Message ID | 20221103021822.308586-1-david.e.box@linux.intel.com |
---|---|
Headers |
Return-Path: <linux-kernel-owner@vger.kernel.org> Delivered-To: ouuuleilei@gmail.com Received: by 2002:a5d:6687:0:0:0:0:0 with SMTP id l7csp269230wru; Wed, 2 Nov 2022 19:20:07 -0700 (PDT) X-Google-Smtp-Source: AMsMyM69tVNuyHw3xxySeGsqPZd3mWNI1oc/HG+0qJV8V+WvLmRVl349DcTlnHnXTLWrTVy4lGzP X-Received: by 2002:a63:e045:0:b0:46f:e244:3136 with SMTP id n5-20020a63e045000000b0046fe2443136mr12125950pgj.95.1667442006781; Wed, 02 Nov 2022 19:20:06 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1667442006; cv=none; d=google.com; s=arc-20160816; b=ytg1DGu9JTwmdw+yUveTL2Tk401nWBSzTuk6nom4K8z/0uOahhzoJvwRXdIxFzMlIe ir2yvnvDMSA7AMKvJOS45dYTR9DfNGzxptOkGPmWO9lJ8d9CRUL+AAvQDYOqKU2TUzZU ZBv+NVM17u48LGZf3rO74GIWPb/mWlNNzvnlXzh+ZapmU67/Go6o9JDBwHKwDP8+VkJI J3kFBWpCAKA2MFS7eb1y90tBiZdsFSxUFtY9Z78ND4VCq5xrj8m8MNzzGkbvXOt+xFG2 3Yz2OVKOs2Qm3YMwSeCyAbCEqstyhucU0qoVjXoO9AUVNo1bx0pgjPcghB1laFCGk7a6 gQyg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :message-id:date:subject:cc:to:from:dkim-signature; bh=PXwRmcLRP+igmNslyOfdfk5gyKM+Z47VLujOLTJoUf0=; b=LfoVqQpoGCCknAnQ79+aD7wMAawSKKtCnczC38EtM+0A4z6HOeTrlotEPNmZxoSj9S BVzClPbHT0BL0srz6sAeMSbp4F4hRAVJNz5wr21MjOZ6Ehr1wD4acgr0CWNLAwX3RfVs ZhXCT3pRNF9mH39KaoSVbXUjKCaYBVcd6h3K/DiKXvg4fmfc9OMrBZBr9EdH+9l/jnCN oXX6zTrAGr8GaPmc7uArH5w766RJGAW60NClcBOZLrCnMAKl+3H+wh6aAzxi9mGkD4oz D2kfp+tKBuhaLQvVvb9M2IGep+4G2Cq/LC+w4ulOswElEx+LgZwEyvMHyxuZ3WjesBIy 7KAQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@intel.com header.s=Intel header.b=DMcLu2Bj; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=intel.com Received: from out1.vger.email (out1.vger.email. [2620:137:e000::1:20]) by mx.google.com with ESMTP id g27-20020a63111b000000b00439cc644c03si18785425pgl.228.2022.11.02.19.19.54; Wed, 02 Nov 2022 19:20:06 -0700 (PDT) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20; Authentication-Results: mx.google.com; dkim=pass header.i=@intel.com header.s=Intel header.b=DMcLu2Bj; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=intel.com Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229971AbiKCCS0 (ORCPT <rfc822;yves.mi.zy@gmail.com> + 99 others); Wed, 2 Nov 2022 22:18:26 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:56134 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229436AbiKCCSY (ORCPT <rfc822;linux-kernel@vger.kernel.org>); Wed, 2 Nov 2022 22:18:24 -0400 Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 20F35E81; Wed, 2 Nov 2022 19:18:23 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1667441903; x=1698977903; h=from:to:cc:subject:date:message-id:mime-version: content-transfer-encoding; bh=dRTGogFr6yFQWzAu44s2Shz3Tuu+kZ6YaOpo+8VRwtE=; b=DMcLu2BjDmudMN0UTyyA6FzOfZelhaQ8aXzibcjvThwM3TFZjGWBNUKD wD87ecQD9wgkVeT9M0zQMQHf/V4yToaol98pmgAsEtm240ZjfYRyDfQly +NXTn3/83rPUqYemS0WbI7mo8eLfSBqFbrU+1UlW3xI6xLFAjkgRLVzcD lmBHge6U5cuhjmdnCeRUWNDjVAsqPDdObXWhbzy9XAVtP9ErHwqBTLJIf 36fdHDJUNSglpacZiiJMinGpULwMqK6jKiWcXilzqmkjsqPfVl2BYXgG5 oPLGYSWzARxBuTWWDlcWEmjHb9o7CLwNLG1Z8LkoRGkou1I6HEtWgummX A==; X-IronPort-AV: E=McAfee;i="6500,9779,10519"; a="395875409" X-IronPort-AV: E=Sophos;i="5.95,235,1661842800"; d="scan'208";a="395875409" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Nov 2022 19:18:22 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6500,9779,10519"; a="759771646" X-IronPort-AV: E=Sophos;i="5.95,235,1661842800"; d="scan'208";a="759771646" Received: from linux.intel.com ([10.54.29.200]) by orsmga004.jf.intel.com with ESMTP; 02 Nov 2022 19:18:22 -0700 Received: from debox1-desk4.intel.com (unknown [10.212.195.54]) by linux.intel.com (Postfix) with ESMTP id 38146580D42; Wed, 2 Nov 2022 19:18:22 -0700 (PDT) From: "David E. Box" <david.e.box@linux.intel.com> To: nirmal.patel@linux.intel.com, jonathan.derrick@linux.dev, lorenzo.pieralisi@arm.com, hch@infradead.org, kw@linux.com, robh@kernel.org, bhelgaas@google.com, david.e.box@linux.intel.com, michael.a.bottini@intel.com, rafael@kernel.org, me@adhityamohan.in Cc: linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH V8 0/4] PCI: vmd: Enable PCIe ASPM and LTR on select hardware Date: Wed, 2 Nov 2022 19:18:18 -0700 Message-Id: <20221103021822.308586-1-david.e.box@linux.intel.com> X-Mailer: git-send-email 2.25.1 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=-5.3 required=5.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_EF,RCVD_IN_DNSWL_MED,SPF_HELO_NONE, SPF_NONE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: <linux-kernel.vger.kernel.org> X-Mailing-List: linux-kernel@vger.kernel.org X-getmail-retrieved-from-mailbox: =?utf-8?q?INBOX?= X-GMAIL-THRID: =?utf-8?q?1748439669456882656?= X-GMAIL-MSGID: =?utf-8?q?1748439669456882656?= |
Series |
PCI: vmd: Enable PCIe ASPM and LTR on select hardware
|
|
Message
David E. Box
Nov. 3, 2022, 2:18 a.m. UTC
This series adds a work around for enabling PCIe ASPM and for setting PCIe LTR values on VMD reserved root ports on select platforms. While configuration of these capabilities is usually done by BIOS, on these platforms these capabilities will not be configured because the ports are not visible to BIOS. This was part of an initial design that expected the driver to completely handle the ports, including power management. However on Linux those ports are still managed by the PCIe core, which has the expectation that they adhere to device standards including BIOS configuration, leading to this problem. The target platforms are Tiger Lake, Alder Lake, and Raptor Lake though the latter has already implemented support for configuring the LTR values. Meteor Lake is expected add BIOS ASPM support, eliminating the future need for this work around. Note, the driver programs the LTRs because BIOS would also normally do this for devices that do not set them by default. Without this, SoC power management would be blocked on those platform. This SoC specific value is the maximum latency required to allow the SoC to enter the deepest power state. This patch addresses the following open bugzillas on VMD enabled laptops that cannot enter low power states. Link: https://bugzilla.kernel.org/show_bug.cgi?id=212355 Link: https://bugzilla.kernel.org/show_bug.cgi?id=215063 Link: https://bugzilla.kernel.org/show_bug.cgi?id=213717 David E. Box (3): PCI: vmd: Use PCI_VDEVICE in device list PCI: vmd: Create feature grouping for client products PCI: vmd: Add quirk to configure PCIe ASPM and LTR Michael Bottini (1): PCI/ASPM: Add pci_enable_link_state() drivers/pci/controller/vmd.c | 96 ++++++++++++++++++++++++++---------- drivers/pci/pcie/aspm.c | 54 ++++++++++++++++++++ include/linux/pci.h | 7 +++ 3 files changed, 131 insertions(+), 26 deletions(-) base-commit: 247f34f7b80357943234f93f247a1ae6b6c3a740
Comments
Hi David, On 11/3/22 10:18, David E. Box wrote: > This series adds a work around for enabling PCIe ASPM and for setting PCIe > LTR values on VMD reserved root ports on select platforms. While > configuration of these capabilities is usually done by BIOS, on these > platforms these capabilities will not be configured because the ports are > not visible to BIOS. This was part of an initial design that expected the > driver to completely handle the ports, including power management. However > on Linux those ports are still managed by the PCIe core, which has the > expectation that they adhere to device standards including BIOS > configuration, leading to this problem. > > The target platforms are Tiger Lake, Alder Lake, and Raptor Lake though the > latter has already implemented support for configuring the LTR values. > Meteor Lake is expected add BIOS ASPM support, eliminating the future need > for this work around. It appears to me that this patch series works only on Tiger Lake. We have tried to revert our current work-arounds in Ubuntu kernels generic-5.15/oem-5.17/oem-6.0/unstable-6.1 and apply this series, the prebuilt kernels can be found in: https://launchpad.net/~vicamo/+archive/ubuntu/ppa-1996620 However, only TGL can still enter PC10 as before. ADL-M, RPL platforms will stay in PC3 with vmd LTR set, but ASPM disabled. i915 RC6 blocked, too: $ sudo cat /sys/kernel/debug/dri/ 0/i915_dmc_info ... DC3CO count: 0 DC3 -> DC5 count: 100 DC5 -> DC6 count: 0 > Note, the driver programs the LTRs because BIOS would also normally do this > for devices that do not set them by default. Without this, SoC power > management would be blocked on those platform. This SoC specific value is > the maximum latency required to allow the SoC to enter the deepest power > state. > > This patch addresses the following open bugzillas on VMD enabled laptops > that cannot enter low power states. > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=212355 > Link: https://bugzilla.kernel.org/show_bug.cgi?id=215063 > Link: https://bugzilla.kernel.org/show_bug.cgi?id=213717 > > David E. Box (3): > PCI: vmd: Use PCI_VDEVICE in device list > PCI: vmd: Create feature grouping for client products > PCI: vmd: Add quirk to configure PCIe ASPM and LTR > > Michael Bottini (1): > PCI/ASPM: Add pci_enable_link_state() > > drivers/pci/controller/vmd.c | 96 ++++++++++++++++++++++++++---------- > drivers/pci/pcie/aspm.c | 54 ++++++++++++++++++++ > include/linux/pci.h | 7 +++ > 3 files changed, 131 insertions(+), 26 deletions(-) > > > base-commit: 247f34f7b80357943234f93f247a1ae6b6c3a740 Regards, You-Sheng Yang
Hi You-Sheng, On Wed, 2022-11-23 at 18:27 +0800, You-Sheng Yang wrote: > Hi David, > > On 11/3/22 10:18, David E. Box wrote: > > This series adds a work around for enabling PCIe ASPM and for setting PCIe > > LTR values on VMD reserved root ports on select platforms. While > > configuration of these capabilities is usually done by BIOS, on these > > platforms these capabilities will not be configured because the ports are > > not visible to BIOS. This was part of an initial design that expected the > > driver to completely handle the ports, including power management. However > > on Linux those ports are still managed by the PCIe core, which has the > > expectation that they adhere to device standards including BIOS > > configuration, leading to this problem. > > > > The target platforms are Tiger Lake, Alder Lake, and Raptor Lake though the > > latter has already implemented support for configuring the LTR values. > > Meteor Lake is expected add BIOS ASPM support, eliminating the future need > > for this work around. > > > It appears to me that this patch series works only on Tiger Lake. We > have tried to revert our current work-arounds in Ubuntu kernels > generic-5.15/oem-5.17/oem-6.0/unstable-6.1 and apply this series, the > prebuilt kernels can be found in: > > https://launchpad.net/~vicamo/+archive/ubuntu/ppa-1996620 > > However, only TGL can still enter PC10 as before. > > > ADL-M, RPL platforms will stay in PC3 with vmd LTR set, but ASPM > disabled. For the patch to work BIOS must allow the OS to control ASPM. If this is not the case then you will see the message "ACPI FADT declares the system doesn't support PCIe ASPM, so disable it". Please check for this on the systems that don't work. If so the only option is a BIOS change to enable it. David > i915 RC6 blocked, too: > > $ sudo cat /sys/kernel/debug/dri/ > > 0/i915_dmc_info > ... > DC3CO count: 0 > DC3 -> DC5 count: 100 > DC5 -> DC6 count: 0 > > > > Note, the driver programs the LTRs because BIOS would also normally do this > > for devices that do not set them by default. Without this, SoC power > > management would be blocked on those platform. This SoC specific value is > > the maximum latency required to allow the SoC to enter the deepest power > > state. > > > > This patch addresses the following open bugzillas on VMD enabled laptops > > that cannot enter low power states. > > > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=212355 > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=215063 > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=213717 > > > > David E. Box (3): > > PCI: vmd: Use PCI_VDEVICE in device list > > PCI: vmd: Create feature grouping for client products > > PCI: vmd: Add quirk to configure PCIe ASPM and LTR > > > > Michael Bottini (1): > > PCI/ASPM: Add pci_enable_link_state() > > > > drivers/pci/controller/vmd.c | 96 ++++++++++++++++++++++++++---------- > > drivers/pci/pcie/aspm.c | 54 ++++++++++++++++++++ > > include/linux/pci.h | 7 +++ > > 3 files changed, 131 insertions(+), 26 deletions(-) > > > > > > base-commit: 247f34f7b80357943234f93f247a1ae6b6c3a740 > > > Regards, > You-Sheng Yang >
On Thu, Nov 24, 2022 at 12:09 AM David E. Box <david.e.box@linux.intel.com> wrote: > > Hi You-Sheng, > > On Wed, 2022-11-23 at 18:27 +0800, You-Sheng Yang wrote: > > Hi David, > > > > On 11/3/22 10:18, David E. Box wrote: > > > This series adds a work around for enabling PCIe ASPM and for setting PCIe > > > LTR values on VMD reserved root ports on select platforms. While > > > configuration of these capabilities is usually done by BIOS, on these > > > platforms these capabilities will not be configured because the ports are > > > not visible to BIOS. This was part of an initial design that expected the > > > driver to completely handle the ports, including power management. However > > > on Linux those ports are still managed by the PCIe core, which has the > > > expectation that they adhere to device standards including BIOS > > > configuration, leading to this problem. > > > > > > The target platforms are Tiger Lake, Alder Lake, and Raptor Lake though the > > > latter has already implemented support for configuring the LTR values. > > > Meteor Lake is expected add BIOS ASPM support, eliminating the future need > > > for this work around. > > > > > > It appears to me that this patch series works only on Tiger Lake. We > > have tried to revert our current work-arounds in Ubuntu kernels > > generic-5.15/oem-5.17/oem-6.0/unstable-6.1 and apply this series, the > > prebuilt kernels can be found in: > > > > https://launchpad.net/~vicamo/+archive/ubuntu/ppa-1996620 > > > > However, only TGL can still enter PC10 as before. > > > > > > ADL-M, RPL platforms will stay in PC3 with vmd LTR set, but ASPM > > disabled. > > For the patch to work BIOS must allow the OS to control ASPM. If this is not the > case then you will see the message "ACPI FADT declares the system doesn't > support PCIe ASPM, so disable it". Please check for this on the systems that > don't work. If so the only option is a BIOS change to enable it. Thank you. It's exactly what you said. The ADL-M/RPL platforms I have do not support OS PCIe ASPM. > David > > > i915 RC6 blocked, too: > > > > $ sudo cat /sys/kernel/debug/dri/ > > > > 0/i915_dmc_info > > ... > > DC3CO count: 0 > > DC3 -> DC5 count: 100 > > DC5 -> DC6 count: 0 > > > > > > > Note, the driver programs the LTRs because BIOS would also normally do this > > > for devices that do not set them by default. Without this, SoC power > > > management would be blocked on those platform. This SoC specific value is > > > the maximum latency required to allow the SoC to enter the deepest power > > > state. > > > > > > This patch addresses the following open bugzillas on VMD enabled laptops > > > that cannot enter low power states. > > > > > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=212355 > > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=215063 > > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=213717 > > > > > > David E. Box (3): > > > PCI: vmd: Use PCI_VDEVICE in device list > > > PCI: vmd: Create feature grouping for client products > > > PCI: vmd: Add quirk to configure PCIe ASPM and LTR > > > > > > Michael Bottini (1): > > > PCI/ASPM: Add pci_enable_link_state() > > > > > > drivers/pci/controller/vmd.c | 96 ++++++++++++++++++++++++++---------- > > > drivers/pci/pcie/aspm.c | 54 ++++++++++++++++++++ > > > include/linux/pci.h | 7 +++ > > > 3 files changed, 131 insertions(+), 26 deletions(-) > > > > > > > > > base-commit: 247f34f7b80357943234f93f247a1ae6b6c3a740 > > > > > > Regards, > > You-Sheng Yang > > >
On Wed, 2022-11-02 at 19:18 -0700, David E. Box wrote: > This series adds a work around for enabling PCIe ASPM and for setting > PCIe > LTR values on VMD reserved root ports on select platforms. While > configuration of these capabilities is usually done by BIOS, on these > platforms these capabilities will not be configured because the ports > are > not visible to BIOS. This was part of an initial design that expected > the > driver to completely handle the ports, including power management. > However > on Linux those ports are still managed by the PCIe core, which has > the > expectation that they adhere to device standards including BIOS > configuration, leading to this problem. > > The target platforms are Tiger Lake, Alder Lake, and Raptor Lake > though the > latter has already implemented support for configuring the LTR > values. > Meteor Lake is expected add BIOS ASPM support, eliminating the future > need > for this work around. > > Note, the driver programs the LTRs because BIOS would also normally > do this > for devices that do not set them by default. Without this, SoC power > management would be blocked on those platform. This SoC specific > value is > the maximum latency required to allow the SoC to enter the deepest > power > state. > > This patch addresses the following open bugzillas on VMD enabled > laptops > that cannot enter low power states. > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=212355 > Link: https://bugzilla.kernel.org/show_bug.cgi?id=215063 > Link: https://bugzilla.kernel.org/show_bug.cgi?id=213717 > > David E. Box (3): > PCI: vmd: Use PCI_VDEVICE in device list > PCI: vmd: Create feature grouping for client products > PCI: vmd: Add quirk to configure PCIe ASPM and LTR > > Michael Bottini (1): > PCI/ASPM: Add pci_enable_link_state() > > drivers/pci/controller/vmd.c | 96 ++++++++++++++++++++++++++-------- > -- > drivers/pci/pcie/aspm.c | 54 ++++++++++++++++++++ > include/linux/pci.h | 7 +++ > 3 files changed, 131 insertions(+), 26 deletions(-) > > > base-commit: 247f34f7b80357943234f93f247a1ae6b6c3a740 I'd like to confirm that this patch series solves the VMD power issues present on the ASUS ROG M16 (GU603) laptop range (PCI dev ID = 467f). The difference is quite drastic.
On Wed, 2022-12-07 at 22:05 +1300, Luke Jones wrote: > On Wed, 2022-11-02 at 19:18 -0700, David E. Box wrote: > > This series adds a work around for enabling PCIe ASPM and for setting > > PCIe > > LTR values on VMD reserved root ports on select platforms. While > > configuration of these capabilities is usually done by BIOS, on these > > platforms these capabilities will not be configured because the ports > > are > > not visible to BIOS. This was part of an initial design that expected > > the > > driver to completely handle the ports, including power management. > > However > > on Linux those ports are still managed by the PCIe core, which has > > the > > expectation that they adhere to device standards including BIOS > > configuration, leading to this problem. > > > > The target platforms are Tiger Lake, Alder Lake, and Raptor Lake > > though the > > latter has already implemented support for configuring the LTR > > values. > > Meteor Lake is expected add BIOS ASPM support, eliminating the future > > need > > for this work around. > > > > Note, the driver programs the LTRs because BIOS would also normally > > do this > > for devices that do not set them by default. Without this, SoC power > > management would be blocked on those platform. This SoC specific > > value is > > the maximum latency required to allow the SoC to enter the deepest > > power > > state. > > > > This patch addresses the following open bugzillas on VMD enabled > > laptops > > that cannot enter low power states. > > > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=212355 > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=215063 > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=213717 > > > > David E. Box (3): > > PCI: vmd: Use PCI_VDEVICE in device list > > PCI: vmd: Create feature grouping for client products > > PCI: vmd: Add quirk to configure PCIe ASPM and LTR > > > > Michael Bottini (1): > > PCI/ASPM: Add pci_enable_link_state() > > > > drivers/pci/controller/vmd.c | 96 ++++++++++++++++++++++++++-------- > > -- > > drivers/pci/pcie/aspm.c | 54 ++++++++++++++++++++ > > include/linux/pci.h | 7 +++ > > 3 files changed, 131 insertions(+), 26 deletions(-) > > > > > > base-commit: 247f34f7b80357943234f93f247a1ae6b6c3a740 > > I'd like to confirm that this patch series solves the VMD power issues > present on the ASUS ROG M16 (GU603) laptop range (PCI dev ID = 467f). > > The difference is quite drastic. > Thanks for testing this Luke. David