erofs: add 'fsoffset' mount option to specify filesystem offset

When attempting to use an archive file, such as APEX on android,
as a file-backed mount source, it fails because EROFS image within
the archive file does not start at offset 0. As a result, a loop
or a dm device is still needed to attach the image file at an
appropriate offset first. Similarly, if an EROFS image within a
block device does not start at offset 0, it cannot be mounted
directly either.

To address this issue, this patch adds a new mount option `fsoffset=x'
to accept a start offset for the primary device. The offset should be
aligned to the block size. EROFS will add this offset before performing
read requests.

Signed-off-by: Sheng Yong <[email protected]>
Signed-off-by: Wang Shuai <[email protected]>
Reviewed-by: Gao Xiang <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
[ Gao Xiang: minor update on documentation and the error message. ]
Reviewed-by: Hongbo Li <[email protected]>
Signed-off-by: Gao Xiang <[email protected]>

Author: Sheng Yong

Documentation/filesystems/erofs.rst

@@ -128,6 +128,7 @@ device=%s              Specify a path to an extra device to be used together.
 fsid=%s                Specify a filesystem image ID for Fscache back-end.
 domain_id=%s           Specify a domain ID in fscache mode so that different images
                        with the same blobs under a given domain ID can share storage.
+fsoffset=%llu          Specify block-aligned filesystem offset for the primary device.
 ===================    =========================================================
 
 Sysfs Entries

fs/erofs/data.c

@@ -27,7 +27,7 @@ void erofs_put_metabuf(struct erofs_buf *buf)
 
 void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, bool need_kmap)
 {
-	pgoff_t index = offset >> PAGE_SHIFT;
+	pgoff_t index = (buf->off + offset) >> PAGE_SHIFT;
 	struct folio *folio = NULL;
 
 	if (buf->page) {
@@ -54,6 +54,7 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb)
 	struct erofs_sb_info *sbi = EROFS_SB(sb);
 
 	buf->file = NULL;
+	buf->off = sbi->dif0.fsoff;
 	if (erofs_is_fileio_mode(sbi)) {
 		buf->file = sbi->dif0.file;	/* some fs like FUSE needs it */
 		buf->mapping = buf->file->f_mapping;
@@ -299,7 +300,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		iomap->private = buf.base;
 	} else {
 		iomap->type = IOMAP_MAPPED;
-		iomap->addr = mdev.m_pa;
+		iomap->addr = mdev.m_dif->fsoff + mdev.m_pa;
 		if (flags & IOMAP_DAX)
 			iomap->addr += mdev.m_dif->dax_part_off;
 	}

fs/erofs/fileio.c

@@ -147,7 +147,8 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio)
 				if (err)
 					break;
 				io->rq = erofs_fileio_rq_alloc(&io->dev);
-				io->rq->bio.bi_iter.bi_sector = io->dev.m_pa >> 9;
+				io->rq->bio.bi_iter.bi_sector =
+					(io->dev.m_dif->fsoff + io->dev.m_pa) >> 9;
 				attached = 0;
 			}
 			if (!bio_add_folio(&io->rq->bio, folio, len, cur))

fs/erofs/internal.h

@@ -44,7 +44,7 @@ struct erofs_device_info {
 	struct erofs_fscache *fscache;
 	struct file *file;
 	struct dax_device *dax_dev;
-	u64 dax_part_off;
+	u64 fsoff, dax_part_off;
 
 	erofs_blk_t blocks;
 	erofs_blk_t uniaddr;
@@ -199,6 +199,7 @@ enum {
 struct erofs_buf {
 	struct address_space *mapping;
 	struct file *file;
+	u64 off;
 	struct page *page;
 	void *base;
 };

fs/erofs/super.c

@@ -359,7 +359,7 @@ 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_directio,
+	Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_fsoffset,
 };
 
 static const struct constant_table erofs_param_cache_strategy[] = {
@@ -386,6 +386,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
 	fsparam_string("fsid",		Opt_fsid),
 	fsparam_string("domain_id",	Opt_domain_id),
 	fsparam_flag_no("directio",	Opt_directio),
+	fsparam_u64("fsoffset",		Opt_fsoffset),
 	{}
 };
 
@@ -509,6 +510,9 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		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;
 }
@@ -649,6 +653,14 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		}
 	}
 
+	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)) {
 		if (!sbi->dif0.dax_dev) {
 			errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
@@ -978,6 +990,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 	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;
 }
 

fs/erofs/zdata.c

@@ -1737,7 +1737,8 @@ static void z_erofs_submit_queue(struct z_erofs_frontend *f,
 					bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
 							REQ_OP_READ, GFP_NOIO);
 				bio->bi_end_io = z_erofs_endio;
-				bio->bi_iter.bi_sector = cur >> 9;
+				bio->bi_iter.bi_sector =
+						(mdev.m_dif->fsoff + cur) >> 9;
 				bio->bi_private = q[JQ_SUBMIT];
 				if (readahead)
 					bio->bi_opf |= REQ_RAHEAD;