summaryrefslogtreecommitdiff
path: root/fs/fuse/inode.c
diff options
context:
space:
mode:
authorGreg Kurz <groug@kaod.org>2021-05-20 18:46:54 +0300
committerMiklos Szeredi <mszeredi@redhat.com>2021-06-22 10:15:35 +0300
commit2d82ab251ef0f6e7716279b04e9b5a01a86ca530 (patch)
tree4233156b8d38ccd5db6bdecf56d16c23afa58def /fs/fuse/inode.c
parent49221cf86d18bb66fe95d3338cb33bd4b9880ca5 (diff)
downloadlinux-2d82ab251ef0f6e7716279b04e9b5a01a86ca530.tar.xz
virtiofs: propagate sync() to file server
Even if POSIX doesn't mandate it, linux users legitimately expect sync() to flush all data and metadata to physical storage when it is located on the same system. This isn't happening with virtiofs though: sync() inside the guest returns right away even though data still needs to be flushed from the host page cache. This is easily demonstrated by doing the following in the guest: $ dd if=/dev/zero of=/mnt/foo bs=1M count=5K ; strace -T -e sync sync 5120+0 records in 5120+0 records out 5368709120 bytes (5.4 GB, 5.0 GiB) copied, 5.22224 s, 1.0 GB/s sync() = 0 <0.024068> and start the following in the host when the 'dd' command completes in the guest: $ strace -T -e fsync /usr/bin/sync virtiofs/foo fsync(3) = 0 <10.371640> There are no good reasons not to honor the expected behavior of sync() actually: it gives an unrealistic impression that virtiofs is super fast and that data has safely landed on HW, which isn't the case obviously. Implement a ->sync_fs() superblock operation that sends a new FUSE_SYNCFS request type for this purpose. Provision a 64-bit placeholder for possible future extensions. Since the file server cannot handle the wait == 0 case, we skip it to avoid a gratuitous roundtrip. Note that this is per-superblock: a FUSE_SYNCFS is send for the root mount and for each submount. Like with FUSE_FSYNC and FUSE_FSYNCDIR, lack of support for FUSE_SYNCFS in the file server is treated as permanent success. This ensures compatibility with older file servers: the client will get the current behavior of sync() not being propagated to the file server. Note that such an operation allows the file server to DoS sync(). Since a typical FUSE file server is an untrusted piece of software running in userspace, this is disabled by default. Only enable it with virtiofs for now since virtiofsd is supposedly trusted by the guest kernel. Reported-by: Robert Krawitz <rlk@redhat.com> Signed-off-by: Greg Kurz <groug@kaod.org> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Diffstat (limited to 'fs/fuse/inode.c')
-rw-r--r--fs/fuse/inode.c40
1 files changed, 40 insertions, 0 deletions
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 393e36b74dc4..93d28dc1f572 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -506,6 +506,45 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf)
return err;
}
+static int fuse_sync_fs(struct super_block *sb, int wait)
+{
+ struct fuse_mount *fm = get_fuse_mount_super(sb);
+ struct fuse_conn *fc = fm->fc;
+ struct fuse_syncfs_in inarg;
+ FUSE_ARGS(args);
+ int err;
+
+ /*
+ * Userspace cannot handle the wait == 0 case. Avoid a
+ * gratuitous roundtrip.
+ */
+ if (!wait)
+ return 0;
+
+ /* The filesystem is being unmounted. Nothing to do. */
+ if (!sb->s_root)
+ return 0;
+
+ if (!fc->sync_fs)
+ return 0;
+
+ memset(&inarg, 0, sizeof(inarg));
+ args.in_numargs = 1;
+ args.in_args[0].size = sizeof(inarg);
+ args.in_args[0].value = &inarg;
+ args.opcode = FUSE_SYNCFS;
+ args.nodeid = get_node_id(sb->s_root->d_inode);
+ args.out_numargs = 0;
+
+ err = fuse_simple_request(fm, &args);
+ if (err == -ENOSYS) {
+ fc->sync_fs = 0;
+ err = 0;
+ }
+
+ return err;
+}
+
enum {
OPT_SOURCE,
OPT_SUBTYPE,
@@ -909,6 +948,7 @@ static const struct super_operations fuse_super_operations = {
.put_super = fuse_put_super,
.umount_begin = fuse_umount_begin,
.statfs = fuse_statfs,
+ .sync_fs = fuse_sync_fs,
.show_options = fuse_show_options,
};