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
  ...

1 files changed, 91 insertions, 29 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ec58bb2373fc..7fa3313ab0e2 100644
--- a/fs/f2fs/f2fs.h
+++ b/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 **);