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
