pidfd: change pidfd_send_signal() to respect PIDFD_THREAD

Turn kill_pid_info() into kill_pid_info_type(), this allows to pass any
pid_type to group_send_sig_info(), despite its name it should work fine
even if type = PIDTYPE_PID.

Change pidfd_send_signal() to use PIDTYPE_PID or PIDTYPE_TGID depending
on PIDFD_THREAD.

While at it kill another TODO comment in pidfd_show_fdinfo(). As Christian
expains fdinfo reports f_flags, userspace can already detect PIDFD_THREAD.

Reviewed-by: Tycho Andersen <tandersen@netflix.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20240209130650.GA8048@redhat.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/kernel/fork.c b/kernel/fork.c
index 4b6d994505cad714e74de3fb3bd9017506c4ddd9..3f22ec90c5c615fab2fdd82ea8bd5142654286ce 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2051,8 +2051,6 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
 
        seq_put_decimal_ll(m, "Pid:\t", nr);
 
-       /* TODO: report PIDFD_THREAD */
-
 #ifdef CONFIG_PID_NS
        seq_put_decimal_ll(m, "\nNSpid:\t", nr);
        if (nr > 0) {

diff --git a/kernel/signal.c b/kernel/signal.c
index 1450689302d90e42f4652273b6f5e85e241e0cf6..8b81696238503cde59bcae83b42a0a00ae46d50f 100644 (file)
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -47,6 +47,7 @@
 #include <linux/cgroup.h>
 #include <linux/audit.h>
 #include <linux/sysctl.h>
+#include <uapi/linux/pidfd.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/signal.h>
@@ -1436,7 +1437,8 @@ void lockdep_assert_task_sighand_held(struct task_struct *task)
 #endif
 
 /*
- * send signal info to all the members of a group
+ * send signal info to all the members of a thread group or to the
+ * individual thread if type == PIDTYPE_PID.
  */
 int group_send_sig_info(int sig, struct kernel_siginfo *info,
                        struct task_struct *p, enum pid_type type)
@@ -1478,7 +1480,8 @@ int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp)
        return ret;
 }
 
-int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
+static int kill_pid_info_type(int sig, struct kernel_siginfo *info,
+                               struct pid *pid, enum pid_type type)
 {
        int error = -ESRCH;
        struct task_struct *p;
@@ -1487,11 +1490,10 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
                rcu_read_lock();
                p = pid_task(pid, PIDTYPE_PID);
                if (p)
-                       error = group_send_sig_info(sig, info, p, PIDTYPE_TGID);
+                       error = group_send_sig_info(sig, info, p, type);
                rcu_read_unlock();
                if (likely(!p || error != -ESRCH))
                        return error;
-
                /*
                 * The task was unhashed in between, try again.  If it
                 * is dead, pid_task() will return NULL, if we race with
@@ -1500,6 +1502,11 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
        }
 }
 
+int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
+{
+       return kill_pid_info_type(sig, info, pid, PIDTYPE_TGID);
+}
+
 static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid)
 {
        int error;
@@ -3873,14 +3880,10 @@ static struct pid *pidfd_to_pid(const struct file *file)
  * @info:   signal info
  * @flags:  future flags
  *
- * The syscall currently only signals via PIDTYPE_PID which covers
- * kill(<positive-pid>, <signal>. It does not signal threads or process
- * groups.
- * In order to extend the syscall to threads and process groups the @flags
- * argument should be used. In essence, the @flags argument will determine
- * what is signaled and not the file descriptor itself. Put in other words,
- * grouping is a property of the flags argument not a property of the file
- * descriptor.
+ * Send the signal to the thread group or to the individual thread depending
+ * on PIDFD_THREAD.
+ * In the future extension to @flags may be used to override the default scope
+ * of @pidfd.
  *
  * Return: 0 on success, negative errno on failure
  */
@@ -3891,6 +3894,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
        struct fd f;
        struct pid *pid;
        kernel_siginfo_t kinfo;
+       enum pid_type type;
 
        /* Enforce flags be set to 0 until we add an extension. */
        if (flags)
@@ -3911,6 +3915,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
        if (!access_pidfd_pidns(pid))
                goto err;
 
+       if (f.file->f_flags & PIDFD_THREAD)
+               type = PIDTYPE_PID;
+       else
+               type = PIDTYPE_TGID;
+
        if (info) {
                ret = copy_siginfo_from_user_any(&kinfo, info);
                if (unlikely(ret))
@@ -3926,12 +3935,10 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
                    (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
                        goto err;
        } else {
-               prepare_kill_siginfo(sig, &kinfo, PIDTYPE_TGID);
+               prepare_kill_siginfo(sig, &kinfo, type);
        }
 
-       /* TODO: respect PIDFD_THREAD */
-       ret = kill_pid_info(sig, &kinfo, pid);
-
+       ret = kill_pid_info_type(sig, &kinfo, pid, type);
 err:
        fdput(f);
        return ret;