linux-kernel - [PATCH 1/2] getrusage: move thread_group_cputime_adjusted() outside of lock_task

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240119141501.GA23739@redhat.com>
Date: Fri, 19 Jan 2024 15:15:01 +0100
From: Oleg Nesterov <oleg@...hat.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Dylan Hatch <dylanbhatch@...gle.com>, Kees Cook <keescook@...omium.org>,
	Frederic Weisbecker <frederic@...nel.org>,
	"Joel Fernandes (Google)" <joel@...lfernandes.org>,
	Ard Biesheuvel <ardb@...nel.org>,
	"Matthew Wilcox (Oracle)" <willy@...radead.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
	"Eric W. Biederman" <ebiederm@...ssion.com>,
	Vincent Whitchurch <vincent.whitchurch@...s.com>,
	Dmitry Vyukov <dvyukov@...gle.com>,
	Luis Chamberlain <mcgrof@...nel.org>,
	Mike Christie <michael.christie@...cle.com>,
	David Hildenbrand <david@...hat.com>,
	Catalin Marinas <catalin.marinas@....com>,
	Stefan Roesch <shr@...kernel.io>, Joey Gouly <joey.gouly@....com>,
	Josh Triplett <josh@...htriplett.org>, Helge Deller <deller@....de>,
	Ondrej Mosnacek <omosnace@...hat.com>,
	Florent Revest <revest@...omium.org>,
	Miguel Ojeda <ojeda@...nel.org>, linux-kernel@...r.kernel.org
Subject: [PATCH 1/2] getrusage: move thread_group_cputime_adjusted() outside
 of lock_task_sighand()

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. Currently the deadlock is not possible,
if getrusage() enters the slow path and takes stats_lock, read_seqretry()
in thread_group_cputime() must always return 0, so thread_group_cputime()
will never try to take the same lock. Yet this looks more safe and better
performance-wise.

Signed-off-by: Oleg Nesterov <oleg@...hat.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