[Virtio-fs] [PATCH 1/2] virtiofsd: cap-ng helpers

[Dr. David Alan Gilbert]

* misono.tomohiro at fujitsu.com (misono.tomohiro at fujitsu.com) wrote:
> > -----Original Message-----
> > From: virtio-fs-bounces at redhat.com [mailto:virtio-fs-bounces at redhat.com] On Behalf Of Dr. David Alan Gilbert (git)
> > Sent: Tuesday, December 3, 2019 10:14 PM
> > To: virtio-fs at redhat.com; vgoyal at redhat.com
> > Subject: [Virtio-fs] [PATCH 1/2] virtiofsd: cap-ng helpers
> > 
> > From: "Dr. David Alan Gilbert" <dgilbert at redhat.com>
> > 
> > libcap-ng reads /proc during capng_get_caps_process, and virtiofsd's
> > sandboxing doesn't have /proc mounted; thus we have to do the
> > caps read before we sandbox it and save/restore the state.
> > 
> > Signed-off-by: Dr. David Alan Gilbert <dgilbert at redhat.com>
> > ---
> >  Makefile                           |  2 +-
> >  contrib/virtiofsd/passthrough_ll.c | 72 ++++++++++++++++++++++++++++++
> >  2 files changed, 73 insertions(+), 1 deletion(-)
> > 
> > diff --git a/Makefile b/Makefile
> > index 237cbdfee1..1484c23a9b 100644
> > --- a/Makefile
> > +++ b/Makefile
> > @@ -323,7 +323,7 @@ HELPERS-$(call land,$(CONFIG_SOFTMMU),$(CONFIG_LINUX)) = qemu-bridge-helper$(EXE
> > 
> >  ifdef CONFIG_LINUX
> >  ifdef CONFIG_SECCOMP
> > -ifdef CONFIG_LIBCAP
> > +ifdef CONFIG_LIBCAP_NG
> >  HELPERS-y += virtiofsd$(EXESUF)
> >  vhost-user-json-y += contrib/virtiofsd/50-qemu-virtiofsd.json
> >  endif
> > diff --git a/contrib/virtiofsd/passthrough_ll.c b/contrib/virtiofsd/passthrough_ll.c
> > index 1688071c10..139261efc1 100644
> > --- a/contrib/virtiofsd/passthrough_ll.c
> > +++ b/contrib/virtiofsd/passthrough_ll.c
> > @@ -47,6 +47,7 @@
> >  #include <string.h>
> >  #include <syslog.h>
> >  #include <limits.h>
> > +#include <cap-ng.h>
> >  #include <dirent.h>
> >  #include <assert.h>
> >  #include <errno.h>
> > @@ -216,6 +217,13 @@ static const struct fuse_opt lo_opts[] = {
> >  };
> >  static bool use_syslog = false;
> >  static int current_log_level;
> > +static struct {
> > +	pthread_mutex_t mutex;
> > +	void *saved;
> > +} cap;
> > +/* That we loaded cap-ng in the current thread from the saved */
> > +static __thread bool cap_loaded = 0;
> > +
> >  static void unref_inode_lolocked(struct lo_data *lo, struct lo_inode *inode, uint64_t n);
> >  static void put_shared(struct lo_data *lo, struct lo_inode *inode);
> > 
> > @@ -242,6 +250,37 @@ static struct lo_data *lo_data(fuse_req_t req)
> >  	return (struct lo_data *) fuse_req_userdata(req);
> >  }
> > 
> > +/*
> > + * Load capng's state from our saved state if the current thread
> > + * hadn't previously been loaded.
> > + * returns 0 on success
> > + */
> > +static int load_capng(void)
> > +{
> > +	if (!cap_loaded) {
> > +		pthread_mutex_lock(&cap.mutex);
> > +		capng_restore_state(&cap.saved);
> > +		/*
> > +		 * restore_state free's the saved copy
> > +		 * so make another.
> > +		 */
> > +		cap.saved = capng_save_state();
> > +		if (!cap.saved) {
> > +			fuse_log(FUSE_LOG_ERR, "capng_save_state (thread)\n");
> > +			return -EINVAL;
> > +		}
> > +		pthread_mutex_unlock(&cap.mutex);
> > +
> > +		/*
> > +		 * We want to use the loaded state for our pid,
> > +		 * not the original
> > +		 */
> > +		capng_setpid(gettid());
> 
> Hi,
> 
> I got build error on Fedora 30 with glibc 2.29 since gettid() wrapper is introduced in glibc 2.30.
> How about using syscall(__NR_gettid) directly? Or is 2.30 required?

Thanks for reporting, I'm on Fedora 31 so didn't notice.
I'll change it to syscall(__NR_gettid).

Dave

> Thanks,
> Misono
> 
> > +		cap_loaded = true;
> > +	}
> > +	return 0;
> > +}
> > +
> >  /* Helpers for dropping and regaining effective capabilities. Returns 0
> >   * on success, error otherwise  */
> >  static int drop_effective_cap(const char *cap_name, bool *cap_dropped)
> > @@ -2754,6 +2793,35 @@ static void setup_namespaces(struct lo_data *lo, struct fuse_session *se)
> >  	}
> >  }
> > 
> > +/*
> > + * Capture the capability state, we'll need to restore this for individual
> > + * threads later; see load_capng.
> > + */
> > +static void setup_capng(void)
> > +{
> > +	/* Note this accesses /proc so has to happen before the sandbox */
> > +	if (capng_get_caps_process()) {
> > +		fuse_log(FUSE_LOG_ERR, "capng_get_caps_process\n");
> > +		exit(1);
> > +	}
> > +	pthread_mutex_init(&cap.mutex, NULL);
> > +	pthread_mutex_lock(&cap.mutex);
> > +	cap.saved = capng_save_state();
> > +	if (!cap.saved) {
> > +		fuse_log(FUSE_LOG_ERR, "capng_save_state\n");
> > +		exit(1);
> > +	}
> > +	pthread_mutex_unlock(&cap.mutex);
> > +}
> > +
> > +static void cleanup_capng(void)
> > +{
> > +	free(cap.saved);
> > +	cap.saved = NULL;
> > +	pthread_mutex_destroy(&cap.mutex);
> > +}
> > +
> > +
> >  /*
> >   * Make the source directory our root so symlinks cannot escape and no other
> >   * files are accessible.  Assumes unshare(CLONE_NEWNS) was already called.
> > @@ -3173,6 +3241,9 @@ int main(int argc, char *argv[])
> > 
> >  	setup_nofile_rlimit();
> > 
> > +	/* Must be before sandbox since it wants /proc */
> > +	setup_capng();
> > +
> >  	setup_sandbox(&lo, se, opts.syslog);
> > 
> >  	setup_root(&lo, &lo.root);
> > @@ -3195,6 +3266,7 @@ int main(int argc, char *argv[])
> > 
> >  err_out4:
> >  	fuse_session_unmount(se);
> > +	cleanup_capng();
> >  err_out3:
> >  	fuse_remove_signal_handlers(se);
> >  err_out2:
> > --
> > 2.23.0
> > 
> > _______________________________________________
> > Virtio-fs mailing list
> > Virtio-fs at redhat.com
> > https://www.redhat.com/mailman/listinfo/virtio-fs
> 
--
Dr. David Alan Gilbert / dgilbert at redhat.com / Manchester, UK