1 files changed, 142 insertions, 41 deletions

diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 78c3f1d70f1d..9f0d3864d9f1 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -8,8 +8,8 @@
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
-#include <linux/backing-dev.h>
 #include <linux/writeback.h>
+#include <linux/sched/mm.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -18,6 +18,10 @@
 
 #include <trace/events/f2fs.h>
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+extern const struct address_space_operations f2fs_compress_aops;
+#endif
+
 void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
 {
 	if (is_inode_flag_set(inode, FI_NEW_INODE))
@@ -77,8 +81,10 @@ static int __written_first_block(struct f2fs_sb_info *sbi,
 
 	if (!__is_valid_data_blkaddr(addr))
 		return 1;
-	if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE))
+	if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE)) {
+		f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
 		return -EFSCORRUPTED;
+	}
 	return 0;
 }
 
@@ -256,8 +262,8 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		return false;
 	}
 
-	if (F2FS_I(inode)->extent_tree) {
-		struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest;
+	if (fi->extent_tree) {
+		struct extent_info *ei = &fi->extent_tree->largest;
 
 		if (ei->len &&
 			(!f2fs_is_valid_blkaddr(sbi, ei->blk,
@@ -272,8 +278,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		}
 	}
 
-	if (f2fs_has_inline_data(inode) &&
-			(!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))) {
+	if (f2fs_sanity_check_inline_data(inode)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_data, run fsck to fix",
 			  __func__, inode->i_ino, inode->i_mode);
@@ -287,22 +292,59 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		return false;
 	}
 
+	if ((fi->i_flags & F2FS_CASEFOLD_FL) && !f2fs_sb_has_casefold(sbi)) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_warn(sbi, "%s: inode (ino=%lx) has casefold flag, but casefold feature is off",
+			  __func__, inode->i_ino);
+		return false;
+	}
+
 	if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) &&
 			fi->i_flags & F2FS_COMPR_FL &&
 			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
 						i_log_cluster_size)) {
-		if (ri->i_compress_algorithm >= COMPRESS_MAX)
+		if (ri->i_compress_algorithm >= COMPRESS_MAX) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported "
+				"compress algorithm: %u, run fsck to fix",
+				  __func__, inode->i_ino,
+				  ri->i_compress_algorithm);
 			return false;
-		if (le64_to_cpu(ri->i_compr_blocks) > inode->i_blocks)
+		}
+		if (le64_to_cpu(ri->i_compr_blocks) >
+				SECTOR_TO_BLOCK(inode->i_blocks)) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			f2fs_warn(sbi, "%s: inode (ino=%lx) has inconsistent "
+				"i_compr_blocks:%llu, i_blocks:%llu, run fsck to fix",
+				  __func__, inode->i_ino,
+				  le64_to_cpu(ri->i_compr_blocks),
+				  SECTOR_TO_BLOCK(inode->i_blocks));
 			return false;
+		}
 		if (ri->i_log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
-			ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE)
+			ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported "
+				"log cluster size: %u, run fsck to fix",
+				  __func__, inode->i_ino,
+				  ri->i_log_cluster_size);
 			return false;
+		}
 	}
 
 	return true;
 }
 
+static void init_idisk_time(struct inode *inode)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+
+	fi->i_disk_time[0] = inode->i_atime;
+	fi->i_disk_time[1] = inode->i_ctime;
+	fi->i_disk_time[2] = inode->i_mtime;
+	fi->i_disk_time[3] = fi->i_crtime;
+}
+
 static int do_read_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -345,13 +387,12 @@ static int do_read_inode(struct inode *inode)
 	fi->i_flags = le32_to_cpu(ri->i_flags);
 	if (S_ISREG(inode->i_mode))
 		fi->i_flags &= ~F2FS_PROJINHERIT_FL;
-	fi->flags = 0;
+	bitmap_zero(fi->flags, FI_MAX);
 	fi->i_advise = ri->i_advise;
 	fi->i_pino = le32_to_cpu(ri->i_pino);
 	fi->i_dir_level = ri->i_dir_level;
 
-	if (f2fs_init_extent_tree(inode, &ri->i_ext))
-		set_page_dirty(node_page);
+	f2fs_init_extent_tree(inode, node_page);
 
 	get_inline_info(inode, ri);
 
@@ -376,6 +417,7 @@ static int do_read_inode(struct inode *inode)
 
 	if (!sanity_check_inode(inode, node_page)) {
 		f2fs_put_page(node_page, 1);
+		f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
 		return -EFSCORRUPTED;
 	}
 
@@ -385,6 +427,7 @@ static int do_read_inode(struct inode *inode)
 
 	/* try to recover cold bit for non-dir inode */
 	if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) {
+		f2fs_wait_on_page_writeback(node_page, NODE, true, true);
 		set_cold_node(node_page, false);
 		set_page_dirty(node_page);
 	}
@@ -425,29 +468,34 @@ static int do_read_inode(struct inode *inode)
 					(fi->i_flags & F2FS_COMPR_FL)) {
 		if (F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
 					i_log_cluster_size)) {
-			fi->i_compr_blocks = le64_to_cpu(ri->i_compr_blocks);
+			atomic_set(&fi->i_compr_blocks,
+					le64_to_cpu(ri->i_compr_blocks));
 			fi->i_compress_algorithm = ri->i_compress_algorithm;
 			fi->i_log_cluster_size = ri->i_log_cluster_size;
+			fi->i_compress_flag = le16_to_cpu(ri->i_compress_flag);
 			fi->i_cluster_size = 1 << fi->i_log_cluster_size;
 			set_inode_flag(inode, FI_COMPRESSED_FILE);
 		}
 	}
 
-	F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
-	F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
-	F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
-	F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
+	init_idisk_time(inode);
 	f2fs_put_page(node_page, 1);
 
 	stat_inc_inline_xattr(inode);
 	stat_inc_inline_inode(inode);
 	stat_inc_inline_dir(inode);
 	stat_inc_compr_inode(inode);
-	stat_add_compr_blocks(inode, F2FS_I(inode)->i_compr_blocks);
+	stat_add_compr_blocks(inode, atomic_read(&fi->i_compr_blocks));
 
 	return 0;
 }
 
+static bool is_meta_ino(struct f2fs_sb_info *sbi, unsigned int ino)
+{
+	return ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi) ||
+		ino == F2FS_COMPRESS_INO(sbi);
+}
+
 struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -459,10 +507,21 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 		return ERR_PTR(-ENOMEM);
 
 	if (!(inode->i_state & I_NEW)) {
+		if (is_meta_ino(sbi, ino)) {
+			f2fs_err(sbi, "inaccessible inode: %lu, run fsck to repair", ino);
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			ret = -EFSCORRUPTED;
+			trace_f2fs_iget_exit(inode, ret);
+			iput(inode);
+			f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
+			return ERR_PTR(ret);
+		}
+
 		trace_f2fs_iget(inode);
 		return inode;
 	}
-	if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
+
+	if (is_meta_ino(sbi, ino))
 		goto make_now;
 
 	ret = do_read_inode(inode);
@@ -475,6 +534,17 @@ make_now:
 	} else if (ino == F2FS_META_INO(sbi)) {
 		inode->i_mapping->a_ops = &f2fs_meta_aops;
 		mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
+	} else if (ino == F2FS_COMPRESS_INO(sbi)) {
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		inode->i_mapping->a_ops = &f2fs_compress_aops;
+		/*
+		 * generic_error_remove_page only truncates pages of regular
+		 * inode
+		 */
+		inode->i_mode |= S_IFREG;
+#endif
+		mapping_set_gfp_mask(inode->i_mapping,
+			GFP_NOFS | __GFP_HIGHMEM | __GFP_MOVABLE);
 	} else if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &f2fs_file_inode_operations;
 		inode->i_fop = &f2fs_file_operations;
@@ -483,7 +553,7 @@ make_now:
 		inode->i_op = &f2fs_dir_inode_operations;
 		inode->i_fop = &f2fs_dir_operations;
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
-		inode_nohighmem(inode);
+		mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (file_is_encrypt(inode))
 			inode->i_op = &f2fs_encrypted_symlink_inode_operations;
@@ -500,6 +570,15 @@ make_now:
 		goto bad_inode;
 	}
 	f2fs_set_inode_flags(inode);
+
+	if (file_should_truncate(inode) &&
+			!is_sbi_flag_set(sbi, SBI_POR_DOING)) {
+		ret = f2fs_truncate(inode);
+		if (ret)
+			goto bad_inode;
+		file_dont_truncate(inode);
+	}
+
 	unlock_new_inode(inode);
 	trace_f2fs_iget(inode);
 	return inode;
@@ -518,7 +597,7 @@ retry:
 	inode = f2fs_iget(sb, ino);
 	if (IS_ERR(inode)) {
 		if (PTR_ERR(inode) == -ENOMEM) {
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			memalloc_retry_wait(GFP_NOFS);
 			goto retry;
 		}
 	}
@@ -602,9 +681,12 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 			F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
 							i_log_cluster_size)) {
 			ri->i_compr_blocks =
-				cpu_to_le64(F2FS_I(inode)->i_compr_blocks);
+				cpu_to_le64(atomic_read(
+					&F2FS_I(inode)->i_compr_blocks));
 			ri->i_compress_algorithm =
 				F2FS_I(inode)->i_compress_algorithm;
+			ri->i_compress_flag =
+				cpu_to_le16(F2FS_I(inode)->i_compress_flag);
 			ri->i_log_cluster_size =
 				F2FS_I(inode)->i_log_cluster_size;
 		}
@@ -614,13 +696,9 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 
 	/* deleted inode */
 	if (inode->i_nlink == 0)
-		clear_inline_node(node_page);
-
-	F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
-	F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
-	F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
-	F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
+		clear_page_private_inline(node_page);
 
+	init_idisk_time(inode);
 #ifdef CONFIG_F2FS_CHECK_FS
 	f2fs_inode_chksum_set(F2FS_I_SB(inode), node_page);
 #endif
@@ -634,11 +712,13 @@ retry:
 	node_page = f2fs_get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page)) {
 		int err = PTR_ERR(node_page);
+
 		if (err == -ENOMEM) {
 			cond_resched();
 			goto retry;
 		} else if (err != -ENOENT) {
-			f2fs_stop_checkpoint(sbi, false);
+			f2fs_stop_checkpoint(sbi, false,
+					STOP_CP_REASON_UPDATE_INODE);
 		}
 		return;
 	}
@@ -666,7 +746,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 	/*
 	 * We need to balance fs here to prevent from producing dirty node pages
-	 * during the urgent cleaning time when runing out of free sections.
+	 * during the urgent cleaning time when running out of free sections.
 	 */
 	f2fs_update_inode_page(inode);
 	if (wbc && wbc->nr_to_write)
@@ -683,15 +763,18 @@ void f2fs_evict_inode(struct inode *inode)
 	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 	int err = 0;
 
-	/* some remained atomic pages should discarded */
-	if (f2fs_is_atomic_file(inode))
-		f2fs_drop_inmem_pages(inode);
+	f2fs_abort_atomic_write(inode, true);
 
 	trace_f2fs_evict_inode(inode);
 	truncate_inode_pages_final(&inode->i_data);
 
+	if ((inode->i_nlink || is_bad_inode(inode)) &&
+		test_opt(sbi, COMPRESS_CACHE) && f2fs_compressed_file(inode))
+		f2fs_invalidate_compress_pages(sbi, inode->i_ino);
+
 	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
-			inode->i_ino == F2FS_META_INO(sbi))
+			inode->i_ino == F2FS_META_INO(sbi) ||
+			inode->i_ino == F2FS_COMPRESS_INO(sbi))
 		goto out_clear;
 
 	f2fs_bug_on(sbi, get_dirty_pages(inode));
@@ -702,7 +785,7 @@ void f2fs_evict_inode(struct inode *inode)
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err) {
 		err = 0;
 		set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
@@ -712,7 +795,8 @@ void f2fs_evict_inode(struct inode *inode)
 	f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
 	f2fs_remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
 
-	sb_start_intwrite(inode->i_sb);
+	if (!is_sbi_flag_set(sbi, SBI_IS_FREEZING))
+		sb_start_intwrite(inode->i_sb);
 	set_inode_flag(inode, FI_NO_ALLOC);
 	i_size_write(inode, 0);
 retry:
@@ -728,8 +812,22 @@ retry:
 		f2fs_lock_op(sbi);
 		err = f2fs_remove_inode_page(inode);
 		f2fs_unlock_op(sbi);
-		if (err == -ENOENT)
+		if (err == -ENOENT) {
 			err = 0;
+
+			/*
+			 * in fuzzed image, another node may has the same
+			 * block address as inode's, if it was truncated
+			 * previously, truncation of inode node will fail.
+			 */
+			if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+				f2fs_warn(F2FS_I_SB(inode),
+					"f2fs_evict_inode: inconsistent node id, ino:%lu",
+					inode->i_ino);
+				f2fs_inode_synced(inode);
+				set_sbi_flag(sbi, SBI_NEED_FSCK);
+			}
+		}
 	}
 
 	/* give more chances, if ENOMEM case */
@@ -743,7 +841,8 @@ retry:
 		if (dquot_initialize_needed(inode))
 			set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
 	}
-	sb_end_intwrite(inode->i_sb);
+	if (!is_sbi_flag_set(sbi, SBI_IS_FREEZING))
+		sb_end_intwrite(inode->i_sb);
 no_delete:
 	dquot_drop(inode);
 
@@ -751,7 +850,8 @@ no_delete:
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
 	stat_dec_compr_inode(inode);
-	stat_sub_compr_blocks(inode, F2FS_I(inode)->i_compr_blocks);
+	stat_sub_compr_blocks(inode,
+			atomic_read(&F2FS_I(inode)->i_compr_blocks));
 
 	if (likely(!f2fs_cp_error(sbi) &&
 				!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
@@ -759,7 +859,7 @@ no_delete:
 	else
 		f2fs_inode_synced(inode);
 
-	/* ino == 0, if f2fs_new_inode() was failed t*/
+	/* for the case f2fs_new_inode() was failed, .i_ino is zero, skip it */
 	if (inode->i_ino)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino,
 							inode->i_ino);
@@ -815,9 +915,10 @@ void f2fs_handle_failed_inode(struct inode *inode)
 	 * so we can prevent losing this orphan when encoutering checkpoint
 	 * and following suddenly power-off.
 	 */
-	err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
+	err = f2fs_get_node_info(sbi, inode->i_ino, &ni, false);
 	if (err) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		set_inode_flag(inode, FI_FREE_NID);
 		f2fs_warn(sbi, "May loss orphan inode, run fsck to fix.");
 		goto out;
 	}