procfs: allow threads to rename siblings via /proc/pid/tasks/tid/comm

Setting a thread's comm to be something unique is a very useful ability
and is helpful for debugging complicated threaded applications.  However
currently the only way to set a thread name is for the thread to name
itself via the PR_SET_NAME prctl.

However, there may be situations where it would be advantageous for a
thread dispatcher to be naming the threads its managing, rather then
having the threads self-describe themselves.  This sort of behavior is
available on other systems via the pthread_setname_np() interface.

This patch exports a task's comm via proc/pid/comm and
proc/pid/task/tid/comm interfaces, and allows thread siblings to write to
these values.

[akpm@linux-foundation.org: cleanups]
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Mike Fulton <fultonm@ca.ibm.com>
Cc: Sean Foley <Sean_Foley@ca.ibm.com>
Cc: Darren Hart <dvhltc@us.ibm.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 86 insertions, 0 deletions

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 94b9f2056f4c..220cc6376ef8 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -38,6 +38,7 @@ Table of Contents
   3.3   /proc/<pid>/io - Display the IO accounting fields
   3.4   /proc/<pid>/coredump_filter - Core dump filtering settings
   3.5   /proc/<pid>/mountinfo - Information about mounts
+  3.6   /proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
 
 
 ------------------------------------------------------------------------------
@@ -1409,3 +1410,11 @@ For more information on mount propagation see:
 
   Documentation/filesystems/sharedsubtree.txt
 
+
+3.6     /proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
+--------------------------------------------------------
+These files provide a method to access a tasks comm value. It also allows for
+a task to set its own or one of its thread siblings comm value. The comm value
+is limited in size compared to the cmdline value, so writing anything longer
+then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
+comm value.
diff --git a/fs/exec.c b/fs/exec.c
index c0c636e34f60..623a5cc3076a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -923,6 +923,15 @@ char *get_task_comm(char *buf, struct task_struct *tsk)
 void set_task_comm(struct task_struct *tsk, char *buf)
 {
         task_lock(tsk);
+
+        /*
+         * Threads may access current->comm without holding
+         * the task lock, so write the string carefully.
+         * Readers without a lock may see incomplete new
+         * names but are safe from non-terminating string reads.
+         */
+        memset(tsk->comm, 0, TASK_COMM_LEN);
+        wmb();
         strlcpy(tsk->comm, buf, sizeof(tsk->comm));
         task_unlock(tsk);
         perf_event_comm(tsk);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index af643b5aefe8..4df4a464a919 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1265,6 +1265,72 @@ static const struct file_operations proc_pid_sched_operations = {
 
 #endif
 
+static ssize_t comm_write(struct file *file, const char __user *buf,
+                                size_t count, loff_t *offset)
+{
+        struct inode *inode = file->f_path.dentry->d_inode;
+        struct task_struct *p;
+        char buffer[TASK_COMM_LEN];
+
+        memset(buffer, 0, sizeof(buffer));
+        if (count > sizeof(buffer) - 1)
+                count = sizeof(buffer) - 1;
+        if (copy_from_user(buffer, buf, count))
+                return -EFAULT;
+
+        p = get_proc_task(inode);
+        if (!p)
+                return -ESRCH;
+
+        if (same_thread_group(current, p))
+                set_task_comm(p, buffer);
+        else
+                count = -EINVAL;
+
+        put_task_struct(p);
+
+        return count;
+}
+
+static int comm_show(struct seq_file *m, void *v)
+{
+        struct inode *inode = m->private;
+        struct task_struct *p;
+
+        p = get_proc_task(inode);
+        if (!p)
+                return -ESRCH;
+
+        task_lock(p);
+        seq_printf(m, "%s\n", p->comm);
+        task_unlock(p);
+
+        put_task_struct(p);
+
+        return 0;
+}
+
+static int comm_open(struct inode *inode, struct file *filp)
+{
+        int ret;
+
+        ret = single_open(filp, comm_show, NULL);
+        if (!ret) {
+                struct seq_file *m = filp->private_data;
+
+                m->private = inode;
+        }
+        return ret;
+}
+
+static const struct file_operations proc_pid_set_comm_operations = {
+        .open           = comm_open,
+        .read           = seq_read,
+        .write          = comm_write,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
 /*
  * We added or removed a vma mapping the executable. The vmas are only mapped
  * during exec and are not mapped with the mmap system call.
@@ -2504,6 +2570,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
+        REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
         INF("syscall",    S_IRUSR, proc_pid_syscall),
 #endif
@@ -2838,6 +2905,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
+        REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
         INF("syscall",   S_IRUSR, proc_pid_syscall),
 #endif