Hi Guenter, This serial of patches introduces an accumulated power reporting algorithm. It will calculate the average power consumption for the processor. The cpu feature flag is CPUID.8000_0007H:EDX[12].
This algorithm is used to test the comparison of processor power consumption with between MWAITX delay and TSC delay on AMD Carrizo platforms. Reference: https://lkml.kernel.org/r/1438744732-1459-1-git-send-email-ray.hu...@amd.com Commit f96756 at tip ("x86/asm: Add MONITORX/MWAITX instruction support") Commit b466bd at tip ("x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer") V1: https://lkml.kernel.org/r/1440662866-28716-1-git-send-email-ray.hu...@amd.com V2: https://lkml.kernel.org/r/1445308109-17970-1-git-send-email-ray.hu...@amd.com V3: https://lkml.kernel.org/r/1446199024-1896-1-git-send-email-ray.hu...@amd.com V4: https://lkml.kernel.org/r/1457662670-3354-1-git-send-email-ray.hu...@amd.com On V5, I used the new x86 topology with compute unit id (cpu_core_id) and compute unit numbers (x86_max_cores) for AMD processors. The change and documentation will go to master soon as below link. And This way is better to use smp_num_siblings which is un-defined variable out of CONFIG_SMP. Refer: https://git.kernel.org/cgit/linux/kernel/git/bp/bp.git/commit/?h=tip-urgent&id=f6ce1851fa2eec2c332255fc25a544658dbfbfe4 Changes from v1 -> v2: - Move fam15h_power_groups and fam15h_power_group into fam15h_power_data to avoid overwrite on multi-CPU system. - Rename FAM15H_MIN_NUM_ATTRS macro and fix return error code. - Remove unnecessary warning print. - Adds do_read_registers_on_cu to do all the read to all MSRs and run it on one of the online cores on each compute unit with smp_call_function_many(). - Use power1_average and power1_average_interval standard entry instread of power1_acc - Fix the CPU-hotplug case. Changes from v2 -> v3: - As Guenter's suggestion, remove typecast, use &data->groups[0]. - Remove all "fam15_power_*" prefix at data. - Remove unnecessary ( ). - Fix the issue that is reported by build test robot, and add CPU_SUP_AMD as the dependence of fam15h_power - Remove the WARN_ON at do_read_registers_on_cu, because it must be behind CPUID check. The MSR must be available since CPUID.8000_0007H:EDX[12] is set - Add get_online_cpus()/put_online_cpus() functions. - Refine commments and the method which generate cpumask for cu. - Add the interval scope to make the value suitable for user experience - Remove the useless mutex. Changes from v3 -> v4: - Rebase the patches to latest groeck/hwmon-next. - Use smp_num_siblings instead of cores_per_cu accessor. - Refine the cpumask method which is inspired by perf solution. - Fix some typo and errors. Changes from v4 -> v5: - Rebase patches to v4.6-rc1. - Use new x86 topology with compute id (cpu_core_id) and compute unit number (x86_max_cores) instead of smp_num_siblings. A simple example: ray@hr-ub:~/tip$ sensors fam15h_power-pci-00c4 Adapter: PCI adapter power1: 19.58 mW (avg = 2.55 mW, interval = 0.01 s) (crit = 15.00 W) ... These patches are rebased on v4.6-rc1. Thanks, Rui Huang Rui (6): hwmon: (fam15h_power) Add CPU_SUP_AMD as the dependence hwmon: (fam15h_power) Add compute unit accumulated power hwmon: (fam15h_power) Add ptsc counter value for accumulated power hwmon: (fam15h_power) Introduce a cpu accumulated power reporting algorithm hwmon: (fam15h_power) Add documentation for TDP and accumulated power algorithm hwmon: (fam15h_power) Add platform check function Documentation/hwmon/fam15h_power | 57 ++++++++++- drivers/hwmon/Kconfig | 2 +- drivers/hwmon/fam15h_power.c | 199 ++++++++++++++++++++++++++++++++++++++- 3 files changed, 252 insertions(+), 6 deletions(-) -- 1.9.1
