Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1596032 > unrolled thread
| Started by | Paul Menzel <pmenzel@molgen.mpg.de> |
|---|---|
| First post | 2017-03-09 13:40 +0100 |
| Last post | 2017-03-10 19:20 +0100 |
| Articles | 8 — 3 participants |
Back to article view | Back to linux.kernel
Kernel panic on Lenovo X60 with tracing enabled Paul Menzel <pmenzel@molgen.mpg.de> - 2017-03-09 13:40 +0100
Re: Kernel panic on Lenovo X60 with tracing enabled Steven Rostedt <rostedt@goodmis.org> - 2017-03-09 15:50 +0100
Re: Kernel panic on Lenovo X60 with tracing enabled Josh Poimboeuf <jpoimboe@redhat.com> - 2017-03-09 17:20 +0100
Re: Kernel panic on Lenovo X60 with tracing enabled Steven Rostedt <rostedt@goodmis.org> - 2017-03-09 18:10 +0100
Re: Kernel panic on Lenovo X60 with tracing enabled Paul Menzel <pmenzel@molgen.mpg.de> - 2017-03-09 21:50 +0100
Re: Kernel panic on Lenovo X60 with tracing enabled Josh Poimboeuf <jpoimboe@redhat.com> - 2017-03-10 00:10 +0100
Re: Kernel panic on Lenovo X60 with tracing enabled Paul Menzel <pmenzel@molgen.mpg.de> - 2017-03-10 10:00 +0100
Re: Kernel panic on Lenovo X60 with tracing enabled Josh Poimboeuf <jpoimboe@redhat.com> - 2017-03-10 19:20 +0100
| From | Paul Menzel <pmenzel@molgen.mpg.de> |
|---|---|
| Date | 2017-03-09 13:40 +0100 |
| Subject | Kernel panic on Lenovo X60 with tracing enabled |
| Message-ID | <tj5wm-5a0-33@gated-at.bofh.it> |
[Multipart message — attachments visible in raw view] — view raw
Dear Steven, dear Ingo, Hopefully, I am contacting the right people for my issue. Suspending a system with Linux 4.9.13 with tracing enabled, it fails with the screen still enabled, and the LED blinking. Attaching a serial console to the dock, shows the messages below. > […] > [ 59.063238] PM: Syncing filesystems ... done. > [ 59.197490] Freezing user space processes ... (elapsed 0.002 seconds) done. > [ 59.207510] Freezing remaining freezable tasks ... (elapsed 0.002 seconds) done. > [ 59.234169] sd 2:0:0:0: [sda] Synchronizing SCSI cache > [ 59.240355] sd 2:0:0:0: [sda] Stopping disk > [ 59.250859] ------------[ cut here ]------------ > [ 59.255562] WARNING: CPU: 0 PID: 774 at /build/linux-ROBWaj/linux-4.9.13/kernel/trace/trace_functions_graph.c:233 ftrace_return_to_handler+0x1aa/0x1e0 > [ 59.269228] Bad frame pointer: expected f6919d98, received f6919db0 > [ 59.269228] from func acpi_pm_device_sleep_wake return to c43b6f9d > [ 59.281993] Modules linked in: cpufreq_powersave(E) cpufreq_conservative(E) cpufreq_userspace(E) iTCO_wdt(E) arc4(E) iTCO_vendor_support(E) coretemp(E) pcmcia(E) kvm_intel(E) iwl3945(E) kvm(E) iwlegacy(E) mac80211(E) irqbypass(E) i915(E) lpc_ich(E) mfd_core(E) evdev(E) yenta_socket(E) serio_raw(E) snd_hda_codec_analog(E) pcmcia_rsrc(E) cfg80211(E) snd_hda_codec_generic(E) pcmcia_core(E) thinkpad_acpi(E) rng_core(E) snd_hda_intel(E) nvram(E) drm_kms_helper(E) rfkill(E) snd_hda_codec(E) battery(E) snd_hda_core(E) snd_hwdep(E) drm(E) snd_pcm(E) snd_timer(E) snd(E) soundcore(E) video(E) i2c_algo_bit(E) shpchp(E) ac(E) acpi_cpufreq(E) tpm_tis(E) button(E) tpm_tis_core(E) tpm(E) fuse(E) parport_pc(E) ppdev(E) lp(E) parport(E) autofs4(E) ext4(E) crc16(E) jbd2(E) fscrypto(E) mbcache(E) ecb(E) cbc(E) algif_skcipher(E) af_alg(E) dm_crypt(E) dm_mod(E) sr_mod(E) cdrom(E) sg(E) sd_mod(E) ata_generic(E) ehci_pci(E) uhci_hcd(E) ehci_hcd(E) ata_piix(E) ahci(E) libahci(E) firewire_ohci(E) sdhci_pci(E) psmouse(E) e1000e(E) libata(E) usbcore(E) i2c_i801(E) i2c_smbus(E) firewire_core(E) crc_itu_t(E) sdhci(E) mmc_core(E) ptp(E) scsi_mod(E) usb_common(E) pps_core(E) thermal(E) > [ 59.388749] CPU: 0 PID: 774 Comm: analyze_suspend Tainted: G E 4.9.0-0.bpo.2-686-pae #1 Debian 4.9.13-1~bpo8+1 > [ 59.392532] Hardware name: LENOVO 636338U/636338U, BIOS CBET4000 4.5-1169-g7129ccb 03/09/2017 > [ 59.392532] f6919d28 c42ee6ec f6919d3c 00000000 c4067c0a c469d538 f6919d5c 00000306 > [ 59.392532] c469d4f0 000000e9 c412e95a 000000e9 00000009 c412e95a c4164039 c43b6f9d > [ 59.392532] 00000002 f6919d48 c4067c76 00000009 00000000 f6919d3c c469d538 f6919d5c > [ 59.392532] Call Trace: > [ 59.392532] [<c42ee6ec>] ? dump_stack+0x55/0x79 > [ 59.392532] [<c4067c0a>] ? __warn+0xea/0x110 > [ 59.392532] [<c412e95a>] ? ftrace_return_to_handler+0x1aa/0x1e0 > [ 59.392532] [<c412e95a>] ? ftrace_return_to_handler+0x1aa/0x1e0 > [ 59.392532] [<c4164039>] ? cgroup_threadgroup_change_end.isra.39+0x1e/0x1e > [ 59.392532] [<c43b6f9d>] ? pnpacpi_suspend+0x5d/0xe0 > [ 59.392532] [<c4067c76>] ? warn_slowpath_fmt+0x46/0x60 > [ 59.392532] [<c412e95a>] ? ftrace_return_to_handler+0x1aa/0x1e0 > [ 59.392532] [<c43804a0>] ? acpi_pm_device_sleep_wake+0x14/0xa8 > [ 59.392532] [<c43b6f9d>] ? pnpacpi_suspend+0x5d/0xe0 > [ 59.392532] [<c43b6f9d>] ? pnpacpi_suspend+0x5d/0xe0 > [ 59.392532] [<c459c542>] ? return_to_handler+0x9/0xf > [ 59.392532] [<c459c539>] ? ftrace_graph_caller+0x19/0x19 > [ 59.392532] [<c43b2e12>] ? pnp_bus_suspend+0x12/0x20 > [ 59.392532] [<c459c539>] ? ftrace_graph_caller+0x19/0x19 > [ 59.392532] [<c4427c66>] ? dpm_run_callback+0x46/0x120 > [ 59.392532] [<c43b2e00>] ? pnp_bus_freeze+0x20/0x20 > [ 59.392532] [<c459c539>] ? ftrace_graph_caller+0x19/0x19 > [ 59.392532] [<c4428659>] ? __device_suspend+0xe9/0x2a0 > [ 59.392532] [<c4429d08>] ? dpm_suspend+0xf8/0x290 > […] The full log from the suspend is attached. The tracing is enabled by the script `analyze_suspend.py` [1], which I call like below. ``` $ sudo ./analyze_suspend.py -config config/suspend-callgraph.cfg \ -filter i915 ``` Suspend and resume with tracing enabled works fine. Please tell me, if you need anything else from my side. Kind regards, Paul [1] https://01.org/suspendresume/ [2] https://github.com/01org/suspendresume/
[toc] | [next] | [standalone]
| From | Steven Rostedt <rostedt@goodmis.org> |
|---|---|
| Date | 2017-03-09 15:50 +0100 |
| Message-ID | <tj7ya-6vj-19@gated-at.bofh.it> |
| In reply to | #1596032 |
On Thu, 9 Mar 2017 13:12:28 +0100 Paul Menzel <pmenzel@molgen.mpg.de> wrote: > Dear Steven, dear Ingo, > > > Hopefully, I am contacting the right people for my issue. > > Suspending a system with Linux 4.9.13 with tracing enabled, it fails > with the screen still enabled, and the LED blinking. Attaching a serial > console to the dock, shows the messages below. I'm betting this is a compiler bug, as that bug that printed is the internal ftrace check for it. (note the bug is only in x86-32 not x86-64) Funny, we are just talking about this bug in another thread, but with a different symptom. Josh, did you say this goes away if you disable optimize for size or does it need to be enabled? -- Steve > > > […] > > [ 59.063238] PM: Syncing filesystems ... done. > > [ 59.197490] Freezing user space processes ... (elapsed 0.002 seconds) done. > > [ 59.207510] Freezing remaining freezable tasks ... (elapsed 0.002 seconds) done. > > [ 59.234169] sd 2:0:0:0: [sda] Synchronizing SCSI cache > > [ 59.240355] sd 2:0:0:0: [sda] Stopping disk > > [ 59.250859] ------------[ cut here ]------------ > > [ 59.255562] WARNING: CPU: 0 PID: 774 at /build/linux-ROBWaj/linux-4.9.13/kernel/trace/trace_functions_graph.c:233 ftrace_return_to_handler+0x1aa/0x1e0 > > [ 59.269228] Bad frame pointer: expected f6919d98, received f6919db0 > > [ 59.269228] from func acpi_pm_device_sleep_wake return to c43b6f9d > > [ 59.281993] Modules linked in: cpufreq_powersave(E) cpufreq_conservative(E) cpufreq_userspace(E) iTCO_wdt(E) arc4(E) iTCO_vendor_support(E) coretemp(E) pcmcia(E) kvm_intel(E) iwl3945(E) kvm(E) iwlegacy(E) mac80211(E) irqbypass(E) i915(E) lpc_ich(E) mfd_core(E) evdev(E) yenta_socket(E) serio_raw(E) snd_hda_codec_analog(E) pcmcia_rsrc(E) cfg80211(E) snd_hda_codec_generic(E) pcmcia_core(E) thinkpad_acpi(E) rng_core(E) snd_hda_intel(E) nvram(E) drm_kms_helper(E) rfkill(E) snd_hda_codec(E) battery(E) snd_hda_core(E) snd_hwdep(E) drm(E) snd_pcm(E) snd_timer(E) snd(E) soundcore(E) video(E) i2c_algo_bit(E) shpchp(E) ac(E) acpi_cpufreq(E) tpm_tis(E) button(E) tpm_tis_core(E) tpm(E) fuse(E) parport_pc(E) ppdev(E) lp(E) parport(E) autofs4(E) ext4(E) crc16(E) jbd2(E) fscrypto(E) mbcache(E) ecb(E) cbc(E) algif_skcipher(E) af_alg(E) dm_crypt(E) dm_mod(E) sr_mod(E) cdrom(E) sg(E) sd_mod(E) ata_generic(E) ehci_pci(E) uhci_hcd(E) ehci_hcd(E) ata_piix(E) ahci(E) libahci(E) firewire_ohci(E) sdhci_pci(E) psmouse(E) e1000e(E) libata(E) usbcore(E) i2c_i801(E) i2c_smbus(E) firewire_core(E) crc_itu_t(E) sdhci(E) mmc_core(E) ptp(E) scsi_mod(E) usb_common(E) pps_core(E) thermal(E) > > [ 59.388749] CPU: 0 PID: 774 Comm: analyze_suspend Tainted: G E 4.9.0-0.bpo.2-686-pae #1 Debian 4.9.13-1~bpo8+1 > > [ 59.392532] Hardware name: LENOVO 636338U/636338U, BIOS CBET4000 4.5-1169-g7129ccb 03/09/2017 > > [ 59.392532] f6919d28 c42ee6ec f6919d3c 00000000 c4067c0a c469d538 f6919d5c 00000306 > > [ 59.392532] c469d4f0 000000e9 c412e95a 000000e9 00000009 c412e95a c4164039 c43b6f9d > > [ 59.392532] 00000002 f6919d48 c4067c76 00000009 00000000 f6919d3c c469d538 f6919d5c > > [ 59.392532] Call Trace: > > [ 59.392532] [<c42ee6ec>] ? dump_stack+0x55/0x79 > > [ 59.392532] [<c4067c0a>] ? __warn+0xea/0x110 > > [ 59.392532] [<c412e95a>] ? ftrace_return_to_handler+0x1aa/0x1e0 > > [ 59.392532] [<c412e95a>] ? ftrace_return_to_handler+0x1aa/0x1e0 > > [ 59.392532] [<c4164039>] ? cgroup_threadgroup_change_end.isra.39+0x1e/0x1e > > [ 59.392532] [<c43b6f9d>] ? pnpacpi_suspend+0x5d/0xe0 > > [ 59.392532] [<c4067c76>] ? warn_slowpath_fmt+0x46/0x60 > > [ 59.392532] [<c412e95a>] ? ftrace_return_to_handler+0x1aa/0x1e0 > > [ 59.392532] [<c43804a0>] ? acpi_pm_device_sleep_wake+0x14/0xa8 > > [ 59.392532] [<c43b6f9d>] ? pnpacpi_suspend+0x5d/0xe0 > > [ 59.392532] [<c43b6f9d>] ? pnpacpi_suspend+0x5d/0xe0 > > [ 59.392532] [<c459c542>] ? return_to_handler+0x9/0xf > > [ 59.392532] [<c459c539>] ? ftrace_graph_caller+0x19/0x19 > > [ 59.392532] [<c43b2e12>] ? pnp_bus_suspend+0x12/0x20 > > [ 59.392532] [<c459c539>] ? ftrace_graph_caller+0x19/0x19 > > [ 59.392532] [<c4427c66>] ? dpm_run_callback+0x46/0x120 > > [ 59.392532] [<c43b2e00>] ? pnp_bus_freeze+0x20/0x20 > > [ 59.392532] [<c459c539>] ? ftrace_graph_caller+0x19/0x19 > > [ 59.392532] [<c4428659>] ? __device_suspend+0xe9/0x2a0 > > [ 59.392532] [<c4429d08>] ? dpm_suspend+0xf8/0x290 > > […] > > The full log from the suspend is attached. > > The tracing is enabled by the script `analyze_suspend.py` [1], which I > call like below. > > ``` > $ sudo ./analyze_suspend.py -config config/suspend-callgraph.cfg \ > -filter i915 > ``` > > Suspend and resume with tracing enabled works fine. > > Please tell me, if you need anything else from my side. > > > Kind regards, > > Paul > > > [1] https://01.org/suspendresume/ > [2] https://github.com/01org/suspendresume/
[toc] | [prev] | [next] | [standalone]
| From | Josh Poimboeuf <jpoimboe@redhat.com> |
|---|---|
| Date | 2017-03-09 17:20 +0100 |
| Message-ID | <tj8Xf-7Er-5@gated-at.bofh.it> |
| In reply to | #1596118 |
On Thu, Mar 09, 2017 at 09:36:30AM -0500, Steven Rostedt wrote: > On Thu, 9 Mar 2017 13:12:28 +0100 > Paul Menzel <pmenzel@molgen.mpg.de> wrote: > > > Dear Steven, dear Ingo, > > > > > > Hopefully, I am contacting the right people for my issue. > > > > Suspending a system with Linux 4.9.13 with tracing enabled, it fails > > with the screen still enabled, and the LED blinking. Attaching a serial > > console to the dock, shows the messages below. > > I'm betting this is a compiler bug, as that bug that printed is the > internal ftrace check for it. (note the bug is only in x86-32 not > x86-64) > > Funny, we are just talking about this bug in another thread, but with a > different symptom. > > Josh, did you say this goes away if you disable optimize for size or > does it need to be enabled? Yeah, assuming it's the same problem, then this is caused by CONFIG_CC_OPTIMIZE_FOR_SIZE. It would be fixed by changing it to CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE. -- Josh
[toc] | [prev] | [next] | [standalone]
| From | Steven Rostedt <rostedt@goodmis.org> |
|---|---|
| Date | 2017-03-09 18:10 +0100 |
| Message-ID | <tj9JE-8bY-25@gated-at.bofh.it> |
| In reply to | #1596177 |
On Thu, 9 Mar 2017 10:16:02 -0600 Josh Poimboeuf <jpoimboe@redhat.com> wrote: > On Thu, Mar 09, 2017 at 09:36:30AM -0500, Steven Rostedt wrote: > > On Thu, 9 Mar 2017 13:12:28 +0100 > > Paul Menzel <pmenzel@molgen.mpg.de> wrote: > > > > > Dear Steven, dear Ingo, > > > > > > > > > Hopefully, I am contacting the right people for my issue. > > > > > > Suspending a system with Linux 4.9.13 with tracing enabled, it fails > > > with the screen still enabled, and the LED blinking. Attaching a serial > > > console to the dock, shows the messages below. > > > > I'm betting this is a compiler bug, as that bug that printed is the > > internal ftrace check for it. (note the bug is only in x86-32 not > > x86-64) > > > > Funny, we are just talking about this bug in another thread, but with a > > different symptom. > > > > Josh, did you say this goes away if you disable optimize for size or > > does it need to be enabled? > > Yeah, assuming it's the same problem, then this is caused by > CONFIG_CC_OPTIMIZE_FOR_SIZE. It would be fixed by changing it to > CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE. > Paul, do you have CONFIG_CC_OPTIMIZE_FOR_SIZE enabled? Can you set it to PERFORMANCE and see if the problem goes away? -- Steve
[toc] | [prev] | [next] | [standalone]
| From | Paul Menzel <pmenzel@molgen.mpg.de> |
|---|---|
| Date | 2017-03-09 21:50 +0100 |
| Message-ID | <tjday-1R7-11@gated-at.bofh.it> |
| In reply to | #1596220 |
On 2017-03-09 17:29, Steven Rostedt wrote: > On Thu, 9 Mar 2017 10:16:02 -0600 > Josh Poimboeuf wrote: > >> On Thu, Mar 09, 2017 at 09:36:30AM -0500, Steven Rostedt wrote: >> > On Thu, 9 Mar 2017 13:12:28 +0100 >> > Paul Menzel wrote: >> > > Hopefully, I am contacting the right people for my issue. >> > > >> > > Suspending a system with Linux 4.9.13 with tracing enabled, it fails >> > > with the screen still enabled, and the LED blinking. Attaching a serial >> > > console to the dock, shows the messages below. >> > >> > I'm betting this is a compiler bug, as that bug that printed is the >> > internal ftrace check for it. (note the bug is only in x86-32 not >> > x86-64) >> > >> > Funny, we are just talking about this bug in another thread, but with a >> > different symptom. >> > >> > Josh, did you say this goes away if you disable optimize for size or >> > does it need to be enabled? >> >> Yeah, assuming it's the same problem, then this is caused by >> CONFIG_CC_OPTIMIZE_FOR_SIZE. It would be fixed by changing it to >> CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE. >> > > Paul, do you have CONFIG_CC_OPTIMIZE_FOR_SIZE enabled? Can you set it > to PERFORMANCE and see if the problem goes away? As far as I can see, the Debian Linux kernel is built with `CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y`. So it might be a different problem? Kind regards, Paul
[toc] | [prev] | [next] | [standalone]
| From | Josh Poimboeuf <jpoimboe@redhat.com> |
|---|---|
| Date | 2017-03-10 00:10 +0100 |
| Message-ID | <tjfm2-3tL-3@gated-at.bofh.it> |
| In reply to | #1596379 |
On Thu, Mar 09, 2017 at 09:43:47PM +0100, Paul Menzel wrote: > On 2017-03-09 17:29, Steven Rostedt wrote: > > On Thu, 9 Mar 2017 10:16:02 -0600 > > Josh Poimboeuf wrote: > > > > > On Thu, Mar 09, 2017 at 09:36:30AM -0500, Steven Rostedt wrote: > > > > On Thu, 9 Mar 2017 13:12:28 +0100 > > > > Paul Menzel wrote: > > > > > > Hopefully, I am contacting the right people for my issue. > > > > > > > > > > Suspending a system with Linux 4.9.13 with tracing enabled, it fails > > > > > with the screen still enabled, and the LED blinking. Attaching a serial > > > > > console to the dock, shows the messages below. > > > > > > > > I'm betting this is a compiler bug, as that bug that printed is the > > > > internal ftrace check for it. (note the bug is only in x86-32 not > > > > x86-64) > > > > > > > > Funny, we are just talking about this bug in another thread, but with a > > > > different symptom. > > > > > > > > Josh, did you say this goes away if you disable optimize for size or > > > > does it need to be enabled? > > > > > > Yeah, assuming it's the same problem, then this is caused by > > > CONFIG_CC_OPTIMIZE_FOR_SIZE. It would be fixed by changing it to > > > CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE. > > > > > > > Paul, do you have CONFIG_CC_OPTIMIZE_FOR_SIZE enabled? Can you set it > > to PERFORMANCE and see if the problem goes away? > > As far as I can see, the Debian Linux kernel is built with > `CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y`. > > So it might be a different problem? Is it a stock Debian kernel? If so, do you have a link where it can be downloaded? -- Josh
[toc] | [prev] | [next] | [standalone]
| From | Paul Menzel <pmenzel@molgen.mpg.de> |
|---|---|
| Date | 2017-03-10 10:00 +0100 |
| Message-ID | <tjoz0-1oL-3@gated-at.bofh.it> |
| In reply to | #1596463 |
Dear Josh, On 03/10/17 00:04, Josh Poimboeuf wrote: > On Thu, Mar 09, 2017 at 09:43:47PM +0100, Paul Menzel wrote: >> On 2017-03-09 17:29, Steven Rostedt wrote: >>> On Thu, 9 Mar 2017 10:16:02 -0600 Josh Poimboeuf wrote: >>> >>>> On Thu, Mar 09, 2017 at 09:36:30AM -0500, Steven Rostedt wrote: >>>>> On Thu, 9 Mar 2017 13:12:28 +0100 Paul Menzel wrote: >> >>>>>> Hopefully, I am contacting the right people for my issue. >>>>>> >>>>>> Suspending a system with Linux 4.9.13 with tracing enabled, it fails >>>>>> with the screen still enabled, and the LED blinking. Attaching a serial >>>>>> console to the dock, shows the messages below. >>>>> >>>>> I'm betting this is a compiler bug, as that bug that printed is the >>>>> internal ftrace check for it. (note the bug is only in x86-32 not >>>>> x86-64) >>>>> >>>>> Funny, we are just talking about this bug in another thread, but with a >>>>> different symptom. >>>>> >>>>> Josh, did you say this goes away if you disable optimize for size or >>>>> does it need to be enabled? >>>> >>>> Yeah, assuming it's the same problem, then this is caused by >>>> CONFIG_CC_OPTIMIZE_FOR_SIZE. It would be fixed by changing it to >>>> CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE. >>> >>> Paul, do you have CONFIG_CC_OPTIMIZE_FOR_SIZE enabled? Can you set it >>> to PERFORMANCE and see if the problem goes away? >> >> As far as I can see, the Debian Linux kernel is built with >> `CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y`. >> >> So it might be a different problem? > > Is it a stock Debian kernel? If so, do you have a link where it can be > downloaded? Sure, hopefully [3] works for you. ``` dpkg -x linux-image-4.9.0-0.bpo.2-686-pae-unsigned_4.9.13-1~bpo8+1_i386.deb target-directory ``` Kind regards, Paul [1] https://packages.debian.org/jessie-backports/linux-image-4.9.0-0.bpo.2-686-pae-unsigned [2] https://packages.debian.org/jessie-backports/i386/linux-image-4.9.0-0.bpo.2-686-pae-unsigned/download [3] http://ftp.us.debian.org/debian/pool/main/l/linux/linux-image-4.9.0-0.bpo.2-686-pae-unsigned_4.9.13-1~bpo8+1_i386.deb [4] https://linux.die.net/man/1/dpkg
[toc] | [prev] | [next] | [standalone]
| From | Josh Poimboeuf <jpoimboe@redhat.com> |
|---|---|
| Date | 2017-03-10 19:20 +0100 |
| Message-ID | <tjxiW-7Ku-41@gated-at.bofh.it> |
| In reply to | #1596715 |
On Fri, Mar 10, 2017 at 09:53:29AM +0100, Paul Menzel wrote: > Dear Josh, > > > On 03/10/17 00:04, Josh Poimboeuf wrote: > > On Thu, Mar 09, 2017 at 09:43:47PM +0100, Paul Menzel wrote: > > > On 2017-03-09 17:29, Steven Rostedt wrote: > > > > On Thu, 9 Mar 2017 10:16:02 -0600 Josh Poimboeuf wrote: > > > > > > > > > On Thu, Mar 09, 2017 at 09:36:30AM -0500, Steven Rostedt wrote: > > > > > > On Thu, 9 Mar 2017 13:12:28 +0100 Paul Menzel wrote: > > > > > > > > > > Hopefully, I am contacting the right people for my issue. > > > > > > > > > > > > > > Suspending a system with Linux 4.9.13 with tracing enabled, it fails > > > > > > > with the screen still enabled, and the LED blinking. Attaching a serial > > > > > > > console to the dock, shows the messages below. > > > > > > > > > > > > I'm betting this is a compiler bug, as that bug that printed is the > > > > > > internal ftrace check for it. (note the bug is only in x86-32 not > > > > > > x86-64) > > > > > > > > > > > > Funny, we are just talking about this bug in another thread, but with a > > > > > > different symptom. > > > > > > > > > > > > Josh, did you say this goes away if you disable optimize for size or > > > > > > does it need to be enabled? > > > > > > > > > > Yeah, assuming it's the same problem, then this is caused by > > > > > CONFIG_CC_OPTIMIZE_FOR_SIZE. It would be fixed by changing it to > > > > > CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE. > > > > > > > > Paul, do you have CONFIG_CC_OPTIMIZE_FOR_SIZE enabled? Can you set it > > > > to PERFORMANCE and see if the problem goes away? > > > > > > As far as I can see, the Debian Linux kernel is built with > > > `CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y`. > > > > > > So it might be a different problem? > > > > Is it a stock Debian kernel? If so, do you have a link where it can be > > downloaded? > > Sure, hopefully [3] works for you. > > ``` > dpkg -x linux-image-4.9.0-0.bpo.2-686-pae-unsigned_4.9.13-1~bpo8+1_i386.deb > target-directory Thanks, that helped. One of the functions on the stack trace has the buggy prologue: acpi_pm_device_sleep_wake: c138048c: 57 push %edi c138048d: 8d 7c 24 08 lea 0x8(%esp),%edi c1380491: 83 e4 f8 and $0xfffffff8,%esp c1380494: ff 77 fc pushl -0x4(%edi) c1380497: 55 push %ebp c1380498: 89 e5 mov %esp,%ebp c138049a: 57 push %edi c138049b: 56 push %esi c138049c: 53 push %ebx c138049d: 83 ec 0c sub $0xc,%esp c13804a0: e8 e7 bf 21 00 call 0xc159c48c (mcount) And the config file indeed has CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y. I found the root cause after a little digging. drivers/acpi/Makefile is setting '-Os' manually: ccflags-y := -Os That line predates git history, so I don't know why it's there, but I'd guess we can probably remove it. I'll submit a fix for it along with the other -maccumulate-outoing-args related patch I was going to do. -- Josh
[toc] | [prev] | [standalone]
Back to top | Article view | linux.kernel
csiph-web