6 +491,14 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 		if (IS_ERR(npage[0]))
 			return PTR_ERR(npage[0]);
 	}
+
+	/* if inline_data is set, should not report any block indices */
+	if (f2fs_has_inline_data(dn->inode) && index) {
+		err = -EINVAL;
+		f2fs_put_page(npage[0], 1);
+		goto release_out;
+	}
+
 	parent = npage[0];
 	if (level != 0)
 		nids[1] = get_nid(parent, offset[0], true);
@@ -585,7 +596,7 @@ static void truncate_node(struct dnode_of_data *dn)
 	}
 invalidate:
 	clear_node_page_dirty(dn->node_page);
-	F2FS_SET_SB_DIRT(sbi);
+	set_sbi_flag(sbi, SBI_IS_DIRTY);
 
 	f2fs_put_page(dn->node_page, 1);
 
@@ -976,6 +987,10 @@ static int read_node_page(struct page *page, int rw)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	struct node_info ni;
+	struct f2fs_io_info fio = {
+		.type = NODE,
+		.rw = rw,
+	};
 
 	get_node_info(sbi, page->index, &ni);
 
@@ -987,7 +1002,8 @@ static int read_node_page(struct page *page, int rw)
 	if (PageUptodate(page))
 		return LOCKED_PAGE;
 
-	return f2fs_submit_page_bio(sbi, page, ni.blk_addr, rw);
+	fio.blk_addr = ni.blk_addr;
+	return f2fs_submit_page_bio(sbi, page, &fio);
 }
 
 /*
@@ -1028,11 +1044,11 @@ repeat:
 	err = read_node_page(page, READ_SYNC);
 	if (err < 0)
 		return ERR_PTR(err);
-	else if (err == LOCKED_PAGE)
-		goto got_it;
+	else if (err != LOCKED_PAGE)
+		lock_page(page);
 
-	lock_page(page);
 	if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) {
+		ClearPageUptodate(page);
 		f2fs_put_page(page, 1);
 		return ERR_PTR(-EIO);
 	}
@@ -1040,7 +1056,6 @@ repeat:
 		f2fs_put_page(page, 1);
 		goto repeat;
 	}
-got_it:
 	return page;
 }
 
@@ -1268,7 +1283,6 @@ static int f2fs_write_node_page(struct page *page,
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	nid_t nid;
-	block_t new_addr;
 	struct node_info ni;
 	struct f2fs_io_info fio = {
 		.type = NODE,
@@ -1277,7 +1291,7 @@ static int f2fs_write_node_page(struct page *page,
 
 	trace_f2fs_writepage(page, NODE);
 
-	if (unlikely(sbi->por_doing))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
@@ -1303,9 +1317,11 @@ static int f2fs_write_node_page(struct page *page,
 	} else {
 		down_read(&sbi->node_write);
 	}
+
 	set_page_writeback(page);
-	write_node_page(sbi, page, &fio, nid, ni.blk_addr, &new_addr);
-	set_node_addr(sbi, &ni, new_addr, is_fsync_dnode(page));
+	fio.blk_addr = ni.blk_addr;
+	write_node_page(sbi, page, nid, &fio);
+	set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
 	dec_page_count(sbi, F2FS_DIRTY_NODES);
 	up_read(&sbi->node_write);
 	unlock_page(page);
@@ -1355,26 +1371,12 @@ static int f2fs_set_node_page_dirty(struct page *page)
 		__set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
 		SetPagePrivate(page);
+		f2fs_trace_pid(page);
 		return 1;
 	}
 	return 0;
 }
 
-static void f2fs_invalidate_node_page(struct page *page, unsigned int offset,
-				      unsigned int length)
-{
-	struct inode *inode = page->mapping->host;
-	if (PageDirty(page))
-		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_NODES);
-	ClearPagePrivate(page);
-}
-
-static int f2fs_release_node_page(struct page *page, gfp_t wait)
-{
-	ClearPagePrivate(page);
-	return 1;
-}
-
 /*
  * Structure of the f2fs node operations
  */
@@ -1382,8 +1384,8 @@ const struct address_space_operations f2fs_node_aops = {
 	.writepage	= f2fs_write_node_page,
 	.writepages	= f2fs_write_node_pages,
 	.set_page_dirty	= f2fs_set_node_page_dirty,
-	.invalidatepage	= f2fs_invalidate_node_page,
-	.releasepage	= f2fs_release_node_page,
+	.invalidatepage	= f2fs_invalidate_page,
+	.releasepage	= f2fs_release_page,
 };
 
 static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
@@ -1726,80 +1728,41 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	return 0;
 }
 
-/*
- * ra_sum_pages() merge contiguous pages into one bio and submit.
- * these pre-read pages are allocated in bd_inode's mapping tree.
- */
-static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages,
-				int start, int nrpages)
-{
-	struct inode *inode = sbi->sb->s_bdev->bd_inode;
-	struct address_space *mapping = inode->i_mapping;
-	int i, page_idx = start;
-	struct f2fs_io_info fio = {
-		.type = META,
-		.rw = READ_SYNC | REQ_META | REQ_PRIO
-	};
-
-	for (i = 0; page_idx < start + nrpages; page_idx++, i++) {
-		/* alloc page in bd_inode for reading node summary info */
-		pages[i] = grab_cache_page(mapping, page_idx);
-		if (!pages[i])
-			break;
-		f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio);
-	}
-
-	f2fs_submit_merged_bio(sbi, META, READ);
-	return i;
-}
-
 int restore_node_summary(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct f2fs_summary_block *sum)
 {
 	struct f2fs_node *rn;
 	struct f2fs_summary *sum_entry;
-	struct inode *inode = sbi->sb->s_bdev->bd_inode;
 	block_t addr;
 	int bio_blocks = MAX_BIO_BLOCKS(sbi);
-	struct page *pages[bio_blocks];
-	int i, idx, last_offset, nrpages, err = 0;
+	int i, idx, last_offset, nrpages;
 
 	/* scan the node segment */
 	last_offset = sbi->blocks_per_seg;
 	addr = START_BLOCK(sbi, segno);
 	sum_entry = &sum->entries[0];
 
-	for (i = 0; !err && i < last_offset; i += nrpages, addr += nrpages) {
+	for (i = 0; i < last_offset; i += nrpages, addr += nrpages) {
 		nrpages = min(last_offset - i, bio_blocks);
 
 		/* readahead node pages */
-		nrpages = ra_sum_pages(sbi, pages, addr, nrpages);
-		if (!nrpages)
-			return -ENOMEM;
+		ra_meta_pages(sbi, addr, nrpages, META_POR);
 
-		for (idx = 0; idx < nrpages; idx++) {
-			if (err)
-				goto skip;
+		for (idx = addr; idx < addr + nrpages; idx++) {
+			struct page *page = get_meta_page(sbi, idx);
 
-			lock_page(pages[idx]);
-			if (unlikely(!PageUptodate(pages[idx]))) {
-				err = -EIO;
-			} else {
-				rn = F2FS_NODE(pages[idx]);
-				sum_entry->nid = rn->footer.nid;
-				sum_entry->version = 0;
-				sum_entry->ofs_in_node = 0;
-				sum_entry++;
-			}
-			unlock_page(pages[idx]);
-skip:
-			page_cache_release(pages[idx]);
+			rn = F2FS_NODE(page);
+			sum_entry->nid = rn->footer.nid;
+			sum_entry->version = 0;
+			sum_entry->ofs_in_node = 0;
+			sum_entry++;
+			f2fs_put_page(page, 1);
 		}
 
-		invalidate_mapping_pages(inode->i_mapping, addr,
+		invalidate_mapping_pages(META_MAPPING(sbi), addr,
 							addr + nrpages);
 	}
-	return err;
+	return 0;
 }
 
 static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
@@ -1923,7 +1886,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
 	struct f2fs_summary_block *sum = curseg->sum_blk;
-	struct nat_entry_set *setvec[NATVEC_SIZE];
+	struct nat_entry_set *setvec[SETVEC_SIZE];
 	struct nat_entry_set *set, *tmp;
 	unsigned int found;
 	nid_t set_idx = 0;
@@ -1940,7 +1903,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
-					set_idx, NATVEC_SIZE, setvec))) {
+					set_idx, SETVEC_SIZE, setvec))) {
 		unsigned idx;
 		set_idx = setvec[found - 1]->set + 1;
 		for (idx = 0; idx < found; idx++)
@@ -2020,6 +1983,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i, *next_i;
 	struct nat_entry *natvec[NATVEC_SIZE];
+	struct nat_entry_set *setvec[SETVEC_SIZE];
 	nid_t nid = 0;
 	unsigned int found;
 
@@ -2044,11 +2008,27 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	while ((found = __gang_lookup_nat_cache(nm_i,
 					nid, NATVEC_SIZE, natvec))) {
 		unsigned idx;
+
 		nid = nat_get_nid(natvec[found - 1]) + 1;
 		for (idx = 0; idx < found; idx++)
 			__del_from_nat_cache(nm_i, natvec[idx]);
 	}
 	f2fs_bug_on(sbi, nm_i->nat_cnt);
+
+	/* destroy nat set cache */
+	nid = 0;
+	while ((found = __gang_lookup_nat_set(nm_i,
+					nid, SETVEC_SIZE, setvec))) {
+		unsigned idx;
+
+		nid = setvec[found - 1]->set + 1;
+		for (idx = 0; idx < found; idx++) {
+			/* entry_cnt is not zero, when cp_error was occurred */
+			f2fs_bug_on(sbi, !list_empty(&setvec[idx]->entry_list));
+			radix_tree_delete(&nm_i->nat_set_root, setvec[idx]->set);
+			kmem_cache_free(nat_entry_set_slab, setvec[idx]);
+		}
+	}
 	up_write(&nm_i->nat_tree_lock);
 
 	kfree(nm_i->nat_bitmap);

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 @@ out:
 		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.c

@@ -20,6 +20,7 @@
 #include "f2fs.h"
 #include "segment.h"
 #include "node.h"
+#include "trace.h"
 #include <trace/events/f2fs.h>
 
 #define __reverse_ffz(x) __reverse_ffs(~(x))
@@ -181,6 +182,7 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	int err;
 
 	SetPagePrivate(page);
+	f2fs_trace_pid(page);
 
 	new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
 
@@ -205,23 +207,6 @@ retry:
 	mutex_unlock(&fi->inmem_lock);
 }
 
-void invalidate_inmem_page(struct inode *inode, struct page *page)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct inmem_pages *cur;
-
-	mutex_lock(&fi->inmem_lock);
-	cur = radix_tree_lookup(&fi->inmem_root, page->index);
-	if (cur) {
-		radix_tree_delete(&fi->inmem_root, cur->page->index);
-		f2fs_put_page(cur->page, 0);
-		list_del(&cur->list);
-		kmem_cache_free(inmem_entry_slab, cur);
-		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
-	}
-	mutex_unlock(&fi->inmem_lock);
-}
-
 void commit_inmem_pages(struct inode *inode, bool abort)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -230,7 +215,7 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 	bool submit_bio = false;
 	struct f2fs_io_info fio = {
 		.type = DATA,
-		.rw = WRITE_SYNC,
+		.rw = WRITE_SYNC | REQ_PRIO,
 	};
 
 	/*
@@ -240,33 +225,38 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 	 * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this
 	 * inode becomes free by iget_locked in f2fs_iget.
 	 */
-	if (!abort)
+	if (!abort) {
 		f2fs_balance_fs(sbi);
-
-	f2fs_lock_op(sbi);
+		f2fs_lock_op(sbi);
+	}
 
 	mutex_lock(&fi->inmem_lock);
 	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
-		lock_page(cur->page);
-		if (!abort && cur->page->mapping == inode->i_mapping) {
-			f2fs_wait_on_page_writeback(cur->page, DATA);
-			if (clear_page_dirty_for_io(cur->page))
-				inode_dec_dirty_pages(inode);
-			do_write_data_page(cur->page, &fio);
-			submit_bio = true;
+		if (!abort) {
+			lock_page(cur->page);
+			if (cur->page->mapping == inode->i_mapping) {
+				f2fs_wait_on_page_writeback(cur->page, DATA);
+				if (clear_page_dirty_for_io(cur->page))
+					inode_dec_dirty_pages(inode);
+				do_write_data_page(cur->page, &fio);
+				submit_bio = true;
+			}
+			f2fs_put_page(cur->page, 1);
+		} else {
+			put_page(cur->page);
 		}
 		radix_tree_delete(&fi->inmem_root, cur->page->index);
-		f2fs_put_page(cur->page, 1);
 		list_del(&cur->list);
 		kmem_cache_free(inmem_entry_slab, cur);
 		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
 	}
-	if (submit_bio)
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
 	mutex_unlock(&fi->inmem_lock);
 
-	filemap_fdatawait_range(inode->i_mapping, 0, LLONG_MAX);
-	f2fs_unlock_op(sbi);
+	if (!abort) {
+		f2fs_unlock_op(sbi);
+		if (submit_bio)
+			f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	}
 }
 
 /*
@@ -290,7 +280,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	/* check the # of cached NAT entries and prefree segments */
 	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) ||
 			excess_prefree_segs(sbi) ||
-			available_free_memory(sbi, INO_ENTRIES))
+			!available_free_memory(sbi, INO_ENTRIES))
 		f2fs_sync_fs(sbi->sb, true);
 }
 
@@ -515,12 +505,13 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
-	unsigned long dmap[entries];
+	unsigned long *dmap = SIT_I(sbi)->tmp_map;
 	unsigned int start = 0, end = -1;
 	bool force = (cpc->reason == CP_DISCARD);
 	int i;
 
-	if (!force && !test_opt(sbi, DISCARD))
+	if (!force && (!test_opt(sbi, DISCARD) ||
+			SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards))
 		return;
 
 	if (force && !se->valid_blocks) {
@@ -548,7 +539,8 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
 	for (i = 0; i < entries; i++)
-		dmap[i] = ~(cur_map[i] | ckpt_map[i]);
+		dmap[i] = force ? ~ckpt_map[i] :
+				(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
 
 	while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
 		start = __find_rev_next_bit(dmap, max_blocks, end + 1);
@@ -735,7 +727,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
 /*
  * Calculate the number of current summary pages for writing
  */
-int npages_for_summary_flush(struct f2fs_sb_info *sbi)
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
 {
 	int valid_sum_count = 0;
 	int i, sum_in_page;
@@ -743,8 +735,13 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi)
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		if (sbi->ckpt->alloc_type[i] == SSR)
 			valid_sum_count += sbi->blocks_per_seg;
-		else
-			valid_sum_count += curseg_blkoff(sbi, i);
+		else {
+			if (for_ra)
+				valid_sum_count += le16_to_cpu(
+					F2FS_CKPT(sbi)->cur_data_blkoff[i]);
+			else
+				valid_sum_count += curseg_blkoff(sbi, i);
+		}
 	}
 
 	sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
@@ -803,7 +800,7 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 	int go_left = 0;
 	int i;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
@@ -876,7 +873,7 @@ got_it:
 	f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
 	__set_inuse(sbi, segno);
 	*newseg = segno;
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
@@ -927,7 +924,7 @@ static void __next_free_blkoff(struct f2fs_sb_info *sbi,
 {
 	struct seg_entry *se = get_seg_entry(sbi, seg->segno);
 	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
-	unsigned long target_map[entries];
+	unsigned long *target_map = SIT_I(sbi)->tmp_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	int i, pos;
@@ -1027,18 +1024,22 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 	stat_inc_seg_type(sbi, curseg);
 }
 
+static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned int old_segno;
+
+	old_segno = curseg->segno;
+	SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
+	locate_dirty_segment(sbi, old_segno);
+}
+
 void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
-	struct curseg_info *curseg;
-	unsigned int old_curseg;
 	int i;
 
-	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
-		curseg = CURSEG_I(sbi, i);
-		old_curseg = curseg->segno;
-		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
-		locate_dirty_segment(sbi, old_curseg);
-	}
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
+		__allocate_new_segments(sbi, i);
 }
 
 static const struct segment_allocation default_salloc_ops = {
@@ -1047,8 +1048,8 @@ static const struct segment_allocation default_salloc_ops = {
 
 int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 {
-	__u64 start = range->start >> sbi->log_blocksize;
-	__u64 end = start + (range->len >> sbi->log_blocksize) - 1;
+	__u64 start = F2FS_BYTES_TO_BLK(range->start);
+	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
 	unsigned int start_segno, end_segno;
 	struct cp_control cpc;
 
@@ -1065,16 +1066,21 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
 						GET_SEGNO(sbi, end);
 	cpc.reason = CP_DISCARD;
-	cpc.trim_start = start_segno;
-	cpc.trim_end = end_segno;
-	cpc.trim_minlen = range->minlen >> sbi->log_blocksize;
+	cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen);
 
 	/* do checkpoint to issue discard commands safely */
-	mutex_lock(&sbi->gc_mutex);
-	write_checkpoint(sbi, &cpc);
-	mutex_unlock(&sbi->gc_mutex);
+	for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
+		cpc.trim_start = start_segno;
+		cpc.trim_end = min_t(unsigned int, rounddown(start_segno +
+				BATCHED_TRIM_SEGMENTS(sbi),
+				sbi->segs_per_sec) - 1, end_segno);
+
+		mutex_lock(&sbi->gc_mutex);
+		write_checkpoint(sbi, &cpc);
+		mutex_unlock(&sbi->gc_mutex);
+	}
 out:
-	range->len = cpc.trimmed << sbi->log_blocksize;
+	range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
 	return 0;
 }
 
@@ -1151,11 +1157,18 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
+	bool direct_io = (type == CURSEG_DIRECT_IO);
+
+	type = direct_io ? CURSEG_WARM_DATA : type;
 
 	curseg = CURSEG_I(sbi, type);
 
 	mutex_lock(&curseg->curseg_mutex);
 
+	/* direct_io'ed data is aligned to the segment for better performance */
+	if (direct_io && curseg->next_blkoff)
+		__allocate_new_segments(sbi, type);
+
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	/*
@@ -1187,39 +1200,39 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 }
 
 static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
-			block_t old_blkaddr, block_t *new_blkaddr,
-			struct f2fs_summary *sum, struct f2fs_io_info *fio)
+			struct f2fs_summary *sum,
+			struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(page, fio->type);
 
-	allocate_data_block(sbi, page, old_blkaddr, new_blkaddr, sum, type);
+	allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type);
 
 	/* writeout dirty page into bdev */
-	f2fs_submit_page_mbio(sbi, page, *new_blkaddr, fio);
+	f2fs_submit_page_mbio(sbi, page, fio);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 {
 	struct f2fs_io_info fio = {
 		.type = META,
-		.rw = WRITE_SYNC | REQ_META | REQ_PRIO
+		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
+		.blk_addr = page->index,
 	};
 
 	set_page_writeback(page);
-	f2fs_submit_page_mbio(sbi, page, page->index, &fio);
+	f2fs_submit_page_mbio(sbi, page, &fio);
 }
 
 void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
-		struct f2fs_io_info *fio,
-		unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr)
+			unsigned int nid, struct f2fs_io_info *fio)
 {
 	struct f2fs_summary sum;
 	set_summary(&sum, nid, 0, 0);
-	do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, fio);
+	do_write_page(sbi, page, &sum, fio);
 }
 
 void write_data_page(struct page *page, struct dnode_of_data *dn,
-		block_t *new_blkaddr, struct f2fs_io_info *fio)
+				struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_summary sum;
@@ -1228,14 +1241,14 @@ void write_data_page(struct page *page, struct dnode_of_data *dn,
 	f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
-
-	do_write_page(sbi, page, dn->data_blkaddr, new_blkaddr, &sum, fio);
+	do_write_page(sbi, page, &sum, fio);
+	dn->data_blkaddr = fio->blk_addr;
 }
 
-void rewrite_data_page(struct page *page, block_t old_blkaddr,
-					struct f2fs_io_info *fio)
+void rewrite_data_page(struct page *page, struct f2fs_io_info *fio)
 {
-	f2fs_submit_page_mbio(F2FS_P_SB(page), page, old_blkaddr, fio);
+	stat_inc_inplace_blocks(F2FS_P_SB(page));
+	f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio);
 }
 
 void recover_data_page(struct f2fs_sb_info *sbi,
@@ -1393,7 +1406,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 		segno = le32_to_cpu(ckpt->cur_data_segno[type]);
 		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
 							CURSEG_HOT_DATA]);
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+		if (__exist_node_summaries(sbi))
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
 		else
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
@@ -1402,7 +1415,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 							CURSEG_HOT_NODE]);
 		blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
 							CURSEG_HOT_NODE]);
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+		if (__exist_node_summaries(sbi))
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
 							type - CURSEG_HOT_NODE);
 		else
@@ -1413,7 +1426,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	sum = (struct f2fs_summary_block *)page_address(new);
 
 	if (IS_NODESEG(type)) {
-		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) {
+		if (__exist_node_summaries(sbi)) {
 			struct f2fs_summary *ns = &sum->entries[0];
 			int i;
 			for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
@@ -1450,12 +1463,22 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 	int err;
 
 	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
+		int npages = npages_for_summary_flush(sbi, true);
+
+		if (npages >= 2)
+			ra_meta_pages(sbi, start_sum_block(sbi), npages,
+								META_CP);
+
 		/* restore for compacted data summary */
 		if (read_compacted_summaries(sbi))
 			return -EINVAL;
 		type = CURSEG_HOT_NODE;
 	}
 
+	if (__exist_node_summaries(sbi))
+		ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
+					NR_CURSEG_TYPE - type, META_CP);
+
 	for (; type <= CURSEG_COLD_NODE; type++) {
 		err = read_normal_summaries(sbi, type);
 		if (err)
@@ -1549,8 +1572,7 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 
 void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 {
-	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
-		write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
+	write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
 }
 
 int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
@@ -1754,7 +1776,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			se = get_seg_entry(sbi, segno);
 
 			/* add discard candidates */
-			if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards) {
+			if (cpc->reason != CP_DISCARD) {
 				cpc->trim_start = segno;
 				add_discard_addrs(sbi, cpc);
 			}
@@ -1833,6 +1855,10 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 			return -ENOMEM;
 	}
 
+	sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+	if (!sit_i->tmp_map)
+		return -ENOMEM;
+
 	if (sbi->segs_per_sec > 1) {
 		sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) *
 					sizeof(struct sec_entry));
@@ -1897,7 +1923,7 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
 	free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi));
 	free_i->free_segments = 0;
 	free_i->free_sections = 0;
-	rwlock_init(&free_i->segmap_lock);
+	spin_lock_init(&free_i->segmap_lock);
 	return 0;
 }
 
@@ -2110,6 +2136,8 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->nr_discards = 0;
 	sm_info->max_discards = 0;
 
+	sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
+
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
 
 	if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
@@ -2212,6 +2240,8 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 			kfree(sit_i->sentries[start].ckpt_valid_map);
 		}
 	}
+	kfree(sit_i->tmp_map);
+
 	vfree(sit_i->sentries);
 	vfree(sit_i->sec_entries);
 	kfree(sit_i->dirty_sentries_bitmap);

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 @@ try_onemore:
 	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 @@ try_onemore:
 	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 @@ try_onemore:
 	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 @@ try_onemore:
 		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 @@ try_onemore:
 		if (err)
 			goto free_kobj;
 	}
+	kfree(options);
 	return 0;
 
 free_kobj:
@@ -1168,6 +1203,8 @@ free_cp:
 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 @@ free_kset:
 	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

@@ -0,0 +1,159 @@
+/*
+ * 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

@@ -0,0 +1,46 @@
+/*
+ * 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(