OpenCloudOS-Kernel/tools/perf/util/cputopo.h

79 lines
2.3 KiB
C
Raw Normal View History

/* 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;
perf tools: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Gustavo A. R. Silva <gustavo@embeddedor.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200515172926.GA31976@embeddedor Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-05-16 01:29:26 +08:00
struct numa_topology_node nodes[];
};
struct hybrid_topology_node {
char *pmu_name;
char *cpus;
};
struct hybrid_topology {
u32 nr;
struct hybrid_topology_node nodes[];
};
perf expr: Make the online topology accessible globally Knowing the topology of online CPUs is useful for more than just expr literals. Move to a global function that caches the value. An additional upside is that this may also avoid computing the CPU topology in some situations. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 17:28:04 +08:00
/*
* The topology for online CPUs, lazily created.
*/
const struct cpu_topology *online_topology(void);
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);
perf topology: Add core_wide 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>
2022-09-01 01:49:23 +08:00
/* 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 */