intel_idle for 2.6.32.stable is available in git: git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6.git idle-release and also as a plain patch: http://ftp.kernel.org/pub/linux/kernel/people/lenb/idle/patches/2.6.32/idle-release-2.6.32.25.diff.gz The patch series is summarized below. cheers, -Len Brown, Intel Open Source Technology Center MAINTAINERS | 7 + arch/x86/include/asm/mwait.h | 15 ++ arch/x86/kernel/acpi/cstate.c | 11 +- drivers/Makefile | 2 +- drivers/acpi/acpi_pad.c | 7 +- drivers/acpi/processor_core.c | 15 +- drivers/cpuidle/cpuidle.c | 43 ++++- drivers/cpuidle/cpuidle.h | 1 - drivers/cpuidle/driver.c | 16 ++- drivers/cpuidle/governors/menu.c | 23 ++- drivers/cpuidle/sysfs.c | 5 +- drivers/idle/Kconfig | 10 + drivers/idle/Makefile | 1 + drivers/idle/intel_idle.c | 448 ++++++++++++++++++++++++++++++++++++++ include/linux/cpuidle.h | 13 +- 15 files changed, 575 insertions(+), 42 deletions(-) create mode 100644 arch/x86/include/asm/mwait.h create mode 100644 drivers/idle/intel_idle.c through these commits: Ai Li (1): cpuidle: extend cpuidle and menu governor to handle dynamic states Arjan van de Ven (1): intel_idle: recognize Lincroft Atom Processor H. Peter Anvin (1): x86, mwait: Move mwait constants to a common header file Len Brown (15): cpuidle: fail to register if !CONFIG_CPU_IDLE cpuidle: add cpuidle_unregister_driver() error check cpuidle: make cpuidle_curr_driver static ACPI: allow a native cpuidle driver to displace ACPI intel_idle: native hardware cpuidle driver for latest Intel processors intel_idle: delete substates DEBUG modparam intel_idle: delete power_policy modparam, and choose substate functions intel_idle: add support for Westmere-EX intel_idle: disable module support intel_idle: no longer EXPERIMENTAL intel_idle: enable Atom C6 intel_idle: simplify test for leave_mm() intel_idle: delete bogus data from cpuidle_state.power_usage intel_idle: add initial Sandy Bridge support intel_idle: do not use the LAPIC timer for ATOM C2 Suresh Siddha (1): intel_idle: Voluntary leave_mm before entering deeper Thomas Weber (1): intel_idle: Change mode 755 => 644 with this log: commit 4a72ecc67d0d722ad14516b22e0761150ea8201f Author: Len Brown <len.brown@xxxxxxxxx> Date: Sat Oct 23 23:25:53 2010 -0400 intel_idle: do not use the LAPIC timer for ATOM C2 If we use the LAPIC timer during ATOM C2 on some nvidia chisets, the system stalls. https://bugzilla.kernel.org/show_bug.cgi?id=21032 Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 8742ad1eb53c3a91934e22a17c22bbb550faf641 Author: Len Brown <len.brown@xxxxxxxxx> Date: Wed Jul 7 00:12:03 2010 -0400 intel_idle: add initial Sandy Bridge support Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit a244fb119774d591a12cb94ebe15ed90d90fab40 Author: Len Brown <len.brown@xxxxxxxxx> Date: Fri Oct 15 21:23:25 2010 -0400 intel_idle: delete bogus data from cpuidle_state.power_usage The mW data in this field is a total fabrication and serves no purpose other than to mislead those who might see it in sysfs. Delete it. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 56aed0ade2eea84a3590e7d5d24a97389a4e9ce6 Author: Len Brown <len.brown@xxxxxxxxx> Date: Fri Oct 15 20:43:06 2010 -0400 intel_idle: simplify test for leave_mm() A run-time test to invoke leave_mm() for the deepest supported C-state is redundant, since the appropriate C-states already have flags with CPUIDLE_FLAG_TLB_FLUSHED set. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit e4e857d0564162a993b74b08d890cdf813d6ad7e Author: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx> Date: Fri Sep 17 15:36:40 2010 -0700 x86, mwait: Move mwait constants to a common header file We have MWAIT constants spread across three different .c files, for no good reason. Move them all into a common header file. Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx> Reviewed-by: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx> Cc: Len Brown <lenb@xxxxxxxxxx> LKML-Reference: <tip-*@git.kernel.org> Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 585572a8bf160978fd30ad037aa743b551176817 Author: Len Brown <len.brown@xxxxxxxxx> Date: Tue Oct 5 13:43:14 2010 -0400 intel_idle: enable Atom C6 ATM-C6 was commented out, pending public documentation. https://bugzilla.kernel.org/show_bug.cgi?id=19762 Tested-by: Dennis Jansen <Dennis.Jansen@...> Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 9b4bab268c14082aa085523326dc3a80a5b8260d Author: Suresh Siddha <suresh.b.siddha@xxxxxxxxx> Date: Thu Sep 30 21:19:07 2010 -0400 intel_idle: Voluntary leave_mm before entering deeper Avoid TLB flush IPIs for the cores in deeper c-states by voluntary leave_mm() before entering into that state. CPUs tend to flush TLB in those c-states anyways. acpi_idle does this with C3-type states, but it was not caried over when intel_idle was introduced. intel_idle can apply it to C-states in addition to those that ACPI might export as C3... Signed-off-by: Suresh Siddha <suresh.b.siddha@xxxxxxxxx> Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit cab349dee0df0cc3984a124b7c13791c1244d7ed Author: Ai Li <aili@xxxxxxxxxxxxxx> Date: Mon Aug 9 17:20:13 2010 -0700 cpuidle: extend cpuidle and menu governor to handle dynamic states On some SoC chips, HW resources may be in use during any particular idle period. As a consequence, the cpuidle states that the SoC is safe to enter can change from idle period to idle period. In addition, the latency and threshold of each cpuidle state can vary, depending on the operating condition when the CPU becomes idle, e.g. the current cpu frequency, the current state of the HW blocks, etc. cpuidle core and the menu governor, in the current form, are geared towards cpuidle states that are static, i.e. the availabiltiy of the states, their latencies, their thresholds are non-changing during run time. cpuidle does not provide any hook that cpuidle drivers can use to adjust those values on the fly for the current idle period before the menu governor selects the target cpuidle state. This patch extends cpuidle core and the menu governor to handle states that are dynamic. There are three additions in the patch and the patch maintains backwards-compatibility with existing cpuidle drivers. 1) add prepare() to struct cpuidle_device. A cpuidle driver can hook into the callback and cpuidle will call prepare() before calling the governor's select function. The callback gives the cpuidle driver a chance to update the dynamic information of the cpuidle states for the current idle period, e.g. state availability, latencies, thresholds, power values, etc. 2) add CPUIDLE_FLAG_IGNORE as one of the state flags. In the prepare() function, a cpuidle driver can set/clear the flag to indicate to the menu governor whether a cpuidle state should be ignored, i.e. not available, during the current idle period. 3) add power_specified bit to struct cpuidle_device. The menu governor currently assumes that the cpuidle states are arranged in the order of increasing latency, threshold, and power savings. This is true or can be made true for static states. Once the state parameters are dynamic, the latencies, thresholds, and power savings for the cpuidle states can increase or decrease by different amounts from idle period to idle period. So the assumption of increasing latency, threshold, and power savings from Cn to C(n+1) can no longer be guaranteed. It can be straightforward to calculate the power consumption of each available state and to specify it in power_usage for the idle period. Using the power_usage fields, the menu governor then selects the state that has the lowest power consumption and that still satisfies all other critieria. The power_specified bit defaults to 0. For existing cpuidle drivers, cpuidle detects that power_specified is 0 and fills in a dummy set of power_usage values. Signed-off-by: Ai Li <aili@xxxxxxxxxxxxxx> Cc: Len Brown <len.brown@xxxxxxxxx> Acked-by: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxx> Cc: Venkatesh Pallipadi <venki@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 6a06b21da93f610aacdad69f22907671195c770f Author: Thomas Weber <weber@xxxxxxxxxxxxx> Date: Mon Jul 12 08:56:43 2010 +0200 intel_idle: Change mode 755 => 644 Remove execution permission from source file. Signed-off-by: Thomas Weber <weber@xxxxxxxxxxxxx> Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 004fa204948744d2dec47f7403bab91346865e86 Author: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx> Date: Wed Jul 21 23:42:25 2010 -0400 intel_idle: recognize Lincroft Atom Processor Signed-off-by: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx> Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 0d6b75b069efbd0fccd12c659c98053bb735651e Author: Len Brown <len.brown@xxxxxxxxx> Date: Sat Aug 14 14:44:08 2010 -0400 intel_idle: no longer EXPERIMENTAL This is a fully supported driver. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit ac42593b4e644676de0b79ac1fdaaf92792274dd Author: Len Brown <len.brown@xxxxxxxxx> Date: Sat Aug 14 14:40:36 2010 -0400 intel_idle: disable module support Right now the module capability is cauing more trouble than it is worth. At least one distro built intel_idle as a module where it lost the init race with ACPI, making it useless. Make intel_idle bool so that if you select it, you will use it. We can restore module capability after cpuidle is enhanced to handle run-time changing of idle drivers. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 8caa41b55daf1b2b2941549c9ef38a8558090c07 Author: Len Brown <len.brown@xxxxxxxxx> Date: Mon Jul 26 23:40:19 2010 -0400 intel_idle: add support for Westmere-EX Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 55d53f89a3d47f622be0cda9553f0cf9a6ad4a4c Author: Len Brown <len.brown@xxxxxxxxx> Date: Fri Jul 23 16:04:46 2010 -0400 intel_idle: delete power_policy modparam, and choose substate functions The idea behind power policy was that it would start off as a modparam, and then hook into the new "global" in-kernel power vs energy tunable. But that tunable isn't happening, so delete the hook here. With the policy hook gone, the sub-state choice functions do not do anything useful, so delete them from the critical path. To handle sub-states in the future, we will advertise them with dedicated cpuidle_state entries. That is necessary because some of the sub-states will have substantially different properties than their peer sub-states. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 0aa4bd37b8f5c2a728eef4b3abd9162f0900a4f0 Author: Len Brown <len.brown@xxxxxxxxx> Date: Fri May 28 02:22:03 2010 -0400 intel_idle: delete substates DEBUG modparam it isn't useful anymore Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 6337fa0599b79761c3e3b1e2bb397ad9c0409086 Author: Len Brown <len.brown@xxxxxxxxx> Date: Mon Mar 8 14:07:30 2010 -0500 intel_idle: native hardware cpuidle driver for latest Intel processors This EXPERIMENTAL driver supersedes acpi_idle on Intel Atom Processors, Intel Core i3/i5/i7 Processors and associated Intel Xeon processors. It does not support the Intel Core2 processor or earlier. For kernels configured with ACPI, CONFIG_INTEL_IDLE=y allows intel_idle to probe before the ACPI processor driver. Booting with "intel_idle.max_cstate=0" disables intel_idle and the system will fall back on ACPI's "acpi_idle". Typical Linux distributions load ACPI processor module early, making CONFIG_INTEL_IDLE=m not easily useful on ACPI platforms. intel_idle probes all processors at module_init time. Processors that are hot-added later will be limited to using C1 in idle. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 8a73284f4c0b95fe0d1c8f27fbdaac2763dcff74 Author: Len Brown <len.brown@xxxxxxxxx> Date: Sat May 22 17:03:29 2010 -0400 ACPI: allow a native cpuidle driver to displace ACPI The ACPI driver would fail probe when it found that another driver had previously registered with cpuidle. But this is a natural situation, as a native hardware cpuidle driver should be able to bind instead of ACPI, and the ACPI processor driver should be able to handle yielding control of C-states while still handling P-states and T-states. Add a KERN_DEBUG line showing when acpi_idle does successfully register. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit e1bb0411e0f791719e12ffc0b6bd403857ddae0f Author: Len Brown <len.brown@xxxxxxxxx> Date: Sat May 22 16:57:26 2010 -0400 cpuidle: make cpuidle_curr_driver static cpuidle_register_driver() sets cpuidle_curr_driver cpuidle_unregister_driver() clears cpuidle_curr_driver We should't expose cpuidle_curr_driver to potential modification except via these interfaces. So make it static and create cpuidle_get_driver() to observe it. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 7a643ed4b275c5a1a418a051b40014a58e1de0ae Author: Len Brown <len.brown@xxxxxxxxx> Date: Sat May 22 16:34:10 2010 -0400 cpuidle: add cpuidle_unregister_driver() error check Assure that cpuidle_unregister_driver() will not clobber the registered driver if unregistered by somebody else. Signed-off-by: Len Brown <len.brown@xxxxxxxxx> commit 429b500b87a38e008e9911d1798bfa7af298ee38 Author: Len Brown <len.brown@xxxxxxxxx> Date: Tue May 11 16:50:52 2010 -0400 cpuidle: fail to register if !CONFIG_CPU_IDLE Signed-off-by: Len Brown <len.brown@xxxxxxxxx> _______________________________________________ linux-pm mailing list linux-pm@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linux-foundation.org/mailman/listinfo/linux-pm
