Merge tag 'f2fs-for-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "Another round of various bug fixes came in. Damien improved SMR drive
  support a bit, and Chao replaced BUG_ON() with reporting errors to
  user since we've not hit from users but did hit from crafted images.
  We've found a disk layout bug in large_nat_bits feature which supports
  very large NAT entries enabled at mkfs. If the feature is enabled, it
  will give a notice to run fsck to correct the on-disk layout.

  Enhancements:
   - reduce memory consumption for SMR drive
   - better discard handling for multiple partitions
   - tracepoints for f2fs_file_write_iter/f2fs_filemap_fault
   - allow to change CP_CHKSUM_OFFSET
   - detect wrong layout of large_nat_bitmap feature
   - enhance checking valid data indices

  Bug fixes:
   - Multiple partition support for SMR drive
   - deadlock problem in f2fs_balance_fs_bg
   - add boundary checks to fix abnormal behaviors on fuzzed images
   - inline_xattr space calculations
   - replace f2fs_bug_on with errors

  In addition, this series contains various memory boundary check and
  sanity check of on-disk consistency"

* tag 'f2fs-for-v5.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (40 commits)
  f2fs: fix to avoid accessing xattr across the boundary
  f2fs: fix to avoid potential race on sbi->unusable_block_count access/update
  f2fs: add tracepoint for f2fs_filemap_fault()
  f2fs: introduce DATA_GENERIC_ENHANCE
  f2fs: fix to handle error in f2fs_disable_checkpoint()
  f2fs: remove redundant check in f2fs_file_write_iter()
  f2fs: fix to be aware of readonly device in write_checkpoint()
  f2fs: fix to skip recovery on readonly device
  f2fs: fix to consider multiple device for readonly check
  f2fs: relocate chksum_offset for large_nat_bitmap feature
  f2fs: allow unfixed f2fs_checkpoint.checksum_offset
  f2fs: Replace spaces with tab
  f2fs: insert space before the open parenthesis '('
  f2fs: allow address pointer number of dnode aligning to specified size
  f2fs: introduce f2fs_read_single_page() for cleanup
  f2fs: mark is_extension_exist() inline
  f2fs: fix to set FI_UPDATE_WRITE correctly
  f2fs: fix to avoid panic in f2fs_inplace_write_data()
  f2fs: fix to do sanity check on valid block count of segment
  f2fs: fix to do sanity check on valid node/block count
  ...

18 files changed, 688 insertions, 302 deletions

diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 63e599524085..217b290ae3a5 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -285,7 +285,7 @@ static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
 	/* assert(atomic_read(acl->a_refcount) == 1); */
 
 	FOREACH_ACL_ENTRY(pa, acl, pe) {
-		switch(pa->e_tag) {
+		switch (pa->e_tag) {
 		case ACL_USER_OBJ:
 			pa->e_perm &= (mode >> 6) | ~S_IRWXO;
 			mode &= (pa->e_perm << 6) | ~S_IRWXU;
@@ -326,7 +326,7 @@ static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
 	}
 
 	*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
-        return not_equiv;
+	return not_equiv;
 }
 
 static int f2fs_acl_create(struct inode *dir, umode_t *mode,
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index a98e1b02279e..ed70b68b2b38 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -66,7 +66,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 		.old_blkaddr = index,
 		.new_blkaddr = index,
 		.encrypted_page = NULL,
-		.is_meta = is_meta,
+		.is_por = !is_meta,
 	};
 	int err;
 
@@ -130,6 +130,30 @@ struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	return __get_meta_page(sbi, index, false);
 }
 
+static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
+							int type)
+{
+	struct seg_entry *se;
+	unsigned int segno, offset;
+	bool exist;
+
+	if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ)
+		return true;
+
+	segno = GET_SEGNO(sbi, blkaddr);
+	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+	se = get_seg_entry(sbi, segno);
+
+	exist = f2fs_test_bit(offset, se->cur_valid_map);
+	if (!exist && type == DATA_GENERIC_ENHANCE) {
+		f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
+			"blkaddr:%u, sit bitmap:%d", blkaddr, exist);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		WARN_ON(1);
+	}
+	return exist;
+}
+
 bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type)
 {
@@ -151,15 +175,22 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 			return false;
 		break;
 	case META_POR:
+		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
+			blkaddr < MAIN_BLKADDR(sbi)))
+			return false;
+		break;
 	case DATA_GENERIC:
+	case DATA_GENERIC_ENHANCE:
+	case DATA_GENERIC_ENHANCE_READ:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
-			blkaddr < MAIN_BLKADDR(sbi))) {
-			if (type == DATA_GENERIC) {
-				f2fs_msg(sbi->sb, KERN_WARNING,
-					"access invalid blkaddr:%u", blkaddr);
-				WARN_ON(1);
-			}
+				blkaddr < MAIN_BLKADDR(sbi))) {
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"access invalid blkaddr:%u", blkaddr);
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			WARN_ON(1);
 			return false;
+		} else {
+			return __is_bitmap_valid(sbi, blkaddr, type);
 		}
 		break;
 	case META_GENERIC:
@@ -189,7 +220,7 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
 		.encrypted_page = NULL,
 		.in_list = false,
-		.is_meta = (type != META_POR),
+		.is_por = (type == META_POR),
 	};
 	struct blk_plug plug;
 
@@ -644,6 +675,12 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
 		return 0;
 
+	if (bdev_read_only(sbi->sb->s_bdev)) {
+		f2fs_msg(sbi->sb, KERN_INFO, "write access "
+			"unavailable, skipping orphan cleanup");
+		return 0;
+	}
+
 	if (s_flags & SB_RDONLY) {
 		f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
 		sbi->sb->s_flags &= ~SB_RDONLY;
@@ -758,13 +795,27 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 	}
 }
 
+static __u32 f2fs_checkpoint_chksum(struct f2fs_sb_info *sbi,
+						struct f2fs_checkpoint *ckpt)
+{
+	unsigned int chksum_ofs = le32_to_cpu(ckpt->checksum_offset);
+	__u32 chksum;
+
+	chksum = f2fs_crc32(sbi, ckpt, chksum_ofs);
+	if (chksum_ofs < CP_CHKSUM_OFFSET) {
+		chksum_ofs += sizeof(chksum);
+		chksum = f2fs_chksum(sbi, chksum, (__u8 *)ckpt + chksum_ofs,
+						F2FS_BLKSIZE - chksum_ofs);
+	}
+	return chksum;
+}
+
 static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
 		struct f2fs_checkpoint **cp_block, struct page **cp_page,
 		unsigned long long *version)
 {
-	unsigned long blk_size = sbi->blocksize;
 	size_t crc_offset = 0;
-	__u32 crc = 0;
+	__u32 crc;
 
 	*cp_page = f2fs_get_meta_page(sbi, cp_addr);
 	if (IS_ERR(*cp_page))
@@ -773,15 +824,27 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
 	*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
 
 	crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
-	if (crc_offset > (blk_size - sizeof(__le32))) {
+	if (crc_offset < CP_MIN_CHKSUM_OFFSET ||
+			crc_offset > CP_CHKSUM_OFFSET) {
 		f2fs_put_page(*cp_page, 1);
 		f2fs_msg(sbi->sb, KERN_WARNING,
 			"invalid crc_offset: %zu", crc_offset);
 		return -EINVAL;
 	}
 
-	crc = cur_cp_crc(*cp_block);
-	if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
+	if (__is_set_ckpt_flags(*cp_block, CP_LARGE_NAT_BITMAP_FLAG)) {
+		if (crc_offset != CP_MIN_CHKSUM_OFFSET) {
+			f2fs_put_page(*cp_page, 1);
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"layout of large_nat_bitmap is deprecated, "
+				"run fsck to repair, chksum_offset: %zu",
+				crc_offset);
+			return -EINVAL;
+		}
+	}
+
+	crc = f2fs_checkpoint_chksum(sbi, *cp_block);
+	if (crc != cur_cp_crc(*cp_block)) {
 		f2fs_put_page(*cp_page, 1);
 		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
 		return -EINVAL;
@@ -1009,13 +1072,11 @@ retry:
 	if (inode) {
 		unsigned long cur_ino = inode->i_ino;
 
-		if (is_dir)
-			F2FS_I(inode)->cp_task = current;
+		F2FS_I(inode)->cp_task = current;
 
 		filemap_fdatawrite(inode->i_mapping);
 
-		if (is_dir)
-			F2FS_I(inode)->cp_task = NULL;
+		F2FS_I(inode)->cp_task = NULL;
 
 		iput(inode);
 		/* We need to give cpu to another writers. */
@@ -1391,7 +1452,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
 
-	crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset));
+	crc32 = f2fs_checkpoint_chksum(sbi, ckpt);
 	*((__le32 *)((unsigned char *)ckpt +
 				le32_to_cpu(ckpt->checksum_offset)))
 				= cpu_to_le32(crc32);
@@ -1475,7 +1536,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	clear_sbi_flag(sbi, SBI_IS_DIRTY);
 	clear_sbi_flag(sbi, SBI_NEED_CP);
 	clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
+
+	spin_lock(&sbi->stat_lock);
 	sbi->unusable_block_count = 0;
+	spin_unlock(&sbi->stat_lock);
+
 	__set_cp_next_pack(sbi);
 
 	/*
@@ -1500,6 +1565,9 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	unsigned long long ckpt_ver;
 	int err = 0;
 
+	if (f2fs_readonly(sbi->sb) || f2fs_hw_is_readonly(sbi))
+		return -EROFS;
+
 	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
 		if (cpc->reason != CP_PAUSE)
 			return 0;
@@ -1516,10 +1584,6 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		err = -EIO;
 		goto out;
 	}
-	if (f2fs_readonly(sbi->sb)) {
-		err = -EROFS;
-		goto out;
-	}
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
 
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 64040e998439..eda4181d2092 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -218,12 +218,14 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
 	struct block_device *bdev = sbi->sb->s_bdev;
 	int i;
 
-	for (i = 0; i < sbi->s_ndevs; i++) {
-		if (FDEV(i).start_blk <= blk_addr &&
-					FDEV(i).end_blk >= blk_addr) {
-			blk_addr -= FDEV(i).start_blk;
-			bdev = FDEV(i).bdev;
-			break;
+	if (f2fs_is_multi_device(sbi)) {
+		for (i = 0; i < sbi->s_ndevs; i++) {
+			if (FDEV(i).start_blk <= blk_addr &&
+			    FDEV(i).end_blk >= blk_addr) {
+				blk_addr -= FDEV(i).start_blk;
+				bdev = FDEV(i).bdev;
+				break;
+			}
 		}
 	}
 	if (bio) {
@@ -237,6 +239,9 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
 	int i;
 
+	if (!f2fs_is_multi_device(sbi))
+		return 0;
+
 	for (i = 0; i < sbi->s_ndevs; i++)
 		if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
 			return i;
@@ -420,7 +425,7 @@ static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
 
 void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
 {
-	__submit_merged_write_cond(sbi, NULL, 0, 0, type, true);
+	__submit_merged_write_cond(sbi, NULL, NULL, 0, type, true);
 }
 
 void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
@@ -448,7 +453,8 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 			fio->encrypted_page : fio->page;
 
 	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
-			__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
+			fio->is_por ? META_POR : (__is_meta_io(fio) ?
+			META_GENERIC : DATA_GENERIC_ENHANCE)))
 		return -EFAULT;
 
 	trace_f2fs_submit_page_bio(page, fio);
@@ -498,9 +504,7 @@ next:
 		spin_unlock(&io->io_lock);
 	}
 
-	if (__is_valid_data_blkaddr(fio->old_blkaddr))
-		verify_block_addr(fio, fio->old_blkaddr);
-	verify_block_addr(fio, fio->new_blkaddr);
+	verify_fio_blkaddr(fio);
 
 	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
 
@@ -557,9 +561,6 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 	struct bio_post_read_ctx *ctx;
 	unsigned int post_read_steps = 0;
 
-	if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
-		return ERR_PTR(-EFAULT);
-
 	bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
@@ -587,8 +588,10 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 static int f2fs_submit_page_read(struct inode *inode, struct page *page,
 							block_t blkaddr)
 {
-	struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct bio *bio;
 
+	bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0);
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
@@ -600,8 +603,8 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page,
 		return -EFAULT;
 	}
 	ClearPageError(page);
-	inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
-	__submit_bio(F2FS_I_SB(inode), bio, DATA);
+	inc_page_count(sbi, F2FS_RD_DATA);
+	__submit_bio(sbi, bio, DATA);
 	return 0;
 }
 
@@ -729,6 +732,11 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
 
 	if (f2fs_lookup_extent_cache(inode, index, &ei)) {
 		dn.data_blkaddr = ei.blk + index - ei.fofs;
+		if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr,
+						DATA_GENERIC_ENHANCE_READ)) {
+			err = -EFAULT;
+			goto put_err;
+		}
 		goto got_it;
 	}
 
@@ -742,6 +750,13 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
 		err = -ENOENT;
 		goto put_err;
 	}
+	if (dn.data_blkaddr != NEW_ADDR &&
+			!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
+						dn.data_blkaddr,
+						DATA_GENERIC_ENHANCE)) {
+		err = -EFAULT;
+		goto put_err;
+	}
 got_it:
 	if (PageUptodate(page)) {
 		unlock_page(page);
@@ -1084,12 +1099,12 @@ next_block:
 	blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
 
 	if (__is_valid_data_blkaddr(blkaddr) &&
-		!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) {
+		!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
 		err = -EFAULT;
 		goto sync_out;
 	}
 
-	if (is_valid_data_blkaddr(sbi, blkaddr)) {
+	if (__is_valid_data_blkaddr(blkaddr)) {
 		/* use out-place-update for driect IO under LFS mode */
 		if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO &&
 							map->m_may_create) {
@@ -1499,6 +1514,118 @@ out:
 	return ret;
 }
 
+static int f2fs_read_single_page(struct inode *inode, struct page *page,
+					unsigned nr_pages,
+					struct f2fs_map_blocks *map,
+					struct bio **bio_ret,
+					sector_t *last_block_in_bio,
+					bool is_readahead)
+{
+	struct bio *bio = *bio_ret;
+	const unsigned blkbits = inode->i_blkbits;
+	const unsigned blocksize = 1 << blkbits;
+	sector_t block_in_file;
+	sector_t last_block;
+	sector_t last_block_in_file;
+	sector_t block_nr;
+	int ret = 0;
+
+	block_in_file = (sector_t)page->index;
+	last_block = block_in_file + nr_pages;
+	last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
+							blkbits;
+	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.
+	 */
+	if ((map->m_flags & F2FS_MAP_MAPPED) &&
+			block_in_file > map->m_lblk &&
+			block_in_file < (map->m_lblk + map->m_len))
+		goto got_it;
+
+	/*
+	 * Then do more f2fs_map_blocks() calls until we are
+	 * done with this page.
+	 */
+	map->m_lblk = block_in_file;
+	map->m_len = last_block - block_in_file;
+
+	ret = f2fs_map_blocks(inode, map, 0, F2FS_GET_BLOCK_DEFAULT);
+	if (ret)
+		goto out;
+got_it:
+	if ((map->m_flags & F2FS_MAP_MAPPED)) {
+		block_nr = map->m_pblk + block_in_file - map->m_lblk;
+		SetPageMappedToDisk(page);
+
+		if (!PageUptodate(page) && !cleancache_get_page(page)) {
+			SetPageUptodate(page);
+			goto confused;
+		}
+
+		if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
+						DATA_GENERIC_ENHANCE_READ)) {
+			ret = -EFAULT;
+			goto out;
+		}
+	} else {
+zero_out:
+		zero_user_segment(page, 0, PAGE_SIZE);
+		if (!PageUptodate(page))
+			SetPageUptodate(page);
+		unlock_page(page);
+		goto out;
+	}
+
+	/*
+	 * This page will go to BIO.  Do we need to send this
+	 * BIO off first?
+	 */
+	if (bio && (*last_block_in_bio != block_nr - 1 ||
+		!__same_bdev(F2FS_I_SB(inode), block_nr, bio))) {
+submit_and_realloc:
+		__submit_bio(F2FS_I_SB(inode), bio, DATA);
+		bio = NULL;
+	}
+	if (bio == NULL) {
+		bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
+				is_readahead ? REQ_RAHEAD : 0);
+		if (IS_ERR(bio)) {
+			ret = PTR_ERR(bio);
+			bio = NULL;
+			goto out;
+		}
+	}
+
+	/*
+	 * If the page is under writeback, we need to wait for
+	 * its completion to see the correct decrypted data.
+	 */
+	f2fs_wait_on_block_writeback(inode, block_nr);
+
+	if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+		goto submit_and_realloc;
+
+	inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
+	ClearPageError(page);
+	*last_block_in_bio = block_nr;
+	goto out;
+confused:
+	if (bio) {
+		__submit_bio(F2FS_I_SB(inode), bio, DATA);
+		bio = NULL;
+	}
+	unlock_page(page);
+out:
+	*bio_ret = bio;
+	return ret;
+}
+
 /*
  * This function was originally taken from fs/mpage.c, and customized for f2fs.
  * Major change was from block_size == page_size in f2fs by default.
@@ -1515,13 +1642,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 	struct bio *bio = NULL;
 	sector_t last_block_in_bio = 0;
 	struct inode *inode = mapping->host;
-	const unsigned blkbits = inode->i_blkbits;
-	const unsigned blocksize = 1 << blkbits;
-	sector_t block_in_file;
-	sector_t last_block;
-	sector_t last_block_in_file;
-	sector_t block_nr;
 	struct f2fs_map_blocks map;
+	int ret = 0;
 
 	map.m_pblk = 0;
 	map.m_lblk = 0;
@@ -1544,98 +1666,13 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 				goto next_page;
 		}
 
-		block_in_file = (sector_t)page->index;
-		last_block = block_in_file + nr_pages;
-		last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
-								blkbits;
-		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.
-		 */
-		if ((map.m_flags & F2FS_MAP_MAPPED) &&
-				block_in_file > map.m_lblk &&
-				block_in_file < (map.m_lblk + map.m_len))
-			goto got_it;
-
-		/*
-		 * Then do more f2fs_map_blocks() calls until we are
-		 * done with this page.
-		 */
-		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;
-got_it:
-		if ((map.m_flags & F2FS_MAP_MAPPED)) {
-			block_nr = map.m_pblk + block_in_file - map.m_lblk;
-			SetPageMappedToDisk(page);
-
-			if (!PageUptodate(page) && !cleancache_get_page(page)) {
-				SetPageUptodate(page);
-				goto confused;
-			}
-
-			if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
-								DATA_GENERIC))
-				goto set_error_page;
-		} else {
-zero_out:
+		ret = f2fs_read_single_page(inode, page, nr_pages, &map, &bio,
+					&last_block_in_bio, is_readahead);
+		if (ret) {
+			SetPageError(page);
 			zero_user_segment(page, 0, PAGE_SIZE);
-			if (!PageUptodate(page))
-				SetPageUptodate(page);
 			unlock_page(page);
-			goto next_page;
 		}
-
-		/*
-		 * This page will go to BIO.  Do we need to send this
-		 * BIO off first?
-		 */
-		if (bio && (last_block_in_bio != block_nr - 1 ||
-			!__same_bdev(F2FS_I_SB(inode), block_nr, bio))) {
-submit_and_realloc:
-			__submit_bio(F2FS_I_SB(inode), bio, DATA);
-			bio = NULL;
-		}
-		if (bio == NULL) {
-			bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
-					is_readahead ? REQ_RAHEAD : 0);
-			if (IS_ERR(bio)) {
-				bio = NULL;
-				goto set_error_page;
-			}
-		}
-
-		/*
-		 * If the page is under writeback, we need to wait for
-		 * its completion to see the correct decrypted data.
-		 */
-		f2fs_wait_on_block_writeback(inode, block_nr);
-
-		if (bio_add_page(bio, page, blocksize, 0) < blocksize)
-			goto submit_and_realloc;
-
-		inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
-		ClearPageError(page);
-		last_block_in_bio = block_nr;
-		goto next_page;
-set_error_page:
-		SetPageError(page);
-		zero_user_segment(page, 0, PAGE_SIZE);
-		unlock_page(page);
-		goto next_page;
-confused:
-		if (bio) {
-			__submit_bio(F2FS_I_SB(inode), bio, DATA);
-			bio = NULL;
-		}
-		unlock_page(page);
 next_page:
 		if (pages)
 			put_page(page);
@@ -1643,7 +1680,7 @@ next_page:
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
 		__submit_bio(F2FS_I_SB(inode), bio, DATA);
-	return 0;
+	return pages ? 0 : ret;
 }
 
 static int f2fs_read_data_page(struct file *file, struct page *page)
@@ -1813,7 +1850,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 		fio->old_blkaddr = ei.blk + page->index - ei.fofs;
 
 		if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
-							DATA_GENERIC))
+						DATA_GENERIC_ENHANCE))
 			return -EFAULT;
 
 		ipu_force = true;
@@ -1840,7 +1877,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 got_it:
 	if (__is_valid_data_blkaddr(fio->old_blkaddr) &&
 		!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
-							DATA_GENERIC)) {
+						DATA_GENERIC_ENHANCE)) {
 		err = -EFAULT;
 		goto out_writepage;
 	}
@@ -1848,7 +1885,8 @@ got_it:
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (ipu_force || (is_valid_data_blkaddr(fio->sbi, fio->old_blkaddr) &&
+	if (ipu_force ||
+		(__is_valid_data_blkaddr(fio->old_blkaddr) &&
 					need_inplace_update(fio))) {
 		err = encrypt_one_page(fio);
 		if (err)
@@ -1866,9 +1904,10 @@ got_it:
 									true);
 			if (PageWriteback(page))
 				end_page_writeback(page);
+		} else {
+			set_inode_flag(inode, FI_UPDATE_WRITE);
 		}
 		trace_f2fs_do_write_data_page(fio->page, IPU);
-		set_inode_flag(inode, FI_UPDATE_WRITE);
 		return err;
 	}
 
@@ -2030,7 +2069,8 @@ out:
 	}
 
 	unlock_page(page);
-	if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode))
+	if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
+					!F2FS_I(inode)->cp_task)
 		f2fs_balance_fs(sbi, need_balance_fs);
 
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -2491,6 +2531,11 @@ repeat:
 		zero_user_segment(page, 0, PAGE_SIZE);
 		SetPageUptodate(page);
 	} else {
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
+				DATA_GENERIC_ENHANCE_READ)) {
+			err = -EFAULT;
+			goto fail;
+		}
 		err = f2fs_submit_page_read(inode, page, blkaddr);
 		if (err)
 			goto fail;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index bacf5c2a8850..06b89a9862ab 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -210,7 +210,14 @@ enum {
 	META_SSA,
 	META_MAX,
 	META_POR,
-	DATA_GENERIC,
+	DATA_GENERIC,		/* check range only */
+	DATA_GENERIC_ENHANCE,	/* strong check on range and segment bitmap */
+	DATA_GENERIC_ENHANCE_READ,	/*
+					 * strong check on range and segment
+					 * bitmap but no warning due to race
+					 * condition of read on truncated area
+					 * by extent_cache
+					 */
 	META_GENERIC,
 };
 
@@ -1041,7 +1048,7 @@ struct f2fs_io_info {
 	bool submitted;		/* indicate IO submission */
 	int need_lock;		/* indicate we need to lock cp_rwsem */
 	bool in_list;		/* indicate fio is in io_list */
-	bool is_meta;		/* indicate borrow meta inode mapping or not */
+	bool is_por;		/* indicate IO is from recovery or not */
 	bool retry;		/* need to reallocate block address */
 	enum iostat_type io_type;	/* io type */
 	struct writeback_control *io_wbc; /* writeback control */
@@ -1068,8 +1075,8 @@ struct f2fs_dev_info {
 	block_t start_blk;
 	block_t end_blk;
 #ifdef CONFIG_BLK_DEV_ZONED
-	unsigned int nr_blkz;			/* Total number of zones */
-	u8 *blkz_type;				/* Array of zones type */
+	unsigned int nr_blkz;		/* Total number of zones */
+	unsigned long *blkz_seq;	/* Bitmap indicating sequential zones */
 #endif
 };
 
@@ -1366,6 +1373,17 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
 }
 #endif
 
+/*
+ * Test if the mounted volume is a multi-device volume.
+ *   - For a single regular disk volume, sbi->s_ndevs is 0.
+ *   - For a single zoned disk volume, sbi->s_ndevs is 1.
+ *   - For a multi-device volume, sbi->s_ndevs is always 2 or more.
+ */
+static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi)
+{
+	return sbi->s_ndevs > 1;
+}
+
 /* For write statistics. Suppose sector size is 512 bytes,
  * and the return value is in kbytes. s is of struct f2fs_sb_info.
  */
@@ -1777,6 +1795,7 @@ enospc:
 	return -ENOSPC;
 }
 
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
 static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 						struct inode *inode,
 						block_t count)
@@ -1785,13 +1804,21 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 
 	spin_lock(&sbi->stat_lock);
 	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
-	f2fs_bug_on(sbi, inode->i_blocks < sectors);
 	sbi->total_valid_block_count -= (block_t)count;
 	if (sbi->reserved_blocks &&
 		sbi->current_reserved_blocks < sbi->reserved_blocks)
 		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
 					sbi->current_reserved_blocks + count);
 	spin_unlock(&sbi->stat_lock);
+	if (unlikely(inode->i_blocks < sectors)) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu",
+			inode->i_ino,
+			(unsigned long long)inode->i_blocks,
+			(unsigned long long)sectors);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		return;
+	}
 	f2fs_i_blocks_write(inode, count, false, true);
 }
 
@@ -1889,7 +1916,11 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 	if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
 		offset = (flag == SIT_BITMAP) ?
 			le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0;
-		return &ckpt->sit_nat_version_bitmap + offset;
+		/*
+		 * if large_nat_bitmap feature is enabled, leave checksum
+		 * protection for all nat/sit bitmaps.
+		 */
+		return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32);
 	}
 
 	if (__cp_payload(sbi) > 0) {
@@ -2008,7 +2039,6 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
 
 	f2fs_bug_on(sbi, !sbi->total_valid_block_count);
 	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
-	f2fs_bug_on(sbi, !is_inode && !inode->i_blocks);
 
 	sbi->total_valid_node_count--;
 	sbi->total_valid_block_count--;
@@ -2018,10 +2048,19 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
 
 	spin_unlock(&sbi->stat_lock);
 
-	if (is_inode)
+	if (is_inode) {
 		dquot_free_inode(inode);
-	else
+	} else {
+		if (unlikely(inode->i_blocks == 0)) {
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"Inconsistent i_blocks, ino:%lu, iblocks:%llu",
+				inode->i_ino,
+				(unsigned long long)inode->i_blocks);
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			return;
+		}
 		f2fs_i_blocks_write(inode, 1, false, true);
+	}
 }
 
 static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
@@ -2545,7 +2584,14 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
 
 static inline unsigned int addrs_per_inode(struct inode *inode)
 {
-	return CUR_ADDRS_PER_INODE(inode) - get_inline_xattr_addrs(inode);
+	unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
+				get_inline_xattr_addrs(inode);
+	return ALIGN_DOWN(addrs, 1);
+}
+
+static inline unsigned int addrs_per_block(struct inode *inode)
+{
+	return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, 1);
 }
 
 static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
@@ -2558,7 +2604,9 @@ static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
 
 static inline int inline_xattr_size(struct inode *inode)
 {
-	return get_inline_xattr_addrs(inode) * sizeof(__le32);
+	if (f2fs_has_inline_xattr(inode))
+		return get_inline_xattr_addrs(inode) * sizeof(__le32);
+	return 0;
 }
 
 static inline int f2fs_has_inline_data(struct inode *inode)
@@ -2800,12 +2848,10 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
 
 #define __is_large_section(sbi)		((sbi)->segs_per_sec > 1)
 
-#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META &&	\
-				(!is_read_io((fio)->op) || (fio)->is_meta))
+#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)
 
 bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type);
-void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
 static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type)
 {
@@ -2824,15 +2870,6 @@ static inline bool __is_valid_data_blkaddr(block_t blkaddr)
 	return true;
 }
 
-static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi,
-						block_t blkaddr)
-{
-	if (!__is_valid_data_blkaddr(blkaddr))
-		return false;
-	verify_blkaddr(sbi, blkaddr, DATA_GENERIC);
-	return true;
-}
-
 static inline void f2fs_set_page_private(struct page *page,
 						unsigned long data)
 {
@@ -3530,16 +3567,12 @@ F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
 F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static inline int get_blkz_type(struct f2fs_sb_info *sbi,
-			struct block_device *bdev, block_t blkaddr)
+static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
+				    block_t blkaddr)
 {
 	unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;
-	int i;
 
-	for (i = 0; i < sbi->s_ndevs; i++)
-		if (FDEV(i).bdev == bdev)
-			return FDEV(i).blkz_type[zno];
-	return -EINVAL;
+	return test_bit(zno, FDEV(devi).blkz_seq);
 }
 #endif
 
@@ -3548,9 +3581,23 @@ static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
 	return f2fs_sb_has_blkzoned(sbi);
 }
 
+static inline bool f2fs_bdev_support_discard(struct block_device *bdev)
+{
+	return blk_queue_discard(bdev_get_queue(bdev)) ||
+	       bdev_is_zoned(bdev)