From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Date: Fri, 10 Jun 2011 12:41:54 +0000 Subject: Re: [PATCH 1/3] printk: Release console_sem after logbuf_lock Message-Id: <1307709714.3941.140.camel@twins> List-Id: References: <20110609130647.937204592@chello.nl> <20110609131307.493181962@chello.nl> <20110609130617.f8aca966.akpm@linux-foundation.org> <20110609202707.GA28951@elte.hu> <1307652883.2497.1028.camel@laptop> <20110609140714.fc9ea187.akpm@linux-foundation.org> <1307705311.3941.118.camel@twins> <1307709030.3941.134.camel@twins> <20110610123416.GA12451@elte.hu> In-Reply-To: <20110610123416.GA12451@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Ingo Molnar Cc: Hugh Dickins , Andrew Morton , Linus Torvalds , Thomas Gleixner , linux-kernel@vger.kernel.org, efault@gmx.de, Arne Jansen , PaulMundt , linux-fbdev@vger.kernel.org On Fri, 2011-06-10 at 14:34 +0200, Ingo Molnar wrote: > * Peter Zijlstra wrote: > > > thinking that that would have my printk stmts appear on both the > > fbcon as well as the serial line. But they fail to appear on the > > latency tracer (current max was 165us waking an idle cpu). > > Have you removed this bit: > > spin_unlock(&logbuf_lock); > stop_critical_timings(); /* don't trace print latency */ > call_console_drivers(_con_start, _log_end); > start_critical_timings(); > local_irq_restore(flags); > > which hides the latencies from the latency tracer? it shouldn't those flags come from spin_lock_irqsave(), which already has IRQs disabled, so the restore shouldn't re-enable them. Hmm,. that might actually already be true for mainline too, yeah, looks like we call vprintk()->console_unlock() with IRQs-disabled. Hohumm..