On Mon, Mar 28, 2016 at 01:32:12PM +0800, Huang Rui wrote:
> This patch adds a member in fam15h_power_data which specifies the
> compute unit accumulated power. It 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(). This behavior can decrease
> IPI numbers.
>
> Suggested-by: Borislav Petkov <b...@alien8.de>
> Signed-off-by: Huang Rui <ray.hu...@amd.com>
> ---
> drivers/hwmon/fam15h_power.c | 65
> +++++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 64 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
> index 4f695d8..ccbc944 100644
> --- a/drivers/hwmon/fam15h_power.c
> +++ b/drivers/hwmon/fam15h_power.c
> @@ -25,6 +25,8 @@
> #include <linux/module.h>
> #include <linux/pci.h>
> #include <linux/bitops.h>
> +#include <linux/cpu.h>
> +#include <linux/cpumask.h>
> #include <asm/processor.h>
> #include <asm/msr.h>
>
> @@ -44,7 +46,9 @@ MODULE_LICENSE("GPL");
>
> #define FAM15H_MIN_NUM_ATTRS 2
> #define FAM15H_NUM_GROUPS 2
> +#define MAX_CUS 8
>
> +#define MSR_F15H_CU_PWR_ACCUMULATOR 0xc001007a
> #define MSR_F15H_CU_MAX_PWR_ACCUMULATOR 0xc001007b
>
> #define PCI_DEVICE_ID_AMD_15H_M70H_NB_F4 0x15b4
> @@ -59,6 +63,8 @@ struct fam15h_power_data {
> struct attribute_group group;
> /* maximum accumulated power of a compute unit */
> u64 max_cu_acc_power;
> + /* accumulated power of the compute units */
> + u64 cu_acc_power[MAX_CUS];
> };
>
> static ssize_t show_power(struct device *dev,
> @@ -125,6 +131,63 @@ static ssize_t show_power_crit(struct device *dev,
> }
> static DEVICE_ATTR(power1_crit, S_IRUGO, show_power_crit, NULL);
>
> +static void do_read_registers_on_cu(void *_data)
> +{
> + struct fam15h_power_data *data = _data;
> + int cpu, cu;
> +
> + cpu = smp_processor_id();
> +
> + /*
> + * With the new x86 topology modelling, cpu core id actually
> + * is compute unit id.
> + */
> + cu = cpu_data(cpu).cpu_core_id;
> +
> + rdmsrl_safe(MSR_F15H_CU_PWR_ACCUMULATOR, &data->cu_acc_power[cu]);
> +}
> +
> +/*
> + * This function is only able to be called when CPUID
> + * Fn8000_0007:EDX[12] is set.
> + */
> +static int read_registers(struct fam15h_power_data *data)
> +{
> + int this_cpu, ret, cpu;
> + int target;
> + cpumask_var_t mask;
> +
> + ret = zalloc_cpumask_var(&mask, GFP_KERNEL);
> + if (!ret)
> + return -ENOMEM;
> +
> + get_online_cpus();
> + this_cpu = get_cpu();
What now?
get_online_cpus() is enough.
> +
> + /*
> + * Choose the first online core of each compute unit, and then
> + * read their MSR value of power and ptsc in a single IPI,
> + * because the MSR value of CPU core represent the compute
> + * unit's.
> + */
> + for_each_online_cpu(cpu) {
> + target = cpumask_first(topology_sibling_cpumask(cpu));
> + if (!cpumask_test_cpu(target, mask))
> + cpumask_set_cpu(target, mask);
> + }
I think you want something like this: iterate over each core and put one
of them into the mask.
core = -1;
for_each_online_cpu(cpu) {
this_core = topology_core_id(cpu);
if (this_core == core)
continue;
core = this_core;
/* get any CPU on this compute unit */
cpumask_set_cpu(cpumask_any(topology_sibling_cpumask(cpu)),
mask);
}
Btw, tglx, peterz, do you guys think it would make sense to have a
generic helper:
for_each_core(cpu)
which would give you any of the threads on the core in the @cpu var when
iterating?
I see only arch/x86/events/intel/cstate.c doing any comparisons with
topology_core_id() now but it might be useful...
--
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
