prlimit: do not grab the tasklist_lock

Unnecessarily grabbing the tasklist_lock can be a scalability bottleneck
for workloads that also must grab the tasklist_lock for waiting,
killing, and cloning.

The tasklist_lock was grabbed to protect tsk->sighand from disappearing
(becoming NULL).  tsk->signal was already protected by holding a
reference to tsk.

update_rlimit_cpu() assumed tsk->sighand != NULL.  With this commit, it
attempts to lock_task_sighand().  However, this means that
update_rlimit_cpu() can fail.  This only happens when a task is exiting.
Note that during exec, sighand may *change*, but it will not be NULL.

Prior to this commit, the do_prlimit() ensured that update_rlimit_cpu()
would not fail by read locking the tasklist_lock and checking tsk->sighand
!= NULL.

If update_rlimit_cpu() fails, there may be other tasks that are not
exiting that share tsk->signal.  However, the group_leader is the last
task to be released, so if we cannot update_rlimit_cpu(group_leader),
then the entire process is exiting.

The only other caller of update_rlimit_cpu() is
selinux_bprm_committing_creds().  It has tsk == current, so
update_rlimit_cpu() cannot fail (current->sighand cannot disappear
until current exits).

This change resulted in a 14% speedup on a microbenchmark where parents
kill and wait on their children, and children getpriority, setpriority,
and getrlimit.

Signed-off-by: Barret Rhoden <brho@google.com>
Link: https://lkml.kernel.org/r/20220106172041.522167-4-brho@google.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>

3 files changed, 24 insertions, 15 deletions

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 5bbcd280bfd2..9cf126c3b27f 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -253,7 +253,7 @@ void posix_cpu_timers_exit_group(struct task_struct *task);
 void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
 			   u64 *newval, u64 *oldval);
 
-void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new);
+int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new);
 
 void posixtimer_rearm(struct kernel_siginfo *info);
 #endif
diff --git a/kernel/sys.c b/kernel/sys.c
index d37d1f882b7d..374f83e95239 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1441,13 +1441,7 @@ static int do_prlimit(struct task_struct *tsk, unsigned int resource,
 			return -EPERM;
 	}
 
-	/* protect tsk->signal and tsk->sighand from disappearing */
-	read_lock(&tasklist_lock);
-	if (!tsk->sighand) {
-		retval = -ESRCH;
-		goto out;
-	}
-
+	/* Holding a refcount on tsk protects tsk->signal from disappearing. */
 	rlim = tsk->signal->rlim + resource;
 	task_lock(tsk->group_leader);
 	if (new_rlim) {
@@ -1476,10 +1470,19 @@ static int do_prlimit(struct task_struct *tsk, unsigned int resource,
 	 */
 	if (!retval && new_rlim && resource == RLIMIT_CPU &&
 	    new_rlim->rlim_cur != RLIM_INFINITY &&
-	    IS_ENABLED(CONFIG_POSIX_TIMERS))
-		update_rlimit_cpu(tsk, new_rlim->rlim_cur);
-out:
-	read_unlock(&tasklist_lock);
+	    IS_ENABLED(CONFIG_POSIX_TIMERS)) {
+		/*
+		 * update_rlimit_cpu can fail if the task is exiting, but there
+		 * may be other tasks in the thread group that are not exiting,
+		 * and they need their cpu timers adjusted.
+		 *
+		 * The group_leader is the last task to be released, so if we
+		 * cannot update_rlimit_cpu on it, then the entire process is
+		 * exiting and we do not need to update at all.
+		 */
+		update_rlimit_cpu(tsk->group_leader, new_rlim->rlim_cur);
+	}
+
 	return retval;
 }
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 96b4e7810426..e13e628509fb 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -34,14 +34,20 @@ void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit)
  * tsk->signal->posix_cputimers.bases[clock].nextevt expiration cache if
  * necessary. Needs siglock protection since other code may update the
  * expiration cache as well.
+ *
+ * Returns 0 on success, -ESRCH on failure.  Can fail if the task is exiting and
+ * we cannot lock_task_sighand.  Cannot fail if task is current.
  */
-void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
+int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
 {
 	u64 nsecs = rlim_new * NSEC_PER_SEC;
+	unsigned long irq_fl;
 
-	spin_lock_irq(&task->sighand->siglock);
+	if (!lock_task_sighand(task, &irq_fl))
+		return -ESRCH;
 	set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL);
-	spin_unlock_irq(&task->sighand->siglock);
+	unlock_task_sighand(task, &irq_fl);
+	return 0;
 }
 
 /*