From: Frederic Weisbecker <frederic@kernel.org>
To: Ingo Molnar <mingo@kernel.org>, Peter Zijlstra <peterz@infradead.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
Chris Wilson <chris@chris-wilson.co.uk>,
Frederic Weisbecker <frederic@kernel.org>
Subject: [PATCH] sched/vtime: Prevent unstable evaluation of WARN(vtime->state)
Date: Thu, 23 Jan 2020 19:08:49 +0100 [thread overview]
Message-ID: <20200123180849.28486-1-frederic@kernel.org> (raw)
From: Chris Wilson <chris@chris-wilson.co.uk>
As the vtime is sampled under loose seqcount protection by kcpustat, the
vtime fields may change as the code flows. Where logic dictates a field
has a static value, use a READ_ONCE.
Fixes: 74722bb223d0 ("sched/vtime: Bring up complete kcpustat accessor")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
kernel/sched/cputime.c | 41 ++++++++++++++++++++++-------------------
1 file changed, 22 insertions(+), 19 deletions(-)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index d43318a489f2..df3577149d2e 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -912,8 +912,10 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
} while (read_seqcount_retry(&vtime->seqcount, seq));
}
-static int vtime_state_check(struct vtime *vtime, int cpu)
+static int vtime_state_fetch(struct vtime *vtime, int cpu)
{
+ int state = READ_ONCE(vtime->state);
+
/*
* We raced against a context switch, fetch the
* kcpustat task again.
@@ -930,10 +932,10 @@ static int vtime_state_check(struct vtime *vtime, int cpu)
*
* Case 1) is ok but 2) is not. So wait for a safe VTIME state.
*/
- if (vtime->state == VTIME_INACTIVE)
+ if (state == VTIME_INACTIVE)
return -EAGAIN;
- return 0;
+ return state;
}
static u64 kcpustat_user_vtime(struct vtime *vtime)
@@ -952,14 +954,15 @@ static int kcpustat_field_vtime(u64 *cpustat,
{
struct vtime *vtime = &tsk->vtime;
unsigned int seq;
- int err;
do {
+ int state;
+
seq = read_seqcount_begin(&vtime->seqcount);
- err = vtime_state_check(vtime, cpu);
- if (err < 0)
- return err;
+ state = vtime_state_fetch(vtime, cpu);
+ if (state < 0)
+ return state;
*val = cpustat[usage];
@@ -972,7 +975,7 @@ static int kcpustat_field_vtime(u64 *cpustat,
*/
switch (usage) {
case CPUTIME_SYSTEM:
- if (vtime->state == VTIME_SYS)
+ if (state == VTIME_SYS)
*val += vtime->stime + vtime_delta(vtime);
break;
case CPUTIME_USER:
@@ -984,11 +987,11 @@ static int kcpustat_field_vtime(u64 *cpustat,
*val += kcpustat_user_vtime(vtime);
break;
case CPUTIME_GUEST:
- if (vtime->state == VTIME_GUEST && task_nice(tsk) <= 0)
+ if (state == VTIME_GUEST && task_nice(tsk) <= 0)
*val += vtime->gtime + vtime_delta(vtime);
break;
case CPUTIME_GUEST_NICE:
- if (vtime->state == VTIME_GUEST && task_nice(tsk) > 0)
+ if (state == VTIME_GUEST && task_nice(tsk) > 0)
*val += vtime->gtime + vtime_delta(vtime);
break;
default:
@@ -1039,23 +1042,23 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
{
struct vtime *vtime = &tsk->vtime;
unsigned int seq;
- int err;
do {
u64 *cpustat;
u64 delta;
+ int state;
seq = read_seqcount_begin(&vtime->seqcount);
- err = vtime_state_check(vtime, cpu);
- if (err < 0)
- return err;
+ state = vtime_state_fetch(vtime, cpu);
+ if (state < 0)
+ return state;
*dst = *src;
cpustat = dst->cpustat;
/* Task is sleeping, dead or idle, nothing to add */
- if (vtime->state < VTIME_SYS)
+ if (state < VTIME_SYS)
continue;
delta = vtime_delta(vtime);
@@ -1064,15 +1067,15 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
* Task runs either in user (including guest) or kernel space,
* add pending nohz time to the right place.
*/
- if (vtime->state == VTIME_SYS) {
+ if (state == VTIME_SYS) {
cpustat[CPUTIME_SYSTEM] += vtime->stime + delta;
- } else if (vtime->state == VTIME_USER) {
+ } else if (state == VTIME_USER) {
if (task_nice(tsk) > 0)
cpustat[CPUTIME_NICE] += vtime->utime + delta;
else
cpustat[CPUTIME_USER] += vtime->utime + delta;
} else {
- WARN_ON_ONCE(vtime->state != VTIME_GUEST);
+ WARN_ON_ONCE(state != VTIME_GUEST);
if (task_nice(tsk) > 0) {
cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta;
cpustat[CPUTIME_NICE] += vtime->gtime + delta;
@@ -1083,7 +1086,7 @@ static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst,
}
} while (read_seqcount_retry(&vtime->seqcount, seq));
- return err;
+ return 0;
}
void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
--
2.25.0
next reply other threads:[~2020-01-23 18:08 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-23 18:08 Frederic Weisbecker [this message]
2020-02-14 16:23 ` [PATCH] sched/vtime: Prevent unstable evaluation of WARN(vtime->state) Frederic Weisbecker
2020-02-27 13:34 ` Frederic Weisbecker
2020-03-06 14:42 ` [tip: sched/core] " tip-bot2 for Chris Wilson
-- strict thread matches above, loose matches on Subject: below --
2019-12-30 1:08 [PATCH 2/6] sched/vtime: Bring up complete kcpustat accessor Frederic Weisbecker
2019-12-30 9:04 ` [PATCH] sched/vtime: Prevent unstable evaluation of WARN(vtime->state) Chris Wilson
2019-12-30 17:39 ` Frederic Weisbecker
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=20200123180849.28486-1-frederic@kernel.org \
--to=frederic@kernel.org \
--cc=chris@chris-wilson.co.uk \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.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;
as well as URLs for NNTP newsgroup(s).