commit 5fc8f707a2aa40c767c3a338738b9b6fcd151ac1 upstream. If MSR_CONFIG_TDP_CONTROL is locked, we currently try to address some MSR 0x80000648 or so. Mask out the relevant level bits 0 and 1. Found while running over the Jailhouse hypervisor which became upset about this strange MSR index. Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit da7d3abe1c9e5ebac2cf86f97e9e89888a5e2094 upstream. This reverts commit 790d849bf811a8ab5d4cd2cce0f6fda92f6aebf2. Using a v4.7-rc7 kernel on a HP ProLiant triggered following messages pcc-cpufreq: (v1.10.00) driver loaded with frequency limits: 1200 MHz, 2800 MHz cpufreq: ondemand governor failed, too long transition latency of HW, fallback to performance governor The last line was shown for each CPU in the system. Testing v4.5 (where commit 790d849b was integrated) triggered similar messages. Same behaviour on a 2nd HP Proliant system. So commit 790d849bf (cpufreq: pcc-cpufreq: update default value of cpuinfo_transition_latency) causes the system to use performance governor which, I guess, was not the intention of the patch. Enabling debug output in pcc-cpufreq provides following verbose output: pcc-cpufreq: (v1.10.00) driver loaded with frequency limits: 1200 MHz, 2800 MHz pcc_get_offset: for CPU 0: pcc_cpu_data input_offset: 0x44, pcc_cpu_data output_offset: 0x48 init: policy->max is 2800000, policy->min is 1200000 get: get_freq for CPU 0 get: SUCCESS: (virtual) output_offset for cpu 0 is 0xffffc9000d7c0048, contains a value of: 0xff06. Speed is: 168000 MHz cpufreq: ondemand governor failed, too long transition latency of HW, fallback to performance governor target: CPU 0 should go to target freq: 2800000 (virtual) input_offset is 0xffffc9000d7c0044 target: was SUCCESSFUL for cpu 0 I am asking to revert 790d849bf to re-enable usage of ondemand governor with pcc-cpufreq. Fixes: 790d849bf (cpufreq: pcc-cpufreq: update default value of cpuinfo_transition_latency) Signed-off-by: Andreas Herrmann <aherrmann@suse.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
CPU notifications from the firmware coming in when cpufreq is suspended cause cpufreq_update_current_freq() to return 0 which triggers the WARN_ON() in cpufreq_update_policy() for no reason. Avoid that by checking cpufreq_suspended before calling cpufreq_update_current_freq(). Fixes: c9d9c929e674 (cpufreq: Abort cpufreq_update_current_freq() for cpufreq_suspended set) Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: 4.6+ <stable@vger.kernel.org> # 4.6+
If of_match_node() fails, this init function bails out without calling of_node_put(). Also change of_node_put(of_root) to of_node_put(np); both of them hold the same pointer, but it seems better to call of_node_put() against the node returned by of_find_node_by_path(). Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
intel_pstate_set_policy() is invoked by the cpufreq core during driver initialization, on changes of policy attributes (minimim and maximum frequency, for example) via sysfs and via CPU notifications from the platform firmware. On some platforms the latter may occur relatively often. Commit bb6ab52f2bef (intel_pstate: Do not set utilization update hook too early) made intel_pstate_set_policy() clear the CPU's utilization update hook before updating the policy attributes for it (and set the hook again after doind that), but that involves invoking synchronize_sched() and adds overhead to the CPU notifications mentioned above and to the sched-RCU handling in general. That extra overhead is arguably not necessary, because updating policy attributes when the CPU's utilization update hook is active should not lead to any adverse effects, so drop the clearing of the hook from intel_pstate_set_policy() and make it check if the hook has been set already when attempting to set it. Fixes: bb6ab52f2bef (intel_pstate: Do not set utilization update hook too early) Reported-by: Jisheng Zhang <jszhang@marvell.com> Tested-by: Jisheng Zhang <jszhang@marvell.com> Tested-by: Doug Smythies <dsmythies@telus.net> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Commit 920de6ebfab8 (ACPICA: Hardware: Enhance acpi_hw_validate_register() with access_width/bit_offset awareness) apparently exposed a latent bug, doorbell.access_width is initialized to 64, but per Lv Zheng, it should be 4, and indeed, making that change does bring pcc-cpufreq back to life. Fixes: 920de6ebfab8 (ACPICA: Hardware: Enhance acpi_hw_validate_register() with access_width/bit_offset awareness) Suggested-by: Lv Zheng <lv.zheng@intel.com> Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The maximum turbo P-State used by the intel_pstate driver may be limited by ACPI _PSS table entry 0. After commit 9522a2ff9cde (cpufreq: intel_pstate: Enforce _PPC limits), the maximum performance on servers will be capped by the _PSS table entry 0 by default. Even though that is formally correct, it may lead to preformance regressions in some cases. Namely, if the _PSS table entry 0 is not the maximum turbo P-State, performance measured after commit 9522a2ff9cde will not match the performance measured before that commit on the same system. For this reason, modify the code to always use the maximum turbo frequency as the one that corresponds to _PSS table entry 0 if turbo is enabled in the BIOS. This way, the performance levels from before commit 9522a2ff9cde will be restored on the affected systems. Fixes: 9522a2ff9cde (cpufreq: intel_pstate: Enforce _PPC limits) Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> [ rjw : Changelog ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
* pm-cpufreq-fixes: cpufreq: intel_pstate: Fix ->set_policy() interface for no_turbo cpufreq: intel_pstate: Fix code ordering in intel_pstate_set_policy() * pm-cpuidle: cpuidle: Do not access cpuidle_devices when !CONFIG_CPU_IDLE
When turbo is disabled, the ->set_policy() interface is broken. For example, when turbo is disabled and cpuinfo.max = 2900000 (full max turbo frequency), setting the limits results in frequency less than the requested one: Set 1000000 KHz results in 0700000 KHz Set 1500000 KHz results in 1100000 KHz Set 2000000 KHz results in 1500000 KHz This is because the limits->max_perf fraction is calculated using the max turbo frequency as the reference, but when the max P-State is capped in intel_pstate_get_min_max(), the reference is not the max turbo P-State. This results in reducing max P-State. One option is to always use max turbo as reference for calculating limits. But this will not be correct. By definition the intel_pstate sysfs limits, shows percentage of available performance. So when BIOS has disabled turbo, the available performance is max non turbo. So the max_perf_pct should still show 100%. Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> [ rjw : Subject & changelog, rewrite in fewer lines of code ] Cc: All applicable <stable@vger.kernel.org> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The limits->max_perf is rounded_up but immediately overwritten by another assignment to limits->max_perf. Move that operation to the correct location. While here also added a pr_debug() call in ->set_policy to aid in debugging. Fixes: 785ee2788141 (cpufreq: intel_pstate: Fix limits->max_perf rounding error) Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> [ rjw : Subject & changelog ] Cc: 4.4+ <stable@vger.kernel.org> # 4.4+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>