On Mon, Apr 17, 2023 at 5:18 PM Christian Brauner <brauner@xxxxxxxxxx> wrote: > > On Thu, Apr 13, 2023 at 03:33:52PM +0200, Alexander Mikhalitsyn wrote: > > Implement SCM_PIDFD, a new type of CMSG type analogical to SCM_CREDENTIALS, > > but it contains pidfd instead of plain pid, which allows programmers not > > to care about PID reuse problem. > > > > Idea comes from UAPI kernel group: > > https://uapi-group.org/kernel-features/ > > > > Big thanks to Christian Brauner and Lennart Poettering for productive > > discussions about this. > > > > Cc: "David S. Miller" <davem@xxxxxxxxxxxxx> > > Cc: Eric Dumazet <edumazet@xxxxxxxxxx> > > Cc: Jakub Kicinski <kuba@xxxxxxxxxx> > > Cc: Paolo Abeni <pabeni@xxxxxxxxxx> > > Cc: Leon Romanovsky <leon@xxxxxxxxxx> > > Cc: David Ahern <dsahern@xxxxxxxxxx> > > Cc: Arnd Bergmann <arnd@xxxxxxxx> > > Cc: Kees Cook <keescook@xxxxxxxxxxxx> > > Cc: Christian Brauner <brauner@xxxxxxxxxx> > > Cc: Kuniyuki Iwashima <kuniyu@xxxxxxxxxx> > > Cc: Lennart Poettering <mzxreary@xxxxxxxxxxx> > > Cc: Luca Boccassi <bluca@xxxxxxxxxx> > > Cc: linux-kernel@xxxxxxxxxxxxxxx > > Cc: netdev@xxxxxxxxxxxxxxx > > Cc: linux-arch@xxxxxxxxxxxxxxx > > Tested-by: Luca Boccassi <bluca@xxxxxxxxxx> > > Reviewed-by: Kuniyuki Iwashima <kuniyu@xxxxxxxxxx> > > Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@xxxxxxxxxxxxx> > > --- > > v4: > > - fixed silent fd_install if writting of CMSG to the userspace fails (pointed by Christian) > > v2: > > According to review comments from Kuniyuki Iwashima and Christian Brauner: > > - use pidfd_create(..) retval as a result > > - whitespace change > > --- > > arch/alpha/include/uapi/asm/socket.h | 2 ++ > > arch/mips/include/uapi/asm/socket.h | 2 ++ > > arch/parisc/include/uapi/asm/socket.h | 2 ++ > > arch/sparc/include/uapi/asm/socket.h | 2 ++ > > include/linux/net.h | 1 + > > include/linux/socket.h | 1 + > > include/net/scm.h | 39 +++++++++++++++++++++++-- > > include/uapi/asm-generic/socket.h | 2 ++ > > net/core/sock.c | 11 +++++++ > > net/mptcp/sockopt.c | 1 + > > net/unix/af_unix.c | 18 ++++++++---- > > tools/include/uapi/asm-generic/socket.h | 2 ++ > > 12 files changed, 76 insertions(+), 7 deletions(-) > > > > diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h > > index 739891b94136..ff310613ae64 100644 > > --- a/arch/alpha/include/uapi/asm/socket.h > > +++ b/arch/alpha/include/uapi/asm/socket.h > > @@ -137,6 +137,8 @@ > > > > #define SO_RCVMARK 75 > > > > +#define SO_PASSPIDFD 76 > > + > > #if !defined(__KERNEL__) > > > > #if __BITS_PER_LONG == 64 > > diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h > > index 18f3d95ecfec..762dcb80e4ec 100644 > > --- a/arch/mips/include/uapi/asm/socket.h > > +++ b/arch/mips/include/uapi/asm/socket.h > > @@ -148,6 +148,8 @@ > > > > #define SO_RCVMARK 75 > > > > +#define SO_PASSPIDFD 76 > > + > > #if !defined(__KERNEL__) > > > > #if __BITS_PER_LONG == 64 > > diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h > > index f486d3dfb6bb..df16a3e16d64 100644 > > --- a/arch/parisc/include/uapi/asm/socket.h > > +++ b/arch/parisc/include/uapi/asm/socket.h > > @@ -129,6 +129,8 @@ > > > > #define SO_RCVMARK 0x4049 > > > > +#define SO_PASSPIDFD 0x404A > > + > > #if !defined(__KERNEL__) > > > > #if __BITS_PER_LONG == 64 > > diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h > > index 2fda57a3ea86..6e2847804fea 100644 > > --- a/arch/sparc/include/uapi/asm/socket.h > > +++ b/arch/sparc/include/uapi/asm/socket.h > > @@ -130,6 +130,8 @@ > > > > #define SO_RCVMARK 0x0054 > > > > +#define SO_PASSPIDFD 0x0055 > > + > > #if !defined(__KERNEL__) > > > > > > diff --git a/include/linux/net.h b/include/linux/net.h > > index b73ad8e3c212..c234dfbe7a30 100644 > > --- a/include/linux/net.h > > +++ b/include/linux/net.h > > @@ -43,6 +43,7 @@ struct net; > > #define SOCK_PASSSEC 4 > > #define SOCK_SUPPORT_ZC 5 > > #define SOCK_CUSTOM_SOCKOPT 6 > > +#define SOCK_PASSPIDFD 7 > > > > #ifndef ARCH_HAS_SOCKET_TYPES > > /** > > diff --git a/include/linux/socket.h b/include/linux/socket.h > > index 13c3a237b9c9..6bf90f251910 100644 > > --- a/include/linux/socket.h > > +++ b/include/linux/socket.h > > @@ -177,6 +177,7 @@ static inline size_t msg_data_left(struct msghdr *msg) > > #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ > > #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ > > #define SCM_SECURITY 0x03 /* rw: security label */ > > +#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ > > > > struct ucred { > > __u32 pid; > > diff --git a/include/net/scm.h b/include/net/scm.h > > index 585adc1346bd..c67f765a165b 100644 > > --- a/include/net/scm.h > > +++ b/include/net/scm.h > > @@ -120,12 +120,44 @@ static inline bool scm_has_secdata(struct socket *sock) > > } > > #endif /* CONFIG_SECURITY_NETWORK */ > > > > +static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm) > > +{ > > + struct file *pidfd_file = NULL; > > + int pidfd; > > + > > + /* > > + * put_cmsg() doesn't return an error if CMSG is truncated, > > + * that's why we need to opencode these checks here. > > + */ > > + if ((msg->msg_controllen <= sizeof(struct cmsghdr)) || > > + (msg->msg_controllen - sizeof(struct cmsghdr)) < sizeof(int)) { > > + msg->msg_flags |= MSG_CTRUNC; > > + return; > > Hm, curious about this: We mark the message as truncated for SCM_PIDFD > but if the same conditions were to apply for SCM_PASSCRED we don't mark > the message as truncated. Am I reading this correct? And is so, you > please briefly explain this difference? Hi, Christian! For SCM_CREDENTIALS we mark it too. Inside the put_cmsg function: https://github.com/torvalds/linux/blob/6a8f57ae2eb07ab39a6f0ccad60c760743051026/net/core/scm.c#L225 The reason why I'm open-coding these checks is that I want to know that the message doesn't fit into the userspace buffer before doing pidfd_prepare and other stuff and because put_cmsg is not returning an error when message doesn't fit in the userspace buffer and we won't be able to properly do pidfd cleanup (put struct pid and fd index). > > > + } > > + > > + WARN_ON_ONCE(!scm->pid); > > + pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); > > + > > + if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { > > If the put_cmsg() of the pidfd fails userspace needs to be able to > detect this. Otherwise they can't distinguish between the SCM_PIDFD > value being zero because the put_cmsg() failed or put_cmsg() succeeded > and the allocated fd nr was 0. If pidfd_prepare fails then userspace will receive SCM_PIDFD message with negative pidfd value. > > Looking at put_cmsg() it looks to me that userspace will receive a > SCM_PIDFD message only if the put_cmsg() is completely successful. IIUC, > then this change is fine. Kind regards, Alex
