From: Sonny Rao <sonnyrao@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: Sonny Rao <sonnyrao@linux.vnet.ibm.com>,
Milton Miller <miltonm@bga.com>, Ingo Molnar <mingo@elte.hu>,
Peter Zijlstra <peterz@infradead.org>
Subject: [PATCH] print_cfq_rq: per_cpu(xx, 0) may not exist
Date: Thu, 18 Nov 2010 04:23:14 -0600 [thread overview]
Message-ID: <1290075796-2975-1-git-send-email-sonnyrao@linux.vnet.ibm.com> (raw)
Per cpu variables only exist for possible cpus. On some architectures
and platforms, cpu 0 may not be possible, and this debug code generates
an oops.
As a variable for the boot cpu seems to be architecture dependent, replace
this aparently arbitrary choice of reference for spread of min vruntime
across run queues from that of cpu 0 to that of the first online cpu.
Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Sonny Rao <sonnyrao@linux.vnet.ibm.com>
---
kernel/sched_debug.c | 6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 2e1b0d1..be586db 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -163,7 +163,7 @@ static void task_group_path(struct task_group *tg, char *buf, int buflen)
void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
- spread, rq0_min_vruntime, spread0;
+ spread, spread0;
struct rq *rq = cpu_rq(cpu);
struct sched_entity *last;
unsigned long flags;
@@ -188,7 +188,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
if (last)
max_vruntime = last->vruntime;
min_vruntime = cfs_rq->min_vruntime;
- rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
raw_spin_unlock_irqrestore(&rq->lock, flags);
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime",
SPLIT_NS(MIN_vruntime));
@@ -199,7 +198,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
spread = max_vruntime - MIN_vruntime;
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread",
SPLIT_NS(spread));
- spread0 = min_vruntime - rq0_min_vruntime;
+ spread0 = min_vruntime - per_cpu(runqueues,
+ cpumask_first(cpu_online_mask)).cfs.min_vruntime;
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0",
SPLIT_NS(spread0));
SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
--
1.5.6.5
next reply other threads:[~2010-11-18 19:21 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-18 10:23 Sonny Rao [this message]
2010-11-18 10:23 ` [PATCH] Fix crash in sym53c8xx_2 error path Sonny Rao
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=1290075796-2975-1-git-send-email-sonnyrao@linux.vnet.ibm.com \
--to=sonnyrao@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=miltonm@bga.com \
--cc=mingo@elte.hu \
--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
all inboxes | Powered by JetHome®