From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Morton Subject: Re: [Bug 42767] New: System unsuable with intel_iommu=on Date: Mon, 13 Feb 2012 12:51:08 -0800 Message-ID: <20120213125108.6325bb07.akpm@linux-foundation.org> References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org Errors-To: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org To: David Woodhouse , iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org Cc: ConiKost-Mmb7MZpHnFY@public.gmane.org, bugzilla-daemon-590EEB7GvNiWaY/ihj7yzEB+6BGkLq7r@public.gmane.org List-Id: iommu@lists.linux-foundation.org (switched to email. Please respond via emailed reply-to-all, not via the bugzilla web interface). On Mon, 13 Feb 2012 20:45:21 GMT bugzilla-daemon-590EEB7GvNiWaY/ihj7yzEB+6BGkLq7r@public.gmane.org wrote: > https://bugzilla.kernel.org/show_bug.cgi?id=42767 > > Summary: System unsuable with intel_iommu=on > Product: Memory Management > Version: 2.5 > Platform: All > OS/Version: Linux > Tree: Mainline > Status: NEW > Severity: normal > Priority: P1 > Component: Other > AssignedTo: akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org > ReportedBy: ConiKost-Mmb7MZpHnFY@public.gmane.org > Regression: No > > > Hi, > i've some very strange problems since kernel 3.2.0. > When I enable the CONFIG_INTEL_IOMMU_DEFAULT_ON, the problems starts. > > OS: Gentoo Linux > Kernel: Gentoo Sources 3.2.5 (tried also with vanilla 3.2.5) > Hardware: Thinkpad X200 Tablet > Bios: 3.20 > > The problems are, that my video card fails with 3d rendering (e.g. GNOME3 > crashes) and my network card stops working after using some network i/o. When I > choose intel_iommu=off, all problems disapear and everything works fine. > > Feb 13 21:24:11 [kernel] [drm:i915_hangcheck_elapsed] *ERROR* Hangcheck timer > elapsed... GPU hung > Feb 13 21:24:11 [kernel] render error detected, EIR: 0x00000010 > Feb 13 21:24:11 [kernel] IPEIR: 0x00000000 > Feb 13 21:24:11 [kernel] IPEHR: 0x18800180 > Feb 13 21:24:11 [kernel] INSTDONE: 0xffffffff > Feb 13 21:24:11 [kernel] INSTPS: 0x4001e020 > Feb 13 21:24:11 [kernel] INSTDONE1: 0xbfffffff > Feb 13 21:24:11 [kernel] ACTHD: 0x013f0000 > Feb 13 21:24:11 [kernel] page table error > Feb 13 21:24:11 [kernel] PGTBL_ER: 0x00100000 > > Feb 13 21:25:44 [kernel] DRHD: handling fault status reg 2 > Feb 13 21:25:44 [kernel] DMAR:[DMA Read] Request device [00:19.0] fault addr > fff84000 > Feb 13 21:25:44 [kernel] DMAR:[fault reason 06] PTE Read access is not set > Feb 13 21:25:47 [kernel] e1000e 0000:00:19.0: eth0: Detected Hardware Unit > Hang: > Feb 13 21:25:47 [kernel] TDH <57> > Feb 13 21:25:47 [kernel] TDT <68> > Feb 13 21:25:47 [kernel] next_to_use <68> > Feb 13 21:25:47 [kernel] next_to_clean <56> > Feb 13 21:25:47 [kernel] buffer_info[next_to_clean]: > Feb 13 21:25:47 [kernel] time_stamp > Feb 13 21:25:47 [kernel] next_to_watch <57> > Feb 13 21:25:47 [kernel] jiffies > Feb 13 21:25:47 [kernel] next_to_watch.status <0> > Feb 13 21:25:47 [kernel] MAC Status <80383> > Feb 13 21:25:47 [kernel] PHY Status <796d> > Feb 13 21:25:47 [kernel] PHY 1000BASE-T Status <3c00> > Feb 13 21:25:47 [kernel] PHY Extended Status <3000> > Feb 13 21:25:47 [kernel] PCI Status <10> > Feb 13 21:25:48 [kernel] fbcondecor: switched decor state to 'off' on console 0 > Feb 13 21:25:48 [kernel] fbcondecor: console 0 using theme > 'battlestar-galactica' > Feb 13 21:25:48 [kernel] fbcondecor: switched decor state to 'on' on console 0 > Feb 13 21:25:49 [kernel] e1000e 0000:00:19.0: eth0: Detected Hardware Unit > Hang: > Feb 13 21:25:49 [kernel] TDH <57> > Feb 13 21:25:49 [kernel] TDT <68> > Feb 13 21:25:49 [kernel] next_to_use <68> > Feb 13 21:25:49 [kernel] next_to_clean <56> > Feb 13 21:25:49 [kernel] buffer_info[next_to_clean]: > Feb 13 21:25:49 [kernel] time_stamp > Feb 13 21:25:49 [kernel] next_to_watch <57> > Feb 13 21:25:49 [kernel] jiffies > Feb 13 21:25:49 [kernel] next_to_watch.status <0> > Feb 13 21:25:49 [kernel] MAC Status <80383> > Feb 13 21:25:49 [kernel] PHY Status <796d> > Feb 13 21:25:49 [kernel] PHY 1000BASE-T Status <3c00> > Feb 13 21:25:49 [kernel] PHY Extended Status <3000> > Feb 13 21:25:49 [kernel] PCI Status <10> > Feb 13 21:25:51 [kernel] ------------[ cut here ]------------ > Feb 13 21:25:51 [kernel] WARNING: at net/sched/sch_generic.c:255 > dev_watchdog+0x249/0x260() > Feb 13 21:25:51 [kernel] Hardware name: 7450EQG > Feb 13 21:25:51 [kernel] NETDEV WATCHDOG: eth0 (e1000e): transmit queue 0 timed > out > Feb 13 21:25:51 [kernel] Modules linked in: > Feb 13 21:25:51 [kernel] Pid: 0, comm: swapper/1 Not tainted 3.2.1-gentoo #1 > Feb 13 21:25:51 [kernel] Call Trace: > Feb 13 21:25:51 [kernel] [] ? > warn_slowpath_common+0x7b/0xc0 > Feb 13 21:25:51 [kernel] [] ? warn_slowpath_fmt+0x45/0x50 > Feb 13 21:25:51 [kernel] [] ? mod_timer+0x13d/0x240 > Feb 13 21:25:51 [kernel] [] ? dev_watchdog+0x249/0x260 > Feb 13 21:25:51 [kernel] [] ? cascade+0x7b/0xa0 > Feb 13 21:25:51 [kernel] [] ? qdisc_reset+0x40/0x40 > Feb 13 21:25:51 [kernel] [] ? run_timer_softirq+0x116/0x270 > Feb 13 21:25:51 [kernel] [] ? __do_softirq+0x98/0x120 > Feb 13 21:25:51 [kernel] [] ? call_softirq+0x1c/0x30 > Feb 13 21:25:51 [kernel] [] ? do_softirq+0x4d/0x80 > Feb 13 21:25:51 [kernel] [] ? irq_exit+0x8e/0xd0 > Feb 13 21:25:51 [kernel] [] ? > smp_apic_timer_interrupt+0x68/0xa0 > Feb 13 21:25:51 [kernel] [] ? apic_timer_interrupt+0x6b/0x70 > Feb 13 21:25:51 [kernel] [] ? > acpi_idle_enter_bm+0x214/0x252 > Feb 13 21:25:51 [kernel] [] ? acpi_idle_enter_bm+0x20f/0x252 > Feb 13 21:25:51 [kernel] [] ? cpuidle_idle_call+0x8a/0xf0 > Feb 13 21:25:51 [kernel] [] ? cpu_idle+0xbf/0x110 > Feb 13 21:25:51 [kernel] [] ? start_secondary+0x1f5/0x1fb > Feb 13 21:25:51 [kernel] ---[ end trace 71e047540e69b903 ]--- > Feb 13 21:25:51 [kernel] e1000e 0000:00:19.0: eth0: Reset adapter >