Re: [PATCH v3 2/2] perf x86: Exposing an Uncore unit to PMON for Intel Xeon® server platform

[Greg KH <gregkh@linuxfoundation.org>]

On Mon, Jan 13, 2020 at 04:54:44PM +0300, roman.sudarikov@linux.intel.com wrote:
> From: Roman Sudarikov <roman.sudarikov@linux.intel.com>
> 
> Current version supports a server line starting Intel® Xeon® Processor
> Scalable Family and introduces mapping for IIO Uncore units only.
> Other units can be added on demand.
> 
> IIO stack to PMON mapping is exposed through:
>     /sys/devices/uncore_iio_<pmu_idx>/platform_mapping
>     in the following format: domain:bus
> 
> For example, on a 4-die Intel Xeon® server platform:
>     $ cat /sys/devices/uncore_iio_0/platform_mapping
>     0000:00,0000:40,0000:80,0000:c0

That's horrid to parse.  Sysfs should be one value per file, why not
have individual files for all of these things?

> Which means:
> IIO PMON block 0 on die 0 belongs to IIO stack on bus 0x00, domain 0x0000
> IIO PMON block 0 on die 1 belongs to IIO stack on bus 0x40, domain 0x0000
> IIO PMON block 0 on die 2 belongs to IIO stack on bus 0x80, domain 0x0000
> IIO PMON block 0 on die 3 belongs to IIO stack on bus 0xc0, domain 0x0000

Where did you get the die number from the above data?



> 
> Co-developed-by: Alexander Antonov <alexander.antonov@intel.com>
> Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
> Signed-off-by: Alexander Antonov <alexander.antonov@intel.com>
> Signed-off-by: Roman Sudarikov <roman.sudarikov@linux.intel.com>
> ---
>  arch/x86/events/intel/uncore.c       |   2 +-
>  arch/x86/events/intel/uncore.h       |   1 +
>  arch/x86/events/intel/uncore_snbep.c | 162 +++++++++++++++++++++++++++
>  3 files changed, 164 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
> index 2c53ad44b51f..c0d86bc8e786 100644
> --- a/arch/x86/events/intel/uncore.c
> +++ b/arch/x86/events/intel/uncore.c
> @@ -16,7 +16,7 @@ struct pci_driver *uncore_pci_driver;
>  DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
>  struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
>  struct pci_extra_dev *uncore_extra_pci_dev;
> -static int max_dies;
> +int max_dies;

Horrible global variable name :(

"unicore_max_dies" instead please.

>  /* mask of cpus that collect uncore events */
>  static cpumask_t uncore_cpu_mask;
> diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
> index f52dd3f112a7..94eacca6f485 100644
> --- a/arch/x86/events/intel/uncore.h
> +++ b/arch/x86/events/intel/uncore.h
> @@ -523,6 +523,7 @@ extern raw_spinlock_t pci2phy_map_lock;
>  extern struct list_head pci2phy_map_head;
>  extern struct pci_extra_dev *uncore_extra_pci_dev;
>  extern struct event_constraint uncore_constraint_empty;
> +extern int max_dies;
>  
>  /* uncore_snb.c */
>  int snb_uncore_pci_init(void);
> diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
> index b10a5ec79e48..2562fde2e5b8 100644
> --- a/arch/x86/events/intel/uncore_snbep.c
> +++ b/arch/x86/events/intel/uncore_snbep.c
> @@ -273,6 +273,30 @@
>  #define SKX_CPUNODEID			0xc0
>  #define SKX_GIDNIDMAP			0xd4
>  
> +/*
> + * The CPU_BUS_NUMBER MSR returns the values of the respective CPUBUSNO CSR
> + * that BIOS programmed. MSR has package scope.
> + * |  Bit  |  Default  |  Description
> + * | [63]  |    00h    | VALID - When set, indicates the CPU bus
> + *                       numbers have been initialized. (RO)
> + * |[62:48]|    ---    | Reserved
> + * |[47:40]|    00h    | BUS_NUM_5 — Return the bus number BIOS assigned
> + *                       CPUBUSNO(5). (RO)
> + * |[39:32]|    00h    | BUS_NUM_4 — Return the bus number BIOS assigned
> + *                       CPUBUSNO(4). (RO)
> + * |[31:24]|    00h    | BUS_NUM_3 — Return the bus number BIOS assigned
> + *                       CPUBUSNO(3). (RO)
> + * |[23:16]|    00h    | BUS_NUM_2 — Return the bus number BIOS assigned
> + *                       CPUBUSNO(2). (RO)
> + * |[15:8] |    00h    | BUS_NUM_1 — Return the bus number BIOS assigned
> + *                       CPUBUSNO(1). (RO)
> + * | [7:0] |    00h    | BUS_NUM_0 — Return the bus number BIOS assigned
> + *                       CPUBUSNO(0). (RO)
> + */
> +#define SKX_MSR_CPU_BUS_NUMBER		0x300
> +#define SKX_MSR_CPU_BUS_VALID_BIT	(1ULL << 63)
> +#define BUS_NUM_STRIDE			8
> +
>  /* SKX CHA */
>  #define SKX_CHA_MSR_PMON_BOX_FILTER_TID		(0x1ffULL << 0)
>  #define SKX_CHA_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 9)
> @@ -3580,6 +3604,9 @@ static struct intel_uncore_ops skx_uncore_iio_ops = {
>  	.read_counter		= uncore_msr_read_counter,
>  };
>  
> +static int skx_iio_get_topology(struct intel_uncore_type *type);
> +static int skx_iio_set_mapping(struct intel_uncore_type *type);
> +
>  static struct intel_uncore_type skx_uncore_iio = {
>  	.name			= "iio",
>  	.num_counters		= 4,
> @@ -3594,6 +3621,8 @@ static struct intel_uncore_type skx_uncore_iio = {
>  	.constraints		= skx_uncore_iio_constraints,
>  	.ops			= &skx_uncore_iio_ops,
>  	.format_group		= &skx_uncore_iio_format_group,
> +	.get_topology		= skx_iio_get_topology,
> +	.set_mapping		= skx_iio_set_mapping,
>  };
>  
>  enum perf_uncore_iio_freerunning_type_id {
> @@ -3780,6 +3809,139 @@ static int skx_count_chabox(void)
>  	return hweight32(val);
>  }
>  
> +static inline int skx_msr_cpu_bus_read(int cpu, u64 *topology)
> +{
> +	u64 msr_value;
> +
> +	if (rdmsrl_on_cpu(cpu, SKX_MSR_CPU_BUS_NUMBER, &msr_value) ||
> +			!(msr_value & SKX_MSR_CPU_BUS_VALID_BIT))
> +		return -1;
> +
> +	*topology = msr_value;
> +
> +	return 0;
> +}
> +
> +static int skx_iio_get_topology(struct intel_uncore_type *type)
> +{
> +	int ret, cpu, die, current_die;
> +	struct pci_bus *bus = NULL;
> +
> +	/*
> +	 * Verified single-segment environments only; disabled for multiple
> +	 * segment topologies for now.
> +	 */
> +	while ((bus = pci_find_next_bus(bus)) && !pci_domain_nr(bus))
> +		;
> +	if (bus) {
> +		pr_info("I/O stack mapping is not supported for multi-seg\n");
> +		return -1;

Do not make up random negative error values, use a #defined one please.

And shouldn't this be dev_err()?  What happens if a user gets this, who
do they complain to, their BIOS vendor?

thanks,

greg k-h