linux_dsm_epyc7002/tools/perf/perf.h
Christophe Leroy 21b8732eb4 perf tools: Allow overriding MAX_NR_CPUS at compile time
After update of kernel, the perf tool doesn't run anymore on my 32MB RAM
powerpc board, but still runs on a 128MB RAM board:

  ~# strace perf
  execve("/usr/sbin/perf", ["perf"], [/* 12 vars */]) = -1 ENOMEM (Cannot allocate memory)
  --- SIGSEGV {si_signo=SIGSEGV, si_code=SI_KERNEL, si_addr=0} ---
  +++ killed by SIGSEGV +++
  Segmentation fault

objdump -x shows that .bss section has a huge size of 24Mbytes:

 27 .bss          016baca8  101cebb8  101cebb8  001cd988  2**3

With especially the following objects having quite big size:

  10205f80 l     O .bss	00140000     runtime_cycles_stats
  10345f80 l     O .bss	00140000     runtime_stalled_cycles_front_stats
  10485f80 l     O .bss	00140000     runtime_stalled_cycles_back_stats
  105c5f80 l     O .bss	00140000     runtime_branches_stats
  10705f80 l     O .bss	00140000     runtime_cacherefs_stats
  10845f80 l     O .bss	00140000     runtime_l1_dcache_stats
  10985f80 l     O .bss	00140000     runtime_l1_icache_stats
  10ac5f80 l     O .bss	00140000     runtime_ll_cache_stats
  10c05f80 l     O .bss	00140000     runtime_itlb_cache_stats
  10d45f80 l     O .bss	00140000     runtime_dtlb_cache_stats
  10e85f80 l     O .bss	00140000     runtime_cycles_in_tx_stats
  10fc5f80 l     O .bss	00140000     runtime_transaction_stats
  11105f80 l     O .bss	00140000     runtime_elision_stats
  11245f80 l     O .bss	00140000     runtime_topdown_total_slots
  11385f80 l     O .bss	00140000     runtime_topdown_slots_retired
  114c5f80 l     O .bss	00140000     runtime_topdown_slots_issued
  11605f80 l     O .bss	00140000     runtime_topdown_fetch_bubbles
  11745f80 l     O .bss	00140000     runtime_topdown_recovery_bubbles

This is due to commit 4d255766d2 ("perf: Bump max number of cpus
to 1024"), because many tables are sized with MAX_NR_CPUS

This patch gives the opportunity to redefine MAX_NR_CPUS via

  $ make EXTRA_CFLAGS=-DMAX_NR_CPUS=1

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/20170922112043.8349468C57@po15668-vm-win7.idsi0.si.c-s.fr
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-01 12:33:24 -03:00

94 lines
2.2 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _PERF_PERF_H
#define _PERF_PERF_H
#include <time.h>
#include <stdbool.h>
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/perf_event.h>
extern bool test_attr__enabled;
void test_attr__ready(void);
void test_attr__init(void);
void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
int fd, int group_fd, unsigned long flags);
#define HAVE_ATTR_TEST
#include "perf-sys.h"
static inline unsigned long long rdclock(void)
{
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
}
#ifndef MAX_NR_CPUS
#define MAX_NR_CPUS 1024
#endif
extern const char *input_name;
extern bool perf_host, perf_guest;
extern const char perf_version_string[];
void pthread__unblock_sigwinch(void);
#include "util/target.h"
struct record_opts {
struct target target;
bool group;
bool inherit_stat;
bool no_buffering;
bool no_inherit;
bool no_inherit_set;
bool no_samples;
bool raw_samples;
bool sample_address;
bool sample_phys_addr;
bool sample_weight;
bool sample_time;
bool sample_time_set;
bool sample_cpu;
bool period;
bool period_set;
bool running_time;
bool full_auxtrace;
bool auxtrace_snapshot_mode;
bool record_namespaces;
bool record_switch_events;
bool all_kernel;
bool all_user;
bool tail_synthesize;
bool overwrite;
bool ignore_missing_thread;
bool strict_freq;
bool sample_id;
unsigned int freq;
unsigned int mmap_pages;
unsigned int auxtrace_mmap_pages;
unsigned int user_freq;
u64 branch_stack;
u64 sample_intr_regs;
u64 sample_user_regs;
u64 default_interval;
u64 user_interval;
size_t auxtrace_snapshot_size;
const char *auxtrace_snapshot_opts;
bool sample_transaction;
unsigned initial_delay;
bool use_clockid;
clockid_t clockid;
unsigned int proc_map_timeout;
};
struct option;
extern const char * const *record_usage;
extern struct option *record_options;
extern int version_verbose;
int record__parse_freq(const struct option *opt, const char *str, int unset);
#endif