From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933463AbcJTF2j (ORCPT ); Thu, 20 Oct 2016 01:28:39 -0400 Received: from mga03.intel.com ([134.134.136.65]:2153 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932719AbcJTF2i (ORCPT ); Thu, 20 Oct 2016 01:28:38 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.31,517,1473145200"; d="scan'208";a="21945040" Message-ID: <1476941325.2098.8.camel@intel.com> Subject: Re: Regression in intel_powerclamp, due to cpu whitelist removal From: Zhang Rui To: Jacob Pan , Alok Kataria Cc: "linux-kernel@vger.kernel.org" , "Ernst, Eric" , "Rafael J. Wysocki" Date: Thu, 20 Oct 2016 13:28:45 +0800 In-Reply-To: <20161019204530.3d2ec1d5@jacob-builder> References: <2FF1D5AB-46C6-4BEC-A5A7-EC9C16A99919@vmware.com> <20161019204530.3d2ec1d5@jacob-builder> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.18.5.2-0ubuntu3 Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 2016-10-19 at 20:45 -0700, Jacob Pan wrote: > On Tue, 18 Oct 2016 14:20:49 +0000 > Alok Kataria wrote: > > > > > Hi Jacob, Zhang,  > > > > One of your recent commit "thermal/powerclamp: remove cpu > > whitelist” [1], has caused a regression in the kernel.  > > > > That commit changed powerclamp_probe from requiring all of the > > following features: > > > > X86_FEATURE_NONSTOP_TSC > > X86_FEATURE_CONSTANT_TSC > > X86_FEATURE_MWAIT > > X86_FEATURE_ARAT            > > > > to *any* of them.  The problem is clamp_thread still wants to use > > mwait_idle_with_hints even if the CPU doesn't support it.  > > > Hi Alok, > > You are right, it should be AND not OR. >   > +Eric who has a patch to address this. > > https://patchwork.kernel.org/patch/9365005/ > > Rui/Rafael, > > Could you consider this as an urgent fix? > yeah, will include this for next -rc. And cc stable v4.7+. thanks, rui > Jacob > > > > This was reported by our users when running ubuntu 16.10 > > (4.8.0-22-generic) inside a VMware VM, though as mentioned above I > > don’t think it is specific to our platform. We have seen kernel > > panics due to invalid opcode because of this. Below is the stack > > trace for your reference.  > > > > [    5.736416] invalid opcode: 0000 [#1] SMP > > [    5.736455] Modules linked in: vmw_vsock_vmci_transport vsock > > vmw_balloon intel_powerclamp coretemp crct10dif_pclmul crc32_pclmul > > ghash_clmulni_intel aesni_intel aes_x86_64 lrw glue_helper > > ablk_helper cryptd intel_rapl_perf input_leds joydev serio_raw > > snd_ens1371 snd_ac97_codec gameport ac97_bus snd_pcm snd_seq_midi > > snd_seq_midi_event snd_rawmidi snd_seq snd_seq_device snd_timer snd > > soundcore i2c_piix4 shpchp vmw_vmci nfit floppy(+) mac_hid > > parport_pc > > ppdev lp parport ip_tables x_tables autofs4 hid_generic usbhid hid > > ahci libahci e1000 mptspi mptscsih psmouse mptbase vmwgfx > > scsi_transport_spi ttm drm_kms_helper syscopyarea sysfillrect > > sysimgblt fb_sys_fops drm pata_acpi fjes [    5.744370] CPU: 1 PID: > > 912 Comm: kidle_inject/1 Not tainted 4.8.0-22-generic #24-Ubuntu > > [    5.744373] Hardware name: VMware, Inc. VMware Virtual > > Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 > > [    5.744375] task: ffff9658f7a663c0 task.stack: ffff9658fa908000 > > [    5.744378] RIP: 0010:[]  [] > > clamp_thread+0x2b8/0x5d0 [intel_powerclamp] [    5.744380] RSP: > > 0018:ffff9658fa90be00  EFLAGS: 00010246 [    5.744383] RAX: > > ffff9658fa908008 RBX: 00000000fffee0a6 RCX: 0000000000000000 > > [    5.744386] RDX: 0000000000000000 RSI: 0000000000000246 RDI: > > 0000000000000246 [    5.744388] RBP: ffff9658fa90bec0 R08: > > ffff9658fa908000 R09: 0000000000000000 [    5.744391] R10: > > 000000000001cbf7 R11: 0000000000000000 R12: ffffffff8db581a0 > > [    5.744393] R13: ffff9658fa908000 R14: 0000000000000000 R15: > > ffff9658fa908000 [    5.744396] FS:  0000000000000000(0000) > > GS:ffff9658fc640000(0000) knlGS:0000000000000000 [    5.744398] CS: > > 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [    5.744401] CR2: > > 00007ffa6cc262e8 CR3: 000000003ab3b000 CR4: 00000000001406e0 > > [    5.744403] Stack: [    5.744406]  0000000000000001 > > ffff9658f7a66dc0 ffff9658fc659200 00000000e878d638 [    5.744409] > > 0000000000000001 00000002fc659200 0000000000000001 ffff9658fa908008 > > [    5.744411]  0000000000000000 ffff9658fc64fea8 00000000fffee0a6 > > ffffffffc05720a0 [    5.744414] Call Trace: [    5.744416] > > [] ? pkg_state_counter+0xa0/0xa0 > > [intel_powerclamp] > > [    5.744419]  [] ? > > powerclamp_set_cur_state+0x170/0x170 [intel_powerclamp] > > [    5.744421]  [] ? > > powerclamp_set_cur_state+0x170/0x170 [intel_powerclamp] > > [    5.744424]  [] kthread+0xd8/0xf0 > > [    5.744427]  [] ret_from_fork+0x1f/0x40 > > [    5.744429]  [] ? > > kthread_create_on_node+0x1e0/0x1e0 [    5.744432] Code: cc e9 ba 00 > > 00 00 eb 19 0f 1f 00 0f ae f0 65 48 8b 04 25 04 69 01 00 0f ae b8 > > 08 > > c0 ff ff 0f ae f0 31 d2 48 8b 44 24 38 48 89 d1 <0f> 01 c8 49 8b 45 > > 08 a8 08 75 0b b9 01 00 00 00 4c 89 f0 0f 01 [    5.744434] RIP > > [] clamp_thread+0x2b8/0x5d0 [intel_powerclamp] > > [    5.744437]  RSP [    5.744440] invalid > > opcode: > > 0000 [#2] SMP [    5.744452] ---[ end trace cf659c4076bf2804 ]--- > > > > Looking at the instruction at the RIP shows that > > the kernel attempted to execute “monitor” instruction.  > > > >  8b8:   0f 01 c8                monitor %rax,%rcx,%rdx > >  8bb:   49 8b 45 08             mov    0x8(%r13),%rax > > > > To fix this, I think you should restore the explicit feature check > > “if block” that was removed in the above mentioned commit. Can you > > please look at this ? > > > > Thanks, > > Alok > > > > > > [1] b721ca0d192754deccb89fb01c77e41e6fd91ad9 > > https://github.com/torvalds/linux/commit/b721ca0d192754deccb89fb01c > > 77e41e6fd91ad9,  > > > [Jacob Pan]