Received-SPF: pass (google.com: domain of linux-kernel+bounces-33630-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Date: Mon, 22 Jan 2024 16:50:50 +0100
From: Oleg Nesterov <oleg@redhat.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>,
	Dylan Hatch <dylanbhatch@google.com>, linux-kernel@vger.kernel.org
Subject: [PATCH v2 1/2] getrusage: move thread_group_cputime_adjusted()
 outside of lock_task_sighand()
Message-ID: <20240122155050.GA26205@redhat.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240122155023.GA26169@redhat.com>
User-Agent: Mutt/1.5.24 (2015-08-30)

thread_group_cputime() does its own locking, we can safely shift
thread_group_cputime_adjusted() which does another for_each_thread loop
outside of ->siglock protected section.

This is also preparation for the next patch which changes getrusage() to
use stats_lock instead of siglock, thread_group_cputime() takes the same
lock.  With the current implementation recursive read_seqbegin_or_lock()
is fine, thread_group_cputime() can't enter the slow mode if the caller
holds stats_lock, yet this looks more safe and better performance-wise.

Reported-and-tested-by: Dylan Hatch <dylanbhatch@google.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 kernel/sys.c | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/kernel/sys.c b/kernel/sys.c
index e219fcfa112d..70ad06ad852e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1785,17 +1785,19 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 	struct task_struct *t;
 	unsigned long flags;
 	u64 tgutime, tgstime, utime, stime;
-	unsigned long maxrss = 0;
+	unsigned long maxrss;
+	struct mm_struct *mm;
 	struct signal_struct *sig = p->signal;
 
-	memset((char *)r, 0, sizeof (*r));
+	memset(r, 0, sizeof(*r));
 	utime = stime = 0;
+	maxrss = 0;
 
 	if (who == RUSAGE_THREAD) {
 		task_cputime_adjusted(current, &utime, &stime);
 		accumulate_thread_rusage(p, r);
 		maxrss = sig->maxrss;
-		goto out;
+		goto out_thread;
 	}
 
 	if (!lock_task_sighand(p, &flags))
@@ -1819,9 +1821,6 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 		fallthrough;
 
 	case RUSAGE_SELF:
-		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-		utime += tgutime;
-		stime += tgstime;
 		r->ru_nvcsw += sig->nvcsw;
 		r->ru_nivcsw += sig->nivcsw;
 		r->ru_minflt += sig->min_flt;
@@ -1839,19 +1838,24 @@ void getrusage(struct task_struct *p, int who, struct rusage *r)
 	}
 	unlock_task_sighand(p, &flags);
 
-out:
-	r->ru_utime = ns_to_kernel_old_timeval(utime);
-	r->ru_stime = ns_to_kernel_old_timeval(stime);
+	if (who == RUSAGE_CHILDREN)
+		goto out_children;
 
-	if (who != RUSAGE_CHILDREN) {
-		struct mm_struct *mm = get_task_mm(p);
+	thread_group_cputime_adjusted(p, &tgutime, &tgstime);
+	utime += tgutime;
+	stime += tgstime;
 
-		if (mm) {
-			setmax_mm_hiwater_rss(&maxrss, mm);
-			mmput(mm);
-		}
+out_thread:
+	mm = get_task_mm(p);
+	if (mm) {
+		setmax_mm_hiwater_rss(&maxrss, mm);
+		mmput(mm);
 	}
+
+out_children:
 	r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
+	r->ru_utime = ns_to_kernel_old_timeval(utime);
+	r->ru_stime = ns_to_kernel_old_timeval(stime);
 }
 
 SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru)
-- 
2.25.1.362.g51ebf55