[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250517090544.2687651-1-shengyong1@xiaomi.com>
Date: Sat, 17 May 2025 17:05:43 +0800
From: Sheng Yong <shengyong2021@...il.com>
To: xiang@...nel.org,
hsiangkao@...ux.alibaba.com,
chao@...nel.org,
zbestahu@...il.com,
jefflexu@...ux.alibaba.com,
dhavale@...gle.com,
lihongbo22@...wei.com
Cc: linux-erofs@...ts.ozlabs.org,
linux-kernel@...r.kernel.org,
Sheng Yong <shengyong1@...omi.com>,
Wang Shuai <wangshuai12@...omi.com>
Subject: [PATCH v7] erofs: add 'fsoffset' mount option to specify filesystem offset
From: Sheng Yong <shengyong1@...omi.com>
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 <shengyong1@...omi.com>
Signed-off-by: Wang Shuai <wangshuai12@...omi.com>
---
Documentation/filesystems/erofs.rst | 1 +
fs/erofs/data.c | 5 +++--
fs/erofs/fileio.c | 3 ++-
fs/erofs/internal.h | 3 ++-
fs/erofs/super.c | 16 +++++++++++++++-
fs/erofs/zdata.c | 3 ++-
6 files changed, 25 insertions(+), 6 deletions(-)
---
v7: * fix documentation and some codin style
* check alignment after erofs_read_superblock and return error in
fscache mode
* update commit message
v6: * fix fsoffset value type in documentation
* change `off' type to u64
https://lore.kernel.org/linux-erofs/6b456e0d-04cf-4ecd-a23a-e91c7d58b592@linux.alibaba.com
v5: * fix fsoffset on multiple device by adding off when creating io
request, erofs_map_device selects the target device an only
primary device has an off
* remove unnecessary checks of fsoffset value
* try to combine off and dax_part_off, but it is not easy to do
that, because dax_part_off is not needed when reading metadata
https://lore.kernel.org/linux-erofs/f62b0d18-f5af-4063-b644-f6b8069ca200@gmail.com
v4: * change mount option `offset=x' to `fsoffset=x'
https://lore.kernel.org/linux-erofs/c5110e03-90ea-40be-b05f-bc920332a1e1@linux.alibaba.com
v3: * rename `offs' to `off'
* parse offset using fsparam_u64 and validate it in fill_super
* update bi_sector inline
https://lore.kernel.org/linux-erofs/98585dd8-d0b6-4000-b46d-a08c64eae44d@linux.alibaba.com
v2: * add a new mount option `offset=X' for start offset, and offset
should be aligned to PAGE_SIZE
* add start offset for both file-backed and bdev-based mounts
https://lore.kernel.org/linux-erofs/0725c2ec-528c-42a8-9557-4713e7e35153@linux.alibaba.com
v1: https://lore.kernel.org/all/20250324022849.2715578-1-shengyong1@xiaomi.com/
diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index c293f8e37468..11b0f8635f04 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/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=%lu Specify image offset for the primary device.
=================== =========================================================
Sysfs Entries
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 2409d2ab0c28..6a329c329f43 100644
--- a/fs/erofs/data.c
+++ b/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;
}
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index 60c7cc4c105c..fb1a01198fde 100644
--- a/fs/erofs/fileio.c
+++ b/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))
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 4ac188d5d894..a32c03a80c70 100644
--- a/fs/erofs/internal.h
+++ b/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;
};
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 79ab268fa57a..8dd57c272014 100644
--- a/fs/erofs/super.c
+++ b/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;
}
@@ -621,6 +625,14 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
}
}
+ if (sbi->dif0.fsoff) {
+ if (sbi->dif0.fsoff & ((1 << sbi->blkszbits) - 1))
+ return invalfc(fc, "fsoffset %llu not aligned to block size",
+ sbi->dif0.fsoff);
+ 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.");
@@ -950,6 +962,8 @@ 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;
}
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index b8e6b76c23d5..4f34b63d026e 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1707,7 +1707,8 @@ 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;
--
2.43.0
Powered by blists - more mailing lists