[PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

Previously there were two chunks of code where the logic to receive file
descriptors was duplicated in net. The compat version of copying
file descriptors via SCM_RIGHTS did not have logic to update cgroups.
Logic to change the cgroup data was added in:
commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")

This was not copied to the compat path. This commit fixes that, and thus
should be cherry-picked into stable.

This introduces a helper (file_receive) which encapsulates the logic for
handling calling security hooks as well as manipulating cgroup information.
This helper can then be used other places in the kernel where file
descriptors are copied between processes

I tested cgroup classid setting on both the compat (x32) path, and the
native path to ensure that when moving the file descriptor the classid
is set.

Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Suggested-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jann Horn <jannh@google.com>,
Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tycho Andersen <tycho@tycho.ws>
Cc: stable@vger.kernel.org
Cc: cgroups@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
 include/linux/file.h |  1 +
 net/compat.c         | 10 +++++-----
 net/core/scm.c       | 14 ++++----------
 4 files changed, 45 insertions(+), 15 deletions(-)

diff --git a/fs/file.c b/fs/file.c
index abb8b7081d7a..5afd76fca8c2 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -18,6 +18,9 @@
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
+#include <net/sock.h>
+#include <net/netprio_cgroup.h>
+#include <net/cls_cgroup.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
@@ -931,6 +934,38 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
 	return err;
 }
 
+/*
+ * File Receive - Receive a file from another process
+ *
+ * This function is designed to receive files from other tasks. It encapsulates
+ * logic around security and cgroups. The file descriptor provided must be a
+ * freshly allocated (unused) file descriptor.
+ *
+ * This helper does not consume a reference to the file, so the caller must put
+ * their reference.
+ *
+ * Returns 0 upon success.
+ */
+int file_receive(int fd, struct file *file)
+{
+	struct socket *sock;
+	int err;
+
+	err = security_file_receive(file);
+	if (err)
+		return err;
+
+	fd_install(fd, get_file(file));
+
+	sock = sock_from_file(file, &err);
+	if (sock) {
+		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
+		sock_update_classid(&sock->sk->sk_cgrp_data);
+	}
+
+	return 0;
+}
+
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
 	int err = -EBADF;
diff --git a/include/linux/file.h b/include/linux/file.h
index 142d102f285e..7b56dc23e560 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -94,4 +94,5 @@ extern void fd_install(unsigned int fd, struct file *file);
 extern void flush_delayed_fput(void);
 extern void __fput_sync(struct file *);
 
+extern int file_receive(int fd, struct file *file);
 #endif /* __LINUX_FILE_H */
diff --git a/net/compat.c b/net/compat.c
index 4bed96e84d9a..8ac0e7e09208 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -293,9 +293,6 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 
 	for (i = 0, cmfptr = (int __user *) CMSG_COMPAT_DATA(cm); i < fdmax; i++, cmfptr++) {
 		int new_fd;
-		err = security_file_receive(fp[i]);
-		if (err)
-			break;
 		err = get_unused_fd_flags(MSG_CMSG_CLOEXEC & kmsg->msg_flags
 					  ? O_CLOEXEC : 0);
 		if (err < 0)
@@ -306,8 +303,11 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 			put_unused_fd(new_fd);
 			break;
 		}
-		/* Bump the usage count and install the file. */
-		fd_install(new_fd, get_file(fp[i]));
+		err = file_receive(new_fd, fp[i]);
+		if (err) {
+			put_unused_fd(new_fd);
+			break;
+		}
 	}
 
 	if (i > 0) {
diff --git a/net/core/scm.c b/net/core/scm.c
index dc6fed1f221c..ba93abf2881b 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -303,11 +303,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 	for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax;
 	     i++, cmfptr++)
 	{
-		struct socket *sock;
 		int new_fd;
-		err = security_file_receive(fp[i]);
-		if (err)
-			break;
 		err = get_unused_fd_flags(MSG_CMSG_CLOEXEC & msg->msg_flags
 					  ? O_CLOEXEC : 0);
 		if (err < 0)
@@ -318,13 +314,11 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 			put_unused_fd(new_fd);
 			break;
 		}
-		/* Bump the usage count and install the file. */
-		sock = sock_from_file(fp[i], &err);
-		if (sock) {
-			sock_update_netprioidx(&sock->sk->sk_cgrp_data);
-			sock_update_classid(&sock->sk->sk_cgrp_data);
+		err = file_receive(new_fd, fp[i]);
+		if (err) {
+			put_unused_fd(new_fd);
+			break;
 		}
-		fd_install(new_fd, get_file(fp[i]));
 	}
 
 	if (i > 0)
-- 
2.25.1

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Tue, Jun 02, 2020 at 06:10:41PM -0700, Sargun Dhillon wrote:
> Previously there were two chunks of code where the logic to receive file
> descriptors was duplicated in net. The compat version of copying
> file descriptors via SCM_RIGHTS did not have logic to update cgroups.
> Logic to change the cgroup data was added in:
> commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
> commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")
> 
> This was not copied to the compat path. This commit fixes that, and thus
> should be cherry-picked into stable.
> 
> This introduces a helper (file_receive) which encapsulates the logic for
> handling calling security hooks as well as manipulating cgroup information.
> This helper can then be used other places in the kernel where file
> descriptors are copied between processes
> 
> I tested cgroup classid setting on both the compat (x32) path, and the
> native path to ensure that when moving the file descriptor the classid
> is set.
> 
> Signed-off-by: Sargun Dhillon <sargun@sargun.me>
> Suggested-by: Kees Cook <keescook@chromium.org>
> Cc: Al Viro <viro@zeniv.linux.org.uk>
> Cc: Christian Brauner <christian.brauner@ubuntu.com>
> Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
> Cc: David S. Miller <davem@davemloft.net>
> Cc: Jann Horn <jannh@google.com>,
> Cc: John Fastabend <john.r.fastabend@intel.com>
> Cc: Tejun Heo <tj@kernel.org>
> Cc: Tycho Andersen <tycho@tycho.ws>
> Cc: stable@vger.kernel.org
> Cc: cgroups@vger.kernel.org
> Cc: linux-fsdevel@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> ---
>  fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
>  include/linux/file.h |  1 +
>  net/compat.c         | 10 +++++-----
>  net/core/scm.c       | 14 ++++----------
>  4 files changed, 45 insertions(+), 15 deletions(-)
> 
> diff --git a/fs/file.c b/fs/file.c
> index abb8b7081d7a..5afd76fca8c2 100644
> --- a/fs/file.c
> +++ b/fs/file.c
> @@ -18,6 +18,9 @@
>  #include <linux/bitops.h>
>  #include <linux/spinlock.h>
>  #include <linux/rcupdate.h>
> +#include <net/sock.h>
> +#include <net/netprio_cgroup.h>
> +#include <net/cls_cgroup.h>
>  
>  unsigned int sysctl_nr_open __read_mostly = 1024*1024;
>  unsigned int sysctl_nr_open_min = BITS_PER_LONG;
> @@ -931,6 +934,38 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
>  	return err;
>  }
>  
> +/*
> + * File Receive - Receive a file from another process
> + *
> + * This function is designed to receive files from other tasks. It encapsulates
> + * logic around security and cgroups. The file descriptor provided must be a
> + * freshly allocated (unused) file descriptor.
> + *
> + * This helper does not consume a reference to the file, so the caller must put
> + * their reference.
> + *
> + * Returns 0 upon success.
> + */
> +int file_receive(int fd, struct file *file)

This is all just a remote version of fd_install(), yet it deviates from
fd_install()'s semantics and naming. That's not great imho. What about
naming this something like:

fd_install_received()

and move the get_file() out of there so it has the same semantics as
fd_install(). It seems rather dangerous to have a function like
fd_install() that consumes a reference once it returned and another
version of this that is basically the same thing but doesn't consume a
reference because it takes its own. Seems an invitation for confusion.
Does that make sense?

> +{
> +	struct socket *sock;
> +	int err;
> +
> +	err = security_file_receive(file);
> +	if (err)
> +		return err;
> +
> +	fd_install(fd, get_file(file));
> +
> +	sock = sock_from_file(file, &err);
> +	if (sock) {
> +		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> +		sock_update_classid(&sock->sk->sk_cgrp_data);
> +	}
> +
> +	return 0;
> +}
> +
>  static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
>  {
>  	int err = -EBADF;
> diff --git a/include/linux/file.h b/include/linux/file.h
> index 142d102f285e..7b56dc23e560 100644
> --- a/include/linux/file.h
> +++ b/include/linux/file.h
> @@ -94,4 +94,5 @@ extern void fd_install(unsigned int fd, struct file *file);
>  extern void flush_delayed_fput(void);
>  extern void __fput_sync(struct file *);
>  
> +extern int file_receive(int fd, struct file *file);
>  #endif /* __LINUX_FILE_H */
> diff --git a/net/compat.c b/net/compat.c
> index 4bed96e84d9a..8ac0e7e09208 100644
> --- a/net/compat.c
> +++ b/net/compat.c
> @@ -293,9 +293,6 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
>  
>  	for (i = 0, cmfptr = (int __user *) CMSG_COMPAT_DATA(cm); i < fdmax; i++, cmfptr++) {
>  		int new_fd;
> -		err = security_file_receive(fp[i]);
> -		if (err)
> -			break;
>  		err = get_unused_fd_flags(MSG_CMSG_CLOEXEC & kmsg->msg_flags
>  					  ? O_CLOEXEC : 0);
>  		if (err < 0)
> @@ -306,8 +303,11 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
>  			put_unused_fd(new_fd);
>  			break;
>  		}
> -		/* Bump the usage count and install the file. */
> -		fd_install(new_fd, get_file(fp[i]));
> +		err = file_receive(new_fd, fp[i]);
> +		if (err) {
> +			put_unused_fd(new_fd);
> +			break;
> +		}
>  	}
>  
>  	if (i > 0) {
> diff --git a/net/core/scm.c b/net/core/scm.c
> index dc6fed1f221c..ba93abf2881b 100644
> --- a/net/core/scm.c
> +++ b/net/core/scm.c
> @@ -303,11 +303,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
>  	for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax;
>  	     i++, cmfptr++)
>  	{
> -		struct socket *sock;
>  		int new_fd;
> -		err = security_file_receive(fp[i]);
> -		if (err)
> -			break;
>  		err = get_unused_fd_flags(MSG_CMSG_CLOEXEC & msg->msg_flags
>  					  ? O_CLOEXEC : 0);
>  		if (err < 0)
> @@ -318,13 +314,11 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
>  			put_unused_fd(new_fd);
>  			break;
>  		}
> -		/* Bump the usage count and install the file. */
> -		sock = sock_from_file(fp[i], &err);
> -		if (sock) {
> -			sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> -			sock_update_classid(&sock->sk->sk_cgrp_data);
> +		err = file_receive(new_fd, fp[i]);
> +		if (err) {
> +			put_unused_fd(new_fd);
> +			break;
>  		}
> -		fd_install(new_fd, get_file(fp[i]));
>  	}
>  
>  	if (i > 0)
> -- 
> 2.25.1
> 

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Thu, Jun 04, 2020 at 03:24:52AM +0200, Christian Brauner wrote:
> On Tue, Jun 02, 2020 at 06:10:41PM -0700, Sargun Dhillon wrote:
> > Previously there were two chunks of code where the logic to receive file
> > descriptors was duplicated in net. The compat version of copying
> > file descriptors via SCM_RIGHTS did not have logic to update cgroups.
> > Logic to change the cgroup data was added in:
> > commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
> > commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")
> > 
> > This was not copied to the compat path. This commit fixes that, and thus
> > should be cherry-picked into stable.
> > 
> > This introduces a helper (file_receive) which encapsulates the logic for
> > handling calling security hooks as well as manipulating cgroup information.
> > This helper can then be used other places in the kernel where file
> > descriptors are copied between processes
> > 
> > I tested cgroup classid setting on both the compat (x32) path, and the
> > native path to ensure that when moving the file descriptor the classid
> > is set.
> > 
> > Signed-off-by: Sargun Dhillon <sargun@sargun.me>
> > Suggested-by: Kees Cook <keescook@chromium.org>
> > Cc: Al Viro <viro@zeniv.linux.org.uk>
> > Cc: Christian Brauner <christian.brauner@ubuntu.com>
> > Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
> > Cc: David S. Miller <davem@davemloft.net>
> > Cc: Jann Horn <jannh@google.com>,
> > Cc: John Fastabend <john.r.fastabend@intel.com>
> > Cc: Tejun Heo <tj@kernel.org>
> > Cc: Tycho Andersen <tycho@tycho.ws>
> > Cc: stable@vger.kernel.org
> > Cc: cgroups@vger.kernel.org
> > Cc: linux-fsdevel@vger.kernel.org
> > Cc: linux-kernel@vger.kernel.org
> > ---
> >  fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
> >  include/linux/file.h |  1 +
> >  net/compat.c         | 10 +++++-----
> >  net/core/scm.c       | 14 ++++----------
> >  4 files changed, 45 insertions(+), 15 deletions(-)
> > 
> > diff --git a/fs/file.c b/fs/file.c
> > index abb8b7081d7a..5afd76fca8c2 100644
> > --- a/fs/file.c
> > +++ b/fs/file.c
> > @@ -18,6 +18,9 @@
> >  #include <linux/bitops.h>
> >  #include <linux/spinlock.h>
> >  #include <linux/rcupdate.h>
> > +#include <net/sock.h>
> > +#include <net/netprio_cgroup.h>
> > +#include <net/cls_cgroup.h>
> >  
> >  unsigned int sysctl_nr_open __read_mostly = 1024*1024;
> >  unsigned int sysctl_nr_open_min = BITS_PER_LONG;
> > @@ -931,6 +934,38 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
> >  	return err;
> >  }
> >  
> > +/*
> > + * File Receive - Receive a file from another process
> > + *
> > + * This function is designed to receive files from other tasks. It encapsulates
> > + * logic around security and cgroups. The file descriptor provided must be a
> > + * freshly allocated (unused) file descriptor.
> > + *
> > + * This helper does not consume a reference to the file, so the caller must put
> > + * their reference.
> > + *
> > + * Returns 0 upon success.
> > + */
> > +int file_receive(int fd, struct file *file)
> 
> This is all just a remote version of fd_install(), yet it deviates from
> fd_install()'s semantics and naming. That's not great imho. What about
> naming this something like:
> 
> fd_install_received()
> 
> and move the get_file() out of there so it has the same semantics as
> fd_install(). It seems rather dangerous to have a function like
> fd_install() that consumes a reference once it returned and another
> version of this that is basically the same thing but doesn't consume a
> reference because it takes its own. Seems an invitation for confusion.
> Does that make sense?

We have some competing opinions on this, I guess. What I really don't
like is the copy/pasting of the get_unused_fd_flags() and
put_unused_fd() needed by (nearly) all the callers. If it's a helper, it
should help. Specifically, I'd like to see this:

int file_receive(int fd, unsigned long flags, struct file *file,
		 int __user *fdptr)
{
	struct socket *sock;
	int err;

	err = security_file_receive(file);
	if (err)
		return err;

	if (fd < 0) {
		/* Install new fd. */
		int new_fd;

		err = get_unused_fd_flags(flags);
		if (err < 0)
			return err;
		new_fd = err;

		/* Copy fd to any waiting user memory. */
		if (fdptr) {
			err = put_user(new_fd, fdptr);
			if (err < 0) {
				put_unused_fd(new_fd);
				return err;
			}
		}
		fd_install(new_fd, get_file(file));
		fd = new_fd;
	} else {
		/* Replace existing fd. */
		err = replace_fd(fd, file, flags);
		if (err)
			return err;
	}

	/* Bump the cgroup usage counts. */
	sock = sock_from_file(fd, &err);
	if (sock) {
		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
		sock_update_classid(&sock->sk->sk_cgrp_data);
	}

	return fd;
}

If everyone else *really* prefers keeping the get_unused_fd_flags() /
put_unused_fd() stuff outside the helper, then I guess I'll give up,
but I think it is MUCH cleaner this way -- all 4 users trim down lots
of code duplication.

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

On Wed, Jun 03, 2020 at 07:22:57PM -0700, Kees Cook wrote:
> On Thu, Jun 04, 2020 at 03:24:52AM +0200, Christian Brauner wrote:
> > On Tue, Jun 02, 2020 at 06:10:41PM -0700, Sargun Dhillon wrote:
> > > Previously there were two chunks of code where the logic to receive file
> > > descriptors was duplicated in net. The compat version of copying
> > > file descriptors via SCM_RIGHTS did not have logic to update cgroups.
> > > Logic to change the cgroup data was added in:
> > > commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
> > > commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")
> > > 
> > > This was not copied to the compat path. This commit fixes that, and thus
> > > should be cherry-picked into stable.
> > > 
> > > This introduces a helper (file_receive) which encapsulates the logic for
> > > handling calling security hooks as well as manipulating cgroup information.
> > > This helper can then be used other places in the kernel where file
> > > descriptors are copied between processes
> > > 
> > > I tested cgroup classid setting on both the compat (x32) path, and the
> > > native path to ensure that when moving the file descriptor the classid
> > > is set.
> > > 
> > > Signed-off-by: Sargun Dhillon <sargun@sargun.me>
> > > Suggested-by: Kees Cook <keescook@chromium.org>
> > > Cc: Al Viro <viro@zeniv.linux.org.uk>
> > > Cc: Christian Brauner <christian.brauner@ubuntu.com>
> > > Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
> > > Cc: David S. Miller <davem@davemloft.net>
> > > Cc: Jann Horn <jannh@google.com>,
> > > Cc: John Fastabend <john.r.fastabend@intel.com>
> > > Cc: Tejun Heo <tj@kernel.org>
> > > Cc: Tycho Andersen <tycho@tycho.ws>
> > > Cc: stable@vger.kernel.org
> > > Cc: cgroups@vger.kernel.org
> > > Cc: linux-fsdevel@vger.kernel.org
> > > Cc: linux-kernel@vger.kernel.org
> > > ---
> > >  fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
> > >  include/linux/file.h |  1 +
> > >  net/compat.c         | 10 +++++-----
> > >  net/core/scm.c       | 14 ++++----------
> > >  4 files changed, 45 insertions(+), 15 deletions(-)
> > > 
> > > diff --git a/fs/file.c b/fs/file.c
> > > index abb8b7081d7a..5afd76fca8c2 100644
> > > --- a/fs/file.c
> > > +++ b/fs/file.c
> > > @@ -18,6 +18,9 @@
> > >  #include <linux/bitops.h>
> > >  #include <linux/spinlock.h>
> > >  #include <linux/rcupdate.h>
> > > +#include <net/sock.h>
> > > +#include <net/netprio_cgroup.h>
> > > +#include <net/cls_cgroup.h>
> > >  
> > >  unsigned int sysctl_nr_open __read_mostly = 1024*1024;
> > >  unsigned int sysctl_nr_open_min = BITS_PER_LONG;
> > > @@ -931,6 +934,38 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
> > >  	return err;
> > >  }
> > >  
> > > +/*
> > > + * File Receive - Receive a file from another process
> > > + *
> > > + * This function is designed to receive files from other tasks. It encapsulates
> > > + * logic around security and cgroups. The file descriptor provided must be a
> > > + * freshly allocated (unused) file descriptor.
> > > + *
> > > + * This helper does not consume a reference to the file, so the caller must put
> > > + * their reference.
> > > + *
> > > + * Returns 0 upon success.
> > > + */
> > > +int file_receive(int fd, struct file *file)
> > 
> > This is all just a remote version of fd_install(), yet it deviates from
> > fd_install()'s semantics and naming. That's not great imho. What about
> > naming this something like:
> > 
> > fd_install_received()
> > 
> > and move the get_file() out of there so it has the same semantics as
> > fd_install(). It seems rather dangerous to have a function like
> > fd_install() that consumes a reference once it returned and another
> > version of this that is basically the same thing but doesn't consume a
> > reference because it takes its own. Seems an invitation for confusion.
> > Does that make sense?
> 
> We have some competing opinions on this, I guess. What I really don't
> like is the copy/pasting of the get_unused_fd_flags() and
> put_unused_fd() needed by (nearly) all the callers. If it's a helper, it
> should help. Specifically, I'd like to see this:
> 
> int file_receive(int fd, unsigned long flags, struct file *file,
> 		 int __user *fdptr)
> {
> 	struct socket *sock;
> 	int err;
> 
> 	err = security_file_receive(file);
> 	if (err)
> 		return err;
> 
> 	if (fd < 0) {
> 		/* Install new fd. */
> 		int new_fd;
> 
> 		err = get_unused_fd_flags(flags);
> 		if (err < 0)
> 			return err;
> 		new_fd = err;
> 
> 		/* Copy fd to any waiting user memory. */
> 		if (fdptr) {
> 			err = put_user(new_fd, fdptr);
> 			if (err < 0) {
> 				put_unused_fd(new_fd);
> 				return err;
> 			}
> 		}
> 		fd_install(new_fd, get_file(file));
> 		fd = new_fd;
> 	} else {
> 		/* Replace existing fd. */
> 		err = replace_fd(fd, file, flags);
> 		if (err)
> 			return err;
> 	}
> 
> 	/* Bump the cgroup usage counts. */
> 	sock = sock_from_file(fd, &err);
> 	if (sock) {
> 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> 		sock_update_classid(&sock->sk->sk_cgrp_data);
> 	}
> 
> 	return fd;
> }
> 
> If everyone else *really* prefers keeping the get_unused_fd_flags() /
> put_unused_fd() stuff outside the helper, then I guess I'll give up,
> but I think it is MUCH cleaner this way -- all 4 users trim down lots
> of code duplication.
> 
> -- 
> Kees Cook
This seems weird that the function has two different return mechanisms
depending on the value of fdptr, especially given that behaviour is
only invoked by SCM, whereas the other callers (addfd, and pidfd_getfd)
just want the FD value returned.

Won't this produce a "bad" result, if the user does:

struct msghdr msg = {};
struct cmsghdr *cmsg;
struct iovec io = {
	.iov_base = &c,
	.iov_len = 1,
};

msg.msg_iov = &io;
msg.msg_iovlen = 1;
msg.msg_control = NULL;
msg.msg_controllen = sizeof(buf);

recvmsg(sock, &msg, 0);
----

This will end up installing the FD, but it will efault, when
scm_detach_fds tries to fill out the rest of the info. 

I mean, we can easily solve this with a null pointer check
in scm_detach_fds, but my fear is that user n will forget
to do this, and make a mistake.

Maybe it would be nice to have:

/* Receives file descriptor and installs it in userspace at uptr. */
static inline intfile_receive_user(struct file *file, unsigned long flags,
				   int __user *fdptr)
{
	if (fdptr == NULL)
		return -EFAULT;

	return __file_receive(-1, flags, file, uptr);
}

And then just let pidfd_getfd, and seccomp_addfd call __file_receive
directly, or offer a different helper like:

static inline file_receive(long fd, struct *file, unsigned long flags)
{
	return __file_receive(fd, flags, file, NULL);
}

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Wed, Jun 03, 2020 at 07:22:57PM -0700, Kees Cook wrote:
> On Thu, Jun 04, 2020 at 03:24:52AM +0200, Christian Brauner wrote:
> > On Tue, Jun 02, 2020 at 06:10:41PM -0700, Sargun Dhillon wrote:
> > > Previously there were two chunks of code where the logic to receive file
> > > descriptors was duplicated in net. The compat version of copying
> > > file descriptors via SCM_RIGHTS did not have logic to update cgroups.
> > > Logic to change the cgroup data was added in:
> > > commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
> > > commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")
> > > 
> > > This was not copied to the compat path. This commit fixes that, and thus
> > > should be cherry-picked into stable.
> > > 
> > > This introduces a helper (file_receive) which encapsulates the logic for
> > > handling calling security hooks as well as manipulating cgroup information.
> > > This helper can then be used other places in the kernel where file
> > > descriptors are copied between processes
> > > 
> > > I tested cgroup classid setting on both the compat (x32) path, and the
> > > native path to ensure that when moving the file descriptor the classid
> > > is set.
> > > 
> > > Signed-off-by: Sargun Dhillon <sargun@sargun.me>
> > > Suggested-by: Kees Cook <keescook@chromium.org>
> > > Cc: Al Viro <viro@zeniv.linux.org.uk>
> > > Cc: Christian Brauner <christian.brauner@ubuntu.com>
> > > Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
> > > Cc: David S. Miller <davem@davemloft.net>
> > > Cc: Jann Horn <jannh@google.com>,
> > > Cc: John Fastabend <john.r.fastabend@intel.com>
> > > Cc: Tejun Heo <tj@kernel.org>
> > > Cc: Tycho Andersen <tycho@tycho.ws>
> > > Cc: stable@vger.kernel.org
> > > Cc: cgroups@vger.kernel.org
> > > Cc: linux-fsdevel@vger.kernel.org
> > > Cc: linux-kernel@vger.kernel.org
> > > ---
> > >  fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
> > >  include/linux/file.h |  1 +
> > >  net/compat.c         | 10 +++++-----
> > >  net/core/scm.c       | 14 ++++----------
> > >  4 files changed, 45 insertions(+), 15 deletions(-)
> > > 
> > > diff --git a/fs/file.c b/fs/file.c
> > > index abb8b7081d7a..5afd76fca8c2 100644
> > > --- a/fs/file.c
> > > +++ b/fs/file.c
> > > @@ -18,6 +18,9 @@
> > >  #include <linux/bitops.h>
> > >  #include <linux/spinlock.h>
> > >  #include <linux/rcupdate.h>
> > > +#include <net/sock.h>
> > > +#include <net/netprio_cgroup.h>
> > > +#include <net/cls_cgroup.h>
> > >  
> > >  unsigned int sysctl_nr_open __read_mostly = 1024*1024;
> > >  unsigned int sysctl_nr_open_min = BITS_PER_LONG;
> > > @@ -931,6 +934,38 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
> > >  	return err;
> > >  }
> > >  
> > > +/*
> > > + * File Receive - Receive a file from another process
> > > + *
> > > + * This function is designed to receive files from other tasks. It encapsulates
> > > + * logic around security and cgroups. The file descriptor provided must be a
> > > + * freshly allocated (unused) file descriptor.
> > > + *
> > > + * This helper does not consume a reference to the file, so the caller must put
> > > + * their reference.
> > > + *
> > > + * Returns 0 upon success.
> > > + */
> > > +int file_receive(int fd, struct file *file)
> > 
> > This is all just a remote version of fd_install(), yet it deviates from
> > fd_install()'s semantics and naming. That's not great imho. What about
> > naming this something like:
> > 
> > fd_install_received()
> > 
> > and move the get_file() out of there so it has the same semantics as
> > fd_install(). It seems rather dangerous to have a function like
> > fd_install() that consumes a reference once it returned and another
> > version of this that is basically the same thing but doesn't consume a
> > reference because it takes its own. Seems an invitation for confusion.
> > Does that make sense?
> 
> We have some competing opinions on this, I guess. What I really don't
> like is the copy/pasting of the get_unused_fd_flags() and
> put_unused_fd() needed by (nearly) all the callers. If it's a helper, it
> should help. Specifically, I'd like to see this:
> 
> int file_receive(int fd, unsigned long flags, struct file *file,
> 		 int __user *fdptr)

I still fail to see what this whole put_user() handling buys us at all
and why this function needs to be anymore complicated then simply:

fd_install_received(int fd, struct file *file)
{
	security_file_receive(file);
 
 	sock = sock_from_file(fd, &err);
 	if (sock) {
 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
 		sock_update_classid(&sock->sk->sk_cgrp_data);
 	}

	fd_install();
	return;
}

exactly like fd_install() but for received files.

For scm you can fail somewhere in the middle of putting any number of
file descriptors so you're left in a state with only a subset of
requested file descriptors installed so it's not really useful there.
And if you manage to install an fd but then fail to put_user() it
userspace can simply check it's fds via proc and has to anyway on any
scm message error. If you fail an scm message userspace better check
their fds.
For seccomp maybe but even there I doubt it and I still maintain that
userspace screwing this up is on them which is how we do this most of
the time. And for pidfd_getfd() this whole put_user() thing doesn't
matter at all.

It's much easier and clearer if we simply have a fd_install() -
fd_install_received() parallelism where we follow an established
convention. _But_ if that blocks you from making this generic enough
then at least the replace_fd() vs fd_install() logic seems it shouldn't
be in there. 

And the function name really needs to drive home the point that it
installs an fd into the tasks fdtable no matter what version you go
with. file_receive() is really not accurate enough for this at all.

> {
> 	struct socket *sock;
> 	int err;
> 
> 	err = security_file_receive(file);
> 	if (err)
> 		return err;
> 
> 	if (fd < 0) {
> 		/* Install new fd. */
> 		int new_fd;
> 
> 		err = get_unused_fd_flags(flags);
> 		if (err < 0)
> 			return err;
> 		new_fd = err;
> 
> 		/* Copy fd to any waiting user memory. */
> 		if (fdptr) {
> 			err = put_user(new_fd, fdptr);
> 			if (err < 0) {
> 				put_unused_fd(new_fd);
> 				return err;
> 			}
> 		}
> 		fd_install(new_fd, get_file(file));
> 		fd = new_fd;
> 	} else {
> 		/* Replace existing fd. */
> 		err = replace_fd(fd, file, flags);
> 		if (err)
> 			return err;
> 	}
> 
> 	/* Bump the cgroup usage counts. */
> 	sock = sock_from_file(fd, &err);
> 	if (sock) {
> 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> 		sock_update_classid(&sock->sk->sk_cgrp_data);
> 	}
> 
> 	return fd;
> }
> 
> If everyone else *really* prefers keeping the get_unused_fd_flags() /
> put_unused_fd() stuff outside the helper, then I guess I'll give up,
> but I think it is MUCH cleaner this way -- all 4 users trim down lots
> of code duplication.
> 
> -- 
> Kees Cook

RE: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[David Laight]

From: Christian Brauner
> Sent: 04 June 2020 13:52
..
> For scm you can fail somewhere in the middle of putting any number of
> file descriptors so you're left in a state with only a subset of
> requested file descriptors installed so it's not really useful there.
> And if you manage to install an fd but then fail to put_user() it
> userspace can simply check it's fds via proc and has to anyway on any
> scm message error. If you fail an scm message userspace better check
> their fds.

There is a similar error path in the sctp 'peeloff' code.
If the put_user() fails it currently closes the fd before
returning -EFAULT.

I'm not at all sure this is helpful.
The application can't tell whether the SIGSEGV happened on the
copyin of the parameters or the copyout of the result.

ISTM that if the application passes an address that cannot
be written to it deserves what it gets - typically an fd it
doesn't know the number of.

What is important is that the kernel data is consistent.
So when the process exits the fd is closed and all the resources
are released.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

On Thu, Jun 04, 2020 at 02:52:26PM +0200, Christian Brauner wrote:
> On Wed, Jun 03, 2020 at 07:22:57PM -0700, Kees Cook wrote:
> > On Thu, Jun 04, 2020 at 03:24:52AM +0200, Christian Brauner wrote:
> > > On Tue, Jun 02, 2020 at 06:10:41PM -0700, Sargun Dhillon wrote:
> > > > Previously there were two chunks of code where the logic to receive file
> > > > descriptors was duplicated in net. The compat version of copying
> > > > file descriptors via SCM_RIGHTS did not have logic to update cgroups.
> > > > Logic to change the cgroup data was added in:
> > > > commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
> > > > commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")
> > > > 
> > > > This was not copied to the compat path. This commit fixes that, and thus
> > > > should be cherry-picked into stable.
> > > > 
> > > > This introduces a helper (file_receive) which encapsulates the logic for
> > > > handling calling security hooks as well as manipulating cgroup information.
> > > > This helper can then be used other places in the kernel where file
> > > > descriptors are copied between processes
> > > > 
> > > > I tested cgroup classid setting on both the compat (x32) path, and the
> > > > native path to ensure that when moving the file descriptor the classid
> > > > is set.
> > > > 
> > > > Signed-off-by: Sargun Dhillon <sargun@sargun.me>
> > > > Suggested-by: Kees Cook <keescook@chromium.org>
> > > > Cc: Al Viro <viro@zeniv.linux.org.uk>
> > > > Cc: Christian Brauner <christian.brauner@ubuntu.com>
> > > > Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
> > > > Cc: David S. Miller <davem@davemloft.net>
> > > > Cc: Jann Horn <jannh@google.com>,
> > > > Cc: John Fastabend <john.r.fastabend@intel.com>
> > > > Cc: Tejun Heo <tj@kernel.org>
> > > > Cc: Tycho Andersen <tycho@tycho.ws>
> > > > Cc: stable@vger.kernel.org
> > > > Cc: cgroups@vger.kernel.org
> > > > Cc: linux-fsdevel@vger.kernel.org
> > > > Cc: linux-kernel@vger.kernel.org
> > > > ---
> > > >  fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
> > > >  include/linux/file.h |  1 +
> > > >  net/compat.c         | 10 +++++-----
> > > >  net/core/scm.c       | 14 ++++----------
> > > >  4 files changed, 45 insertions(+), 15 deletions(-)
> > > > 
> > > 
> > > This is all just a remote version of fd_install(), yet it deviates from
> > > fd_install()'s semantics and naming. That's not great imho. What about
> > > naming this something like:
> > > 
> > > fd_install_received()
> > > 
> > > and move the get_file() out of there so it has the same semantics as
> > > fd_install(). It seems rather dangerous to have a function like
> > > fd_install() that consumes a reference once it returned and another
> > > version of this that is basically the same thing but doesn't consume a
> > > reference because it takes its own. Seems an invitation for confusion.
> > > Does that make sense?
> > 
> > We have some competing opinions on this, I guess. What I really don't
> > like is the copy/pasting of the get_unused_fd_flags() and
> > put_unused_fd() needed by (nearly) all the callers. If it's a helper, it
> > should help. Specifically, I'd like to see this:
> > 
> > int file_receive(int fd, unsigned long flags, struct file *file,
> > 		 int __user *fdptr)
> 
> I still fail to see what this whole put_user() handling buys us at all
> and why this function needs to be anymore complicated then simply:
> 
> fd_install_received(int fd, struct file *file)
> {
> 	security_file_receive(file);
>  
>  	sock = sock_from_file(fd, &err);
>  	if (sock) {
>  		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
>  		sock_update_classid(&sock->sk->sk_cgrp_data);
>  	}
> 
> 	fd_install();
> 	return;
> }
> 
> exactly like fd_install() but for received files.
> 
> For scm you can fail somewhere in the middle of putting any number of
> file descriptors so you're left in a state with only a subset of
> requested file descriptors installed so it's not really useful there.
> And if you manage to install an fd but then fail to put_user() it
> userspace can simply check it's fds via proc and has to anyway on any
> scm message error. If you fail an scm message userspace better check
> their fds.
> For seccomp maybe but even there I doubt it and I still maintain that
> userspace screwing this up is on them which is how we do this most of
> the time. And for pidfd_getfd() this whole put_user() thing doesn't
> matter at all.
> 
> It's much easier and clearer if we simply have a fd_install() -
> fd_install_received() parallelism where we follow an established
> convention. _But_ if that blocks you from making this generic enough
> then at least the replace_fd() vs fd_install() logic seems it shouldn't
> be in there. 
> 
> And the function name really needs to drive home the point that it
> installs an fd into the tasks fdtable no matter what version you go
> with. file_receive() is really not accurate enough for this at all.
> 
> > {
> > 	struct socket *sock;
> > 	int err;
> > 
> > 	err = security_file_receive(file);
> > 	if (err)
> > 		return err;
> > 
> > 	if (fd < 0) {
> > 		/* Install new fd. */
> > 		int new_fd;
> > 
> > 		err = get_unused_fd_flags(flags);
> > 		if (err < 0)
> > 			return err;
> > 		new_fd = err;
> > 
> > 		/* Copy fd to any waiting user memory. */
> > 		if (fdptr) {
> > 			err = put_user(new_fd, fdptr);
> > 			if (err < 0) {
> > 				put_unused_fd(new_fd);
> > 				return err;
> > 			}
> > 		}
> > 		fd_install(new_fd, get_file(file));
> > 		fd = new_fd;
> > 	} else {
> > 		/* Replace existing fd. */
> > 		err = replace_fd(fd, file, flags);
> > 		if (err)
> > 			return err;
> > 	}
> > 
> > 	/* Bump the cgroup usage counts. */
> > 	sock = sock_from_file(fd, &err);
> > 	if (sock) {
> > 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> > 		sock_update_classid(&sock->sk->sk_cgrp_data);
> > 	}
> > 
> > 	return fd;
> > }
> > 
> > If everyone else *really* prefers keeping the get_unused_fd_flags() /
> > put_unused_fd() stuff outside the helper, then I guess I'll give up,
> > but I think it is MUCH cleaner this way -- all 4 users trim down lots
> > of code duplication.
> > 
> > -- 
> > Kees Cook
How about this:


static int do_dup2(struct files_struct *files,
	struct file *file, unsigned fd, unsigned flags)
__releases(&files->file_lock)
{
	struct file *tofree;
	struct fdtable *fdt;

	...

	/*
	 * New bit, allowing the file to be null. Doesn't have the same
	 * "sanity check" bits from __alloc_fd
	 */
	if (likely(file))
		get_file(file);
	rcu_assign_pointer(fdt->fd[fd], file);

	__set_open_fd(fd, fdt);

	...
}

/*
 * File Receive - Receive a file from another process
 *
 * Encapsulates the logic to handle receiving a file from another task. It
 * does not install the file descriptor. That is delegated to the user. If
 * an error occurs that results in the file descriptor not being installed,
 * they must put_unused_fd.
 *
 * fd should be >= 0 if you intend on replacing a file descriptor, or
 * alternatively -1 if you want file_receive to allocate an FD for you
 *
 * Returns the fd number on success.
 * Returns negative error code on failure.
 *
 */
int file_receive(int fd, unsigned int flags, struct file *file)
{
	int err;
	struct socket *sock;
	struct files_struct *files = current->files;

	err = security_file_receive(file);
	if (err)
		return err;

	if (fd >= 0) {
		if (fd >= rlimit(RLIMIT_NOFILE))
			return -EBADF;

		spin_lock(&files->file_lock);
		err = expand_files(files, fd);
		if (err < 0) {
			goto out_unlock;
		}

		err = do_dup2(files, NULL, fd, flags);
		if (err)
			return err;
	} else {
		fd = get_unused_fd_flags(flags);
		if (fd < 0)
			return fd;
	}

	sock = sock_from_file(file, &err);
	if (sock) {
		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
		sock_update_classid(&sock->sk->sk_cgrp_data);
	}

	return fd;

out_unlock:
	spin_unlock(&files->file_lock);
	return err;
}

---

then the code in scm.c:
err = file_receive(-1, flags, fp[i]);
if (err < 0)
	break;

new_fd = err;
err = put_user(new_fd, cmfptr);
if (err) {
	put_unused_fd(new_fd);
	break;
}

/* Bump the usage count and install the file. */
fd_install(new_fd, get_file(fp[i]));

And addfd:
ret = file_receive(addfd->fd, addfd->flags, addfd->file);
if (ret >= 0)
	fd_install(ret, get_file(addfd->file));
addfd->ret = ret;

----

This way there is:
1. No "put_user" logic in file_receive
2. Minimal (single) branching logic, unless there's something in between
   the file_receive and installing the FD, such as put_user.
3. Doesn't implement fd_install, so there's no ambiguity about it being
   file_install_received vs. just the receive logic.

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Fri, Jun 05, 2020 at 07:54:36AM +0000, Sargun Dhillon wrote:
> On Thu, Jun 04, 2020 at 02:52:26PM +0200, Christian Brauner wrote:
> > On Wed, Jun 03, 2020 at 07:22:57PM -0700, Kees Cook wrote:
> > > On Thu, Jun 04, 2020 at 03:24:52AM +0200, Christian Brauner wrote:
> > > > On Tue, Jun 02, 2020 at 06:10:41PM -0700, Sargun Dhillon wrote:
> > > > > Previously there were two chunks of code where the logic to receive file
> > > > > descriptors was duplicated in net. The compat version of copying
> > > > > file descriptors via SCM_RIGHTS did not have logic to update cgroups.
> > > > > Logic to change the cgroup data was added in:
> > > > > commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
> > > > > commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")
> > > > > 
> > > > > This was not copied to the compat path. This commit fixes that, and thus
> > > > > should be cherry-picked into stable.
> > > > > 
> > > > > This introduces a helper (file_receive) which encapsulates the logic for
> > > > > handling calling security hooks as well as manipulating cgroup information.
> > > > > This helper can then be used other places in the kernel where file
> > > > > descriptors are copied between processes
> > > > > 
> > > > > I tested cgroup classid setting on both the compat (x32) path, and the
> > > > > native path to ensure that when moving the file descriptor the classid
> > > > > is set.
> > > > > 
> > > > > Signed-off-by: Sargun Dhillon <sargun@sargun.me>
> > > > > Suggested-by: Kees Cook <keescook@chromium.org>
> > > > > Cc: Al Viro <viro@zeniv.linux.org.uk>
> > > > > Cc: Christian Brauner <christian.brauner@ubuntu.com>
> > > > > Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
> > > > > Cc: David S. Miller <davem@davemloft.net>
> > > > > Cc: Jann Horn <jannh@google.com>,
> > > > > Cc: John Fastabend <john.r.fastabend@intel.com>
> > > > > Cc: Tejun Heo <tj@kernel.org>
> > > > > Cc: Tycho Andersen <tycho@tycho.ws>
> > > > > Cc: stable@vger.kernel.org
> > > > > Cc: cgroups@vger.kernel.org
> > > > > Cc: linux-fsdevel@vger.kernel.org
> > > > > Cc: linux-kernel@vger.kernel.org
> > > > > ---
> > > > >  fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
> > > > >  include/linux/file.h |  1 +
> > > > >  net/compat.c         | 10 +++++-----
> > > > >  net/core/scm.c       | 14 ++++----------
> > > > >  4 files changed, 45 insertions(+), 15 deletions(-)
> > > > > 
> > > > 
> > > > This is all just a remote version of fd_install(), yet it deviates from
> > > > fd_install()'s semantics and naming. That's not great imho. What about
> > > > naming this something like:
> > > > 
> > > > fd_install_received()
> > > > 
> > > > and move the get_file() out of there so it has the same semantics as
> > > > fd_install(). It seems rather dangerous to have a function like
> > > > fd_install() that consumes a reference once it returned and another
> > > > version of this that is basically the same thing but doesn't consume a
> > > > reference because it takes its own. Seems an invitation for confusion.
> > > > Does that make sense?
> > > 
> > > We have some competing opinions on this, I guess. What I really don't
> > > like is the copy/pasting of the get_unused_fd_flags() and
> > > put_unused_fd() needed by (nearly) all the callers. If it's a helper, it
> > > should help. Specifically, I'd like to see this:
> > > 
> > > int file_receive(int fd, unsigned long flags, struct file *file,
> > > 		 int __user *fdptr)
> > 
> > I still fail to see what this whole put_user() handling buys us at all
> > and why this function needs to be anymore complicated then simply:
> > 
> > fd_install_received(int fd, struct file *file)
> > {
> > 	security_file_receive(file);
> >  
> >  	sock = sock_from_file(fd, &err);
> >  	if (sock) {
> >  		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> >  		sock_update_classid(&sock->sk->sk_cgrp_data);
> >  	}
> > 
> > 	fd_install();
> > 	return;
> > }
> > 
> > exactly like fd_install() but for received files.
> > 
> > For scm you can fail somewhere in the middle of putting any number of
> > file descriptors so you're left in a state with only a subset of
> > requested file descriptors installed so it's not really useful there.
> > And if you manage to install an fd but then fail to put_user() it
> > userspace can simply check it's fds via proc and has to anyway on any
> > scm message error. If you fail an scm message userspace better check
> > their fds.
> > For seccomp maybe but even there I doubt it and I still maintain that
> > userspace screwing this up is on them which is how we do this most of
> > the time. And for pidfd_getfd() this whole put_user() thing doesn't
> > matter at all.
> > 
> > It's much easier and clearer if we simply have a fd_install() -
> > fd_install_received() parallelism where we follow an established
> > convention. _But_ if that blocks you from making this generic enough
> > then at least the replace_fd() vs fd_install() logic seems it shouldn't
> > be in there. 
> > 
> > And the function name really needs to drive home the point that it
> > installs an fd into the tasks fdtable no matter what version you go
> > with. file_receive() is really not accurate enough for this at all.
> > 
> > > {
> > > 	struct socket *sock;
> > > 	int err;
> > > 
> > > 	err = security_file_receive(file);
> > > 	if (err)
> > > 		return err;
> > > 
> > > 	if (fd < 0) {
> > > 		/* Install new fd. */
> > > 		int new_fd;
> > > 
> > > 		err = get_unused_fd_flags(flags);
> > > 		if (err < 0)
> > > 			return err;
> > > 		new_fd = err;
> > > 
> > > 		/* Copy fd to any waiting user memory. */
> > > 		if (fdptr) {
> > > 			err = put_user(new_fd, fdptr);
> > > 			if (err < 0) {
> > > 				put_unused_fd(new_fd);
> > > 				return err;
> > > 			}
> > > 		}
> > > 		fd_install(new_fd, get_file(file));
> > > 		fd = new_fd;
> > > 	} else {
> > > 		/* Replace existing fd. */
> > > 		err = replace_fd(fd, file, flags);
> > > 		if (err)
> > > 			return err;
> > > 	}
> > > 
> > > 	/* Bump the cgroup usage counts. */
> > > 	sock = sock_from_file(fd, &err);
> > > 	if (sock) {
> > > 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> > > 		sock_update_classid(&sock->sk->sk_cgrp_data);
> > > 	}
> > > 
> > > 	return fd;
> > > }
> > > 
> > > If everyone else *really* prefers keeping the get_unused_fd_flags() /
> > > put_unused_fd() stuff outside the helper, then I guess I'll give up,
> > > but I think it is MUCH cleaner this way -- all 4 users trim down lots
> > > of code duplication.
> > > 
> > > -- 
> > > Kees Cook
> How about this:
> 
> 
> static int do_dup2(struct files_struct *files,
> 	struct file *file, unsigned fd, unsigned flags)
> __releases(&files->file_lock)
> {
> 	struct file *tofree;
> 	struct fdtable *fdt;
> 
> 	...
> 
> 	/*
> 	 * New bit, allowing the file to be null. Doesn't have the same
> 	 * "sanity check" bits from __alloc_fd
> 	 */
> 	if (likely(file))
> 		get_file(file);
> 	rcu_assign_pointer(fdt->fd[fd], file);
> 
> 	__set_open_fd(fd, fdt);

IIUC, this means we can get the fdt into a state of an open fd with a
NULL file... is that okay? That feels like something Al might rebel at.
:)

> 
> 	...
> }
> 
> /*
>  * File Receive - Receive a file from another process
>  *
>  * Encapsulates the logic to handle receiving a file from another task. It
>  * does not install the file descriptor. That is delegated to the user. If
>  * an error occurs that results in the file descriptor not being installed,
>  * they must put_unused_fd.
>  *
>  * fd should be >= 0 if you intend on replacing a file descriptor, or
>  * alternatively -1 if you want file_receive to allocate an FD for you
>  *
>  * Returns the fd number on success.
>  * Returns negative error code on failure.
>  *
>  */
> int file_receive(int fd, unsigned int flags, struct file *file)
> {
> 	int err;
> 	struct socket *sock;
> 	struct files_struct *files = current->files;
> 
> 	err = security_file_receive(file);
> 	if (err)
> 		return err;
> 
> 	if (fd >= 0) {
> 		if (fd >= rlimit(RLIMIT_NOFILE))
> 			return -EBADF;
> 
> 		spin_lock(&files->file_lock);
> 		err = expand_files(files, fd);
> 		if (err < 0) {
> 			goto out_unlock;
> 		}
> 
> 		err = do_dup2(files, NULL, fd, flags);
> 		if (err)
> 			return err;

This seems like we're duplicating some checks and missing others -- I
really think we need to do this using the existing primitives. But I'd
really like some review or commentary from Al. We can do this a bunch of
ways, and I'd like to know which way looks best to him. :(

> This way there is:
> 1. No "put_user" logic in file_receive
> 2. Minimal (single) branching logic, unless there's something in between
>    the file_receive and installing the FD, such as put_user.
> 3. Doesn't implement fd_install, so there's no ambiguity about it being
>    file_install_received vs. just the receive logic.

I still wonder if we should refactor SCM_RIGHTS to just delay put_user
failures, which would simplify a bunch. It's a behavior change, but it
seems from Al and Jann that it just shouldn't matter. (And if it does,
we'll hear about it.)

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Tue, Jun 09, 2020 at 12:43:48PM -0700, Kees Cook wrote:
> On Fri, Jun 05, 2020 at 07:54:36AM +0000, Sargun Dhillon wrote:
> > On Thu, Jun 04, 2020 at 02:52:26PM +0200, Christian Brauner wrote:
> > > On Wed, Jun 03, 2020 at 07:22:57PM -0700, Kees Cook wrote:
> > > > On Thu, Jun 04, 2020 at 03:24:52AM +0200, Christian Brauner wrote:
> > > > > On Tue, Jun 02, 2020 at 06:10:41PM -0700, Sargun Dhillon wrote:
> > > > > > Previously there were two chunks of code where the logic to receive file
> > > > > > descriptors was duplicated in net. The compat version of copying
> > > > > > file descriptors via SCM_RIGHTS did not have logic to update cgroups.
> > > > > > Logic to change the cgroup data was added in:
> > > > > > commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
> > > > > > commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")
> > > > > > 
> > > > > > This was not copied to the compat path. This commit fixes that, and thus
> > > > > > should be cherry-picked into stable.
> > > > > > 
> > > > > > This introduces a helper (file_receive) which encapsulates the logic for
> > > > > > handling calling security hooks as well as manipulating cgroup information.
> > > > > > This helper can then be used other places in the kernel where file
> > > > > > descriptors are copied between processes
> > > > > > 
> > > > > > I tested cgroup classid setting on both the compat (x32) path, and the
> > > > > > native path to ensure that when moving the file descriptor the classid
> > > > > > is set.
> > > > > > 
> > > > > > Signed-off-by: Sargun Dhillon <sargun@sargun.me>
> > > > > > Suggested-by: Kees Cook <keescook@chromium.org>
> > > > > > Cc: Al Viro <viro@zeniv.linux.org.uk>
> > > > > > Cc: Christian Brauner <christian.brauner@ubuntu.com>
> > > > > > Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
> > > > > > Cc: David S. Miller <davem@davemloft.net>
> > > > > > Cc: Jann Horn <jannh@google.com>,
> > > > > > Cc: John Fastabend <john.r.fastabend@intel.com>
> > > > > > Cc: Tejun Heo <tj@kernel.org>
> > > > > > Cc: Tycho Andersen <tycho@tycho.ws>
> > > > > > Cc: stable@vger.kernel.org
> > > > > > Cc: cgroups@vger.kernel.org
> > > > > > Cc: linux-fsdevel@vger.kernel.org
> > > > > > Cc: linux-kernel@vger.kernel.org
> > > > > > ---
> > > > > >  fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
> > > > > >  include/linux/file.h |  1 +
> > > > > >  net/compat.c         | 10 +++++-----
> > > > > >  net/core/scm.c       | 14 ++++----------
> > > > > >  4 files changed, 45 insertions(+), 15 deletions(-)
> > > > > > 
> > > > > 
> > > > > This is all just a remote version of fd_install(), yet it deviates from
> > > > > fd_install()'s semantics and naming. That's not great imho. What about
> > > > > naming this something like:
> > > > > 
> > > > > fd_install_received()
> > > > > 
> > > > > and move the get_file() out of there so it has the same semantics as
> > > > > fd_install(). It seems rather dangerous to have a function like
> > > > > fd_install() that consumes a reference once it returned and another
> > > > > version of this that is basically the same thing but doesn't consume a
> > > > > reference because it takes its own. Seems an invitation for confusion.
> > > > > Does that make sense?
> > > > 
> > > > We have some competing opinions on this, I guess. What I really don't
> > > > like is the copy/pasting of the get_unused_fd_flags() and
> > > > put_unused_fd() needed by (nearly) all the callers. If it's a helper, it
> > > > should help. Specifically, I'd like to see this:
> > > > 
> > > > int file_receive(int fd, unsigned long flags, struct file *file,
> > > > 		 int __user *fdptr)
> > > 
> > > I still fail to see what this whole put_user() handling buys us at all
> > > and why this function needs to be anymore complicated then simply:
> > > 
> > > fd_install_received(int fd, struct file *file)
> > > {
> > > 	security_file_receive(file);
> > >  
> > >  	sock = sock_from_file(fd, &err);
> > >  	if (sock) {
> > >  		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> > >  		sock_update_classid(&sock->sk->sk_cgrp_data);
> > >  	}
> > > 
> > > 	fd_install();
> > > 	return;
> > > }
> > > 
> > > exactly like fd_install() but for received files.
> > > 
> > > For scm you can fail somewhere in the middle of putting any number of
> > > file descriptors so you're left in a state with only a subset of
> > > requested file descriptors installed so it's not really useful there.
> > > And if you manage to install an fd but then fail to put_user() it
> > > userspace can simply check it's fds via proc and has to anyway on any
> > > scm message error. If you fail an scm message userspace better check
> > > their fds.
> > > For seccomp maybe but even there I doubt it and I still maintain that
> > > userspace screwing this up is on them which is how we do this most of
> > > the time. And for pidfd_getfd() this whole put_user() thing doesn't
> > > matter at all.
> > > 
> > > It's much easier and clearer if we simply have a fd_install() -
> > > fd_install_received() parallelism where we follow an established
> > > convention. _But_ if that blocks you from making this generic enough
> > > then at least the replace_fd() vs fd_install() logic seems it shouldn't
> > > be in there. 
> > > 
> > > And the function name really needs to drive home the point that it
> > > installs an fd into the tasks fdtable no matter what version you go
> > > with. file_receive() is really not accurate enough for this at all.
> > > 
> > > > {
> > > > 	struct socket *sock;
> > > > 	int err;
> > > > 
> > > > 	err = security_file_receive(file);
> > > > 	if (err)
> > > > 		return err;
> > > > 
> > > > 	if (fd < 0) {
> > > > 		/* Install new fd. */
> > > > 		int new_fd;
> > > > 
> > > > 		err = get_unused_fd_flags(flags);
> > > > 		if (err < 0)
> > > > 			return err;
> > > > 		new_fd = err;
> > > > 
> > > > 		/* Copy fd to any waiting user memory. */
> > > > 		if (fdptr) {
> > > > 			err = put_user(new_fd, fdptr);
> > > > 			if (err < 0) {
> > > > 				put_unused_fd(new_fd);
> > > > 				return err;
> > > > 			}
> > > > 		}
> > > > 		fd_install(new_fd, get_file(file));
> > > > 		fd = new_fd;
> > > > 	} else {
> > > > 		/* Replace existing fd. */
> > > > 		err = replace_fd(fd, file, flags);
> > > > 		if (err)
> > > > 			return err;
> > > > 	}
> > > > 
> > > > 	/* Bump the cgroup usage counts. */
> > > > 	sock = sock_from_file(fd, &err);
> > > > 	if (sock) {
> > > > 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> > > > 		sock_update_classid(&sock->sk->sk_cgrp_data);
> > > > 	}
> > > > 
> > > > 	return fd;
> > > > }
> > > > 
> > > > If everyone else *really* prefers keeping the get_unused_fd_flags() /
> > > > put_unused_fd() stuff outside the helper, then I guess I'll give up,
> > > > but I think it is MUCH cleaner this way -- all 4 users trim down lots
> > > > of code duplication.
> > > > 
> > > > -- 
> > > > Kees Cook
> > How about this:
> > 
> > 
> > static int do_dup2(struct files_struct *files,
> > 	struct file *file, unsigned fd, unsigned flags)
> > __releases(&files->file_lock)
> > {
> > 	struct file *tofree;
> > 	struct fdtable *fdt;
> > 
> > 	...
> > 
> > 	/*
> > 	 * New bit, allowing the file to be null. Doesn't have the same
> > 	 * "sanity check" bits from __alloc_fd
> > 	 */
> > 	if (likely(file))
> > 		get_file(file);
> > 	rcu_assign_pointer(fdt->fd[fd], file);
> > 
> > 	__set_open_fd(fd, fdt);
> 
> IIUC, this means we can get the fdt into a state of an open fd with a
> NULL file... is that okay? That feels like something Al might rebel at.
> :)
> 
> > 
> > 	...
> > }
> > 
> > /*
> >  * File Receive - Receive a file from another process
> >  *
> >  * Encapsulates the logic to handle receiving a file from another task. It
> >  * does not install the file descriptor. That is delegated to the user. If
> >  * an error occurs that results in the file descriptor not being installed,
> >  * they must put_unused_fd.
> >  *
> >  * fd should be >= 0 if you intend on replacing a file descriptor, or
> >  * alternatively -1 if you want file_receive to allocate an FD for you
> >  *
> >  * Returns the fd number on success.
> >  * Returns negative error code on failure.
> >  *
> >  */
> > int file_receive(int fd, unsigned int flags, struct file *file)
> > {
> > 	int err;
> > 	struct socket *sock;
> > 	struct files_struct *files = current->files;
> > 
> > 	err = security_file_receive(file);
> > 	if (err)
> > 		return err;
> > 
> > 	if (fd >= 0) {
> > 		if (fd >= rlimit(RLIMIT_NOFILE))
> > 			return -EBADF;
> > 
> > 		spin_lock(&files->file_lock);
> > 		err = expand_files(files, fd);
> > 		if (err < 0) {
> > 			goto out_unlock;
> > 		}
> > 
> > 		err = do_dup2(files, NULL, fd, flags);
> > 		if (err)
> > 			return err;
> 
> This seems like we're duplicating some checks and missing others -- I
> really think we need to do this using the existing primitives. But I'd
> really like some review or commentary from Al. We can do this a bunch of
> ways, and I'd like to know which way looks best to him. :(
> 
> > This way there is:
> > 1. No "put_user" logic in file_receive
> > 2. Minimal (single) branching logic, unless there's something in between
> >    the file_receive and installing the FD, such as put_user.
> > 3. Doesn't implement fd_install, so there's no ambiguity about it being
> >    file_install_received vs. just the receive logic.
> 
> I still wonder if we should refactor SCM_RIGHTS to just delay put_user
> failures, which would simplify a bunch. It's a behavior change, but it

I'm looking at __scm_install_fd() and I wonder what specifically you
mean by that? The put_user() seems to be placed such that the install
occurrs only if it succeeded. Sure, it only handles a single fd but
whatever. Userspace knows that already. Just look at systemd when a msg
fails:

void cmsg_close_all(struct msghdr *mh) {
        struct cmsghdr *cmsg;

        assert(mh);

        CMSG_FOREACH(cmsg, mh)
                if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SCM_RIGHTS)
                        close_many((int*) CMSG_DATA(cmsg), (cmsg->cmsg_len - CMSG_LEN(0)) / sizeof(int));
}

The only reasonable scenario for this whole mess I can think of is sm like (pseudo code):

fd_install_received(int fd, struct file *file)
{
 	sock = sock_from_file(fd, &err);
 	if (sock) {
 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
 		sock_update_classid(&sock->sk->sk_cgrp_data);
 	}

	fd_install();
}

error = 0;
fdarray = malloc(fdmax);
for (i = 0; i < fdmax; i++) {
	fdarray[i] = get_unused_fd_flags(o_flags);
	if (fdarray[i] < 0) {
		error = -EBADF;
		break;
	}

	error = security_file_receive(file);
	if (error)
		break;

	error = put_user(fd_array[i], ufd);
	if (error)
		break;
}

for (i = 0; i < fdmax; i++) {
	if (error) {
		/* ignore errors */
		put_user(-EBADF, ufd); /* If this put_user() fails and the first one succeeded userspace might now close an fd it didn't intend to. */
		put_unused_fd(fdarray[i]);
	} else {
		fd_install_received(fdarray[i], file);
	}
}

Christian

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Tue, Jun 09, 2020 at 10:03:46PM +0200, Christian Brauner wrote:
> I'm looking at __scm_install_fd() and I wonder what specifically you
> mean by that? The put_user() seems to be placed such that the install
> occurrs only if it succeeded. Sure, it only handles a single fd but
> whatever. Userspace knows that already. Just look at systemd when a msg
> fails:
> 
> void cmsg_close_all(struct msghdr *mh) {
>         struct cmsghdr *cmsg;
> 
>         assert(mh);
> 
>         CMSG_FOREACH(cmsg, mh)
>                 if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SCM_RIGHTS)
>                         close_many((int*) CMSG_DATA(cmsg), (cmsg->cmsg_len - CMSG_LEN(0)) / sizeof(int));
> }
> 
> The only reasonable scenario for this whole mess I can think of is sm like (pseudo code):
> 
> fd_install_received(int fd, struct file *file)
> {
>  	sock = sock_from_file(fd, &err);
>  	if (sock) {
>  		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
>  		sock_update_classid(&sock->sk->sk_cgrp_data);
>  	}
> 
> 	fd_install();
> }
> 
> error = 0;
> fdarray = malloc(fdmax);
> for (i = 0; i < fdmax; i++) {
> 	fdarray[i] = get_unused_fd_flags(o_flags);
> 	if (fdarray[i] < 0) {
> 		error = -EBADF;
> 		break;
> 	}
> 
> 	error = security_file_receive(file);
> 	if (error)
> 		break;
> 
> 	error = put_user(fd_array[i], ufd);
> 	if (error)
> 		break;
> }
> 
> for (i = 0; i < fdmax; i++) {
> 	if (error) {
> 		/* ignore errors */
> 		put_user(-EBADF, ufd); /* If this put_user() fails and the first one succeeded userspace might now close an fd it didn't intend to. */
> 		put_unused_fd(fdarray[i]);
> 	} else {
> 		fd_install_received(fdarray[i], file);
> 	}
> }

I see 4 cases of the same code pattern (get_unused_fd_flags(),
sock_update_*(), fd_install()), one of them has this difficult put_user()
in the middle, and one of them has a potential replace_fd() instead of
the get_used/fd_install. So, to me, it makes sense to have a helper that
encapsulates the common work that each of those call sites has to do,
which I keep cringing at all these suggestions that leave portions of it
outside the helper.

If it's too ugly to keep the put_user() in the helper, then we can try
what was suggested earlier, and just totally rework the failure path for
SCM_RIGHTS.

LOL. And while we were debating this, hch just went and cleaned stuff
up:

2618d530dd8b ("net/scm: cleanup scm_detach_fds")

So, um, yeah, now my proposal is actually even closer to what we already
have there. We just add the replace_fd() logic to __scm_install_fd() and
we're done with it.

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On June 9, 2020 10:55:42 PM GMT+02:00, Kees Cook <keescook@chromium.org> wrote:
>On Tue, Jun 09, 2020 at 10:03:46PM +0200, Christian Brauner wrote:
>> I'm looking at __scm_install_fd() and I wonder what specifically you
>> mean by that? The put_user() seems to be placed such that the install
>> occurrs only if it succeeded. Sure, it only handles a single fd but
>> whatever. Userspace knows that already. Just look at systemd when a
>msg
>> fails:
>> 
>> void cmsg_close_all(struct msghdr *mh) {
>>         struct cmsghdr *cmsg;
>> 
>>         assert(mh);
>> 
>>         CMSG_FOREACH(cmsg, mh)
>>                 if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type
>== SCM_RIGHTS)
>>                         close_many((int*) CMSG_DATA(cmsg),
>(cmsg->cmsg_len - CMSG_LEN(0)) / sizeof(int));
>> }
>> 
>> The only reasonable scenario for this whole mess I can think of is sm
>like (pseudo code):
>> 
>> fd_install_received(int fd, struct file *file)
>> {
>>  	sock = sock_from_file(fd, &err);
>>  	if (sock) {
>>  		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
>>  		sock_update_classid(&sock->sk->sk_cgrp_data);
>>  	}
>> 
>> 	fd_install();
>> }
>> 
>> error = 0;
>> fdarray = malloc(fdmax);
>> for (i = 0; i < fdmax; i++) {
>> 	fdarray[i] = get_unused_fd_flags(o_flags);
>> 	if (fdarray[i] < 0) {
>> 		error = -EBADF;
>> 		break;
>> 	}
>> 
>> 	error = security_file_receive(file);
>> 	if (error)
>> 		break;
>> 
>> 	error = put_user(fd_array[i], ufd);
>> 	if (error)
>> 		break;
>> }
>> 
>> for (i = 0; i < fdmax; i++) {
>> 	if (error) {
>> 		/* ignore errors */
>> 		put_user(-EBADF, ufd); /* If this put_user() fails and the first
>one succeeded userspace might now close an fd it didn't intend to. */
>> 		put_unused_fd(fdarray[i]);
>> 	} else {
>> 		fd_install_received(fdarray[i], file);
>> 	}
>> }
>
>I see 4 cases of the same code pattern (get_unused_fd_flags(),
>sock_update_*(), fd_install()), one of them has this difficult
>put_user()
>in the middle, and one of them has a potential replace_fd() instead of
>the get_used/fd_install. So, to me, it makes sense to have a helper
>that
>encapsulates the common work that each of those call sites has to do,
>which I keep cringing at all these suggestions that leave portions of
>it
>outside the helper.
>
>If it's too ugly to keep the put_user() in the helper, then we can try
>what was suggested earlier, and just totally rework the failure path
>for
>SCM_RIGHTS.
>
>LOL. And while we were debating this, hch just went and cleaned stuff
>up:
>
>2618d530dd8b ("net/scm: cleanup scm_detach_fds")
>
>So, um, yeah, now my proposal is actually even closer to what we
>already
>have there. We just add the replace_fd() logic to __scm_install_fd()
>and
>we're done with it.

Cool, you have a link? :)

Christian

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Tue, Jun 09, 2020 at 11:27:30PM +0200, Christian Brauner wrote:
> On June 9, 2020 10:55:42 PM GMT+02:00, Kees Cook <keescook@chromium.org> wrote:
> >LOL. And while we were debating this, hch just went and cleaned stuff up:
> >
> >2618d530dd8b ("net/scm: cleanup scm_detach_fds")
> >
> >So, um, yeah, now my proposal is actually even closer to what we already
> >have there. We just add the replace_fd() logic to __scm_install_fd() and
> >we're done with it.
> 
> Cool, you have a link? :)

How about this:

https://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git/commit/?h=devel/seccomp/addfd/v3.1&id=bb94586b9e7cc88e915536c2e9fb991a97b62416

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

On Tue, Jun 09, 2020 at 10:27:54PM -0700, Kees Cook wrote:
> On Tue, Jun 09, 2020 at 11:27:30PM +0200, Christian Brauner wrote:
> > On June 9, 2020 10:55:42 PM GMT+02:00, Kees Cook <keescook@chromium.org> wrote:
> > >LOL. And while we were debating this, hch just went and cleaned stuff up:
> > >
> > >2618d530dd8b ("net/scm: cleanup scm_detach_fds")
> > >
> > >So, um, yeah, now my proposal is actually even closer to what we already
> > >have there. We just add the replace_fd() logic to __scm_install_fd() and
> > >we're done with it.
> > 
> > Cool, you have a link? :)
> 
> How about this:
> 
Thank you.
> https://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git/commit/?h=devel/seccomp/addfd/v3.1&id=bb94586b9e7cc88e915536c2e9fb991a97b62416
> 
> -- 
> Kees Cook

+		if (ufd) {
+			error = put_user(new_fd, ufd);
+			if (error) {
+				put_unused_fd(new_fd);
+				return error;
+			}
+ 		}
I'm fairly sure this introduces a bug[1] if the user does:

struct msghdr msg = {};
struct cmsghdr *cmsg;
struct iovec io = {
	.iov_base = &c,
	.iov_len = 1,
};

msg.msg_iov = &io;
msg.msg_iovlen = 1;
msg.msg_control = NULL;
msg.msg_controllen = sizeof(buf);

recvmsg(sock, &msg, 0);

They will have the FD installed, no error message, but FD number wont be written 
to memory AFAICT. If two FDs are passed, you will get an efault. They will both
be installed, but memory wont be written to. Maybe instead of 0, make it a
poison pointer, or -1 instead?

-----
As an aside, all of this junk should be dropped:
+	ret = get_user(size, &uaddfd->size);
+	if (ret)
+		return ret;
+
+	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
+	if (ret)
+		return ret;

and the size member of the seccomp_notif_addfd struct. I brought this up 
off-list with Tycho that ioctls have the size of the struct embedded in them. We 
should just use that. The ioctl definition is based on this[2]:
#define _IOC(dir,type,nr,size) \
	(((dir)  << _IOC_DIRSHIFT) | \
	 ((type) << _IOC_TYPESHIFT) | \
	 ((nr)   << _IOC_NRSHIFT) | \
	 ((size) << _IOC_SIZESHIFT))


We should just use copy_from_user for now. In the future, we can either 
introduce new ioctl names for new structs, or extract the size dynamically from 
the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.

----
+#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
+						struct seccomp_notif_addfd)

Lastly, what I believe to be a small mistake, it should be SECCOMP_IOW, based on 
the documentation in ioctl.h -- "_IOW means userland is writing and kernel is 
reading."


[1]: https://lore.kernel.org/lkml/20200604052040.GA16501@ircssh-2.c.rugged-nimbus-611.internal/
[2]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/uapi/asm-generic/ioctl.h?id=v5.7#n69

RE: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[David Laight]

From: Sargun Dhillon
> Sent: 10 June 2020 09:13
> 
> On Tue, Jun 09, 2020 at 10:27:54PM -0700, Kees Cook wrote:
> > On Tue, Jun 09, 2020 at 11:27:30PM +0200, Christian Brauner wrote:
> > > On June 9, 2020 10:55:42 PM GMT+02:00, Kees Cook <keescook@chromium.org> wrote:
> > > >LOL. And while we were debating this, hch just went and cleaned stuff up:
> > > >
> > > >2618d530dd8b ("net/scm: cleanup scm_detach_fds")
> > > >
> > > >So, um, yeah, now my proposal is actually even closer to what we already
> > > >have there. We just add the replace_fd() logic to __scm_install_fd() and
> > > >we're done with it.
> > >
> > > Cool, you have a link? :)
> >
> > How about this:
> >
> Thank you.
> >
> https://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git/commit/?h=devel/seccomp/addfd/v3.1&id=b
> b94586b9e7cc88e915536c2e9fb991a97b62416
> >
> > --
> > Kees Cook
> 
> +		if (ufd) {
> +			error = put_user(new_fd, ufd);
> +			if (error) {
> +				put_unused_fd(new_fd);
> +				return error;
> +			}
> + 		}
> I'm fairly sure this introduces a bug[1] if the user does:
> 
> struct msghdr msg = {};
> struct cmsghdr *cmsg;
> struct iovec io = {
> 	.iov_base = &c,
> 	.iov_len = 1,
> };
> 
> msg.msg_iov = &io;
> msg.msg_iovlen = 1;
> msg.msg_control = NULL;
> msg.msg_controllen = sizeof(buf);
> 
> recvmsg(sock, &msg, 0);
> 
> They will have the FD installed, no error message, but FD number wont be written
> to memory AFAICT. If two FDs are passed, you will get an efault. They will both
> be installed, but memory wont be written to. Maybe instead of 0, make it a
> poison pointer, or -1 instead?

IMHO if the buffer isn't big enough the nothing should happen.
(or maybe a few of the fds be returned and the others left for later.)

OTOH if the user passed an invalid address then installing the fd
and returning EFAULT (and hence SIGSEGV) seems reasonable.
Properly written apps just don't do that.

In essence the 'copy_to_user' is done by the wrapper code.
The code filling in the CMSG buffer can be considered to be
writing a kernel buffer.

IIRC other kernels (eg NetBSD) do the copies for ioctl() requests
in the ioctl syscall wrapper.
The IOW/IOR/IOWR flags have to be right.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Wed, Jun 10, 2020 at 08:48:45AM +0000, David Laight wrote:
> From: Sargun Dhillon
> > Sent: 10 June 2020 09:13
> In essence the 'copy_to_user' is done by the wrapper code.
> The code filling in the CMSG buffer can be considered to be
> writing a kernel buffer.
> 
> IIRC other kernels (eg NetBSD) do the copies for ioctl() requests
> in the ioctl syscall wrapper.
> The IOW/IOR/IOWR flags have to be right.

Yeah, this seems like it'd make a lot more sense (and would have easily
caught the IOR/IOW issue pointed out later in the thread). I wonder how
insane it would be to try to fix that globally in the kernel...

-- 
Kees Cook

RE: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[David Laight]

From: Kees Cook
> Sent: 11 June 2020 04:03
...
> > IIRC other kernels (eg NetBSD) do the copies for ioctl() requests
> > in the ioctl syscall wrapper.
> > The IOW/IOR/IOWR flags have to be right.
> 
> Yeah, this seems like it'd make a lot more sense (and would have easily
> caught the IOR/IOW issue pointed out later in the thread). I wonder how
> insane it would be to try to fix that globally in the kernel...

Seems like a good idea to me.
(Even though I'll need to fix our 'out of tree' modules.)

Unlike [sg]etsockopt() at least the buffer is bounded to 1k.

But you'd really need to add new kernel_ioctl() entry points
before deprecating the existing ones a release or two later.

With a bit of luck there aren't any drivers ported from SYSV that
just treat the ioctl command as a 32bit transparent value and
the argument as an integer.

I actually suspect that BSD added IOW (etc) in the 16bit to 32bit port.
The kernel copies being moved to the syscall stub at the same time.
Since Linux has only ever been 32bit and uses IOW is it actually odd
that Linus didn't do the copies in the stub.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> On Tue, Jun 09, 2020 at 10:27:54PM -0700, Kees Cook wrote:
> > On Tue, Jun 09, 2020 at 11:27:30PM +0200, Christian Brauner wrote:
> > > On June 9, 2020 10:55:42 PM GMT+02:00, Kees Cook <keescook@chromium.org> wrote:
> > > >LOL. And while we were debating this, hch just went and cleaned stuff up:
> > > >
> > > >2618d530dd8b ("net/scm: cleanup scm_detach_fds")
> > > >
> > > >So, um, yeah, now my proposal is actually even closer to what we already
> > > >have there. We just add the replace_fd() logic to __scm_install_fd() and
> > > >we're done with it.
> > > 
> > > Cool, you have a link? :)
> > 
> > How about this:
> > 
> Thank you.
> > https://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git/commit/?h=devel/seccomp/addfd/v3.1&id=bb94586b9e7cc88e915536c2e9fb991a97b62416
> > 
> > -- 
> > Kees Cook
> 
> +		if (ufd) {
> +			error = put_user(new_fd, ufd);
> +			if (error) {
> +				put_unused_fd(new_fd);
> +				return error;
> +			}
> + 		}
> I'm fairly sure this introduces a bug[1] if the user does:

Ah, sorry, I missed this before I posted my "v3.2" tree link.

> 
> struct msghdr msg = {};
> struct cmsghdr *cmsg;
> struct iovec io = {
> 	.iov_base = &c,
> 	.iov_len = 1,
> };
> 
> msg.msg_iov = &io;
> msg.msg_iovlen = 1;
> msg.msg_control = NULL;
> msg.msg_controllen = sizeof(buf);
> 
> recvmsg(sock, &msg, 0);
> 
> They will have the FD installed, no error message, but FD number wont be written 
> to memory AFAICT. If two FDs are passed, you will get an efault. They will both
> be installed, but memory wont be written to. Maybe instead of 0, make it a
> poison pointer, or -1 instead?

Hmmm. I see what you mean -- SCM_RIGHTS effectively _requires_ a valid
__user pointer, so we can't use NULL to indicate "we don't want this".
I'm not sure I can pass this through directly at all, though.

> -----
> As an aside, all of this junk should be dropped:
> +	ret = get_user(size, &uaddfd->size);
> +	if (ret)
> +		return ret;
> +
> +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> +	if (ret)
> +		return ret;
> 
> and the size member of the seccomp_notif_addfd struct. I brought this up 
> off-list with Tycho that ioctls have the size of the struct embedded in them. We 
> should just use that. The ioctl definition is based on this[2]:
> #define _IOC(dir,type,nr,size) \
> 	(((dir)  << _IOC_DIRSHIFT) | \
> 	 ((type) << _IOC_TYPESHIFT) | \
> 	 ((nr)   << _IOC_NRSHIFT) | \
> 	 ((size) << _IOC_SIZESHIFT))
> 
> 
> We should just use copy_from_user for now. In the future, we can either 
> introduce new ioctl names for new structs, or extract the size dynamically from 
> the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.

Okay, sounds good.

> ----
> +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> +						struct seccomp_notif_addfd)
> 
> Lastly, what I believe to be a small mistake, it should be SECCOMP_IOW, based on 
> the documentation in ioctl.h -- "_IOW means userland is writing and kernel is 
> reading."

Okay, let me tweak things and get a "v3.3". ;)

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> As an aside, all of this junk should be dropped:
> +	ret = get_user(size, &uaddfd->size);
> +	if (ret)
> +		return ret;
> +
> +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> +	if (ret)
> +		return ret;
> 
> and the size member of the seccomp_notif_addfd struct. I brought this up 
> off-list with Tycho that ioctls have the size of the struct embedded in them. We 
> should just use that. The ioctl definition is based on this[2]:
> #define _IOC(dir,type,nr,size) \
> 	(((dir)  << _IOC_DIRSHIFT) | \
> 	 ((type) << _IOC_TYPESHIFT) | \
> 	 ((nr)   << _IOC_NRSHIFT) | \
> 	 ((size) << _IOC_SIZESHIFT))
> 
> 
> We should just use copy_from_user for now. In the future, we can either 
> introduce new ioctl names for new structs, or extract the size dynamically from 
> the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.

Yeah, that seems reasonable. Here's the diff for that part:

diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 7b6028b399d8..98bf19b4e086 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -118,7 +118,6 @@ struct seccomp_notif_resp {
 
 /**
  * struct seccomp_notif_addfd
- * @size: The size of the seccomp_notif_addfd datastructure
  * @id: The ID of the seccomp notification
  * @flags: SECCOMP_ADDFD_FLAG_*
  * @srcfd: The local fd number
@@ -126,7 +125,6 @@ struct seccomp_notif_resp {
  * @newfd_flags: The O_* flags the remote FD should have applied
  */
 struct seccomp_notif_addfd {
-	__u64 size;
 	__u64 id;
 	__u32 flags;
 	__u32 srcfd;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 3c913f3b8451..00cbdad6c480 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1297,14 +1297,9 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
 	struct seccomp_notif_addfd addfd;
 	struct seccomp_knotif *knotif;
 	struct seccomp_kaddfd kaddfd;
-	u64 size;
 	int ret;
 
-	ret = get_user(size, &uaddfd->size);
-	if (ret)
-		return ret;
-
-	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
+	ret = copy_from_user(&addfd, uaddfd, sizeof(addfd));
 	if (ret)
 		return ret;
 

> 
> ----
> +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> +						struct seccomp_notif_addfd)
> 
> Lastly, what I believe to be a small mistake, it should be SECCOMP_IOW, based on 
> the documentation in ioctl.h -- "_IOW means userland is writing and kernel is 
> reading."

Oooooh. Yeah; good catch. Uhm, that means SECCOMP_IOCTL_NOTIF_ID_VALID
is wrong too, yes? Tycho, Christian, how disruptive would this be to
fix? (Perhaps support both and deprecate the IOR version at some point
in the future?)

Diff for just addfd's change:

diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 7b6028b399d8..98bf19b4e086 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -146,7 +144,7 @@ struct seccomp_notif_addfd {
 						struct seccomp_notif_resp)
 #define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
 /* On success, the return value is the remote process's added fd number */
-#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
+#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOW(3,	\
 						struct seccomp_notif_addfd)
 
 #endif /* _UAPI_LINUX_SECCOMP_H */

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> 
> Yeah, that seems reasonable. Here's the diff for that part:
> 
> diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
> index 7b6028b399d8..98bf19b4e086 100644
> --- a/include/uapi/linux/seccomp.h
> +++ b/include/uapi/linux/seccomp.h
> @@ -118,7 +118,6 @@ struct seccomp_notif_resp {
>  
>  /**
>   * struct seccomp_notif_addfd
> - * @size: The size of the seccomp_notif_addfd datastructure
>   * @id: The ID of the seccomp notification
>   * @flags: SECCOMP_ADDFD_FLAG_*
>   * @srcfd: The local fd number
> @@ -126,7 +125,6 @@ struct seccomp_notif_resp {
>   * @newfd_flags: The O_* flags the remote FD should have applied
>   */
>  struct seccomp_notif_addfd {
> -	__u64 size;
>  	__u64 id;
>  	__u32 flags;
>  	__u32 srcfd;
> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> index 3c913f3b8451..00cbdad6c480 100644
> --- a/kernel/seccomp.c
> +++ b/kernel/seccomp.c
> @@ -1297,14 +1297,9 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
>  	struct seccomp_notif_addfd addfd;
>  	struct seccomp_knotif *knotif;
>  	struct seccomp_kaddfd kaddfd;
> -	u64 size;
>  	int ret;
>  
> -	ret = get_user(size, &uaddfd->size);
> -	if (ret)
> -		return ret;
> -
> -	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> +	ret = copy_from_user(&addfd, uaddfd, sizeof(addfd));
>  	if (ret)
>  		return ret;
>  
> 
Looks good to me. If we ever change the size of this struct, we can do the work 
then to copy_struct_from_user.

> > 
> > ----
> > +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> > +						struct seccomp_notif_addfd)
> > 
> > Lastly, what I believe to be a small mistake, it should be SECCOMP_IOW, based on 
> > the documentation in ioctl.h -- "_IOW means userland is writing and kernel is 
> > reading."
> 
> Oooooh. Yeah; good catch. Uhm, that means SECCOMP_IOCTL_NOTIF_ID_VALID
> is wrong too, yes? Tycho, Christian, how disruptive would this be to
> fix? (Perhaps support both and deprecate the IOR version at some point
> in the future?)
I think at a minimum we should change the uapi, and accept both (for now). Maybe 
a pr_warn_once telling people not to use the old one.

I can do the patch, if you want. 
> 
> Diff for just addfd's change:
> 
> diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
> index 7b6028b399d8..98bf19b4e086 100644
> --- a/include/uapi/linux/seccomp.h
> +++ b/include/uapi/linux/seccomp.h
> @@ -146,7 +144,7 @@ struct seccomp_notif_addfd {
>  						struct seccomp_notif_resp)
>  #define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
>  /* On success, the return value is the remote process's added fd number */
> -#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOW(3,	\
>  						struct seccomp_notif_addfd)
>  
>  #endif /* _UAPI_LINUX_SECCOMP_H */
> 
> -- 
> Kees Cook
Looks good. Thank you.

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > As an aside, all of this junk should be dropped:
> > +	ret = get_user(size, &uaddfd->size);
> > +	if (ret)
> > +		return ret;
> > +
> > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > +	if (ret)
> > +		return ret;
> > 
> > and the size member of the seccomp_notif_addfd struct. I brought this up 
> > off-list with Tycho that ioctls have the size of the struct embedded in them. We 
> > should just use that. The ioctl definition is based on this[2]:
> > #define _IOC(dir,type,nr,size) \
> > 	(((dir)  << _IOC_DIRSHIFT) | \
> > 	 ((type) << _IOC_TYPESHIFT) | \
> > 	 ((nr)   << _IOC_NRSHIFT) | \
> > 	 ((size) << _IOC_SIZESHIFT))
> > 
> > 
> > We should just use copy_from_user for now. In the future, we can either 
> > introduce new ioctl names for new structs, or extract the size dynamically from 
> > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> 
> Yeah, that seems reasonable. Here's the diff for that part:
> 
> diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
> index 7b6028b399d8..98bf19b4e086 100644
> --- a/include/uapi/linux/seccomp.h
> +++ b/include/uapi/linux/seccomp.h
> @@ -118,7 +118,6 @@ struct seccomp_notif_resp {
>  
>  /**
>   * struct seccomp_notif_addfd
> - * @size: The size of the seccomp_notif_addfd datastructure
>   * @id: The ID of the seccomp notification
>   * @flags: SECCOMP_ADDFD_FLAG_*
>   * @srcfd: The local fd number
> @@ -126,7 +125,6 @@ struct seccomp_notif_resp {
>   * @newfd_flags: The O_* flags the remote FD should have applied
>   */
>  struct seccomp_notif_addfd {
> -	__u64 size;
>  	__u64 id;
>  	__u32 flags;
>  	__u32 srcfd;
> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> index 3c913f3b8451..00cbdad6c480 100644
> --- a/kernel/seccomp.c
> +++ b/kernel/seccomp.c
> @@ -1297,14 +1297,9 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
>  	struct seccomp_notif_addfd addfd;
>  	struct seccomp_knotif *knotif;
>  	struct seccomp_kaddfd kaddfd;
> -	u64 size;
>  	int ret;
>  
> -	ret = get_user(size, &uaddfd->size);
> -	if (ret)
> -		return ret;
> -
> -	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> +	ret = copy_from_user(&addfd, uaddfd, sizeof(addfd));
>  	if (ret)
>  		return ret;
>  
> 
> > 
> > ----
> > +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> > +						struct seccomp_notif_addfd)
> > 
> > Lastly, what I believe to be a small mistake, it should be SECCOMP_IOW, based on 
> > the documentation in ioctl.h -- "_IOW means userland is writing and kernel is 
> > reading."
> 
> Oooooh. Yeah; good catch. Uhm, that means SECCOMP_IOCTL_NOTIF_ID_VALID
> is wrong too, yes? Tycho, Christian, how disruptive would this be to
> fix? (Perhaps support both and deprecate the IOR version at some point
> in the future?)

We have custom defines in our source code, i.e.
#define SECCOMP_IOCTL_NOTIF_ID_VALID  SECCOMP_IOR(2, __u64)
so ideally we'd have a SECCOMP_IOCTL_NOTIF_ID_VALID_V2

Does that sound ok?

Christian

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

On Thu, Jun 11, 2020 at 11:19:42AM +0200, Christian Brauner wrote:
> On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> > On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > > As an aside, all of this junk should be dropped:
> > > +	ret = get_user(size, &uaddfd->size);
> > > +	if (ret)
> > > +		return ret;
> > > +
> > > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > +	if (ret)
> > > +		return ret;
> > > 
> > > and the size member of the seccomp_notif_addfd struct. I brought this up 
> > > off-list with Tycho that ioctls have the size of the struct embedded in them. We 
> > > should just use that. The ioctl definition is based on this[2]:
> > > #define _IOC(dir,type,nr,size) \
> > > 	(((dir)  << _IOC_DIRSHIFT) | \
> > > 	 ((type) << _IOC_TYPESHIFT) | \
> > > 	 ((nr)   << _IOC_NRSHIFT) | \
> > > 	 ((size) << _IOC_SIZESHIFT))
> > > 
> > > 
> > > We should just use copy_from_user for now. In the future, we can either 
> > > introduce new ioctl names for new structs, or extract the size dynamically from 
> > > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> > 
> > Yeah, that seems reasonable. Here's the diff for that part:
> > 
> > diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
> > index 7b6028b399d8..98bf19b4e086 100644
> > --- a/include/uapi/linux/seccomp.h
> > +++ b/include/uapi/linux/seccomp.h
> > @@ -118,7 +118,6 @@ struct seccomp_notif_resp {
> >  
> >  /**
> >   * struct seccomp_notif_addfd
> > - * @size: The size of the seccomp_notif_addfd datastructure
> >   * @id: The ID of the seccomp notification
> >   * @flags: SECCOMP_ADDFD_FLAG_*
> >   * @srcfd: The local fd number
> > @@ -126,7 +125,6 @@ struct seccomp_notif_resp {
> >   * @newfd_flags: The O_* flags the remote FD should have applied
> >   */
> >  struct seccomp_notif_addfd {
> > -	__u64 size;
> >  	__u64 id;
> >  	__u32 flags;
> >  	__u32 srcfd;
> > diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> > index 3c913f3b8451..00cbdad6c480 100644
> > --- a/kernel/seccomp.c
> > +++ b/kernel/seccomp.c
> > @@ -1297,14 +1297,9 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
> >  	struct seccomp_notif_addfd addfd;
> >  	struct seccomp_knotif *knotif;
> >  	struct seccomp_kaddfd kaddfd;
> > -	u64 size;
> >  	int ret;
> >  
> > -	ret = get_user(size, &uaddfd->size);
> > -	if (ret)
> > -		return ret;
> > -
> > -	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > +	ret = copy_from_user(&addfd, uaddfd, sizeof(addfd));
> >  	if (ret)
> >  		return ret;
> >  
> > 
> > > 
> > > ----
> > > +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> > > +						struct seccomp_notif_addfd)
> > > 
> > > Lastly, what I believe to be a small mistake, it should be SECCOMP_IOW, based on 
> > > the documentation in ioctl.h -- "_IOW means userland is writing and kernel is 
> > > reading."
> > 
> > Oooooh. Yeah; good catch. Uhm, that means SECCOMP_IOCTL_NOTIF_ID_VALID
> > is wrong too, yes? Tycho, Christian, how disruptive would this be to
> > fix? (Perhaps support both and deprecate the IOR version at some point
> > in the future?)
> 
> We have custom defines in our source code, i.e.
> #define SECCOMP_IOCTL_NOTIF_ID_VALID  SECCOMP_IOR(2, __u64)
> so ideally we'd have a SECCOMP_IOCTL_NOTIF_ID_VALID_V2
> 
> Does that sound ok?
> 
> Christian
Why not change the public API in seccomp.h to:
#define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOW(2, __u64)

And then in seccomp.c:
#define SECCOMP_IOCTL_NOTIF_ID_VALID_OLD	SECCOMP_IOR(2, __u64)
static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
				 unsigned long arg)
{
	struct seccomp_filter *filter = file->private_data;
	void __user *buf = (void __user *)arg;

	switch (cmd) {
	case SECCOMP_IOCTL_NOTIF_RECV:
		return seccomp_notify_recv(filter, buf);
	case SECCOMP_IOCTL_NOTIF_SEND:
		return seccomp_notify_send(filter, buf);
	case SECCOMP_IOCTL_NOTIF_ID_VALID_OLD:
		pr_warn_once("Detected usage of legacy (incorrect) version of seccomp notifier notif_id_valid ioctl\n");
	case SECCOMP_IOCTL_NOTIF_ID_VALID:
		return seccomp_notify_id_valid(filter, buf);
	default:
		return -EINVAL;
	}
}
---- 

So, both will work fine, and whenevery anyone recompiles, or picks up new 
headers, they will start calling the "right" one without a code change, and
we wont break any userspace.

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Thu, Jun 11, 2020 at 10:39:23AM +0000, Sargun Dhillon wrote:
> On Thu, Jun 11, 2020 at 11:19:42AM +0200, Christian Brauner wrote:
> > On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> > > On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > > > As an aside, all of this junk should be dropped:
> > > > +	ret = get_user(size, &uaddfd->size);
> > > > +	if (ret)
> > > > +		return ret;
> > > > +
> > > > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > > +	if (ret)
> > > > +		return ret;
> > > > 
> > > > and the size member of the seccomp_notif_addfd struct. I brought this up 
> > > > off-list with Tycho that ioctls have the size of the struct embedded in them. We 
> > > > should just use that. The ioctl definition is based on this[2]:
> > > > #define _IOC(dir,type,nr,size) \
> > > > 	(((dir)  << _IOC_DIRSHIFT) | \
> > > > 	 ((type) << _IOC_TYPESHIFT) | \
> > > > 	 ((nr)   << _IOC_NRSHIFT) | \
> > > > 	 ((size) << _IOC_SIZESHIFT))
> > > > 
> > > > 
> > > > We should just use copy_from_user for now. In the future, we can either 
> > > > introduce new ioctl names for new structs, or extract the size dynamically from 
> > > > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> > > 
> > > Yeah, that seems reasonable. Here's the diff for that part:
> > > 
> > > diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
> > > index 7b6028b399d8..98bf19b4e086 100644
> > > --- a/include/uapi/linux/seccomp.h
> > > +++ b/include/uapi/linux/seccomp.h
> > > @@ -118,7 +118,6 @@ struct seccomp_notif_resp {
> > >  
> > >  /**
> > >   * struct seccomp_notif_addfd
> > > - * @size: The size of the seccomp_notif_addfd datastructure
> > >   * @id: The ID of the seccomp notification
> > >   * @flags: SECCOMP_ADDFD_FLAG_*
> > >   * @srcfd: The local fd number
> > > @@ -126,7 +125,6 @@ struct seccomp_notif_resp {
> > >   * @newfd_flags: The O_* flags the remote FD should have applied
> > >   */
> > >  struct seccomp_notif_addfd {
> > > -	__u64 size;
> > >  	__u64 id;
> > >  	__u32 flags;
> > >  	__u32 srcfd;
> > > diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> > > index 3c913f3b8451..00cbdad6c480 100644
> > > --- a/kernel/seccomp.c
> > > +++ b/kernel/seccomp.c
> > > @@ -1297,14 +1297,9 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
> > >  	struct seccomp_notif_addfd addfd;
> > >  	struct seccomp_knotif *knotif;
> > >  	struct seccomp_kaddfd kaddfd;
> > > -	u64 size;
> > >  	int ret;
> > >  
> > > -	ret = get_user(size, &uaddfd->size);
> > > -	if (ret)
> > > -		return ret;
> > > -
> > > -	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > +	ret = copy_from_user(&addfd, uaddfd, sizeof(addfd));
> > >  	if (ret)
> > >  		return ret;
> > >  
> > > 
> > > > 
> > > > ----
> > > > +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> > > > +						struct seccomp_notif_addfd)
> > > > 
> > > > Lastly, what I believe to be a small mistake, it should be SECCOMP_IOW, based on 
> > > > the documentation in ioctl.h -- "_IOW means userland is writing and kernel is 
> > > > reading."
> > > 
> > > Oooooh. Yeah; good catch. Uhm, that means SECCOMP_IOCTL_NOTIF_ID_VALID
> > > is wrong too, yes? Tycho, Christian, how disruptive would this be to
> > > fix? (Perhaps support both and deprecate the IOR version at some point
> > > in the future?)
> > 
> > We have custom defines in our source code, i.e.
> > #define SECCOMP_IOCTL_NOTIF_ID_VALID  SECCOMP_IOR(2, __u64)
> > so ideally we'd have a SECCOMP_IOCTL_NOTIF_ID_VALID_V2
> > 
> > Does that sound ok?
> > 
> > Christian
> Why not change the public API in seccomp.h to:
> #define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOW(2, __u64)
> 
> And then in seccomp.c:
> #define SECCOMP_IOCTL_NOTIF_ID_VALID_OLD	SECCOMP_IOR(2, __u64)
> static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
> 				 unsigned long arg)
> {
> 	struct seccomp_filter *filter = file->private_data;
> 	void __user *buf = (void __user *)arg;
> 
> 	switch (cmd) {
> 	case SECCOMP_IOCTL_NOTIF_RECV:
> 		return seccomp_notify_recv(filter, buf);
> 	case SECCOMP_IOCTL_NOTIF_SEND:
> 		return seccomp_notify_send(filter, buf);
> 	case SECCOMP_IOCTL_NOTIF_ID_VALID_OLD:
> 		pr_warn_once("Detected usage of legacy (incorrect) version of seccomp notifier notif_id_valid ioctl\n");
> 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
> 		return seccomp_notify_id_valid(filter, buf);
> 	default:
> 		return -EINVAL;
> 	}
> }
> ---- 
> 
> So, both will work fine, and whenevery anyone recompiles, or picks up new 
> headers, they will start calling the "right" one without a code change, and
> we wont break any userspace.

Yeah, that's what I'd prefer here.

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > As an aside, all of this junk should be dropped:
> > +	ret = get_user(size, &uaddfd->size);
> > +	if (ret)
> > +		return ret;
> > +
> > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > +	if (ret)
> > +		return ret;
> > 
> > and the size member of the seccomp_notif_addfd struct. I brought this up 
> > off-list with Tycho that ioctls have the size of the struct embedded in them. We 
> > should just use that. The ioctl definition is based on this[2]:
> > #define _IOC(dir,type,nr,size) \
> > 	(((dir)  << _IOC_DIRSHIFT) | \
> > 	 ((type) << _IOC_TYPESHIFT) | \
> > 	 ((nr)   << _IOC_NRSHIFT) | \
> > 	 ((size) << _IOC_SIZESHIFT))
> > 
> > 
> > We should just use copy_from_user for now. In the future, we can either 
> > introduce new ioctl names for new structs, or extract the size dynamically from 
> > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> 
> Yeah, that seems reasonable. Here's the diff for that part:

Why does it matter that the ioctl() has the size of the struct embedded
within? Afaik, the kernel itself doesn't do anything with that size. It
merely checks that the size is not pathological and it does so at
compile time.

#ifdef __CHECKER__
#define _IOC_TYPECHECK(t) (sizeof(t))
#else
/* provoke compile error for invalid uses of size argument */
extern unsigned int __invalid_size_argument_for_IOC;
#define _IOC_TYPECHECK(t) \
	((sizeof(t) == sizeof(t[1]) && \
	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
	  sizeof(t) : __invalid_size_argument_for_IOC)
#endif

The size itself is not verified at runtime. copy_struct_from_user()
still makes sense at least if we're going to allow expanding the struct
in the future.

Leaving that aside, the proposed direction here seems to mean that any
change to the struct itself will immediately mean a new ioctl() but
afaict, that also means a new struct. Since when you simply extend the
struct for the sake of the new ioctl you also change the size for the
ioctl.

Sure, you can simply treat the struct coming through the old ioctl as
being "capped" by e.g. hiding the size as suggested but then the gain
by having two separate ioctls is 0 compared to simply versioning the
struct with an explicit size member since the size encoded in the ioctl
and the actual size of the struct don't line up anymore which is the
only plus I can see for relying on _IOC_SIZE(). All this manages to do
then is to make it more annoying for userspace since they now need to
maintain multiple ioctls(). And if you have - however unlikely - say
three different ioctls all to be used with a different struct size of
the same struct I now need to know which ioctl() goes with which size of
the struct (I guess you could append the size to the ioctl name?
*shudder*). If you have the size in the struct itself you don't need to
care about any of that.
Maybe I'm not making sense or I misunderstand what's going on though.

Christian

> 
> diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
> index 7b6028b399d8..98bf19b4e086 100644
> --- a/include/uapi/linux/seccomp.h
> +++ b/include/uapi/linux/seccomp.h
> @@ -118,7 +118,6 @@ struct seccomp_notif_resp {
>  
>  /**
>   * struct seccomp_notif_addfd
> - * @size: The size of the seccomp_notif_addfd datastructure
>   * @id: The ID of the seccomp notification
>   * @flags: SECCOMP_ADDFD_FLAG_*
>   * @srcfd: The local fd number
> @@ -126,7 +125,6 @@ struct seccomp_notif_resp {
>   * @newfd_flags: The O_* flags the remote FD should have applied
>   */
>  struct seccomp_notif_addfd {
> -	__u64 size;
>  	__u64 id;
>  	__u32 flags;
>  	__u32 srcfd;
> diff --git a/kernel/seccomp.c b/kernel/seccomp.c
> index 3c913f3b8451..00cbdad6c480 100644
> --- a/kernel/seccomp.c
> +++ b/kernel/seccomp.c
> @@ -1297,14 +1297,9 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
>  	struct seccomp_notif_addfd addfd;
>  	struct seccomp_knotif *knotif;
>  	struct seccomp_kaddfd kaddfd;
> -	u64 size;
>  	int ret;
>  
> -	ret = get_user(size, &uaddfd->size);
> -	if (ret)
> -		return ret;
> -
> -	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> +	ret = copy_from_user(&addfd, uaddfd, sizeof(addfd));
>  	if (ret)
>  		return ret;
>  
> 
> > 
> > ----
> > +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> > +						struct seccomp_notif_addfd)
> > 
> > Lastly, what I believe to be a small mistake, it should be SECCOMP_IOW, based on 
> > the documentation in ioctl.h -- "_IOW means userland is writing and kernel is 
> > reading."
> 
> Oooooh. Yeah; good catch. Uhm, that means SECCOMP_IOCTL_NOTIF_ID_VALID
> is wrong too, yes? Tycho, Christian, how disruptive would this be to
> fix? (Perhaps support both and deprecate the IOR version at some point
> in the future?)
> 
> Diff for just addfd's change:
> 
> diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
> index 7b6028b399d8..98bf19b4e086 100644
> --- a/include/uapi/linux/seccomp.h
> +++ b/include/uapi/linux/seccomp.h
> @@ -146,7 +144,7 @@ struct seccomp_notif_addfd {
>  						struct seccomp_notif_resp)
>  #define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
>  /* On success, the return value is the remote process's added fd number */
> -#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
> +#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOW(3,	\
>  						struct seccomp_notif_addfd)
>  
>  #endif /* _UAPI_LINUX_SECCOMP_H */
> 
> -- 
> Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

On Thu, Jun 11, 2020 at 12:01:14PM +0200, Christian Brauner wrote:
> On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> > On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > > As an aside, all of this junk should be dropped:
> > > +	ret = get_user(size, &uaddfd->size);
> > > +	if (ret)
> > > +		return ret;
> > > +
> > > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > +	if (ret)
> > > +		return ret;
> > > 
> > > and the size member of the seccomp_notif_addfd struct. I brought this up 
> > > off-list with Tycho that ioctls have the size of the struct embedded in them. We 
> > > should just use that. The ioctl definition is based on this[2]:
> > > #define _IOC(dir,type,nr,size) \
> > > 	(((dir)  << _IOC_DIRSHIFT) | \
> > > 	 ((type) << _IOC_TYPESHIFT) | \
> > > 	 ((nr)   << _IOC_NRSHIFT) | \
> > > 	 ((size) << _IOC_SIZESHIFT))
> > > 
> > > 
> > > We should just use copy_from_user for now. In the future, we can either 
> > > introduce new ioctl names for new structs, or extract the size dynamically from 
> > > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> > 
> > Yeah, that seems reasonable. Here's the diff for that part:
> 
> Why does it matter that the ioctl() has the size of the struct embedded
> within? Afaik, the kernel itself doesn't do anything with that size. It
> merely checks that the size is not pathological and it does so at
> compile time.
> 
> #ifdef __CHECKER__
> #define _IOC_TYPECHECK(t) (sizeof(t))
> #else
> /* provoke compile error for invalid uses of size argument */
> extern unsigned int __invalid_size_argument_for_IOC;
> #define _IOC_TYPECHECK(t) \
> 	((sizeof(t) == sizeof(t[1]) && \
> 	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
> 	  sizeof(t) : __invalid_size_argument_for_IOC)
> #endif
> 
> The size itself is not verified at runtime. copy_struct_from_user()
> still makes sense at least if we're going to allow expanding the struct
> in the future.
Right, but if we simply change our headers and extend the struct, it will break 
all existing programs compiled against those headers. In order to avoid that, if 
we intend on extending this struct by appending to it, we need to have a 
backwards compatibility mechanism. Just having copy_struct_from_user isn't 
enough. The data structure either must be fixed size, or we need a way to handle 
multiple ioctl numbers derived from headers with different sized struct arguments

The two approaches I see are:
1. use more indirection. This has previous art in drm[1]. That's look
something like this:

struct seccomp_notif_addfd_ptr {
	__u64 size;
	__u64 addr;
}

... And then it'd be up to us to dereference the addr and copy struct from user.

2. Expose one ioctl to the user, many internally

e.g., public api:

struct seccomp_notif {
	__u64 id;
	__u64 pid;
	struct seccomp_data;
	__u64 fancy_new_field;
}

#define SECCOMP_IOCTL_NOTIF_RECV	SECCOMP_IOWR(0, struct seccomp_notif)

internally:
struct seccomp_notif_v1 {
	__u64 id;
	__u64 pid;
	struct seccomp_data;
}

struct seccomp_notif_v2 {
	__u64 id;
	__u64 pid;
	struct seccomp_data;
	__u64 fancy_new_field;
}

and we can switch like this:
	switch (cmd) {
	/* for example. We actually have to do this for any struct we intend to 
	 * extend to get proper backwards compatibility
	 */
	case SECCOMP_IOWR(0, struct seccomp_notif_v1)
		return seccomp_notify_recv(filter, buf, sizeof(struct seccomp_notif_v1));
	case SECCOMP_IOWR(0, struct seccomp_notif_v2)
		return seccomp_notify_recv(filter, buf, sizeof(struct seccomp_notif_v3));
...
	case SECCOMP_IOCTL_NOTIF_SEND:
		return seccomp_notify_send(filter, buf);
	case SECCOMP_IOCTL_NOTIF_ID_VALID:
		return seccomp_notify_id_valid(filter, buf);
	default:
		return -EINVAL;
	}

This has the downside that programs compiled against more modern kernel headers 
will break on older kernels.

3. We can take the approach you suggested.

#define UNSIZED(cmd)	(cmd & ~(_IOC_SIZEMASK << _IOC_SIZESHIFT)
static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
				 unsigned long arg)
{
	struct seccomp_filter *filter = file->private_data;
	void __user *buf = (void __user *)arg;
	int size = _IOC_SIZE(cmd);
	cmd = UNSIZED(cmd);

	switch (cmd) {
	/* for example. We actually have to do this for any struct we intend to 
	 * extend to get proper backwards compatibility
	 */
	case UNSIZED(SECCOMP_IOCTL_NOTIF_RECV):
		return seccomp_notify_recv(filter, buf, size);
...
	case SECCOMP_IOCTL_NOTIF_SEND:
		return seccomp_notify_send(filter, buf);
	case SECCOMP_IOCTL_NOTIF_ID_VALID:
		return seccomp_notify_id_valid(filter, buf);
	default:
		return -EINVAL;
	}
}

> 
> Leaving that aside, the proposed direction here seems to mean that any
> change to the struct itself will immediately mean a new ioctl() but
> afaict, that also means a new struct. Since when you simply extend the
> struct for the sake of the new ioctl you also change the size for the
> ioctl.
> 
> Sure, you can simply treat the struct coming through the old ioctl as
> being "capped" by e.g. hiding the size as suggested but then the gain
> by having two separate ioctls is 0 compared to simply versioning the
> struct with an explicit size member since the size encoded in the ioctl
> and the actual size of the struct don't line up anymore which is the
> only plus I can see for relying on _IOC_SIZE(). All this manages to do
> then is to make it more annoying for userspace since they now need to
> maintain multiple ioctls(). And if you have - however unlikely - say
> three different ioctls all to be used with a different struct size of
> the same struct I now need to know which ioctl() goes with which size of
> the struct (I guess you could append the size to the ioctl name?
> *shudder*). If you have the size in the struct itself you don't need to
> care about any of that.
> Maybe I'm not making sense or I misunderstand what's going on though.
> 
> Christian
> 
I don't understand why userspace has to have any knowledge of this. As soon as 
we add the code above, and we use copy_struct_from_user based on _that_ size,
userspace will get free upgrades. If they are compiling against an older header
than the kernel, size will return a smaller number, and thus we will zero
out our trailing bits, and if their number is bigger, we just check their
bits are appropriately zeroed.

This approach would be forwards-and-backwards compatible.

There's a little bit of prior art here as well [2]. The approach is that
we effectively do the thing we had earlier with passing a size with
copy_struct_from_user, but instead of the size being embedded in the struct,
it's embedded in the ioctl command itself.


[1]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/uapi/drm/radeon_drm.h?h=v5.7#n831
[2]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/firewire/core-cdev.c?id=v5.7#n1621

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Thu, Jun 11, 2020 at 11:06:31AM +0000, Sargun Dhillon wrote:
> On Thu, Jun 11, 2020 at 12:01:14PM +0200, Christian Brauner wrote:
> > On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> > > On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > > > As an aside, all of this junk should be dropped:
> > > > +	ret = get_user(size, &uaddfd->size);
> > > > +	if (ret)
> > > > +		return ret;
> > > > +
> > > > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > > +	if (ret)
> > > > +		return ret;
> > > > 
> > > > and the size member of the seccomp_notif_addfd struct. I brought this up 
> > > > off-list with Tycho that ioctls have the size of the struct embedded in them. We 
> > > > should just use that. The ioctl definition is based on this[2]:
> > > > #define _IOC(dir,type,nr,size) \
> > > > 	(((dir)  << _IOC_DIRSHIFT) | \
> > > > 	 ((type) << _IOC_TYPESHIFT) | \
> > > > 	 ((nr)   << _IOC_NRSHIFT) | \
> > > > 	 ((size) << _IOC_SIZESHIFT))
> > > > 
> > > > 
> > > > We should just use copy_from_user for now. In the future, we can either 
> > > > introduce new ioctl names for new structs, or extract the size dynamically from 
> > > > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> > > 
> > > Yeah, that seems reasonable. Here's the diff for that part:
> > 
> > Why does it matter that the ioctl() has the size of the struct embedded
> > within? Afaik, the kernel itself doesn't do anything with that size. It
> > merely checks that the size is not pathological and it does so at
> > compile time.
> > 
> > #ifdef __CHECKER__
> > #define _IOC_TYPECHECK(t) (sizeof(t))
> > #else
> > /* provoke compile error for invalid uses of size argument */
> > extern unsigned int __invalid_size_argument_for_IOC;
> > #define _IOC_TYPECHECK(t) \
> > 	((sizeof(t) == sizeof(t[1]) && \
> > 	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
> > 	  sizeof(t) : __invalid_size_argument_for_IOC)
> > #endif
> > 
> > The size itself is not verified at runtime. copy_struct_from_user()
> > still makes sense at least if we're going to allow expanding the struct
> > in the future.
> Right, but if we simply change our headers and extend the struct, it will break 
> all existing programs compiled against those headers. In order to avoid that, if 
> we intend on extending this struct by appending to it, we need to have a 
> backwards compatibility mechanism. Just having copy_struct_from_user isn't 
> enough. The data structure either must be fixed size, or we need a way to handle 
> multiple ioctl numbers derived from headers with different sized struct arguments
> 
> The two approaches I see are:
> 1. use more indirection. This has previous art in drm[1]. That's look
> something like this:
> 
> struct seccomp_notif_addfd_ptr {
> 	__u64 size;
> 	__u64 addr;
> }
> 
> ... And then it'd be up to us to dereference the addr and copy struct from user.

Which isn't great but could do.

> 
> 2. Expose one ioctl to the user, many internally
> 
> e.g., public api:
> 
> struct seccomp_notif {
> 	__u64 id;
> 	__u64 pid;
> 	struct seccomp_data;
> 	__u64 fancy_new_field;
> }
> 
> #define SECCOMP_IOCTL_NOTIF_RECV	SECCOMP_IOWR(0, struct seccomp_notif)
> 
> internally:
> struct seccomp_notif_v1 {
> 	__u64 id;
> 	__u64 pid;
> 	struct seccomp_data;
> }
> 
> struct seccomp_notif_v2 {
> 	__u64 id;
> 	__u64 pid;
> 	struct seccomp_data;
> 	__u64 fancy_new_field;
> }
> 
> and we can switch like this:
> 	switch (cmd) {
> 	/* for example. We actually have to do this for any struct we intend to 
> 	 * extend to get proper backwards compatibility
> 	 */
> 	case SECCOMP_IOWR(0, struct seccomp_notif_v1)
> 		return seccomp_notify_recv(filter, buf, sizeof(struct seccomp_notif_v1));
> 	case SECCOMP_IOWR(0, struct seccomp_notif_v2)
> 		return seccomp_notify_recv(filter, buf, sizeof(struct seccomp_notif_v3));
> ...
> 	case SECCOMP_IOCTL_NOTIF_SEND:
> 		return seccomp_notify_send(filter, buf);
> 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
> 		return seccomp_notify_id_valid(filter, buf);
> 	default:
> 		return -EINVAL;
> 	}
> 
> This has the downside that programs compiled against more modern kernel headers 
> will break on older kernels.
> 
> 3. We can take the approach you suggested.
> 
> #define UNSIZED(cmd)	(cmd & ~(_IOC_SIZEMASK << _IOC_SIZESHIFT)
> static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
> 				 unsigned long arg)
> {
> 	struct seccomp_filter *filter = file->private_data;
> 	void __user *buf = (void __user *)arg;
> 	int size = _IOC_SIZE(cmd);
> 	cmd = UNSIZED(cmd);
> 
> 	switch (cmd) {
> 	/* for example. We actually have to do this for any struct we intend to 
> 	 * extend to get proper backwards compatibility
> 	 */
> 	case UNSIZED(SECCOMP_IOCTL_NOTIF_RECV):
> 		return seccomp_notify_recv(filter, buf, size);
> ...
> 	case SECCOMP_IOCTL_NOTIF_SEND:
> 		return seccomp_notify_send(filter, buf);
> 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
> 		return seccomp_notify_id_valid(filter, buf);
> 	default:
> 		return -EINVAL;
> 	}
> }
> 
> > 
> > Leaving that aside, the proposed direction here seems to mean that any
> > change to the struct itself will immediately mean a new ioctl() but
> > afaict, that also means a new struct. Since when you simply extend the
> > struct for the sake of the new ioctl you also change the size for the
> > ioctl.
> > 
> > Sure, you can simply treat the struct coming through the old ioctl as
> > being "capped" by e.g. hiding the size as suggested but then the gain
> > by having two separate ioctls is 0 compared to simply versioning the
> > struct with an explicit size member since the size encoded in the ioctl
> > and the actual size of the struct don't line up anymore which is the
> > only plus I can see for relying on _IOC_SIZE(). All this manages to do
> > then is to make it more annoying for userspace since they now need to
> > maintain multiple ioctls(). And if you have - however unlikely - say
> > three different ioctls all to be used with a different struct size of
> > the same struct I now need to know which ioctl() goes with which size of
> > the struct (I guess you could append the size to the ioctl name?
> > *shudder*). If you have the size in the struct itself you don't need to
> > care about any of that.
> > Maybe I'm not making sense or I misunderstand what's going on though.
> > 
> > Christian
> > 
> I don't understand why userspace has to have any knowledge of this. As soon as 
> we add the code above, and we use copy_struct_from_user based on _that_ size,

Hm, which code exactly?

In the previous mail the only thing proposed was to switch to a simple
copy_from_user() which effectively bars us from extending the
seccomp_addfd struct which this is about, right? At that point, the only
option then becomes to either introduce a new ioctl() and a new struct
or to go for the hack in e.g. 3. (Afaiu, 2. is not working anymore
because we break userspace as soon as we append "fancy_new_field" to the
struct because it changes the ioctl() unless I'm missing something.)

Let me maybe rephrase: I'd prefer we merge something for addfd that is
extensible with minimal burden on userspace. 
But if we are fine with saying "we don't care, let's just use
copy_from_user() for addfd and if we extend we add a new struct + ioctl"
then ok, sure. But I would prefer to keep dealing with new structs +
ioctls (Look at the end of btrfs.h [1] unlikely to be a problem for us,
but still.) as little as possible because that will be more churn in
userspace code than I'd prefer.

So either [1] or - since none of the generic extensibility seems to be
particularly nice - we bite the bullet and just add a:

__u64 reserved[4]

field and hope that this will carry us for a long time (probably will
for quite a long time) and defer the new ioctl() problem.

[1]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/uapi/linux/btrfs.h

> userspace will get free upgrades. If they are compiling against an older header
> than the kernel, size will return a smaller number, and thus we will zero
> out our trailing bits, and if their number is bigger, we just check their
> bits are appropriately zeroed.
> 
> This approach would be forwards-and-backwards compatible.
> 
> There's a little bit of prior art here as well [2]. The approach is that
> we effectively do the thing we had earlier with passing a size with
> copy_struct_from_user, but instead of the size being embedded in the struct,
> it's embedded in the ioctl command itself.

That looks super sketchy. :D

Christian

RE: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[David Laight]

From: Sargun Dhillon
> Sent: 11 June 2020 12:07
> Subject: Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes
> 
> On Thu, Jun 11, 2020 at 12:01:14PM +0200, Christian Brauner wrote:
> > On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> > > On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > > > As an aside, all of this junk should be dropped:
> > > > +	ret = get_user(size, &uaddfd->size);
> > > > +	if (ret)
> > > > +		return ret;
> > > > +
> > > > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > > +	if (ret)
> > > > +		return ret;
> > > >
> > > > and the size member of the seccomp_notif_addfd struct. I brought this up
> > > > off-list with Tycho that ioctls have the size of the struct embedded in them. We
> > > > should just use that. The ioctl definition is based on this[2]:
> > > > #define _IOC(dir,type,nr,size) \
> > > > 	(((dir)  << _IOC_DIRSHIFT) | \
> > > > 	 ((type) << _IOC_TYPESHIFT) | \
> > > > 	 ((nr)   << _IOC_NRSHIFT) | \
> > > > 	 ((size) << _IOC_SIZESHIFT))
> > > >
> > > >
> > > > We should just use copy_from_user for now. In the future, we can either
> > > > introduce new ioctl names for new structs, or extract the size dynamically from
> > > > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> > >
> > > Yeah, that seems reasonable. Here's the diff for that part:
> >
> > Why does it matter that the ioctl() has the size of the struct embedded
> > within? Afaik, the kernel itself doesn't do anything with that size. It
> > merely checks that the size is not pathological and it does so at
> > compile time.
> >
> > #ifdef __CHECKER__
> > #define _IOC_TYPECHECK(t) (sizeof(t))
> > #else
> > /* provoke compile error for invalid uses of size argument */
> > extern unsigned int __invalid_size_argument_for_IOC;
> > #define _IOC_TYPECHECK(t) \
> > 	((sizeof(t) == sizeof(t[1]) && \
> > 	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
> > 	  sizeof(t) : __invalid_size_argument_for_IOC)
> > #endif
> >
> > The size itself is not verified at runtime. copy_struct_from_user()
> > still makes sense at least if we're going to allow expanding the struct
> > in the future.
> Right, but if we simply change our headers and extend the struct, it will break
> all existing programs compiled against those headers. In order to avoid that, if
> we intend on extending this struct by appending to it, we need to have a
> backwards compatibility mechanism. Just having copy_struct_from_user isn't
> enough. The data structure either must be fixed size, or we need a way to handle
> multiple ioctl numbers derived from headers with different sized struct arguments
> 
> The two approaches I see are:
> 1. use more indirection. This has previous art in drm[1]. That's look
> something like this:
> 
> struct seccomp_notif_addfd_ptr {
> 	__u64 size;
> 	__u64 addr;
> }
> 
> ... And then it'd be up to us to dereference the addr and copy struct from user.

Do not go down that route. It isn't worth the pain.

You should also assume that userspace might have a compile-time check
on the buffer length (I've written one - not hard) and that the kernel
might (in the future - or on a BSD kernel) be doing the user copies
for you.

Also, if you change the structure you almost certainly need to
change the name of the ioctl cmd as well as its value.
Otherwise a recompiled program will pass the new cmd value (and
hopefully the right sized buffer) but it won't have initialised
the buffer properly.
This is likely to lead to unexpected behaviour.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Thu, Jun 11, 2020 at 02:56:22PM +0000, David Laight wrote:
> From: Sargun Dhillon
> > Sent: 11 June 2020 12:07
> > Subject: Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes
> > 
> > On Thu, Jun 11, 2020 at 12:01:14PM +0200, Christian Brauner wrote:
> > > On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> > > > On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > > > > As an aside, all of this junk should be dropped:
> > > > > +	ret = get_user(size, &uaddfd->size);
> > > > > +	if (ret)
> > > > > +		return ret;
> > > > > +
> > > > > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > > > +	if (ret)
> > > > > +		return ret;
> > > > >
> > > > > and the size member of the seccomp_notif_addfd struct. I brought this up
> > > > > off-list with Tycho that ioctls have the size of the struct embedded in them. We
> > > > > should just use that. The ioctl definition is based on this[2]:
> > > > > #define _IOC(dir,type,nr,size) \
> > > > > 	(((dir)  << _IOC_DIRSHIFT) | \
> > > > > 	 ((type) << _IOC_TYPESHIFT) | \
> > > > > 	 ((nr)   << _IOC_NRSHIFT) | \
> > > > > 	 ((size) << _IOC_SIZESHIFT))
> > > > >
> > > > >
> > > > > We should just use copy_from_user for now. In the future, we can either
> > > > > introduce new ioctl names for new structs, or extract the size dynamically from
> > > > > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> > > >
> > > > Yeah, that seems reasonable. Here's the diff for that part:
> > >
> > > Why does it matter that the ioctl() has the size of the struct embedded
> > > within? Afaik, the kernel itself doesn't do anything with that size. It
> > > merely checks that the size is not pathological and it does so at
> > > compile time.
> > >
> > > #ifdef __CHECKER__
> > > #define _IOC_TYPECHECK(t) (sizeof(t))
> > > #else
> > > /* provoke compile error for invalid uses of size argument */
> > > extern unsigned int __invalid_size_argument_for_IOC;
> > > #define _IOC_TYPECHECK(t) \
> > > 	((sizeof(t) == sizeof(t[1]) && \
> > > 	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
> > > 	  sizeof(t) : __invalid_size_argument_for_IOC)
> > > #endif
> > >
> > > The size itself is not verified at runtime. copy_struct_from_user()
> > > still makes sense at least if we're going to allow expanding the struct
> > > in the future.
> > Right, but if we simply change our headers and extend the struct, it will break
> > all existing programs compiled against those headers. In order to avoid that, if
> > we intend on extending this struct by appending to it, we need to have a
> > backwards compatibility mechanism. Just having copy_struct_from_user isn't
> > enough. The data structure either must be fixed size, or we need a way to handle
> > multiple ioctl numbers derived from headers with different sized struct arguments
> > 
> > The two approaches I see are:
> > 1. use more indirection. This has previous art in drm[1]. That's look
> > something like this:
> > 
> > struct seccomp_notif_addfd_ptr {
> > 	__u64 size;
> > 	__u64 addr;
> > }
> > 
> > ... And then it'd be up to us to dereference the addr and copy struct from user.
> 
> Do not go down that route. It isn't worth the pain.
> 
> You should also assume that userspace might have a compile-time check
> on the buffer length (I've written one - not hard) and that the kernel
> might (in the future - or on a BSD kernel) be doing the user copies
> for you.
> 
> Also, if you change the structure you almost certainly need to
> change the name of the ioctl cmd as well as its value.
> Otherwise a recompiled program will pass the new cmd value (and
> hopefully the right sized buffer) but it won't have initialised
> the buffer properly.
> This is likely to lead to unexpected behaviour.

Hmmm.

So, while initially I thought Sargun's observation about ioctl's fixed
struct size was right, I think I've been swayed to Christian's view
(which is supported by the long tail of struct size pain we've seen in
other APIs).

Doing a separate ioctl for each structure version seems like the "old
solution" now that we've got EA syscalls. So, I'd like to keep the size
and copy_struct_from_user().

Which leaves us with the question of how to deal with the ioctl
numbering. As we've seen, there is no actual enforcement of direction
nor size, so to that end, while we could provide the hints about both, I
guess we just don't need to. To that end, perhaps _IO() is best:

#define SECCOMP_IOCTL_NOTIF_ADDFD       SECCOMP_IO(3)

Alternatively, we could use a size of either 0, 8(u64), or -1, and then
use IORW() so we _also_ won't paint ourselves into a corner if we ever
want to write something back to userspace in the structure:

#define SECCOMP_IOCTL_EA(nr) _IOC(_IOC_READ|_IOC_WRITE,SECCOMP_IOC_MAGIC,(nr),0)
#define SECCOMP_IOCTL_NOTIF_ADDFD       SECCOMP_IOCTL_EA(3)

or

#define SECCOMP_IOCTL_EA(nr) _IOC(_IOC_READ|_IOC_WRITE,SECCOMP_IOC_MAGIC,(nr),8)
#define SECCOMP_IOCTL_NOTIF_ADDFD       SECCOMP_IOCTL_EA(3)

or

#define SECCOMP_IOCTL_EA(nr) _IOC(_IOC_READ|_IOC_WRITE,SECCOMP_IOC_MAGIC,(nr),_IOC_SIZEMASK)
#define SECCOMP_IOCTL_NOTIF_ADDFD       SECCOMP_IOCTL_EA(3)

I think I prefer the last one.

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Thu, Jun 11, 2020 at 04:49:37PM -0700, Kees Cook wrote:
> I think I prefer the last one.

Here's where I am with things:

https://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git/log/?h=devel/seccomp/addfd/v3.3

If we can agree on the ioctl numbering solution, I can actually send the
series for email review...

-- 
Kees Cook

RE: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[David Laight]

From: Kees Cook
> Sent: 12 June 2020 00:50
> > From: Sargun Dhillon
> > > Sent: 11 June 2020 12:07
> > > Subject: Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across
> processes
> > >
> > > On Thu, Jun 11, 2020 at 12:01:14PM +0200, Christian Brauner wrote:
> > > > On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> > > > > On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > > > > > As an aside, all of this junk should be dropped:
> > > > > > +	ret = get_user(size, &uaddfd->size);
> > > > > > +	if (ret)
> > > > > > +		return ret;
> > > > > > +
> > > > > > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > > > > +	if (ret)
> > > > > > +		return ret;
> > > > > >
> > > > > > and the size member of the seccomp_notif_addfd struct. I brought this up
> > > > > > off-list with Tycho that ioctls have the size of the struct embedded in them. We
> > > > > > should just use that. The ioctl definition is based on this[2]:
> > > > > > #define _IOC(dir,type,nr,size) \
> > > > > > 	(((dir)  << _IOC_DIRSHIFT) | \
> > > > > > 	 ((type) << _IOC_TYPESHIFT) | \
> > > > > > 	 ((nr)   << _IOC_NRSHIFT) | \
> > > > > > 	 ((size) << _IOC_SIZESHIFT))
> > > > > >
> > > > > >
> > > > > > We should just use copy_from_user for now. In the future, we can either
> > > > > > introduce new ioctl names for new structs, or extract the size dynamically from
> > > > > > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> > > > >
> > > > > Yeah, that seems reasonable. Here's the diff for that part:
> > > >
> > > > Why does it matter that the ioctl() has the size of the struct embedded
> > > > within? Afaik, the kernel itself doesn't do anything with that size. It
> > > > merely checks that the size is not pathological and it does so at
> > > > compile time.
> > > >
> > > > #ifdef __CHECKER__
> > > > #define _IOC_TYPECHECK(t) (sizeof(t))
> > > > #else
> > > > /* provoke compile error for invalid uses of size argument */
> > > > extern unsigned int __invalid_size_argument_for_IOC;
> > > > #define _IOC_TYPECHECK(t) \
> > > > 	((sizeof(t) == sizeof(t[1]) && \
> > > > 	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
> > > > 	  sizeof(t) : __invalid_size_argument_for_IOC)
> > > > #endif
> > > >
> > > > The size itself is not verified at runtime. copy_struct_from_user()
> > > > still makes sense at least if we're going to allow expanding the struct
> > > > in the future.
> > > Right, but if we simply change our headers and extend the struct, it will break
> > > all existing programs compiled against those headers. In order to avoid that, if
> > > we intend on extending this struct by appending to it, we need to have a
> > > backwards compatibility mechanism. Just having copy_struct_from_user isn't
> > > enough. The data structure either must be fixed size, or we need a way to handle
> > > multiple ioctl numbers derived from headers with different sized struct arguments
> > >
> > > The two approaches I see are:
> > > 1. use more indirection. This has previous art in drm[1]. That's look
> > > something like this:
> > >
> > > struct seccomp_notif_addfd_ptr {
> > > 	__u64 size;
> > > 	__u64 addr;
> > > }
> > >
> > > ... And then it'd be up to us to dereference the addr and copy struct from user.
> >
> > Do not go down that route. It isn't worth the pain.
> >
> > You should also assume that userspace might have a compile-time check
> > on the buffer length (I've written one - not hard) and that the kernel
> > might (in the future - or on a BSD kernel) be doing the user copies
> > for you.
> >
> > Also, if you change the structure you almost certainly need to
> > change the name of the ioctl cmd as well as its value.
> > Otherwise a recompiled program will pass the new cmd value (and
> > hopefully the right sized buffer) but it won't have initialised
> > the buffer properly.
> > This is likely to lead to unexpected behaviour.
> 
> Hmmm.
> 
> So, while initially I thought Sargun's observation about ioctl's fixed
> struct size was right, I think I've been swayed to Christian's view
> (which is supported by the long tail of struct size pain we've seen in
> other APIs).
> 
> Doing a separate ioctl for each structure version seems like the "old
> solution" now that we've got EA syscalls. So, I'd like to keep the size
> and copy_struct_from_user().

If the size is variable then why not get the application to fill
in the size of the structure it is sending at the time of the ioctl.

So you'd have:
#define xxx_IOCTL_17(param) _IOCW('X', 17, sizeof *(param))

The application code would then do:
	ioctl(fd, xxx_IOCTL_17(arg), arg);

The kernel code can either choose to have specific 'case'
for each size, or mask off the length bits and do the
length check later.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

On Fri, Jun 12, 2020 at 08:36:03AM +0000, David Laight wrote:
> From: Kees Cook
> > Sent: 12 June 2020 00:50
> > > From: Sargun Dhillon
> > > > Sent: 11 June 2020 12:07
> > > > Subject: Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across
> > processes
> > > >
> > > > On Thu, Jun 11, 2020 at 12:01:14PM +0200, Christian Brauner wrote:
> > > > > On Wed, Jun 10, 2020 at 07:59:55PM -0700, Kees Cook wrote:
> > > > > > On Wed, Jun 10, 2020 at 08:12:38AM +0000, Sargun Dhillon wrote:
> > > > > > > As an aside, all of this junk should be dropped:
> > > > > > > +	ret = get_user(size, &uaddfd->size);
> > > > > > > +	if (ret)
> > > > > > > +		return ret;
> > > > > > > +
> > > > > > > +	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > > > > > > +	if (ret)
> > > > > > > +		return ret;
> > > > > > >
> > > > > > > and the size member of the seccomp_notif_addfd struct. I brought this up
> > > > > > > off-list with Tycho that ioctls have the size of the struct embedded in them. We
> > > > > > > should just use that. The ioctl definition is based on this[2]:
> > > > > > > #define _IOC(dir,type,nr,size) \
> > > > > > > 	(((dir)  << _IOC_DIRSHIFT) | \
> > > > > > > 	 ((type) << _IOC_TYPESHIFT) | \
> > > > > > > 	 ((nr)   << _IOC_NRSHIFT) | \
> > > > > > > 	 ((size) << _IOC_SIZESHIFT))
> > > > > > >
> > > > > > >
> > > > > > > We should just use copy_from_user for now. In the future, we can either
> > > > > > > introduce new ioctl names for new structs, or extract the size dynamically from
> > > > > > > the ioctl (and mask it out on the switch statement in seccomp_notify_ioctl.
> > > > > >
> > > > > > Yeah, that seems reasonable. Here's the diff for that part:
> > > > >
> > > > > Why does it matter that the ioctl() has the size of the struct embedded
> > > > > within? Afaik, the kernel itself doesn't do anything with that size. It
> > > > > merely checks that the size is not pathological and it does so at
> > > > > compile time.
> > > > >
> > > > > #ifdef __CHECKER__
> > > > > #define _IOC_TYPECHECK(t) (sizeof(t))
> > > > > #else
> > > > > /* provoke compile error for invalid uses of size argument */
> > > > > extern unsigned int __invalid_size_argument_for_IOC;
> > > > > #define _IOC_TYPECHECK(t) \
> > > > > 	((sizeof(t) == sizeof(t[1]) && \
> > > > > 	  sizeof(t) < (1 << _IOC_SIZEBITS)) ? \
> > > > > 	  sizeof(t) : __invalid_size_argument_for_IOC)
> > > > > #endif
> > > > >
> > > > > The size itself is not verified at runtime. copy_struct_from_user()
> > > > > still makes sense at least if we're going to allow expanding the struct
> > > > > in the future.
> > > > Right, but if we simply change our headers and extend the struct, it will break
> > > > all existing programs compiled against those headers. In order to avoid that, if
> > > > we intend on extending this struct by appending to it, we need to have a
> > > > backwards compatibility mechanism. Just having copy_struct_from_user isn't
> > > > enough. The data structure either must be fixed size, or we need a way to handle
> > > > multiple ioctl numbers derived from headers with different sized struct arguments
> > > >
> > > > The two approaches I see are:
> > > > 1. use more indirection. This has previous art in drm[1]. That's look
> > > > something like this:
> > > >
> > > > struct seccomp_notif_addfd_ptr {
> > > > 	__u64 size;
> > > > 	__u64 addr;
> > > > }
> > > >
> > > > ... And then it'd be up to us to dereference the addr and copy struct from user.
> > >
> > > Do not go down that route. It isn't worth the pain.
> > >
> > > You should also assume that userspace might have a compile-time check
> > > on the buffer length (I've written one - not hard) and that the kernel
> > > might (in the future - or on a BSD kernel) be doing the user copies
> > > for you.
> > >
> > > Also, if you change the structure you almost certainly need to
> > > change the name of the ioctl cmd as well as its value.
> > > Otherwise a recompiled program will pass the new cmd value (and
> > > hopefully the right sized buffer) but it won't have initialised
> > > the buffer properly.
> > > This is likely to lead to unexpected behaviour.
Why do you say this? Assuming people are just pulling in <linux/seccomp.h>
they will get both the ioctl number, and the struct. The one case where
I can see things going wrong is languages which implement their own struct
packing / ioctls and wouldn't get the updated # because it's hard coded.


> > 
> > Hmmm.
> > 
> > So, while initially I thought Sargun's observation about ioctl's fixed
> > struct size was right, I think I've been swayed to Christian's view
> > (which is supported by the long tail of struct size pain we've seen in
> > other APIs).
> > 
> > Doing a separate ioctl for each structure version seems like the "old
> > solution" now that we've got EA syscalls. So, I'd like to keep the size
> > and copy_struct_from_user().
> 
> If the size is variable then why not get the application to fill
> in the size of the structure it is sending at the time of the ioctl.
> 
> So you'd have:
> #define xxx_IOCTL_17(param) _IOCW('X', 17, sizeof *(param))
> 
> The application code would then do:
> 	ioctl(fd, xxx_IOCTL_17(arg), arg);
> 
> The kernel code can either choose to have specific 'case'
> for each size, or mask off the length bits and do the
> length check later.
> 
> 	David
> 
> 
My suggest, written out (no idea if this code actually works), is as follows:

ioctl.h:
/* This needs to be added */
#define IOCDIR_MASK	(_IOC_DIRMASK << _IOC_DIRSHIFT)


seccomp.h:

struct struct seccomp_notif_addfd {
	__u64 fd;
	...
}

/* or IOW? */
#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOWR(3, struct seccomp_notif_addfd)

seccomp.c:
static long seccomp_notify_addfd(struct seccomp_filter *filter,
				 struct seccomp_notif_addfd __user *uaddfd int size)
{
	struct seccomp_notif_addfd addfd;
	int ret;

	if (size < 32)
		return -EINVAL;
	if (size > PAGE_SIZE)
		return -E2BIG;

	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
	if (ret)
		return ret;

	...
}

/* Mask out size */
#define SIZE_MASK(cmd)	(~IOCSIZE_MASK & cmd)

/* Mask out direction */
#define DIR_MASK(cmd)	(~IOCDIR_MASK & cmd)

static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
				 unsigned long arg)
{
	struct seccomp_filter *filter = file->private_data;
	void __user *buf = (void __user *)arg;

	/* Fixed size ioctls. Can be converted later on? */
	switch (cmd) {
	case SECCOMP_IOCTL_NOTIF_RECV:
		return seccomp_notify_recv(filter, buf);
	case SECCOMP_IOCTL_NOTIF_SEND:
		return seccomp_notify_send(filter, buf);
	case SECCOMP_IOCTL_NOTIF_ID_VALID:
		return seccomp_notify_id_valid(filter, buf);
	}

	/* Probably should make some nicer macros here */
	switch (SIZE_MASK(DIR_MASK(cmd))) {
	case SIZE_MASK(DIR_MASK(SECCOMP_IOCTL_NOTIF_ADDFD)):
		return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd));
	default:
		return -EINVAL;
	}
}

--------

What boxes does this tick?
* Forwards (and backwards) compatibility
* Applies to existing commands
* Command can be extended without requiring new ioctl to be defined
* It well accomodates the future where we want to have a kernel
  helper copy the structures from userspace

The fact that the size of the argument struct, and the ioctl are defined in the 
same header gives us the ability to "cheat", and for the argument size to be 
included / embedded for free in the command passed to ioctl. In turn, this
gives us two benefits. First, it means we don't have to copy from user twice,
and can just do it all in one shot since the size is passed with the syscall
arguments. Second, it means that the user does not have to do the following:

seccomp_notif_addfd addfd = {};
addfd.size = sizeof(struct seccomp_notif_addfd)

Because sizeof(struct seccomp_notif_addfd) is embedded in 
SECCOMP_IOCTL_NOTIF_ADDFD based on the same headers they plucked the struct out of.

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Fri, Jun 12, 2020 at 10:46:30AM +0000, Sargun Dhillon wrote:
> My suggest, written out (no idea if this code actually works), is as follows:
> 
> ioctl.h:
> /* This needs to be added */
> #define IOCDIR_MASK	(_IOC_DIRMASK << _IOC_DIRSHIFT)

This exists already:

#define _IOC_DIRMASK    ((1 << _IOC_DIRBITS)-1)

> 
> 
> seccomp.h:
> 
> struct struct seccomp_notif_addfd {
> 	__u64 fd;
> 	...
> }
> 
> /* or IOW? */
> #define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOWR(3, struct seccomp_notif_addfd)
> 
> seccomp.c:
> static long seccomp_notify_addfd(struct seccomp_filter *filter,
> 				 struct seccomp_notif_addfd __user *uaddfd int size)
> {
> 	struct seccomp_notif_addfd addfd;
> 	int ret;
> 
> 	if (size < 32)
> 		return -EINVAL;
> 	if (size > PAGE_SIZE)
> 		return -E2BIG;

(Tanget: what was the reason for copy_struct_from_user() not including
the min/max check? I have a memory of Al objecting to having an
"internal" limit?)

> 
> 	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> 	if (ret)
> 		return ret;
> 
> 	...
> }
> 
> /* Mask out size */
> #define SIZE_MASK(cmd)	(~IOCSIZE_MASK & cmd)
> 
> /* Mask out direction */
> #define DIR_MASK(cmd)	(~IOCDIR_MASK & cmd)
> 
> static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
> 				 unsigned long arg)
> {
> 	struct seccomp_filter *filter = file->private_data;
> 	void __user *buf = (void __user *)arg;
> 
> 	/* Fixed size ioctls. Can be converted later on? */
> 	switch (cmd) {
> 	case SECCOMP_IOCTL_NOTIF_RECV:
> 		return seccomp_notify_recv(filter, buf);
> 	case SECCOMP_IOCTL_NOTIF_SEND:
> 		return seccomp_notify_send(filter, buf);
> 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
> 		return seccomp_notify_id_valid(filter, buf);
> 	}
> 
> 	/* Probably should make some nicer macros here */
> 	switch (SIZE_MASK(DIR_MASK(cmd))) {
> 	case SIZE_MASK(DIR_MASK(SECCOMP_IOCTL_NOTIF_ADDFD)):

Ah yeah, I like this because of what you mention below: it's forward
compat too. (I'd just use the ioctl masks directly...)

	switch (cmd & ~(_IOC_SIZEMASK | _IOC_DIRMASK))

> 		return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd));

I really like that this ends up having the same construction as a
standard EA syscall: the size is part of the syscall arguments.

> 	default:
> 		return -EINVAL;
> 	}
> }
> 
> --------
> 
> What boxes does this tick?
> * Forwards (and backwards) compatibility
> * Applies to existing commands
> * Command can be extended without requiring new ioctl to be defined

(Technically, a new one is always redefined, but it's automatic in that
the kernel needs to do nothing.)

> * It well accomodates the future where we want to have a kernel
>   helper copy the structures from userspace

Yeah, this is a good solution.

> The fact that the size of the argument struct, and the ioctl are defined in the 
> same header gives us the ability to "cheat", and for the argument size to be 
> included / embedded for free in the command passed to ioctl. In turn, this
> gives us two benefits. First, it means we don't have to copy from user twice,
> and can just do it all in one shot since the size is passed with the syscall
> arguments. Second, it means that the user does not have to do the following:
> 
> seccomp_notif_addfd addfd = {};
> addfd.size = sizeof(struct seccomp_notif_addfd)
> 
> Because sizeof(struct seccomp_notif_addfd) is embedded in 
> SECCOMP_IOCTL_NOTIF_ADDFD based on the same headers they plucked the struct out of.

Cool. I will do more patch reworking! ;)

-- 
Kees Cook

RE: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[David Laight]

From: Kees Cook
> Sent: 12 June 2020 16:13
...
> > 	/* Fixed size ioctls. Can be converted later on? */
> > 	switch (cmd) {
> > 	case SECCOMP_IOCTL_NOTIF_RECV:
> > 		return seccomp_notify_recv(filter, buf);
> > 	case SECCOMP_IOCTL_NOTIF_SEND:
> > 		return seccomp_notify_send(filter, buf);
> > 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
> > 		return seccomp_notify_id_valid(filter, buf);
> > 	}
> >
> > 	/* Probably should make some nicer macros here */
> > 	switch (SIZE_MASK(DIR_MASK(cmd))) {
> > 	case SIZE_MASK(DIR_MASK(SECCOMP_IOCTL_NOTIF_ADDFD)):
> 
> Ah yeah, I like this because of what you mention below: it's forward
> compat too. (I'd just use the ioctl masks directly...)
> 
> 	switch (cmd & ~(_IOC_SIZEMASK | _IOC_DIRMASK))

Since you need the same mask on the case labels I think
I'd define a helper just across the switch statement:

#define M(cmd) ((cmd & ~(_IOC_SIZEMASK | _IOC_DIRMASK))
	switch (M(cmd)) {
	case M(SECCOMP_IOCTL_NOTIF_RECV):
	...
	}
#undef M

It is probably wrong to mask off DIRMASK.
But you might need to add extra case labels for
the broken one(s).

Prior to worries about indirect jumps you could
get a dense set of case label and faster code.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Fri, Jun 12, 2020 at 08:13:25AM -0700, Kees Cook wrote:
> On Fri, Jun 12, 2020 at 10:46:30AM +0000, Sargun Dhillon wrote:
> > My suggest, written out (no idea if this code actually works), is as follows:
> > 
> > ioctl.h:
> > /* This needs to be added */
> > #define IOCDIR_MASK	(_IOC_DIRMASK << _IOC_DIRSHIFT)
> 
> This exists already:
> 
> #define _IOC_DIRMASK    ((1 << _IOC_DIRBITS)-1)
> 
> > 
> > 
> > seccomp.h:
> > 
> > struct struct seccomp_notif_addfd {
> > 	__u64 fd;
> > 	...
> > }
> > 
> > /* or IOW? */
> > #define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOWR(3, struct seccomp_notif_addfd)
> > 
> > seccomp.c:
> > static long seccomp_notify_addfd(struct seccomp_filter *filter,
> > 				 struct seccomp_notif_addfd __user *uaddfd int size)
> > {
> > 	struct seccomp_notif_addfd addfd;
> > 	int ret;
> > 
> > 	if (size < 32)
> > 		return -EINVAL;
> > 	if (size > PAGE_SIZE)
> > 		return -E2BIG;
> 
> (Tanget: what was the reason for copy_struct_from_user() not including
> the min/max check? I have a memory of Al objecting to having an
> "internal" limit?)

Al didn't want the PAGE_SIZE limit in there because there's nothing
inherently wrong with copying insane amounts of memory.

(Another tangent. I've asked this on Twitter not too long ago: do we
have stats how long copy_from_user()/copy_struct_from_user() takes with
growing struct/memory size? I'd be really interested in this. I have a
feeling that clone3()'s and - having had a chat with David Howells -
openat2()'s structs will continue to grow for a while... and I'd really
like to have some numbers on when copy_struct_from_user() becomes
costly or how costly it becomes.)

> 
> > 
> > 	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
> > 	if (ret)
> > 		return ret;
> > 
> > 	...
> > }
> > 
> > /* Mask out size */
> > #define SIZE_MASK(cmd)	(~IOCSIZE_MASK & cmd)
> > 
> > /* Mask out direction */
> > #define DIR_MASK(cmd)	(~IOCDIR_MASK & cmd)
> > 
> > static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
> > 				 unsigned long arg)
> > {
> > 	struct seccomp_filter *filter = file->private_data;
> > 	void __user *buf = (void __user *)arg;
> > 
> > 	/* Fixed size ioctls. Can be converted later on? */
> > 	switch (cmd) {
> > 	case SECCOMP_IOCTL_NOTIF_RECV:
> > 		return seccomp_notify_recv(filter, buf);
> > 	case SECCOMP_IOCTL_NOTIF_SEND:
> > 		return seccomp_notify_send(filter, buf);
> > 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
> > 		return seccomp_notify_id_valid(filter, buf);
> > 	}
> > 
> > 	/* Probably should make some nicer macros here */
> > 	switch (SIZE_MASK(DIR_MASK(cmd))) {
> > 	case SIZE_MASK(DIR_MASK(SECCOMP_IOCTL_NOTIF_ADDFD)):
> 
> Ah yeah, I like this because of what you mention below: it's forward
> compat too. (I'd just use the ioctl masks directly...)
> 
> 	switch (cmd & ~(_IOC_SIZEMASK | _IOC_DIRMASK))
> 
> > 		return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd));
> 
> I really like that this ends up having the same construction as a
> standard EA syscall: the size is part of the syscall arguments.

This is basically what I had proposed in my previous mail, right?

Christian

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Kees Cook]

On Fri, Jun 12, 2020 at 08:28:16PM +0200, Christian Brauner wrote:
> Al didn't want the PAGE_SIZE limit in there because there's nothing
> inherently wrong with copying insane amounts of memory.

Right, ok.

> (Another tangent. I've asked this on Twitter not too long ago: do we
> have stats how long copy_from_user()/copy_struct_from_user() takes with
> growing struct/memory size? I'd be really interested in this. I have a
> feeling that clone3()'s and - having had a chat with David Howells -
> openat2()'s structs will continue to grow for a while... and I'd really
> like to have some numbers on when copy_struct_from_user() becomes
> costly or how costly it becomes.)

How long it takes? It should be basically the same, the costs should be
mostly in switching memory protections, etc. I wouldn't imagine how many
bytes being copied would matter much here, given the sub-page sizes.

> > Ah yeah, I like this because of what you mention below: it's forward
> > compat too. (I'd just use the ioctl masks directly...)
> > 
> > 	switch (cmd & ~(_IOC_SIZEMASK | _IOC_DIRMASK))
> > 
> > > 		return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd));
> > 
> > I really like that this ends up having the same construction as a
> > standard EA syscall: the size is part of the syscall arguments.
> 
> This is basically what I had proposed in my previous mail, right?

I guess I missed it! Well, then I think we're all in agreement? :)

-- 
Kees Cook

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Fri, Jun 12, 2020 at 11:38:33AM -0700, Kees Cook wrote:
> On Fri, Jun 12, 2020 at 08:28:16PM +0200, Christian Brauner wrote:
> > Al didn't want the PAGE_SIZE limit in there because there's nothing
> > inherently wrong with copying insane amounts of memory.
> 
> Right, ok.
> 
> > (Another tangent. I've asked this on Twitter not too long ago: do we
> > have stats how long copy_from_user()/copy_struct_from_user() takes with
> > growing struct/memory size? I'd be really interested in this. I have a
> > feeling that clone3()'s and - having had a chat with David Howells -
> > openat2()'s structs will continue to grow for a while... and I'd really
> > like to have some numbers on when copy_struct_from_user() becomes
> > costly or how costly it becomes.)
> 
> How long it takes? It should be basically the same, the costs should be
> mostly in switching memory protections, etc. I wouldn't imagine how many
> bytes being copied would matter much here, given the sub-page sizes.

This makes me _very_ happy.

Christian

RE: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[David Laight]

From: Christian Brauner
> Sent: 12 June 2020 19:28
...
> > > 	if (size < 32)
> > > 		return -EINVAL;
> > > 	if (size > PAGE_SIZE)
> > > 		return -E2BIG;
> >
> > (Tanget: what was the reason for copy_struct_from_user() not including
> > the min/max check? I have a memory of Al objecting to having an
> > "internal" limit?)
> 
> Al didn't want the PAGE_SIZE limit in there because there's nothing
> inherently wrong with copying insane amounts of memory.

The problem is really allowing a user process to allocate
unbounded blocks of memory, not the copy itself.

The limit for IOW() etc is 16k - not a problem.
If a 32bit size is set to just under 4GB so you really want
to allocate 4GB of memory then find the request is garbage.
Seems like a nice DoS attack.
A 64bit size can be worse.

Potentially the limit should be in memdup_user() itself.
And possibly an extra parameter giving a per-call lower? limit.

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Christian Brauner]

On Tue, Jun 09, 2020 at 11:27:30PM +0200, Christian Brauner wrote:
> On June 9, 2020 10:55:42 PM GMT+02:00, Kees Cook <keescook@chromium.org> wrote:
> >On Tue, Jun 09, 2020 at 10:03:46PM +0200, Christian Brauner wrote:
> >> I'm looking at __scm_install_fd() and I wonder what specifically you
> >> mean by that? The put_user() seems to be placed such that the install
> >> occurrs only if it succeeded. Sure, it only handles a single fd but
> >> whatever. Userspace knows that already. Just look at systemd when a
> >msg
> >> fails:
> >> 
> >> void cmsg_close_all(struct msghdr *mh) {
> >>         struct cmsghdr *cmsg;
> >> 
> >>         assert(mh);
> >> 
> >>         CMSG_FOREACH(cmsg, mh)
> >>                 if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type
> >== SCM_RIGHTS)
> >>                         close_many((int*) CMSG_DATA(cmsg),
> >(cmsg->cmsg_len - CMSG_LEN(0)) / sizeof(int));
> >> }
> >> 
> >> The only reasonable scenario for this whole mess I can think of is sm
> >like (pseudo code):
> >> 
> >> fd_install_received(int fd, struct file *file)
> >> {
> >>  	sock = sock_from_file(fd, &err);
> >>  	if (sock) {
> >>  		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
> >>  		sock_update_classid(&sock->sk->sk_cgrp_data);
> >>  	}
> >> 
> >> 	fd_install();
> >> }
> >> 
> >> error = 0;
> >> fdarray = malloc(fdmax);
> >> for (i = 0; i < fdmax; i++) {
> >> 	fdarray[i] = get_unused_fd_flags(o_flags);
> >> 	if (fdarray[i] < 0) {
> >> 		error = -EBADF;
> >> 		break;
> >> 	}
> >> 
> >> 	error = security_file_receive(file);
> >> 	if (error)
> >> 		break;
> >> 
> >> 	error = put_user(fd_array[i], ufd);
> >> 	if (error)
> >> 		break;
> >> }
> >> 
> >> for (i = 0; i < fdmax; i++) {
> >> 	if (error) {
> >> 		/* ignore errors */
> >> 		put_user(-EBADF, ufd); /* If this put_user() fails and the first
> >one succeeded userspace might now close an fd it didn't intend to. */
> >> 		put_unused_fd(fdarray[i]);
> >> 	} else {
> >> 		fd_install_received(fdarray[i], file);
> >> 	}
> >> }
> >
> >I see 4 cases of the same code pattern (get_unused_fd_flags(),
> >sock_update_*(), fd_install()), one of them has this difficult
> >put_user()
> >in the middle, and one of them has a potential replace_fd() instead of
> >the get_used/fd_install. So, to me, it makes sense to have a helper
> >that
> >encapsulates the common work that each of those call sites has to do,
> >which I keep cringing at all these suggestions that leave portions of
> >it
> >outside the helper.
> >
> >If it's too ugly to keep the put_user() in the helper, then we can try
> >what was suggested earlier, and just totally rework the failure path
> >for
> >SCM_RIGHTS.
> >
> >LOL. And while we were debating this, hch just went and cleaned stuff
> >up:
> >
> >2618d530dd8b ("net/scm: cleanup scm_detach_fds")
> >
> >So, um, yeah, now my proposal is actually even closer to what we
> >already
> >have there. We just add the replace_fd() logic to __scm_install_fd()
> >and
> >we're done with it.
> 
> Cool, you have a link? :)

For the record, as I didn't see this yesterday since I was already
looking at a kernel with Christoph's changes. His changes just move the
logic that was already there before into a separate helper.

So effectively nothing has changed semantically in the scm code at all.

This is why I was asking yesterday what you meant by reworking the scm
code's put_user() logic as it seems obviously correct as it is done now.

Christian

Re: [PATCH v3 1/4] fs, net: Standardize on file_receive helper to move fds across processes

[Sargun Dhillon]

On Thu, Jun 04, 2020 at 03:24:52AM +0200, Christian Brauner wrote:
> On Tue, Jun 02, 2020 at 06:10:41PM -0700, Sargun Dhillon wrote:
> > Previously there were two chunks of code where the logic to receive file
> > descriptors was duplicated in net. The compat version of copying
> > file descriptors via SCM_RIGHTS did not have logic to update cgroups.
> > Logic to change the cgroup data was added in:
> > commit 48a87cc26c13 ("net: netprio: fd passed in SCM_RIGHTS datagram not set correctly")
> > commit d84295067fc7 ("net: net_cls: fd passed in SCM_RIGHTS datagram not set correctly")
> > 
> > This was not copied to the compat path. This commit fixes that, and thus
> > should be cherry-picked into stable.
> > 
> > This introduces a helper (file_receive) which encapsulates the logic for
> > handling calling security hooks as well as manipulating cgroup information.
> > This helper can then be used other places in the kernel where file
> > descriptors are copied between processes
> > 
> > I tested cgroup classid setting on both the compat (x32) path, and the
> > native path to ensure that when moving the file descriptor the classid
> > is set.
> > 
> > Signed-off-by: Sargun Dhillon <sargun@sargun.me>
> > Suggested-by: Kees Cook <keescook@chromium.org>
> > Cc: Al Viro <viro@zeniv.linux.org.uk>
> > Cc: Christian Brauner <christian.brauner@ubuntu.com>
> > Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
> > Cc: David S. Miller <davem@davemloft.net>
> > Cc: Jann Horn <jannh@google.com>,
> > Cc: John Fastabend <john.r.fastabend@intel.com>
> > Cc: Tejun Heo <tj@kernel.org>
> > Cc: Tycho Andersen <tycho@tycho.ws>
> > Cc: stable@vger.kernel.org
> > Cc: cgroups@vger.kernel.org
> > Cc: linux-fsdevel@vger.kernel.org
> > Cc: linux-kernel@vger.kernel.org
> > ---
> >  fs/file.c            | 35 +++++++++++++++++++++++++++++++++++
> >  include/linux/file.h |  1 +
> >  net/compat.c         | 10 +++++-----
> >  net/core/scm.c       | 14 ++++----------
> >  4 files changed, 45 insertions(+), 15 deletions(-)
> > 
> > diff --git a/fs/file.c b/fs/file.c
> > index abb8b7081d7a..5afd76fca8c2 100644
> > --- a/fs/file.c
> > +++ b/fs/file.c
> > @@ -18,6 +18,9 @@
> >  #include <linux/bitops.h>
> >  #include <linux/spinlock.h>
> >  #include <linux/rcupdate.h>
> > +#include <net/sock.h>
> > +#include <net/netprio_cgroup.h>
> > +#include <net/cls_cgroup.h>
> >  
> >  unsigned int sysctl_nr_open __read_mostly = 1024*1024;
> >  unsigned int sysctl_nr_open_min = BITS_PER_LONG;
> > @@ -931,6 +934,38 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
> >  	return err;
> >  }
> >  
> > +/*
> > + * File Receive - Receive a file from another process
> > + *
> > + * This function is designed to receive files from other tasks. It encapsulates
> > + * logic around security and cgroups. The file descriptor provided must be a
> > + * freshly allocated (unused) file descriptor.
> > + *
> > + * This helper does not consume a reference to the file, so the caller must put
> > + * their reference.
> > + *
> > + * Returns 0 upon success.
> > + */
> > +int file_receive(int fd, struct file *file)
> 
> This is all just a remote version of fd_install(), yet it deviates from
> fd_install()'s semantics and naming. That's not great imho. What about
> naming this something like:
> 
> fd_install_received()
> 
> and move the get_file() out of there so it has the same semantics as
> fd_install(). It seems rather dangerous to have a function like
> fd_install() that consumes a reference once it returned and another
> version of this that is basically the same thing but doesn't consume a
> reference because it takes its own. Seems an invitation for confusion.
> Does that make sense?
> 
You're right. The reason for the difference in my mind is that fd_install
always succeeds, whereas file_receive can fail. It's easier to do something
like:
fd_install(fd, get_file(f))
vs.
if (file_receive(fd, get_file(f))
	fput(f);

Alternatively, if the reference was always consumed, it is somewhat
easier.

I'm fine either way, but just explaining my reasoning for the difference
in behaviour.

[PATCH v3 2/4] pid: Use file_receive helper to copy FDs

[Sargun Dhillon]

The code to copy file descriptors was duplicated in pidfd_getfd.
Rather than continue to duplicate it, this hoists the code out of
kernel/pid.c and uses the newly added file_receive helper.

Earlier, when this was implemented there was some back-and-forth
about how the semantics should work around copying around file
descriptors [1], and it was decided that the default behaviour
should be to not modify cgroup data. As a matter of least surprise,
this approach follows the default semantics as presented by SCM_RIGHTS.

In the future, a flag can be added to avoid manipulating the cgroup
data on copy.

[1]: https://lore.kernel.org/lkml/20200107175927.4558-1-sargun@sargun.me/

Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Suggested-by: Kees Cook <keescook@chromium.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jann Horn <jannh@google.com>
Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Tycho Andersen <tycho@tycho.ws>
Cc: stable@vger.kernel.org
Cc: cgroups@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 kernel/pid.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/kernel/pid.c b/kernel/pid.c
index c835b844aca7..1642cf940aa1 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -606,7 +606,7 @@ static int pidfd_getfd(struct pid *pid, int fd)
 {
 	struct task_struct *task;
 	struct file *file;
-	int ret;
+	int ret, err;
 
 	task = get_pid_task(pid, PIDTYPE_PID);
 	if (!task)
@@ -617,18 +617,16 @@ static int pidfd_getfd(struct pid *pid, int fd)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = security_file_receive(file);
-	if (ret) {
-		fput(file);
-		return ret;
-	}
-
 	ret = get_unused_fd_flags(O_CLOEXEC);
-	if (ret < 0)
-		fput(file);
-	else
-		fd_install(ret, file);
+	if (ret >= 0) {
+		err = file_receive(ret, file);
+		if (err) {
+			put_unused_fd(ret);
+			ret = err;
+		}
+	}
 
+	fput(file);
 	return ret;
 }
 
-- 
2.25.1

[PATCH v3 3/4] seccomp: Introduce addfd ioctl to seccomp user notifier

[Sargun Dhillon]

This adds a seccomp notifier ioctl which allows for the listener to "add"
file descriptors to a process which originated a seccomp user
notification. This allows calls like mount, and mknod to be "implemented",
as the return value, and the arguments are data in memory. On the other
hand, calls like connect can be "implemented" using pidfd_getfd.

Unfortunately, there are calls which return file descriptors, like
open, which are vulnerable to TOC-TOU attacks, and require that the
more privileged supervisor can inspect the argument, and perform the
syscall on behalf of the process generating the notification. This
allows the file descriptor generated from that open call to be
returned to the calling process.

In addition, there is funcitonality to allow for replacement of
specific file descriptors, following dup2-like semantics.

This extends a previously added helper (file_receive), and introduces
a new helper built on top of it -- file_receive_replace, which is
meant to assist with calling replace_fd, with files received from
remote processes.

As a note, the seccomp_notif_addfd structure is laid out based on 8-byte
alignment without requiring packing as there have been packing issues with
uapi highlighted before [1][2]. Although we could overload the newfd field
and use -1 to indicate that it is not to be used, doing so requires
changing the size of the fd field, and introduces struct packing
complexity.

[1]: https://lore.kernel.org/lkml/87o8w9bcaf.fsf@mid.deneb.enyo.de/
[2]: https://lore.kernel.org/lkml/a328b91d-fd8f-4f27-b3c2-91a9c45f18c0@rasmusvillemoes.dk/

Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Suggested-by: Matt Denton <mpdenton@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Chris Palmer <palmer@google.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Robert Sesek <rsesek@google.com>
Cc: Tycho Andersen <tycho@tycho.ws>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-api@vger.kernel.org
---
 fs/file.c                    |  29 +++++-
 include/linux/file.h         |   1 +
 include/uapi/linux/seccomp.h |  25 +++++
 kernel/seccomp.c             | 184 ++++++++++++++++++++++++++++++++++-
 4 files changed, 234 insertions(+), 5 deletions(-)

diff --git a/fs/file.c b/fs/file.c
index 5afd76fca8c2..eb413c1fdb7f 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -938,15 +938,19 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
  * File Receive - Receive a file from another process
  *
  * This function is designed to receive files from other tasks. It encapsulates
- * logic around security and cgroups. The file descriptor provided must be a
- * freshly allocated (unused) file descriptor.
+ * logic around security and cgroups. It can either replace an existing file
+ * descriptor, or install the file at a new unused one. If the file is meant
+ * to be installed on a new file descriptor, it must be allocated with the
+ * right flags by the user and the flags passed must be 0 -- as anything else
+ * is ignored.
  *
  * This helper does not consume a reference to the file, so the caller must put
  * their reference.
  *
  * Returns 0 upon success.
  */
-int file_receive(int fd, struct file *file)
+static int __file_receive(int fd, unsigned int flags, struct file *file,
+			  bool replace)
 {
 	struct socket *sock;
 	int err;
@@ -955,7 +959,14 @@ int file_receive(int fd, struct file *file)
 	if (err)
 		return err;
 
-	fd_install(fd, get_file(file));
+	if (replace) {
+		err = replace_fd(fd, file, flags);
+		if (err)
+			return err;
+	} else {
+		WARN_ON(flags);
+		fd_install(fd, get_file(file));
+	}
 
 	sock = sock_from_file(file, &err);
 	if (sock) {
@@ -966,6 +977,16 @@ int file_receive(int fd, struct file *file)
 	return 0;
 }
 
+int file_receive_replace(int fd, unsigned int flags, struct file *file)
+{
+	return __file_receive(fd, flags, file, true);
+}
+
+int file_receive(int fd, struct file *file)
+{
+	return __file_receive(fd, 0, file, false);
+}
+
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
 	int err = -EBADF;
diff --git a/include/linux/file.h b/include/linux/file.h
index 7b56dc23e560..e4ca058fb559 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -94,5 +94,6 @@ extern void fd_install(unsigned int fd, struct file *file);
 extern void flush_delayed_fput(void);
 extern void __fput_sync(struct file *);
 
+extern int file_receive_replace(int fd, unsigned int flags, struct file *file);
 extern int file_receive(int fd, struct file *file);
 #endif /* __LINUX_FILE_H */
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index c1735455bc53..aec3e43c4418 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -113,6 +113,27 @@ struct seccomp_notif_resp {
 	__u32 flags;
 };
 
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD	(1UL << 0) /* Specify remote fd */
+
+/**
+ * struct seccomp_notif_addfd
+ * @size: The size of the seccomp_notif_addfd datastructure
+ * @id: The ID of the seccomp notification
+ * @flags: SECCOMP_ADDFD_FLAG_*
+ * @srcfd: The local fd number
+ * @newfd: Optional remote FD number if SETFD option is set, otherwise 0.
+ * @newfd_flags: Flags the remote FD should be allocated under
+ */
+struct seccomp_notif_addfd {
+	__u64 size;
+	__u64 id;
+	__u32 flags;
+	__u32 srcfd;
+	__u32 newfd;
+	__u32 newfd_flags;
+};
+
 #define SECCOMP_IOC_MAGIC		'!'
 #define SECCOMP_IO(nr)			_IO(SECCOMP_IOC_MAGIC, nr)
 #define SECCOMP_IOR(nr, type)		_IOR(SECCOMP_IOC_MAGIC, nr, type)
@@ -124,4 +145,8 @@ struct seccomp_notif_resp {
 #define SECCOMP_IOCTL_NOTIF_SEND	SECCOMP_IOWR(1,	\
 						struct seccomp_notif_resp)
 #define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
+/* On success, the return value is the remote process's added fd number */
+#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
+						struct seccomp_notif_addfd)
+
 #endif /* _UAPI_LINUX_SECCOMP_H */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 34dbf77569b3..c39e901e8af5 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -78,10 +78,42 @@ struct seccomp_knotif {
 	long val;
 	u32 flags;
 
-	/* Signals when this has entered SECCOMP_NOTIFY_REPLIED */
+	/*
+	 * Signals when this has changed states, such as the listener
+	 * dying, a new seccomp addfd message, or changing to REPLIED
+	 */
 	struct completion ready;
 
 	struct list_head list;
+
+	/* outstanding addfd requests */
+	struct list_head addfd;
+};
+
+/**
+ * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages
+ *
+ * @file: A reference to the file to install in the other task
+ * @fd: The fd number to install it at. If the fd number is -1, it means the
+ *      installing process should allocate the fd as normal.
+ * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
+ *         is allowed.
+ * @ret: The return value of the installing process. It is set to the fd num
+ *       upon success (>= 0).
+ * @completion: Indicates that the installing process has completed fd
+ *              installation, or gone away (either due to successful
+ *              reply, or signal)
+ *
+ */
+struct seccomp_kaddfd {
+	struct file *file;
+	int fd;
+	unsigned int flags;
+
+	/* To only be set on reply */
+	int ret;
+	struct completion completion;
+	struct list_head list;
 };
 
 /**
@@ -784,6 +816,36 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
 	return filter->notif->next_id++;
 }
 
+static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd)
+{
+	int ret, err;
+
+	/*
+	 * Remove the notification, and reset the list pointers, indicating
+	 * that it has been handled.
+	 */
+	list_del_init(&addfd->list);
+
+	if (addfd->fd == -1) {
+		ret = get_unused_fd_flags(addfd->flags);
+		if (ret < 0)
+			goto err;
+
+		err = file_receive(ret, addfd->file);
+		if (err) {
+			put_unused_fd(ret);
+			ret = err;
+		}
+	} else {
+		ret = file_receive_replace(addfd->fd, addfd->flags,
+					   addfd->file);
+	}
+
+err:
+	addfd->ret = ret;
+	complete(&addfd->completion);
+}
+
 static int seccomp_do_user_notification(int this_syscall,
 					struct seccomp_filter *match,
 					const struct seccomp_data *sd)
@@ -792,6 +854,7 @@ static int seccomp_do_user_notification(int this_syscall,
 	u32 flags = 0;
 	long ret = 0;
 	struct seccomp_knotif n = {};
+	struct seccomp_kaddfd *addfd, *tmp;
 
 	mutex_lock(&match->notify_lock);
 	err = -ENOSYS;
@@ -804,6 +867,7 @@ static int seccomp_do_user_notification(int this_syscall,
 	n.id = seccomp_next_notify_id(match);
 	init_completion(&n.ready);
 	list_add(&n.list, &match->notif->notifications);
+	INIT_LIST_HEAD(&n.addfd);
 
 	up(&match->notif->request);
 	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
@@ -812,14 +876,31 @@ static int seccomp_do_user_notification(int this_syscall,
 	/*
 	 * This is where we wait for a reply from userspace.
 	 */
+wait:
 	err = wait_for_completion_interruptible(&n.ready);
 	mutex_lock(&match->notify_lock);
 	if (err == 0) {
+		/* Check if we were woken up by a addfd message */
+		addfd = list_first_entry_or_null(&n.addfd,
+						 struct seccomp_kaddfd, list);
+		if (addfd && n.state != SECCOMP_NOTIFY_REPLIED) {
+			seccomp_handle_addfd(addfd);
+			mutex_unlock(&match->notify_lock);
+			goto wait;
+		}
 		ret = n.val;
 		err = n.error;
 		flags = n.flags;
 	}
 
+	/* If there were any pending addfd calls, clear them out */
+	list_for_each_entry_safe(addfd, tmp, &n.addfd, list) {
+		/* The process went away before we got a chance to handle it */
+		addfd->ret = -ESRCH;
+		list_del_init(&addfd->list);
+		complete(&addfd->completion);
+	}
+
 	/*
 	 * Note that it's possible the listener died in between the time when
 	 * we were notified of a respons (or a signal) and when we were able to
@@ -1060,6 +1141,11 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
 		knotif->error = -ENOSYS;
 		knotif->val = 0;
 
+		/*
+		 * We do not need to wake up any pending addfd messages, as
+		 * the notifier will do that for us, as this just looks
+		 * like a standard reply.
+		 */
 		complete(&knotif->ready);
 	}
 
@@ -1224,6 +1310,100 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
 	return ret;
 }
 
+static long seccomp_notify_addfd(struct seccomp_filter *filter,
+				 struct seccomp_notif_addfd __user *uaddfd)
+{
+	struct seccomp_notif_addfd addfd;
+	struct seccomp_knotif *knotif;
+	struct seccomp_kaddfd kaddfd;
+	u64 size;
+	int ret;
+
+	ret = get_user(size, &uaddfd->size);
+	if (ret)
+		return ret;
+
+	ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
+	if (ret)
+		return ret;
+
+	if (addfd.newfd_flags & ~O_CLOEXEC)
+		return -EINVAL;
+
+	if (addfd.flags & ~SECCOMP_ADDFD_FLAG_SETFD)
+		return -EINVAL;
+
+	if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD))
+		return -EINVAL;
+
+	kaddfd.file = fget(addfd.srcfd);
+	if (!kaddfd.file)
+		return -EBADF;
+
+	kaddfd.flags = addfd.newfd_flags;
+	kaddfd.fd = (addfd.flags & SECCOMP_ADDFD_FLAG_SETFD) ?
+		    addfd.newfd : -1;
+	init_completion(&kaddfd.completion);
+
+	ret = mutex_lock_interruptible(&filter->notify_lock);
+	if (ret < 0)
+		goto out;
+
+	knotif = find_notification(filter, addfd.id);
+	if (!knotif) {
+		ret = -ENOENT;
+		goto out_unlock;
+	}
+
+	/*
+	 * We do not want to allow for FD injection to occur before the
+	 * notification has been picked up by a userspace handler, or after
+	 * the notification has been replied to.
+	 */
+	if (knotif->state != SECCOMP_NOTIFY_SENT) {
+		ret = -EINPROGRESS;
+		goto out_unlock;
+	}
+
+	list_add(&kaddfd.list, &knotif->addfd);
+	complete(&knotif->ready);
+	mutex_unlock(&filter->notify_lock);
+
+	/* Now we wait for it to be processed or be interrupted */
+	ret = wait_for_completion_interruptible(&kaddfd.completion);
+	if (ret == 0) {
+		/*
+		 * We had a successful completion. The other side has already
+		 * removed us from the addfd queue, and
+		 * wait_for_completion_interruptible has a memory barrier upon
+		 * success that lets us read this value directly without
+		 * locking.
+		 */
+		ret = kaddfd.ret;
+		goto out;
+	}
+
+	mutex_lock(&filter->notify_lock);
+	/*
+	 * Even though we were woken up by a signal and not a successful
+	 * completion, a completion may have happened in the mean time.
+	 *
+	 * We need to check again if the addfd request has been handled,
+	 * and if not, we will remove it from the queue.
+	 */
+	if (list_empty(&kaddfd.list))
+		ret = kaddfd.ret;
+	else
+		list_del(&kaddfd.list);
+
+out_unlock:
+	mutex_unlock(&filter->notify_lock);
+out:
+	fput(kaddfd.file);
+
+	return ret;
+}
+
 static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
 				 unsigned long arg)
 {
@@ -1237,6 +1417,8 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
 		return seccomp_notify_send(filter, buf);
 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
 		return seccomp_notify_id_valid(filter, buf);
+	case SECCOMP_IOCTL_NOTIF_ADDFD:
+		return seccomp_notify_addfd(filter, buf);
 	default:
 		return -EINVAL;
 	}
-- 
2.25.1

[PATCH v3 4/4] selftests/seccomp: Test SECCOMP_IOCTL_NOTIF_ADDFD

[Sargun Dhillon]

Test whether we can add file descriptors in response to notifications.
This injects the file descriptors via notifications, and then uses
kcmp to determine whether or not it has been successful.

It also includes some basic sanity checking for arguments.

Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Chris Palmer <palmer@google.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Robert Sesek <rsesek@google.com>
Cc: Tycho Andersen <tycho@tycho.ws>
Cc: Matt Denton <mpdenton@google.com>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 tools/testing/selftests/seccomp/seccomp_bpf.c | 183 ++++++++++++++++++
 1 file changed, 183 insertions(+)

diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 402ccb3a4e52..a786b1734ddd 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -45,6 +45,7 @@
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <linux/kcmp.h>
+#include <sys/resource.h>
 
 #include <unistd.h>
 #include <sys/syscall.h>
@@ -182,6 +183,12 @@ struct seccomp_metadata {
 #define SECCOMP_IOCTL_NOTIF_SEND	SECCOMP_IOWR(1,	\
 						struct seccomp_notif_resp)
 #define SECCOMP_IOCTL_NOTIF_ID_VALID	SECCOMP_IOR(2, __u64)
+/* On success, the return value is the remote process's added fd number */
+#define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOR(3,	\
+						struct seccomp_notif_addfd)
+
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD	(1UL << 0) /* Specify remote fd */
 
 struct seccomp_notif {
 	__u64 id;
@@ -202,6 +209,15 @@ struct seccomp_notif_sizes {
 	__u16 seccomp_notif_resp;
 	__u16 seccomp_data;
 };
+
+struct seccomp_notif_addfd {
+	__u64 size;
+	__u64 id;
+	__u32 flags;
+	__u32 srcfd;
+	__u32 newfd;
+	__u32 newfd_flags;
+};
 #endif
 
 #ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY
@@ -3822,6 +3838,173 @@ TEST(user_notification_filter_empty_threaded)
 	EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0);
 }
 
+TEST(user_notification_sendfd)
+{
+	pid_t pid;
+	long ret;
+	int status, listener, memfd;
+	struct seccomp_notif_addfd addfd = {};
+	struct seccomp_notif req = {};
+	struct seccomp_notif_resp resp = {};
+	/* 100 ms */
+	struct timespec delay = { .tv_nsec = 100000000 };
+
+	memfd = memfd_create("test", 0);
+	ASSERT_GE(memfd, 0);
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	/* Check that the basic notification machinery works */
+	listener = user_trap_syscall(__NR_getppid,
+				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	ASSERT_GE(listener, 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		if (syscall(__NR_getppid) != USER_NOTIF_MAGIC)
+			exit(1);
+		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
+	}
+
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+
+	addfd.size = sizeof(addfd);
+	addfd.srcfd = memfd;
+	addfd.newfd_flags = O_CLOEXEC;
+	addfd.newfd = 0;
+	addfd.id = req.id;
+	addfd.flags = 0xff;
+
+	/* Verify bad flags cannot be set */
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* Verify that remote_fd cannot be set without setting flags */
+	addfd.flags = 0;
+	addfd.newfd = 1;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* Verify we can set an arbitrary remote fd */
+	addfd.newfd = 0;
+
+	ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd);
+	EXPECT_GE(ret, 0);
+	EXPECT_EQ(filecmp(getpid(), pid, memfd, ret), 0);
+
+	/* Verify we can set a specific remote fd */
+	addfd.newfd = 42;
+	addfd.flags = SECCOMP_ADDFD_FLAG_SETFD;
+
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), 42);
+	EXPECT_EQ(filecmp(getpid(), pid, memfd, 42), 0);
+
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+	/*
+	 * This sets the ID of the ADD FD to the last request plus 1. The
+	 * notification ID increments 1 per notification.
+	 */
+	addfd.id = req.id + 1;
+
+	/* This spins until the underlying notification is generated */
+	while (ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd) != -1 &&
+	       errno != -EINPROGRESS)
+		nanosleep(&delay, NULL);
+
+	memset(&req, 0, sizeof(req));
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+	ASSERT_EQ(addfd.id, req.id);
+
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+
+	close(memfd);
+}
+
+TEST(user_notification_sendfd_rlimit)
+{
+	pid_t pid;
+	long ret;
+	int status, listener, memfd;
+	struct seccomp_notif_addfd addfd = {};
+	struct seccomp_notif req = {};
+	struct seccomp_notif_resp resp = {};
+	const struct rlimit lim = {
+		.rlim_cur	= 0,
+		.rlim_max	= 0,
+	};
+
+	memfd = memfd_create("test", 0);
+	ASSERT_GE(memfd, 0);
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	/* Check that the basic notification machinery works */
+	listener = user_trap_syscall(__NR_getppid,
+				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	ASSERT_GE(listener, 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0)
+		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
+
+
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+
+	ASSERT_EQ(prlimit(pid, RLIMIT_NOFILE, &lim, NULL), 0);
+
+	addfd.size = sizeof(addfd);
+	addfd.srcfd = memfd;
+	addfd.newfd_flags = O_CLOEXEC;
+	addfd.newfd = 0;
+	addfd.id = req.id;
+	addfd.flags = 0;
+
+	/* Should probably spot check /proc/sys/fs/file-nr */
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EMFILE);
+
+	addfd.newfd = 100;
+	addfd.flags = SECCOMP_ADDFD_FLAG_SETFD;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EBADF);
+
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+
+	close(memfd);
+}
+
 /*
  * TODO:
  * - expand NNP testing
-- 
2.25.1