Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753531AbZJCF4t (ORCPT ); Sat, 3 Oct 2009 01:56:49 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753473AbZJCF4s (ORCPT ); Sat, 3 Oct 2009 01:56:48 -0400 Received: from vms173009pub.verizon.net ([206.46.173.9]:44946 "EHLO vms173009pub.verizon.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752996AbZJCF4r (ORCPT ); Sat, 3 Oct 2009 01:56:47 -0400 Date: Sat, 03 Oct 2009 01:56:32 -0400 (EDT) From: Len Brown X-X-Sender: lenb@localhost.localdomain To: Linus Torvalds Cc: Andrew Morton , Linux Kernel Mailing List , linux-acpi@vger.kernel.org, Peter Zijlstra , Shaohua Li , Vaidyanathan Srinivasan Subject: [git pull request] ACPI Processor Aggregator Driver for 2.6.32-rc1 Message-id: User-Agent: Alpine 2.00 (LFD 1167 2008-08-23) MIME-version: 1.0 Content-type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4667 Lines: 121 Hi Linus, please pull from: git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git acpi-pad This will add the ACPI Processor Aggregator Driver to the kernel. acpi_pad implements a new ACPI feature where the baseboard management controller can ask Linux to force busy processors to stay idle. The BMC does this under dire electrical or thermal conditions after it has already lowered the P-state to low frequencey mode on all processors, yet the emergency persists. This offline technique is used before employing even more invasive measures, such as taking T-states down to 1/8th of LFM, or powering-off the server completely. This driver will have no effect on the installed base, no no old systems implement this new feature. However, this simle driver in Linux will be useful as this feature is deployed by OEMs on new hardware. As I mentioned previously, this is an ACPI patch, not a scheduler patch. PeterZ is hoping to implement a more sophisticated method for forcing idle time in the system with the scheduler, and when that is available, I'll be delighted to update this driver to invoke it. thanks! -- Len Brown Intel Open Source Technology Center ps. individual patches are available on linux-acpi@vger.kernel.org and a consolidated plain patch is available here: http://ftp.kernel.org/pub/linux/kernel/people/lenb/acpi/patches/2.6.31/acpi-acpi-pad-20090521-2.6.31-rc4.diff.gz MAINTAINERS | 8 + drivers/acpi/Kconfig | 12 + drivers/acpi/Makefile | 2 + drivers/acpi/acpi_pad.c | 514 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 536 insertions(+), 0 deletions(-) create mode 100644 drivers/acpi/acpi_pad.c through these commits: Len Brown (1): acpi_pad: build only on X86 Shaohua Li (1): ACPI: create Processor Aggregator Device driver with this log: commit d91f79ebc3191b15dbe385925af4840f4e68df77 Author: Len Brown Date: Sun Sep 27 02:35:55 2009 -0400 acpi_pad: build only on X86 X86_FEATURE_MWAIT doesn't exist on ia64... Signed-off-by: Len Brown commit 8e0af5141ab950b78b3ebbfaded5439dcf8b3a8d Author: Shaohua Li Date: Mon Jul 27 18:11:02 2009 -0400 ACPI: create Processor Aggregator Device driver ACPI 4.0 created the logical "processor aggregator device" as a mechinism for platforms to ask the OS to force otherwise busy processors to enter (power saving) idle. The intent is to lower power consumption to ride-out transient electrical and thermal emergencies, rather than powering off the server. On platforms that can save more power/performance via P-states, the platform will first exhaust P-states before forcing idle. However, the relative benefit of P-states vs. idle states is platform dependent, and thus this driver need not know or care about it. This driver does not use the kernel's CPU hot-plug mechanism because after the transient emergency is over, the system must be returned to its normal state, and hotplug would permanently break both cpusets and binding. So to force idle, the driver creates a power saving thread. The scheduler will migrate the thread to the preferred CPU. The thread has max priority and has SCHED_RR policy, so it can occupy one CPU. To save power, the thread will invoke the deep C-state entry instructions. To avoid starvation, the thread will sleep 5% of the time time for every second (current RT scheduler has threshold to avoid starvation, but if other CPUs are idle, the CPU can borrow CPU timer from other, which makes the mechanism not work here) Vaidyanathan Srinivasan has proposed scheduler enhancements to allow injecting idle time into the system. This driver doesn't depend on those enhancements, but could cut over to them when they are available. Peter Z. does not favor upstreaming this driver until the those scheduler enhancements are in place. However, we favor upstreaming this driver now because it is useful now, and can be enhanced over time. Signed-off-by: Shaohua Li NACKed-by: Peter Zijlstra Cc: Vaidyanathan Srinivasan Signed-off-by: Len Brown -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/