Merge tag 'for-f2fs-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've added new features such as disk quota and statx,
  and modified internal bio management flow to merge more IOs depending
  on block types. We've also made internal threads freezeable for
  Android battery life. In addition to them, there are some patches to
  avoid lock contention as well as a couple of deadlock conditions.

  Enhancements:
   - support usrquota, grpquota, and statx
   - manage DATA/NODE typed bios separately to serialize more IOs
   - modify f2fs_lock_op/wio_mutex to avoid lock contention
   - prevent lock contention in migratepage

  Bug fixes:
   - fix missing load of written inode flag
   - fix worst case victim selection in GC
   - freezeable GC and discard threads for Android battery life
   - sanitize f2fs metadata to deal with security hole
   - clean up sysfs-related code and docs"

* tag 'for-f2fs-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (59 commits)
  f2fs: support plain user/group quota
  f2fs: avoid deadlock caused by lock order of page and lock_op
  f2fs: use spin_{,un}lock_irq{save,restore}
  f2fs: relax migratepage for atomic written page
  f2fs: don't count inode block in in-memory inode.i_blocks
  Revert "f2fs: fix to clean previous mount option when remount_fs"
  f2fs: do not set LOST_PINO for renamed dir
  f2fs: do not set LOST_PINO for newly created dir
  f2fs: skip ->writepages for {mete,node}_inode during recovery
  f2fs: introduce __check_sit_bitmap
  f2fs: stop gc/discard thread in prior during umount
  f2fs: introduce reserved_blocks in sysfs
  f2fs: avoid redundant f2fs_flush after remount
  f2fs: report # of free inodes more precisely
  f2fs: add ioctl to do gc with target block address
  f2fs: don't need to check encrypted inode for partial truncation
  f2fs: measure inode.i_blocks as generic filesystem
  f2fs: set CP_TRIMMED_FLAG correctly
  f2fs: require key for truncate(2) of encrypted file
  f2fs: move sysfs code from super.c to fs/f2fs/sysfs.c
  ...

1 files changed, 150 insertions, 51 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index fd2e651bad6d..94a88b233e98 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/quotaops.h>
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
 #include <linux/fscrypt_supp.h>
 #else
@@ -88,6 +89,8 @@ extern char *fault_name[FAULT_MAX];
 #define F2FS_MOUNT_FAULT_INJECTION	0x00010000
 #define F2FS_MOUNT_ADAPTIVE		0x00020000
 #define F2FS_MOUNT_LFS			0x00040000
+#define F2FS_MOUNT_USRQUOTA		0x00080000
+#define F2FS_MOUNT_GRPQUOTA		0x00100000
 
 #define clear_opt(sbi, option)	((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option)
 #define set_opt(sbi, option)	((sbi)->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -303,6 +306,8 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 						struct f2fs_move_range)
 #define F2FS_IOC_FLUSH_DEVICE		_IOW(F2FS_IOCTL_MAGIC, 10,	\
 						struct f2fs_flush_device)
+#define F2FS_IOC_GARBAGE_COLLECT_RANGE	_IOW(F2FS_IOCTL_MAGIC, 11,	\
+						struct f2fs_gc_range)
 
 #define F2FS_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
 #define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
@@ -327,6 +332,12 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 #define F2FS_IOC32_GETVERSION		FS_IOC32_GETVERSION
 #endif
 
+struct f2fs_gc_range {
+	u32 sync;
+	u64 start;
+	u64 len;
+};
+
 struct f2fs_defragment {
 	u64 start;
 	u64 len;
@@ -513,12 +524,19 @@ struct f2fs_inode_info {
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	loff_t	last_disk_size;		/* lastly written file size */
 
+#ifdef CONFIG_QUOTA
+	struct dquot *i_dquot[MAXQUOTAS];
+
+	/* quota space reservation, managed internally by quota code */
+	qsize_t i_reserved_quota;
+#endif
 	struct list_head dirty_list;	/* dirty list for dirs and files */
 	struct list_head gdirty_list;	/* linked in global dirty list */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
 	struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
+	struct rw_semaphore i_mmap_sem;
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -792,17 +810,33 @@ enum page_type {
 	OPU,
 };
 
+enum temp_type {
+	HOT = 0,	/* must be zero for meta bio */
+	WARM,
+	COLD,
+	NR_TEMP_TYPE,
+};
+
+enum need_lock_type {
+	LOCK_REQ = 0,
+	LOCK_DONE,
+	LOCK_RETRY,
+};
+
 struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
+	enum temp_type temp;	/* contains HOT/WARM/COLD */
 	int op;			/* contains REQ_OP_ */
 	int op_flags;		/* req_flag_bits */
 	block_t new_blkaddr;	/* new block address to be written */
 	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
+	struct list_head list;		/* serialize IOs */
 	bool submitted;		/* indicate IO submission */
-	bool need_lock;		/* indicate we need to lock cp_rwsem */
+	int need_lock;		/* indicate we need to lock cp_rwsem */
+	bool in_list;		/* indicate fio is in io_list */
 };
 
 #define is_read_io(rw) ((rw) == READ)
@@ -812,6 +846,8 @@ struct f2fs_bio_info {
 	sector_t last_block_in_bio;	/* last block number */
 	struct f2fs_io_info fio;	/* store buffered io info. */
 	struct rw_semaphore io_rwsem;	/* blocking op for bio */
+	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
+	struct list_head io_list;	/* track fios */
 };
 
 #define FDEV(i)				(sbi->devs[i])
@@ -879,9 +915,9 @@ struct f2fs_sb_info {
 	struct f2fs_sm_info *sm_info;		/* segment manager */
 
 	/* for bio operations */
-	struct f2fs_bio_info read_io;			/* for read bios */
-	struct f2fs_bio_info write_io[NR_PAGE_TYPE];	/* for write bios */
-	struct mutex wio_mutex[NODE + 1];	/* bio ordering for NODE/DATA */
+	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
+	struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE];
+						/* bio ordering for NODE/DATA */
 	int write_io_size_bits;			/* Write IO size bits */
 	mempool_t *write_io_dummy;		/* Dummy pages */
 
@@ -939,6 +975,8 @@ struct f2fs_sb_info {
 	block_t total_valid_block_count;	/* # of valid blocks */
 	block_t discard_blks;			/* discard command candidats */
 	block_t last_valid_block_count;		/* for recovery */
+	block_t reserved_blocks;		/* configurable reserved blocks */
+
 	u32 s_next_generation;			/* for NFS support */
 
 	/* # of pages, see count_type */
@@ -1228,9 +1266,11 @@ static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 
 static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 {
-	spin_lock(&sbi->cp_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 	__set_ckpt_flags(F2FS_CKPT(sbi), f);
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
@@ -1244,22 +1284,26 @@ static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f
 
 static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 {
-	spin_lock(&sbi->cp_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
 {
+	unsigned long flags;
+
 	set_sbi_flag(sbi, SBI_NEED_FSCK);
 
 	if (lock)
-		spin_lock(&sbi->cp_lock);
+		spin_lock_irqsave(&sbi->cp_lock, flags);
 	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
 	kfree(NM_I(sbi)->nat_bits);
 	NM_I(sbi)->nat_bits = NULL;
 	if (lock)
-		spin_unlock(&sbi->cp_lock);
+		spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
@@ -1275,6 +1319,11 @@ static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 	down_read(&sbi->cp_rwsem);
 }
 
+static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
+{
+	return down_read_trylock(&sbi->cp_rwsem);
+}
+
 static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 {
 	up_read(&sbi->cp_rwsem);
@@ -1324,17 +1373,14 @@ static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
 	return 0;
 }
 
-#define F2FS_DEFAULT_ALLOCATED_BLOCKS	1
-
 /*
  * Check whether the inode has blocks or not
  */
 static inline int F2FS_HAS_BLOCKS(struct inode *inode)
 {
-	if (F2FS_I(inode)->i_xattr_nid)
-		return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS + 1;
-	else
-		return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS;
+	block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;
+
+	return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
 }
 
 static inline bool f2fs_has_xattr_block(unsigned int ofs)
@@ -1342,16 +1388,23 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
 	return ofs == XATTR_NODE_OFFSET;
 }
 
-static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool);
-static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
+static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
+static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 				 struct inode *inode, blkcnt_t *count)
 {
-	blkcnt_t diff;
+	blkcnt_t diff = 0, release = 0;
+	block_t avail_user_block_count;
+	int ret;
+
+	ret = dquot_reserve_block(inode, *count);
+	if (ret)
+		return ret;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(sbi, FAULT_BLOCK)) {
 		f2fs_show_injection_info(FAULT_BLOCK);
-		return false;
+		release = *count;
+		goto enospc;
 	}
 #endif
 	/*
@@ -1362,32 +1415,42 @@ static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
 
 	spin_lock(&sbi->stat_lock);
 	sbi->total_valid_block_count += (block_t)(*count);
-	if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) {
-		diff = sbi->total_valid_block_count - sbi->user_block_count;
+	avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks;
+	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
+		diff = sbi->total_valid_block_count - avail_user_block_count;
 		*count -= diff;
-		sbi->total_valid_block_count = sbi->user_block_count;
+		release = diff;
+		sbi->total_valid_block_count = avail_user_block_count;
 		if (!*count) {
 			spin_unlock(&sbi->stat_lock);
 			percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
-			return false;
+			goto enospc;
 		}
 	}
 	spin_unlock(&sbi->stat_lock);
 
-	f2fs_i_blocks_write(inode, *count, true);
-	return true;
+	if (release)
+		dquot_release_reservation_block(inode, release);
+	f2fs_i_blocks_write(inode, *count, true, true);
+	return 0;
+
+enospc:
+	dquot_release_reservation_block(inode, release);
+	return -ENOSPC;
 }
 
 static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 						struct inode *inode,
-						blkcnt_t count)
+						block_t count)
 {
+	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;
+
 	spin_lock(&sbi->stat_lock);
 	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
-	f2fs_bug_on(sbi, inode->i_blocks < count);
+	f2fs_bug_on(sbi, inode->i_blocks < sectors);
 	sbi->total_valid_block_count -= (block_t)count;
 	spin_unlock(&sbi->stat_lock);
-	f2fs_i_blocks_write(inode, count, false);
+	f2fs_i_blocks_write(inode, count, false, true);
 }
 
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -1516,51 +1579,70 @@ static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
 	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
 }
 
-static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
-						struct inode *inode)
+static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
+					struct inode *inode, bool is_inode)
 {
 	block_t	valid_block_count;
 	unsigned int valid_node_count;
+	bool quota = inode && !is_inode;
+
+	if (quota) {
+		int ret = dquot_reserve_block(inode, 1);
+		if (ret)
+			return ret;
+	}
 
 	spin_lock(&sbi->stat_lock);
 
 	valid_block_count = sbi->total_valid_block_count + 1;
-	if (unlikely(valid_block_count > sbi->user_block_count)) {
+	if (unlikely(valid_block_count + sbi->reserved_blocks >
+						sbi->user_block_count)) {
 		spin_unlock(&sbi->stat_lock);
-		return false;
+		goto enospc;
 	}
 
 	valid_node_count = sbi->total_valid_node_count + 1;
 	if (unlikely(valid_node_count > sbi->total_node_count)) {
 		spin_unlock(&sbi->stat_lock);
-		return false;
+		goto enospc;
 	}
 
-	if (inode)
-		f2fs_i_blocks_write(inode, 1, true);
-
 	sbi->total_valid_node_count++;
 	sbi->total_valid_block_count++;
 	spin_unlock(&sbi->stat_lock);
 
+	if (inode) {
+		if (is_inode)
+			f2fs_mark_inode_dirty_sync(inode, true);
+		else
+			f2fs_i_blocks_write(inode, 1, true, true);
+	}
+
 	percpu_counter_inc(&sbi->alloc_valid_block_count);
-	return true;
+	return 0;
+
+enospc:
+	if (quota)
+		dquot_release_reservation_block(inode, 1);
+	return -ENOSPC;
 }
 
 static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
-						struct inode *inode)
+					struct inode *inode, bool is_inode)
 {
 	spin_lock(&sbi->stat_lock);
 
 	f2fs_bug_on(sbi, !sbi->total_valid_block_count);
 	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
-	f2fs_bug_on(sbi, !inode->i_blocks);
+	f2fs_bug_on(sbi, !is_inode && !inode->i_blocks);
 
-	f2fs_i_blocks_write(inode, 1, false);
 	sbi->total_valid_node_count--;
 	sbi->total_valid_block_count--;
 
 	spin_unlock(&sbi->stat_lock);
+
+	if (!is_inode)
+		f2fs_i_blocks_write(inode, 1, false, true);
 }
 
 static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
@@ -1835,13 +1917,21 @@ static inline void f2fs_i_links_write(struct inode *inode, bool inc)
 }
 
 static inline void f2fs_i_blocks_write(struct inode *inode,
-					blkcnt_t diff, bool add)
+					block_t diff, bool add, bool claim)
 {
 	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
 	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
 
-	inode->i_blocks = add ? inode->i_blocks + diff :
-				inode->i_blocks - diff;
+	/* add = 1, claim = 1 should be dquot_reserve_block in pair */
+	if (add) {
+		if (claim)
+			dquot_claim_block(inode, diff);
+		else
+			dquot_alloc_block_nofail(inode, diff);
+	} else {
+		dquot_free_block(inode, diff);
+	}
+
 	f2fs_mark_inode_dirty_sync(inode, true);
 	if (clean || recover)
 		set_inode_flag(inode, FI_AUTO_RECOVER);
@@ -2236,6 +2326,7 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
 void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
 bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
 void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new);
+void stop_discard_thread(struct f2fs_sb_info *sbi);
 void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
 void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 void release_discard_addrs(struct f2fs_sb_info *sbi);
@@ -2258,7 +2349,8 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 			bool recover_newaddr);
 void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 			block_t old_blkaddr, block_t *new_blkaddr,
-			struct f2fs_summary *sum, int type);
+			struct f2fs_summary *sum, int type,
+			struct f2fs_io_info *fio, bool add_list);
 void f2fs_wait_on_page_writeback(struct page *page,
 			enum page_type type, bool ordered);
 void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
@@ -2308,14 +2400,13 @@ void destroy_checkpoint_caches(void);
 /*
  * data.c
  */
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
-			int rw);
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
 				struct inode *inode, nid_t ino, pgoff_t idx,
-				enum page_type type, int rw);
-void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi);
+				enum page_type type);
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
 int f2fs_submit_page_bio(struct f2fs_io_info *fio);
-int f2fs_submit_page_mbio(struct f2fs_io_info *fio);
+int f2fs_submit_page_write(struct f2fs_io_info *fio);
 struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
 			block_t blk_addr, struct bio *bio);
 int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
@@ -2633,6 +2724,14 @@ int __init create_extent_cache(void);
 void destroy_extent_cache(void);
 
 /*
+ * sysfs.c
+ */
+int __init f2fs_register_sysfs(void);
+void f2fs_unregister_sysfs(void);
+int f2fs_init_sysfs(struct f2fs_sb_info *sbi);
+void f2fs_exit_sysfs(struct f2fs_sb_info *sbi);
+
+/*
  * crypto support
  */
 static inline bool f2fs_encrypted_inode(struct inode *inode)