LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Christian Brauner <christian@brauner.io>
To: ebiederm@xmission.com, linux-kernel@vger.kernel.org
Cc: serge@hallyn.com, jannh@google.com, luto@kernel.org,
	akpm@linux-foundation.org, oleg@redhat.com, cyphar@cyphar.com,
	viro@zeniv.linux.org.uk, linux-fsdevel@vger.kernel.org,
	linux-api@vger.kernel.org, dancol@google.com,
	timmurray@google.com, linux-man@vger.kernel.org,
	Christian Brauner <christian@brauner.io>,
	Kees Cook <keescook@chromium.org>
Subject: [PATCH v1 2/2] signal: add procfd_signal() syscall
Date: Mon, 19 Nov 2018 11:32:39 +0100
Message-ID: <20181119103241.5229-3-christian@brauner.io> (raw)
In-Reply-To: <20181119103241.5229-1-christian@brauner.io>

The kill() syscall operates on process identifiers. After a process has
exited its pid can be reused by another process. If a caller sends a signal
to a reused pid it will end up signaling the wrong process. This issue has
often surfaced and there has been a push [1] to address this problem.

A prior patch has introduced the ability to get a file descriptor
referencing struct pid by opening /proc/<pid>. This guarantees a stable
handle on a process which can be used to send signals to the referenced
process. Discussion has shown that a dedicated syscall is preferable over
ioctl()s. Thus, the  new syscall procfd_signal() is introduced to solve
this problem. It operates on a process file descriptor.
The syscall takes an additional siginfo_t and flags argument. If siginfo_t
is NULL then procfd_signal() behaves like kill() if it is not NULL it
behaves like rt_sigqueueinfo.
The flags argument is added to allow for future extensions of this syscall.
It currently needs to be passed as 0.

With this patch a process can be killed via:

 #define _GNU_SOURCE
 #include <errno.h>
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <signal.h>
 #include <sys/stat.h>
 #include <sys/syscall.h>
 #include <sys/types.h>
 #include <unistd.h>

 int main(int argc, char *argv[])
 {
         int ret;
         char buf[1000];

         if (argc < 2)
                 exit(EXIT_FAILURE);

         ret = snprintf(buf, sizeof(buf), "/proc/%s", argv[1]);
         if (ret < 0)
                 exit(EXIT_FAILURE);

         int fd = open(buf, O_DIRECTORY | O_CLOEXEC);
         if (fd < 0) {
                 printf("%s - Failed to open \"%s\"\n", strerror(errno), buf);
                 exit(EXIT_FAILURE);
         }

         ret = syscall(__NR_procfd_signal, fd, SIGKILL, NULL, 0);
         if (ret < 0) {
                 printf("Failed to send SIGKILL \"%s\"\n", strerror(errno));
                 close(fd);
                 exit(EXIT_FAILURE);
         }

         close(fd);

         exit(EXIT_SUCCESS);
 }

[1]: https://lkml.org/lkml/2018/11/18/130

Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Serge Hallyn <serge@hallyn.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andy Lutomirsky <luto@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Christian Brauner <christian@brauner.io>
---
Changelog:
v1:
- patch introduced
---
 arch/x86/entry/syscalls/syscall_32.tbl |  1 +
 arch/x86/entry/syscalls/syscall_64.tbl |  1 +
 fs/proc/base.c                         |  6 ++
 include/linux/proc_fs.h                |  1 +
 include/linux/syscalls.h               |  2 +
 kernel/signal.c                        | 76 ++++++++++++++++++++++++--
 6 files changed, 81 insertions(+), 6 deletions(-)

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 3cf7b533b3d1..e637eab883e9 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -398,3 +398,4 @@
 384	i386	arch_prctl		sys_arch_prctl			__ia32_compat_sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents		__ia32_compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq			__ia32_sys_rseq
+387	i386	procfd_signal		sys_procfd_signal		__ia32_sys_procfd_signal
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f0b1709a5ffb..e95f6741ab42 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,7 @@
 332	common	statx			__x64_sys_statx
 333	common	io_pgetevents		__x64_sys_io_pgetevents
 334	common	rseq			__x64_sys_rseq
+335	common	procfd_signal		__x64_sys_procfd_signal
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6365a4fea314..a12c9de92bd0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3055,6 +3055,12 @@ static const struct file_operations proc_tgid_base_operations = {
 	.release	= proc_tgid_release,
 };
 
+bool proc_is_procfd(const struct file *file)
+{
+	return d_is_dir(file->f_path.dentry) &&
+	       (file->f_op == &proc_tgid_base_operations);
+}
+
 static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	return proc_pident_lookup(dir, dentry,
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index d0e1f1522a78..2d53a47fba34 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -73,6 +73,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 						    int (*show)(struct seq_file *, void *),
 						    proc_write_t write,
 						    void *data);
+extern bool proc_is_procfd(const struct file *file);
 
 #else /* CONFIG_PROC_FS */
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2ac3d13a915b..a5ca8cb84566 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -907,6 +907,8 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 			  unsigned mask, struct statx __user *buffer);
 asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len,
 			 int flags, uint32_t sig);
+asmlinkage long sys_procfd_signal(int fd, int sig, siginfo_t __user *info,
+				  int flags);
 
 /*
  * Architecture-specific system calls
diff --git a/kernel/signal.c b/kernel/signal.c
index 9a32bc2088c9..e8a8929de710 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -19,7 +19,9 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/proc_fs.h>
 #include <linux/tty.h>
 #include <linux/binfmts.h>
 #include <linux/coredump.h>
@@ -3286,6 +3288,16 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese,
 }
 #endif
 
+static inline void prepare_kill_siginfo(int sig, struct kernel_siginfo *info)
+{
+	clear_siginfo(info);
+	info->si_signo = sig;
+	info->si_errno = 0;
+	info->si_code = SI_USER;
+	info->si_pid = task_tgid_vnr(current);
+	info->si_uid = from_kuid_munged(current_user_ns(), current_uid());
+}
+
 /**
  *  sys_kill - send a signal to a process
  *  @pid: the PID of the process
@@ -3295,16 +3307,68 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
 {
 	struct kernel_siginfo info;
 
-	clear_siginfo(&info);
-	info.si_signo = sig;
-	info.si_errno = 0;
-	info.si_code = SI_USER;
-	info.si_pid = task_tgid_vnr(current);
-	info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
+	prepare_kill_siginfo(sig, &info);
 
 	return kill_something_info(sig, &info, pid);
 }
 
+/**
+ *  sys_procfd_signal - send a signal to a process through a process file
+ *                      descriptor
+ *  @fd: the file descriptor of the process
+ *  @sig: signal to be sent
+ *  @info: the signal info
+ *  @flags: future flags to be passed
+ */
+SYSCALL_DEFINE4(procfd_signal, int, fd, int, sig, siginfo_t __user *, info,
+		int, flags)
+{
+	int ret;
+	struct pid *pid;
+	kernel_siginfo_t kinfo;
+	struct fd f;
+
+	/* Enforce flags be set to 0 until we add an extension. */
+	if (flags)
+		return -EINVAL;
+
+	f = fdget_raw(fd);
+	if (!f.file)
+		return -EBADF;
+
+	ret = -EINVAL;
+	/* Is this a process file descriptor? */
+	if (!proc_is_procfd(f.file))
+		goto err;
+
+	pid = f.file->private_data;
+	if (!pid)
+		goto err;
+
+	if (info) {
+		ret = __copy_siginfo_from_user(sig, &kinfo, info);
+		if (unlikely(ret))
+			goto err;
+		/*
+		 * Not even root can pretend to send signals from the kernel.
+		 * Nor can they impersonate a kill()/tgkill(), which adds
+		 * source info.
+		 */
+		ret = -EPERM;
+		if ((kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL) &&
+		    (task_pid(current) != pid))
+			goto err;
+	} else {
+		prepare_kill_siginfo(sig, &kinfo);
+	}
+
+	ret = kill_pid_info(sig, &kinfo, pid);
+
+err:
+	fdput(f);
+	return ret;
+}
+
 static int
 do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info)
 {
-- 
2.19.1


  parent reply index

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-19 10:32 [PATCH v1 0/2] proc: allow signaling processes via file descriptors Christian Brauner
2018-11-19 10:32 ` [PATCH v1 1/2] proc: get process file descriptor from /proc/<pid> Christian Brauner
2018-11-19 15:32   ` Andy Lutomirski
2018-11-19 18:20     ` Christian Brauner
2018-11-19 10:32 ` Christian Brauner [this message]
2018-11-19 15:45   ` [PATCH v1 2/2] signal: add procfd_signal() syscall Andy Lutomirski
2018-11-19 15:57     ` Daniel Colascione
2018-11-19 18:39     ` Christian Brauner
2018-11-19 15:59   ` Daniel Colascione
2018-11-19 18:29     ` Christian Brauner
2018-11-19 19:02       ` Eric W. Biederman
2018-11-19 19:31         ` Christian Brauner
2018-11-19 19:39           ` Daniel Colascione
2018-11-19 17:10   ` Eugene Syromiatnikov
2018-11-19 18:23     ` Christian Brauner
2018-11-19 17:14   ` Eugene Syromiatnikov
2018-11-19 20:28   ` Aleksa Sarai
2018-11-19 20:55     ` Christian Brauner
2018-11-19 21:13       ` Christian Brauner
2018-11-19 21:18       ` Aleksa Sarai
2018-11-19 21:20         ` Christian Brauner
2018-11-19 21:21         ` Christian Brauner
2018-11-19 21:25           ` Aleksa Sarai
2018-11-19 21:26           ` Daniel Colascione
2018-11-19 21:36             ` Aleksa Sarai
2018-11-19 21:37             ` Christian Brauner
2018-11-19 21:41               ` Daniel Colascione
2018-11-20  4:59                 ` Eric W. Biederman
2018-11-20 10:31                   ` Christian Brauner
2018-11-21 21:39                     ` Serge E. Hallyn
2018-11-19 21:23         ` Aleksa Sarai
2018-11-22  7:41           ` Serge E. Hallyn
2018-11-19 22:39   ` Tycho Andersen
2018-11-19 22:49     ` Daniel Colascione
2018-11-19 23:07       ` Tycho Andersen
2018-11-20  0:27         ` Andy Lutomirski
2018-11-20  0:32           ` Christian Brauner
2018-11-20  0:34             ` Andy Lutomirski
2018-11-20  0:49           ` Daniel Colascione
2018-11-22  7:48     ` Serge E. Hallyn
2018-11-19 23:35   ` kbuild test robot
2018-11-19 23:37   ` kbuild test robot
2018-11-19 23:45     ` Christian Brauner
2018-11-28 21:45   ` Joey Pabalinas
2018-11-28 22:05     ` Christian Brauner
2018-11-28 23:02       ` Joey Pabalinas
2018-11-19 10:32 ` [PATCH] procfd_signal.2: document procfd_signal syscall Christian Brauner
2018-11-20 13:29   ` Michael Kerrisk (man-pages)
2018-11-28 20:59   ` Florian Weimer
2018-11-28 21:12     ` Christian Brauner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20181119103241.5229-3-christian@brauner.io \
    --to=christian@brauner.io \
    --cc=akpm@linux-foundation.org \
    --cc=cyphar@cyphar.com \
    --cc=dancol@google.com \
    --cc=ebiederm@xmission.com \
    --cc=jannh@google.com \
    --cc=keescook@chromium.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-man@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=oleg@redhat.com \
    --cc=serge@hallyn.com \
    --cc=timmurray@google.com \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git