Merge branch 'perf/urgent' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar 2019-02-09 13:15:32 +01:00
commit 9821517a53
10 changed files with 69 additions and 17 deletions

View File

@ -268,7 +268,7 @@ struct sockaddr_in {
#define IN_MULTICAST(a) IN_CLASSD(a)
#define IN_MULTICAST_NET 0xe0000000
#define IN_BADCLASS(a) ((((long int) (a) ) == 0xffffffff)
#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff)
#define IN_EXPERIMENTAL(a) IN_BADCLASS((a))
#define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000)

View File

@ -19,8 +19,11 @@ C2C stands for Cache To Cache.
The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows
you to track down the cacheline contentions.
The tool is based on x86's load latency and precise store facility events
provided by Intel CPUs. These events provide:
On x86, the tool is based on load latency and precise store facility events
provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling
with thresholding feature.
These events provide:
- memory address of the access
- type of the access (load and store details)
- latency (in cycles) of the load access
@ -46,7 +49,7 @@ RECORD OPTIONS
-l::
--ldlat::
Configure mem-loads latency.
Configure mem-loads latency. (x86 only)
-k::
--all-kernel::
@ -119,11 +122,16 @@ Following perf record options are configured by default:
-W,-d,--phys-data,--sample-cpu
Unless specified otherwise with '-e' option, following events are monitored by
default:
default on x86:
cpu/mem-loads,ldlat=30/P
cpu/mem-stores/P
and following on PowerPC:
cpu/mem-loads/
cpu/mem-stores/
User can pass any 'perf record' option behind '--' mark, like (to enable
callchains and system wide monitoring):

View File

@ -82,7 +82,7 @@ RECORD OPTIONS
Be more verbose (show counter open errors, etc)
--ldlat <n>::
Specify desired latency for loads event.
Specify desired latency for loads event. (x86 only)
In addition, for report all perf report options are valid, and for record
all perf record options.

View File

@ -2,6 +2,7 @@ libperf-y += header.o
libperf-y += sym-handling.o
libperf-y += kvm-stat.o
libperf-y += perf_regs.o
libperf-y += mem-events.o
libperf-$(CONFIG_DWARF) += dwarf-regs.o
libperf-$(CONFIG_DWARF) += skip-callchain-idx.o

View File

@ -0,0 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
#include "mem-events.h"
/* PowerPC does not support 'ldlat' parameter. */
char *perf_mem_events__name(int i)
{
if (i == PERF_MEM_EVENTS__LOAD)
return (char *) "cpu/mem-loads/";
return (char *) "cpu/mem-stores/";
}

View File

@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
bool found = false;
struct perf_evsel *evsel, *tmp;
struct parse_events_error err = { .idx = 0, };
int ret = parse_events(evlist, "probe:vfs_getname*", &err);
if (IS_ERR(evsel))
if (ret)
return false;
if (perf_evsel__field(evsel, "pathname") == NULL) {
evlist__for_each_entry_safe(evlist, evsel, tmp) {
if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname"))
continue;
if (perf_evsel__field(evsel, "pathname")) {
evsel->handler = trace__vfs_getname;
found = true;
continue;
}
list_del_init(&evsel->node);
evsel->evlist = NULL;
perf_evsel__delete(evsel);
return false;
}
evsel->handler = trace__vfs_getname;
perf_evlist__add(evlist, evsel);
return true;
return found;
}
static struct perf_evsel *perf_evsel__new_pgfault(u64 config)

View File

@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
return -1;
}
is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED);
is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED);
if (should_be_signed && !is_signed) {
pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
evsel->name, name, is_signed, should_be_signed);

View File

@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module)
}
PM.run(*Module);
return std::move(Buffer);
return Buffer;
}
}

View File

@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
static char mem_loads_name[100];
static bool mem_loads_name__init;
char *perf_mem_events__name(int i)
char * __weak perf_mem_events__name(int i)
{
if (i == PERF_MEM_EVENTS__LOAD) {
if (!mem_loads_name__init) {

View File

@ -19,6 +19,20 @@
#define EM_AARCH64 183 /* ARM 64 bit */
#endif
#ifndef ELF32_ST_VISIBILITY
#define ELF32_ST_VISIBILITY(o) ((o) & 0x03)
#endif
/* For ELF64 the definitions are the same. */
#ifndef ELF64_ST_VISIBILITY
#define ELF64_ST_VISIBILITY(o) ELF32_ST_VISIBILITY (o)
#endif
/* How to extract information held in the st_other field. */
#ifndef GELF_ST_VISIBILITY
#define GELF_ST_VISIBILITY(val) ELF64_ST_VISIBILITY (val)
#endif
typedef Elf64_Nhdr GElf_Nhdr;
#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
return GELF_ST_TYPE(sym->st_info);
}
static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
{
return GELF_ST_VISIBILITY(sym->st_other);
}
#ifndef STT_GNU_IFUNC
#define STT_GNU_IFUNC 10
#endif
@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
return elf_sym__type(sym) == STT_NOTYPE &&
sym->st_name != 0 &&
sym->st_shndx != SHN_UNDEF &&
sym->st_shndx != SHN_ABS;
sym->st_shndx != SHN_ABS &&
elf_sym__visibility(sym) != STV_HIDDEN &&
elf_sym__visibility(sym) != STV_INTERNAL;
}
static bool elf_sym__filter(GElf_Sym *sym)