Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 29 Oct 2018 22:10:37 +0000
Message-Id: <20181029221037.87724-1-dancol@google.com>
Mime-Version: 1.0
Subject: [RFC PATCH] Implement /proc/pid/kill
From:   Daniel Colascione <dancol@google.com>
To:     linux-kernel@vger.kernel.org
Cc:     timmurray@google.com, joelaf@google.com, surenb@google.com,
        Daniel Colascione <dancol@google.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Add a simple proc-based kill interface. To use /proc/pid/kill, just
write the signal number in base-10 ASCII to the kill file of the
process to be killed: for example, 'echo 9 > /proc/$$/kill'.

Semantically, /proc/pid/kill works like kill(2), except that the
process ID comes from the proc filesystem context instead of from an
explicit system call parameter. This way, it's possible to avoid races
between inspecting some aspect of a process and that process's PID
being reused for some other process.

With /proc/pid/kill, it's possible to write a proper race-free and
safe pkill(1). An approximation follows. A real program might use
openat(2), having opened a process's /proc/pid directory explicitly,
with the directory file descriptor serving as a sort of "process
handle".

    #!/bin/bash
    set -euo pipefail
    pat=$1
    for proc_status in /proc/*/status; do (
        cd $(dirname $proc_status)
        readarray proc_argv -d'' < cmdline
        if ((${#proc_argv[@]} > 0)) &&
               [[ ${proc_argv[0]} = *$pat* ]];
        then
            echo 15 > kill
        fi
    ) || true; done

Signed-off-by: Daniel Colascione <dancol@google.com>
---
 fs/proc/base.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 7e9f07bf260d..923d62b21e67 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -205,6 +205,44 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
 	return result;
 }
 
+static ssize_t proc_pid_kill_write(struct file *file,
+				   const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	ssize_t res;
+	int sig;
+	char buffer[4];
+
+	res = -EINVAL;
+	if (*ppos != 0)
+		goto out;
+
+	res = -EINVAL;
+	if (count > sizeof(buffer) - 1)
+		goto out;
+
+	res = -EFAULT;
+	if (copy_from_user(buffer, buf, count))
+		goto out;
+
+	buffer[count] = '\0';
+	res = kstrtoint(strstrip(buffer), 10, &sig);
+	if (res)
+		goto out;
+
+	res = kill_pid(proc_pid(file_inode(file)), sig, 0);
+	if (res)
+		goto out;
+	res = count;
+out:
+	return res;
+
+}
+
+static const struct file_operations proc_pid_kill_ops = {
+	.write	= proc_pid_kill_write,
+};
+
 static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf,
 			      size_t count, loff_t *ppos)
 {
@@ -2935,6 +2973,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
 	ONE("syscall",    S_IRUSR, proc_pid_syscall),
 #endif
+	REG("kill",       S_IRUGO | S_IWUGO, proc_pid_kill_ops),
 	REG("cmdline",    S_IRUGO, proc_pid_cmdline_ops),
 	ONE("stat",       S_IRUGO, proc_tgid_stat),
 	ONE("statm",      S_IRUGO, proc_pid_statm),
-- 
2.19.1.568.g152ad8e336-goog