[PATCH v6] vfs: fix copy_file_range regression in cross-fs copies
From: Luis Henriques <hidden>
Date: 2021-02-18 19:08:42
Also in:
ceph-devel, linux-fsdevel, linux-nfs, lkml
Subsystem:
filesystems (vfs and infrastructure), kernel nfsd, sunrpc, and lockd servers, the rest · Maintainers:
Alexander Viro, Christian Brauner, Chuck Lever, Jeff Layton, Linus Torvalds
A regression has been reported by Nicolas Boichat, found while using the
copy_file_range syscall to copy a tracefs file. Before commit
5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices") the
kernel would return -EXDEV to userspace when trying to copy a file across
different filesystems. After this commit, the syscall doesn't fail anymore
and instead returns zero (zero bytes copied), as this file's content is
generated on-the-fly and thus reports a size of zero.
This patch restores some cross-filesystem copy restrictions that existed
prior to commit 5dae222a5ff0 ("vfs: allow copy_file_range to copy across
devices"). Filesystems are still allowed to fall-back to the VFS
generic_copy_file_range() implementation, but that has now to be done
explicitly.
nfsd is also modified to fall-back into generic_copy_file_range() in case
vfs_copy_file_range() fails with -EOPNOTSUPP or -EXDEV.
Fixes: 5dae222a5ff0 ("vfs: allow copy_file_range to copy across devices")
Link: https://lore.kernel.org/linux-fsdevel/20210212044405.4120619-1-drinkcat@chromium.org/ (local)
Link: https://lore.kernel.org/linux-fsdevel/CANMq1KDZuxir2LM5jOTm0xx+BnvW=ZmpsG47CyHFJwnw7zSX6Q@mail.gmail.com/ (local)
Link: https://lore.kernel.org/linux-fsdevel/20210126135012.1.If45b7cdc3ff707bc1efa17f5366057d60603c45f@changeid/ (local)
Reported-by: Nicolas Boichat <redacted>
Signed-off-by: Luis Henriques <redacted>
---
And v6 is upon us. Behold!
Changes since v5
- check if ->copy_file_range is NULL before calling it
Changes since v4
- nfsd falls-back to generic_copy_file_range() only *if* it gets -EOPNOTSUPP
or -EXDEV.
Changes since v3
- dropped the COPY_FILE_SPLICE flag
- kept the f_op's checks early in generic_copy_file_checks, implementing
Amir's suggestions
- modified nfsd to use generic_copy_file_range()
Changes since v2
- do all the required checks earlier, in generic_copy_file_checks(),
adding new checks for ->remap_file_range
- new COPY_FILE_SPLICE flag
- don't remove filesystem's fallback to generic_copy_file_range()
- updated commit changelog (and subject)
Changes since v1 (after Amir review)
- restored do_copy_file_range() helper
- return -EOPNOTSUPP if fs doesn't implement CFR
- updated commit description
fs/nfsd/vfs.c | 8 +++++++-
fs/read_write.c | 53 ++++++++++++++++++++++++-------------------------
2 files changed, 33 insertions(+), 28 deletions(-)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 04937e51de56..23dab0fa9087 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c@@ -568,6 +568,7 @@ __be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos, ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, u64 dst_pos, u64 count) { + ssize_t ret; /* * Limit copy to 4MB to prevent indefinitely blocking an nfsd
@@ -578,7 +579,12 @@ ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, * limit like this and pipeline multiple COPY requests. */ count = min_t(u64, count, 1 << 22); - return vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0); + ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0); + + if (ret == -EOPNOTSUPP || ret == -EXDEV) + ret = generic_copy_file_range(src, src_pos, dst, dst_pos, + count, 0); + return ret; } __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp,
diff --git a/fs/read_write.c b/fs/read_write.c
index 75f764b43418..0348aaa9e237 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c@@ -1388,28 +1388,6 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, } EXPORT_SYMBOL(generic_copy_file_range); -static ssize_t do_copy_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t len, unsigned int flags) -{ - /* - * Although we now allow filesystems to handle cross sb copy, passing - * a file of the wrong filesystem type to filesystem driver can result - * in an attempt to dereference the wrong type of ->private_data, so - * avoid doing that until we really have a good reason. NFS defines - * several different file_system_type structures, but they all end up - * using the same ->copy_file_range() function pointer. - */ - if (file_out->f_op->copy_file_range && - file_out->f_op->copy_file_range == file_in->f_op->copy_file_range) - return file_out->f_op->copy_file_range(file_in, pos_in, - file_out, pos_out, - len, flags); - - return generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, - flags); -} - /* * Performs necessary checks before doing a file copy *
@@ -1427,6 +1405,25 @@ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, loff_t size_in; int ret; + /* + * Although we now allow filesystems to handle cross sb copy, passing + * a file of the wrong filesystem type to filesystem driver can result + * in an attempt to dereference the wrong type of ->private_data, so + * avoid doing that until we really have a good reason. NFS defines + * several different file_system_type structures, but they all end up + * using the same ->copy_file_range() function pointer. + */ + if (file_out->f_op->copy_file_range) { + if (file_in->f_op->copy_file_range != + file_out->f_op->copy_file_range) + return -EXDEV; + } else if (file_in->f_op->remap_file_range) { + if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) + return -EXDEV; + } else { + return -EOPNOTSUPP; + } + ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret;
@@ -1499,8 +1496,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * Try cloning first, this is supported by more file systems, and * more efficient if both clone and copy are supported (e.g. NFS). */ - if (file_in->f_op->remap_file_range && - file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { + if (file_in->f_op->remap_file_range) { loff_t cloned; cloned = file_in->f_op->remap_file_range(file_in, pos_in,
@@ -1511,11 +1507,14 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, ret = cloned; goto done; } + /* Resort to copy_file_range if implemented. */ + ret = -EOPNOTSUPP; } - ret = do_copy_file_range(file_in, pos_in, file_out, pos_out, len, - flags); - WARN_ON_ONCE(ret == -EOPNOTSUPP); + if (file_out->f_op->copy_file_range) + ret = file_out->f_op->copy_file_range(file_in, pos_in, + file_out, pos_out, + len, flags); done: if (ret > 0) { fsnotify_access(file_in);