BACKPORT: pid: add pidfd_open()

This adds the pidfd_open() syscall. It allows a caller to retrieve pollable
pidfds for a process which did not get created via CLONE_PIDFD, i.e. for a
process that is created via traditional fork()/clone() calls that is only
referenced by a PID:

int pidfd = pidfd_open(1234, 0);
ret = pidfd_send_signal(pidfd, SIGSTOP, NULL, 0);

With the introduction of pidfds through CLONE_PIDFD it is possible to
created pidfds at process creation time.
However, a lot of processes get created with traditional PID-based calls
such as fork() or clone() (without CLONE_PIDFD). For these processes a
caller can currently not create a pollable pidfd. This is a problem for
Android's low memory killer (LMK) and service managers such as systemd.
Both are examples of tools that want to make use of pidfds to get reliable
notification of process exit for non-parents (pidfd polling) and race-free
signal sending (pidfd_send_signal()). They intend to switch to this API for
process supervision/management as soon as possible. Having no way to get
pollable pidfds from PID-only processes is one of the biggest blockers for
them in adopting this api. With pidfd_open() making it possible to retrieve
pidfds for PID-based processes we enable them to adopt this api.

In line with Arnd's recent changes to consolidate syscall numbers across
architectures, I have added the pidfd_open() syscall to all architectures
at the same time.

Signed-off-by: Christian Brauner <christian@brauner.io>
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jann Horn <jannh@google.com>
Cc: Perry Lutomirsky <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-api@vger.kernel.org
(cherry picked from commit 32fcb426ec001cb6d5a4a195091a8486ea77e2df)

Conflicts:
        kernel/pid.c

(1. Replaced PIDTYPE_TGID with PIDTYPE_PID and thread_group_leader() check in pidfd_open() call)

Mot-CRs-fixed: (CR)

Bug: 135608568
Test: test program using syscall(__NR_sys_pidfd_open,..) and poll()
Change-Id: I52a93a73722d7f7754dae05f63b94b4ca4a71a75
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-on: https://gerrit.mot.com/1505856
SME-Granted: SME Approvals Granted
SLTApproved: Slta Waiver
Tested-by: Jira Key
Reviewed-by: Wang Wang <wangwang1@lenovo.com>
Reviewed-by: Yonghui Jia <jiayh2@motorola.com>
Submit-Approved: Jira Key
Reviewed-on: https://gerrit.mot.com/1796165
Reviewed-by: Xiangpo Zhao <zhaoxp3@motorola.com>

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 87a4653097a404f0783f38b8ea59773a1c135ba2..816532c7c17e253a04a0b2a4aff2a8522567063c 100644 (file)
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -901,6 +901,7 @@ asmlinkage long sys_open_by_handle_at(int mountdirfd,
                                      struct file_handle __user *handle,
                                      int flags);
 asmlinkage long sys_setns(int fd, int nstype);
+asmlinkage long sys_pidfd_open(pid_t pid, unsigned int flags);
 asmlinkage long sys_process_vm_readv(pid_t pid,
                                     const struct iovec __user *lvec,
                                     unsigned long liovcnt,

diff --git a/kernel/pid.c b/kernel/pid.c
index 020dedbdf066bccbc370cba20be8dc7dbc914629..1f67bc038ac7236f5039a73196c231268e5a501b 100644 (file)
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -38,6 +38,8 @@
 #include <linux/syscalls.h>
 #include <linux/proc_ns.h>
 #include <linux/proc_fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 
 #define pid_hashfn(nr, ns)     \
@@ -565,6 +567,76 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
        return pid;
 }
 
+/**
+ * pidfd_create() - Create a new pid file descriptor.
+ *
+ * @pid:  struct pid that the pidfd will reference
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set.
+ *
+ * Note, that this function can only be called after the fd table has
+ * been unshared to avoid leaking the pidfd to the new process.
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ *         On error, a negative errno number will be returned.
+ */
+static int pidfd_create(struct pid *pid)
+{
+       int fd;
+
+       fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
+                             O_RDWR | O_CLOEXEC);
+       if (fd < 0)
+               put_pid(pid);
+
+       return fd;
+}
+
+/**
+ * pidfd_open() - Open new pid file descriptor.
+ *
+ * @pid:   pid for which to retrieve a pidfd
+ * @flags: flags to pass
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set for
+ * the process identified by @pid. Currently, the process identified by
+ * @pid must be a thread-group leader. This restriction currently exists
+ * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot
+ * be used with CLONE_THREAD) and pidfd polling (only supports thread group
+ * leaders).
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ *         On error, a negative errno number will be returned.
+ */
+SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
+{
+       int fd, ret;
+       struct pid *p;
+       struct task_struct *tsk;
+
+       if (flags)
+               return -EINVAL;
+
+       if (pid <= 0)
+               return -EINVAL;
+
+       p = find_get_pid(pid);
+       if (!p)
+               return -ESRCH;
+
+       ret = 0;
+       rcu_read_lock();
+       tsk = pid_task(p, PIDTYPE_PID);
+       /* Check that pid belongs to a group leader task */
+       if (!tsk || !thread_group_leader(tsk))
+               ret = -EINVAL;
+       rcu_read_unlock();
+
+       fd = ret ?: pidfd_create(p);
+       put_pid(p);
+       return fd;
+}
+
 /*
  * The pid hash table is scaled according to the amount of memory in the
  * machine.  From a minimum of 16 slots up to 4096 slots at one gigabyte or