1 files changed, 180 insertions, 118 deletions

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index c235a8e4315e..1b529ace4db0 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -39,29 +39,21 @@ void _erofs_printk(struct super_block *sb, const char *fmt, ...)
 
 static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata)
 {
-	size_t len = 1 << EROFS_SB(sb)->blkszbits;
-	struct erofs_super_block *dsb;
-	u32 expected_crc, crc;
+	struct erofs_super_block *dsb = sbdata + EROFS_SUPER_OFFSET;
+	u32 len = 1 << EROFS_SB(sb)->blkszbits, crc;
 
 	if (len > EROFS_SUPER_OFFSET)
 		len -= EROFS_SUPER_OFFSET;
+	len -= offsetof(struct erofs_super_block, checksum) +
+			sizeof(dsb->checksum);
 
-	dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET, len, GFP_KERNEL);
-	if (!dsb)
-		return -ENOMEM;
-
-	expected_crc = le32_to_cpu(dsb->checksum);
-	dsb->checksum = 0;
-	/* to allow for x86 boot sectors and other oddities. */
-	crc = crc32c(~0, dsb, len);
-	kfree(dsb);
-
-	if (crc != expected_crc) {
-		erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected",
-			  crc, expected_crc);
-		return -EBADMSG;
-	}
-	return 0;
+	/* skip .magic(pre-verified) and .checksum(0) fields */
+	crc = crc32c(0x5045B54A, (&dsb->checksum) + 1, len);
+	if (crc == le32_to_cpu(dsb->checksum))
+		return 0;
+	erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected",
+		  crc, le32_to_cpu(dsb->checksum));
+	return -EBADMSG;
 }
 
 static void erofs_inode_init_once(void *ptr)
@@ -102,7 +94,7 @@ void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
 	int len, i, cnt;
 
 	*offset = round_up(*offset, 4);
-	ptr = erofs_bread(buf, *offset, EROFS_KMAP);
+	ptr = erofs_bread(buf, *offset, true);
 	if (IS_ERR(ptr))
 		return ptr;
 
@@ -118,7 +110,7 @@ void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
 	for (i = 0; i < len; i += cnt) {
 		cnt = min_t(int, sb->s_blocksize - erofs_blkoff(sb, *offset),
 			    len - i);
-		ptr = erofs_bread(buf, *offset, EROFS_KMAP);
+		ptr = erofs_bread(buf, *offset, true);
 		if (IS_ERR(ptr)) {
 			kfree(buffer);
 			return ptr;
@@ -149,7 +141,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 	struct erofs_deviceslot *dis;
 	struct file *file;
 
-	dis = erofs_read_metabuf(buf, sb, *pos, EROFS_KMAP);
+	dis = erofs_read_metabuf(buf, sb, *pos, false);
 	if (IS_ERR(dis))
 		return PTR_ERR(dis);
 
@@ -173,12 +165,20 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 				filp_open(dif->path, O_RDONLY | O_LARGEFILE, 0) :
 				bdev_file_open_by_path(dif->path,
 						BLK_OPEN_READ, sb->s_type, NULL);
-		if (IS_ERR(file))
+		if (IS_ERR(file)) {
+			if (file == ERR_PTR(-ENOTBLK))
+				return -EINVAL;
 			return PTR_ERR(file);
+		}
 
 		if (!erofs_is_fileio_mode(sbi)) {
 			dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file),
 					&dif->dax_part_off, NULL, NULL);
+			if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) {
+				erofs_info(sb, "DAX unsupported by %s. Turning off DAX.",
+					   dif->path);
+				clear_opt(&sbi->opt, DAX_ALWAYS);
+			}
 		} else if (!S_ISREG(file_inode(file)->i_mode)) {
 			fput(file);
 			return -EINVAL;
@@ -186,8 +186,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 		dif->file = file;
 	}
 
-	dif->blocks = le32_to_cpu(dis->blocks);
-	dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr);
+	dif->blocks = le32_to_cpu(dis->blocks_lo);
+	dif->uniaddr = le32_to_cpu(dis->uniaddr_lo);
 	sbi->total_blocks += dif->blocks;
 	*pos += EROFS_DEVT_SLOT_SIZE;
 	return 0;
@@ -203,7 +203,7 @@ static int erofs_scan_devices(struct super_block *sb,
 	struct erofs_device_info *dif;
 	int id, err = 0;
 
-	sbi->total_blocks = sbi->primarydevice_blocks;
+	sbi->total_blocks = sbi->dif0.blocks;
 	if (!erofs_sb_has_device_table(sbi))
 		ondisk_extradevs = 0;
 	else
@@ -215,8 +215,13 @@ static int erofs_scan_devices(struct super_block *sb,
 			  ondisk_extradevs, sbi->devs->extra_devices);
 		return -EINVAL;
 	}
-	if (!ondisk_extradevs)
+	if (!ondisk_extradevs) {
+		if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) {
+			erofs_info(sb, "DAX unsupported by block device. Turning off DAX.");
+			clear_opt(&sbi->opt, DAX_ALWAYS);
+		}
 		return 0;
+	}
 
 	if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb))
 		sbi->devs->flatdev = true;
@@ -263,7 +268,7 @@ static int erofs_read_superblock(struct super_block *sb)
 	void *data;
 	int ret;
 
-	data = erofs_read_metabuf(&buf, sb, 0, EROFS_KMAP);
+	data = erofs_read_metabuf(&buf, sb, 0, false);
 	if (IS_ERR(data)) {
 		erofs_err(sb, "cannot read erofs superblock");
 		return PTR_ERR(data);
@@ -276,7 +281,7 @@ static int erofs_read_superblock(struct super_block *sb)
 		goto out;
 	}
 
-	sbi->blkszbits  = dsb->blkszbits;
+	sbi->blkszbits = dsb->blkszbits;
 	if (sbi->blkszbits < 9 || sbi->blkszbits > PAGE_SHIFT) {
 		erofs_err(sb, "blkszbits %u isn't supported", sbi->blkszbits);
 		goto out;
@@ -307,7 +312,7 @@ static int erofs_read_superblock(struct super_block *sb)
 			  sbi->sb_size);
 		goto out;
 	}
-	sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks);
+	sbi->dif0.blocks = le32_to_cpu(dsb->blocks_lo);
 	sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
 #ifdef CONFIG_EROFS_FS_XATTR
 	sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr);
@@ -316,31 +321,39 @@ static int erofs_read_superblock(struct super_block *sb)
 	sbi->xattr_filter_reserved = dsb->xattr_filter_reserved;
 #endif
 	sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
-	sbi->root_nid = le16_to_cpu(dsb->root_nid);
+	if (erofs_sb_has_48bit(sbi) && dsb->rootnid_8b) {
+		sbi->root_nid = le64_to_cpu(dsb->rootnid_8b);
+		sbi->dif0.blocks = sbi->dif0.blocks |
+				((u64)le16_to_cpu(dsb->rb.blocks_hi) << 32);
+	} else {
+		sbi->root_nid = le16_to_cpu(dsb->rb.rootnid_2b);
+	}
 	sbi->packed_nid = le64_to_cpu(dsb->packed_nid);
+	if (erofs_sb_has_metabox(sbi)) {
+		if (sbi->sb_size <= offsetof(struct erofs_super_block,
+					     metabox_nid))
+			return -EFSCORRUPTED;
+		sbi->metabox_nid = le64_to_cpu(dsb->metabox_nid);
+		if (sbi->metabox_nid & BIT_ULL(EROFS_DIRENT_NID_METABOX_BIT))
+			return -EFSCORRUPTED;	/* self-loop detection */
+	}
 	sbi->inos = le64_to_cpu(dsb->inos);
 
-	sbi->build_time = le64_to_cpu(dsb->build_time);
-	sbi->build_time_nsec = le32_to_cpu(dsb->build_time_nsec);
-
+	sbi->epoch = (s64)le64_to_cpu(dsb->epoch);
+	sbi->fixed_nsec = le32_to_cpu(dsb->fixed_nsec);
 	super_set_uuid(sb, (void *)dsb->uuid, sizeof(dsb->uuid));
 
-	ret = strscpy(sbi->volume_name, dsb->volume_name,
-		      sizeof(dsb->volume_name));
-	if (ret < 0) {	/* -E2BIG */
-		erofs_err(sb, "bad volume name without NIL terminator");
-		ret = -EFSCORRUPTED;
-		goto out;
-	}
-
 	/* parse on-disk compression configurations */
 	ret = z_erofs_parse_cfgs(sb, dsb);
 	if (ret < 0)
 		goto out;
 
-	/* handle multiple devices */
 	ret = erofs_scan_devices(sb, dsb);
 
+	if (erofs_sb_has_48bit(sbi))
+		erofs_info(sb, "EXPERIMENTAL 48-bit layout support in use. Use at your own risk!");
+	if (erofs_sb_has_metabox(sbi))
+		erofs_info(sb, "EXPERIMENTAL metadata compression support in use. Use at your own risk!");
 	if (erofs_is_fscache_mode(sb))
 		erofs_info(sb, "[deprecated] fscache-based on-demand read feature in use. Use at your own risk!");
 out:
@@ -364,15 +377,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi)
 }
 
 enum {
-	Opt_user_xattr,
-	Opt_acl,
-	Opt_cache_strategy,
-	Opt_dax,
-	Opt_dax_enum,
-	Opt_device,
-	Opt_fsid,
-	Opt_domain_id,
-	Opt_err
+	Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum,
+	Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_fsoffset,
 };
 
 static const struct constant_table erofs_param_cache_strategy[] = {
@@ -398,6 +404,8 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
 	fsparam_string("device",	Opt_device),
 	fsparam_string("fsid",		Opt_fsid),
 	fsparam_string("domain_id",	Opt_domain_id),
+	fsparam_flag_no("directio",	Opt_directio),
+	fsparam_u64("fsoffset",		Opt_fsoffset),
 	{}
 };
 
@@ -511,30 +519,69 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
 		break;
 #endif
-	default:
-		return -ENOPARAM;
+	case Opt_directio:
+#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
+		if (result.boolean)
+			set_opt(&sbi->opt, DIRECT_IO);
+		else
+			clear_opt(&sbi->opt, DIRECT_IO);
+#else
+		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+#endif
+		break;
+	case Opt_fsoffset:
+		sbi->dif0.fsoff = result.uint_64;
+		break;
 	}
 	return 0;
 }
 
-static struct inode *erofs_nfs_get_inode(struct super_block *sb,
-					 u64 ino, u32 generation)
+static int erofs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
+			   struct inode *parent)
 {
-	return erofs_iget(sb, ino);
+	erofs_nid_t nid = EROFS_I(inode)->nid;
+	int len = parent ? 6 : 3;
+
+	if (*max_len < len) {
+		*max_len = len;
+		return FILEID_INVALID;
+	}
+
+	fh[0] = (u32)(nid >> 32);
+	fh[1] = (u32)(nid & 0xffffffff);
+	fh[2] = inode->i_generation;
+
+	if (parent) {
+		nid = EROFS_I(parent)->nid;
+
+		fh[3] = (u32)(nid >> 32);
+		fh[4] = (u32)(nid & 0xffffffff);
+		fh[5] = parent->i_generation;
+	}
+
+	*max_len = len;
+	return parent ? FILEID_INO64_GEN_PARENT : FILEID_INO64_GEN;
 }
 
 static struct dentry *erofs_fh_to_dentry(struct super_block *sb,
 		struct fid *fid, int fh_len, int fh_type)
 {
-	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
-				    erofs_nfs_get_inode);
+	if ((fh_type != FILEID_INO64_GEN &&
+	     fh_type != FILEID_INO64_GEN_PARENT) || fh_len < 3)
+		return NULL;
+
+	return d_obtain_alias(erofs_iget(sb,
+		((u64)fid->raw[0] << 32) | fid->raw[1]));
 }
 
 static struct dentry *erofs_fh_to_parent(struct super_block *sb,
 		struct fid *fid, int fh_len, int fh_type)
 {
-	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
-				    erofs_nfs_get_inode);
+	if (fh_type != FILEID_INO64_GEN_PARENT || fh_len < 6)
+		return NULL;
+
+	return d_obtain_alias(erofs_iget(sb,
+		((u64)fid->raw[3] << 32) | fid->raw[4]));
 }
 
 static struct dentry *erofs_get_parent(struct dentry *child)
@@ -550,7 +597,7 @@ static struct dentry *erofs_get_parent(struct dentry *child)
 }
 
 static const struct export_operations erofs_export_ops = {
-	.encode_fh = generic_encode_ino32_fh,
+	.encode_fh = erofs_encode_fh,
 	.fh_to_dentry = erofs_fh_to_dentry,
 	.fh_to_parent = erofs_fh_to_parent,
 	.get_parent = erofs_get_parent,
@@ -602,9 +649,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 			return -EINVAL;
 		}
 
-		sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev,
-						  &sbi->dax_part_off,
-						  NULL, NULL);
+		sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev,
+				&sbi->dif0.dax_part_off, NULL, NULL);
 	}
 
 	err = erofs_read_superblock(sb);
@@ -626,14 +672,17 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		}
 	}
 
-	if (test_opt(&sbi->opt, DAX_ALWAYS)) {
-		if (!sbi->dax_dev) {
-			errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
-			clear_opt(&sbi->opt, DAX_ALWAYS);
-		} else if (sbi->blkszbits != PAGE_SHIFT) {
-			errorfc(fc, "unsupported blocksize for DAX");
-			clear_opt(&sbi->opt, DAX_ALWAYS);
-		}
+	if (sbi->dif0.fsoff) {
+		if (sbi->dif0.fsoff & (sb->s_blocksize - 1))
+			return invalfc(fc, "fsoffset %llu is not aligned to block size %lu",
+				       sbi->dif0.fsoff, sb->s_blocksize);
+		if (erofs_is_fscache_mode(sb))
+			return invalfc(fc, "cannot use fsoffset in fscache mode");
+	}
+
+	if (test_opt(&sbi->opt, DAX_ALWAYS) && sbi->blkszbits != PAGE_SHIFT) {
+		erofs_info(sb, "unsupported blocksize for DAX");
+		clear_opt(&sbi->opt, DAX_ALWAYS);
 	}
 
 	sb->s_time_gran = 1;
@@ -645,9 +694,22 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	else
 		sb->s_flags &= ~SB_POSIXACL;
 
-#ifdef CONFIG_EROFS_FS_ZIP
-	xa_init(&sbi->managed_pslots);
-#endif
+	err = z_erofs_init_super(sb);
+	if (err)
+		return err;
+
+	if (erofs_sb_has_fragments(sbi) && sbi->packed_nid) {
+		inode = erofs_iget(sb, sbi->packed_nid);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+		sbi->packed_inode = inode;
+	}
+	if (erofs_sb_has_metabox(sbi)) {
+		inode = erofs_iget(sb, sbi->metabox_nid);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+		sbi->metabox_inode = inode;
+	}
 
 	inode = erofs_iget(sb, sbi->root_nid);
 	if (IS_ERR(inode))
@@ -659,24 +721,11 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		iput(inode);
 		return -EINVAL;
 	}
-
 	sb->s_root = d_make_root(inode);
 	if (!sb->s_root)
 		return -ENOMEM;
 
 	erofs_shrinker_register(sb);
-	if (erofs_sb_has_fragments(sbi) && sbi->packed_nid) {
-		sbi->packed_inode = erofs_iget(sb, sbi->packed_nid);
-		if (IS_ERR(sbi->packed_inode)) {
-			err = PTR_ERR(sbi->packed_inode);
-			sbi->packed_inode = NULL;
-			return err;
-		}
-	}
-	err = erofs_init_managed_cache(sb);
-	if (err)
-		return err;
-
 	err = erofs_xattr_prefixes_init(sb);
 	if (err)
 		return err;
@@ -686,6 +735,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
+	sbi->dir_ra_bytes = EROFS_DIR_RA_BYTES;
 	erofs_info(sb, "mounted with root inode @ nid %llu.", sbi->root_nid);
 	return 0;
 }
@@ -703,16 +753,18 @@ static int erofs_fc_get_tree(struct fs_context *fc)
 			GET_TREE_BDEV_QUIET_LOOKUP : 0);
 #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
 	if (ret == -ENOTBLK) {
+		struct file *file;
+
 		if (!fc->source)
 			return invalf(fc, "No source specified");
-		sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0);
-		if (IS_ERR(sbi->fdev))
-			return PTR_ERR(sbi->fdev);
+		file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0);
+		if (IS_ERR(file))
+			return PTR_ERR(file);
+		sbi->dif0.file = file;
 
-		if (S_ISREG(file_inode(sbi->fdev)->i_mode) &&
-		    sbi->fdev->f_mapping->a_ops->read_folio)
+		if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) &&
+		    sbi->dif0.file->f_mapping->a_ops->read_folio)
 			return get_tree_nodev(fc, erofs_fc_fill_super);
-		fput(sbi->fdev);
 	}
 #endif
 	return ret;
@@ -763,19 +815,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs)
 	kfree(devs);
 }
 
-static void erofs_fc_free(struct fs_context *fc)
+static void erofs_sb_free(struct erofs_sb_info *sbi)
 {
-	struct erofs_sb_info *sbi = fc->s_fs_info;
-
-	if (!sbi)
-		return;
-
 	erofs_free_dev_context(sbi->devs);
 	kfree(sbi->fsid);
 	kfree(sbi->domain_id);
+	if (sbi->dif0.file)
+		fput(sbi->dif0.file);
 	kfree(sbi);
 }
 
+static void erofs_fc_free(struct fs_context *fc)
+{
+	struct erofs_sb_info *sbi = fc->s_fs_info;
+
+	if (sbi) /* free here if an error occurs before transferring to sb */
+		erofs_sb_free(sbi);
+}
+
 static const struct fs_context_operations erofs_context_ops = {
 	.parse_param	= erofs_fc_parse_param,
 	.get_tree       = erofs_fc_get_tree,
@@ -805,23 +862,31 @@ static int erofs_init_fs_context(struct fs_context *fc)
 	return 0;
 }
 
+static void erofs_drop_internal_inodes(struct erofs_sb_info *sbi)
+{
+	iput(sbi->packed_inode);
+	sbi->packed_inode = NULL;
+	iput(sbi->metabox_inode);
+	sbi->metabox_inode = NULL;
+#ifdef CONFIG_EROFS_FS_ZIP
+	iput(sbi->managed_cache);
+	sbi->managed_cache = NULL;
+#endif
+}
+
 static void erofs_kill_sb(struct super_block *sb)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 
-	if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev)
+	if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) ||
+	    sbi->dif0.file)
 		kill_anon_super(sb);
 	else
 		kill_block_super(sb);
-
-	erofs_free_dev_context(sbi->devs);
-	fs_put_dax(sbi->dax_dev, NULL);
+	erofs_drop_internal_inodes(sbi);
+	fs_put_dax(sbi->dif0.dax_dev, NULL);
 	erofs_fscache_unregister_fs(sb);
-	kfree(sbi->fsid);
-	kfree(sbi->domain_id);
-	if (sbi->fdev)
-		fput(sbi->fdev);
-	kfree(sbi);
+	erofs_sb_free(sbi);
 	sb->s_fs_info = NULL;
 }
 
@@ -829,17 +894,10 @@ static void erofs_put_super(struct super_block *sb)
 {
 	struct erofs_sb_info *const sbi = EROFS_SB(sb);
 
-	DBG_BUGON(!sbi);
-
 	erofs_unregister_sysfs(sb);
 	erofs_shrinker_unregister(sb);
 	erofs_xattr_prefixes_cleanup(sb);
-#ifdef CONFIG_EROFS_FS_ZIP
-	iput(sbi->managed_cache);
-	sbi->managed_cache = NULL;
-#endif
-	iput(sbi->packed_inode);
-	sbi->packed_inode = NULL;
+	erofs_drop_internal_inodes(sbi);
 	erofs_free_dev_context(sbi->devs);
 	sbi->devs = NULL;
 	erofs_fscache_unregister_fs(sb);
@@ -947,12 +1005,16 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",dax=always");
 	if (test_opt(opt, DAX_NEVER))
 		seq_puts(seq, ",dax=never");
+	if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO))
+		seq_puts(seq, ",directio");
 #ifdef CONFIG_EROFS_FS_ONDEMAND
 	if (sbi->fsid)
 		seq_printf(seq, ",fsid=%s", sbi->fsid);
 	if (sbi->domain_id)
 		seq_printf(seq, ",domain_id=%s", sbi->domain_id);
 #endif
+	if (sbi->dif0.fsoff)
+		seq_printf(seq, ",fsoffset=%llu", sbi->dif0.fsoff);
 	return 0;
 }