Re: [PATCH v2 05/10] hwmon: (fam15h_power) Add compute unit accumulated power

[Borislav Petkov <bp@suse.de>]

On Tue, Oct 20, 2015 at 10:28:24AM +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 <bp@alien8.de>
> Signed-off-by: Huang Rui <ray.huang@amd.com>
> Cc: Guenter Roeck <linux@roeck-us.net>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Ingo Molnar <mingo@kernel.org>
> ---
>  drivers/hwmon/fam15h_power.c | 68 +++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 67 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
> index e2bfab5..88e4f3e 100644
> --- a/drivers/hwmon/fam15h_power.c
> +++ b/drivers/hwmon/fam15h_power.c
> @@ -25,6 +25,7 @@
>  #include <linux/module.h>
>  #include <linux/pci.h>
>  #include <linux/bitops.h>
> +#include <linux/cpumask.h>
>  #include <asm/processor.h>
>  #include <asm/msr.h>
>  
> @@ -44,7 +45,9 @@ 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
>  
>  struct fam15h_power_data {
> @@ -57,6 +60,8 @@ struct fam15h_power_data {
>  	struct attribute_group fam15h_power_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,
> @@ -115,6 +120,65 @@ 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, cores_per_cu;
> +
> +	cpu = smp_processor_id();
> +
> +	cores_per_cu = amd_get_cores_per_cu();
> +	cu = cpu / cores_per_cu;
> +
> +	WARN_ON(rdmsrl_safe(MSR_F15H_CU_PWR_ACCUMULATOR,
> +			    &data->cu_acc_power[cu]));

I guess the WARN_ON's here should be WARN_ON_ONCE() - otherwise dmesg is
filling up very quickly.

> +}
> +
> +static int read_registers(struct fam15h_power_data *data)
> +{
> +	int this_cpu, ret;
> +	int cu_num, cores_per_cu, cpu, cu;
> +	cpumask_var_t mask;
> +
> +	cores_per_cu = amd_get_cores_per_cu();
> +	cu_num = boot_cpu_data.x86_max_cores / cores_per_cu;
> +
> +	WARN_ON_ONCE(cu_num > MAX_CUS);
> +
> +	ret = zalloc_cpumask_var(&mask, GFP_KERNEL);
> +	if (!ret)
> +		return -ENOMEM;
> +
> +	this_cpu = get_cpu();

This should be get_online_cpus() and its counterpart below should be
put_online_cpus().

> +
> +	/*
> +	 * Choose the first online core of each compute unit, and then
> +	 * read their MSR value of power and ptsc in one time of IPI,

						in a single IPI.

> +	 * because the MSR value of cpu core represent the compute

s/cpu/CPU/

do that in *all* your text.

> +	 * unit's. This behavior can decrease IPI numbers between the

	  unit's ?

What does that sentence even mean?

> +	 * cores.
> +	 */
> +	cpu = cpumask_first(cpu_online_mask);
> +	cu = cpu / cores_per_cu;
> +	while (cpu < boot_cpu_data.x86_max_cores) {
> +		if (cu <= cpu / cores_per_cu) {
> +			cu = cpu / cores_per_cu + 1;
> +			cpumask_set_cpu(cpu, mask);
> +		}
> +		cpu = cpumask_next(cu * cores_per_cu - 1, cpu_online_mask);
> +	}

This is hard to parse - I *think* you're setting a bit in mask for a
core in each CU...

If so, I think you can simplify it by generating a tmp mask which
contains the cores of CU0, i.e. something like that:

	11_00_00_...

and then do cpumask_and(res, ...) to find the online cores on that CU
and then do cpumask_set_cpu(cpumask_any(res), mask) to select one CPU on
that CU.

And then shift to the next CU:

	cpumask_shift_right(dst, src_mask, cores_per_cu);

I think this should be cleaner and less error prone, without the
conditionals...

> +
> +	if (cpumask_test_cpu(this_cpu, mask))
> +		do_read_registers_on_cu(data);
> +
> +	smp_call_function_many(mask, do_read_registers_on_cu, data, true);
> +	put_cpu();
> +
> +	free_cpumask_var(mask);
> +
> +	return 0;
> +}
> +
>  static int fam15h_power_init_attrs(struct pci_dev *pdev,
>  				   struct fam15h_power_data *data)
>  {
> @@ -253,7 +317,9 @@ static int fam15h_power_init_data(struct pci_dev *f4,
>  
>  	data->max_cu_acc_power = tmp;
>  
> -	return 0;
> +	ret = read_registers(data);
> +
> +	return ret;

Simply:

	return read_registers(data);

>  }
>  
>  static int fam15h_power_probe(struct pci_dev *pdev,
> -- 
> 1.9.1
> 

-- 
Regards/Gruss,
    Boris.

SUSE Linux GmbH, GF: Felix Imendörffer, Jane Smithard, Graham Norton, HRB 21284 (AG Nürnberg)
--