linux/drivers/cpufreq, branch v4.9

Merge branches 'pm-cpufreq-fixes' and 'pm-sleep-fixes'

2016-10-28T23:29:17Z

* pm-cpufreq-fixes: cpufreq: intel_pstate: Always set max P-state in performance mode cpufreq: intel_pstate: Set P-state upfront in performance mode * pm-sleep-fixes: PM / suspend: Fix missing KERN_CONT for suspend message

cpufreq: intel_pstate: Always set max P-state in performance mode

2016-10-24T21:20:25Z

The only times at which intel_pstate checks the policy set for a given CPU is the initialization of that CPU and updates of its policy settings from cpufreq when intel_pstate_set_policy() is invoked. That is insufficient, however, because intel_pstate uses the same P-state selection function for all CPUs regardless of the policy setting for each of them and the P-state limits are shared between them. Thus if the policy is set to "performance" for a particular CPU, it may not behave as expected if the cpufreq settings are changed subsequently for another CPU. That can be easily demonstrated by writing "performance" to scaling_governor for all CPUs and then switching it to "powersave" for one of them in which case all of the CPUs will behave as though their scaling_governor were all "powersave" (even though the policy still appears to be "performance" for the remaining CPUs). Fix this problem by modifying intel_pstate_adjust_busy_pstate() to always set the P-state to the maximum allowed by the current limits for all CPUs whose policy is set to "performance". Note that it still is recommended to always change the policy setting in the same way for all CPUs even with this fix applied to avoid confusion. Signed-off-by: Rafael J. Wysocki

cpufreq: intel_pstate: Set P-state upfront in performance mode

2016-10-21T20:18:22Z

After commit a4675fbc4a7a (cpufreq: intel_pstate: Replace timers with utilization update callbacks) the cpufreq governor callbacks may not be invoked on NOHZ_FULL CPUs and, in particular, switching to the "performance" policy via sysfs may not have any effect on them. That is a problem, because it usually is desirable to squeeze the last bit of performance out of those CPUs, so work around it by setting the maximum P-state (within the limits) in intel_pstate_set_policy() upfront when the policy is CPUFREQ_POLICY_PERFORMANCE. Fixes: a4675fbc4a7a (cpufreq: intel_pstate: Replace timers with utilization update callbacks) Signed-off-by: Rafael J. Wysocki Acked-by: Srinivas Pandruvada

Merge tag 'pm-extra-4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

2016-10-14T19:46:13Z

Pull more power management updates from Rafael Wysocki: "This includes a couple of fixes for cpufreq regressions introduced in 4.8, a rework of the intel_pstate algorithm used on Atom processors (that took some time to test) plus a fix and a couple of cleanups in that driver, a CPPC cpufreq driver fix, and a some devfreq fixes and cleanups (core and exynos-nocp). Specifics: - Fix two cpufreq regressions causing undesirable changes in behavior to appear (one in the core and one in the conservative governor) introduced during the 4.8 cycle (Aaro Koskinen, Rafael Wysocki). - Fix the way the intel_pstate driver accesses MSRs related to the hardware-managed P-states (HWP) feature during the initialization which currently is unsafe and may cause the processor to generate a general protection fault (Srinivas Pandruvada). - Rework the intel_pstate's P-state selection algorithm used on Atom processors to avoid known problems with the current one and to make the computation more straightforward, which also happens to improve performance in multiple benchmarks a bit (Rafael Wysocki). - Improve two comments in the intel_pstate driver (Rafael Wysocki). - Fix the desired performance computation in the CPPC cpufreq driver (Hoan Tran). - Fix the devfreq core to avoid printing misleading error messages in some cases (Tobias Jakobi). - Fix the error code path in devfreq_add_device() to use proper locking around list modifications (Axel Lin). - Fix a build failure and remove a couple of redundant updates of variables in the exynos-nocp devfreq driver (Axel Lin)" * tag 'pm-extra-4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: cpufreq: CPPC: Correct desired_perf calculation cpufreq: conservative: Fix next frequency selection cpufreq: skip invalid entries when searching the frequency cpufreq: intel_pstate: Fix struct pstate_adjust_policy kerneldoc cpufreq: intel_pstate: Proportional algorithm for Atom PM / devfreq: Skip status update on uninitialized previous_freq PM / devfreq: Add proper locking around list_del() PM / devfreq: exynos-nocp: Remove redundant code PM / devfreq: exynos-nocp: Select REGMAP_MMIO cpufreq: intel_pstate: Clarify comment in get_target_pstate_use_performance() cpufreq: intel_pstate: Fix unsafe HWP MSR access

cpufreq: CPPC: Correct desired_perf calculation

2016-10-13T21:10:41Z

The desired_perf is an abstract performance number. Its value should be in the range of [lowest perf, highest perf] of CPPC. The correct calculation is desired_perf = freq * cppc_highest_perf / cppc_dmi_max_khz And cppc_cpufreq_set_target() returns if desired_perf is exactly the same with the old perf. Signed-off-by: Hoan Tran Reviewed-by: Prashanth Prakash Signed-off-by: Rafael J. Wysocki

cpufreq: conservative: Fix next frequency selection

2016-10-13T12:42:06Z

Commit d352cf47d93e (cpufreq: conservative: Do not use transition notifications) overlooked the case when the "frequency step" used by the conservative governor is small relative to the distances between the available frequencies and broke the algorithm by using policy->cur instead of the previously requested frequency when computing the next one. As a result, the governor may not be able to go outside of a narrow range between two consecutive available frequencies. Fix the problem by making the governor save the previously requested frequency and select the next one relative that value (unless it is out of range, in which case policy->cur will be used instead). Fixes: d352cf47d93e (cpufreq: conservative: Do not use transition notifications) Link: https://bugzilla.kernel.org/show_bug.cgi?id=177171 Reported-and-tested-by: Aleksey Rybalkin Acked-by: Viresh Kumar Cc: 4.8+ # 4.8+ Signed-off-by: Rafael J. Wysocki

cpufreq: intel_pstate: Fix struct pstate_adjust_policy kerneldoc

2016-10-12T18:58:14Z

It looks like the name of struct pstate_adjust_policy was updated without updating its kerneldoc comment accordingly, so fix that mistake. Signed-off-by: Rafael J. Wysocki

cpufreq: intel_pstate: Proportional algorithm for Atom

2016-10-12T18:58:13Z

The PID algorithm used by the intel_pstate driver tends to drive performance to the minimum for workloads with utilization below the setpoint, which is undesirable, so replace it with a modified "proportional" algorithm on Atom. The new algorithm will set the new P-state to be 1.25 times the available maximum times the (frequency-invariant) utilization during the previous sampling period except when the target P-state computed this way is lower than the average P-state during the previous sampling period. In the latter case, it will increase the target by 50% of the difference between it and the average P-state to prevent performance from dropping down too fast in some cases. Signed-off-by: Rafael J. Wysocki Tested-by: Srinivas Pandruvada

cpufreq: intel_pstate: Clarify comment in get_target_pstate_use_performance()

2016-10-09T16:54:57Z

Make the comment explaining the meaning of the perf_scaled variable in get_target_pstate_use_performance() more straightforward. Signed-off-by: Rafael J. Wysocki

cpufreq: intel_pstate: Fix unsafe HWP MSR access

2016-10-09T16:54:13Z

This is a requirement that MSR MSR_PM_ENABLE must be set to 0x01 before reading MSR_HWP_CAPABILITIES on a given CPU. If cpufreq init() is scheduled on a CPU which is not same as policy->cpu or migrates to a different CPU before calling msr read for MSR_HWP_CAPABILITIES, it is possible that MSR_PM_ENABLE was not to set to 0x01 on that CPU. This will cause GP fault. So like other places in this path rdmsrl_on_cpu should be used instead of rdmsrl. Moreover the scope of MSR_HWP_CAPABILITIES is on per thread basis, so it should be read from the same CPU, for which MSR MSR_HWP_REQUEST is getting set. dmesg dump or warning: [ 22.014488] WARNING: CPU: 139 PID: 1 at arch/x86/mm/extable.c:50 ex_handler_rdmsr_unsafe+0x68/0x70 [ 22.014492] unchecked MSR access error: RDMSR from 0x771 [ 22.014493] Modules linked in: [ 22.014507] CPU: 139 PID: 1 Comm: swapper/0 Not tainted 4.7.5+ #1 ... ... [ 22.014516] Call Trace: [ 22.014542] [] dump_stack+0x63/0x82 [ 22.014558] [] __warn+0xcb/0xf0 [ 22.014561] [] warn_slowpath_fmt+0x4f/0x60 [ 22.014563] [] ex_handler_rdmsr_unsafe+0x68/0x70 [ 22.014564] [] fixup_exception+0x39/0x50 [ 22.014604] [] do_general_protection+0x80/0x150 [ 22.014610] [] general_protection+0x28/0x30 [ 22.014635] [] ? get_target_pstate_use_performance+0xb0/0xb0 [ 22.014642] [] ? native_read_msr+0x7/0x40 [ 22.014657] [] intel_pstate_hwp_set+0x23/0x130 [ 22.014660] [] intel_pstate_set_policy+0x1b6/0x340 [ 22.014662] [] cpufreq_set_policy+0xeb/0x2c0 [ 22.014664] [] cpufreq_init_policy+0x79/0xe0 [ 22.014666] [] ? cpufreq_update_policy+0x120/0x120 [ 22.014669] [] cpufreq_online+0x406/0x820 [ 22.014671] [] cpufreq_add_dev+0x5f/0x90 [ 22.014717] [] subsys_interface_register+0xb8/0x100 [ 22.014719] [] cpufreq_register_driver+0x14c/0x210 [ 22.014749] [] intel_pstate_init+0x39d/0x4d5 [ 22.014751] [] ? cpufreq_gov_dbs_init+0x12/0x12 Cc: 4.3+ # 4.3+ Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki