f2fs: Sync code with branch upstream-linux-4.9.y

2026-06-07 03:15:31 +09:00 · 2020-04-19 15:15:25 +02:00
parent ea9fb79ddc
commit dd7611915b
16 changed files with 442 additions and 100 deletions
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -352,12 +352,14 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode,
 		return PTR_ERR(p);

 	clone = f2fs_acl_clone(p, GFP_NOFS);
-	if (!clone)
-		goto no_mem;
+	if (!clone) {
+		ret = -ENOMEM;
+		goto release_acl;
+	}

 	ret = f2fs_acl_create_masq(clone, mode);
 	if (ret < 0)
-		goto no_mem_clone;
+		goto release_clone;

 	if (ret == 0)
 		posix_acl_release(clone);
@@ -371,11 +373,11 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode,

 	return 0;

-no_mem_clone:
+release_clone:
 	posix_acl_release(clone);
-no_mem:
+release_acl:
 	posix_acl_release(p);
-	return -ENOMEM;
+	return ret;
 }

 int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -85,8 +85,10 @@ repeat:
 	fio.page = page;

 	if (f2fs_submit_page_bio(&fio)) {
-		f2fs_put_page(page, 1);
-		goto repeat;
+		memset(page_address(page), 0, PAGE_SIZE);
+		f2fs_stop_checkpoint(sbi, false);
+		f2fs_bug_on(sbi, 1);
+		return page;
 	}

 	lock_page(page);
@@ -117,7 +119,8 @@ struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	return __get_meta_page(sbi, index, false);
 }

-bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type)
 {
 	switch (type) {
 	case META_NAT:
@@ -137,8 +140,20 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
 			return false;
 		break;
 	case META_POR:
+	case DATA_GENERIC:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
-			blkaddr < MAIN_BLKADDR(sbi)))
+			blkaddr < MAIN_BLKADDR(sbi))) {
+			if (type == DATA_GENERIC) {
+				f2fs_msg(sbi->sb, KERN_WARNING,
+					"access invalid blkaddr:%u", blkaddr);
+				WARN_ON(1);
+			}
+			return false;
+		}
+		break;
+	case META_GENERIC:
+		if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
+			blkaddr >= MAIN_BLKADDR(sbi)))
 			return false;
 		break;
 	default:
@@ -173,7 +188,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 	blk_start_plug(&plug);
 	for (; nrpages-- > 0; blkno++) {

-		if (!is_valid_blkaddr(sbi, blkno, type))
+		if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
 			goto out;

 		switch (type) {
@@ -745,7 +760,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,

 	crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
 	if (crc_offset > (blk_size - sizeof(__le32))) {
-        f2fs_put_page(*cp_page, 1);
+		f2fs_put_page(*cp_page, 1);
 		f2fs_msg(sbi->sb, KERN_WARNING,
 			"invalid crc_offset: %zu", crc_offset);
 		return -EINVAL;
@@ -774,6 +789,14 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 					&cp_page_1, version);
 	if (err)
 		return NULL;
+
+	if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
+					sbi->blocks_per_seg) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"invalid cp_pack_total_block_count:%u",
+			le32_to_cpu(cp_block->cp_pack_total_block_count));
+		goto invalid_cp;
+	}
 	pre_version = *version;

 	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
@@ -837,15 +860,15 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);

-	/* Sanity checking of checkpoint */
-	if (sanity_check_ckpt(sbi))
-		goto free_fail_no_cp;
-
 	if (cur_page == cp1)
 		sbi->cur_cp_pack = 1;
 	else
 		sbi->cur_cp_pack = 2;

+	/* Sanity checking of checkpoint */
+	if (sanity_check_ckpt(sbi))
+		goto free_fail_no_cp;
+
 	if (cp_blks <= 1)
 		goto done;

--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -438,7 +438,10 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	struct page *page = fio->encrypted_page ?
 			fio->encrypted_page : fio->page;

-	verify_block_addr(fio, fio->new_blkaddr);
+	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
+			__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
+		return -EFAULT;
+
 	trace_f2fs_submit_page_bio(page, fio);
 	f2fs_trace_ios(fio, 0);

@@ -483,7 +486,7 @@ next:
 		spin_unlock(&io->io_lock);
 	}

-	if (fio->old_blkaddr != NEW_ADDR)
+	if (__is_valid_data_blkaddr(fio->old_blkaddr))
 		verify_block_addr(fio, fio->old_blkaddr);
 	verify_block_addr(fio, fio->new_blkaddr);

@@ -1043,7 +1046,13 @@ next_dnode:
 next_block:
 	blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);

-	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
+	if (__is_valid_data_blkaddr(blkaddr) &&
+		!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) {
+		err = -EFAULT;
+		goto sync_out;
+	}
+
+	if (!is_valid_data_blkaddr(sbi, blkaddr)) {
 		if (create) {
 			if (unlikely(f2fs_cp_error(sbi))) {
 				err = -EIO;
@@ -1493,6 +1502,10 @@ got_it:
 				SetPageUptodate(page);
 				goto confused;
 			}
+
+			if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
+								DATA_GENERIC))
+				goto set_error_page;
 		} else {
 			zero_user_segment(page, 0, PAGE_SIZE);
 			if (!PageUptodate(page))
@@ -1721,6 +1734,7 @@ int do_write_data_page(struct f2fs_io_info *fio)
 	/* This page is already truncated */
 	if (fio->old_blkaddr == NULL_ADDR) {
 		ClearPageUptodate(page);
+		clear_cold_data(page);
 		goto out_writepage;
 	}
 got_it:
@@ -1756,6 +1770,12 @@ got_it:
 	if (err)
 		goto out_writepage;

+	if (__is_valid_data_blkaddr(fio->old_blkaddr) &&
+		!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
+							DATA_GENERIC)) {
+		err = -EFAULT;
+		goto out_writepage;
+	}
 	set_page_writeback(page);
 	ClearPageError(page);

@@ -1782,7 +1802,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 	loff_t i_size = i_size_read(inode);
 	const pgoff_t end_index = ((unsigned long long) i_size)
 							>> PAGE_SHIFT;
-	loff_t psize = (page->index + 1) << PAGE_SHIFT;
+	loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
 	unsigned offset = 0;
 	bool need_balance_fs = false;
 	int err = 0;
@@ -1877,8 +1897,10 @@ done:

 out:
 	inode_dec_dirty_pages(inode);
-	if (err)
+	if (err) {
 		ClearPageUptodate(page);
+		clear_cold_data(page);
+	}

 	if (wbc->for_reclaim) {
 		f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA);
@@ -2243,9 +2265,6 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	block_t blkaddr = NULL_ADDR;
 	int err = 0;

-#ifdef CONFIG_AMLOGIC_VMAP
-	trace_android_fs_datawrite_wrap(inode, pos, len);
-#else
 	if (trace_android_fs_datawrite_start_enabled()) {
 		char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];

@@ -2256,7 +2275,6 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 						 current->pid, path,
 						 current->comm);
 	}
-#endif
 	trace_f2fs_write_begin(inode, pos, len, flags);

 	if (f2fs_is_atomic_file(inode) &&
@@ -2417,12 +2435,6 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)

 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);

-#ifdef CONFIG_AMLOGIC_VMAP
-	if (rw == READ)
-		trace_android_fs_dataread_wrap(inode, offset, count);
-	if (rw == WRITE)
-		trace_android_fs_datawrite_wrap(inode, offset, count);
-#else
 	if (trace_android_fs_dataread_start_enabled() &&
 	    (rw == READ)) {
 		char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
@@ -2445,7 +2457,6 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 						 current->pid, path,
 						 current->comm);
 	}
-#endif
 	if (rw == WRITE && whint_mode == WHINT_MODE_OFF)
 		iocb->ki_hint = WRITE_LIFE_NOT_SET;

@@ -2506,6 +2517,8 @@ 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 drop_inmem_page(inode, page);
@@ -2524,6 +2537,7 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 	if (IS_ATOMIC_WRITTEN_PAGE(page))
 		return 0;

+	clear_cold_data(page);
 	set_page_private(page, 0);
 	ClearPagePrivate(page);
 	return 1;
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -740,6 +740,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 		clear_page_dirty_for_io(page);
 		ClearPagePrivate(page);
 		ClearPageUptodate(page);
+		clear_cold_data(page);
 		inode_dec_dirty_pages(dir);
 		remove_dirty_inode(dir);
 	}
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -194,7 +194,7 @@ struct cp_control {
 };

 /*
- * For CP/NAT/SIT/SSA readahead
+ * indicate meta/data type
 */
 enum {
 	META_CP,
@@ -202,6 +202,8 @@ enum {
 	META_SIT,
 	META_SSA,
 	META_POR,
+	DATA_GENERIC,
+	META_GENERIC,
 };

 /* for the list of ino */
@@ -2512,10 +2514,19 @@ static inline bool is_dot_dotdot(const struct qstr *str)

 static inline bool f2fs_may_extent_tree(struct inode *inode)
 {
-	if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	if (!test_opt(sbi, EXTENT_CACHE) ||
 			is_inode_flag_set(inode, FI_NO_EXTENT))
 		return false;

+	/*
+	 * for recovered files during mount do not create extents
+	 * if shrinker is not registered.
+	 */
+	if (list_empty(&sbi->s_list))
+		return false;
+
 	return S_ISREG(inode->i_mode);
 }

@@ -2634,6 +2645,39 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
 	spin_unlock(&sbi->iostat_lock);
 }

+#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META &&	\
+				(!is_read_io(fio->op) || fio->is_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)
+{
+	if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"invalid blkaddr: %u, type: %d, run fsck to fix.",
+			blkaddr, type);
+		f2fs_bug_on(sbi, 1);
+	}
+}
+
+static inline bool __is_valid_data_blkaddr(block_t blkaddr)
+{
+	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+		return false;
+	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;
+}
+
 /*
 * file.c
 */
@@ -2851,6 +2895,8 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
 struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
 struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
 struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type);
 bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type);
 int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 			int type, bool sync);
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -219,6 +219,9 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,

 	trace_f2fs_sync_file_enter(inode);

+	if (S_ISDIR(inode->i_mode))
+		goto go_write;
+
 	/* if fdatasync is triggered, let's do in-place-update */
 	if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
 		set_inode_flag(inode, FI_NEED_IPU);
@@ -347,13 +350,13 @@ static pgoff_t __get_first_dirty_index(struct address_space *mapping,
 	return pgofs;
 }

-static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
-							int whence)
+static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr,
+				pgoff_t dirty, pgoff_t pgofs, int whence)
 {
 	switch (whence) {
 	case SEEK_DATA:
 		if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
-			(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
+			is_valid_data_blkaddr(sbi, blkaddr))
 			return true;
 		break;
 	case SEEK_HOLE:
@@ -416,7 +419,15 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 			blkaddr = datablock_addr(dn.inode,
 					dn.node_page, dn.ofs_in_node);

-			if (__found_offset(blkaddr, dirty, pgofs, whence)) {
+			if (__is_valid_data_blkaddr(blkaddr) &&
+				!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
+						blkaddr, DATA_GENERIC)) {
+				f2fs_put_dnode(&dn);
+				goto fail;
+			}
+
+			if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty,
+							pgofs, whence)) {
 				f2fs_put_dnode(&dn);
 				goto found;
 			}
@@ -508,6 +519,11 @@ void truncate_data_blocks_range(struct dnode_of_data *dn, int count)

 		dn->data_blkaddr = NULL_ADDR;
 		set_data_blkaddr(dn);
+
+		if (__is_valid_data_blkaddr(blkaddr) &&
+			!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
+			continue;
+
 		invalidate_blocks(sbi, blkaddr);
 		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
 			clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
@@ -1070,7 +1086,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 				}
 				dn.ofs_in_node++;
 				i++;
-				new_size = (dst + i) << PAGE_SHIFT;
+				new_size = (loff_t)(dst + i) << PAGE_SHIFT;
 				if (dst_inode->i_size < new_size)
 					f2fs_i_size_write(dst_inode, new_size);
 			} while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR));
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1109,7 +1109,7 @@ stop:

 	put_gc_inode(&gc_list);

-	if (sync)
+	if (sync && !ret)
 		ret = sec_freed ? 0 : -EAGAIN;
 	return ret;
 }
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -86,9 +86,6 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 {
 	struct page *ipage;

-#ifdef CONFIG_AMLOGIC_VMAP
-	trace_android_fs_dataread_wrap(inode, page_offset(page), PAGE_SIZE);
-#else
 	if (trace_android_fs_dataread_start_enabled()) {
 		char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];

@@ -99,7 +96,6 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 						PAGE_SIZE, current->pid,
 						path, current->comm);
 	}
-#endif

 	ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
 	if (IS_ERR(ipage)) {
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -68,13 +68,16 @@ static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }

-static bool __written_first_block(struct f2fs_inode *ri)
+static int __written_first_block(struct f2fs_sb_info *sbi,
+					struct f2fs_inode *ri)
 {
 	block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]);

-	if (addr != NEW_ADDR && addr != NULL_ADDR)
-		return true;
-	return false;
+	if (!__is_valid_data_blkaddr(addr))
+		return 1;
+	if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC))
+		return -EFAULT;
+	return 0;
 }

 static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -185,6 +188,50 @@ void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page)
 	ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page));
 }

+static bool sanity_check_inode(struct inode *inode, struct page *node_page)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	unsigned long long iblocks;
+
+	iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
+	if (!iblocks) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, "
+			"run fsck to fix.",
+			__func__, inode->i_ino, iblocks);
+		return false;
+	}
+
+	if (ino_of_node(node_page) != nid_of_node(node_page)) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"%s: corrupted inode footer i_ino=%lx, ino,nid: "
+			"[%u, %u] run fsck to fix.",
+			__func__, inode->i_ino,
+			ino_of_node(node_page), nid_of_node(node_page));
+		return false;
+	}
+
+	if (F2FS_I(inode)->extent_tree) {
+		struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest;
+
+		if (ei->len &&
+			(!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC) ||
+			!f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
+							DATA_GENERIC))) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"%s: inode (ino=%lx) extent info [%u, %u, %u] "
+				"is incorrect, run fsck to fix",
+				__func__, inode->i_ino,
+				ei->blk, ei->fofs, ei->len);
+			return false;
+		}
+	}
+	return true;
+}
+
 static int do_read_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -192,6 +239,7 @@ static int do_read_inode(struct inode *inode)
 	struct page *node_page;
 	struct f2fs_inode *ri;
 	projid_t i_projid;
+	int err;

 	/* Check if ino is within scope */
 	if (check_nid_range(sbi, inode->i_ino)) {
@@ -235,6 +283,11 @@ static int do_read_inode(struct inode *inode)

 	get_inline_info(inode, ri);

+	if (!sanity_check_inode(inode, node_page)) {
+		f2fs_put_page(node_page, 1);
+		return -EINVAL;
+	}
+
 	fi->i_extra_isize = f2fs_has_extra_attr(inode) ?
 					le16_to_cpu(ri->i_extra_isize) : 0;

@@ -262,7 +315,12 @@ static int do_read_inode(struct inode *inode)
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);

-	if (__written_first_block(ri))
+	err = __written_first_block(sbi, ri);
+	if (err < 0) {
+		f2fs_put_page(node_page, 1);
+		return err;
+	}
+	if (!err)
 		set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);

 	if (!need_inode_block_update(sbi, inode->i_ino))
@@ -354,6 +412,7 @@ make_now:
 	return inode;

 bad_inode:
+	f2fs_inode_synced(inode);
 	iget_failed(inode);
 	trace_f2fs_iget_exit(inode, ret);
 	return ERR_PTR(ret);
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -364,8 +364,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 			new_blkaddr == NULL_ADDR);
 	f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR &&
 			new_blkaddr == NEW_ADDR);
-	f2fs_bug_on(sbi, nat_get_blkaddr(e) != NEW_ADDR &&
-			nat_get_blkaddr(e) != NULL_ADDR &&
+	f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) &&
 			new_blkaddr == NEW_ADDR);

 	/* increment version no as node is removed */
@@ -376,7 +375,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,

 	/* change address */
 	nat_set_blkaddr(e, new_blkaddr);
-	if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR)
+	if (!is_valid_data_blkaddr(sbi, new_blkaddr))
 		set_nat_flag(e, IS_CHECKPOINTED, false);
 	__set_nat_cache_dirty(nm_i, e);

@@ -719,6 +718,7 @@ static void truncate_node(struct dnode_of_data *dn)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct node_info ni;
+	pgoff_t index;

 	get_node_info(sbi, dn->nid, &ni);

@@ -736,10 +736,11 @@ static void truncate_node(struct dnode_of_data *dn)
 	clear_node_page_dirty(dn->node_page);
 	set_sbi_flag(sbi, SBI_IS_DIRTY);

+	index = dn->node_page->index;
 	f2fs_put_page(dn->node_page, 1);

 	invalidate_mapping_pages(NODE_MAPPING(sbi),
-			dn->node_page->index, dn->node_page->index);
+			index, index);

 	dn->node_page = NULL;
 	trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);
@@ -1394,6 +1395,12 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 		return 0;
 	}

+	if (__is_valid_data_blkaddr(ni.blk_addr) &&
+		!f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) {
+		up_read(&sbi->node_write);
+		goto redirty_out;
+	}
+
 	if (atomic && !test_opt(sbi, NOBARRIER))
 		fio.op_flags |= REQ_PREFLUSH | REQ_FUA;

--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -214,6 +214,8 @@ static void recover_inode(struct inode *inode, struct page *page)
 	char *name;

 	inode->i_mode = le16_to_cpu(raw->i_mode);
+	i_uid_write(inode, le32_to_cpu(raw->i_uid));
+	i_gid_write(inode, le32_to_cpu(raw->i_gid));
 	f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
 	inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime);
 	inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
@@ -254,7 +256,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
 	while (1) {
 		struct fsync_inode_entry *entry;

-		if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
 			return 0;

 		page = get_tmp_page(sbi, blkaddr);
@@ -474,7 +476,15 @@ retry_dn:

 	get_node_info(sbi, dn.nid, &ni);
 	f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
-	f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page));
+
+	if (ofs_of_node(dn.node_page) != ofs_of_node(page)) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u",
+			inode->i_ino, ofs_of_node(dn.node_page),
+			ofs_of_node(page));
+		err = -EFAULT;
+		goto err;
+	}

 	for (; start < end; start++, dn.ofs_in_node++) {
 		block_t src, dest;
@@ -508,7 +518,7 @@ retry_dn:
 		}

 		/* dest is valid block, try to recover from src to dest */
-		if (is_valid_blkaddr(sbi, dest, META_POR)) {
+		if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {

 			if (src == NULL_ADDR) {
 				err = reserve_new_block(&dn);
@@ -569,7 +579,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
 	while (1) {
 		struct fsync_inode_entry *entry;

-		if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
 			break;

 		ra_meta_pages_cond(sbi, blkaddr);
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -260,8 +260,10 @@ retry:
 		}
 next:
 		/* we don't need to invalidate this in the sccessful status */
-		if (drop || recover)
+		if (drop || recover) {
 			ClearPageUptodate(page);
+			clear_cold_data(page);
+		}
 		set_page_private(page, 0);
 		ClearPagePrivate(page);
 		f2fs_put_page(page, 1);
@@ -1892,7 +1894,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
 	struct seg_entry *se;
 	bool is_cp = false;

-	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+	if (!is_valid_data_blkaddr(sbi, blkaddr))
 		return true;

 	down_read(&sit_i->sentry_lock);
@@ -2954,7 +2956,7 @@ void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
 	struct page *cpage;

-	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+	if (!is_valid_data_blkaddr(sbi, blkaddr))
 		return;

 	cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
@@ -3669,6 +3671,15 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
 		unsigned int old_valid_blocks;

 		start = le32_to_cpu(segno_in_journal(journal, i));
+		if (start >= MAIN_SEGS(sbi)) {
+			f2fs_msg(sbi->sb, KERN_ERR,
+					"Wrong journal entry on segno %u",
+					start);
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			err = -EINVAL;
+			break;
+		}
+
 		se = &sit_i->sentries[start];
 		sit = sit_in_journal(journal, i);

@@ -3784,6 +3795,41 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
 	return init_victim_secmap(sbi);
 }

+static int sanity_check_curseg(struct f2fs_sb_info *sbi)
+{
+	int i;
+
+	/*
+	 * In LFS/SSR curseg, .next_blkoff should point to an unused blkaddr;
+	 * In LFS curseg, all blkaddr after .next_blkoff should be unused.
+	 */
+	for (i = 0; i < NO_CHECK_TYPE; i++) {
+		struct curseg_info *curseg = CURSEG_I(sbi, i);
+		struct seg_entry *se = get_seg_entry(sbi, curseg->segno);
+		unsigned int blkofs = curseg->next_blkoff;
+
+		if (f2fs_test_bit(blkofs, se->cur_valid_map))
+			goto out;
+
+		if (curseg->alloc_type == SSR)
+			continue;
+
+		for (blkofs += 1; blkofs < sbi->blocks_per_seg; blkofs++) {
+			if (!f2fs_test_bit(blkofs, se->cur_valid_map))
+				continue;
+out:
+			f2fs_msg(sbi->sb, KERN_ERR,
+				"Current segment's next free block offset is "
+				"inconsistent with bitmap, logtype:%u, "
+				"segno:%u, type:%u, next_blkoff:%u, blkofs:%u",
+				i, curseg->segno, curseg->alloc_type,
+				curseg->next_blkoff, blkofs);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 /*
 * Update min, max modified time for cost-benefit GC algorithm
 */
@@ -3878,6 +3924,10 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	if (err)
 		return err;

+	err = sanity_check_curseg(sbi);
+	if (err)
+		return err;
+
 	init_min_max_mtime(sbi);
 	return 0;
 }
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -40,18 +40,18 @@
 	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))

 #define IS_CURSEC(sbi, secno)						\
-	(((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
-	  (sbi)->segs_per_sec))	\
+	((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
+	  sbi->segs_per_sec))	\

 #define MAIN_BLKADDR(sbi)						\
 	(SM_I(sbi) ? SM_I(sbi)->main_blkaddr : 				\
@@ -66,7 +66,7 @@
 #define TOTAL_SEGS(sbi)							\
 	(SM_I(sbi) ? SM_I(sbi)->segment_count : 				\
 		le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
-#define TOTAL_BLKS(sbi)	(TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg)
+#define TOTAL_BLKS(sbi)	(TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)

 #define MAX_BLKADDR(sbi)	(SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
 #define SEGMENT_SIZE(sbi)	(1ULL << ((sbi)->log_blocksize +	\
@@ -85,7 +85,7 @@
 	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1))

 #define GET_SEGNO(sbi, blk_addr)					\
-	((((blk_addr) == NULL_ADDR) || ((blk_addr) == NEW_ADDR)) ?	\
+	((!is_valid_data_blkaddr(sbi, blk_addr)) ?			\
 	NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi),			\
 		GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
 #define BLKS_PER_SEC(sbi)					\
@@ -645,13 +645,10 @@ static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;

-	if (PAGE_TYPE_OF_BIO(fio->type) == META &&
-				(!is_read_io(fio->op) || fio->is_meta))
-		BUG_ON(blk_addr < SEG0_BLKADDR(sbi) ||
-				blk_addr >= MAIN_BLKADDR(sbi));
+	if (__is_meta_io(fio))
+		verify_blkaddr(sbi, blk_addr, META_GENERIC);
 	else
-		BUG_ON(blk_addr < MAIN_BLKADDR(sbi) ||
-				blk_addr >= MAX_BLKADDR(sbi));
+		verify_blkaddr(sbi, blk_addr, DATA_GENERIC);
 }

 /*
@@ -660,7 +657,6 @@ static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
 static inline int check_block_count(struct f2fs_sb_info *sbi,
 		int segno, struct f2fs_sit_entry *raw_sit)
 {
-#ifdef CONFIG_F2FS_CHECK_FS
 	bool is_valid  = test_bit_le(0, raw_sit->valid_map) ? true : false;
 	int valid_blocks = 0;
 	int cur_pos = 0, next_pos;
@@ -687,7 +683,7 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		return -EINVAL;
 	}
-#endif
+
 	/* check segment usage, and check boundary of a given segment number */
 	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
 					|| segno > TOTAL_SEGS(sbi) - 1)) {
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -138,6 +138,6 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi)
 	f2fs_shrink_extent_tree(sbi, __count_extent_cache(sbi));

 	spin_lock(&f2fs_list_lock);
-	list_del(&sbi->s_list);
+	list_del_init(&sbi->s_list);
 	spin_unlock(&f2fs_list_lock);
 }
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2139,6 +2139,8 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
 static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 				struct buffer_head *bh)
 {
+	block_t segment_count, segs_per_sec, secs_per_zone;
+	block_t total_sections, blocks_per_seg;
 	struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
 					(bh->b_data + F2FS_SUPER_OFFSET);
 	struct super_block *sb = sbi->sb;
@@ -2195,6 +2197,68 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		return 1;
 	}

+	segment_count = le32_to_cpu(raw_super->segment_count);
+	segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
+	secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
+	total_sections = le32_to_cpu(raw_super->section_count);
+
+	/* blocks_per_seg should be 512, given the above check */
+	blocks_per_seg = 1 << le32_to_cpu(raw_super->log_blocks_per_seg);
+
+	if (segment_count > F2FS_MAX_SEGMENT ||
+				segment_count < F2FS_MIN_SEGMENTS) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid segment count (%u)",
+			segment_count);
+		return 1;
+	}
+
+	if (total_sections > segment_count ||
+			total_sections < F2FS_MIN_SEGMENTS ||
+			segs_per_sec > segment_count || !segs_per_sec) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid segment/section count (%u, %u x %u)",
+			segment_count, total_sections, segs_per_sec);
+		return 1;
+	}
+
+	if ((segment_count / segs_per_sec) < total_sections) {
+		f2fs_msg(sb, KERN_INFO,
+			"Small segment_count (%u < %u * %u)",
+			segment_count, segs_per_sec, total_sections);
+		return 1;
+	}
+
+	if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong segment_count / block_count (%u > %llu)",
+			segment_count, le64_to_cpu(raw_super->block_count));
+		return 1;
+	}
+
+	if (secs_per_zone > total_sections || !secs_per_zone) {
+		f2fs_msg(sb, KERN_INFO,
+			"Wrong secs_per_zone / total_sections (%u, %u)",
+			secs_per_zone, total_sections);
+		return 1;
+	}
+	if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION) {
+		f2fs_msg(sb, KERN_INFO,
+			"Corrupted extension count (%u > %u)",
+			le32_to_cpu(raw_super->extension_count),
+			F2FS_MAX_EXTENSION);
+		return 1;
+	}
+
+	if (le32_to_cpu(raw_super->cp_payload) >
+				(blocks_per_seg - F2FS_CP_PACKS)) {
+		f2fs_msg(sb, KERN_INFO,
+			"Insane cp_payload (%u > %u)",
+			le32_to_cpu(raw_super->cp_payload),
+			blocks_per_seg - F2FS_CP_PACKS);
+		return 1;
+	}
+
 	/* check reserved ino info */
 	if (le32_to_cpu(raw_super->node_ino) != 1 ||
 		le32_to_cpu(raw_super->meta_ino) != 2 ||
@@ -2207,13 +2271,6 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		return 1;
 	}

-	if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
-		f2fs_msg(sb, KERN_INFO,
-			"Invalid segment count (%u)",
-			le32_to_cpu(raw_super->segment_count));
-		return 1;
-	}
-
 	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
 	if (sanity_check_area_boundary(sbi, bh))
 		return 1;
@@ -2231,7 +2288,10 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	unsigned int sit_segs, nat_segs;
 	unsigned int sit_bitmap_size, nat_bitmap_size;
 	unsigned int log_blocks_per_seg;
-	int i;
+	unsigned int segment_count_main;
+	unsigned int cp_pack_start_sum, cp_payload;
+	block_t user_block_count;
+	int i, j;

 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -2255,6 +2315,16 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 		return 1;
 	}

+	user_block_count = le64_to_cpu(ckpt->user_block_count);
+	segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+	log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+	if (!user_block_count || user_block_count >=
+			segment_count_main << log_blocks_per_seg) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong user_block_count: %u", user_block_count);
+		return 1;
+	}
+
 	main_segs = le32_to_cpu(raw_super->segment_count_main);
 	blocks_per_seg = sbi->blocks_per_seg;

@@ -2262,16 +2332,47 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 		if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
 			le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg)
 			return 1;
+		for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) {
+			if (le32_to_cpu(ckpt->cur_node_segno[i]) ==
+				le32_to_cpu(ckpt->cur_node_segno[j])) {
+				f2fs_msg(sbi->sb, KERN_ERR,
+					"Node segment (%u, %u) has the same "
+					"segno: %u", i, j,
+					le32_to_cpu(ckpt->cur_node_segno[i]));
+				return 1;
+			}
+		}
 	}
 	for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
 		if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs ||
 			le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg)
 			return 1;
+		for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) {
+			if (le32_to_cpu(ckpt->cur_data_segno[i]) ==
+				le32_to_cpu(ckpt->cur_data_segno[j])) {
+				f2fs_msg(sbi->sb, KERN_ERR,
+					"Data segment (%u, %u) has the same "
+					"segno: %u", i, j,
+					le32_to_cpu(ckpt->cur_data_segno[i]));
+				return 1;
+			}
+		}
+	}
+	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
+		for (j = 0; j < NR_CURSEG_DATA_TYPE; j++) {
+			if (le32_to_cpu(ckpt->cur_node_segno[i]) ==
+				le32_to_cpu(ckpt->cur_data_segno[j])) {
+				f2fs_msg(sbi->sb, KERN_ERR,
+					"Node segment (%u) and Data segment (%u)"
+					" has the same segno: %u", i, j,
+					le32_to_cpu(ckpt->cur_node_segno[i]));
+				return 1;
+			}
+		}
 	}

 	sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);
 	nat_bitmap_size = le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
-	log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);

 	if (sit_bitmap_size != ((sit_segs / 2) << log_blocks_per_seg) / 8 ||
 		nat_bitmap_size != ((nat_segs / 2) << log_blocks_per_seg) / 8) {
@@ -2281,6 +2382,17 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 		return 1;
 	}

+	cp_pack_start_sum = __start_sum_addr(sbi);
+	cp_payload = __cp_payload(sbi);
+	if (cp_pack_start_sum < cp_payload + 1 ||
+		cp_pack_start_sum > blocks_per_seg - 1 -
+			NR_CURSEG_TYPE) {
+		f2fs_msg(sbi->sb, KERN_ERR,
+			"Wrong cp_pack_start_sum: %u",
+			cp_pack_start_sum);
+		return 1;
+	}
+
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
 		return 1;
@@ -2342,8 +2454,12 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
 	if (err)
 		return err;

-	return percpu_counter_init(&sbi->total_valid_inode_count, 0,
+	err = percpu_counter_init(&sbi->total_valid_inode_count, 0,
 								GFP_KERNEL);
+	if (err)
+		percpu_counter_destroy(&sbi->alloc_valid_block_count);
+
+	return err;
 }

 #ifdef CONFIG_BLK_DEV_ZONED
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -17,7 +17,7 @@
 #include "trace.h"

 static RADIX_TREE(pids, GFP_ATOMIC);
-static struct mutex pids_lock;
+static spinlock_t pids_lock;
 static struct last_io_info last_io;

 static inline void __print_last_io(void)
@@ -61,23 +61,29 @@ void f2fs_trace_pid(struct page *page)

 	set_page_private(page, (unsigned long)pid);

+retry:
 	if (radix_tree_preload(GFP_NOFS))
 		return;

-	mutex_lock(&pids_lock);
+	spin_lock(&pids_lock);
 	p = radix_tree_lookup(&pids, pid);
 	if (p == current)
 		goto out;
 	if (p)
 		radix_tree_delete(&pids, pid);

-	f2fs_radix_tree_insert(&pids, pid, current);
+	if (radix_tree_insert(&pids, pid, current)) {
+		spin_unlock(&pids_lock);
+		radix_tree_preload_end();
+		cond_resched();
+		goto retry;
+	}

 	trace_printk("%3x:%3x %4x %-16s\n",
 			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
 			pid, current->comm);
 out:
-	mutex_unlock(&pids_lock);
+	spin_unlock(&pids_lock);
 	radix_tree_preload_end();
 }

@@ -122,7 +128,7 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)

 void f2fs_build_trace_ios(void)
 {
-	mutex_init(&pids_lock);
+	spin_lock_init(&pids_lock);
 }

 #define PIDVEC_SIZE	128
@@ -150,7 +156,7 @@ void f2fs_destroy_trace_ios(void)
 	pid_t next_pid = 0;
 	unsigned int found;

-	mutex_lock(&pids_lock);
+	spin_lock(&pids_lock);
 	while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) {
 		unsigned idx;

@@ -158,5 +164,5 @@ void f2fs_destroy_trace_ios(void)
 		for (idx = 0; idx < found; idx++)
 			radix_tree_delete(&pids, pid[idx]);
 	}
-	mutex_unlock(&pids_lock);
+	spin_unlock(&pids_lock);
 }