Merge tag 'f2fs-for-5.1' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "We've continued mainly to fix bugs in this round, as f2fs has been
  shipped in more devices. Especially, we've focused on stabilizing
  checkpoint=disable feature, and provided some interfaces for QA.

  Enhancements:
   - expose FS_NOCOW_FL for pin_file
   - run discard jobs at unmount time with timeout
   - tune discarding thread to avoid idling which consumes power
   - some checking codes to address vulnerabilities
   - give random value to i_generation
   - shutdown with more flags for QA

  Bug fixes:
   - clean up stale objects when mount is failed along with
     checkpoint=disable
   - fix system being stuck due to wrong count by atomic writes
   - handle some corrupted disk cases
   - fix a deadlock in f2fs_read_inline_dir

  We've also added some minor build error fixes and clean-up patches"

* tag 'f2fs-for-5.1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (53 commits)
  f2fs: set pin_file under CAP_SYS_ADMIN
  f2fs: fix to avoid deadlock in f2fs_read_inline_dir()
  f2fs: fix to adapt small inline xattr space in __find_inline_xattr()
  f2fs: fix to do sanity check with inode.i_inline_xattr_size
  f2fs: give some messages for inline_xattr_size
  f2fs: don't trigger read IO for beyond EOF page
  f2fs: fix to add refcount once page is tagged PG_private
  f2fs: remove wrong comment in f2fs_invalidate_page()
  f2fs: fix to use kvfree instead of kzfree
  f2fs: print more parameters in trace_f2fs_map_blocks
  f2fs: trace f2fs_ioc_shutdown
  f2fs: fix to avoid deadlock of atomic file operations
  f2fs: fix to dirty inode for i_mode recovery
  f2fs: give random value to i_generation
  f2fs: no need to take page lock in readdir
  f2fs: fix to update iostat correctly in IPU path
  f2fs: fix encrypted page memory leak
  f2fs: make fault injection covering __submit_flush_wait()
  f2fs: fix to retry fill_super only if recovery failed
  f2fs: silence VM_WARN_ON_ONCE in mempool_alloc
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -86,6 +86,13 @@ Description:
 		The unit size is one block, now only support configuring in range
 		of [1, 512].
 
+What:          /sys/fs/f2fs/<disk>/umount_discard_timeout
+Date:          January 2019
+Contact:       "Jaegeuk Kim" <[email protected]>
+Description:
+		Set timeout to issue discard commands during umount.
+		Default: 5 secs
+
 What:		/sys/fs/f2fs/<disk>/max_victim_search
 Date:		January 2014
 Contact:	"Jaegeuk Kim" <[email protected]>

Documentation/filesystems/f2fs.txt

@@ -126,6 +126,8 @@ disable_ext_identify   Disable the extension list configured by mkfs, so f2fs
                        does not aware of cold files such as media files.
 inline_xattr           Enable the inline xattrs feature.
 noinline_xattr         Disable the inline xattrs feature.
+inline_xattr_size=%u   Support configuring inline xattr size, it depends on
+		       flexible inline xattr feature.
 inline_data            Enable the inline data feature: New created small(<~3.4k)
                        files can be written into inode block.
 inline_dentry          Enable the inline dir feature: data in new created

fs/f2fs/checkpoint.c

@@ -306,8 +306,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 		goto skip_write;
 
 	/* collect a number of dirty meta pages and write together */
-	if (wbc->for_kupdate ||
-		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
+	if (wbc->sync_mode != WB_SYNC_ALL &&
+			get_pages(sbi, F2FS_DIRTY_META) <
+					nr_pages_to_skip(sbi, META))
 		goto skip_write;
 
 	/* if locked failed, cp will flush dirty pages instead */
@@ -405,7 +406,7 @@ 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_set_page_private(page, 0);
 		f2fs_trace_pid(page);
 		return 1;
 	}
@@ -956,7 +957,7 @@ void f2fs_update_dirty_page(struct inode *inode, struct page *page)
 	inode_inc_dirty_pages(inode);
 	spin_unlock(&sbi->inode_lock[type]);
 
-	SetPagePrivate(page);
+	f2fs_set_page_private(page, 0);
 	f2fs_trace_pid(page);
 }
 
@@ -1259,10 +1260,17 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	else
 		__clear_ckpt_flags(ckpt, CP_DISABLED_FLAG);
 
+	if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK))
+		__set_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG);
+	else
+		__clear_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG);
+
 	if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH))
 		__set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
-	else
-		__clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
+	/*
+	 * TODO: we count on fsck.f2fs to clear this flag until we figure out
+	 * missing cases which clear it incorrectly.
+	 */
 
 	if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR))
 		__set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);

fs/f2fs/data.c

@@ -301,9 +301,10 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
 		for (; start < F2FS_IO_SIZE(sbi); start++) {
 			struct page *page =
 				mempool_alloc(sbi->write_io_dummy,
-					GFP_NOIO | __GFP_ZERO | __GFP_NOFAIL);
+					      GFP_NOIO | __GFP_NOFAIL);
 			f2fs_bug_on(sbi, !page);
 
+			zero_user_segment(page, 0, PAGE_SIZE);
 			SetPagePrivate(page);
 			set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE);
 			lock_page(page);
@@ -1553,6 +1554,9 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 		if (last_block > last_block_in_file)
 			last_block = last_block_in_file;
 
+		/* just zeroing out page which is beyond EOF */
+		if (block_in_file >= last_block)
+			goto zero_out;
 		/*
 		 * Map blocks using the previous result first.
 		 */
@@ -1565,16 +1569,11 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 		 * Then do more f2fs_map_blocks() calls until we are
 		 * done with this page.
 		 */
-		map.m_flags = 0;
-
-		if (block_in_file < last_block) {
-			map.m_lblk = block_in_file;
-			map.m_len = last_block - block_in_file;
+		map.m_lblk = block_in_file;
+		map.m_len = last_block - block_in_file;
 
-			if (f2fs_map_blocks(inode, &map, 0,
-						F2FS_GET_BLOCK_DEFAULT))
-				goto set_error_page;
-		}
+		if (f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT))
+			goto set_error_page;
 got_it:
 		if ((map.m_flags & F2FS_MAP_MAPPED)) {
 			block_nr = map.m_pblk + block_in_file - map.m_lblk;
@@ -1589,6 +1588,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 								DATA_GENERIC))
 				goto set_error_page;
 		} else {
+zero_out:
 			zero_user_segment(page, 0, PAGE_SIZE);
 			if (!PageUptodate(page))
 				SetPageUptodate(page);
@@ -1863,8 +1863,13 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 		if (fio->need_lock == LOCK_REQ)
 			f2fs_unlock_op(fio->sbi);
 		err = f2fs_inplace_write_data(fio);
-		if (err && PageWriteback(page))
-			end_page_writeback(page);
+		if (err) {
+			if (f2fs_encrypted_file(inode))
+				fscrypt_pullback_bio_page(&fio->encrypted_page,
+									true);
+			if (PageWriteback(page))
+				end_page_writeback(page);
+		}
 		trace_f2fs_do_write_data_page(fio->page, IPU);
 		set_inode_flag(inode, FI_UPDATE_WRITE);
 		return err;
@@ -2315,7 +2320,8 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
 		down_write(&F2FS_I(inode)->i_mmap_sem);
 
 		truncate_pagecache(inode, i_size);
-		f2fs_truncate_blocks(inode, i_size, true, true);
+		if (!IS_NOQUOTA(inode))
+			f2fs_truncate_blocks(inode, i_size, true);
 
 		up_write(&F2FS_I(inode)->i_mmap_sem);
 		up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
@@ -2585,14 +2591,11 @@ static void f2fs_dio_submit_bio(struct bio *bio, struct inode *inode,
 {
 	struct f2fs_private_dio *dio;
 	bool write = (bio_op(bio) == REQ_OP_WRITE);
-	int err;
 
 	dio = f2fs_kzalloc(F2FS_I_SB(inode),
 			sizeof(struct f2fs_private_dio), GFP_NOFS);
-	if (!dio) {
-		err = -ENOMEM;
+	if (!dio)
 		goto out;
-	}
 
 	dio->inode = inode;
 	dio->orig_end_io = bio->bi_end_io;
@@ -2710,12 +2713,10 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
 
 	clear_cold_data(page);
 
-	/* This is atomic written page, keep Private */
 	if (IS_ATOMIC_WRITTEN_PAGE(page))
 		return f2fs_drop_inmem_page(inode, page);
 
-	set_page_private(page, 0);
-	ClearPagePrivate(page);
+	f2fs_clear_page_private(page);
 }
 
 int f2fs_release_page(struct page *page, gfp_t wait)
@@ -2729,8 +2730,7 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 		return 0;
 
 	clear_cold_data(page);
-	set_page_private(page, 0);
-	ClearPagePrivate(page);
+	f2fs_clear_page_private(page);
 	return 1;
 }
 
@@ -2798,12 +2798,8 @@ int f2fs_migrate_page(struct address_space *mapping,
 			return -EAGAIN;
 	}
 
-	/*
-	 * A reference is expected if PagePrivate set when move mapping,
-	 * however F2FS breaks this for maintaining dirty page counts when
-	 * truncating pages. So here adjusting the 'extra_count' make it work.
-	 */
-	extra_count = (atomic_written ? 1 : 0) - page_has_private(page);
+	/* one extra reference was held for atomic_write page */
+	extra_count = atomic_written ? 1 : 0;
 	rc = migrate_page_move_mapping(mapping, newpage,
 				page, mode, extra_count);
 	if (rc != MIGRATEPAGE_SUCCESS) {
@@ -2824,9 +2820,10 @@ int f2fs_migrate_page(struct address_space *mapping,
 		get_page(newpage);
 	}
 
-	if (PagePrivate(page))
-		SetPagePrivate(newpage);
-	set_page_private(newpage, page_private(page));
+	if (PagePrivate(page)) {
+		f2fs_set_page_private(newpage, page_private(page));
+		f2fs_clear_page_private(page);
+	}
 
 	if (mode != MIGRATE_SYNC_NO_COPY)
 		migrate_page_copy(newpage, page);

fs/f2fs/debug.c

@@ -96,8 +96,10 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->free_secs = free_sections(sbi);
 	si->prefree_count = prefree_segments(sbi);
 	si->dirty_count = dirty_segments(sbi);
-	si->node_pages = NODE_MAPPING(sbi)->nrpages;
-	si->meta_pages = META_MAPPING(sbi)->nrpages;
+	if (sbi->node_inode)
+		si->node_pages = NODE_MAPPING(sbi)->nrpages;
+	if (sbi->meta_inode)
+		si->meta_pages = META_MAPPING(sbi)->nrpages;
 	si->nats = NM_I(sbi)->nat_cnt;
 	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
 	si->sits = MAIN_SEGS(sbi);
@@ -175,7 +177,6 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
 static void update_mem_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = F2FS_STAT(sbi);
-	unsigned npages;
 	int i;
 
 	if (si->base_mem)
@@ -258,10 +259,14 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 						sizeof(struct extent_node);
 
 	si->page_mem = 0;
-	npages = NODE_MAPPING(sbi)->nrpages;
-	si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
-	npages = META_MAPPING(sbi)->nrpages;
-	si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+	if (sbi->node_inode) {
+		unsigned npages = NODE_MAPPING(sbi)->nrpages;
+		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+	}
+	if (sbi->meta_inode) {
+		unsigned npages = META_MAPPING(sbi)->nrpages;
+		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+	}
 }
 
 static int stat_show(struct seq_file *s, void *v)

fs/f2fs/dir.c

@@ -728,7 +728,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 		!f2fs_truncate_hole(dir, page->index, page->index + 1)) {
 		f2fs_clear_page_cache_dirty_tag(page);
 		clear_page_dirty_for_io(page);
-		ClearPagePrivate(page);
+		f2fs_clear_page_private(page);
 		ClearPageUptodate(page);
 		clear_cold_data(page);
 		inode_dec_dirty_pages(dir);
@@ -800,6 +800,10 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 		if (de->name_len == 0) {
 			bit_pos++;
 			ctx->pos = start_pos + bit_pos;
+			printk_ratelimited(
+				"%s, invalid namelen(0), ino:%u, run fsck to fix.",
+				KERN_WARNING, le32_to_cpu(de->ino));
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
 			continue;
 		}
 
@@ -810,7 +814,8 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 
 		/* check memory boundary before moving forward */
 		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
-		if (unlikely(bit_pos > d->max)) {
+		if (unlikely(bit_pos > d->max ||
+				le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) {
 			f2fs_msg(sbi->sb, KERN_WARNING,
 				"%s: corrupted namelen=%d, run fsck to fix.",
 				__func__, le16_to_cpu(de->name_len));
@@ -891,7 +896,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 			page_cache_sync_readahead(inode->i_mapping, ra, file, n,
 				min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
 
-		dentry_page = f2fs_get_lock_data_page(inode, n, false);
+		dentry_page = f2fs_find_data_page(inode, n);
 		if (IS_ERR(dentry_page)) {
 			err = PTR_ERR(dentry_page);
 			if (err == -ENOENT) {
@@ -909,11 +914,11 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		err = f2fs_fill_dentries(ctx, &d,
 				n * NR_DENTRY_IN_BLOCK, &fstr);
 		if (err) {
-			f2fs_put_page(dentry_page, 1);
+			f2fs_put_page(dentry_page, 0);
 			break;
 		}
 
-		f2fs_put_page(dentry_page, 1);
+		f2fs_put_page(dentry_page, 0);
 	}
 out_free:
 	fscrypt_fname_free_buffer(&fstr);

fs/f2fs/extent_cache.c

@@ -506,7 +506,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode,
 	unsigned int end = fofs + len;
 	unsigned int pos = (unsigned int)fofs;
 	bool updated = false;
-	bool leftmost;
+	bool leftmost = false;
 
 	if (!et)
 		return;