linux-kernel - Re: [PATCH] Do not force shutdown/reboot to boot cpu.

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: <20130410190003.GH3658@sgi.com>
Date:	Wed, 10 Apr 2013 14:00:03 -0500
From:	Robin Holt <holt@....com>
To:	Ingo Molnar <mingo@...nel.org>
Cc:	Robin Holt <holt@....com>, Russ Anderson <rja@....com>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	"H. Peter Anvin" <hpa@...or.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Shawn Guo <shawn.guo@...aro.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Ingo Molnar <mingo@...hat.com>,
	the arch/x86 maintainers <x86@...nel.org>
Subject: Re: [PATCH] Do not force shutdown/reboot to boot cpu.

> > I'm proposing to make 'reboot' overhead profilable, via a debug hack:
> > 
> >         echo 1 > /proc/sys/kernel/magic_dont_fully_reboot_flag
> > 
> > 	perf record reboot
> > 
> > perf is using NMIs to profile - and since much of cpu_down() is with irqs 
> > disabled, NMI profiling would be needed to see inside the overhead.
> > 
> > (Assuming the 240 msecs is CPU overhead, not waiting for some IRQ/IPI event.)


I had the machine booted as 512 cpus.
I tweaked the kernel like this:

diff --git a/kernel/sys.c b/kernel/sys.c
index 39c9c4a..b42bd4f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -368,8 +368,10 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
  */
 void kernel_restart(char *cmd)
 {
-       kernel_restart_prepare(cmd);
+       // kernel_restart_prepare(cmd);
        disable_nonboot_cpus();
+       enable_nonboot_cpus();
+       return;
        if (!cmd)
                printk(KERN_EMERG "Restarting system.\n");
        else

perf record -a /sbin/reboot -d -f -n

The top of 'perf report' has:
Events: 14M cycles
    22.58%          swapper  [kernel.kallsyms]           [k] update_cfs_rq_blocked_load
    10.52%          swapper  [kernel.kallsyms]           [k] load_balance
     4.96%          swapper  [kernel.kallsyms]           [k] ktime_get
     4.12%          swapper  [kernel.kallsyms]           [k] update_blocked_averages
     3.55%          swapper  [kernel.kallsyms]           [k] idle_cpu
     1.97%          swapper  [kernel.kallsyms]           [k] uv_read_rtc
     0.98%          swapper  [kernel.kallsyms]           [k] rcu_process_gp_end
     0.84%          swapper  [kernel.kallsyms]           [k] apic_timer_interrupt
     0.84%          swapper  [kernel.kallsyms]           [k] __lock_text_start
     0.84%          swapper  [kernel.kallsyms]           [k] _raw_spin_lock_irqsave
     0.73%          swapper  [kernel.kallsyms]           [k] native_safe_halt
     0.56%          swapper  [kernel.kallsyms]           [k] rcu_check_callbacks
     0.56%          swapper  [kernel.kallsyms]           [k] native_write_msr_safe
     0.44%          swapper  [kernel.kallsyms]           [k] cpumask_next_and
     0.42%           reboot  [kernel.kallsyms]           [k] kmem_cache_alloc_node

The perf data is 676 MB.  I don't know how well it compresses, but the
lzma task has been running for a while.

Thanks,
Robin
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/