mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 21:57:43 +00:00
cc2c4e26ec
It is possible to optimize metrics when all SMT threads (CPUs) on a core are measuring events in system wide mode. For example, TMA metrics defines CORE_CLKS for Sandybrdige as: if SMT is disabled: CPU_CLK_UNHALTED.THREAD if SMT is enabled and recording on all SMT threads: CPU_CLK_UNHALTED.THREAD_ANY / 2 if SMT is enabled and not recording on all SMT threads: (CPU_CLK_UNHALTED.THREAD/2)* (1+CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE/CPU_CLK_UNHALTED.REF_XCLK ) That is two more events are necessary when not gathering counts on all SMT threads. To distinguish all SMT threads on a core vs system wide (all CPUs) call the new property core wide. Add a core wide test that determines the property from user requested CPUs, the topology and system wide. System wide is required as other processes running on a SMT thread will change the counts. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.garry@huawei.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Kshipra Bopardikar <kshipra.bopardikar@intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220831174926.579643-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
73 lines
2.2 KiB
C
73 lines
2.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __PERF_CPUTOPO_H
|
|
#define __PERF_CPUTOPO_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
struct cpu_topology {
|
|
/* The number of unique package_cpus_lists below. */
|
|
u32 package_cpus_lists;
|
|
/* The number of unique die_cpu_lists below. */
|
|
u32 die_cpus_lists;
|
|
/* The number of unique core_cpu_lists below. */
|
|
u32 core_cpus_lists;
|
|
/*
|
|
* An array of strings where each string is unique and read from
|
|
* /sys/devices/system/cpu/cpuX/topology/package_cpus_list. From the ABI
|
|
* each of these is a human-readable list of CPUs sharing the same
|
|
* physical_package_id. The format is like 0-3, 8-11, 14,17.
|
|
*/
|
|
const char **package_cpus_list;
|
|
/*
|
|
* An array of string where each string is unique and from
|
|
* /sys/devices/system/cpu/cpuX/topology/die_cpus_list. From the ABI
|
|
* each of these is a human-readable list of CPUs within the same die.
|
|
* The format is like 0-3, 8-11, 14,17.
|
|
*/
|
|
const char **die_cpus_list;
|
|
/*
|
|
* An array of string where each string is unique and from
|
|
* /sys/devices/system/cpu/cpuX/topology/core_cpus_list. From the ABI
|
|
* each of these is a human-readable list of CPUs within the same
|
|
* core. The format is like 0-3, 8-11, 14,17.
|
|
*/
|
|
const char **core_cpus_list;
|
|
};
|
|
|
|
struct numa_topology_node {
|
|
char *cpus;
|
|
u32 node;
|
|
u64 mem_total;
|
|
u64 mem_free;
|
|
};
|
|
|
|
struct numa_topology {
|
|
u32 nr;
|
|
struct numa_topology_node nodes[];
|
|
};
|
|
|
|
struct hybrid_topology_node {
|
|
char *pmu_name;
|
|
char *cpus;
|
|
};
|
|
|
|
struct hybrid_topology {
|
|
u32 nr;
|
|
struct hybrid_topology_node nodes[];
|
|
};
|
|
|
|
struct cpu_topology *cpu_topology__new(void);
|
|
void cpu_topology__delete(struct cpu_topology *tp);
|
|
/* Determine from the core list whether SMT was enabled. */
|
|
bool cpu_topology__smt_on(const struct cpu_topology *topology);
|
|
/* Are the sets of SMT siblings all enabled or all disabled in user_requested_cpus. */
|
|
bool cpu_topology__core_wide(const struct cpu_topology *topology,
|
|
const char *user_requested_cpu_list);
|
|
|
|
struct numa_topology *numa_topology__new(void);
|
|
void numa_topology__delete(struct numa_topology *tp);
|
|
|
|
struct hybrid_topology *hybrid_topology__new(void);
|
|
void hybrid_topology__delete(struct hybrid_topology *tp);
|
|
|
|
#endif /* __PERF_CPUTOPO_H */
|