Merge tag 'f2fs-for-4.15-rc1' of git://git.kernel.org/pub/scm/linux/k…

…ernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we introduce sysfile-based quota support which is
  required for Android by default. In addition, we allow that users are
  able to reserve some blocks in runtime to mitigate performance drops
  in low free space.

  Enhancements:
   - assign proper data segments according to write_hints given by user
   - issue cache_flush on dirty devices only among multiple devices
   - exploit cp_error flag and add more faults to enhance fault
     injection test
   - conduct more readaheads during f2fs_readdir
   - add a range for discard commands

  Bug fixes:
   - fix zero stat->st_blocks when inline_data is set
   - drop crypto key and free stale memory pointer while evict_inode is
     failing
   - fix some corner cases in free space and segment management
   - fix wrong last_disk_size

  This series includes lots of clean-ups and code enhancement in terms
  of xattr operations, discard/flush command control. In addition, it
  adds versatile debugfs entries to monitor f2fs status"

* tag 'f2fs-for-4.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (75 commits)
  f2fs: deny accessing encryption policy if encryption is off
  f2fs: inject fault in inc_valid_node_count
  f2fs: fix to clear FI_NO_PREALLOC
  f2fs: expose quota information in debugfs
  f2fs: separate nat entry mem alloc from nat_tree_lock
  f2fs: validate before set/clear free nat bitmap
  f2fs: avoid opened loop codes in __add_ino_entry
  f2fs: apply write hints to select the type of segments for buffered write
  f2fs: introduce scan_curseg_cache for cleanup
  f2fs: optimize the way of traversing free_nid_bitmap
  f2fs: keep scanning until enough free nids are acquired
  f2fs: trace checkpoint reason in fsync()
  f2fs: keep isize once block is reserved cross EOF
  f2fs: avoid race in between GC and block exchange
  f2fs: save a multiplication for last_nid calculation
  f2fs: fix summary info corruption
  f2fs: remove dead code in update_meta_page
  f2fs: remove unneeded semicolon
  f2fs: don't bother with inode->i_version
  f2fs: check curseg space before foreground GC
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -51,6 +51,18 @@ Description:
 		 Controls the dirty page count condition for the in-place-update
 		 policies.
 
+What:		/sys/fs/f2fs/<disk>/min_hot_blocks
+Date:		March 2017
+Contact:	"Jaegeuk Kim" <[email protected]>
+Description:
+		 Controls the dirty page count condition for redefining hot data.
+
+What:		/sys/fs/f2fs/<disk>/min_ssr_sections
+Date:		October 2017
+Contact:	"Chao Yu" <[email protected]>
+Description:
+		 Controls the fee section threshold to trigger SSR allocation.
+
 What:		/sys/fs/f2fs/<disk>/max_small_discards
 Date:		November 2013
 Contact:	"Jaegeuk Kim" <[email protected]>
@@ -102,6 +114,12 @@ Contact:	"Jaegeuk Kim" <[email protected]>
 Description:
 		 Controls the idle timing.
 
+What:		/sys/fs/f2fs/<disk>/iostat_enable
+Date:		August 2017
+Contact:	"Chao Yu" <[email protected]>
+Description:
+		 Controls to enable/disable IO stat.
+
 What:		/sys/fs/f2fs/<disk>/ra_nid_pages
 Date:		October 2015
 Contact:	"Chao Yu" <[email protected]>
@@ -122,6 +140,12 @@ Contact:	"Shuoran Liu" <[email protected]>
 Description:
 		 Shows total written kbytes issued to disk.
 
+What:		/sys/fs/f2fs/<disk>/feature
+Date:		July 2017
+Contact:	"Jaegeuk Kim" <[email protected]>
+Description:
+		 Shows all enabled features in current device.
+
 What:		/sys/fs/f2fs/<disk>/inject_rate
 Date:		May 2016
 Contact:	"Sheng Yong" <[email protected]>
@@ -138,7 +162,18 @@ What:		/sys/fs/f2fs/<disk>/reserved_blocks
 Date:		June 2017
 Contact:	"Chao Yu" <[email protected]>
 Description:
-		 Controls current reserved blocks in system.
+		 Controls target reserved blocks in system, the threshold
+		 is soft, it could exceed current available user space.
+
+What:		/sys/fs/f2fs/<disk>/current_reserved_blocks
+Date:		October 2017
+Contact:	"Yunlong Song" <[email protected]>
+Contact:	"Chao Yu" <[email protected]>
+Description:
+		 Shows current reserved blocks in system, it may be temporarily
+		 smaller than target_reserved_blocks, but will gradually
+		 increase to target_reserved_blocks when more free blocks are
+		 freed by user later.
 
 What:		/sys/fs/f2fs/<disk>/gc_urgent
 Date:		August 2017

fs/f2fs/acl.c

@@ -250,6 +250,9 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 
 int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		return -EIO;
+
 	return __f2fs_set_acl(inode, type, acl, NULL);
 }
 

fs/f2fs/checkpoint.c

@@ -29,7 +29,6 @@ struct kmem_cache *inode_entry_slab;
 void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
 {
 	set_ckpt_flags(sbi, CP_ERROR_FLAG);
-	sbi->sb->s_flags |= MS_RDONLY;
 	if (!end_io)
 		f2fs_flush_merged_writes(sbi);
 }
@@ -398,31 +397,34 @@ const struct address_space_operations f2fs_meta_aops = {
 #endif
 };
 
-static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
+static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino,
+						unsigned int devidx, int type)
 {
 	struct inode_management *im = &sbi->im[type];
 	struct ino_entry *e, *tmp;
 
 	tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
-retry:
+
 	radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
 
 	spin_lock(&im->ino_lock);
 	e = radix_tree_lookup(&im->ino_root, ino);
 	if (!e) {
 		e = tmp;
-		if (radix_tree_insert(&im->ino_root, ino, e)) {
-			spin_unlock(&im->ino_lock);
-			radix_tree_preload_end();
-			goto retry;
-		}
+		if (unlikely(radix_tree_insert(&im->ino_root, ino, e)))
+			f2fs_bug_on(sbi, 1);
+
 		memset(e, 0, sizeof(struct ino_entry));
 		e->ino = ino;
 
 		list_add_tail(&e->list, &im->ino_list);
 		if (type != ORPHAN_INO)
 			im->ino_num++;
 	}
+
+	if (type == FLUSH_INO)
+		f2fs_set_bit(devidx, (char *)&e->dirty_device);
+
 	spin_unlock(&im->ino_lock);
 	radix_tree_preload_end();
 
@@ -451,7 +453,7 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 {
 	/* add new dirty ino entry into list */
-	__add_ino_entry(sbi, ino, type);
+	__add_ino_entry(sbi, ino, 0, type);
 }
 
 void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -477,7 +479,7 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
 	struct ino_entry *e, *tmp;
 	int i;
 
-	for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) {
+	for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) {
 		struct inode_management *im = &sbi->im[i];
 
 		spin_lock(&im->ino_lock);
@@ -491,6 +493,27 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
 	}
 }
 
+void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+					unsigned int devidx, int type)
+{
+	__add_ino_entry(sbi, ino, devidx, type);
+}
+
+bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
+					unsigned int devidx, int type)
+{
+	struct inode_management *im = &sbi->im[type];
+	struct ino_entry *e;
+	bool is_dirty = false;
+
+	spin_lock(&im->ino_lock);
+	e = radix_tree_lookup(&im->ino_root, ino);
+	if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device))
+		is_dirty = true;
+	spin_unlock(&im->ino_lock);
+	return is_dirty;
+}
+
 int acquire_orphan_inode(struct f2fs_sb_info *sbi)
 {
 	struct inode_management *im = &sbi->im[ORPHAN_INO];
@@ -527,7 +550,7 @@ void release_orphan_inode(struct f2fs_sb_info *sbi)
 void add_orphan_inode(struct inode *inode)
 {
 	/* add new orphan ino entry into list */
-	__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO);
+	__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO);
 	update_inode_page(inode);
 }
 
@@ -551,7 +574,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 		return err;
 	}
 
-	__add_ino_entry(sbi, ino, ORPHAN_INO);
+	__add_ino_entry(sbi, ino, 0, ORPHAN_INO);
 
 	inode = f2fs_iget_retry(sbi->sb, ino);
 	if (IS_ERR(inode)) {
@@ -587,6 +610,9 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	block_t start_blk, orphan_blocks, i, j;
 	unsigned int s_flags = sbi->sb->s_flags;
 	int err = 0;
+#ifdef CONFIG_QUOTA
+	int quota_enabled;
+#endif
 
 	if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
 		return 0;
@@ -599,8 +625,9 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 #ifdef CONFIG_QUOTA
 	/* Needed for iput() to work correctly and not trash data */
 	sbi->sb->s_flags |= MS_ACTIVE;
+
 	/* Turn on quotas so that they are updated correctly */
-	f2fs_enable_quota_files(sbi);
+	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY);
 #endif
 
 	start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
@@ -628,7 +655,8 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 out:
 #ifdef CONFIG_QUOTA
 	/* Turn quotas off */
-	f2fs_quota_off_umount(sbi->sb);
+	if (quota_enabled)
+		f2fs_quota_off_umount(sbi->sb);
 #endif
 	sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
 
@@ -983,7 +1011,7 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 				update_inode_page(inode);
 			iput(inode);
 		}
-	};
+	}
 	return 0;
 }
 
@@ -1143,6 +1171,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct super_block *sb = sbi->sb;
 	struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
 	u64 kbytes_written;
+	int err;
 
 	/* Flush all the NAT/SIT pages */
 	while (get_pages(sbi, F2FS_DIRTY_META)) {
@@ -1236,6 +1265,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
+	/* flush all device cache */
+	err = f2fs_flush_device_cache(sbi);
+	if (err)
+		return err;
+
 	/* write out checkpoint buffer at block 0 */
 	update_meta_page(sbi, ckpt, start_blk++);
 

fs/f2fs/data.c

@@ -173,7 +173,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 {
 	struct bio *bio;
 
-	bio = f2fs_bio_alloc(npages);
+	bio = f2fs_bio_alloc(sbi, npages, true);
 
 	f2fs_target_device(sbi, blk_addr, bio);
 	bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
@@ -418,8 +418,8 @@ int f2fs_submit_page_write(struct f2fs_io_info *fio)
 
 	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
 
-	/* set submitted = 1 as a return value */
-	fio->submitted = 1;
+	/* set submitted = true as a return value */
+	fio->submitted = true;
 
 	inc_page_count(sbi, WB_DATA_TYPE(bio_page));
 
@@ -473,7 +473,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 		f2fs_wait_on_block_writeback(sbi, blkaddr);
 	}
 
-	bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
 	if (!bio) {
 		if (ctx)
 			fscrypt_release_ctx(ctx);
@@ -833,6 +833,13 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	struct f2fs_map_blocks map;
 	int err = 0;
 
+	/* convert inline data for Direct I/O*/
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
+	}
+
 	if (is_inode_flag_set(inode, FI_NO_PREALLOC))
 		return 0;
 
@@ -845,15 +852,11 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 
 	map.m_next_pgofs = NULL;
 
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		err = f2fs_convert_inline_inode(inode);
-		if (err)
-			return err;
+	if (iocb->ki_flags & IOCB_DIRECT)
 		return f2fs_map_blocks(inode, &map, 1,
 			__force_buffered_io(inode, WRITE) ?
 				F2FS_GET_BLOCK_PRE_AIO :
 				F2FS_GET_BLOCK_PRE_DIO);
-	}
 	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
 		err = f2fs_convert_inline_inode(inode);
 		if (err)
@@ -1334,7 +1337,7 @@ static int f2fs_read_data_pages(struct file *file,
 			struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages)
 {
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = mapping->host;
 	struct page *page = list_last_entry(pages, struct page, lru);
 
 	trace_f2fs_readpages(inode, page, nr_pages);
@@ -1495,6 +1498,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 	int err = 0;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
+		.ino = inode->i_ino,
 		.type = DATA,
 		.op = REQ_OP_WRITE,
 		.op_flags = wbc_to_write_flags(wbc),
@@ -1566,8 +1570,11 @@ static int __write_data_page(struct page *page, bool *submitted,
 			err = do_write_data_page(&fio);
 		}
 	}
+
+	down_write(&F2FS_I(inode)->i_sem);
 	if (F2FS_I(inode)->last_disk_size < psize)
 		F2FS_I(inode)->last_disk_size = psize;
+	up_write(&F2FS_I(inode)->i_sem);
 
 done:
 	if (err && err != -ENOENT)
@@ -1932,6 +1939,12 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 
 	trace_f2fs_write_begin(inode, pos, len, flags);
 
+	if (f2fs_is_atomic_file(inode) &&
+			!available_free_memory(sbi, INMEM_PAGES)) {
+		err = -ENOMEM;
+		goto fail;
+	}
+
 	/*
 	 * We should check this at this moment to avoid deadlock on inode page
 	 * and #0 page. The locking rule for inline_data conversion should be:
@@ -1947,7 +1960,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	 * Do not use grab_cache_page_write_begin() to avoid deadlock due to
 	 * wait_for_stable_page. Will wait that below with our IO control.
 	 */
-	page = pagecache_get_page(mapping, index,
+	page = f2fs_pagecache_get_page(mapping, index,
 				FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
 	if (!page) {
 		err = -ENOMEM;
@@ -2009,6 +2022,8 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 fail:
 	f2fs_put_page(page, 1);
 	f2fs_write_failed(mapping, pos + len);
+	if (f2fs_is_atomic_file(inode))
+		drop_inmem_pages_all(sbi);
 	return err;
 }