Re: [3.9-rc1] irq 16: nobody cared (was [3.9-rc1] very poor interrupt responses)

From: Yinghai Lu <yinghai@kernel.org>
To: Jiri Kosina <jkosina@suse.cz>
Cc: Peter Hurley <peter@hurleysoftware.com>,
	Thomas Meyer <thomas@m3y3r.de>,
	Shawn Starr <shawn.starr@rogers.com>,
	Alan Stern <stern@rowland.harvard.edu>,
	Kernel development list <linux-kernel@vger.kernel.org>,
	USB list <linux-usb@vger.kernel.org>,
	linux-acpi@vger.kernel.org, "Rafael J. Wysocki" <rjw@sisk.pl>,
	Bjorn Helgaas <bhelgaas@google.com>,
	linux-pci@vger.kernel.org
Subject: Re: [3.9-rc1] irq 16: nobody cared (was [3.9-rc1] very poor interrupt responses)
Date: Thu, 14 Mar 2013 11:48:05 -0700	[thread overview]
Message-ID: <CAE9FiQXM5qTasq38CoroJk8uzCt5GLFBL9jxN5SDBQreqA7pFw@mail.gmail.com> (raw)
In-Reply-To: <alpine.LRH.2.00.1303132233080.27467@twin.jikos.cz>

On Wed, Mar 13, 2013 at 2:35 PM, Jiri Kosina <jkosina@suse.cz> wrote:
> OK, this is a "me too", on Thinkpad x200s.
>
> [    4.116847] irq 16: nobody cared (try booting with the "irqpoll" option)
> [    4.116849] Pid: 1, comm: systemd Not tainted 3.9.0-rc2-00188-g6c23cbb #186
> [    4.116850] Call Trace:
> [    4.116860]  <IRQ>  [<ffffffff810db0f8>] __report_bad_irq+0x38/0xf0
> [    4.116862]  [<ffffffff810db3a3>] note_interrupt+0x1f3/0x240
> [    4.116865]  [<ffffffff810d8977>] handle_irq_event_percpu+0x147/0x230
> [    4.116867]  [<ffffffff810d8aa9>] handle_irq_event+0x49/0x70
> [    4.116869]  [<ffffffff810dbbc1>] handle_fasteoi_irq+0x61/0x100
> [    4.116873]  [<ffffffff81004689>] handle_irq+0x59/0x150
> [    4.116877]  [<ffffffff8104e916>] ? irq_enter+0x16/0x80
> [    4.116879]  [<ffffffff81003d4b>] do_IRQ+0x5b/0xe0
> [    4.116883]  [<ffffffff815563ad>] common_interrupt+0x6d/0x6d
> [    4.116888]  <EOI>  [<ffffffff81320dc1>] ? cfb_imageblit+0x581/0x5b0
> [    4.116891]  [<ffffffff8131e019>] bit_putcs+0x329/0x560
> [    4.116893]  [<ffffffff8131dc8f>] ? bit_cursor+0x5cf/0x630
> [    4.116896]  [<ffffffff81317a28>] fbcon_putcs+0xf8/0x130
> [    4.116898]  [<ffffffff8131dcf0>] ? bit_cursor+0x630/0x630
> [    4.116900]  [<ffffffff8131a27e>] fbcon_redraw+0x16e/0x1e0
> [    4.116902]  [<ffffffff8131a554>] fbcon_scroll+0x264/0xe40
> [    4.116905]  [<ffffffff8138a263>] scrup+0x113/0x120
> [    4.116907]  [<ffffffff8138a4d0>] lf+0x80/0x90
> [    4.116910]  [<ffffffff8138e1dd>] do_con_trol+0xcd/0x1360
> [    4.116912]  [<ffffffff8138f725>] do_con_write+0x2b5/0xa10
> [    4.116915]  [<ffffffff81552bb7>] ? __mutex_lock_slowpath+0x237/0x2e0
> [    4.116917]  [<ffffffff8138fed9>] con_write+0x19/0x30
> [    4.116920]  [<ffffffff8137823b>] do_output_char+0x1eb/0x220
> [    4.116922]  [<ffffffff813782b6>] process_output+0x46/0x70
> [    4.116924]  [<ffffffff81378b0f>] n_tty_write+0x13f/0x2f0
> [    4.116928]  [<ffffffff8107a900>] ? try_to_wake_up+0x2b0/0x2b0
> [    4.116930]  [<ffffffff8137553c>] tty_write+0x1cc/0x280
> [    4.116932]  [<ffffffff813789d0>] ? n_tty_ioctl+0x110/0x110
> [    4.116934]  [<ffffffff8137569d>] redirected_tty_write+0xad/0xc0
> [    4.116937]  [<ffffffff811733ab>] vfs_write+0xcb/0x130
> [    4.116939]  [<ffffffff81173bac>] sys_write+0x5c/0xa0
> [    4.116943]  [<ffffffff8155e4a9>] system_call_fastpath+0x16/0x1b
> [    4.116943] handlers:
> [    4.116959] [<ffffffffa0048450>] usb_hcd_irq [usbcore]
> [    4.116960] Disabling IRQ #16
>
> I don't think I have seen this message on rc1+ (8343bce, to be precise),
> but I have definitely seen sluggish system response on that kernel as
> well.
>
> Attaching lspci, /proc/interrupts and dmesg.

can you post dmesg with "debug ignore_loglevel pci=routeirq" with
current linus tree and v3.8 or previous working kernel?

Thanks

Yinghai