Merge tag 'vfs-7.4-rc1.shared.net-next.pidfd' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull pidfd updates from Christian Brauner:
 "This adds thread specific pidfds to af_unix sockets.

  SO_PASSPIDFD and SO_PEERPIDFD hand out a pidfd for the thread-group
  leader. A coredump server on the coredump socket can't get a handle on
  the thread that took the signal and is writing the dump, and anything
  doing per-thread authentication has the same problem. The sending and
  the connecting thread are recorded in addition to the thread-group
  leader and sk_peer_pid becomes an array indexed by pid type.

  SO_PASSPIDFD_THREAD works like SO_PASSPIDFD but delivers an
  SCM_PIDFD_THREAD cmsg for the sending thread. Both options are
  independent so a receiver can ask for both. On SOCK_STREAM sockets
  recvmsg() only stops merging data at a thread boundary when the
  receiver asked for a thread pidfd. SO_PEERPIDFD_THREAD returns a pidfd
  for the thread that called connect(), listen() or socketpair(). pidfs
  records the coredump on the dumping thread's struct pid too so its
  pidfd reports it like the leader's does. Selftests for af_unix and the
  coredump socket are included"

* tag 'vfs-7.4-rc1.shared.net-next.pidfd' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  selftests/coredump: check the dumping thread's pidfd
  pidfs: record the coredump on the dumping thread's pid too
  selftests/net: SO_PEERPIDFD_THREAD
  net: add SO_PEERPIDFD_THREAD to get a thread-specific pidfd
  af_unix: record the pid of the connecting thread
  net: turn sk_peer_pid into an array indexed by pid type
  selftests/net: SO_PASSPIDFD_THREAD
  net: add SO_PASSPIDFD_THREAD to get a thread-specific SCM_PIDFD
  af_unix: record the pid of the sending thread
  pid: add helpers to operate on a struct pid array

10 files changed, 107 insertions, 14 deletions

diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 74af57b9406b..8e857770dd21 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
+#include <linux/pid_types.h>
 #include <linux/sched/coredump.h>
 #include <uapi/linux/coredump.h>
 #include <asm/siginfo.h>
@@ -51,7 +52,8 @@ struct coredump_params {
 	int vma_count;
 	size_t vma_data_size;
 	struct core_vma_metadata *vma_meta;
-	struct pid *pid;
+	/* Dumping thread and its thread-group leader by pid type. */
+	DECLARE_PIDS(pid, PIDTYPE_TGID);
 };
 
 extern unsigned int core_file_note_size_limit;
diff --git a/include/linux/pid.h b/include/linux/pid.h
index a0458c713e4e..185bf0cde2d1 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -2,6 +2,9 @@
 #ifndef _LINUX_PID_H
 #define _LINUX_PID_H
 
+#include <linux/array_size.h>
+#include <linux/build_bug.h>
+#include <linux/minmax.h>
 #include <linux/pid_types.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
@@ -92,6 +95,56 @@ static inline struct pid *get_pid(struct pid *pid)
 }
 
 extern void put_pid(struct pid *pid);
+
+/*
+ * Helpers for arrays of struct pid indexed by pid type declared with
+ * DECLARE_PIDS(). The array covers PIDTYPE_PID up to the pid type it
+ * was declared with and the helpers take that bound from the array.
+ */
+static inline void __get_pids(struct pid **dst, struct pid *const *src,
+			      enum pid_type last)
+{
+	for (enum pid_type type = PIDTYPE_PID; type <= last; type++)
+		dst[type] = get_pid(src[type]);
+}
+
+static inline void __put_pids(struct pid **pids, enum pid_type last)
+{
+	for (enum pid_type type = PIDTYPE_PID; type <= last; type++) {
+		put_pid(pids[type]);
+		pids[type] = NULL;
+	}
+}
+
+static inline void __swap_pids(struct pid **a, struct pid **b,
+			       enum pid_type last)
+{
+	for (enum pid_type type = PIDTYPE_PID; type <= last; type++)
+		swap(a[type], b[type]);
+}
+
+static inline bool __pids_equal(struct pid *const *a, struct pid *const *b,
+				enum pid_type last)
+{
+	for (enum pid_type type = PIDTYPE_PID; type <= last; type++)
+		if (a[type] != b[type])
+			return false;
+	return true;
+}
+
+/* The last pid type an array declared with DECLARE_PIDS() covers. */
+#define pids_last(pids)							\
+	((enum pid_type)(ARRAY_SIZE(pids) - 1 +				\
+			 BUILD_BUG_ON_ZERO(ARRAY_SIZE(pids) > PIDTYPE_MAX)))
+
+#define __pids_last2(a, b)						\
+	(pids_last(a) + BUILD_BUG_ON_ZERO(ARRAY_SIZE(a) != ARRAY_SIZE(b)))
+
+#define get_pids(dst, src)	__get_pids(dst, src, __pids_last2(dst, src))
+#define put_pids(pids)		__put_pids(pids, pids_last(pids))
+#define swap_pids(a, b)		__swap_pids(a, b, __pids_last2(a, b))
+#define pids_equal(a, b)	__pids_equal(a, b, __pids_last2(a, b))
+
 extern struct task_struct *pid_task(struct pid *pid, enum pid_type);
 static inline bool pid_has_task(struct pid *pid, enum pid_type type)
 {
diff --git a/include/linux/pid_types.h b/include/linux/pid_types.h
index c2aee1d91dcf..3302690a2a28 100644
--- a/include/linux/pid_types.h
+++ b/include/linux/pid_types.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_PID_TYPES_H
 #define _LINUX_PID_TYPES_H
 
+#include <linux/build_bug.h>
+
 enum pid_type {
 	PIDTYPE_PID,
 	PIDTYPE_TGID,
@@ -10,6 +12,12 @@ enum pid_type {
 	PIDTYPE_MAX,
 };
 
+struct pid;
+
+/* An array of struct pid indexed by pid type, PIDTYPE_PID up to @last. */
+#define DECLARE_PIDS(name, last)					\
+	struct pid *name[(last) + 1 + BUILD_BUG_ON_ZERO((last) >= PIDTYPE_MAX)]
+
 struct pid_namespace;
 extern struct pid_namespace init_pid_ns;
 
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
index 0abf7da9ab23..3c1e82f1a369 100644
--- a/include/linux/pidfs.h
+++ b/include/linux/pidfs.h
@@ -3,6 +3,7 @@
 #define _LINUX_PID_FS_H
 
 #include <linux/gfp_types.h>
+#include <linux/pid.h>
 
 struct coredump_params;
 
@@ -32,5 +33,9 @@ static inline int pidfs_register_pid(struct pid *pid)
 }
 
 void pidfs_free_pid(struct pid *pid);
+int __pidfs_register_pids(struct pid *const *pids, enum pid_type last);
+
+/* Register the pids of an array declared with DECLARE_PIDS(). */
+#define pidfs_register_pids(pids)	__pidfs_register_pids(pids, pids_last(pids))
 
 #endif /* _LINUX_PID_FS_H */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index bfb84f025b67..f65d97fe199c 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -697,6 +697,24 @@ struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
 	return pid;
 }
 
+/* Fill @pids with the pid types of @task up to @last, without references. */
+static inline void __task_pids(struct pid **pids, enum pid_type last,
+			       struct task_struct *task)
+{
+	for (enum pid_type type = PIDTYPE_PID; type <= last; type++)
+		pids[type] = task_pid_type(task, type);
+}
+
+static inline void __get_task_pids(struct pid **pids, enum pid_type last,
+				   struct task_struct *task)
+{
+	for (enum pid_type type = PIDTYPE_PID; type <= last; type++)
+		pids[type] = get_pid(task_pid_type(task, type));
+}
+
+#define task_pids(pids, task)		__task_pids(pids, pids_last(pids), task)
+#define get_task_pids(pids, task)	__get_task_pids(pids, pids_last(pids), task)
+
 static inline struct pid *task_tgid(struct task_struct *task)
 {
 	return task->signal->pids[PIDTYPE_TGID];
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 5a5eb1250103..b17fdb7d38a7 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -189,10 +189,11 @@ static inline size_t msg_data_left(const struct msghdr *msg)
 
 /* "Socket"-level control message types: */
 
-#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)		*/
+#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)		*/
+#define SCM_PIDFD_THREAD	0x05	/* ro: thread pidfd (int)	*/
 
 struct ucred {
 	__u32	pid;
diff --git a/include/net/scm.h b/include/net/scm.h
index 86ae6bc109ec..b68a143f42de 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -42,7 +42,7 @@ struct scm_fp_list {
 };
 
 struct scm_cookie {
-	struct pid		*pid;		/* Skb credentials */
+	DECLARE_PIDS(pid, PIDTYPE_TGID);	/* Skb credentials by pid type */
 	struct scm_fp_list	*fp;		/* Passed files		*/
 	struct scm_creds	creds;		/* Skb credentials	*/
 #ifdef CONFIG_SECURITY_NETWORK
@@ -69,7 +69,6 @@ static __inline__ void unix_get_peersec_dgram(struct socket *sock, struct scm_co
 static __inline__ void scm_set_cred(struct scm_cookie *scm,
 				    struct pid *pid, kuid_t uid, kgid_t gid)
 {
-	scm->pid = get_pid(pid);
 	scm->creds.pid = pid_vnr(pid);
 	scm->creds.uid = uid;
 	scm->creds.gid = gid;
@@ -77,8 +76,7 @@ static __inline__ void scm_set_cred(struct scm_cookie *scm,
 
 static __inline__ void scm_destroy_cred(struct scm_cookie *scm)
 {
-	put_pid(scm->pid);
-	scm->pid = NULL;
+	put_pids(scm->pid);
 }
 
 static __inline__ void scm_destroy(struct scm_cookie *scm)
@@ -94,8 +92,10 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg,
 	memset(scm, 0, sizeof(*scm));
 	scm->creds.uid = INVALID_UID;
 	scm->creds.gid = INVALID_GID;
-	if (forcecreds)
+	if (forcecreds) {
+		scm->pid[PIDTYPE_TGID] = get_pid(task_tgid(current));
 		scm_set_cred(scm, task_tgid(current), current_uid(), current_gid());
+	}
 	unix_get_peersec_dgram(sock, scm);
 	if (msg->msg_controllen <= 0)
 		return 0;
diff --git a/include/net/sock.h b/include/net/sock.h
index 60ea55dc1885..77dfb170d3c8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -301,7 +301,7 @@ struct sk_filter;
   *	@sk_type: socket type (%SOCK_STREAM, etc)
   *	@sk_protocol: which protocol this socket belongs in this network family
   *	@sk_peer_lock: lock protecting @sk_peer_pid and @sk_peer_cred
-  *	@sk_peer_pid: &struct pid for this socket's peer
+  *	@sk_peer_pid: &struct pid for this socket's peer, by pid type
   *	@sk_peer_cred: %SO_PEERCRED setting
   *	@sk_rcvlowat: %SO_RCVLOWAT setting
   *	@sk_rcvtimeo: %SO_RCVTIMEO setting
@@ -356,6 +356,7 @@ struct sk_filter;
   *	@sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY
   *	@sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD
   *	@sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS
+  *	@sk_scm_pidfd_thread: flagged by SO_PASSPIDFD_THREAD to recv a thread SCM_PIDFD
   *	@sk_scm_unused: unused flags for scm_recv()
   *	@ns_tracker: tracker for netns reference
   *	@sk_user_frags: xarray of pages the user is holding a reference on.
@@ -545,7 +546,7 @@ struct sock {
 	u64			sk_ino;
 	spinlock_t		sk_peer_lock;
 	int			sk_bind_phc;
-	struct pid		*sk_peer_pid;
+	DECLARE_PIDS(sk_peer_pid, PIDTYPE_TGID);
 	const struct cred	*sk_peer_cred;
 
 	ktime_t			sk_stamp;
@@ -562,7 +563,8 @@ struct sock {
 				sk_scm_security : 1,
 				sk_scm_pidfd : 1,
 				sk_scm_rights : 1,
-				sk_scm_unused : 4;
+				sk_scm_pidfd_thread : 1,
+				sk_scm_unused : 3;
 		};
 	};
 	u8			sk_clockid;
diff --git a/include/trace/events/landlock.h b/include/trace/events/landlock.h
index 3a43638c9bc2..9e172ea22d95 100644
--- a/include/trace/events/landlock.h
+++ b/include/trace/events/landlock.h
@@ -1037,7 +1037,7 @@ TRACE_EVENT(landlock_deny_scope_abstract_unix_socket,
 		 * updates.  The peer socket keeps a reference to sk_peer_pid
 		 * through pid_nr(); sun_path is the reliable identifier.
 		 */
-		peer_pid		= READ_ONCE(peer->sk_peer_pid);
+		peer_pid		= READ_ONCE(peer->sk_peer_pid[PIDTYPE_TGID]);
 		__entry->peer_pid	= peer_pid ? pid_nr(peer_pid) : 0;
 		__assign_str(sun_path);
 	),
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 84ea7b92936e..56fed7ab27ab 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -152,6 +152,10 @@
 
 #define SO_RIGHTS_NOTRUNC	85
 
+#define SO_PASSPIDFD_THREAD	86
+
+#define SO_PEERPIDFD_THREAD	87
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))