From: riel@redhat.com
To: linux-kernel@vger.kernel.org
Cc: x86@kernel.org, williams@redhat.com, luto@kernel.org,
mingo@kernel.org, bonzini@redhat.com, fweisbec@redhat.com,
peterz@infradead.org, heiko.carstens@de.ibm.com,
tglx@linutronix.de, Rik van Riel <riel@redhat.com>,
Andy Lutomirsky <amluto@amacapital.com>
Subject: [PATCH 2/3] remove local_irq_save from __acct_update_integrals
Date: Thu, 30 Apr 2015 17:23:54 -0400 [thread overview]
Message-ID: <1430429035-25563-3-git-send-email-riel@redhat.com> (raw)
In-Reply-To: <1430429035-25563-1-git-send-email-riel@redhat.com>
From: Rik van Riel <riel@redhat.com>
The function __acct_update_integrals() is called both from irq context
and task context. This creates a race where irq context can advance
tsk->acct_timexpd to a value larger than time, leading to a negative
value, which causes a divide error. See commit 6d5b5acca9e5
("Fix fixpoint divide exception in acct_update_integrals")
In 2012, __acct_update_integrals() was changed to get utime and stime
as function parameters. This re-introduced the bug, because an irq
can hit in-between the call to task_cputime() and where irqs actually
get disabled.
However, this race condition was originally reproduced on Hercules,
and I have not seen any reports of it re-occurring since it was
re-introduced 3 years ago.
On the other hand, the irq disabling and re-enabling, which no longer
even protects us against the race today, show up prominently in the
perf profile of a program that makes a very large number of system calls
in a short period of time, when nohz_full= (and context tracking) is
enabled.
This patch replaces the (now ineffective) irq blocking with a cheaper
way to test for the race condition, and speeds up my microbenchmark
with 10 million iterations, average of 5 runs, tiny stddev:
run time system time
vanilla 5.49s 2.08s
patch 5.21s 1.92s
Cc: Andy Lutomirsky <amluto@amacapital.com>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
---
arch/powerpc/include/asm/cputime.h | 3 +++
arch/s390/include/asm/cputime.h | 3 +++
include/asm-generic/cputime_jiffies.h | 2 ++
include/asm-generic/cputime_nsecs.h | 3 +++
kernel/tsacct.c | 16 ++++++++++++----
5 files changed, 23 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index e2452550bcb1..e41b32f68a2c 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -32,6 +32,9 @@ static inline void setup_cputime_one_jiffy(void) { }
typedef u64 __nocast cputime_t;
typedef u64 __nocast cputime64_t;
+typedef s64 signed_cputime_t;
+typedef s64 signed_cputime64_t;
+
#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
#ifdef __KERNEL__
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 221b454c734a..2e8c268cc2a7 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -18,6 +18,9 @@
typedef unsigned long long __nocast cputime_t;
typedef unsigned long long __nocast cputime64_t;
+typedef signed long long signed_cputime_t;
+typedef signed long long signed_cputime64_t;
+
#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
static inline unsigned long __div(unsigned long long n, unsigned long base)
diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h
index fe386fc6e85e..b96b6a1b6c97 100644
--- a/include/asm-generic/cputime_jiffies.h
+++ b/include/asm-generic/cputime_jiffies.h
@@ -2,6 +2,7 @@
#define _ASM_GENERIC_CPUTIME_JIFFIES_H
typedef unsigned long __nocast cputime_t;
+typedef signed long signed_cputime_t;
#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
@@ -11,6 +12,7 @@ typedef unsigned long __nocast cputime_t;
#define jiffies_to_cputime(__hz) (__force cputime_t)(__hz)
typedef u64 __nocast cputime64_t;
+typedef s64 signed_cputime_t;
#define cputime64_to_jiffies64(__ct) (__force u64)(__ct)
#define jiffies64_to_cputime64(__jif) (__force cputime64_t)(__jif)
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
index 0419485891f2..c1ad2f90a4d9 100644
--- a/include/asm-generic/cputime_nsecs.h
+++ b/include/asm-generic/cputime_nsecs.h
@@ -21,6 +21,9 @@
typedef u64 __nocast cputime_t;
typedef u64 __nocast cputime64_t;
+typedef s64 signed_cputime_t;
+typedef s64 signed_cputime64_t;
+
#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
#define cputime_one_jiffy jiffies_to_cputime(1)
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 9e225425bc3a..e497c1c05675 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -125,15 +125,24 @@ static void __acct_update_integrals(struct task_struct *tsk,
{
cputime_t time, dtime;
struct timeval value;
- unsigned long flags;
u64 delta;
if (unlikely(!tsk->mm))
return;
- local_irq_save(flags);
+ /*
+ * This code is called both from task context and irq context.
+ * There is a rare race where irq context advances tsk->acct_timexpd
+ * to a value larger than time, leading to a negative dtime, which
+ * could lead to a divide error in cputime_to_jiffies.
+ * The statistics updated here are fairly rough estimates; just
+ * ignore irq and task double accounting the same timer tick.
+ */
time = stime + utime;
- dtime = time - tsk->acct_timexpd;
+ dtime = time - READ_ONCE(tsk->acct_timexpd);
+ if (unlikely((signed_cputime_t)dtime <= 0))
+ return;
+
jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
delta = value.tv_sec;
delta = delta * USEC_PER_SEC + value.tv_usec;
@@ -143,7 +152,6 @@ static void __acct_update_integrals(struct task_struct *tsk,
tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
}
- local_irq_restore(flags);
}
/**
--
2.1.0
next prev parent reply other threads:[~2015-04-30 21:24 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-04-30 21:23 [PATCH 0/3] reduce nohz_full syscall overhead by 10% riel
2015-04-30 21:23 ` [PATCH 1/3] reduce indentation in __acct_update_integrals riel
2015-04-30 21:23 ` riel [this message]
2015-04-30 21:23 ` [PATCH 3/3] context_tracking,x86: remove extraneous irq disable & enable from context tracking on syscall entry riel
2015-04-30 21:56 ` Andy Lutomirski
2015-05-01 6:40 ` Ingo Molnar
2015-05-01 15:20 ` Rik van Riel
2015-05-01 15:59 ` Ingo Molnar
2015-05-01 16:03 ` Andy Lutomirski
2015-05-01 16:21 ` Ingo Molnar
2015-05-01 16:26 ` Rik van Riel
2015-05-01 16:34 ` Ingo Molnar
2015-05-01 18:05 ` Rik van Riel
2015-05-01 18:40 ` Ingo Molnar
2015-05-01 19:11 ` Rik van Riel
2015-05-01 19:37 ` Andy Lutomirski
2015-05-02 5:27 ` Ingo Molnar
2015-05-02 18:27 ` Rik van Riel
2015-05-03 18:41 ` Andy Lutomirski
2015-05-07 10:35 ` Ingo Molnar
2015-05-04 9:26 ` Paolo Bonzini
2015-05-04 13:30 ` Rik van Riel
2015-05-04 14:06 ` Rik van Riel
2015-05-04 14:19 ` Rik van Riel
2015-05-04 15:59 ` question about RCU dynticks_nesting Rik van Riel
2015-05-04 18:39 ` Paul E. McKenney
2015-05-04 19:39 ` Rik van Riel
2015-05-04 20:02 ` Paul E. McKenney
2015-05-04 20:13 ` Rik van Riel
2015-05-04 20:38 ` Paul E. McKenney
2015-05-04 20:53 ` Rik van Riel
2015-05-05 5:54 ` Paul E. McKenney
2015-05-06 1:49 ` Mike Galbraith
2015-05-06 3:44 ` Mike Galbraith
2015-05-06 6:06 ` Paul E. McKenney
2015-05-06 6:52 ` Mike Galbraith
2015-05-06 7:01 ` Mike Galbraith
2015-05-07 0:59 ` Frederic Weisbecker
2015-05-07 15:44 ` Rik van Riel
2015-05-04 19:00 ` Rik van Riel
2015-05-04 19:39 ` Paul E. McKenney
2015-05-04 19:59 ` Rik van Riel
2015-05-04 20:40 ` Paul E. McKenney
2015-05-05 10:53 ` Peter Zijlstra
2015-05-05 12:34 ` Paul E. McKenney
2015-05-05 13:00 ` Peter Zijlstra
2015-05-05 18:35 ` Paul E. McKenney
2015-05-05 21:09 ` Rik van Riel
2015-05-06 5:41 ` Paul E. McKenney
2015-05-05 10:48 ` Peter Zijlstra
2015-05-05 10:51 ` Peter Zijlstra
2015-05-05 12:30 ` Paul E. McKenney
2015-05-02 4:06 ` [PATCH 3/3] context_tracking,x86: remove extraneous irq disable & enable from context tracking on syscall entry Mike Galbraith
2015-05-01 16:37 ` Ingo Molnar
2015-05-01 16:40 ` Rik van Riel
2015-05-01 16:45 ` Ingo Molnar
2015-05-01 16:54 ` Rik van Riel
2015-05-01 17:12 ` Ingo Molnar
2015-05-01 17:22 ` Rik van Riel
2015-05-01 17:59 ` Ingo Molnar
2015-05-01 16:22 ` Rik van Riel
2015-05-01 16:27 ` Ingo Molnar
2015-05-03 13:23 ` Mike Galbraith
2015-05-03 17:30 ` Rik van Riel
2015-05-03 18:24 ` Andy Lutomirski
2015-05-03 18:52 ` Rik van Riel
2015-05-07 10:48 ` Ingo Molnar
2015-05-07 12:18 ` Frederic Weisbecker
2015-05-07 12:29 ` Ingo Molnar
2015-05-07 15:47 ` Rik van Riel
2015-05-08 7:58 ` Ingo Molnar
2015-05-07 12:22 ` Andy Lutomirski
2015-05-07 12:44 ` Ingo Molnar
2015-05-07 12:49 ` Ingo Molnar
2015-05-08 6:17 ` Paul E. McKenney
2015-05-07 12:52 ` Andy Lutomirski
2015-05-07 15:08 ` Ingo Molnar
2015-05-07 17:47 ` Andy Lutomirski
2015-05-08 6:37 ` Ingo Molnar
2015-05-08 10:59 ` Andy Lutomirski
2015-05-08 11:27 ` Ingo Molnar
2015-05-08 12:56 ` Andy Lutomirski
2015-05-08 13:27 ` Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1430429035-25563-3-git-send-email-riel@redhat.com \
--to=riel@redhat.com \
--cc=amluto@amacapital.com \
--cc=bonzini@redhat.com \
--cc=fweisbec@redhat.com \
--cc=heiko.carstens@de.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=williams@redhat.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome