Re: [RFC][PATCH 0/3] perf fixes

From: Jiri Olsa <jolsa@redhat.com>
To: Vince Weaver <vincent.weaver@maine.edu>
Cc: Peter Zijlstra <peterz@infradead.org>,
	mingo@kernel.org, linux-kernel@vger.kernel.org,
	eranian@gmail.com, mark.rutland@arm.com,
	torvalds@linux-foundation.org, tglx@linutronix.de
Subject: Re: [RFC][PATCH 0/3] perf fixes
Date: Mon, 26 Jan 2015 19:34:15 +0100	[thread overview]
Message-ID: <20150126183415.GA7810@krava.brq.redhat.com> (raw)
In-Reply-To: <alpine.DEB.2.11.1501261300570.30598@vincent-weaver-1.umelst.maine.edu>

On Mon, Jan 26, 2015 at 01:03:47PM -0500, Vince Weaver wrote:
> On Mon, 26 Jan 2015, Vince Weaver wrote:
> 
> > I applied this to (just before) 3.19-rc6 and let it run on my 
> > troublemaking Haswell machine overnight.  It is looking good!
> 
> spoke too soon, managed to trigger one of the new warnings you added.
> 
> This is
>         WARN_ON_ONCE(event->ctx != ctx);
> in event_sched_out()

I trigered the same one, should be addressed by the fix Peter
sent in earlier email

jirka

> 
> [42437.159176] ------------[ cut here ]------------
> [42437.164613] WARNING: CPU: 1 PID: 15433 at kernel/events/core.c:1525 event_sched_out.isra.72+0x25e/0x2c0()
> [42437.175338] Modules linked in: fuse x86_pkg_temp_thermal intel_powerclamp intel_rapl iosf_mbi coretemp kvm snd_hda_codec_realtek snd_hda_codec_hdmi snd_hda_codec_generic snd_hda_intel crct10dif_pclmul snd_hda_controller crc32_pclmul ppdev ghash_clmulni_intel iTCO_wdt iTCO_vendor_support aesni_intel aes_x86_64 lpc_ich mfd_core evdev lrw mei_me i915 psmouse snd_hda_codec mei xhci_pci gf128mul i2c_i801 serio_raw xhci_hcd glue_helper snd_hwdep snd_pcm ablk_helper cryptd snd_timer drm_kms_helper parport_pc parport tpm_tis pcspkr snd tpm drm battery video soundcore wmi i2c_algo_bit button processor sg sr_mod sd_mod cdrom ehci_pci ehci_hcd ahci libahci e1000e libata ptp usbcore scsi_mod usb_common pps_core crc32c_intel thermal fan thermal_sys
> [42437.248890] CPU: 1 PID: 15433 Comm: perf_fuzzer Tainted: G        W      3.19.0-rc5+ #125
> [42437.258294] Hardware name: LENOVO 10AM000AUS/SHARKBAY, BIOS FBKT72AUS 01/26/2014
> [42437.266772]  ffffffff81a3f194 ffff8800c83bfbc8 ffffffff816b6741 0000000000000000
> [42437.275427]  0000000000000000 ffff8800c83bfc08 ffffffff8106dcda 01926893541204d2
> [42437.284054]  ffff8800c69a4800 ffff88011ea5ced0 ffff88011ea5ced4 ffff880118ce4000
> [42437.292660] Call Trace:
> [42437.295915]  [<ffffffff816b6741>] dump_stack+0x45/0x57
> [42437.302023]  [<ffffffff8106dcda>] warn_slowpath_common+0x8a/0xc0
> [42437.309080]  [<ffffffff8106ddca>] warn_slowpath_null+0x1a/0x20
> [42437.315950]  [<ffffffff811587ee>] event_sched_out.isra.72+0x25e/0x2c0
> [42437.323445]  [<ffffffff811588c1>] group_sched_out+0x71/0xd0
> [42437.330045]  [<ffffffff8101d90a>] ? native_sched_clock+0x2a/0x90
> [42437.337116]  [<ffffffff81158d2e>] ctx_sched_out+0xee/0x150
> [42437.343610]  [<ffffffff81158dcb>] task_ctx_sched_out+0x3b/0x80
> [42437.350461]  [<ffffffff8115a489>] __perf_install_in_context+0x79/0x1e0
> [42437.358073]  [<ffffffff81154570>] remote_function+0x50/0x60
> [42437.364702]  [<ffffffff810ef53e>] generic_exec_single+0x12e/0x190
> [42437.371828]  [<ffffffff81154520>] ? task_clock_event_add+0x40/0x40
> [42437.379083]  [<ffffffff810ef607>] smp_call_function_single+0x67/0xa0
> [42437.386491]  [<ffffffff81153419>] task_function_call+0x49/0x60
> [42437.393364]  [<ffffffff8115a410>] ? perf_cpu_hrtimer_handler+0x270/0x270
> [42437.401167]  [<ffffffff811549fb>] perf_install_in_context+0x8b/0x100
> [42437.408611]  [<ffffffff8115e082>] SYSC_perf_event_open+0x892/0xc60
> [42437.415841]  [<ffffffff8115e89e>] SyS_perf_event_open+0xe/0x10
> [42437.422680]  [<ffffffff816be6ad>] system_call_fastpath+0x16/0x1b
> [42437.429728] ---[ end trace 963de0bbaca247a8 ]---
>