aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/util
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/Build2
-rw-r--r--tools/perf/util/annotate.c21
-rw-r--r--tools/perf/util/arm-spe-decoder/arm-spe-decoder.c59
-rw-r--r--tools/perf/util/arm-spe-decoder/arm-spe-decoder.h17
-rw-r--r--tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c601
-rw-r--r--tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h122
-rw-r--r--tools/perf/util/arm-spe.c2
-rw-r--r--tools/perf/util/auxtrace.c19
-rw-r--r--tools/perf/util/auxtrace.h2
-rw-r--r--tools/perf/util/bpf-event.c2
-rw-r--r--tools/perf/util/bpf-loader.c15
-rw-r--r--tools/perf/util/bpf-loader.h3
-rw-r--r--tools/perf/util/build-id.c177
-rw-r--r--tools/perf/util/build-id.h20
-rw-r--r--tools/perf/util/callchain.c99
-rw-r--r--tools/perf/util/callchain.h9
-rw-r--r--tools/perf/util/cgroup.c267
-rw-r--r--tools/perf/util/cgroup.h3
-rw-r--r--tools/perf/util/config.c2
-rw-r--r--tools/perf/util/config.h2
-rw-r--r--tools/perf/util/cpumap.c171
-rw-r--r--tools/perf/util/cpumap.h55
-rw-r--r--tools/perf/util/data.c60
-rw-r--r--tools/perf/util/data.h12
-rw-r--r--tools/perf/util/debug.c9
-rw-r--r--tools/perf/util/debug.h2
-rw-r--r--tools/perf/util/dso.c68
-rw-r--r--tools/perf/util/dso.h9
-rw-r--r--tools/perf/util/dsos.c9
-rw-r--r--tools/perf/util/dwarf-aux.c28
-rw-r--r--tools/perf/util/env.c15
-rw-r--r--tools/perf/util/env.h4
-rw-r--r--tools/perf/util/event.c2
-rw-r--r--tools/perf/util/event.h4
-rw-r--r--tools/perf/util/evlist.c411
-rw-r--r--tools/perf/util/evlist.h144
-rw-r--r--tools/perf/util/evsel.c169
-rw-r--r--tools/perf/util/evsel.h94
-rw-r--r--tools/perf/util/evswitch.c4
-rw-r--r--tools/perf/util/expr.c68
-rw-r--r--tools/perf/util/expr.h17
-rw-r--r--tools/perf/util/expr.y2
-rw-r--r--tools/perf/util/group.h8
-rw-r--r--tools/perf/util/hashmap.c3
-rw-r--r--tools/perf/util/hashmap.h27
-rw-r--r--tools/perf/util/header.c79
-rw-r--r--tools/perf/util/hist.c5
-rw-r--r--tools/perf/util/hist.h26
-rw-r--r--tools/perf/util/include/linux/linkage.h7
-rw-r--r--tools/perf/util/intel-pt.c11
-rw-r--r--tools/perf/util/jitdump.c14
-rw-r--r--tools/perf/util/machine.c96
-rw-r--r--tools/perf/util/machine.h4
-rw-r--r--tools/perf/util/map.c21
-rw-r--r--tools/perf/util/map.h14
-rw-r--r--tools/perf/util/map_symbol.h1
-rw-r--r--tools/perf/util/mem-events.c45
-rw-r--r--tools/perf/util/mem-events.h3
-rw-r--r--tools/perf/util/mem2node.c3
-rw-r--r--tools/perf/util/metricgroup.c439
-rw-r--r--tools/perf/util/metricgroup.h9
-rw-r--r--tools/perf/util/parse-events.c52
-rw-r--r--tools/perf/util/parse-events.h2
-rw-r--r--tools/perf/util/parse-events.l2
-rw-r--r--tools/perf/util/parse-events.y8
-rw-r--r--tools/perf/util/parse-regs-options.c2
-rw-r--r--tools/perf/util/perf_event_attr_fprintf.c2
-rw-r--r--tools/perf/util/pmu.c96
-rw-r--r--tools/perf/util/pmu.h3
-rw-r--r--tools/perf/util/print_binary.c2
-rw-r--r--tools/perf/util/probe-event.c69
-rw-r--r--tools/perf/util/probe-file.c13
-rw-r--r--tools/perf/util/probe-finder.c66
-rw-r--r--tools/perf/util/probe-finder.h7
-rw-r--r--tools/perf/util/python.c25
-rw-r--r--tools/perf/util/record.c12
-rw-r--r--tools/perf/util/record.h2
-rw-r--r--tools/perf/util/s390-cpumsf.c6
-rw-r--r--tools/perf/util/s390-sample-raw.c5
-rw-r--r--tools/perf/util/sample-raw.c4
-rw-r--r--tools/perf/util/sample-raw.h7
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c9
-rw-r--r--tools/perf/util/session.c73
-rw-r--r--tools/perf/util/sideband_evlist.c14
-rw-r--r--tools/perf/util/sort.c32
-rw-r--r--tools/perf/util/sort.h1
-rw-r--r--tools/perf/util/stat-display.c116
-rw-r--r--tools/perf/util/stat-shadow.c387
-rw-r--r--tools/perf/util/stat.c26
-rw-r--r--tools/perf/util/stat.h40
-rw-r--r--tools/perf/util/stream.c342
-rw-r--r--tools/perf/util/stream.h41
-rw-r--r--tools/perf/util/symbol-elf.c140
-rw-r--r--tools/perf/util/symbol-minimal.c31
-rw-r--r--tools/perf/util/symbol.c178
-rw-r--r--tools/perf/util/symbol.h13
-rw-r--r--tools/perf/util/synthetic-events.c23
-rw-r--r--tools/perf/util/topdown.c58
-rw-r--r--tools/perf/util/topdown.h12
-rw-r--r--tools/perf/util/tsc.c81
-rw-r--r--tools/perf/util/tsc.h5
-rw-r--r--tools/perf/util/unwind-libdw.c32
-rw-r--r--tools/perf/util/util.h6
103 files changed, 4186 insertions, 1475 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index cd5e41960e64..e2563d0154eb 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -101,6 +101,8 @@ perf-y += call-path.o
perf-y += rwsem.o
perf-y += thread-stack.o
perf-y += spark.o
+perf-y += topdown.o
+perf-y += stream.o
perf-$(CONFIG_AUXTRACE) += auxtrace.o
perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
perf-$(CONFIG_AUXTRACE) += intel-pt.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0a1fcf787538..ce8c07bc8c56 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -10,10 +10,6 @@
#include <inttypes.h>
#include <libgen.h>
#include <stdlib.h>
-#include <bpf/bpf.h>
-#include <bpf/btf.h>
-#include <bpf/libbpf.h>
-#include <linux/btf.h>
#include "util.h" // hex_width()
#include "ui/ui.h"
#include "sort.h"
@@ -152,6 +148,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
#include "arch/arm/annotate/instructions.c"
#include "arch/arm64/annotate/instructions.c"
#include "arch/csky/annotate/instructions.c"
+#include "arch/mips/annotate/instructions.c"
#include "arch/x86/annotate/instructions.c"
#include "arch/powerpc/annotate/instructions.c"
#include "arch/s390/annotate/instructions.c"
@@ -175,6 +172,13 @@ static struct arch architectures[] = {
.init = csky__annotate_init,
},
{
+ .name = "mips",
+ .init = mips__annotate_init,
+ .objdump = {
+ .comment_char = '#',
+ },
+ },
+ {
.name = "x86",
.init = x86__annotate_init,
.instructions = x86__instructions,
@@ -1578,8 +1582,7 @@ int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, s
char *build_id_msg = NULL;
if (dso->has_build_id) {
- build_id__sprintf(dso->build_id,
- sizeof(dso->build_id), bf + 15);
+ build_id__sprintf(&dso->bid, bf + 15);
build_id_msg = bf;
}
scnprintf(buf, buflen,
@@ -1677,6 +1680,10 @@ fallback:
#define PACKAGE "perf"
#include <bfd.h>
#include <dis-asm.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
static int symbol__disassemble_bpf(struct symbol *sym,
struct annotate_args *args)
@@ -3127,6 +3134,8 @@ static int annotation__config(const char *var, const char *value, void *data)
value);
} else if (!strcmp(var, "annotate.use_offset")) {
opt->use_offset = perf_config_bool("use_offset", value);
+ } else if (!strcmp(var, "annotate.disassembler_style")) {
+ opt->disassembler_style = value;
} else {
pr_debug("%s variable unknown, ignoring...", var);
}
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 93e063f22be5..90d575cee1b9 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -12,6 +12,7 @@
#include <string.h>
#include <stdint.h>
#include <stdlib.h>
+#include <linux/bitops.h>
#include <linux/compiler.h>
#include <linux/zalloc.h>
@@ -21,42 +22,51 @@
#include "arm-spe-decoder.h"
-#ifndef BIT
-#define BIT(n) (1UL << (n))
-#endif
-
static u64 arm_spe_calc_ip(int index, u64 payload)
{
- u8 *addr = (u8 *)&payload;
- int ns, el;
+ u64 ns, el, val;
/* Instruction virtual address or Branch target address */
if (index == SPE_ADDR_PKT_HDR_INDEX_INS ||
index == SPE_ADDR_PKT_HDR_INDEX_BRANCH) {
- ns = addr[7] & SPE_ADDR_PKT_NS;
- el = (addr[7] & SPE_ADDR_PKT_EL_MASK) >> SPE_ADDR_PKT_EL_OFFSET;
+ ns = SPE_ADDR_PKT_GET_NS(payload);
+ el = SPE_ADDR_PKT_GET_EL(payload);
+
+ /* Clean highest byte */
+ payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
/* Fill highest byte for EL1 or EL2 (VHE) mode */
if (ns && (el == SPE_ADDR_PKT_EL1 || el == SPE_ADDR_PKT_EL2))
- addr[7] = 0xff;
- /* Clean highest byte for other cases */
- else
- addr[7] = 0x0;
+ payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT;
/* Data access virtual address */
} else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT) {
- /* Fill highest byte if bits [48..55] is 0xff */
- if (addr[6] == 0xff)
- addr[7] = 0xff;
- /* Otherwise, cleanup tags */
- else
- addr[7] = 0x0;
+ /* Clean tags */
+ payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
+
+ /*
+ * Armv8 ARM (ARM DDI 0487F.c), chapter "D10.2.1 Address packet"
+ * defines the data virtual address payload format, the top byte
+ * (bits [63:56]) is assigned as top-byte tag; so we only can
+ * retrieve address value from bits [55:0].
+ *
+ * According to Documentation/arm64/memory.rst, if detects the
+ * specific pattern in bits [55:52] of payload which falls in
+ * the kernel space, should fixup the top byte and this allows
+ * perf tool to parse DSO symbol for data address correctly.
+ *
+ * For this reason, if detects the bits [55:52] is 0xf, will
+ * fill 0xff into the top byte.
+ */
+ val = SPE_ADDR_PKT_ADDR_GET_BYTE_6(payload);
+ if ((val & 0xf0ULL) == 0xf0ULL)
+ payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT;
/* Data access physical address */
} else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS) {
- /* Cleanup byte 7 */
- addr[7] = 0x0;
+ /* Clean highest byte */
+ payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
} else {
pr_err("unsupported address packet index: 0x%x\n", index);
}
@@ -182,16 +192,13 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
if (payload & BIT(EV_TLB_ACCESS))
decoder->record.type |= ARM_SPE_TLB_ACCESS;
- if ((idx == 2 || idx == 4 || idx == 8) &&
- (payload & BIT(EV_LLC_MISS)))
+ if (payload & BIT(EV_LLC_MISS))
decoder->record.type |= ARM_SPE_LLC_MISS;
- if ((idx == 2 || idx == 4 || idx == 8) &&
- (payload & BIT(EV_LLC_ACCESS)))
+ if (payload & BIT(EV_LLC_ACCESS))
decoder->record.type |= ARM_SPE_LLC_ACCESS;
- if ((idx == 2 || idx == 4 || idx == 8) &&
- (payload & BIT(EV_REMOTE_ACCESS)))
+ if (payload & BIT(EV_REMOTE_ACCESS))
decoder->record.type |= ARM_SPE_REMOTE_ACCESS;
if (payload & BIT(EV_MISPRED))
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index a5111a8d4360..24727b8ca7ff 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -13,23 +13,6 @@
#include "arm-spe-pkt-decoder.h"
-enum arm_spe_events {
- EV_EXCEPTION_GEN = 0,
- EV_RETIRED = 1,
- EV_L1D_ACCESS = 2,
- EV_L1D_REFILL = 3,
- EV_TLB_ACCESS = 4,
- EV_TLB_WALK = 5,
- EV_NOT_TAKEN = 6,
- EV_MISPRED = 7,
- EV_LLC_ACCESS = 8,
- EV_LLC_MISS = 9,
- EV_REMOTE_ACCESS = 10,
- EV_ALIGNMENT = 11,
- EV_PARTIAL_PREDICATE = 17,
- EV_EMPTY_PREDICATE = 18,
-};
-
enum arm_spe_sample_type {
ARM_SPE_L1D_ACCESS = 1 << 0,
ARM_SPE_L1D_MISS = 1 << 1,
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
index b94001b756c7..f3ac9d40cebf 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
@@ -8,36 +8,11 @@
#include <string.h>
#include <endian.h>
#include <byteswap.h>
+#include <linux/bitops.h>
+#include <stdarg.h>
#include "arm-spe-pkt-decoder.h"
-#define BIT(n) (1ULL << (n))
-
-#define NS_FLAG BIT(63)
-#define EL_FLAG (BIT(62) | BIT(61))
-
-#define SPE_HEADER0_PAD 0x0
-#define SPE_HEADER0_END 0x1
-#define SPE_HEADER0_ADDRESS 0x30 /* address packet (short) */
-#define SPE_HEADER0_ADDRESS_MASK 0x38
-#define SPE_HEADER0_COUNTER 0x18 /* counter packet (short) */
-#define SPE_HEADER0_COUNTER_MASK 0x38
-#define SPE_HEADER0_TIMESTAMP 0x71
-#define SPE_HEADER0_TIMESTAMP 0x71
-#define SPE_HEADER0_EVENTS 0x2
-#define SPE_HEADER0_EVENTS_MASK 0xf
-#define SPE_HEADER0_SOURCE 0x3
-#define SPE_HEADER0_SOURCE_MASK 0xf
-#define SPE_HEADER0_CONTEXT 0x24
-#define SPE_HEADER0_CONTEXT_MASK 0x3c
-#define SPE_HEADER0_OP_TYPE 0x8
-#define SPE_HEADER0_OP_TYPE_MASK 0x3c
-#define SPE_HEADER1_ALIGNMENT 0x0
-#define SPE_HEADER1_ADDRESS 0xb0 /* address packet (extended) */
-#define SPE_HEADER1_ADDRESS_MASK 0xf8
-#define SPE_HEADER1_COUNTER 0x98 /* counter packet (extended) */
-#define SPE_HEADER1_COUNTER_MASK 0xf8
-
#if __BYTE_ORDER == __BIG_ENDIAN
#define le16_to_cpu bswap_16
#define le32_to_cpu bswap_32
@@ -70,27 +45,28 @@ const char *arm_spe_pkt_name(enum arm_spe_pkt_type type)
return arm_spe_packet_name[type];
}
-/* return ARM SPE payload size from its encoding,
- * which is in bits 5:4 of the byte.
- * 00 : byte
- * 01 : halfword (2)
- * 10 : word (4)
- * 11 : doubleword (8)
+/*
+ * Extracts the field "sz" from header bits and converts to bytes:
+ * 00 : byte (1)
+ * 01 : halfword (2)
+ * 10 : word (4)
+ * 11 : doubleword (8)
*/
-static int payloadlen(unsigned char byte)
+static unsigned int arm_spe_payload_len(unsigned char hdr)
{
- return 1 << ((byte & 0x30) >> 4);
+ return 1U << ((hdr & GENMASK_ULL(5, 4)) >> 4);
}
static int arm_spe_get_payload(const unsigned char *buf, size_t len,
+ unsigned char ext_hdr,
struct arm_spe_pkt *packet)
{
- size_t payload_len = payloadlen(buf[0]);
+ size_t payload_len = arm_spe_payload_len(buf[ext_hdr]);
- if (len < 1 + payload_len)
+ if (len < 1 + ext_hdr + payload_len)
return ARM_SPE_NEED_MORE_BYTES;
- buf++;
+ buf += 1 + ext_hdr;
switch (payload_len) {
case 1: packet->payload = *(uint8_t *)buf; break;
@@ -100,7 +76,7 @@ static int arm_spe_get_payload(const unsigned char *buf, size_t len,
default: return ARM_SPE_BAD_PACKET;
}
- return 1 + payload_len;
+ return 1 + ext_hdr + payload_len;
}
static int arm_spe_get_pad(struct arm_spe_pkt *packet)
@@ -131,127 +107,128 @@ static int arm_spe_get_timestamp(const unsigned char *buf, size_t len,
struct arm_spe_pkt *packet)
{
packet->type = ARM_SPE_TIMESTAMP;
- return arm_spe_get_payload(buf, len, packet);
+ return arm_spe_get_payload(buf, len, 0, packet);
}
static int arm_spe_get_events(const unsigned char *buf, size_t len,
struct arm_spe_pkt *packet)
{
- int ret = arm_spe_get_payload(buf, len, packet);
-
packet->type = ARM_SPE_EVENTS;
/* we use index to identify Events with a less number of
* comparisons in arm_spe_pkt_desc(): E.g., the LLC-ACCESS,
- * LLC-REFILL, and REMOTE-ACCESS events are identified iff
+ * LLC-REFILL, and REMOTE-ACCESS events are identified if
* index > 1.
*/
- packet->index = ret - 1;
+ packet->index = arm_spe_payload_len(buf[0]);
- return ret;
+ return arm_spe_get_payload(buf, len, 0, packet);
}
static int arm_spe_get_data_source(const unsigned char *buf, size_t len,
struct arm_spe_pkt *packet)
{
packet->type = ARM_SPE_DATA_SOURCE;
- return arm_spe_get_payload(buf, len, packet);
+ return arm_spe_get_payload(buf, len, 0, packet);
}
static int arm_spe_get_context(const unsigned char *buf, size_t len,
struct arm_spe_pkt *packet)
{
packet->type = ARM_SPE_CONTEXT;
- packet->index = buf[0] & 0x3;
-
- return arm_spe_get_payload(buf, len, packet);
+ packet->index = SPE_CTX_PKT_HDR_INDEX(buf[0]);
+ return arm_spe_get_payload(buf, len, 0, packet);
}
static int arm_spe_get_op_type(const unsigned char *buf, size_t len,
struct arm_spe_pkt *packet)
{
packet->type = ARM_SPE_OP_TYPE;
- packet->index = buf[0] & 0x3;
- return arm_spe_get_payload(buf, len, packet);
+ packet->index = SPE_OP_PKT_HDR_CLASS(buf[0]);
+ return arm_spe_get_payload(buf, len, 0, packet);
}
static int arm_spe_get_counter(const unsigned char *buf, size_t len,
const unsigned char ext_hdr, struct arm_spe_pkt *packet)
{
- if (len < 2)
- return ARM_SPE_NEED_MORE_BYTES;
-
packet->type = ARM_SPE_COUNTER;
+
if (ext_hdr)
- packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7);
+ packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]);
else
- packet->index = buf[0] & 0x7;
-
- packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
+ packet->index = SPE_HDR_SHORT_INDEX(buf[0]);
- return 1 + ext_hdr + 2;
+ return arm_spe_get_payload(buf, len, ext_hdr, packet);
}
static int arm_spe_get_addr(const unsigned char *buf, size_t len,
const unsigned char ext_hdr, struct arm_spe_pkt *packet)
{
- if (len < 8)
- return ARM_SPE_NEED_MORE_BYTES;
-
packet->type = ARM_SPE_ADDRESS;
+
if (ext_hdr)
- packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7);
+ packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]);
else
- packet->index = buf[0] & 0x7;
-
- memcpy_le64(&packet->payload, buf + 1, 8);
+ packet->index = SPE_HDR_SHORT_INDEX(buf[0]);
- return 1 + ext_hdr + 8;
+ return arm_spe_get_payload(buf, len, ext_hdr, packet);
}
static int arm_spe_do_get_packet(const unsigned char *buf, size_t len,
struct arm_spe_pkt *packet)
{
- unsigned int byte;
+ unsigned int hdr;
+ unsigned char ext_hdr = 0;
memset(packet, 0, sizeof(struct arm_spe_pkt));
if (!len)
return ARM_SPE_NEED_MORE_BYTES;
- byte = buf[0];
- if (byte == SPE_HEADER0_PAD)
+ hdr = buf[0];
+
+ if (hdr == SPE_HEADER0_PAD)
return arm_spe_get_pad(packet);
- else if (byte == SPE_HEADER0_END) /* no timestamp at end of record */
+
+ if (hdr == SPE_HEADER0_END) /* no timestamp at end of record */
return arm_spe_get_end(packet);
- else if (byte & 0xc0 /* 0y11xxxxxx */) {
- if (byte & 0x80) {
- if ((byte & SPE_HEADER0_ADDRESS_MASK) == SPE_HEADER0_ADDRESS)
- return arm_spe_get_addr(buf, len, 0, packet);
- if ((byte & SPE_HEADER0_COUNTER_MASK) == SPE_HEADER0_COUNTER)
- return arm_spe_get_counter(buf, len, 0, packet);
- } else
- if (byte == SPE_HEADER0_TIMESTAMP)
- return arm_spe_get_timestamp(buf, len, packet);
- else if ((byte & SPE_HEADER0_EVENTS_MASK) == SPE_HEADER0_EVENTS)
- return arm_spe_get_events(buf, len, packet);
- else if ((byte & SPE_HEADER0_SOURCE_MASK) == SPE_HEADER0_SOURCE)
- return arm_spe_get_data_source(buf, len, packet);
- else if ((byte & SPE_HEADER0_CONTEXT_MASK) == SPE_HEADER0_CONTEXT)
- return arm_spe_get_context(buf, len, packet);
- else if ((byte & SPE_HEADER0_OP_TYPE_MASK) == SPE_HEADER0_OP_TYPE)
- return arm_spe_get_op_type(buf, len, packet);
- } else if ((byte & 0xe0) == 0x20 /* 0y001xxxxx */) {
- /* 16-bit header */
- byte = buf[1];
- if (byte == SPE_HEADER1_ALIGNMENT)
+
+ if (hdr == SPE_HEADER0_TIMESTAMP)
+ return arm_spe_get_timestamp(buf, len, packet);
+
+ if ((hdr & SPE_HEADER0_MASK1) == SPE_HEADER0_EVENTS)
+ return arm_spe_get_events(buf, len, packet);
+
+ if ((hdr & SPE_HEADER0_MASK1) == SPE_HEADER0_SOURCE)
+ return arm_spe_get_data_source(buf, len, packet);
+
+ if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_CONTEXT)
+ return arm_spe_get_context(buf, len, packet);
+
+ if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_OP_TYPE)
+ return arm_spe_get_op_type(buf, len, packet);
+
+ if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) {
+ /* 16-bit extended format header */
+ ext_hdr = 1;
+
+ hdr = buf[1];
+ if (hdr == SPE_HEADER1_ALIGNMENT)
return arm_spe_get_alignment(buf, len, packet);
- else if ((byte & SPE_HEADER1_ADDRESS_MASK) == SPE_HEADER1_ADDRESS)
- return arm_spe_get_addr(buf, len, 1, packet);
- else if ((byte & SPE_HEADER1_COUNTER_MASK) == SPE_HEADER1_COUNTER)
- return arm_spe_get_counter(buf, len, 1, packet);
}
+ /*
+ * The short format header's byte 0 or the extended format header's
+ * byte 1 has been assigned to 'hdr', which uses the same encoding for
+ * address packet and counter packet, so don't need to distinguish if
+ * it's short format or extended format and handle in once.
+ */
+ if ((hdr & SPE_HEADER0_MASK3) == SPE_HEADER0_ADDRESS)
+ return arm_spe_get_addr(buf, len, ext_hdr, packet);
+
+ if ((hdr & SPE_HEADER0_MASK3) == SPE_HEADER0_COUNTER)
+ return arm_spe_get_counter(buf, len, ext_hdr, packet);
+
return ARM_SPE_BAD_PACKET;
}
@@ -271,192 +248,286 @@ int arm_spe_get_packet(const unsigned char *buf, size_t len,
return ret;
}
+static int arm_spe_pkt_out_string(int *err, char **buf_p, size_t *blen,
+ const char *fmt, ...)
+{
+ va_list ap;
+ int ret;
+
+ /* Bail out if any error occurred */
+ if (err && *err)
+ return *err;
+
+ va_start(ap, fmt);
+ ret = vsnprintf(*buf_p, *blen, fmt, ap);
+ va_end(ap);
+
+ if (ret < 0) {
+ if (err && !*err)
+ *err = ret;
+
+ /*
+ * A return value of *blen or more means that the output was
+ * truncated and the buffer is overrun.
+ */
+ } else if ((size_t)ret >= *blen) {
+ (*buf_p)[*blen - 1] = '\0';
+
+ /*
+ * Set *err to 'ret' to avoid overflow if tries to
+ * fill this buffer sequentially.
+ */
+ if (err && !*err)
+ *err = ret;
+ } else {
+ *buf_p += ret;
+ *blen -= ret;
+ }
+
+ return ret;
+}
+
+static int arm_spe_pkt_desc_event(const struct arm_spe_pkt *packet,
+ char *buf, size_t buf_len)
+{
+ u64 payload = packet->payload;
+ int err = 0;
+
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, "EV");
+
+ if (payload & BIT(EV_EXCEPTION_GEN))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCEPTION-GEN");
+ if (payload & BIT(EV_RETIRED))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " RETIRED");
+ if (payload & BIT(EV_L1D_ACCESS))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " L1D-ACCESS");
+ if (payload & BIT(EV_L1D_REFILL))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " L1D-REFILL");
+ if (payload & BIT(EV_TLB_ACCESS))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " TLB-ACCESS");
+ if (payload & BIT(EV_TLB_WALK))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " TLB-REFILL");
+ if (payload & BIT(EV_NOT_TAKEN))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " NOT-TAKEN");
+ if (payload & BIT(EV_MISPRED))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " MISPRED");
+ if (payload & BIT(EV_LLC_ACCESS))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " LLC-ACCESS");
+ if (payload & BIT(EV_LLC_MISS))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " LLC-REFILL");
+ if (payload & BIT(EV_REMOTE_ACCESS))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " REMOTE-ACCESS");
+ if (payload & BIT(EV_ALIGNMENT))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " ALIGNMENT");
+ if (payload & BIT(EV_PARTIAL_PREDICATE))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-PARTIAL-PRED");
+ if (payload & BIT(EV_EMPTY_PREDICATE))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-EMPTY-PRED");
+
+ return err;
+}
+
+static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet,
+ char *buf, size_t buf_len)
+{
+ u64 payload = packet->payload;
+ int err = 0;
+
+ switch (packet->index) {
+ case SPE_OP_PKT_HDR_CLASS_OTHER:
+ if (SPE_OP_PKT_IS_OTHER_SVE_OP(payload)) {
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, "SVE-OTHER");
+
+ /* SVE effective vector length */
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d",
+ SPE_OP_PKG_SVE_EVL(payload));
+
+ if (payload & SPE_OP_PKT_SVE_FP)
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " FP");
+ if (payload & SPE_OP_PKT_SVE_PRED)
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED");
+ } else {
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, "OTHER");
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " %s",
+ payload & SPE_OP_PKT_COND ?
+ "COND-SELECT" : "INSN-OTHER");
+ }
+ break;
+ case SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len,
+ payload & 0x1 ? "ST" : "LD");
+
+ if (SPE_OP_PKT_IS_LDST_ATOMIC(payload)) {
+ if (payload & SPE_OP_PKT_AT)
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " AT");
+ if (payload & SPE_OP_PKT_EXCL)
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCL");
+ if (payload & SPE_OP_PKT_AR)
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " AR");
+ }
+
+ switch (SPE_OP_PKT_LDST_SUBCLASS_GET(payload)) {
+ case SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " SIMD-FP");
+ break;
+ case SPE_OP_PKT_LDST_SUBCLASS_GP_REG:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " GP-REG");
+ break;
+ case SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " UNSPEC-REG");
+ break;
+ case SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " NV-SYSREG");
+ break;
+ default:
+ break;
+ }
+
+ if (SPE_OP_PKT_IS_LDST_SVE(payload)) {
+ /* SVE effective vector length */
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d",
+ SPE_OP_PKG_SVE_EVL(payload));
+
+ if (payload & SPE_OP_PKT_SVE_PRED)
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED");
+ if (payload & SPE_OP_PKT_SVE_SG)
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " SG");
+ }
+ break;
+ case SPE_OP_PKT_HDR_CLASS_BR_ERET:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, "B");
+
+ if (payload & SPE_OP_PKT_COND)
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " COND");
+
+ if (SPE_OP_PKT_IS_INDIRECT_BRANCH(payload))
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, " IND");
+
+ break;
+ default:
+ /* Unknown index */
+ err = -1;
+ break;
+ }
+
+ return err;
+}
+
+static int arm_spe_pkt_desc_addr(const struct arm_spe_pkt *packet,
+ char *buf, size_t buf_len)
+{
+ int ns, el, idx = packet->index;
+ int ch, pat;
+ u64 payload = packet->payload;
+ int err = 0;
+
+ switch (idx) {
+ case SPE_ADDR_PKT_HDR_INDEX_INS:
+ case SPE_ADDR_PKT_HDR_INDEX_BRANCH:
+ ns = !!SPE_ADDR_PKT_GET_NS(payload);
+ el = SPE_ADDR_PKT_GET_EL(payload);
+ payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
+ arm_spe_pkt_out_string(&err, &buf, &buf_len,
+ "%s 0x%llx el%d ns=%d",
+ (idx == 1) ? "TGT" : "PC", payload, el, ns);
+ break;
+ case SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len,
+ "VA 0x%llx", payload);
+ break;
+ case SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS:
+ ns = !!SPE_ADDR_PKT_GET_NS(payload);
+ ch = !!SPE_ADDR_PKT_GET_CH(payload);
+ pat = SPE_ADDR_PKT_GET_PAT(payload);
+ payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
+ arm_spe_pkt_out_string(&err, &buf, &buf_len,
+ "PA 0x%llx ns=%d ch=%d pat=%x",
+ payload, ns, ch, pat);
+ break;
+ default:
+ /* Unknown index */
+ err = -1;
+ break;
+ }
+
+ return err;
+}
+
+static int arm_spe_pkt_desc_counter(const struct arm_spe_pkt *packet,
+ char *buf, size_t buf_len)
+{
+ u64 payload = packet->payload;
+ const char *name = arm_spe_pkt_name(packet->type);
+ int err = 0;
+
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, "%s %d ", name,
+ (unsigned short)payload);
+
+ switch (packet->index) {
+ case SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, "TOT");
+ break;
+ case SPE_CNT_PKT_HDR_INDEX_ISSUE_LAT:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, "ISSUE");
+ break;
+ case SPE_CNT_PKT_HDR_INDEX_TRANS_LAT:
+ arm_spe_pkt_out_string(&err, &buf, &buf_len, "XLAT");
+ break;
+ default:
+ break;
+ }
+
+ return err;
+}
+
int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf,
size_t buf_len)
{
- int ret, ns, el, idx = packet->index;
+ int idx = packet->index;
unsigned long long payload = packet->payload;
const char *name = arm_spe_pkt_name(packet->type);
+ char *buf_orig = buf;
+ size_t blen = buf_len;
+ int err = 0;
switch (packet->type) {
case ARM_SPE_BAD:
case ARM_SPE_PAD:
case ARM_SPE_END:
- return snprintf(buf, buf_len, "%s", name);
- case ARM_SPE_EVENTS: {
- size_t blen = buf_len;
-
- ret = 0;
- ret = snprintf(buf, buf_len, "EV");
- buf += ret;
- blen -= ret;
- if (payload & 0x1) {
- ret = snprintf(buf, buf_len, " EXCEPTION-GEN");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x2) {
- ret = snprintf(buf, buf_len, " RETIRED");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x4) {
- ret = snprintf(buf, buf_len, " L1D-ACCESS");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x8) {
- ret = snprintf(buf, buf_len, " L1D-REFILL");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x10) {
- ret = snprintf(buf, buf_len, " TLB-ACCESS");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x20) {
- ret = snprintf(buf, buf_len, " TLB-REFILL");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x40) {
- ret = snprintf(buf, buf_len, " NOT-TAKEN");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x80) {
- ret = snprintf(buf, buf_len, " MISPRED");
- buf += ret;
- blen -= ret;
- }
- if (idx > 1) {
- if (payload & 0x100) {
- ret = snprintf(buf, buf_len, " LLC-ACCESS");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x200) {
- ret = snprintf(buf, buf_len, " LLC-REFILL");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x400) {
- ret = snprintf(buf, buf_len, " REMOTE-ACCESS");
- buf += ret;
- blen -= ret;
- }
- }
- if (ret < 0)
- return ret;
- blen -= ret;
- return buf_len - blen;
- }
+ arm_spe_pkt_out_string(&err, &buf, &blen, "%s", name);
+ break;
+ case ARM_SPE_EVENTS:
+ err = arm_spe_pkt_desc_event(packet, buf, buf_len);
+ break;
case ARM_SPE_OP_TYPE:
- switch (idx) {
- case 0: return snprintf(buf, buf_len, "%s", payload & 0x1 ?
- "COND-SELECT" : "INSN-OTHER");
- case 1: {
- size_t blen = buf_len;
-
- if (payload & 0x1)
- ret = snprintf(buf, buf_len, "ST");
- else
- ret = snprintf(buf, buf_len, "LD");
- buf += ret;
- blen -= ret;
- if (payload & 0x2) {
- if (payload & 0x4) {
- ret = snprintf(buf, buf_len, " AT");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x8) {
- ret = snprintf(buf, buf_len, " EXCL");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x10) {
- ret = snprintf(buf, buf_len, " AR");
- buf += ret;
- blen -= ret;
- }
- } else if (payload & 0x4) {
- ret = snprintf(buf, buf_len, " SIMD-FP");
- buf += ret;
- blen -= ret;
- }
- if (ret < 0)
- return ret;
- blen -= ret;
- return buf_len - blen;
- }
- case 2: {
- size_t blen = buf_len;
-
- ret = snprintf(buf, buf_len, "B");
- buf += ret;
- blen -= ret;
- if (payload & 0x1) {
- ret = snprintf(buf, buf_len, " COND");
- buf += ret;
- blen -= ret;
- }
- if (payload & 0x2) {
- ret = snprintf(buf, buf_len, " IND");
- buf += ret;
- blen -= ret;
- }
- if (ret < 0)
- return ret;
- blen -= ret;
- return buf_len - blen;
- }
- default: return 0;
- }
+ err = arm_spe_pkt_desc_op_type(packet, buf, buf_len);
+ break;
case ARM_SPE_DATA_SOURCE:
case ARM_SPE_TIMESTAMP:
- return snprintf(buf, buf_len, "%s %lld", name, payload);
+ arm_spe_pkt_out_string(&err, &buf, &blen, "%s %lld", name, payload);
+ break;
case ARM_SPE_ADDRESS:
- switch (idx) {
- case 0:
- case 1: ns = !!(packet->payload & NS_FLAG);
- el = (packet->payload & EL_FLAG) >> 61;
- payload &= ~(0xffULL << 56);
- return snprintf(buf, buf_len, "%s 0x%llx el%d ns=%d",
- (idx == 1) ? "TGT" : "PC", payload, el, ns);
- case 2: return snprintf(buf, buf_len, "VA 0x%llx", payload);
- case 3: ns = !!(packet->payload & NS_FLAG);
- payload &= ~(0xffULL << 56);
- return snprintf(buf, buf_len, "PA 0x%llx ns=%d",
- payload, ns);
- default: return 0;
- }
+ err = arm_spe_pkt_desc_addr(packet, buf, buf_len);
+ break;
case ARM_SPE_CONTEXT:
- return snprintf(buf, buf_len, "%s 0x%lx el%d", name,
- (unsigned long)payload, idx + 1);
- case ARM_SPE_COUNTER: {
- size_t blen = buf_len;
-
- ret = snprintf(buf, buf_len, "%s %d ", name,
- (unsigned short)payload);
- buf += ret;
- blen -= ret;
- switch (idx) {
- case 0: ret = snprintf(buf, buf_len, "TOT"); break;
- case 1: ret = snprintf(buf, buf_len, "ISSUE"); break;
- case 2: ret = snprintf(buf, buf_len, "XLAT"); break;
- default: ret = 0;
- }
- if (ret < 0)
- return ret;
- blen -= ret;
- return buf_len - blen;
- }
+ arm_spe_pkt_out_string(&err, &buf, &blen, "%s 0x%lx el%d",
+ name, (unsigned long)payload, idx + 1);
+ break;
+ case ARM_SPE_COUNTER:
+ err = arm_spe_pkt_desc_counter(packet, buf, buf_len);
+ break;
default:
+ /* Unknown packet type */
+ err = -1;
break;
}
- return snprintf(buf, buf_len, "%s 0x%llx (%d)",
- name, payload, packet->index);
+ /* Output raw data if detect any error */
+ if (err) {
+ err = 0;
+ arm_spe_pkt_out_string(&err, &buf_orig, &buf_len, "%s 0x%llx (%d)",
+ name, payload, packet->index);
+ }
+
+ return err;
}
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h
index 4c870521b8eb..9b970e7bf1e2 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h
@@ -36,19 +36,115 @@ struct arm_spe_pkt {
uint64_t payload;
};
-#define SPE_ADDR_PKT_HDR_INDEX_INS (0x0)
-#define SPE_ADDR_PKT_HDR_INDEX_BRANCH (0x1)
-#define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT (0x2)
-#define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS (0x3)
-
-#define SPE_ADDR_PKT_NS BIT(7)
-#define SPE_ADDR_PKT_CH BIT(6)
-#define SPE_ADDR_PKT_EL_OFFSET (5)
-#define SPE_ADDR_PKT_EL_MASK (0x3 << SPE_ADDR_PKT_EL_OFFSET)
-#define SPE_ADDR_PKT_EL0 (0)
-#define SPE_ADDR_PKT_EL1 (1)
-#define SPE_ADDR_PKT_EL2 (2)
-#define SPE_ADDR_PKT_EL3 (3)
+/* Short header (HEADER0) and extended header (HEADER1) */
+#define SPE_HEADER0_PAD 0x0
+#define SPE_HEADER0_END 0x1
+#define SPE_HEADER0_TIMESTAMP 0x71
+/* Mask for event & data source */
+#define SPE_HEADER0_MASK1 (GENMASK_ULL(7, 6) | GENMASK_ULL(3, 0))
+#define SPE_HEADER0_EVENTS 0x42
+#define SPE_HEADER0_SOURCE 0x43
+/* Mask for context & operation */
+#define SPE_HEADER0_MASK2 GENMASK_ULL(7, 2)
+#define SPE_HEADER0_CONTEXT 0x64
+#define SPE_HEADER0_OP_TYPE 0x48
+/* Mask for extended format */
+#define SPE_HEADER0_EXTENDED 0x20
+/* Mask for address & counter */
+#define SPE_HEADER0_MASK3 GENMASK_ULL(7, 3)
+#define SPE_HEADER0_ADDRESS 0xb0
+#define SPE_HEADER0_COUNTER 0x98
+#define SPE_HEADER1_ALIGNMENT 0x0
+
+#define SPE_HDR_SHORT_INDEX(h) ((h) & GENMASK_ULL(2, 0))
+#define SPE_HDR_EXTENDED_INDEX(h0, h1) (((h0) & GENMASK_ULL(1, 0)) << 3 | \
+ SPE_HDR_SHORT_INDEX(h1))
+
+/* Address packet header */
+#define SPE_ADDR_PKT_HDR_INDEX_INS 0x0
+#define SPE_ADDR_PKT_HDR_INDEX_BRANCH 0x1
+#define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT 0x2
+#define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS 0x3
+
+/* Address packet payload */
+#define SPE_ADDR_PKT_ADDR_BYTE7_SHIFT 56
+#define SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(v) ((v) & GENMASK_ULL(55, 0))
+#define SPE_ADDR_PKT_ADDR_GET_BYTE_6(v) (((v) & GENMASK_ULL(55, 48)) >> 48)
+
+#define SPE_ADDR_PKT_GET_NS(v) (((v) & BIT_ULL(63)) >> 63)
+#define SPE_ADDR_PKT_GET_EL(v) (((v) & GENMASK_ULL(62, 61)) >> 61)
+#define SPE_ADDR_PKT_GET_CH(v) (((v) & BIT_ULL(62)) >> 62)
+#define SPE_ADDR_PKT_GET_PAT(v) (((v) & GENMASK_ULL(59, 56)) >> 56)
+
+#define SPE_ADDR_PKT_EL0 0
+#define SPE_ADDR_PKT_EL1 1
+#define SPE_ADDR_PKT_EL2 2
+#define SPE_ADDR_PKT_EL3 3
+
+/* Context packet header */
+#define SPE_CTX_PKT_HDR_INDEX(h) ((h) & GENMASK_ULL(1, 0))
+
+/* Counter packet header */
+#define SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT 0x0
+#define SPE_CNT_PKT_HDR_INDEX_ISSUE_LAT 0x1
+#define SPE_CNT_PKT_HDR_INDEX_TRANS_LAT 0x2
+
+/* Event packet payload */
+enum arm_spe_events {
+ EV_EXCEPTION_GEN = 0,
+ EV_RETIRED = 1,
+ EV_L1D_ACCESS = 2,
+ EV_L1D_REFILL = 3,
+ EV_TLB_ACCESS = 4,
+ EV_TLB_WALK = 5,
+ EV_NOT_TAKEN = 6,
+ EV_MISPRED = 7,
+ EV_LLC_ACCESS = 8,
+ EV_LLC_MISS = 9,
+ EV_REMOTE_ACCESS = 10,
+ EV_ALIGNMENT = 11,
+ EV_PARTIAL_PREDICATE = 17,
+ EV_EMPTY_PREDICATE = 18,
+};
+
+/* Operation packet header */
+#define SPE_OP_PKT_HDR_CLASS(h) ((h) & GENMASK_ULL(1, 0))
+#define SPE_OP_PKT_HDR_CLASS_OTHER 0x0
+#define SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC 0x1
+#define SPE_OP_PKT_HDR_CLASS_BR_ERET 0x2
+
+#define SPE_OP_PKT_IS_OTHER_SVE_OP(v) (((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x8)
+
+#define SPE_OP_PKT_COND BIT(0)
+
+#define SPE_OP_PKT_LDST_SUBCLASS_GET(v) ((v) & GENMASK_ULL(7, 1))
+#define SPE_OP_PKT_LDST_SUBCLASS_GP_REG 0x0
+#define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP 0x4
+#define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG 0x10
+#define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG 0x30
+
+#define SPE_OP_PKT_IS_LDST_ATOMIC(v) (((v) & (GENMASK_ULL(7, 5) | BIT(1))) == 0x2)
+
+#define SPE_OP_PKT_AR BIT(4)
+#define SPE_OP_PKT_EXCL BIT(3)
+#define SPE_OP_PKT_AT BIT(2)
+#define SPE_OP_PKT_ST BIT(0)
+
+#define SPE_OP_PKT_IS_LDST_SVE(v) (((v) & (BIT(3) | BIT(1))) == 0x8)
+
+#define SPE_OP_PKT_SVE_SG BIT(7)
+/*
+ * SVE effective vector length (EVL) is stored in byte 0 bits [6:4];
+ * the length is rounded up to a power of two and use 32 as one step,
+ * so EVL calculation is:
+ *
+ * 32 * (2 ^ bits [6:4]) = 32 << (bits [6:4])
+ */
+#define SPE_OP_PKG_SVE_EVL(v) (32 << (((v) & GENMASK_ULL(6, 4)) >> 4))
+#define SPE_OP_PKT_SVE_PRED BIT(2)
+#define SPE_OP_PKT_SVE_FP BIT(1)
+
+#define SPE_OP_PKT_IS_INDIRECT_BRANCH(v) (((v) & GENMASK_ULL(7, 1)) == 0x2)
const char *arm_spe_pkt_name(enum arm_spe_pkt_type);
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 3882a5360ada..8901a1656a41 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -113,7 +113,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
if (ret > 0) {
ret = arm_spe_pkt_desc(&packet, desc,
ARM_SPE_PKT_DESC_MAX);
- if (ret > 0)
+ if (!ret)
color_fprintf(stdout, color, " %s\n", desc);
} else {
color_fprintf(stdout, color, " Bad packet!\n");
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 42a85c86421d..a60878498139 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -62,9 +62,7 @@
* Make a group from 'leader' to 'last', requiring that the events were not
* already grouped to a different leader.
*/
-static int perf_evlist__regroup(struct evlist *evlist,
- struct evsel *leader,
- struct evsel *last)
+static int evlist__regroup(struct evlist *evlist, struct evsel *leader, struct evsel *last)
{
struct evsel *evsel;
bool grp;
@@ -658,8 +656,7 @@ int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx)
if (evsel->core.attr.type == itr->pmu->type) {
if (evsel->disabled)
return 0;
- return perf_evlist__enable_event_idx(itr->evlist, evsel,
- idx);
+ return evlist__enable_event_idx(itr->evlist, evsel, idx);
}
}
return -EINVAL;
@@ -776,7 +773,7 @@ no_opt:
evsel->core.attr.aux_sample_size = term->val.aux_sample_size;
/* If possible, group with the AUX event */
if (aux_evsel && evsel->core.attr.aux_sample_size)
- perf_evlist__regroup(evlist, aux_evsel, evsel);
+ evlist__regroup(evlist, aux_evsel, evsel);
}
}
@@ -1017,7 +1014,7 @@ struct auxtrace_queue *auxtrace_queues__sample_queue(struct auxtrace_queues *que
if (!id)
return NULL;
- sid = perf_evlist__id2sid(session->evlist, id);
+ sid = evlist__id2sid(session->evlist, id);
if (!sid)
return NULL;
@@ -1047,7 +1044,7 @@ int auxtrace_queues__add_sample(struct auxtrace_queues *queues,
if (!id)
return -EINVAL;
- sid = perf_evlist__id2sid(session->evlist, id);
+ sid = evlist__id2sid(session->evlist, id);
if (!sid)
return -ENOENT;
@@ -1082,7 +1079,7 @@ static int auxtrace_queue_data_cb(struct perf_session *session,
if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE)
return 0;
- err = perf_evlist__parse_sample(session->evlist, event, &sample);
+ err = evlist__parse_sample(session->evlist, event, &sample);
if (err)
return err;
@@ -1333,6 +1330,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
synth_opts->flc = true;
synth_opts->llc = true;
synth_opts->tlb = true;
+ synth_opts->mem = true;
synth_opts->remote_access = true;
if (no_sample) {
@@ -1554,6 +1552,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
case 'a':
synth_opts->remote_access = true;
break;
+ case 'M':
+ synth_opts->mem = true;
+ break;
case 'q':
synth_opts->quick += 1;
break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 951d2d14cf24..7e5c9e1552bd 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -88,6 +88,7 @@ enum itrace_period_type {
* @llc: whether to synthesize last level cache events
* @tlb: whether to synthesize TLB events
* @remote_access: whether to synthesize remote access events
+ * @mem: whether to synthesize memory events
* @callchain_sz: maximum callchain size
* @last_branch_sz: branch context size
* @period: 'instructions' events period
@@ -126,6 +127,7 @@ struct itrace_synth_opts {
bool llc;
bool tlb;
bool remote_access;
+ bool mem;
unsigned int callchain_sz;
unsigned int last_branch_sz;
unsigned long long period;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 3742511a08d1..57d58c81a5f8 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -526,7 +526,7 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
*/
attr.wakeup_watermark = 1;
- return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
+ return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
}
void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 2feb751516ab..9087f1bffd3d 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -328,12 +328,6 @@ config_bpf_program(struct bpf_program *prog)
probe_conf.no_inlines = false;
probe_conf.force_add = false;
- config_str = bpf_program__title(prog, false);
- if (IS_ERR(config_str)) {
- pr_debug("bpf: unable to get title for program\n");
- return PTR_ERR(config_str);
- }
-
priv = calloc(sizeof(*priv), 1);
if (!priv) {
pr_debug("bpf: failed to alloc priv\n");
@@ -341,6 +335,7 @@ config_bpf_program(struct bpf_program *prog)
}
pev = &priv->pev;
+ config_str = bpf_program__section_name(prog);
pr_debug("bpf: config program '%s'\n", config_str);
err = parse_prog_config(config_str, &main_str, &is_tp, pev);
if (err)
@@ -454,10 +449,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n,
if (err) {
const char *title;
- title = bpf_program__title(prog, false);
- if (!title)
- title = "[unknown]";
-
+ title = bpf_program__section_name(prog);
pr_debug("Failed to generate prologue for program %s\n",
title);
return err;
@@ -1066,12 +1058,11 @@ __bpf_map__config_event(struct bpf_map *map,
struct parse_events_term *term,
struct evlist *evlist)
{
- struct evsel *evsel;
const struct bpf_map_def *def;
struct bpf_map_op *op;
const char *map_name = bpf_map__name(map);
+ struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str);
- evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
if (!evsel) {
pr_debug("Event (for '%s') '%s' doesn't exist\n",
map_name, term->val.str);
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 25251d63164c..5d1c725cea29 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -8,6 +8,8 @@
#include <linux/compiler.h>
#include <linux/err.h>
+
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/libbpf.h>
enum bpf_loader_errno {
@@ -38,6 +40,7 @@ enum bpf_loader_errno {
BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG, /* Index too large */
__BPF_LOADER_ERRNO__END,
};
+#endif // HAVE_LIBBPF_SUPPORT
struct evsel;
struct evlist;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 31207b6e2066..02df36b30ac5 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -37,6 +37,8 @@
#include <linux/ctype.h>
#include <linux/zalloc.h>
+#include <linux/string.h>
+#include <asm/bug.h>
static bool no_buildid_cache;
@@ -95,13 +97,15 @@ struct perf_tool build_id__mark_dso_hit_ops = {
.ordered_events = true,
};
-int build_id__sprintf(const u8 *build_id, int len, char *bf)
+int build_id__sprintf(const struct build_id *build_id, char *bf)
{
char *bid = bf;
- const u8 *raw = build_id;
- int i;
+ const u8 *raw = build_id->data;
+ size_t i;
+
+ bf[0] = 0x0;
- for (i = 0; i < len; ++i) {
+ for (i = 0; i < build_id->size; ++i) {
sprintf(bid, "%02x", *raw);
++raw;
bid += 2;
@@ -113,7 +117,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf)
int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id)
{
char notes[PATH_MAX];
- u8 build_id[BUILD_ID_SIZE];
+ struct build_id bid;
int ret;
if (!root_dir)
@@ -121,25 +125,23 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id)
scnprintf(notes, sizeof(notes), "%s/sys/kernel/notes", root_dir);
- ret = sysfs__read_build_id(notes, build_id, sizeof(build_id));
+ ret = sysfs__read_build_id(notes, &bid);
if (ret < 0)
return ret;
- return build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+ return build_id__sprintf(&bid, sbuild_id);
}
int filename__sprintf_build_id(const char *pathname, char *sbuild_id)
{
- u8 build_id[BUILD_ID_SIZE];
+ struct build_id bid;
int ret;
- ret = filename__read_build_id(pathname, build_id, sizeof(build_id));
+ ret = filename__read_build_id(pathname, &bid);
if (ret < 0)
return ret;
- else if (ret != sizeof(build_id))
- return -EINVAL;
- return build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+ return build_id__sprintf(&bid, sbuild_id);
}
/* asnprintf consolidates asprintf and snprintf */
@@ -259,10 +261,9 @@ static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso,
"debug" : "elf"));
}
-char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
- bool is_debug)
+char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+ bool is_debug, bool is_kallsyms)
{
- bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
bool is_vdso = dso__is_vdso((struct dso *)dso);
char sbuild_id[SBUILD_ID_SIZE];
char *linkname;
@@ -272,7 +273,7 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
if (!dso->has_build_id)
return NULL;
- build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+ build_id__sprintf(&dso->bid, sbuild_id);
linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
if (!linkname)
return NULL;
@@ -291,13 +292,21 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
return bf;
}
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+ bool is_debug)
+{
+ bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
+
+ return __dso__build_id_filename(dso, bf, size, is_debug, is_kallsyms);
+}
+
#define dsos__for_each_with_build_id(pos, head) \
list_for_each_entry(pos, head, node) \
if (!pos->has_build_id) \
continue; \
else
-static int write_buildid(const char *name, size_t name_len, u8 *build_id,
+static int write_buildid(const char *name, size_t name_len, struct build_id *bid,
pid_t pid, u16 misc, struct feat_fd *fd)
{
int err;
@@ -308,7 +317,9 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
len = PERF_ALIGN(len, NAME_ALIGN);
memset(&b, 0, sizeof(b));
- memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+ memcpy(&b.data, bid->data, bid->size);
+ b.size = (u8) bid->size;
+ misc |= PERF_RECORD_MISC_BUILD_ID_SIZE;
b.pid = pid;
b.header.misc = misc;
b.header.size = sizeof(b) + len;
@@ -355,7 +366,7 @@ static int machine__write_buildid_table(struct machine *machine,
in_kernel = pos->kernel ||
is_kernel_module(name,
PERF_RECORD_MISC_CPUMODE_UNKNOWN);
- err = write_buildid(name, name_len, pos->build_id, machine->pid,
+ err = write_buildid(name, name_len, &pos->bid, machine->pid,
in_kernel ? kmisc : umisc, fd);
if (err)
break;
@@ -660,24 +671,15 @@ out:
return realname;
}
-int build_id_cache__add_s(const char *sbuild_id, const char *name,
- struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
+int
+build_id_cache__add(const char *sbuild_id, const char *name, const char *realname,
+ struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
{
const size_t size = PATH_MAX;
- char *realname = NULL, *filename = NULL, *dir_name = NULL,
- *linkname = zalloc(size), *tmp;
+ char *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *tmp;
char *debugfile = NULL;
int err = -1;
- if (!is_kallsyms) {
- if (!is_vdso)
- realname = nsinfo__realpath(name, nsi);
- else
- realname = realpath(name, NULL);
- if (!realname)
- goto out_free;
- }
-
dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms,
is_vdso);
if (!dir_name)
@@ -751,8 +753,25 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
tmp = dir_name + strlen(buildid_dir) - 5;
memcpy(tmp, "../..", 5);
- if (symlink(tmp, linkname) == 0)
+ if (symlink(tmp, linkname) == 0) {
err = 0;
+ } else if (errno == EEXIST) {
+ char path[PATH_MAX];
+ ssize_t len;
+
+ len = readlink(linkname, path, sizeof(path) - 1);
+ if (len <= 0) {
+ pr_err("Cant read link: %s\n", linkname);
+ goto out_free;
+ }
+ path[len] = '\0';
+
+ if (strcmp(tmp, path)) {
+ pr_debug("build <%s> already linked to %s\n",
+ sbuild_id, linkname);
+ }
+ err = 0;
+ }
/* Update SDT cache : error is just warned */
if (realname &&
@@ -760,8 +779,6 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
out_free:
- if (!is_kallsyms)
- free(realname);
free(filename);
free(debugfile);
free(dir_name);
@@ -769,13 +786,36 @@ out_free:
return err;
}
-static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
+int build_id_cache__add_s(const char *sbuild_id, const char *name,
+ struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
+{
+ char *realname = NULL;
+ int err = -1;
+
+ if (!is_kallsyms) {
+ if (!is_vdso)
+ realname = nsinfo__realpath(name, nsi);
+ else
+ realname = realpath(name, NULL);
+ if (!realname)
+ goto out_free;
+ }
+
+ err = build_id_cache__add(sbuild_id, name, realname, nsi, is_kallsyms, is_vdso);
+
+out_free:
+ if (!is_kallsyms)
+ free(realname);
+ return err;
+}
+
+static int build_id_cache__add_b(const struct build_id *bid,
const char *name, struct nsinfo *nsi,
bool is_kallsyms, bool is_vdso)
{
char sbuild_id[SBUILD_ID_SIZE];
- build_id__sprintf(build_id, build_id_size, sbuild_id);
+ build_id__sprintf(bid, sbuild_id);
return build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms,
is_vdso);
@@ -831,57 +871,54 @@ out_free:
return err;
}
-static int dso__cache_build_id(struct dso *dso, struct machine *machine)
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+ void *priv __maybe_unused)
{
bool is_kallsyms = dso__is_kallsyms(dso);
bool is_vdso = dso__is_vdso(dso);
const char *name = dso->long_name;
+ if (!dso->has_build_id)
+ return 0;
+
if (dso__is_kcore(dso)) {
is_kallsyms = true;
name = machine->mmap_name;
}
- return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
- dso->nsinfo, is_kallsyms, is_vdso);
+ return build_id_cache__add_b(&dso->bid, name, dso->nsinfo,
+ is_kallsyms, is_vdso);
}
-static int __dsos__cache_build_ids(struct list_head *head,
- struct machine *machine)
+static int
+machines__for_each_dso(struct machines *machines, machine__dso_t fn, void *priv)
{
- struct dso *pos;
- int err = 0;
-
- dsos__for_each_with_build_id(pos, head)
- if (dso__cache_build_id(pos, machine))
- err = -1;
+ int ret = machine__for_each_dso(&machines->host, fn, priv);
+ struct rb_node *nd;
- return err;
-}
+ for (nd = rb_first_cached(&machines->guests); nd;
+ nd = rb_next(nd)) {
+ struct machine *pos = rb_entry(nd, struct machine, rb_node);
-static int machine__cache_build_ids(struct machine *machine)
-{
- return __dsos__cache_build_ids(&machine->dsos.head, machine);
+ ret |= machine__for_each_dso(pos, fn, priv);
+ }
+ return ret ? -1 : 0;
}
-int perf_session__cache_build_ids(struct perf_session *session)
+int __perf_session__cache_build_ids(struct perf_session *session,
+ machine__dso_t fn, void *priv)
{
- struct rb_node *nd;
- int ret;
-
if (no_buildid_cache)
return 0;
if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST)
return -1;
- ret = machine__cache_build_ids(&session->machines.host);
+ return machines__for_each_dso(&session->machines, fn, priv) ? -1 : 0;
+}
- for (nd = rb_first_cached(&session->machines.guests); nd;
- nd = rb_next(nd)) {
- struct machine *pos = rb_entry(nd, struct machine, rb_node);
- ret |= machine__cache_build_ids(pos);
- }
- return ret ? -1 : 0;
+int perf_session__cache_build_ids(struct perf_session *session)
+{
+ return __perf_session__cache_build_ids(session, dso__cache_build_id, NULL);
}
static bool machine__read_build_ids(struct machine *machine, bool with_hits)
@@ -902,3 +939,15 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
return ret;
}
+
+void build_id__init(struct build_id *bid, const u8 *data, size_t size)
+{
+ WARN_ON(size > BUILD_ID_SIZE);
+ memcpy(bid->data, data, size);
+ bid->size = size;
+}
+
+bool build_id__is_defined(const struct build_id *bid)
+{
+ return bid && bid->size ? !!memchr_inv(bid->data, 0, bid->size) : false;
+}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index aad419bb165c..02613f4b2c29 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -5,16 +5,24 @@
#define BUILD_ID_SIZE 20
#define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1)
+#include "machine.h"
#include "tool.h"
#include <linux/types.h>
+struct build_id {
+ u8 data[BUILD_ID_SIZE];
+ size_t size;
+};
+
struct nsinfo;
extern struct perf_tool build_id__mark_dso_hit_ops;
struct dso;
struct feat_fd;
-int build_id__sprintf(const u8 *build_id, int len, char *bf);
+void build_id__init(struct build_id *bid, const u8 *data, size_t size);
+int build_id__sprintf(const struct build_id *build_id, char *bf);
+bool build_id__is_defined(const struct build_id *bid);
int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
@@ -22,6 +30,8 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
bool is_debug);
+char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+ bool is_debug, bool is_kallsyms);
int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
struct perf_sample *sample, struct evsel *evsel,
@@ -29,10 +39,16 @@ int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
int dsos__hit_all(struct perf_session *session);
+int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event,
+ struct perf_sample *sample, struct evsel *evsel,
+ struct machine *machine);
+
bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
int perf_session__write_buildid_table(struct perf_session *session,
struct feat_fd *fd);
int perf_session__cache_build_ids(struct perf_session *session);
+int __perf_session__cache_build_ids(struct perf_session *session,
+ machine__dso_t fn, void *priv);
char *build_id_cache__origname(const char *sbuild_id);
char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
@@ -47,6 +63,8 @@ char *build_id_cache__complement(const char *incomplete_sbuild_id);
int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi,
struct strlist **result);
bool build_id_cache__cached(const char *sbuild_id);
+int build_id_cache__add(const char *sbuild_id, const char *name, const char *realname,
+ struct nsinfo *nsi, bool is_kallsyms, bool is_vdso);
int build_id_cache__add_s(const char *sbuild_id,
const char *name, struct nsinfo *nsi,
bool is_kallsyms, bool is_vdso);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 2775b752f2fa..1b60985690bb 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1613,3 +1613,102 @@ void callchain_param_setup(u64 sample_type)
callchain_param.record_mode = CALLCHAIN_FP;
}
}
+
+static bool chain_match(struct callchain_list *base_chain,
+ struct callchain_list *pair_chain)
+{
+ enum match_result match;
+
+ match = match_chain_strings(base_chain->srcline,
+ pair_chain->srcline);
+ if (match != MATCH_ERROR)
+ return match == MATCH_EQ;
+
+ match = match_chain_dso_addresses(base_chain->ms.map,
+ base_chain->ip,
+ pair_chain->ms.map,
+ pair_chain->ip);
+
+ return match == MATCH_EQ;
+}
+
+bool callchain_cnode_matched(struct callchain_node *base_cnode,
+ struct callchain_node *pair_cnode)
+{
+ struct callchain_list *base_chain, *pair_chain;
+ bool match = false;
+
+ pair_chain = list_first_entry(&pair_cnode->val,
+ struct callchain_list,
+ list);
+
+ list_for_each_entry(base_chain, &base_cnode->val, list) {
+ if (&pair_chain->list == &pair_cnode->val)
+ return false;
+
+ if (!base_chain->srcline || !pair_chain->srcline) {
+ pair_chain = list_next_entry(pair_chain, list);
+ continue;
+ }
+
+ match = chain_match(base_chain, pair_chain);
+ if (!match)
+ return false;
+
+ pair_chain = list_next_entry(pair_chain, list);
+ }
+
+ /*
+ * Say chain1 is ABC, chain2 is ABCD, we consider they are
+ * not fully matched.
+ */
+ if (pair_chain && (&pair_chain->list != &pair_cnode->val))
+ return false;
+
+ return match;
+}
+
+static u64 count_callchain_hits(struct hist_entry *he)
+{
+ struct rb_root *root = &he->sorted_chain;
+ struct rb_node *rb_node = rb_first(root);
+ struct callchain_node *node;
+ u64 chain_hits = 0;
+
+ while (rb_node) {
+ node = rb_entry(rb_node, struct callchain_node, rb_node);
+ chain_hits += node->hit;
+ rb_node = rb_next(rb_node);
+ }
+
+ return chain_hits;
+}
+
+u64 callchain_total_hits(struct hists *hists)
+{
+ struct rb_node *next = rb_first_cached(&hists->entries);
+ u64 chain_hits = 0;
+
+ while (next) {
+ struct hist_entry *he = rb_entry(next, struct hist_entry,
+ rb_node);
+
+ chain_hits += count_callchain_hits(he);
+ next = rb_next(&he->rb_node);
+ }
+
+ return chain_hits;
+}
+
+s64 callchain_avg_cycles(struct callchain_node *cnode)
+{
+ struct callchain_list *chain;
+ s64 cycles = 0;
+
+ list_for_each_entry(chain, &cnode->val, list) {
+ if (chain->srcline && chain->branch_count)
+ cycles += chain->cycles_count / chain->branch_count;
+ }
+
+ return cycles;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index fe36a9e5ccd1..5824134f983b 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -13,6 +13,7 @@ struct ip_callchain;
struct map;
struct perf_sample;
struct thread;
+struct hists;
#define HELP_PAD "\t\t\t\t"
@@ -298,4 +299,12 @@ int callchain_branch_counts(struct callchain_root *root,
u64 *abort_count, u64 *cycles_count);
void callchain_param_setup(u64 sample_type);
+
+bool callchain_cnode_matched(struct callchain_node *base_cnode,
+ struct callchain_node *pair_cnode);
+
+u64 callchain_total_hits(struct hists *hists);
+
+s64 callchain_avg_cycles(struct callchain_node *cnode);
+
#endif /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 050dea9f1e88..5dff7e489921 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -3,6 +3,9 @@
#include "evsel.h"
#include "cgroup.h"
#include "evlist.h"
+#include "rblist.h"
+#include "metricgroup.h"
+#include "stat.h"
#include <linux/zalloc.h>
#include <sys/types.h>
#include <sys/stat.h>
@@ -10,9 +13,19 @@
#include <stdlib.h>
#include <string.h>
#include <api/fs/fs.h>
+#include <ftw.h>
+#include <regex.h>
int nr_cgroups;
+/* used to match cgroup name with patterns */
+struct cgroup_name {
+ struct list_head list;
+ bool used;
+ char name[];
+};
+static LIST_HEAD(cgroup_list);
+
static int open_cgroup(const char *name)
{
char path[PATH_MAX + 1];
@@ -48,7 +61,7 @@ static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str
return NULL;
}
-static struct cgroup *cgroup__new(const char *name)
+static struct cgroup *cgroup__new(const char *name, bool do_open)
{
struct cgroup *cgroup = zalloc(sizeof(*cgroup));
@@ -58,9 +71,14 @@ static struct cgroup *cgroup__new(const char *name)
cgroup->name = strdup(name);
if (!cgroup->name)
goto out_err;
- cgroup->fd = open_cgroup(name);
- if (cgroup->fd == -1)
- goto out_free_name;
+
+ if (do_open) {
+ cgroup->fd = open_cgroup(name);
+ if (cgroup->fd == -1)
+ goto out_free_name;
+ } else {
+ cgroup->fd = -1;
+ }
}
return cgroup;
@@ -76,7 +94,7 @@ struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name)
{
struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
- return cgroup ?: cgroup__new(name);
+ return cgroup ?: cgroup__new(name, true);
}
static int add_cgroup(struct evlist *evlist, const char *str)
@@ -141,6 +159,137 @@ void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup)
evsel__set_default_cgroup(evsel, cgroup);
}
+/* helper function for ftw() in match_cgroups and list_cgroups */
+static int add_cgroup_name(const char *fpath, const struct stat *sb __maybe_unused,
+ int typeflag)
+{
+ struct cgroup_name *cn;
+
+ if (typeflag != FTW_D)
+ return 0;
+
+ cn = malloc(sizeof(*cn) + strlen(fpath) + 1);
+ if (cn == NULL)
+ return -1;
+
+ cn->used = false;
+ strcpy(cn->name, fpath);
+
+ list_add_tail(&cn->list, &cgroup_list);
+ return 0;
+}
+
+static void release_cgroup_list(void)
+{
+ struct cgroup_name *cn;
+
+ while (!list_empty(&cgroup_list)) {
+ cn = list_first_entry(&cgroup_list, struct cgroup_name, list);
+ list_del(&cn->list);
+ free(cn);
+ }
+}
+
+/* collect given cgroups only */
+static int list_cgroups(const char *str)
+{
+ const char *p, *e, *eos = str + strlen(str);
+ struct cgroup_name *cn;
+ char *s;
+
+ /* use given name as is - for testing purpose */
+ for (;;) {
+ p = strchr(str, ',');
+ e = p ? p : eos;
+
+ if (e - str) {
+ int ret;
+
+ s = strndup(str, e - str);
+ if (!s)
+ return -1;
+ /* pretend if it's added by ftw() */
+ ret = add_cgroup_name(s, NULL, FTW_D);
+ free(s);
+ if (ret)
+ return -1;
+ } else {
+ if (add_cgroup_name("", NULL, FTW_D) < 0)
+ return -1;
+ }
+
+ if (!p)
+ break;
+ str = p+1;
+ }
+
+ /* these groups will be used */
+ list_for_each_entry(cn, &cgroup_list, list)
+ cn->used = true;
+
+ return 0;
+}
+
+/* collect all cgroups first and then match with the pattern */
+static int match_cgroups(const char *str)
+{
+ char mnt[PATH_MAX];
+ const char *p, *e, *eos = str + strlen(str);
+ struct cgroup_name *cn;
+ regex_t reg;
+ int prefix_len;
+ char *s;
+
+ if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event"))
+ return -1;
+
+ /* cgroup_name will have a full path, skip the root directory */
+ prefix_len = strlen(mnt);
+
+ /* collect all cgroups in the cgroup_list */
+ if (ftw(mnt, add_cgroup_name, 20) < 0)
+ return -1;
+
+ for (;;) {
+ p = strchr(str, ',');
+ e = p ? p : eos;
+
+ /* allow empty cgroups, i.e., skip */
+ if (e - str) {
+ /* termination added */
+ s = strndup(str, e - str);
+ if (!s)
+ return -1;
+ if (regcomp(&reg, s, REG_NOSUB)) {
+ free(s);
+ return -1;
+ }
+
+ /* check cgroup name with the pattern */
+ list_for_each_entry(cn, &cgroup_list, list) {
+ char *name = cn->name + prefix_len;
+
+ if (name[0] == '/' && name[1])
+ name++;
+ if (!regexec(&reg, name, 0, NULL, 0))
+ cn->used = true;
+ }
+ regfree(&reg);
+ free(s);
+ } else {
+ /* first entry to root cgroup */
+ cn = list_first_entry(&cgroup_list, struct cgroup_name,
+ list);
+ cn->used = true;
+ }
+
+ if (!p)
+ break;
+ str = p+1;
+ }
+ return prefix_len;
+}
+
int parse_cgroups(const struct option *opt, const char *str,
int unset __maybe_unused)
{
@@ -193,6 +342,114 @@ int parse_cgroups(const struct option *opt, const char *str,
return 0;
}
+static bool has_pattern_string(const char *str)
+{
+ return !!strpbrk(str, "{}[]()|*+?^$");
+}
+
+int evlist__expand_cgroup(struct evlist *evlist, const char *str,
+ struct rblist *metric_events, bool open_cgroup)
+{
+ struct evlist *orig_list, *tmp_list;
+ struct evsel *pos, *evsel, *leader;
+ struct rblist orig_metric_events;
+ struct cgroup *cgrp = NULL;
+ struct cgroup_name *cn;
+ int ret = -1;
+ int prefix_len;
+
+ if (evlist->core.nr_entries == 0) {
+ fprintf(stderr, "must define events before cgroups\n");
+ return -EINVAL;
+ }
+
+ orig_list = evlist__new();
+ tmp_list = evlist__new();
+ if (orig_list == NULL || tmp_list == NULL) {
+ fprintf(stderr, "memory allocation failed\n");
+ return -ENOMEM;
+ }
+
+ /* save original events and init evlist */
+ evlist__splice_list_tail(orig_list, &evlist->core.entries);
+ evlist->core.nr_entries = 0;
+
+ if (metric_events) {
+ orig_metric_events = *metric_events;
+ rblist__init(metric_events);
+ } else {
+ rblist__init(&orig_metric_events);
+ }
+
+ if (has_pattern_string(str))
+ prefix_len = match_cgroups(str);
+ else
+ prefix_len = list_cgroups(str);
+
+ if (prefix_len < 0)
+ goto out_err;
+
+ list_for_each_entry(cn, &cgroup_list, list) {
+ char *name;
+
+ if (!cn->used)
+ continue;
+
+ /* cgroup_name might have a full path, skip the prefix */
+ name = cn->name + prefix_len;
+ if (name[0] == '/' && name[1])
+ name++;
+ cgrp = cgroup__new(name, open_cgroup);
+ if (cgrp == NULL)
+ goto out_err;
+
+ leader = NULL;
+ evlist__for_each_entry(orig_list, pos) {
+ evsel = evsel__clone(pos);
+ if (evsel == NULL)
+ goto out_err;
+
+ cgroup__put(evsel->cgrp);
+ evsel->cgrp = cgroup__get(cgrp);
+
+ if (evsel__is_group_leader(pos))
+ leader = evsel;
+ evsel->leader = leader;
+
+ evlist__add(tmp_list, evsel);
+ }
+ /* cgroup__new() has a refcount, release it here */
+ cgroup__put(cgrp);
+ nr_cgroups++;
+
+ if (metric_events) {
+ perf_stat__collect_metric_expr(tmp_list);
+ if (metricgroup__copy_metric_events(tmp_list, cgrp,
+ metric_events,
+ &orig_metric_events) < 0)
+ goto out_err;
+ }
+
+ evlist__splice_list_tail(evlist, &tmp_list->core.entries);
+ tmp_list->core.nr_entries = 0;
+ }
+
+ if (list_empty(&evlist->core.entries)) {
+ fprintf(stderr, "no cgroup matched: %s\n", str);
+ goto out_err;
+ }
+
+ ret = 0;
+
+out_err:
+ evlist__delete(orig_list);
+ evlist__delete(tmp_list);
+ rblist__exit(&orig_metric_events);
+ release_cgroup_list();
+
+ return ret;
+}
+
static struct cgroup *__cgroup__findnew(struct rb_root *root, uint64_t id,
bool create, const char *path)
{
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index e98d5975fe55..162906f3412a 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -22,8 +22,11 @@ struct cgroup *cgroup__get(struct cgroup *cgroup);
void cgroup__put(struct cgroup *cgroup);
struct evlist;
+struct rblist;
struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name);
+int evlist__expand_cgroup(struct evlist *evlist, const char *cgroups,
+ struct rblist *metric_events, bool open_cgroup);
void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 20be0504fb95..6969f82843ee 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -489,7 +489,7 @@ int perf_default_config(const char *var, const char *value,
return 0;
}
-static int perf_config_from_file(config_fn_t fn, const char *filename, void *data)
+int perf_config_from_file(config_fn_t fn, const char *filename, void *data)
{
int ret;
FILE *f = fopen(filename, "r");
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index c10b66dde2f3..8c881e3a3ec3 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -26,6 +26,8 @@ struct perf_config_set {
extern const char *config_exclusive_filename;
typedef int (*config_fn_t)(const char *, const char *, void *);
+
+int perf_config_from_file(config_fn_t fn, const char *filename, void *data);
int perf_default_config(const char *, const char *, void *);
int perf_config(config_fn_t fn, void *);
int perf_config_int(int *dest, const char *, const char *);
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index dc5c5e6fc502..87d3eca9b872 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -95,6 +95,23 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr)
return cpus;
}
+struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr)
+{
+ struct cpu_aggr_map *cpus = malloc(sizeof(*cpus) + sizeof(struct aggr_cpu_id) * nr);
+
+ if (cpus != NULL) {
+ int i;
+
+ cpus->nr = nr;
+ for (i = 0; i < nr; i++)
+ cpus->map[i] = cpu_map__empty_aggr_cpu_id();
+
+ refcount_set(&cpus->refcnt, 1);
+ }
+
+ return cpus;
+}
+
static int cpu__get_topology_int(int cpu, const char *name, int *value)
{
char path[PATH_MAX];
@@ -111,40 +128,57 @@ int cpu_map__get_socket_id(int cpu)
return ret ?: value;
}
-int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
+struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx,
+ void *data __maybe_unused)
{
int cpu;
+ struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
if (idx > map->nr)
- return -1;
+ return id;
cpu = map->map[idx];
- return cpu_map__get_socket_id(cpu);
+ id.socket = cpu_map__get_socket_id(cpu);
+ return id;
}
-static int cmp_ids(const void *a, const void *b)
+static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer)
{
- return *(int *)a - *(int *)b;
+ struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer;
+ struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer;
+
+ if (a->node != b->node)
+ return a->node - b->node;
+ else if (a->socket != b->socket)
+ return a->socket - b->socket;
+ else if (a->die != b->die)
+ return a->die - b->die;
+ else if (a->core != b->core)
+ return a->core - b->core;
+ else
+ return a->thread - b->thread;
}
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
- int (*f)(struct perf_cpu_map *map, int cpu, void *data),
+int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
+ struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
void *data)
{
- struct perf_cpu_map *c;
int nr = cpus->nr;
- int cpu, s1, s2;
+ struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr);
+ int cpu, s2;
+ struct aggr_cpu_id s1;
- /* allocate as much as possible */
- c = calloc(1, sizeof(*c) + nr * sizeof(int));
if (!c)
return -1;
+ /* Reset size as it may only be partially filled */
+ c->nr = 0;
+
for (cpu = 0; cpu < nr; cpu++) {
s1 = f(cpus, cpu, data);
for (s2 = 0; s2 < c->nr; s2++) {
- if (s1 == c->map[s2])
+ if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2]))
break;
}
if (s2 == c->nr) {
@@ -153,9 +187,8 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
}
}
/* ensure we process id in increasing order */
- qsort(c->map, c->nr, sizeof(int), cmp_ids);
+ qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id);
- refcount_set(&c->refcnt, 1);
*res = c;
return 0;
}
@@ -167,37 +200,32 @@ int cpu_map__get_die_id(int cpu)
return ret ?: value;
}
-int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data)
{
- int cpu, die_id, s;
+ int cpu, die;
+ struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
if (idx > map->nr)
- return -1;
+ return id;
cpu = map->map[idx];
- die_id = cpu_map__get_die_id(cpu);
+ die = cpu_map__get_die_id(cpu);
/* There is no die_id on legacy system. */
- if (die_id == -1)
- die_id = 0;
-
- s = cpu_map__get_socket(map, idx, data);
- if (s == -1)
- return -1;
+ if (die == -1)
+ die = 0;
/*
- * Encode socket in bit range 15:8
- * die_id is relative to socket, and
- * we need a global id. So we combine
- * socket + die id
+ * die_id is relative to socket, so start
+ * with the socket ID and then add die to
+ * make a unique ID.
*/
- if (WARN_ONCE(die_id >> 8, "The die id number is too big.\n"))
- return -1;
-
- if (WARN_ONCE(s >> 8, "The socket id number is too big.\n"))
- return -1;
+ id = cpu_map__get_socket(map, idx, data);
+ if (cpu_map__aggr_cpu_id_is_empty(id))
+ return id;
- return (s << 8) | (die_id & 0xff);
+ id.die = die;
+ return id;
}
int cpu_map__get_core_id(int cpu)
@@ -211,59 +239,58 @@ int cpu_map__get_node_id(int cpu)
return cpu__get_node(cpu);
}
-int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
{
- int cpu, s_die;
+ int cpu;
+ struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
if (idx > map->nr)
- return -1;
+ return id;
cpu = map->map[idx];
cpu = cpu_map__get_core_id(cpu);
- /* s_die is the combination of socket + die id */
- s_die = cpu_map__get_die(map, idx, data);
- if (s_die == -1)
- return -1;
+ /* cpu_map__get_die returns a struct with socket and die set*/
+ id = cpu_map__get_die(map, idx, data);
+ if (cpu_map__aggr_cpu_id_is_empty(id))
+ return id;
/*
- * encode socket in bit range 31:24
- * encode die id in bit range 23:16
- * core_id is relative to socket and die,
- * we need a global id. So we combine
- * socket + die id + core id
+ * core_id is relative to socket and die, we need a global id.
+ * So we combine the result from cpu_map__get_die with the core id
*/
- if (WARN_ONCE(cpu >> 16, "The core id number is too big.\n"))
- return -1;
-
- return (s_die << 16) | (cpu & 0xffff);
+ id.core = cpu;
+ return id;
}
-int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
+struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
{
+ struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+
if (idx < 0 || idx >= map->nr)
- return -1;
+ return id;
- return cpu_map__get_node_id(map->map[idx]);
+ id.node = cpu_map__get_node_id(map->map[idx]);
+ return id;
}
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp)
+int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp)
{
return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
}
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep)
+int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep)
{
return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL);
}
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep)
+int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep)
{
return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
}
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **numap)
+int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap)
{
return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL);
}
@@ -586,3 +613,33 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
return online;
}
+
+bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b)
+{
+ return a.thread == b.thread &&
+ a.node == b.node &&
+ a.socket == b.socket &&
+ a.die == b.die &&
+ a.core == b.core;
+}
+
+bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a)
+{
+ return a.thread == -1 &&
+ a.node == -1 &&
+ a.socket == -1 &&
+ a.die == -1 &&
+ a.core == -1;
+}
+
+struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void)
+{
+ struct aggr_cpu_id ret = {
+ .thread = -1,
+ .node = -1,
+ .socket = -1,
+ .die = -1,
+ .core = -1
+ };
+ return ret;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 3a442f021468..a27eeaf086e8 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -7,25 +7,41 @@
#include <internal/cpumap.h>
#include <perf/cpumap.h>
+struct aggr_cpu_id {
+ int thread;
+ int node;
+ int socket;
+ int die;
+ int core;
+};
+
+struct cpu_aggr_map {
+ refcount_t refcnt;
+ int nr;
+ struct aggr_cpu_id map[];
+};
+
struct perf_record_cpu_map_data;
struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
+struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr);
+
struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);
int cpu_map__get_socket_id(int cpu);
-int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data);
+struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data);
int cpu_map__get_die_id(int cpu);
-int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
+struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
int cpu_map__get_core_id(int cpu);
-int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
+struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
int cpu_map__get_node_id(int cpu);
-int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp);
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep);
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep);
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **nodep);
+struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data);
+int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp);
+int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep);
+int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep);
+int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep);
const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */
static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
@@ -35,21 +51,6 @@ static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
return sock->map[s];
}
-static inline int cpu_map__id_to_socket(int id)
-{
- return id >> 24;
-}
-
-static inline int cpu_map__id_to_die(int id)
-{
- return (id >> 16) & 0xff;
-}
-
-static inline int cpu_map__id_to_cpu(int id)
-{
- return id & 0xffff;
-}
-
int cpu__setup_cpunode_map(void);
int cpu__max_node(void);
@@ -57,11 +58,15 @@ int cpu__max_cpu(void);
int cpu__max_present_cpu(void);
int cpu__get_node(int cpu);
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
- int (*f)(struct perf_cpu_map *map, int cpu, void *data),
+int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
+ struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
void *data);
int cpu_map__cpu(struct perf_cpu_map *cpus, int idx);
bool cpu_map__has(struct perf_cpu_map *cpus, int cpu);
+bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b);
+bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a);
+struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void);
+
#endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index c47aa34fdc0a..f29af4fc3d09 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -174,8 +174,21 @@ static bool check_pipe(struct perf_data *data)
is_pipe = true;
}
- if (is_pipe)
- data->file.fd = fd;
+ if (is_pipe) {
+ if (data->use_stdio) {
+ const char *mode;
+
+ mode = perf_data__is_read(data) ? "r" : "w";
+ data->file.fptr = fdopen(fd, mode);
+
+ if (data->file.fptr == NULL) {
+ data->file.fd = fd;
+ data->use_stdio = false;
+ }
+ } else {
+ data->file.fd = fd;
+ }
+ }
return data->is_pipe = is_pipe;
}
@@ -334,6 +347,9 @@ int perf_data__open(struct perf_data *data)
if (check_pipe(data))
return 0;
+ /* currently it allows stdio for pipe only */
+ data->use_stdio = false;
+
if (!data->path)
data->path = "perf.data";
@@ -353,7 +369,21 @@ void perf_data__close(struct perf_data *data)
perf_data__close_dir(data);
zfree(&data->file.path);
- close(data->file.fd);
+
+ if (data->use_stdio)
+ fclose(data->file.fptr);
+ else
+ close(data->file.fd);
+}
+
+ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size)
+{
+ if (data->use_stdio) {
+ if (fread(buf, size, 1, data->file.fptr) == 1)
+ return size;
+ return feof(data->file.fptr) ? 0 : -1;
+ }
+ return readn(data->file.fd, buf, size);
}
ssize_t perf_data_file__write(struct perf_data_file *file,
@@ -365,6 +395,11 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
ssize_t perf_data__write(struct perf_data *data,
void *buf, size_t size)
{
+ if (data->use_stdio) {
+ if (fwrite(buf, size, 1, data->file.fptr) == 1)
+ return size;
+ return -1;
+ }
return perf_data_file__write(&data->file, buf, size);
}
@@ -457,3 +492,22 @@ char *perf_data__kallsyms_name(struct perf_data *data)
return kallsyms_name;
}
+
+bool is_perf_data(const char *path)
+{
+ bool ret = false;
+ FILE *file;
+ u64 magic;
+
+ file = fopen(path, "r");
+ if (!file)
+ return false;
+
+ if (fread(&magic, 1, 8, file) < 8)
+ goto out;
+
+ ret = is_perf_magic(magic);
+out:
+ fclose(file);
+ return ret;
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 75947ef6bc17..62a3e66fbee8 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -2,6 +2,7 @@
#ifndef __PERF_DATA_H
#define __PERF_DATA_H
+#include <stdio.h>
#include <stdbool.h>
enum perf_data_mode {
@@ -16,7 +17,10 @@ enum perf_dir_version {
struct perf_data_file {
char *path;
- int fd;
+ union {
+ int fd;
+ FILE *fptr;
+ };
unsigned long size;
};
@@ -26,6 +30,7 @@ struct perf_data {
bool is_pipe;
bool is_dir;
bool force;
+ bool use_stdio;
enum perf_data_mode mode;
struct {
@@ -62,11 +67,15 @@ static inline bool perf_data__is_single_file(struct perf_data *data)
static inline int perf_data__fd(struct perf_data *data)
{
+ if (data->use_stdio)
+ return fileno(data->file.fptr);
+
return data->file.fd;
}
int perf_data__open(struct perf_data *data);
void perf_data__close(struct perf_data *data);
+ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size);
ssize_t perf_data__write(struct perf_data *data,
void *buf, size_t size);
ssize_t perf_data_file__write(struct perf_data_file *file,
@@ -89,4 +98,5 @@ int perf_data__update_dir(struct perf_data *data);
unsigned long perf_data__size(struct perf_data *data);
int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz);
char *perf_data__kallsyms_name(struct perf_data *data);
+bool is_perf_data(const char *path);
#endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 5cda5565777a..50fd6a4be4e0 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -30,6 +30,12 @@ bool dump_trace = false, quiet = false;
int debug_ordered_events;
static int redirect_to_stderr;
int debug_data_convert;
+static FILE *debug_file;
+
+void debug_set_file(FILE *file)
+{
+ debug_file = file;
+}
int veprintf(int level, int var, const char *fmt, va_list args)
{
@@ -39,7 +45,7 @@ int veprintf(int level, int var, const char *fmt, va_list args)
if (use_browser >= 1 && !redirect_to_stderr)
ui_helpline__vshow(fmt, args);
else
- ret = vfprintf(stderr, fmt, args);
+ ret = vfprintf(debug_file, fmt, args);
}
return ret;
@@ -227,6 +233,7 @@ DEBUG_WRAPPER(debug, 1);
void perf_debug_setup(void)
{
+ debug_set_file(stderr);
libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index f1734abd98dd..43f712295645 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -5,6 +5,7 @@
#include <stdarg.h>
#include <stdbool.h>
+#include <stdio.h>
#include <linux/compiler.h>
extern int verbose;
@@ -62,6 +63,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5)
int veprintf(int level, int var, const char *fmt, va_list args);
int perf_debug_option(const char *str);
+void debug_set_file(FILE *file);
void perf_debug_setup(void);
int perf_quiet_option(void);
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 5a3b4755f0b3..d786cf6b0cfa 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -11,8 +11,10 @@
#include <errno.h>
#include <fcntl.h>
#include <stdlib.h>
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/libbpf.h>
#include "bpf-event.h"
+#endif
#include "compress.h"
#include "env.h"
#include "namespaces.h"
@@ -172,9 +174,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
break;
}
- build_id__sprintf(dso->build_id,
- sizeof(dso->build_id),
- build_id_hex);
+ build_id__sprintf(&dso->bid, build_id_hex);
len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
snprintf(filename + len, size - len, "%.2s/%s.debug",
build_id_hex, build_id_hex + 2);
@@ -279,18 +279,12 @@ bool dso__needs_decompress(struct dso *dso)
dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
}
-static int decompress_kmodule(struct dso *dso, const char *name,
- char *pathname, size_t len)
+int filename__decompress(const char *name, char *pathname,
+ size_t len, int comp, int *err)
{
char tmpbuf[] = KMOD_DECOMP_NAME;
int fd = -1;
- if (!dso__needs_decompress(dso))
- return -1;
-
- if (dso->comp == COMP_ID__NONE)
- return -1;
-
/*
* We have proper compression id for DSO and yet the file
* behind the 'name' can still be plain uncompressed object.
@@ -304,17 +298,17 @@ static int decompress_kmodule(struct dso *dso, const char *name,
* To keep this transparent, we detect this and return the file
* descriptor to the uncompressed file.
*/
- if (!compressions[dso->comp].is_compressed(name))
+ if (!compressions[comp].is_compressed(name))
return open(name, O_RDONLY);
fd = mkstemp(tmpbuf);
if (fd < 0) {
- dso->load_errno = errno;
+ *err = errno;
return -1;
}
- if (compressions[dso->comp].decompress(name, fd)) {
- dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
+ if (compressions[comp].decompress(name, fd)) {
+ *err = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
close(fd);
fd = -1;
}
@@ -328,6 +322,19 @@ static int decompress_kmodule(struct dso *dso, const char *name,
return fd;
}
+static int decompress_kmodule(struct dso *dso, const char *name,
+ char *pathname, size_t len)
+{
+ if (!dso__needs_decompress(dso))
+ return -1;
+
+ if (dso->comp == COMP_ID__NONE)
+ return -1;
+
+ return filename__decompress(name, pathname, len, dso->comp,
+ &dso->load_errno);
+}
+
int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
{
return decompress_kmodule(dso, name, NULL, 0);
@@ -730,6 +737,7 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
return false;
}
+#ifdef HAVE_LIBBPF_SUPPORT
static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)
{
struct bpf_prog_info_node *node;
@@ -767,6 +775,7 @@ static int bpf_size(struct dso *dso)
dso->data.file_size = node->info_linear->info.jited_prog_len;
return 0;
}
+#endif // HAVE_LIBBPF_SUPPORT
static void
dso_cache__free(struct dso *dso)
@@ -896,10 +905,12 @@ static struct dso_cache *dso_cache__populate(struct dso *dso,
*ret = -ENOMEM;
return NULL;
}
-
+#ifdef HAVE_LIBBPF_SUPPORT
if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
*ret = bpf_read(dso, cache_offset, cache->data);
- else if (dso->binary_type == DSO_BINARY_TYPE__OOL)
+ else
+#endif
+ if (dso->binary_type == DSO_BINARY_TYPE__OOL)
*ret = DSO__DATA_CACHE_SIZE;
else
*ret = file_read(dso, machine, cache_offset, cache->data);
@@ -1020,10 +1031,10 @@ int dso__data_file_size(struct dso *dso, struct machine *machine)
if (dso->data.status == DSO_DATA_STATUS_ERROR)
return -1;
-
+#ifdef HAVE_LIBBPF_SUPPORT
if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
return bpf_size(dso);
-
+#endif
return file_size(dso, machine);
}
@@ -1328,15 +1339,16 @@ void dso__put(struct dso *dso)
dso__delete(dso);
}
-void dso__set_build_id(struct dso *dso, void *build_id)
+void dso__set_build_id(struct dso *dso, struct build_id *bid)
{
- memcpy(dso->build_id, build_id, sizeof(dso->build_id));
+ dso->bid = *bid;
dso->has_build_id = 1;
}
-bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
+bool dso__build_id_equal(const struct dso *dso, struct build_id *bid)
{
- return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
+ return dso->bid.size == bid->size &&
+ memcmp(dso->bid.data, bid->data, dso->bid.size) == 0;
}
void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
@@ -1346,8 +1358,7 @@ void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
if (machine__is_default_guest(machine))
return;
sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
- if (sysfs__read_build_id(path, dso->build_id,
- sizeof(dso->build_id)) == 0)
+ if (sysfs__read_build_id(path, &dso->bid) == 0)
dso->has_build_id = true;
}
@@ -1365,18 +1376,17 @@ int dso__kernel_module_get_build_id(struct dso *dso,
"%s/sys/module/%.*s/notes/.note.gnu.build-id",
root_dir, (int)strlen(name) - 1, name);
- if (sysfs__read_build_id(filename, dso->build_id,
- sizeof(dso->build_id)) == 0)
+ if (sysfs__read_build_id(filename, &dso->bid) == 0)
dso->has_build_id = true;
return 0;
}
-size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
+static size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
{
char sbuild_id[SBUILD_ID_SIZE];
- build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+ build_id__sprintf(&dso->bid, sbuild_id);
return fprintf(fp, "%s", sbuild_id);
}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 8ad17f395a19..cd2fe64a3c5d 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -176,7 +176,7 @@ struct dso {
bool sorted_by_name;
bool loaded;
u8 rel;
- u8 build_id[BUILD_ID_SIZE];
+ struct build_id bid;
u64 text_offset;
const char *short_name;
const char *long_name;
@@ -260,8 +260,8 @@ bool dso__sorted_by_name(const struct dso *dso);
void dso__set_sorted_by_name(struct dso *dso);
void dso__sort_by_name(struct dso *dso);
-void dso__set_build_id(struct dso *dso, void *build_id);
-bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
+void dso__set_build_id(struct dso *dso, struct build_id *bid);
+bool dso__build_id_equal(const struct dso *dso, struct build_id *bid);
void dso__read_running_kernel_build_id(struct dso *dso,
struct machine *machine);
int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
@@ -274,6 +274,8 @@ bool dso__needs_decompress(struct dso *dso);
int dso__decompress_kmodule_fd(struct dso *dso, const char *name);
int dso__decompress_kmodule_path(struct dso *dso, const char *name,
char *pathname, size_t len);
+int filename__decompress(const char *name, char *pathname,
+ size_t len, int comp, int *err);
#define KMOD_DECOMP_NAME "/tmp/perf-kmod-XXXXXX"
#define KMOD_DECOMP_LEN sizeof(KMOD_DECOMP_NAME)
@@ -362,7 +364,6 @@ struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
void dso__reset_find_symbol_cache(struct dso *dso);
-size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp);
size_t dso__fprintf(struct dso *dso, FILE *fp);
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index 939471731ea6..183a81d5b2f9 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -73,8 +73,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
continue;
}
nsinfo__mountns_enter(pos->nsinfo, &nsc);
- if (filename__read_build_id(pos->long_name, pos->build_id,
- sizeof(pos->build_id)) > 0) {
+ if (filename__read_build_id(pos->long_name, &pos->bid) > 0) {
have_build_id = true;
pos->has_build_id = true;
}
@@ -288,10 +287,12 @@ size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
size_t ret = 0;
list_for_each_entry(pos, head, node) {
+ char sbuild_id[SBUILD_ID_SIZE];
+
if (skip && skip(pos, parm))
continue;
- ret += dso__fprintf_buildid(pos, fp);
- ret += fprintf(fp, " %s\n", pos->long_name);
+ build_id__sprintf(&pos->bid, sbuild_id);
+ ret += fprintf(fp, "%-40s %s\n", sbuild_id, pos->long_name);
}
return ret;
}
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index aa898014ad12..7b2d471a6419 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -356,9 +356,25 @@ bool die_is_signed_type(Dwarf_Die *tp_die)
bool die_is_func_def(Dwarf_Die *dw_die)
{
Dwarf_Attribute attr;
+ Dwarf_Addr addr = 0;
+
+ if (dwarf_tag(dw_die) != DW_TAG_subprogram)
+ return false;
+
+ if (dwarf_attr(dw_die, DW_AT_declaration, &attr))
+ return false;
- return (dwarf_tag(dw_die) == DW_TAG_subprogram &&
- dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL);
+ /*
+ * DW_AT_declaration can be lost from function declaration
+ * by gcc's bug #97060.
+ * So we need to check this subprogram DIE has DW_AT_inline
+ * or an entry address.
+ */
+ if (!dwarf_attr(dw_die, DW_AT_inline, &attr) &&
+ die_entrypc(dw_die, &addr) < 0)
+ return false;
+
+ return true;
}
/**
@@ -373,6 +389,7 @@ bool die_is_func_def(Dwarf_Die *dw_die)
int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr)
{
Dwarf_Addr base, end;
+ Dwarf_Attribute attr;
if (!addr)
return -EINVAL;
@@ -380,6 +397,13 @@ int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr)
if (dwarf_entrypc(dw_die, addr) == 0)
return 0;
+ /*
+ * Since the dwarf_ranges() will return 0 if there is no
+ * DW_AT_ranges attribute, we should check it first.
+ */
+ if (!dwarf_attr(dw_die, DW_AT_ranges, &attr))
+ return -ENOENT;
+
return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0;
}
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index fadc59708ece..9130f6fad8d5 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -5,16 +5,18 @@
#include "util/header.h"
#include <linux/ctype.h>
#include <linux/zalloc.h>
-#include "bpf-event.h"
#include "cgroup.h"
#include <errno.h>
#include <sys/utsname.h>
-#include <bpf/libbpf.h>
#include <stdlib.h>
#include <string.h>
struct perf_env perf_env;
+#ifdef HAVE_LIBBPF_SUPPORT
+#include "bpf-event.h"
+#include <bpf/libbpf.h>
+
void perf_env__insert_bpf_prog_info(struct perf_env *env,
struct bpf_prog_info_node *info_node)
{
@@ -163,6 +165,11 @@ static void perf_env__purge_bpf(struct perf_env *env)
up_write(&env->bpf_progs.lock);
}
+#else // HAVE_LIBBPF_SUPPORT
+static void perf_env__purge_bpf(struct perf_env *env __maybe_unused)
+{
+}
+#endif // HAVE_LIBBPF_SUPPORT
void perf_env__exit(struct perf_env *env)
{
@@ -197,11 +204,13 @@ void perf_env__exit(struct perf_env *env)
zfree(&env->memory_nodes);
}
-void perf_env__init(struct perf_env *env)
+void perf_env__init(struct perf_env *env __maybe_unused)
{
+#ifdef HAVE_LIBBPF_SUPPORT
env->bpf_progs.infos = RB_ROOT;
env->bpf_progs.btfs = RB_ROOT;
init_rwsem(&env->bpf_progs.lock);
+#endif
}
int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index a12972652006..ca249bf5e984 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -77,7 +77,7 @@ struct perf_env {
struct numa_node *numa_nodes;
struct memory_node *memory_nodes;
unsigned long long memory_bsize;
-
+#ifdef HAVE_LIBBPF_SUPPORT
/*
* bpf_info_lock protects bpf rbtrees. This is needed because the
* trees are accessed by different threads in perf-top
@@ -89,7 +89,7 @@ struct perf_env {
struct rb_root btfs;
u32 btfs_cnt;
} bpf_progs;
-
+#endif // HAVE_LIBBPF_SUPPORT
/* same reason as above (for perf-top) */
struct {
struct rw_semaphore lock;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 317a26571845..05616d4138a9 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -398,7 +398,7 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
if (event->header.type == PERF_RECORD_SWITCH)
return fprintf(fp, " %s\n", in_out);
- return fprintf(fp, " %s %s pid/tid: %5u/%-5u\n",
+ return fprintf(fp, " %s %s pid/tid: %5d/%-5d\n",
in_out, out ? "next" : "prev",
event->context_switch.next_prev_pid,
event->context_switch.next_prev_tid);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b828b99176f4..ff403ea578e1 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -135,6 +135,7 @@ struct perf_sample {
u32 raw_size;
u64 data_src;
u64 phys_addr;
+ u64 data_page_size;
u64 cgroup;
u32 flags;
u16 insn_len;
@@ -408,4 +409,7 @@ extern int sysctl_perf_event_max_stack;
extern int sysctl_perf_event_max_contexts_per_stack;
extern unsigned int proc_map_timeout;
+#define PAGE_SIZE_NAME_LEN 32
+char *get_page_size_name(u64 size, char *str);
+
#endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c0768c61eb43..05363a7247c4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -78,7 +78,7 @@ struct evlist *evlist__new(void)
return evlist;
}
-struct evlist *perf_evlist__new_default(void)
+struct evlist *evlist__new_default(void)
{
struct evlist *evlist = evlist__new();
@@ -90,7 +90,7 @@ struct evlist *perf_evlist__new_default(void)
return evlist;
}
-struct evlist *perf_evlist__new_dummy(void)
+struct evlist *evlist__new_dummy(void)
{
struct evlist *evlist = evlist__new();
@@ -103,13 +103,13 @@ struct evlist *perf_evlist__new_dummy(void)
}
/**
- * perf_evlist__set_id_pos - set the positions of event ids.
+ * evlist__set_id_pos - set the positions of event ids.
* @evlist: selected event list
*
* Events with compatible sample types all have the same id_pos
* and is_pos. For convenience, put a copy on evlist.
*/
-void perf_evlist__set_id_pos(struct evlist *evlist)
+void evlist__set_id_pos(struct evlist *evlist)
{
struct evsel *first = evlist__first(evlist);
@@ -117,14 +117,14 @@ void perf_evlist__set_id_pos(struct evlist *evlist)
evlist->is_pos = first->is_pos;
}
-static void perf_evlist__update_id_pos(struct evlist *evlist)
+static void evlist__update_id_pos(struct evlist *evlist)
{
struct evsel *evsel;
evlist__for_each_entry(evlist, evsel)
evsel__calc_id_pos(evsel);
- perf_evlist__set_id_pos(evlist);
+ evlist__set_id_pos(evlist);
}
static void evlist__purge(struct evlist *evlist)
@@ -168,7 +168,7 @@ void evlist__add(struct evlist *evlist, struct evsel *entry)
perf_evlist__add(&evlist->core, &entry->core);
if (evlist->core.nr_entries == 1)
- perf_evlist__set_id_pos(evlist);
+ evlist__set_id_pos(evlist);
}
void evlist__remove(struct evlist *evlist, struct evsel *evsel)
@@ -177,27 +177,36 @@ void evlist__remove(struct evlist *evlist, struct evsel *evsel)
perf_evlist__remove(&evlist->core, &evsel->core);
}
-void perf_evlist__splice_list_tail(struct evlist *evlist,
- struct list_head *list)
+void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list)
{
- struct evsel *evsel, *temp;
+ while (!list_empty(list)) {
+ struct evsel *evsel, *temp, *leader = NULL;
- __evlist__for_each_entry_safe(list, temp, evsel) {
- list_del_init(&evsel->core.node);
- evlist__add(evlist, evsel);
+ __evlist__for_each_entry_safe(list, temp, evsel) {
+ list_del_init(&evsel->core.node);
+ evlist__add(evlist, evsel);
+ leader = evsel;
+ break;
+ }
+
+ __evlist__for_each_entry_safe(list, temp, evsel) {
+ if (evsel->leader == leader) {
+ list_del_init(&evsel->core.node);
+ evlist__add(evlist, evsel);
+ }
+ }
}
}
int __evlist__set_tracepoints_handlers(struct evlist *evlist,
const struct evsel_str_handler *assocs, size_t nr_assocs)
{
- struct evsel *evsel;
size_t i;
int err;
for (i = 0; i < nr_assocs; i++) {
// Adding a handler for an event not in this evlist, just ignore it.
- evsel = perf_evlist__find_tracepoint_by_name(evlist, assocs[i].name);
+ struct evsel *evsel = evlist__find_tracepoint_by_name(evlist, assocs[i].name);
if (evsel == NULL)
continue;
@@ -212,7 +221,7 @@ out:
return err;
}
-void __perf_evlist__set_leader(struct list_head *list)
+void __evlist__set_leader(struct list_head *list)
{
struct evsel *evsel, *leader;
@@ -226,11 +235,11 @@ void __perf_evlist__set_leader(struct list_head *list)
}
}
-void perf_evlist__set_leader(struct evlist *evlist)
+void evlist__set_leader(struct evlist *evlist)
{
if (evlist->core.nr_entries) {
evlist->nr_groups = evlist->core.nr_entries > 1 ? 1 : 0;
- __perf_evlist__set_leader(&evlist->core.entries);
+ __evlist__set_leader(&evlist->core.entries);
}
}
@@ -274,7 +283,7 @@ static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attr
list_add_tail(&evsel->core.node, &head);
}
- perf_evlist__splice_list_tail(evlist, &head);
+ evlist__splice_list_tail(evlist, &head);
return 0;
@@ -294,8 +303,7 @@ int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *a
return evlist__add_attrs(evlist, attrs, nr_attrs);
}
-struct evsel *
-perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
+struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
{
struct evsel *evsel;
@@ -308,9 +316,7 @@ perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
return NULL;
}
-struct evsel *
-perf_evlist__find_tracepoint_by_name(struct evlist *evlist,
- const char *name)
+struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name)
{
struct evsel *evsel;
@@ -335,8 +341,7 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name,
return 0;
}
-static int perf_evlist__nr_threads(struct evlist *evlist,
- struct evsel *evsel)
+static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel)
{
if (evsel->core.system_wide)
return 1;
@@ -376,7 +381,30 @@ bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
return true;
}
-void evlist__disable(struct evlist *evlist)
+static int evsel__strcmp(struct evsel *pos, char *evsel_name)
+{
+ if (!evsel_name)
+ return 0;
+ if (evsel__is_dummy_event(pos))
+ return 1;
+ return strcmp(pos->name, evsel_name);
+}
+
+static int evlist__is_enabled(struct evlist *evlist)
+{
+ struct evsel *pos;
+
+ evlist__for_each_entry(evlist, pos) {
+ if (!evsel__is_group_leader(pos) || !pos->core.fd)
+ continue;
+ /* If at least one event is enabled, evlist is enabled. */
+ if (!pos->disabled)
+ return true;
+ }
+ return false;
+}
+
+static void __evlist__disable(struct evlist *evlist, char *evsel_name)
{
struct evsel *pos;
struct affinity affinity;
@@ -392,6 +420,8 @@ void evlist__disable(struct evlist *evlist)
affinity__set(&affinity, cpu);
evlist__for_each_entry(evlist, pos) {
+ if (evsel__strcmp(pos, evsel_name))
+ continue;
if (evsel__cpu_iter_skip(pos, cpu))
continue;
if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
@@ -409,15 +439,34 @@ void evlist__disable(struct evlist *evlist)
affinity__cleanup(&affinity);
evlist__for_each_entry(evlist, pos) {
+ if (evsel__strcmp(pos, evsel_name))
+ continue;
if (!evsel__is_group_leader(pos) || !pos->core.fd)
continue;
pos->disabled = true;
}
- evlist->enabled = false;
+ /*
+ * If we disabled only single event, we need to check
+ * the enabled state of the evlist manually.
+ */
+ if (evsel_name)
+ evlist->enabled = evlist__is_enabled(evlist);
+ else
+ evlist->enabled = false;
}
-void evlist__enable(struct evlist *evlist)
+void evlist__disable(struct evlist *evlist)
+{
+ __evlist__disable(evlist, NULL);
+}
+
+void evlist__disable_evsel(struct evlist *evlist, char *evsel_name)
+{
+ __evlist__disable(evlist, evsel_name);
+}
+
+static void __evlist__enable(struct evlist *evlist, char *evsel_name)
{
struct evsel *pos;
struct affinity affinity;
@@ -430,6 +479,8 @@ void evlist__enable(struct evlist *evlist)
affinity__set(&affinity, cpu);
evlist__for_each_entry(evlist, pos) {
+ if (evsel__strcmp(pos, evsel_name))
+ continue;
if (evsel__cpu_iter_skip(pos, cpu))
continue;
if (!evsel__is_group_leader(pos) || !pos->core.fd)
@@ -439,24 +490,40 @@ void evlist__enable(struct evlist *evlist)
}
affinity__cleanup(&affinity);
evlist__for_each_entry(evlist, pos) {
+ if (evsel__strcmp(pos, evsel_name))
+ continue;
if (!evsel__is_group_leader(pos) || !pos->core.fd)
continue;
pos->disabled = false;
}
+ /*
+ * Even single event sets the 'enabled' for evlist,
+ * so the toggle can work properly and toggle to
+ * 'disabled' state.
+ */
evlist->enabled = true;
}
-void perf_evlist__toggle_enable(struct evlist *evlist)
+void evlist__enable(struct evlist *evlist)
+{
+ __evlist__enable(evlist, NULL);
+}
+
+void evlist__enable_evsel(struct evlist *evlist, char *evsel_name)
+{
+ __evlist__enable(evlist, evsel_name);
+}
+
+void evlist__toggle_enable(struct evlist *evlist)
{
(evlist->enabled ? evlist__disable : evlist__enable)(evlist);
}
-static int perf_evlist__enable_event_cpu(struct evlist *evlist,
- struct evsel *evsel, int cpu)
+static int evlist__enable_event_cpu(struct evlist *evlist, struct evsel *evsel, int cpu)
{
int thread;
- int nr_threads = perf_evlist__nr_threads(evlist, evsel);
+ int nr_threads = evlist__nr_threads(evlist, evsel);
if (!evsel->core.fd)
return -EINVAL;
@@ -469,9 +536,7 @@ static int perf_evlist__enable_event_cpu(struct evlist *evlist,
return 0;
}
-static int perf_evlist__enable_event_thread(struct evlist *evlist,
- struct evsel *evsel,
- int thread)
+static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread)
{
int cpu;
int nr_cpus = perf_cpu_map__nr(evlist->core.cpus);
@@ -487,15 +552,14 @@ static int perf_evlist__enable_event_thread(struct evlist *evlist,
return 0;
}
-int perf_evlist__enable_event_idx(struct evlist *evlist,
- struct evsel *evsel, int idx)
+int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
{
bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus);
if (per_cpu_mmaps)
- return perf_evlist__enable_event_cpu(evlist, evsel, idx);
- else
- return perf_evlist__enable_event_thread(evlist, evsel, idx);
+ return evlist__enable_event_cpu(evlist, evsel, idx);
+
+ return evlist__enable_event_thread(evlist, evsel, idx);
}
int evlist__add_pollfd(struct evlist *evlist, int fd)
@@ -513,7 +577,7 @@ int evlist__poll(struct evlist *evlist, int timeout)
return perf_evlist__poll(&evlist->core, timeout);
}
-struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id)
+struct perf_sample_id *evlist__id2sid(struct evlist *evlist, u64 id)
{
struct hlist_head *head;
struct perf_sample_id *sid;
@@ -529,14 +593,14 @@ struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id)
return NULL;
}
-struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id)
+struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id)
{
struct perf_sample_id *sid;
if (evlist->core.nr_entries == 1 || !id)
return evlist__first(evlist);
- sid = perf_evlist__id2sid(evlist, id);
+ sid = evlist__id2sid(evlist, id);
if (sid)
return container_of(sid->evsel, struct evsel, core);
@@ -546,23 +610,21 @@ struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id)
return NULL;
}
-struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist,
- u64 id)
+struct evsel *evlist__id2evsel_strict(struct evlist *evlist, u64 id)
{
struct perf_sample_id *sid;
if (!id)
return NULL;
- sid = perf_evlist__id2sid(evlist, id);
+ sid = evlist__id2sid(evlist, id);
if (sid)
return container_of(sid->evsel, struct evsel, core);
return NULL;
}
-static int perf_evlist__event2id(struct evlist *evlist,
- union perf_event *event, u64 *id)
+static int evlist__event2id(struct evlist *evlist, union perf_event *event, u64 *id)
{
const __u64 *array = event->sample.array;
ssize_t n;
@@ -582,8 +644,7 @@ static int perf_evlist__event2id(struct evlist *evlist,
return 0;
}
-struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
- union perf_event *event)
+struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event)
{
struct evsel *first = evlist__first(evlist);
struct hlist_head *head;
@@ -598,7 +659,7 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
event->header.type != PERF_RECORD_SAMPLE)
return first;
- if (perf_evlist__event2id(evlist, event, &id))
+ if (evlist__event2id(evlist, event, &id))
return NULL;
/* Synthesized events have an id of zero */
@@ -615,7 +676,7 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
return NULL;
}
-static int perf_evlist__set_paused(struct evlist *evlist, bool value)
+static int evlist__set_paused(struct evlist *evlist, bool value)
{
int i;
@@ -635,14 +696,14 @@ static int perf_evlist__set_paused(struct evlist *evlist, bool value)
return 0;
}
-static int perf_evlist__pause(struct evlist *evlist)
+static int evlist__pause(struct evlist *evlist)
{
- return perf_evlist__set_paused(evlist, true);
+ return evlist__set_paused(evlist, true);
}
-static int perf_evlist__resume(struct evlist *evlist)
+static int evlist__resume(struct evlist *evlist)
{
- return perf_evlist__set_paused(evlist, false);
+ return evlist__set_paused(evlist, false);
}
static void evlist__munmap_nofree(struct evlist *evlist)
@@ -727,7 +788,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx)
if (overwrite) {
evlist->overwrite_mmap = maps;
if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
- perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+ evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
} else {
evlist->mmap = maps;
}
@@ -827,7 +888,7 @@ static long parse_pages_arg(const char *str, unsigned long min,
return pages;
}
-int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
+int __evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
{
unsigned long max = UINT_MAX;
long pages;
@@ -845,10 +906,9 @@ int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
return 0;
}
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
- int unset __maybe_unused)
+int evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset __maybe_unused)
{
- return __perf_evlist__parse_mmap_pages(opt->value, str);
+ return __evlist__parse_mmap_pages(opt->value, str);
}
/**
@@ -904,7 +964,7 @@ int evlist__mmap(struct evlist *evlist, unsigned int pages)
return evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0);
}
-int perf_evlist__create_maps(struct evlist *evlist, struct target *target)
+int evlist__create_maps(struct evlist *evlist, struct target *target)
{
bool all_threads = (target->per_thread && target->system_wide);
struct perf_cpu_map *cpus;
@@ -957,25 +1017,7 @@ out_delete_threads:
return -1;
}
-void __perf_evlist__set_sample_bit(struct evlist *evlist,
- enum perf_event_sample_format bit)
-{
- struct evsel *evsel;
-
- evlist__for_each_entry(evlist, evsel)
- __evsel__set_sample_bit(evsel, bit);
-}
-
-void __perf_evlist__reset_sample_bit(struct evlist *evlist,
- enum perf_event_sample_format bit)
-{
- struct evsel *evsel;
-
- evlist__for_each_entry(evlist, evsel)
- __evsel__reset_sample_bit(evsel, bit);
-}
-
-int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
+int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
{
struct evsel *evsel;
int err = 0;
@@ -998,7 +1040,7 @@ int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
return err;
}
-int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
+int evlist__set_tp_filter(struct evlist *evlist, const char *filter)
{
struct evsel *evsel;
int err = 0;
@@ -1018,7 +1060,7 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
return err;
}
-int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter)
+int evlist__append_tp_filter(struct evlist *evlist, const char *filter)
{
struct evsel *evsel;
int err = 0;
@@ -1064,32 +1106,32 @@ out_free:
return NULL;
}
-int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
+int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
{
char *filter = asprintf__tp_filter_pids(npids, pids);
- int ret = perf_evlist__set_tp_filter(evlist, filter);
+ int ret = evlist__set_tp_filter(evlist, filter);
free(filter);
return ret;
}
-int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid)
+int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid)
{
- return perf_evlist__set_tp_filter_pids(evlist, 1, &pid);
+ return evlist__set_tp_filter_pids(evlist, 1, &pid);
}
-int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
+int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
{
char *filter = asprintf__tp_filter_pids(npids, pids);
- int ret = perf_evlist__append_tp_filter(evlist, filter);
+ int ret = evlist__append_tp_filter(evlist, filter);
free(filter);
return ret;
}
-int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid)
+int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid)
{
- return perf_evlist__append_tp_filter_pids(evlist, 1, &pid);
+ return evlist__append_tp_filter_pids(evlist, 1, &pid);
}
bool evlist__valid_sample_type(struct evlist *evlist)
@@ -1140,7 +1182,7 @@ u64 evlist__combined_branch_type(struct evlist *evlist)
return branch_type;
}
-bool perf_evlist__valid_read_format(struct evlist *evlist)
+bool evlist__valid_read_format(struct evlist *evlist)
{
struct evsel *first = evlist__first(evlist), *pos = first;
u64 read_format = first->core.attr.read_format;
@@ -1162,7 +1204,7 @@ bool perf_evlist__valid_read_format(struct evlist *evlist)
return true;
}
-u16 perf_evlist__id_hdr_size(struct evlist *evlist)
+u16 evlist__id_hdr_size(struct evlist *evlist)
{
struct evsel *first = evlist__first(evlist);
struct perf_sample *data;
@@ -1213,8 +1255,7 @@ bool evlist__sample_id_all(struct evlist *evlist)
return first->core.attr.sample_id_all;
}
-void perf_evlist__set_selected(struct evlist *evlist,
- struct evsel *evsel)
+void evlist__set_selected(struct evlist *evlist, struct evsel *evsel)
{
evlist->selected = evsel;
}
@@ -1253,7 +1294,7 @@ void evlist__close(struct evlist *evlist)
}
}
-static int perf_evlist__create_syswide_maps(struct evlist *evlist)
+static int evlist__create_syswide_maps(struct evlist *evlist)
{
struct perf_cpu_map *cpus;
struct perf_thread_map *threads;
@@ -1295,12 +1336,12 @@ int evlist__open(struct evlist *evlist)
* as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
*/
if (evlist->core.threads == NULL && evlist->core.cpus == NULL) {
- err = perf_evlist__create_syswide_maps(evlist);
+ err = evlist__create_syswide_maps(evlist);
if (err < 0)
goto out_err;
}
- perf_evlist__update_id_pos(evlist);
+ evlist__update_id_pos(evlist);
evlist__for_each_entry(evlist, evsel) {
err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads);
@@ -1315,9 +1356,8 @@ out_err:
return err;
}
-int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target,
- const char *argv[], bool pipe_output,
- void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
+int evlist__prepare_workload(struct evlist *evlist, struct target *target, const char *argv[],
+ bool pipe_output, void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
{
int child_ready_pipe[2], go_pipe[2];
char bf;
@@ -1362,7 +1402,7 @@ int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target,
/*
* The parent will ask for the execvp() to be performed by
* writing exactly one byte, in workload.cork_fd, usually via
- * perf_evlist__start_workload().
+ * evlist__start_workload().
*
* For cancelling the workload without actually running it,
* the parent will just close workload.cork_fd, without writing
@@ -1429,7 +1469,7 @@ out_close_ready_pipe:
return -1;
}
-int perf_evlist__start_workload(struct evlist *evlist)
+int evlist__start_workload(struct evlist *evlist)
{
if (evlist->workload.cork_fd > 0) {
char bf = 0;
@@ -1448,21 +1488,18 @@ int perf_evlist__start_workload(struct evlist *evlist)
return 0;
}
-int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event,
- struct perf_sample *sample)
+int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
{
- struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+ struct evsel *evsel = evlist__event2evsel(evlist, event);
if (!evsel)
return -EFAULT;
return evsel__parse_sample(evsel, event, sample);
}
-int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
- union perf_event *event,
- u64 *timestamp)
+int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp)
{
- struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+ struct evsel *evsel = evlist__event2evsel(evlist, event);
if (!evsel)
return -EFAULT;
@@ -1553,8 +1590,7 @@ int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size
return 0;
}
-void perf_evlist__to_front(struct evlist *evlist,
- struct evsel *move_evsel)
+void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel)
{
struct evsel *evsel, *n;
LIST_HEAD(move);
@@ -1570,7 +1606,7 @@ void perf_evlist__to_front(struct evlist *evlist,
list_splice(&move, &evlist->core.entries);
}
-struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist)
+struct evsel *evlist__get_tracking_event(struct evlist *evlist)
{
struct evsel *evsel;
@@ -1582,8 +1618,7 @@ struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist)
return evlist__first(evlist);
}
-void perf_evlist__set_tracking_event(struct evlist *evlist,
- struct evsel *tracking_evsel)
+void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel)
{
struct evsel *evsel;
@@ -1598,9 +1633,7 @@ void perf_evlist__set_tracking_event(struct evlist *evlist,
tracking_evsel->tracking = true;
}
-struct evsel *
-perf_evlist__find_evsel_by_str(struct evlist *evlist,
- const char *str)
+struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str)
{
struct evsel *evsel;
@@ -1614,8 +1647,7 @@ perf_evlist__find_evsel_by_str(struct evlist *evlist,
return NULL;
}
-void perf_evlist__toggle_bkw_mmap(struct evlist *evlist,
- enum bkw_mmap_state state)
+void evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state)
{
enum bkw_mmap_state old_state = evlist->bkw_mmap_state;
enum action {
@@ -1658,10 +1690,10 @@ void perf_evlist__toggle_bkw_mmap(struct evlist *evlist,
switch (action) {
case PAUSE:
- perf_evlist__pause(evlist);
+ evlist__pause(evlist);
break;
case RESUME:
- perf_evlist__resume(evlist);
+ evlist__resume(evlist);
break;
case NONE:
default:
@@ -1672,7 +1704,7 @@ state_err:
return;
}
-bool perf_evlist__exclude_kernel(struct evlist *evlist)
+bool evlist__exclude_kernel(struct evlist *evlist)
{
struct evsel *evsel;
@@ -1689,19 +1721,17 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist)
* the group display. Set the artificial group and set the leader's
* forced_leader flag to notify the display code.
*/
-void perf_evlist__force_leader(struct evlist *evlist)
+void evlist__force_leader(struct evlist *evlist)
{
if (!evlist->nr_groups) {
struct evsel *leader = evlist__first(evlist);
- perf_evlist__set_leader(evlist);
+ evlist__set_leader(evlist);
leader->forced_leader = true;
}
}
-struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
- struct evsel *evsel,
- bool close)
+struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel *evsel, bool close)
{
struct evsel *c2, *leader;
bool is_open = true;
@@ -1732,6 +1762,91 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
return leader;
}
+static int evlist__parse_control_fifo(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close)
+{
+ char *s, *p;
+ int ret = 0, fd;
+
+ if (strncmp(str, "fifo:", 5))
+ return -EINVAL;
+
+ str += 5;
+ if (!*str || *str == ',')
+ return -EINVAL;
+
+ s = strdup(str);
+ if (!s)
+ return -ENOMEM;
+
+ p = strchr(s, ',');
+ if (p)
+ *p = '\0';
+
+ /*
+ * O_RDWR avoids POLLHUPs which is necessary to allow the other
+ * end of a FIFO to be repeatedly opened and closed.
+ */
+ fd = open(s, O_RDWR | O_NONBLOCK | O_CLOEXEC);
+ if (fd < 0) {
+ pr_err("Failed to open '%s'\n", s);
+ ret = -errno;
+ goto out_free;
+ }
+ *ctl_fd = fd;
+ *ctl_fd_close = true;
+
+ if (p && *++p) {
+ /* O_RDWR | O_NONBLOCK means the other end need not be open */
+ fd = open(p, O_RDWR | O_NONBLOCK | O_CLOEXEC);
+ if (fd < 0) {
+ pr_err("Failed to open '%s'\n", p);
+ ret = -errno;
+ goto out_free;
+ }
+ *ctl_fd_ack = fd;
+ }
+
+out_free:
+ free(s);
+ return ret;
+}
+
+int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close)
+{
+ char *comma = NULL, *endptr = NULL;
+
+ *ctl_fd_close = false;
+
+ if (strncmp(str, "fd:", 3))
+ return evlist__parse_control_fifo(str, ctl_fd, ctl_fd_ack, ctl_fd_close);
+
+ *ctl_fd = strtoul(&str[3], &endptr, 0);
+ if (endptr == &str[3])
+ return -EINVAL;
+
+ comma = strchr(str, ',');
+ if (comma) {
+ if (endptr != comma)
+ return -EINVAL;
+
+ *ctl_fd_ack = strtoul(comma + 1, &endptr, 0);
+ if (endptr == comma + 1 || *endptr != '\0')
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+void evlist__close_control(int ctl_fd, int ctl_fd_ack, bool *ctl_fd_close)
+{
+ if (*ctl_fd_close) {
+ *ctl_fd_close = false;
+ close(ctl_fd);
+ if (ctl_fd_ack >= 0)
+ close(ctl_fd_ack);
+ }
+}
+
int evlist__initialize_ctlfd(struct evlist *evlist, int fd, int ack)
{
if (fd == -1) {
@@ -1783,6 +1898,7 @@ static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd,
char c;
size_t bytes_read = 0;
+ *cmd = EVLIST_CTL_CMD_UNSUPPORTED;
memset(cmd_data, 0, data_size);
data_size--;
@@ -1794,30 +1910,39 @@ static int evlist__ctlfd_recv(struct evlist *evlist, enum evlist_ctl_cmd *cmd,
cmd_data[bytes_read++] = c;
if (bytes_read == data_size)
break;
- } else {
- if (err == -1)
+ continue;
+ } else if (err == -1) {
+ if (errno == EINTR)
+ continue;
+ if (errno == EAGAIN || errno == EWOULDBLOCK)
+ err = 0;
+ else
pr_err("Failed to read from ctlfd %d: %m\n", evlist->ctl_fd.fd);
- break;
}
+ break;
} while (1);
pr_debug("Message from ctl_fd: \"%s%s\"\n", cmd_data,
bytes_read == data_size ? "" : c == '\n' ? "\\n" : "\\0");
- if (err > 0) {
+ if (bytes_read > 0) {
if (!strncmp(cmd_data, EVLIST_CTL_CMD_ENABLE_TAG,
(sizeof(EVLIST_CTL_CMD_ENABLE_TAG)-1))) {
*cmd = EVLIST_CTL_CMD_ENABLE;
} else if (!strncmp(cmd_data, EVLIST_CTL_CMD_DISABLE_TAG,
(sizeof(EVLIST_CTL_CMD_DISABLE_TAG)-1))) {
*cmd = EVLIST_CTL_CMD_DISABLE;
+ } else if (!strncmp(cmd_data, EVLIST_CTL_CMD_SNAPSHOT_TAG,
+ (sizeof(EVLIST_CTL_CMD_SNAPSHOT_TAG)-1))) {
+ *cmd = EVLIST_CTL_CMD_SNAPSHOT;
+ pr_debug("is snapshot\n");
}
}
- return err;
+ return bytes_read ? (int)bytes_read : err;
}
-static int evlist__ctlfd_ack(struct evlist *evlist)
+int evlist__ctlfd_ack(struct evlist *evlist)
{
int err;
@@ -1853,13 +1978,16 @@ int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd)
case EVLIST_CTL_CMD_DISABLE:
evlist__disable(evlist);
break;
+ case EVLIST_CTL_CMD_SNAPSHOT:
+ break;
case EVLIST_CTL_CMD_ACK:
case EVLIST_CTL_CMD_UNSUPPORTED:
default:
pr_debug("ctlfd: unsupported %d\n", *cmd);
break;
}
- if (!(*cmd == EVLIST_CTL_CMD_ACK || *cmd == EVLIST_CTL_CMD_UNSUPPORTED))
+ if (!(*cmd == EVLIST_CTL_CMD_ACK || *cmd == EVLIST_CTL_CMD_UNSUPPORTED ||
+ *cmd == EVLIST_CTL_CMD_SNAPSHOT))
evlist__ctlfd_ack(evlist);
}
}
@@ -1871,3 +1999,14 @@ int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd)
return err;
}
+
+struct evsel *evlist__find_evsel(struct evlist *evlist, int idx)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(evlist, evsel) {
+ if (evsel->idx == idx)
+ return evsel;
+ }
+ return NULL;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index c73f7f7f120b..1aae75895dea 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -87,8 +87,8 @@ struct evsel_str_handler {
};
struct evlist *evlist__new(void);
-struct evlist *perf_evlist__new_default(void);
-struct evlist *perf_evlist__new_dummy(void);
+struct evlist *evlist__new_default(void);
+struct evlist *evlist__new_dummy(void);
void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
void evlist__exit(struct evlist *evlist);
@@ -112,14 +112,11 @@ int __evlist__add_default_attrs(struct evlist *evlist,
int evlist__add_dummy(struct evlist *evlist);
-int perf_evlist__add_sb_event(struct evlist *evlist,
- struct perf_event_attr *attr,
- evsel__sb_cb_t cb,
- void *data);
+int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
+ evsel__sb_cb_t cb, void *data);
void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data);
-int perf_evlist__start_sb_thread(struct evlist *evlist,
- struct target *target);
-void perf_evlist__stop_sb_thread(struct evlist *evlist);
+int evlist__start_sb_thread(struct evlist *evlist, struct target *target);
+void evlist__stop_sb_thread(struct evlist *evlist);
int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler);
@@ -130,45 +127,29 @@ int __evlist__set_tracepoints_handlers(struct evlist *evlist,
#define evlist__set_tracepoints_handlers(evlist, array) \
__evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
-void __perf_evlist__set_sample_bit(struct evlist *evlist,
- enum perf_event_sample_format bit);
-void __perf_evlist__reset_sample_bit(struct evlist *evlist,
- enum perf_event_sample_format bit);
+int evlist__set_tp_filter(struct evlist *evlist, const char *filter);
+int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid);
+int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
-#define perf_evlist__set_sample_bit(evlist, bit) \
- __perf_evlist__set_sample_bit(evlist, PERF_SAMPLE_##bit)
+int evlist__append_tp_filter(struct evlist *evlist, const char *filter);
-#define perf_evlist__reset_sample_bit(evlist, bit) \
- __perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit)
+int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid);
+int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
-int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter);
-int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid);
-int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
-
-int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter);
-
-int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid);
-int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
-
-struct evsel *
-perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id);
-
-struct evsel *
-perf_evlist__find_tracepoint_by_name(struct evlist *evlist,
- const char *name);
+struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id);
+struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name);
int evlist__add_pollfd(struct evlist *evlist, int fd);
int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask);
int evlist__poll(struct evlist *evlist, int timeout);
-struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id);
-struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist,
- u64 id);
+struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id);
+struct evsel *evlist__id2evsel_strict(struct evlist *evlist, u64 id);
-struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id);
+struct perf_sample_id *evlist__id2sid(struct evlist *evlist, u64 id);
-void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state);
+void evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state);
void evlist__mmap_consume(struct evlist *evlist, int idx);
@@ -177,24 +158,19 @@ void evlist__close(struct evlist *evlist);
struct callchain_param;
-void perf_evlist__set_id_pos(struct evlist *evlist);
-void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
- struct callchain_param *callchain);
+void evlist__set_id_pos(struct evlist *evlist);
+void evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain);
int record_opts__config(struct record_opts *opts);
-int perf_evlist__prepare_workload(struct evlist *evlist,
- struct target *target,
- const char *argv[], bool pipe_output,
- void (*exec_error)(int signo, siginfo_t *info,
- void *ucontext));
-int perf_evlist__start_workload(struct evlist *evlist);
+int evlist__prepare_workload(struct evlist *evlist, struct target *target,
+ const char *argv[], bool pipe_output,
+ void (*exec_error)(int signo, siginfo_t *info, void *ucontext));
+int evlist__start_workload(struct evlist *evlist);
struct option;
-int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
-int perf_evlist__parse_mmap_pages(const struct option *opt,
- const char *str,
- int unset);
+int __evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
+int evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset);
unsigned long perf_event_mlock_kb_in_pages(void);
@@ -209,41 +185,36 @@ size_t evlist__mmap_size(unsigned long pages);
void evlist__disable(struct evlist *evlist);
void evlist__enable(struct evlist *evlist);
-void perf_evlist__toggle_enable(struct evlist *evlist);
+void evlist__toggle_enable(struct evlist *evlist);
+void evlist__disable_evsel(struct evlist *evlist, char *evsel_name);
+void evlist__enable_evsel(struct evlist *evlist, char *evsel_name);
-int perf_evlist__enable_event_idx(struct evlist *evlist,
- struct evsel *evsel, int idx);
+int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx);
-void perf_evlist__set_selected(struct evlist *evlist,
- struct evsel *evsel);
+void evlist__set_selected(struct evlist *evlist, struct evsel *evsel);
-int perf_evlist__create_maps(struct evlist *evlist, struct target *target);
-int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel);
+int evlist__create_maps(struct evlist *evlist, struct target *target);
+int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel);
-void __perf_evlist__set_leader(struct list_head *list);
-void perf_evlist__set_leader(struct evlist *evlist);
+void __evlist__set_leader(struct list_head *list);
+void evlist__set_leader(struct evlist *evlist);
u64 __evlist__combined_sample_type(struct evlist *evlist);
u64 evlist__combined_sample_type(struct evlist *evlist);
u64 evlist__combined_branch_type(struct evlist *evlist);
bool evlist__sample_id_all(struct evlist *evlist);
-u16 perf_evlist__id_hdr_size(struct evlist *evlist);
-
-int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event,
- struct perf_sample *sample);
+u16 evlist__id_hdr_size(struct evlist *evlist);
-int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
- union perf_event *event,
- u64 *timestamp);
+int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample);
+int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp);
bool evlist__valid_sample_type(struct evlist *evlist);
bool evlist__valid_sample_id_all(struct evlist *evlist);
-bool perf_evlist__valid_read_format(struct evlist *evlist);
+bool evlist__valid_read_format(struct evlist *evlist);
-void perf_evlist__splice_list_tail(struct evlist *evlist,
- struct list_head *list);
+void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list);
-static inline bool perf_evlist__empty(struct evlist *evlist)
+static inline bool evlist__empty(struct evlist *evlist)
{
return list_empty(&evlist->core.entries);
}
@@ -265,9 +236,8 @@ static inline struct evsel *evlist__last(struct evlist *evlist)
int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size);
int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size);
-bool perf_evlist__can_select_event(struct evlist *evlist, const char *str);
-void perf_evlist__to_front(struct evlist *evlist,
- struct evsel *move_evsel);
+bool evlist__can_select_event(struct evlist *evlist, const char *str);
+void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel);
/**
* __evlist__for_each_entry - iterate thru all the evsels
@@ -339,30 +309,27 @@ void perf_evlist__to_front(struct evlist *evlist,
evlist__cpu_iter_start(evlist); \
perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)
-struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist);
-void perf_evlist__set_tracking_event(struct evlist *evlist,
- struct evsel *tracking_evsel);
+struct evsel *evlist__get_tracking_event(struct evlist *evlist);
+void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel);
void evlist__cpu_iter_start(struct evlist *evlist);
bool evsel__cpu_iter_skip(struct evsel *ev, int cpu);
bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu);
-struct evsel *
-perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
+struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
+
+struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event);
-struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
- union perf_event *event);
+bool evlist__exclude_kernel(struct evlist *evlist);
-bool perf_evlist__exclude_kernel(struct evlist *evlist);
+void evlist__force_leader(struct evlist *evlist);
-void perf_evlist__force_leader(struct evlist *evlist);
+struct evsel *evlist__reset_weak_group(struct evlist *evlist, struct evsel *evsel, bool close);
-struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
- struct evsel *evsel,
- bool close);
#define EVLIST_CTL_CMD_ENABLE_TAG "enable"
#define EVLIST_CTL_CMD_DISABLE_TAG "disable"
#define EVLIST_CTL_CMD_ACK_TAG "ack\n"
+#define EVLIST_CTL_CMD_SNAPSHOT_TAG "snapshot"
#define EVLIST_CTL_CMD_MAX_LEN 64
@@ -370,15 +337,20 @@ enum evlist_ctl_cmd {
EVLIST_CTL_CMD_UNSUPPORTED = 0,
EVLIST_CTL_CMD_ENABLE,
EVLIST_CTL_CMD_DISABLE,
- EVLIST_CTL_CMD_ACK
+ EVLIST_CTL_CMD_ACK,
+ EVLIST_CTL_CMD_SNAPSHOT,
};
+int evlist__parse_control(const char *str, int *ctl_fd, int *ctl_fd_ack, bool *ctl_fd_close);
+void evlist__close_control(int ctl_fd, int ctl_fd_ack, bool *ctl_fd_close);
int evlist__initialize_ctlfd(struct evlist *evlist, int ctl_fd, int ctl_fd_ack);
int evlist__finalize_ctlfd(struct evlist *evlist);
bool evlist__ctlfd_initialized(struct evlist *evlist);
int evlist__ctlfd_process(struct evlist *evlist, enum evlist_ctl_cmd *cmd);
+int evlist__ctlfd_ack(struct evlist *evlist);
#define EVLIST_ENABLED_MSG "Events enabled\n"
#define EVLIST_DISABLED_MSG "Events disabled\n"
+struct evsel *evlist__find_evsel(struct evlist *evlist, int idx);
#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 459b51e90063..c26ea82220bd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -331,6 +331,110 @@ error_free:
goto out;
}
+static int evsel__copy_config_terms(struct evsel *dst, struct evsel *src)
+{
+ struct evsel_config_term *pos, *tmp;
+
+ list_for_each_entry(pos, &src->config_terms, list) {
+ tmp = malloc(sizeof(*tmp));
+ if (tmp == NULL)
+ return -ENOMEM;
+
+ *tmp = *pos;
+ if (tmp->free_str) {
+ tmp->val.str = strdup(pos->val.str);
+ if (tmp->val.str == NULL) {
+ free(tmp);
+ return -ENOMEM;
+ }
+ }
+ list_add_tail(&tmp->list, &dst->config_terms);
+ }
+ return 0;
+}
+
+/**
+ * evsel__clone - create a new evsel copied from @orig
+ * @orig: original evsel
+ *
+ * The assumption is that @orig is not configured nor opened yet.
+ * So we only care about the attributes that can be set while it's parsed.
+ */
+struct evsel *evsel__clone(struct evsel *orig)
+{
+ struct evsel *evsel;
+
+ BUG_ON(orig->core.fd);
+ BUG_ON(orig->counts);
+ BUG_ON(orig->priv);
+ BUG_ON(orig->per_pkg_mask);
+
+ /* cannot handle BPF objects for now */
+ if (orig->bpf_obj)
+ return NULL;
+
+ evsel = evsel__new(&orig->core.attr);
+ if (evsel == NULL)
+ return NULL;
+
+ evsel->core.cpus = perf_cpu_map__get(orig->core.cpus);
+ evsel->core.own_cpus = perf_cpu_map__get(orig->core.own_cpus);
+ evsel->core.threads = perf_thread_map__get(orig->core.threads);
+ evsel->core.nr_members = orig->core.nr_members;
+ evsel->core.system_wide = orig->core.system_wide;
+
+ if (orig->name) {
+ evsel->name = strdup(orig->name);
+ if (evsel->name == NULL)
+ goto out_err;
+ }
+ if (orig->group_name) {
+ evsel->group_name = strdup(orig->group_name);
+ if (evsel->group_name == NULL)
+ goto out_err;
+ }
+ if (orig->pmu_name) {
+ evsel->pmu_name = strdup(orig->pmu_name);
+ if (evsel->pmu_name == NULL)
+ goto out_err;
+ }
+ if (orig->filter) {
+ evsel->filter = strdup(orig->filter);
+ if (evsel->filter == NULL)
+ goto out_err;
+ }
+ evsel->cgrp = cgroup__get(orig->cgrp);
+ evsel->tp_format = orig->tp_format;
+ evsel->handler = orig->handler;
+ evsel->leader = orig->leader;
+
+ evsel->max_events = orig->max_events;
+ evsel->tool_event = orig->tool_event;
+ evsel->unit = orig->unit;
+ evsel->scale = orig->scale;
+ evsel->snapshot = orig->snapshot;
+ evsel->per_pkg = orig->per_pkg;
+ evsel->percore = orig->percore;
+ evsel->precise_max = orig->precise_max;
+ evsel->use_uncore_alias = orig->use_uncore_alias;
+ evsel->is_libpfm_event = orig->is_libpfm_event;
+
+ evsel->exclude_GH = orig->exclude_GH;
+ evsel->sample_read = orig->sample_read;
+ evsel->auto_merge_stats = orig->auto_merge_stats;
+ evsel->collect_stat = orig->collect_stat;
+ evsel->weak_group = orig->weak_group;
+
+ if (evsel__copy_config_terms(evsel, orig) < 0)
+ goto out_err;
+
+ return evsel;
+
+out_err:
+ evsel__delete(evsel);
+ return NULL;
+}
+
/*
* Returns pointer with encoded error via <linux/err.h> interface.
*/
@@ -393,7 +497,7 @@ static const char *__evsel__hw_name(u64 config)
return "unknown-hardware";
}
-static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
+static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
{
int colon = 0, r = 0;
struct perf_event_attr *attr = &evsel->core.attr;
@@ -432,7 +536,7 @@ static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
{
int r = scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config));
- return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+ return r + evsel__add_modifiers(evsel, bf + r, size - r);
}
const char *evsel__sw_names[PERF_COUNT_SW_MAX] = {
@@ -458,7 +562,7 @@ static const char *__evsel__sw_name(u64 config)
static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
{
int r = scnprintf(bf, size, "%s", __evsel__sw_name(evsel->core.attr.config));
- return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+ return r + evsel__add_modifiers(evsel, bf + r, size - r);
}
static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
@@ -483,7 +587,7 @@ static int evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
{
struct perf_event_attr *attr = &evsel->core.attr;
int r = __evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
- return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+ return r + evsel__add_modifiers(evsel, bf + r, size - r);
}
const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES] = {
@@ -578,13 +682,13 @@ out_err:
static int evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size)
{
int ret = __evsel__hw_cache_name(evsel->core.attr.config, bf, size);
- return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+ return ret + evsel__add_modifiers(evsel, bf + ret, size - ret);
}
static int evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
{
int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config);
- return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+ return ret + evsel__add_modifiers(evsel, bf + ret, size - ret);
}
static int evsel__tool_name(char *bf, size_t size)
@@ -746,9 +850,7 @@ void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
return __evsel__config_callchain(evsel, opts, param);
}
-static void
-perf_evsel__reset_callgraph(struct evsel *evsel,
- struct callchain_param *param)
+static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param)
{
struct perf_event_attr *attr = &evsel->core.attr;
@@ -884,7 +986,7 @@ static void evsel__apply_config_terms(struct evsel *evsel,
/* If global callgraph set, clear it */
if (callchain_param.enabled)
- perf_evsel__reset_callgraph(evsel, &callchain_param);
+ evsel__reset_callgraph(evsel, &callchain_param);
/* set perf-event callgraph */
if (param.enabled) {
@@ -1086,6 +1188,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
evsel__set_sample_bit(evsel, CGROUP);
}
+ if (opts->sample_data_page_size)
+ evsel__set_sample_bit(evsel, DATA_PAGE_SIZE);
+
if (opts->record_switch_events)
attr->context_switch = track;
@@ -1330,9 +1435,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu, int thread)
return perf_evsel__read(&evsel->core, cpu, thread, count);
}
-static void
-perf_evsel__set_count(struct evsel *counter, int cpu, int thread,
- u64 val, u64 ena, u64 run)
+static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run)
{
struct perf_counts_values *count;
@@ -1345,9 +1448,7 @@ perf_evsel__set_count(struct evsel *counter, int cpu, int thread,
perf_counts__set_loaded(counter->counts, cpu, thread, true);
}
-static int
-perf_evsel__process_group_data(struct evsel *leader,
- int cpu, int thread, u64 *data)
+static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data)
{
u64 read_format = leader->core.attr.read_format;
struct sample_read_value *v;
@@ -1366,18 +1467,16 @@ perf_evsel__process_group_data(struct evsel *leader,
v = (struct sample_read_value *) data;
- perf_evsel__set_count(leader, cpu, thread,
- v[0].value, ena, run);
+ evsel__set_count(leader, cpu, thread, v[0].value, ena, run);
for (i = 1; i < nr; i++) {
struct evsel *counter;
- counter = perf_evlist__id2evsel(leader->evlist, v[i].id);
+ counter = evlist__id2evsel(leader->evlist, v[i].id);
if (!counter)
return -EINVAL;
- perf_evsel__set_count(counter, cpu, thread,
- v[i].value, ena, run);
+ evsel__set_count(counter, cpu, thread, v[i].value, ena, run);
}
return 0;
@@ -1410,7 +1509,7 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread)
if (readn(FD(leader, cpu, thread), data, size) <= 0)
return -errno;
- return perf_evsel__process_group_data(leader, cpu, thread, data);
+ return evsel__process_group_data(leader, cpu, thread, data);
}
int evsel__read_counter(struct evsel *evsel, int cpu, int thread)
@@ -1463,9 +1562,7 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread)
return fd;
}
-static void perf_evsel__remove_fd(struct evsel *pos,
- int nr_cpus, int nr_threads,
- int thread_idx)
+static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx)
{
for (int cpu = 0; cpu < nr_cpus; cpu++)
for (int thread = thread_idx; thread < nr_threads - 1; thread++)
@@ -1484,7 +1581,7 @@ static int update_fds(struct evsel *evsel,
evlist__for_each_entry(evsel->evlist, pos) {
nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
- perf_evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
+ evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
/*
* Since fds for next evsel has not been created,
@@ -1684,6 +1781,11 @@ retry_open:
FD(evsel, cpu, thread) = fd;
+ if (unlikely(test_attr__enabled)) {
+ test_attr__open(&evsel->core.attr, pid, cpus->map[cpu],
+ fd, group_fd, flags);
+ }
+
if (fd < 0) {
err = -errno;
@@ -1771,7 +1873,12 @@ try_fallback:
* Must probe features in the order they were added to the
* perf_event_attr interface.
*/
- if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
+ if (!perf_missing_features.data_page_size &&
+ (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)) {
+ perf_missing_features.data_page_size = true;
+ pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n");
+ goto out_close;
+ } else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
perf_missing_features.cgroup = true;
pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n");
goto out_close;
@@ -2256,6 +2363,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
array++;
}
+ data->data_page_size = 0;
+ if (type & PERF_SAMPLE_DATA_PAGE_SIZE) {
+ data->data_page_size = *array;
+ array++;
+ }
+
if (type & PERF_SAMPLE_AUX) {
OVERFLOW_CHECK_u64(array);
sz = *array++;
@@ -2565,6 +2678,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
"We found oprofile daemon running, please stop it and try again.");
break;
case EINVAL:
+ if (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE && perf_missing_features.data_page_size)
+ return scnprintf(msg, size, "Asking for the data page size isn't supported by this kernel.");
if (evsel->core.attr.write_backward && perf_missing_features.write_backward)
return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
if (perf_missing_features.clockid)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 35e3f6d66085..cd1d8dd43199 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -42,65 +42,79 @@ enum perf_tool_event {
*/
struct evsel {
struct perf_evsel core;
- struct evlist *evlist;
- char *filter;
+ struct evlist *evlist;
+ off_t id_offset;
+ int idx;
+ int id_pos;
+ int is_pos;
+ unsigned int sample_size;
+
+ /*
+ * These fields can be set in the parse-events code or similar.
+ * Please check evsel__clone() to copy them properly so that
+ * they can be released properly.
+ */
+ struct {
+ char *name;
+ char *group_name;
+ const char *pmu_name;
+ struct tep_event *tp_format;
+ char *filter;
+ unsigned long max_events;
+ double scale;
+ const char *unit;
+ struct cgroup *cgrp;
+ enum perf_tool_event tool_event;
+ /* parse modifier helper */
+ int exclude_GH;
+ int sample_read;
+ bool snapshot;
+ bool per_pkg;
+ bool percore;
+ bool precise_max;
+ bool use_uncore_alias;
+ bool is_libpfm_event;
+ bool auto_merge_stats;
+ bool collect_stat;
+ bool weak_group;
+ int bpf_fd;
+ struct bpf_object *bpf_obj;
+ };
+
+ /*
+ * metric fields are similar, but needs more care as they can have
+ * references to other metric (evsel).
+ */
+ const char * metric_expr;
+ const char * metric_name;
+ struct evsel **metric_events;
+ struct evsel *metric_leader;
+
+ void *handler;
struct perf_counts *counts;
struct perf_counts *prev_raw_counts;
- int idx;
- unsigned long max_events;
unsigned long nr_events_printed;
- char *name;
- double scale;
- const char *unit;
- struct tep_event *tp_format;
- off_t id_offset;
struct perf_stat_evsel *stats;
void *priv;
u64 db_id;
- struct cgroup *cgrp;
- void *handler;
- unsigned int sample_size;
- int id_pos;
- int is_pos;
- enum perf_tool_event tool_event;
bool uniquified_name;
- bool snapshot;
bool supported;
bool needs_swap;
bool disabled;
bool no_aux_samples;
bool immediate;
bool tracking;
- bool per_pkg;
- bool precise_max;
bool ignore_missing_thread;
bool forced_leader;
- bool use_uncore_alias;
- bool is_libpfm_event;
- /* parse modifier helper */
- int exclude_GH;
- int sample_read;
- unsigned long *per_pkg_mask;
- struct evsel *leader;
- char *group_name;
bool cmdline_group_boundary;
- struct list_head config_terms;
- struct bpf_object *bpf_obj;
- int bpf_fd;
- int err;
- bool auto_merge_stats;
bool merged_stat;
- const char * metric_expr;
- const char * metric_name;
- struct evsel **metric_events;
- struct evsel *metric_leader;
- bool collect_stat;
- bool weak_group;
bool reset_group;
bool errored;
- bool percore;
+ unsigned long *per_pkg_mask;
+ struct evsel *leader;
+ struct list_head config_terms;
+ int err;
int cpu_iter;
- const char *pmu_name;
struct {
evsel__sb_cb_t *cb;
void *data;
@@ -130,6 +144,7 @@ struct perf_missing_features {
bool aux_output;
bool branch_hw_idx;
bool cgroup;
+ bool data_page_size;
};
extern struct perf_missing_features perf_missing_features;
@@ -169,6 +184,7 @@ static inline struct evsel *evsel__new(struct perf_event_attr *attr)
return evsel__new_idx(attr, 0);
}
+struct evsel *evsel__clone(struct evsel *orig);
struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx);
/*
diff --git a/tools/perf/util/evswitch.c b/tools/perf/util/evswitch.c
index 3ba72f743d3c..40cb56a9347d 100644
--- a/tools/perf/util/evswitch.c
+++ b/tools/perf/util/evswitch.c
@@ -41,7 +41,7 @@ static int evswitch__fprintf_enoent(FILE *fp, const char *evtype, const char *ev
int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp)
{
if (evswitch->on_name) {
- evswitch->on = perf_evlist__find_evsel_by_str(evlist, evswitch->on_name);
+ evswitch->on = evlist__find_evsel_by_str(evlist, evswitch->on_name);
if (evswitch->on == NULL) {
evswitch__fprintf_enoent(fp, "on", evswitch->on_name);
return -ENOENT;
@@ -50,7 +50,7 @@ int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp)
}
if (evswitch->off_name) {
- evswitch->off = perf_evlist__find_evsel_by_str(evlist, evswitch->off_name);
+ evswitch->off = evlist__find_evsel_by_str(evlist, evswitch->off_name);
if (evswitch->off == NULL) {
evswitch__fprintf_enoent(fp, "off", evswitch->off_name);
return -ENOENT;
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 53482ef53c41..a850fd0be3ee 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -17,6 +17,29 @@
extern int expr_debug;
#endif
+struct expr_id_data {
+ union {
+ double val;
+ struct {
+ double val;
+ const char *metric_name;
+ const char *metric_expr;
+ } ref;
+ struct expr_id *parent;
+ };
+
+ enum {
+ /* Holding a double value. */
+ EXPR_ID_DATA__VALUE,
+ /* Reference to another metric. */
+ EXPR_ID_DATA__REF,
+ /* A reference but the value has been computed. */
+ EXPR_ID_DATA__REF_VALUE,
+ /* A parent is remembered for the recursion check. */
+ EXPR_ID_DATA__PARENT,
+ } kind;
+};
+
static size_t key_hash(const void *key, void *ctx __maybe_unused)
{
const char *str = (const char *)key;
@@ -48,6 +71,7 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id)
return -ENOMEM;
data_ptr->parent = ctx->parent;
+ data_ptr->kind = EXPR_ID_DATA__PARENT;
ret = hashmap__set(&ctx->ids, id, data_ptr,
(const void **)&old_key, (void **)&old_data);
@@ -69,7 +93,7 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val)
if (!data_ptr)
return -ENOMEM;
data_ptr->val = val;
- data_ptr->is_ref = false;
+ data_ptr->kind = EXPR_ID_DATA__VALUE;
ret = hashmap__set(&ctx->ids, id, data_ptr,
(const void **)&old_key, (void **)&old_data);
@@ -114,8 +138,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref)
*/
data_ptr->ref.metric_name = ref->metric_name;
data_ptr->ref.metric_expr = ref->metric_expr;
- data_ptr->ref.counted = false;
- data_ptr->is_ref = true;
+ data_ptr->kind = EXPR_ID_DATA__REF;
ret = hashmap__set(&ctx->ids, name, data_ptr,
(const void **)&old_key, (void **)&old_data);
@@ -148,17 +171,30 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id,
data = *datap;
- pr_debug2("lookup: is_ref %d, counted %d, val %f: %s\n",
- data->is_ref, data->ref.counted, data->val, id);
-
- if (data->is_ref && !data->ref.counted) {
- data->ref.counted = true;
+ switch (data->kind) {
+ case EXPR_ID_DATA__VALUE:
+ pr_debug2("lookup(%s): val %f\n", id, data->val);
+ break;
+ case EXPR_ID_DATA__PARENT:
+ pr_debug2("lookup(%s): parent %s\n", id, data->parent->id);
+ break;
+ case EXPR_ID_DATA__REF:
+ pr_debug2("lookup(%s): ref metric name %s\n", id,
+ data->ref.metric_name);
pr_debug("processing metric: %s ENTRY\n", id);
- if (expr__parse(&data->val, ctx, data->ref.metric_expr, 1)) {
+ data->kind = EXPR_ID_DATA__REF_VALUE;
+ if (expr__parse(&data->ref.val, ctx, data->ref.metric_expr, 1)) {
pr_debug("%s failed to count\n", id);
return -1;
}
pr_debug("processing metric: %s EXIT: %f\n", id, data->val);
+ break;
+ case EXPR_ID_DATA__REF_VALUE:
+ pr_debug2("lookup(%s): ref val %f metric name %s\n", id,
+ data->ref.val, data->ref.metric_name);
+ break;
+ default:
+ assert(0); /* Unreachable. */
}
return 0;
@@ -241,3 +277,17 @@ int expr__find_other(const char *expr, const char *one,
return ret;
}
+
+double expr_id_data__value(const struct expr_id_data *data)
+{
+ if (data->kind == EXPR_ID_DATA__VALUE)
+ return data->val;
+ assert(data->kind == EXPR_ID_DATA__REF_VALUE);
+ return data->ref.val;
+}
+
+struct expr_id *expr_id_data__parent(struct expr_id_data *data)
+{
+ assert(data->kind == EXPR_ID_DATA__PARENT);
+ return data->parent;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index fc2b5e824a66..dcf8d19b83c8 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -23,19 +23,7 @@ struct expr_parse_ctx {
struct expr_id *parent;
};
-struct expr_id_data {
- union {
- double val;
- struct {
- const char *metric_name;
- const char *metric_expr;
- bool counted;
- } ref;
- struct expr_id *parent;
- };
-
- bool is_ref;
-};
+struct expr_id_data;
struct expr_scanner_ctx {
int start_token;
@@ -57,4 +45,7 @@ int expr__parse(double *final_val, struct expr_parse_ctx *ctx,
int expr__find_other(const char *expr, const char *one,
struct expr_parse_ctx *ids, int runtime);
+double expr_id_data__value(const struct expr_id_data *data);
+struct expr_id *expr_id_data__parent(struct expr_id_data *data);
+
#endif
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index d34b370391c6..b2ada8f8309a 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -93,7 +93,7 @@ expr: NUMBER
YYABORT;
}
- $$ = data->val;
+ $$ = expr_id_data__value(data);
free($1);
}
| expr '|' expr { $$ = (long)$1 | (long)$3; }
diff --git a/tools/perf/util/group.h b/tools/perf/util/group.h
deleted file mode 100644
index f36c7e31780a..000000000000
--- a/tools/perf/util/group.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef GROUP_H
-#define GROUP_H 1
-
-bool arch_topdown_check_group(bool *warn);
-void arch_topdown_group_warn(void);
-
-#endif
diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c
index a405dad068f5..3c20b126d60d 100644
--- a/tools/perf/util/hashmap.c
+++ b/tools/perf/util/hashmap.c
@@ -15,6 +15,9 @@
/* make sure libbpf doesn't use kernel-only integer typedefs */
#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
/* start with 4 buckets */
#define HASHMAP_MIN_CAP_BITS 2
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index e0af36b0e5d8..10a4c4cd13cf 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -15,6 +15,9 @@
static inline size_t hash_bits(size_t h, int bits)
{
/* shuffle bits and return requested number of upper bits */
+ if (bits == 0)
+ return 0;
+
#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
/* LP64 case */
return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
@@ -25,6 +28,18 @@ static inline size_t hash_bits(size_t h, int bits)
#endif
}
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+ size_t h = 0;
+
+ while (*s) {
+ h = h * 31 + *s;
+ s++;
+ }
+ return h;
+}
+
typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
@@ -162,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value);
* @key: key to iterate entries for
*/
#define hashmap__for_each_key_entry(map, cur, _key) \
- for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
- map->cap_bits); \
- map->buckets ? map->buckets[bkt] : NULL; }); \
+ for (cur = map->buckets \
+ ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+ : NULL; \
cur; \
cur = cur->next) \
if (map->equal_fn(cur->key, (_key), map->ctx))
#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \
- for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
- map->cap_bits); \
- cur = map->buckets ? map->buckets[bkt] : NULL; }); \
+ for (cur = map->buckets \
+ ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+ : NULL; \
cur && ({ tmp = cur->next; true; }); \
cur = tmp) \
if (map->equal_fn(cur->key, (_key), map->ctx))
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 9cf4efdcbbbd..c4ed3dc2c8f4 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -19,7 +19,9 @@
#include <sys/utsname.h>
#include <linux/time64.h>
#include <dirent.h>
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/libbpf.h>
+#endif
#include <perf/cpumap.h>
#include "dso.h"
@@ -987,13 +989,6 @@ out:
up_read(&env->bpf_progs.lock);
return ret;
}
-#else // HAVE_LIBBPF_SUPPORT
-static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused,
- struct evlist *evlist __maybe_unused)
-{
- return 0;
-}
-#endif // HAVE_LIBBPF_SUPPORT
static int write_bpf_btf(struct feat_fd *ff,
struct evlist *evlist __maybe_unused)
@@ -1027,6 +1022,7 @@ out:
up_read(&env->bpf_progs.lock);
return ret;
}
+#endif // HAVE_LIBBPF_SUPPORT
static int cpu_cache_level__sort(const void *a, const void *b)
{
@@ -1638,6 +1634,7 @@ static void print_dir_format(struct feat_fd *ff, FILE *fp)
fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version);
}
+#ifdef HAVE_LIBBPF_SUPPORT
static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
{
struct perf_env *env = &ff->ph->env;
@@ -1683,6 +1680,7 @@ static void print_bpf_btf(struct feat_fd *ff, FILE *fp)
up_read(&env->bpf_progs.lock);
}
+#endif // HAVE_LIBBPF_SUPPORT
static void free_event_desc(struct evsel *events)
{
@@ -2082,8 +2080,14 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
dso = machine__findnew_dso(machine, filename);
if (dso != NULL) {
char sbuild_id[SBUILD_ID_SIZE];
+ struct build_id bid;
+ size_t size = BUILD_ID_SIZE;
- dso__set_build_id(dso, &bev->build_id);
+ if (bev->header.misc & PERF_RECORD_MISC_BUILD_ID_SIZE)
+ size = bev->size;
+
+ build_id__init(&bid, bev->data, size);
+ dso__set_build_id(dso, &bid);
if (dso_space != DSO_SPACE__USER) {
struct kmod_path m = { .name = NULL, };
@@ -2095,10 +2099,9 @@ static int __event_process_build_id(struct perf_record_header_build_id *bev,
free(m.name);
}
- build_id__sprintf(dso->build_id, sizeof(dso->build_id),
- sbuild_id);
- pr_debug("build id event received for %s: %s\n",
- dso->long_name, sbuild_id);
+ build_id__sprintf(&dso->bid, sbuild_id);
+ pr_debug("build id event received for %s: %s [%zu]\n",
+ dso->long_name, sbuild_id, size);
dso__put(dso);
}
@@ -2260,8 +2263,7 @@ static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused)
return 0;
}
-static struct evsel *
-perf_evlist__find_by_index(struct evlist *evlist, int idx)
+static struct evsel *evlist__find_by_index(struct evlist *evlist, int idx)
{
struct evsel *evsel;
@@ -2273,16 +2275,14 @@ perf_evlist__find_by_index(struct evlist *evlist, int idx)
return NULL;
}
-static void
-perf_evlist__set_event_name(struct evlist *evlist,
- struct evsel *event)
+static void evlist__set_event_name(struct evlist *evlist, struct evsel *event)
{
struct evsel *evsel;
if (!event->name)
return;
- evsel = perf_evlist__find_by_index(evlist, event->idx);
+ evsel = evlist__find_by_index(evlist, event->idx);
if (!evsel)
return;
@@ -2310,7 +2310,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
}
for (evsel = events; evsel->core.attr.size; evsel++)
- perf_evlist__set_event_name(session->evlist, evsel);
+ evlist__set_event_name(session->evlist, evsel);
if (!session->data->is_pipe)
free_event_desc(events);
@@ -2933,12 +2933,6 @@ out:
up_write(&env->bpf_progs.lock);
return err;
}
-#else // HAVE_LIBBPF_SUPPORT
-static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused)
-{
- return 0;
-}
-#endif // HAVE_LIBBPF_SUPPORT
static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
{
@@ -2985,6 +2979,7 @@ out:
free(node);
return err;
}
+#endif // HAVE_LIBBPF_SUPPORT
static int process_compressed(struct feat_fd *ff,
void *data __maybe_unused)
@@ -3115,8 +3110,10 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
FEAT_OPR(MEM_TOPOLOGY, mem_topology, true),
FEAT_OPR(CLOCKID, clockid, false),
FEAT_OPN(DIR_FORMAT, dir_format, false),
+#ifdef HAVE_LIBBPF_SUPPORT
FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false),
FEAT_OPR(BPF_BTF, bpf_btf, false),
+#endif
FEAT_OPR(COMPRESSED, compressed, false),
FEAT_OPR(CPU_PMU_CAPS, cpu_pmu_caps, false),
FEAT_OPR(CLOCK_DATA, clock_data, false),
@@ -3326,6 +3323,14 @@ int perf_session__write_header(struct perf_session *session,
attr_offset = lseek(ff.fd, 0, SEEK_CUR);
evlist__for_each_entry(evlist, evsel) {
+ if (evsel->core.attr.size < sizeof(evsel->core.attr)) {
+ /*
+ * We are likely in "perf inject" and have read
+ * from an older file. Update attr size so that
+ * reader gets the right offset to the ids.
+ */
+ evsel->core.attr.size = sizeof(evsel->core.attr);
+ }
f_attr = (struct perf_file_attr){
.attr = evsel->core.attr,
.ids = {
@@ -3647,7 +3652,8 @@ static int perf_file_section__process(struct perf_file_section *section,
}
static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
- struct perf_header *ph, int fd,
+ struct perf_header *ph,
+ struct perf_data* data,
bool repipe)
{
struct feat_fd ff = {
@@ -3656,7 +3662,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
};
ssize_t ret;
- ret = readn(fd, header, sizeof(*header));
+ ret = perf_data__read(data, header, sizeof(*header));
if (ret <= 0)
return -1;
@@ -3679,8 +3685,7 @@ static int perf_header__read_pipe(struct perf_session *session)
struct perf_header *header = &session->header;
struct perf_pipe_file_header f_header;
- if (perf_file_header__read_pipe(&f_header, header,
- perf_data__fd(session->data),
+ if (perf_file_header__read_pipe(&f_header, header, session->data,
session->repipe) < 0) {
pr_debug("incompatible file format\n");
return -EINVAL;
@@ -3735,8 +3740,7 @@ static int read_attr(int fd, struct perf_header *ph,
return ret <= 0 ? -1 : 0;
}
-static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel,
- struct tep_handle *pevent)
+static int evsel__prepare_tracepoint_event(struct evsel *evsel, struct tep_handle *pevent)
{
struct tep_event *event;
char bf[128];
@@ -3767,14 +3771,13 @@ static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel,
return 0;
}
-static int perf_evlist__prepare_tracepoint_events(struct evlist *evlist,
- struct tep_handle *pevent)
+static int evlist__prepare_tracepoint_events(struct evlist *evlist, struct tep_handle *pevent)
{
struct evsel *pos;
evlist__for_each_entry(evlist, pos) {
if (pos->core.attr.type == PERF_TYPE_TRACEPOINT &&
- perf_evsel__prepare_tracepoint_event(pos, pevent))
+ evsel__prepare_tracepoint_event(pos, pevent))
return -1;
}
@@ -3883,8 +3886,7 @@ int perf_session__read_header(struct perf_session *session)
perf_header__process_sections(header, fd, &session->tevent,
perf_file_section__process);
- if (perf_evlist__prepare_tracepoint_events(session->evlist,
- session->tevent.pevent))
+ if (evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent))
goto out_delete_evlist;
return 0;
@@ -4032,7 +4034,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
evlist = *pevlist;
- evsel = perf_evlist__id2evsel(evlist, ev->id);
+ evsel = evlist__id2evsel(evlist, ev->id);
if (evsel == NULL)
return -EINVAL;
@@ -4105,8 +4107,7 @@ int perf_event__process_tracing_data(struct perf_session *session,
return -1;
}
- perf_evlist__prepare_tracepoint_events(session->evlist,
- session->tevent.pevent);
+ evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent);
return size_read + padding;
}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8a793e4c9400..a08fb9ea411b 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -188,6 +188,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR,
unresolved_col_width + 4 + 2);
+ hists__new_col_len(hists, HISTC_MEM_DATA_PAGE_SIZE,
+ unresolved_col_width + 4 + 2);
+
} else {
symlen = unresolved_col_width + 4 + 2;
hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
@@ -2654,7 +2657,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
}
}
-size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp)
+size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp)
{
struct evsel *pos;
size_t ret = 0;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 96b1c13bbccc..14f66330923d 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -56,6 +56,7 @@ enum hist_column {
HISTC_MEM_DADDR_SYMBOL,
HISTC_MEM_DADDR_DSO,
HISTC_MEM_PHYS_DADDR,
+ HISTC_MEM_DATA_PAGE_SIZE,
HISTC_MEM_LOCKED,
HISTC_MEM_TLB,
HISTC_MEM_LVL,
@@ -196,7 +197,7 @@ void hists__inc_nr_samples(struct hists *hists, bool filtered);
size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
int max_cols, float min_pcnt, FILE *fp,
bool ignore_callchains);
-size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp);
+size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp);
void hists__filter_by_dso(struct hists *hists);
void hists__filter_by_thread(struct hists *hists);
@@ -464,12 +465,9 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
struct hist_browser_timer *hbt,
struct annotation_options *annotation_opts);
-int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help,
- struct hist_browser_timer *hbt,
- float min_pcnt,
- struct perf_env *env,
- bool warn_lost_event,
- struct annotation_options *annotation_options);
+int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt,
+ float min_pcnt, struct perf_env *env, bool warn_lost_event,
+ struct annotation_options *annotation_options);
int script_browse(const char *script_opt, struct evsel *evsel);
@@ -483,13 +481,13 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
struct annotation_options *annotation_opts);
#else
static inline
-int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
- const char *help __maybe_unused,
- struct hist_browser_timer *hbt __maybe_unused,
- float min_pcnt __maybe_unused,
- struct perf_env *env __maybe_unused,
- bool warn_lost_event __maybe_unused,
- struct annotation_options *annotation_options __maybe_unused)
+int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
+ const char *help __maybe_unused,
+ struct hist_browser_timer *hbt __maybe_unused,
+ float min_pcnt __maybe_unused,
+ struct perf_env *env __maybe_unused,
+ bool warn_lost_event __maybe_unused,
+ struct annotation_options *annotation_options __maybe_unused)
{
return 0;
}
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index b8a5159361b4..5acf053fca7d 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -25,6 +25,7 @@
/* SYM_L_* -- linkage of symbols */
#define SYM_L_GLOBAL(name) .globl name
+#define SYM_L_WEAK(name) .weak name
#define SYM_L_LOCAL(name) /* nothing */
#define ALIGN __ALIGN
@@ -84,6 +85,12 @@
SYM_END(name, SYM_T_FUNC)
#endif
+/* SYM_FUNC_START_WEAK -- use for weak functions */
+#ifndef SYM_FUNC_START_WEAK
+#define SYM_FUNC_START_WEAK(name) \
+ SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)
+#endif
+
/*
* SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
* SYM_FUNC_START_WEAK, ...
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 0af4e81c46e2..60214de42f31 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1101,6 +1101,8 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
if (queue->tid == -1 || pt->have_sched_switch) {
ptq->tid = machine__get_current_tid(pt->machine, ptq->cpu);
+ if (ptq->tid == -1)
+ ptq->pid = -1;
thread__zput(ptq->thread);
}
@@ -2518,11 +2520,10 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
static int intel_pt_process_switch(struct intel_pt *pt,
struct perf_sample *sample)
{
- struct evsel *evsel;
pid_t tid;
int cpu, ret;
+ struct evsel *evsel = evlist__id2evsel(pt->session->evlist, sample->id);
- evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
if (evsel != pt->switch_evsel)
return 0;
@@ -2603,10 +2604,8 @@ static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
tid = sample->tid;
}
- if (tid == -1) {
- pr_err("context_switch event has no tid\n");
- return -EINVAL;
- }
+ if (tid == -1)
+ intel_pt_log("context_switch event has no tid\n");
ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
if (ret <= 0)
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 0804308ef285..055bab7a92b3 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -374,11 +374,15 @@ static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp)
if (!jd->use_arch_timestamp)
return timestamp;
- tc.time_shift = jd->session->time_conv.time_shift;
- tc.time_mult = jd->session->time_conv.time_mult;
- tc.time_zero = jd->session->time_conv.time_zero;
-
- if (!tc.time_mult)
+ tc.time_shift = jd->session->time_conv.time_shift;
+ tc.time_mult = jd->session->time_conv.time_mult;
+ tc.time_zero = jd->session->time_conv.time_zero;
+ tc.time_cycles = jd->session->time_conv.time_cycles;
+ tc.time_mask = jd->session->time_conv.time_mask;
+ tc.cap_user_time_zero = jd->session->time_conv.cap_user_time_zero;
+ tc.cap_user_time_short = jd->session->time_conv.cap_user_time_short;
+
+ if (!tc.cap_user_time_zero)
return 0;
return tsc_to_perf_time(timestamp, &tc);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 85587de027a5..1e9d3f982b47 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -786,11 +786,20 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
union perf_event *event,
struct perf_sample *sample __maybe_unused)
{
+ struct symbol *sym;
struct map *map;
map = maps__find(&machine->kmaps, event->ksymbol.addr);
- if (map)
+ if (!map)
+ return 0;
+
+ if (map != machine->vmlinux_map)
maps__remove(&machine->kmaps, map);
+ else {
+ sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
+ if (sym)
+ dso__delete_symbol(map->dso, sym);
+ }
return 0;
}
@@ -1572,32 +1581,25 @@ static bool machine__uses_kcore(struct machine *machine)
}
static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
- union perf_event *event)
+ struct extra_kernel_map *xm)
{
return machine__is(machine, "x86_64") &&
- is_entry_trampoline(event->mmap.filename);
+ is_entry_trampoline(xm->name);
}
static int machine__process_extra_kernel_map(struct machine *machine,
- union perf_event *event)
+ struct extra_kernel_map *xm)
{
struct dso *kernel = machine__kernel_dso(machine);
- struct extra_kernel_map xm = {
- .start = event->mmap.start,
- .end = event->mmap.start + event->mmap.len,
- .pgoff = event->mmap.pgoff,
- };
if (kernel == NULL)
return -1;
- strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN);
-
- return machine__create_extra_kernel_map(machine, kernel, &xm);
+ return machine__create_extra_kernel_map(machine, kernel, xm);
}
static int machine__process_kernel_mmap_event(struct machine *machine,
- union perf_event *event)
+ struct extra_kernel_map *xm)
{
struct map *map;
enum dso_space_type dso_space;
@@ -1612,20 +1614,18 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
else
dso_space = DSO_SPACE__KERNEL_GUEST;
- is_kernel_mmap = memcmp(event->mmap.filename,
- machine->mmap_name,
+ is_kernel_mmap = memcmp(xm->name, machine->mmap_name,
strlen(machine->mmap_name) - 1) == 0;
- if (event->mmap.filename[0] == '/' ||
- (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
- map = machine__addnew_module_map(machine, event->mmap.start,
- event->mmap.filename);
+ if (xm->name[0] == '/' ||
+ (!is_kernel_mmap && xm->name[0] == '[')) {
+ map = machine__addnew_module_map(machine, xm->start,
+ xm->name);
if (map == NULL)
goto out_problem;
- map->end = map->start + event->mmap.len;
+ map->end = map->start + xm->end - xm->start;
} else if (is_kernel_mmap) {
- const char *symbol_name = (event->mmap.filename +
- strlen(machine->mmap_name));
+ const char *symbol_name = (xm->name + strlen(machine->mmap_name));
/*
* Should be there already, from the build-id table in
* the header.
@@ -1679,18 +1679,17 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
if (strstr(kernel->long_name, "vmlinux"))
dso__set_short_name(kernel, "[kernel.vmlinux]", false);
- machine__update_kernel_mmap(machine, event->mmap.start,
- event->mmap.start + event->mmap.len);
+ machine__update_kernel_mmap(machine, xm->start, xm->end);
/*
* Avoid using a zero address (kptr_restrict) for the ref reloc
* symbol. Effectively having zero here means that at record
* time /proc/sys/kernel/kptr_restrict was non zero.
*/
- if (event->mmap.pgoff != 0) {
+ if (xm->pgoff != 0) {
map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map,
symbol_name,
- event->mmap.pgoff);
+ xm->pgoff);
}
if (machine__is_default_guest(machine)) {
@@ -1699,8 +1698,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
*/
dso__load(kernel, machine__kernel_map(machine));
}
- } else if (perf_event__is_extra_kernel_mmap(machine, event)) {
- return machine__process_extra_kernel_map(machine, event);
+ } else if (perf_event__is_extra_kernel_mmap(machine, xm)) {
+ return machine__process_extra_kernel_map(machine, xm);
}
return 0;
out_problem:
@@ -1726,7 +1725,14 @@ int machine__process_mmap2_event(struct machine *machine,
if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
sample->cpumode == PERF_RECORD_MISC_KERNEL) {
- ret = machine__process_kernel_mmap_event(machine, event);
+ struct extra_kernel_map xm = {
+ .start = event->mmap2.start,
+ .end = event->mmap2.start + event->mmap2.len,
+ .pgoff = event->mmap2.pgoff,
+ };
+
+ strlcpy(xm.name, event->mmap2.filename, KMAP_NAME_LEN);
+ ret = machine__process_kernel_mmap_event(machine, &xm);
if (ret < 0)
goto out_problem;
return 0;
@@ -1776,7 +1782,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
sample->cpumode == PERF_RECORD_MISC_KERNEL) {
- ret = machine__process_kernel_mmap_event(machine, event);
+ struct extra_kernel_map xm = {
+ .start = event->mmap.start,
+ .end = event->mmap.start + event->mmap.len,
+ .pgoff = event->mmap.pgoff,
+ };
+
+ strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN);
+ ret = machine__process_kernel_mmap_event(machine, &xm);
if (ret < 0)
goto out_problem;
return 0;
@@ -2010,11 +2023,12 @@ static void ip__resolve_ams(struct thread *thread,
ams->ms.sym = al.sym;
ams->ms.map = al.map;
ams->phys_addr = 0;
+ ams->data_page_size = 0;
}
static void ip__resolve_data(struct thread *thread,
u8 m, struct addr_map_symbol *ams,
- u64 addr, u64 phys_addr)
+ u64 addr, u64 phys_addr, u64 daddr_page_size)
{
struct addr_location al;
@@ -2028,6 +2042,7 @@ static void ip__resolve_data(struct thread *thread,
ams->ms.sym = al.sym;
ams->ms.map = al.map;
ams->phys_addr = phys_addr;
+ ams->data_page_size = daddr_page_size;
}
struct mem_info *sample__resolve_mem(struct perf_sample *sample,
@@ -2040,7 +2055,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
- sample->addr, sample->phys_addr);
+ sample->addr, sample->phys_addr,
+ sample->data_page_size);
mi->data_src.val = sample->data_src;
return mi;
@@ -2964,7 +2980,7 @@ int machines__for_each_thread(struct machines *machines,
pid_t machine__get_current_tid(struct machine *machine, int cpu)
{
- int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
return -1;
@@ -2976,7 +2992,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
pid_t tid)
{
struct thread *thread;
- int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
if (cpu < 0)
return -EINVAL;
@@ -3100,3 +3116,15 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
*addrp = map->unmap_ip(map, sym->start);
return sym->name;
}
+
+int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv)
+{
+ struct dso *pos;
+ int err = 0;
+
+ list_for_each_entry(pos, &machine->dsos.head, node) {
+ if (fn(pos, machine, priv))
+ err = -1;
+ }
+ return err;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 062c36a8433c..26368d3c1754 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -250,6 +250,10 @@ void machines__destroy_kernel_maps(struct machines *machines);
size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
+typedef int (*machine__dso_t)(struct dso *dso, struct machine *machine, void *priv);
+
+int machine__for_each_dso(struct machine *machine, machine__dso_t fn,
+ void *priv);
int machine__for_each_thread(struct machine *machine,
int (*fn)(struct thread *thread, void *p),
void *priv);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index cc0faf8f1321..f44ede437dc7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -27,21 +27,6 @@
static void __maps__insert(struct maps *maps, struct map *map);
-static inline int is_anon_memory(const char *filename, u32 flags)
-{
- return flags & MAP_HUGETLB ||
- !strcmp(filename, "//anon") ||
- !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
- !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
-}
-
-static inline int is_no_dso_memory(const char *filename)
-{
- return !strncmp(filename, "[stack", 6) ||
- !strncmp(filename, "/SYSV",5) ||
- !strcmp(filename, "[heap]");
-}
-
static inline int is_android_lib(const char *filename)
{
return strstarts(filename, "/data/app-lib/") ||
@@ -158,7 +143,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
int anon, no_dso, vdso, android;
android = is_android_lib(filename);
- anon = is_anon_memory(filename, flags);
+ anon = is_anon_memory(filename) || flags & MAP_HUGETLB;
vdso = is_vdso_map(filename);
no_dso = is_no_dso_memory(filename);
map->prot = prot;
@@ -346,9 +331,7 @@ int map__load(struct map *map)
if (map->dso->has_build_id) {
char sbuild_id[SBUILD_ID_SIZE];
- build_id__sprintf(map->dso->build_id,
- sizeof(map->dso->build_id),
- sbuild_id);
+ build_id__sprintf(&map->dso->bid, sbuild_id);
pr_debug("%s with build id %s not found", name, sbuild_id);
} else
pr_debug("Failed to open %s", name);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index c2f5d28fe73a..b1c0686db1b7 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -171,4 +171,18 @@ static inline bool is_bpf_image(const char *name)
return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 ||
strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0;
}
+
+static inline int is_anon_memory(const char *filename)
+{
+ return !strcmp(filename, "//anon") ||
+ !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
+ !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
+}
+
+static inline int is_no_dso_memory(const char *filename)
+{
+ return !strncmp(filename, "[stack", 6) ||
+ !strncmp(filename, "/SYSV", 5) ||
+ !strcmp(filename, "[heap]");
+}
#endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h
index 5b8ca93798e9..7d22ade082c8 100644
--- a/tools/perf/util/map_symbol.h
+++ b/tools/perf/util/map_symbol.h
@@ -19,5 +19,6 @@ struct addr_map_symbol {
u64 addr;
u64 al_addr;
u64 phys_addr;
+ u64 data_page_size;
};
#endif // __PERF_MAP_SYMBOL
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index ea0af0bc4314..19007e463b8a 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -17,9 +17,10 @@ unsigned int perf_mem_events__loads_ldlat = 30;
#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
-struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
- E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "mem-loads"),
- E("ldlat-stores", "cpu/mem-stores/P", "mem-stores"),
+static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+ E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "cpu/events/mem-loads"),
+ E("ldlat-stores", "cpu/mem-stores/P", "cpu/events/mem-stores"),
+ E(NULL, NULL, NULL),
};
#undef E
@@ -28,19 +29,31 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
static char mem_loads_name[100];
static bool mem_loads_name__init;
+struct perf_mem_event * __weak perf_mem_events__ptr(int i)
+{
+ if (i >= PERF_MEM_EVENTS__MAX)
+ return NULL;
+
+ return &perf_mem_events[i];
+}
+
char * __weak perf_mem_events__name(int i)
{
+ struct perf_mem_event *e = perf_mem_events__ptr(i);
+
+ if (!e)
+ return NULL;
+
if (i == PERF_MEM_EVENTS__LOAD) {
if (!mem_loads_name__init) {
mem_loads_name__init = true;
scnprintf(mem_loads_name, sizeof(mem_loads_name),
- perf_mem_events[i].name,
- perf_mem_events__loads_ldlat);
+ e->name, perf_mem_events__loads_ldlat);
}
return mem_loads_name;
}
- return (char *)perf_mem_events[i].name;
+ return (char *)e->name;
}
int perf_mem_events__parse(const char *str)
@@ -61,7 +74,10 @@ int perf_mem_events__parse(const char *str)
while (tok) {
for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
- struct perf_mem_event *e = &perf_mem_events[j];
+ struct perf_mem_event *e = perf_mem_events__ptr(j);
+
+ if (!e->tag)
+ continue;
if (strstr(e->tag, tok))
e->record = found = true;
@@ -90,10 +106,17 @@ int perf_mem_events__init(void)
for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
char path[PATH_MAX];
- struct perf_mem_event *e = &perf_mem_events[j];
+ struct perf_mem_event *e = perf_mem_events__ptr(j);
struct stat st;
- scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+ /*
+ * If the event entry isn't valid, skip initialization
+ * and "e->supported" will keep false.
+ */
+ if (!e->tag)
+ continue;
+
+ scnprintf(path, PATH_MAX, "%s/devices/%s",
mnt, e->sysfs_name);
if (!stat(path, &st))
@@ -108,10 +131,10 @@ void perf_mem_events__list(void)
int j;
for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
- struct perf_mem_event *e = &perf_mem_events[j];
+ struct perf_mem_event *e = perf_mem_events__ptr(j);
fprintf(stderr, "%-13s%-*s%s\n",
- e->tag,
+ e->tag ?: "",
verbose > 0 ? 25 : 0,
verbose > 0 ? perf_mem_events__name(j) : "",
e->supported ? ": available" : "");
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 904dad34f7f7..5ef178278909 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -28,16 +28,17 @@ struct mem_info {
enum {
PERF_MEM_EVENTS__LOAD,
PERF_MEM_EVENTS__STORE,
+ PERF_MEM_EVENTS__LOAD_STORE,
PERF_MEM_EVENTS__MAX,
};
-extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
extern unsigned int perf_mem_events__loads_ldlat;
int perf_mem_events__parse(const char *str);
int perf_mem_events__init(void);
char *perf_mem_events__name(int i);
+struct perf_mem_event *perf_mem_events__ptr(int i);
void perf_mem_events__list(void);
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
index c84f5841c7ab..03a7d7b27737 100644
--- a/tools/perf/util/mem2node.c
+++ b/tools/perf/util/mem2node.c
@@ -96,7 +96,8 @@ int mem2node__init(struct mem2node *map, struct perf_env *env)
/* Cut unused entries, due to merging. */
tmp_entries = realloc(entries, sizeof(*entries) * j);
- if (tmp_entries || WARN_ON_ONCE(j == 0))
+ if (tmp_entries ||
+ WARN_ONCE(j == 0, "No memory nodes, is CONFIG_MEMORY_HOTPLUG enabled?\n"))
entries = tmp_entries;
for (i = 0; i < j; i++) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index ab5030fcfed4..e6d3452031e5 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -15,7 +15,6 @@
#include "rblist.h"
#include <string.h>
#include <errno.h>
-#include "pmu-events/pmu-events.h"
#include "strlist.h"
#include <assert.h>
#include <linux/ctype.h>
@@ -25,6 +24,7 @@
#include <api/fs/fs.h>
#include "util.h"
#include <asm/bug.h>
+#include "cgroup.h"
struct metric_event *metricgroup__lookup(struct rblist *metric_events,
struct evsel *evsel,
@@ -150,8 +150,28 @@ static void expr_ids__exit(struct expr_ids *ids)
free(ids->id[i].id);
}
+static bool contains_event(struct evsel **metric_events, int num_events,
+ const char *event_name)
+{
+ int i;
+
+ for (i = 0; i < num_events; i++) {
+ if (!strcmp(metric_events[i]->name, event_name))
+ return true;
+ }
+ return false;
+}
+
+static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2)
+{
+ if (!ev1->pmu_name || !ev2->pmu_name)
+ return false;
+
+ return !strcmp(ev1->pmu_name, ev2->pmu_name);
+}
+
/**
- * Find a group of events in perf_evlist that correpond to those from a parsed
+ * Find a group of events in perf_evlist that correspond to those from a parsed
* metric expression. Note, as find_evsel_group is called in the same order as
* perf_evlist was constructed, metric_no_merge doesn't need to test for
* underfilling a group.
@@ -180,7 +200,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
int i = 0, matched_events = 0, events_to_match;
const int idnum = (int)hashmap__size(&pctx->ids);
- /* duration_time is grouped separately. */
+ /*
+ * duration_time is always grouped separately, when events are grouped
+ * (ie has_constraint is false) then ignore it in the matching loop and
+ * add it to metric_events at the end.
+ */
if (!has_constraint &&
hashmap__find(&pctx->ids, "duration_time", (void **)&val_ptr))
events_to_match = idnum - 1;
@@ -207,23 +231,20 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
sizeof(struct evsel *) * idnum);
current_leader = ev->leader;
}
- if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) {
- if (has_constraint) {
- /*
- * Events aren't grouped, ensure the same event
- * isn't matched from two groups.
- */
- for (i = 0; i < matched_events; i++) {
- if (!strcmp(ev->name,
- metric_events[i]->name)) {
- break;
- }
- }
- if (i != matched_events)
- continue;
- }
+ /*
+ * Check for duplicate events with the same name. For example,
+ * uncore_imc/cas_count_read/ will turn into 6 events per socket
+ * on skylakex. Only the first such event is placed in
+ * metric_events. If events aren't grouped then this also
+ * ensures that the same event in different sibling groups
+ * aren't both added to metric_events.
+ */
+ if (contains_event(metric_events, matched_events, ev->name))
+ continue;
+ /* Does this event belong to the parse context? */
+ if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr))
metric_events[matched_events++] = ev;
- }
+
if (matched_events == events_to_match)
break;
}
@@ -239,7 +260,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
}
if (matched_events != idnum) {
- /* Not whole match */
+ /* Not a whole match */
return NULL;
}
@@ -247,8 +268,33 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
for (i = 0; i < idnum; i++) {
ev = metric_events[i];
- ev->metric_leader = ev;
+ /* Don't free the used events. */
set_bit(ev->idx, evlist_used);
+ /*
+ * The metric leader points to the identically named event in
+ * metric_events.
+ */
+ ev->metric_leader = ev;
+ /*
+ * Mark two events with identical names in the same group (or
+ * globally) as being in use as uncore events may be duplicated
+ * for each pmu. Set the metric leader of such events to be the
+ * event that appears in metric_events.
+ */
+ evlist__for_each_entry_continue(perf_evlist, ev) {
+ /*
+ * If events are grouped then the search can terminate
+ * when then group is left.
+ */
+ if (!has_constraint &&
+ ev->leader != metric_events[i]->leader &&
+ evsel_same_pmu(ev->leader, metric_events[i]->leader))
+ break;
+ if (!strcmp(metric_events[i]->name, ev->name)) {
+ set_bit(ev->idx, evlist_used);
+ ev->metric_leader = metric_events[i];
+ }
+ }
}
return metric_events[0];
@@ -376,6 +422,12 @@ static bool match_metric(const char *n, const char *list)
return false;
}
+static bool match_pe_metric(struct pmu_event *pe, const char *metric)
+{
+ return match_metric(pe->metric_group, metric) ||
+ match_metric(pe->metric_name, metric);
+}
+
struct mep {
struct rb_node nd;
const char *name;
@@ -454,6 +506,115 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
putchar('\n');
}
+static int metricgroup__print_pmu_event(struct pmu_event *pe,
+ bool metricgroups, char *filter,
+ bool raw, bool details,
+ struct rblist *groups,
+ struct strlist *metriclist)
+{
+ const char *g;
+ char *omg, *mg;
+
+ g = pe->metric_group;
+ if (!g && pe->metric_name) {
+ if (pe->name)
+ return 0;
+ g = "No_group";
+ }
+
+ if (!g)
+ return 0;
+
+ mg = strdup(g);
+
+ if (!mg)
+ return -ENOMEM;
+ omg = mg;
+ while ((g = strsep(&mg, ";")) != NULL) {
+ struct mep *me;
+ char *s;
+
+ g = skip_spaces(g);
+ if (*g == 0)
+ g = "No_group";
+ if (filter && !strstr(g, filter))
+ continue;
+ if (raw)
+ s = (char *)pe->metric_name;
+ else {
+ if (asprintf(&s, "%s\n%*s%s]",
+ pe->metric_name, 8, "[", pe->desc) < 0)
+ return -1;
+ if (details) {
+ if (asprintf(&s, "%s\n%*s%s]",
+ s, 8, "[", pe->metric_expr) < 0)
+ return -1;
+ }
+ }
+
+ if (!s)
+ continue;
+
+ if (!metricgroups) {
+ strlist__add(metriclist, s);
+ } else {
+ me = mep_lookup(groups, g);
+ if (!me)
+ continue;
+ strlist__add(me->metrics, s);
+ }
+
+ if (!raw)
+ free(s);
+ }
+ free(omg);
+
+ return 0;
+}
+
+struct metricgroup_print_sys_idata {
+ struct strlist *metriclist;
+ char *filter;
+ struct rblist *groups;
+ bool metricgroups;
+ bool raw;
+ bool details;
+};
+
+typedef int (*metricgroup_sys_event_iter_fn)(struct pmu_event *pe, void *);
+
+struct metricgroup_iter_data {
+ metricgroup_sys_event_iter_fn fn;
+ void *data;
+};
+
+static int metricgroup__sys_event_iter(struct pmu_event *pe, void *data)
+{
+ struct metricgroup_iter_data *d = data;
+ struct perf_pmu *pmu = NULL;
+
+ if (!pe->metric_expr || !pe->compat)
+ return 0;
+
+ while ((pmu = perf_pmu__scan(pmu))) {
+
+ if (!pmu->id || strcmp(pmu->id, pe->compat))
+ continue;
+
+ return d->fn(pe, d->data);
+ }
+
+ return 0;
+}
+
+static int metricgroup__print_sys_event_iter(struct pmu_event *pe, void *data)
+{
+ struct metricgroup_print_sys_idata *d = data;
+
+ return metricgroup__print_pmu_event(pe, d->metricgroups, d->filter, d->raw,
+ d->details, d->groups, d->metriclist);
+}
+
void metricgroup__print(bool metrics, bool metricgroups, char *filter,
bool raw, bool details)
{
@@ -464,9 +625,6 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
struct rb_node *node, *next;
struct strlist *metriclist = NULL;
- if (!map)
- return;
-
if (!metricgroups) {
metriclist = strlist__new(NULL, NULL);
if (!metriclist)
@@ -477,73 +635,41 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
groups.node_new = mep_new;
groups.node_cmp = mep_cmp;
groups.node_delete = mep_delete;
- for (i = 0; ; i++) {
- const char *g;
+ for (i = 0; map; i++) {
pe = &map->table[i];
if (!pe->name && !pe->metric_group && !pe->metric_name)
break;
if (!pe->metric_expr)
continue;
- g = pe->metric_group;
- if (!g && pe->metric_name) {
- if (pe->name)
- continue;
- g = "No_group";
- }
- if (g) {
- char *omg;
- char *mg = strdup(g);
-
- if (!mg)
- return;
- omg = mg;
- while ((g = strsep(&mg, ";")) != NULL) {
- struct mep *me;
- char *s;
-
- g = skip_spaces(g);
- if (*g == 0)
- g = "No_group";
- if (filter && !strstr(g, filter))
- continue;
- if (raw)
- s = (char *)pe->metric_name;
- else {
- if (asprintf(&s, "%s\n%*s%s]",
- pe->metric_name, 8, "[", pe->desc) < 0)
- return;
-
- if (details) {
- if (asprintf(&s, "%s\n%*s%s]",
- s, 8, "[", pe->metric_expr) < 0)
- return;
- }
- }
-
- if (!s)
- continue;
+ if (metricgroup__print_pmu_event(pe, metricgroups, filter,
+ raw, details, &groups,
+ metriclist) < 0)
+ return;
+ }
- if (!metricgroups) {
- strlist__add(metriclist, s);
- } else {
- me = mep_lookup(&groups, g);
- if (!me)
- continue;
- strlist__add(me->metrics, s);
- }
+ {
+ struct metricgroup_iter_data data = {
+ .fn = metricgroup__print_sys_event_iter,
+ .data = (void *) &(struct metricgroup_print_sys_idata){
+ .metriclist = metriclist,
+ .metricgroups = metricgroups,
+ .filter = filter,
+ .raw = raw,
+ .details = details,
+ .groups = &groups,
+ },
+ };
- if (!raw)
- free(s);
- }
- free(omg);
- }
+ pmu_for_each_sys_event(metricgroup__sys_event_iter, &data);
}
- if (metricgroups && !raw)
- printf("\nMetric Groups:\n\n");
- else if (metrics && !raw)
- printf("\nMetrics:\n\n");
+ if (!filter || !rblist__empty(&groups)) {
+ if (metricgroups && !raw)
+ printf("\nMetric Groups:\n\n");
+ else if (metrics && !raw)
+ printf("\nMetrics:\n\n");
+ }
for (node = rb_first_cached(&groups.entries); node; node = next) {
struct mep *me = container_of(node, struct mep, nd);
@@ -639,11 +765,20 @@ static bool metricgroup__has_constraint(struct pmu_event *pe)
return false;
}
-int __weak arch_get_runtimeparam(void)
+int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused)
{
return 1;
}
+struct metricgroup_add_iter_data {
+ struct list_head *metric_list;
+ const char *metric;
+ struct expr_ids *ids;
+ int *ret;
+ bool *has_match;
+ bool metric_no_group;
+};
+
static int __add_metric(struct list_head *metric_list,
struct pmu_event *pe,
bool metric_no_group,
@@ -753,10 +888,11 @@ static int __add_metric(struct list_head *metric_list,
return 0;
}
-#define map_for_each_event(__pe, __idx, __map) \
- for (__idx = 0, __pe = &__map->table[__idx]; \
- __pe->name || __pe->metric_group || __pe->metric_name; \
- __pe = &__map->table[++__idx])
+#define map_for_each_event(__pe, __idx, __map) \
+ if (__map) \
+ for (__idx = 0, __pe = &__map->table[__idx]; \
+ __pe->name || __pe->metric_group || __pe->metric_name; \
+ __pe = &__map->table[++__idx])
#define map_for_each_metric(__pe, __idx, __map, __metric) \
map_for_each_event(__pe, __idx, __map) \
@@ -794,7 +930,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa
if (ret)
return ret;
- p = data->parent;
+ p = expr_id_data__parent(data);
while (p->parent) {
if (!strcmp(p->id, id)) {
@@ -815,7 +951,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa
}
p->id = strdup(id);
- p->parent = data->parent;
+ p->parent = expr_id_data__parent(data);
*parent = p;
return p->id ? 0 : -ENOMEM;
@@ -910,7 +1046,7 @@ static int add_metric(struct list_head *metric_list,
} else {
int j, count;
- count = arch_get_runtimeparam();
+ count = arch_get_runtimeparam(pe);
/* This loop is added to create multiple
* events depend on count value and add
@@ -924,6 +1060,30 @@ static int add_metric(struct list_head *metric_list,
return ret;
}
+static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe,
+ void *data)
+{
+ struct metricgroup_add_iter_data *d = data;
+ struct metric *m = NULL;
+ int ret;
+
+ if (!match_pe_metric(pe, d->metric))
+ return 0;
+
+ ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids);
+ if (ret)
+ return ret;
+
+ ret = resolve_metric(d->metric_no_group,
+ d->metric_list, NULL, d->ids);
+ if (ret)
+ return ret;
+
+ *(d->has_match) = true;
+
+ return *d->ret;
+}
+
static int metricgroup__add_metric(const char *metric, bool metric_no_group,
struct strbuf *events,
struct list_head *metric_list,
@@ -954,6 +1114,21 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
goto out;
}
+ {
+ struct metricgroup_iter_data data = {
+ .fn = metricgroup__add_metric_sys_event_iter,
+ .data = (void *) &(struct metricgroup_add_iter_data) {
+ .metric_list = &list,
+ .metric = metric,
+ .metric_no_group = metric_no_group,
+ .ids = &ids,
+ .has_match = &has_match,
+ .ret = &ret,
+ },
+ };
+
+ pmu_for_each_sys_event(metricgroup__sys_event_iter, &data);
+ }
/* End of pmu events. */
if (!has_match) {
ret = -EINVAL;
@@ -1080,8 +1255,6 @@ int metricgroup__parse_groups(const struct option *opt,
struct evlist *perf_evlist = *(struct evlist **)opt->value;
struct pmu_events_map *map = perf_pmu__find_map(NULL);
- if (!map)
- return 0;
return parse_groups(perf_evlist, str, metric_no_group,
metric_no_merge, NULL, metric_events, map);
@@ -1119,3 +1292,87 @@ bool metricgroup__has_metric(const char *metric)
}
return false;
}
+
+int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp,
+ struct rblist *new_metric_events,
+ struct rblist *old_metric_events)
+{
+ unsigned i;
+
+ for (i = 0; i < rblist__nr_entries(old_metric_events); i++) {
+ struct rb_node *nd;
+ struct metric_event *old_me, *new_me;
+ struct metric_expr *old_expr, *new_expr;
+ struct evsel *evsel;
+ size_t alloc_size;
+ int idx, nr;
+
+ nd = rblist__entry(old_metric_events, i);
+ old_me = container_of(nd, struct metric_event, nd);
+
+ evsel = evlist__find_evsel(evlist, old_me->evsel->idx);
+ if (!evsel)
+ return -EINVAL;
+ new_me = metricgroup__lookup(new_metric_events, evsel, true);
+ if (!new_me)
+ return -ENOMEM;
+
+ pr_debug("copying metric event for cgroup '%s': %s (idx=%d)\n",
+ cgrp ? cgrp->name : "root", evsel->name, evsel->idx);
+
+ list_for_each_entry(old_expr, &old_me->head, nd) {
+ new_expr = malloc(sizeof(*new_expr));
+ if (!new_expr)
+ return -ENOMEM;
+
+ new_expr->metric_expr = old_expr->metric_expr;
+ new_expr->metric_name = old_expr->metric_name;
+ new_expr->metric_unit = old_expr->metric_unit;
+ new_expr->runtime = old_expr->runtime;
+
+ if (old_expr->metric_refs) {
+ /* calculate number of metric_events */
+ for (nr = 0; old_expr->metric_refs[nr].metric_name; nr++)
+ continue;
+ alloc_size = sizeof(*new_expr->metric_refs);
+ new_expr->metric_refs = calloc(nr + 1, alloc_size);
+ if (!new_expr->metric_refs) {
+ free(new_expr);
+ return -ENOMEM;
+ }
+
+ memcpy(new_expr->metric_refs, old_expr->metric_refs,
+ nr * alloc_size);
+ } else {
+ new_expr->metric_refs = NULL;
+ }
+
+ /* calculate number of metric_events */
+ for (nr = 0; old_expr->metric_events[nr]; nr++)
+ continue;
+ alloc_size = sizeof(*new_expr->metric_events);
+ new_expr->metric_events = calloc(nr + 1, alloc_size);
+ if (!new_expr->metric_events) {
+ free(new_expr->metric_refs);
+ free(new_expr);
+ return -ENOMEM;
+ }
+
+ /* copy evsel in the same position */
+ for (idx = 0; idx < nr; idx++) {
+ evsel = old_expr->metric_events[idx];
+ evsel = evlist__find_evsel(evlist, evsel->idx);
+ if (evsel == NULL) {
+ free(new_expr->metric_events);
+ free(new_expr->metric_refs);
+ free(new_expr);
+ return -EINVAL;
+ }
+ new_expr->metric_events[idx] = evsel;
+ }
+
+ list_add(&new_expr->nd, &new_me->head);
+ }
+ }
+ return 0;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 62623a39cbec..ed1b9392e624 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -5,12 +5,15 @@
#include <linux/list.h>
#include <linux/rbtree.h>
#include <stdbool.h>
+#include "pmu-events/pmu-events.h"
+struct evlist;
struct evsel;
struct evlist;
struct option;
struct rblist;
struct pmu_events_map;
+struct cgroup;
struct metric_event {
struct rb_node nd;
@@ -52,6 +55,10 @@ int metricgroup__parse_groups_test(struct evlist *evlist,
void metricgroup__print(bool metrics, bool groups, char *filter,
bool raw, bool details);
bool metricgroup__has_metric(const char *metric);
-int arch_get_runtimeparam(void);
+int arch_get_runtimeparam(struct pmu_event *pe __maybe_unused);
void metricgroup__rblist_exit(struct rblist *metric_events);
+
+int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp,
+ struct rblist *new_metric_events,
+ struct rblist *old_metric_events);
#endif
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 667cbca1547a..42c84adeb2fb 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -353,18 +353,20 @@ __add_event(struct list_head *list, int *idx,
const char *cpu_list)
{
struct evsel *evsel;
- struct perf_cpu_map *cpus = pmu ? pmu->cpus :
+ struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
if (init_attr)
event_attr_init(attr);
evsel = evsel__new_idx(attr, *idx);
- if (!evsel)
+ if (!evsel) {
+ perf_cpu_map__put(cpus);
return NULL;
+ }
(*idx)++;
- evsel->core.cpus = perf_cpu_map__get(cpus);
+ evsel->core.cpus = cpus;
evsel->core.own_cpus = perf_cpu_map__get(cpus);
evsel->core.system_wide = pmu ? pmu->is_uncore : false;
evsel->auto_merge_stats = auto_merge_stats;
@@ -666,6 +668,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
return ret;
}
+#ifdef HAVE_LIBBPF_SUPPORT
struct __add_bpf_event_param {
struct parse_events_state *parse_state;
struct list_head *list;
@@ -898,6 +901,30 @@ int parse_events_load_bpf(struct parse_events_state *parse_state,
list_splice_tail(&obj_head_config, head_config);
return err;
}
+#else // HAVE_LIBBPF_SUPPORT
+int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
+ struct list_head *list __maybe_unused,
+ struct bpf_object *obj __maybe_unused,
+ struct list_head *head_config __maybe_unused)
+{
+ parse_events__handle_error(parse_state->error, 0,
+ strdup("BPF support is not compiled"),
+ strdup("Make sure libbpf-devel is available at build time."));
+ return -ENOTSUP;
+}
+
+int parse_events_load_bpf(struct parse_events_state *parse_state,
+ struct list_head *list __maybe_unused,
+ char *bpf_file_name __maybe_unused,
+ bool source __maybe_unused,
+ struct list_head *head_config __maybe_unused)
+{
+ parse_events__handle_error(parse_state->error, 0,
+ strdup("BPF support is not compiled"),
+ strdup("Make sure libbpf-devel is available at build time."));
+ return -ENOTSUP;
+}
+#endif // HAVE_LIBBPF_SUPPORT
static int
parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
@@ -940,12 +967,12 @@ do { \
}
int parse_events_add_breakpoint(struct list_head *list, int *idx,
- void *ptr, char *type, u64 len)
+ u64 addr, char *type, u64 len)
{
struct perf_event_attr attr;
memset(&attr, 0, sizeof(attr));
- attr.bp_addr = (unsigned long) ptr;
+ attr.bp_addr = addr;
if (parse_breakpoint_type(type, &attr))
return -EINVAL;
@@ -1742,7 +1769,7 @@ void parse_events__set_leader(char *name, struct list_head *list,
if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
return;
- __perf_evlist__set_leader(list);
+ __evlist__set_leader(list);
leader = list_entry(list->next, struct evsel, core.node);
leader->group_name = name ? strdup(name) : NULL;
}
@@ -1773,6 +1800,7 @@ struct event_modifier {
int sample_read;
int pinned;
int weak;
+ int exclusive;
};
static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -1788,6 +1816,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
int precise_max = 0;
int sample_read = 0;
int pinned = evsel ? evsel->core.attr.pinned : 0;
+ int exclusive = evsel ? evsel->core.attr.exclusive : 0;
int exclude = eu | ek | eh;
int exclude_GH = evsel ? evsel->exclude_GH : 0;
@@ -1831,6 +1860,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
sample_read = 1;
} else if (*str == 'D') {
pinned = 1;
+ } else if (*str == 'e') {
+ exclusive = 1;
} else if (*str == 'W') {
weak = 1;
} else
@@ -1864,6 +1895,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
mod->sample_read = sample_read;
mod->pinned = pinned;
mod->weak = weak;
+ mod->exclusive = exclusive;
return 0;
}
@@ -1877,7 +1909,7 @@ static int check_modifier(char *str)
char *p = str;
/* The sizeof includes 0 byte as well. */
- if (strlen(str) > (sizeof("ukhGHpppPSDIW") - 1))
+ if (strlen(str) > (sizeof("ukhGHpppPSDIWe") - 1))
return -1;
while (*p) {
@@ -1919,8 +1951,10 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
evsel->precise_max = mod.precise_max;
evsel->weak_group = mod.weak;
- if (evsel__is_group_leader(evsel))
+ if (evsel__is_group_leader(evsel)) {
evsel->core.attr.pinned = mod.pinned;
+ evsel->core.attr.exclusive = mod.exclusive;
+ }
}
return 0;
@@ -2149,7 +2183,7 @@ int __parse_events(struct evlist *evlist, const char *str,
/*
* Add list to the evlist even with errors to allow callers to clean up.
*/
- perf_evlist__splice_list_tail(evlist, &parse_state.list);
+ evlist__splice_list_tail(evlist, &parse_state.list);
if (!ret) {
struct evsel *last;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 00cde7d2e30c..e80c9b74f2f2 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -190,7 +190,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
struct parse_events_error *error,
struct list_head *head_config);
int parse_events_add_breakpoint(struct list_head *list, int *idx,
- void *ptr, char *type, u64 len);
+ u64 addr, char *type, u64 len);
int parse_events_add_pmu(struct parse_events_state *parse_state,
struct list_head *list, char *name,
struct list_head *head_config,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 3ca5fd2829ca..9db5097317f4 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -210,7 +210,7 @@ name_tag [\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\']
name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
/* If you add a modifier you need to update check_modifier() */
-modifier_event [ukhpPGHSDIW]+
+modifier_event [ukhpPGHSDIWe]+
modifier_bp [rwx]{1,3}
%%
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 645bf4f1859f..d5b6aff82f21 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -511,7 +511,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc
list = alloc_list();
ABORT_ON(!list);
err = parse_events_add_breakpoint(list, &parse_state->idx,
- (void *)(uintptr_t) $2, $6, $4);
+ $2, $6, $4);
free($6);
if (err) {
free(list);
@@ -528,7 +528,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc
list = alloc_list();
ABORT_ON(!list);
if (parse_events_add_breakpoint(list, &parse_state->idx,
- (void *)(uintptr_t) $2, NULL, $4)) {
+ $2, NULL, $4)) {
free(list);
YYABORT;
}
@@ -544,7 +544,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
list = alloc_list();
ABORT_ON(!list);
err = parse_events_add_breakpoint(list, &parse_state->idx,
- (void *)(uintptr_t) $2, $4, 0);
+ $2, $4, 0);
free($4);
if (err) {
free(list);
@@ -561,7 +561,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
list = alloc_list();
ABORT_ON(!list);
if (parse_events_add_breakpoint(list, &parse_state->idx,
- (void *)(uintptr_t) $2, NULL, 0)) {
+ $2, NULL, 0)) {
free(list);
YYABORT;
}
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index e687497b3aac..a4a100425b3a 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -54,7 +54,7 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr)
#endif
fputc('\n', stderr);
/* just printing available regs */
- return -1;
+ goto error;
}
#ifdef HAVE_PERF_REGS_SUPPORT
for (r = sample_reg_masks; r->name; r++) {
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index e67a227c0ce7..fb0bb6684438 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -35,7 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX),
- bit_name(CGROUP),
+ bit_name(CGROUP), bit_name(DATA_PAGE_SIZE),
{ .name = NULL, }
};
#undef bit_name
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d41caeb35cf6..44ef28302fc7 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -597,6 +597,7 @@ static struct perf_cpu_map *__pmu_cpumask(const char *path)
* Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
* may have a "cpus" file.
*/
+#define SYS_TEMPLATE_ID "./bus/event_source/devices/%s/identifier"
#define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask"
#define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus"
@@ -635,6 +636,21 @@ static bool pmu_is_uncore(const char *name)
return file_available(path);
}
+static char *pmu_id(const char *name)
+{
+ char path[PATH_MAX], *str;
+ size_t len;
+
+ snprintf(path, PATH_MAX, SYS_TEMPLATE_ID, name);
+
+ if (sysfs__read_str(path, &str, &len) < 0)
+ return NULL;
+
+ str[len - 1] = 0; /* remove line feed */
+
+ return str;
+}
+
/*
* PMU CORE devices have different name other than cpu in sysfs on some
* platforms.
@@ -796,6 +812,83 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
pmu_add_cpu_aliases_map(head, pmu, map);
}
+void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data)
+{
+ int i = 0;
+
+ while (1) {
+ struct pmu_sys_events *event_table;
+ int j = 0;
+
+ event_table = &pmu_sys_event_tables[i++];
+
+ if (!event_table->table)
+ break;
+
+ while (1) {
+ struct pmu_event *pe = &event_table->table[j++];
+ int ret;
+
+ if (!pe->name && !pe->metric_group && !pe->metric_name)
+ break;
+
+ ret = fn(pe, data);
+ if (ret)
+ break;
+ }
+ }
+}
+
+struct pmu_sys_event_iter_data {
+ struct list_head *head;
+ struct perf_pmu *pmu;
+};
+
+static int pmu_add_sys_aliases_iter_fn(struct pmu_event *pe, void *data)
+{
+ struct pmu_sys_event_iter_data *idata = data;
+ struct perf_pmu *pmu = idata->pmu;
+
+ if (!pe->name) {
+ if (pe->metric_group || pe->metric_name)
+ return 0;
+ return -EINVAL;
+ }
+
+ if (!pe->compat || !pe->pmu)
+ return 0;
+
+ if (!strcmp(pmu->id, pe->compat) &&
+ pmu_uncore_alias_match(pe->pmu, pmu->name)) {
+ __perf_pmu__new_alias(idata->head, NULL,
+ (char *)pe->name,
+ (char *)pe->desc,
+ (char *)pe->event,
+ (char *)pe->long_desc,
+ (char *)pe->topic,
+ (char *)pe->unit,
+ (char *)pe->perpkg,
+ (char *)pe->metric_expr,
+ (char *)pe->metric_name,
+ (char *)pe->deprecated);
+ }
+
+ return 0;
+}
+
+static void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu)
+{
+ struct pmu_sys_event_iter_data idata = {
+ .head = head,
+ .pmu = pmu,
+ };
+
+ if (!pmu->id)
+ return;
+
+ pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, &idata);
+}
+
struct perf_event_attr * __weak
perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
{
@@ -847,8 +940,11 @@ static struct perf_pmu *pmu_lookup(const char *name)
pmu->name = strdup(name);
pmu->type = type;
pmu->is_uncore = pmu_is_uncore(name);
+ if (pmu->is_uncore)
+ pmu->id = pmu_id(name);
pmu->max_precise = pmu_max_precise(name);
pmu_add_cpu_aliases(&aliases, pmu);
+ pmu_add_sys_aliases(&aliases, pmu);
INIT_LIST_HEAD(&pmu->format);
INIT_LIST_HEAD(&pmu->aliases);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index a64e9c9ce731..8164388478c6 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -30,6 +30,7 @@ struct perf_pmu_caps {
struct perf_pmu {
char *name;
+ char *id;
__u32 type;
bool selectable;
bool is_uncore;
@@ -116,6 +117,8 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
bool pmu_uncore_alias_match(const char *pmu_name, const char *name);
void perf_pmu_free_alias(struct perf_pmu_alias *alias);
+typedef int (*pmu_sys_event_iter_fn)(struct pmu_event *pe, void *data);
+void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data);
int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
int perf_pmu__caps_parse(struct perf_pmu *pmu);
diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c
index 599a1543871d..13fdc51c61d9 100644
--- a/tools/perf/util/print_binary.c
+++ b/tools/perf/util/print_binary.c
@@ -50,7 +50,7 @@ int is_printable_array(char *p, unsigned int len)
len--;
- for (i = 0; i < len; i++) {
+ for (i = 0; i < len && p[i]; i++) {
if (!isprint(p[i]) && !isspace(p[i]))
return 0;
}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 99d36ac77c08..8eae2afff71a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -43,6 +43,10 @@
#include <linux/ctype.h>
#include <linux/zalloc.h>
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+#include <elfutils/debuginfod.h>
+#endif
+
#define PERFPROBE_GROUP "probe"
bool probe_event_dry_run; /* Dry run flag */
@@ -129,9 +133,10 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
struct map *map;
/* ref_reloc_sym is just a label. Need a special fix*/
- reloc_sym = kernel_get_ref_reloc_sym(NULL);
+ reloc_sym = kernel_get_ref_reloc_sym(&map);
if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
- *addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
+ *addr = (!map->reloc || reloc) ? reloc_sym->addr :
+ reloc_sym->unrelocated_addr;
else {
sym = machine__find_kernel_symbol_by_name(host_machine, name, &map);
if (!sym)
@@ -337,6 +342,8 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
map = machine__kernel_map(host_machine);
dso = map->dso;
+ if (!dso->has_build_id)
+ dso__read_running_kernel_build_id(dso, host_machine);
vmlinux_name = symbol_conf.vmlinux_name;
dso->load_errno = 0;
@@ -452,6 +459,49 @@ static int get_alternative_line_range(struct debuginfo *dinfo,
return ret;
}
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+static struct debuginfo *open_from_debuginfod(struct dso *dso, struct nsinfo *nsi,
+ bool silent)
+{
+ debuginfod_client *c = debuginfod_begin();
+ char sbuild_id[SBUILD_ID_SIZE + 1];
+ struct debuginfo *ret = NULL;
+ struct nscookie nsc;
+ char *path;
+ int fd;
+
+ if (!c)
+ return NULL;
+
+ build_id__sprintf(&dso->bid, sbuild_id);
+ fd = debuginfod_find_debuginfo(c, (const unsigned char *)sbuild_id,
+ 0, &path);
+ if (fd >= 0)
+ close(fd);
+ debuginfod_end(c);
+ if (fd < 0) {
+ if (!silent)
+ pr_debug("Failed to find debuginfo in debuginfod.\n");
+ return NULL;
+ }
+ if (!silent)
+ pr_debug("Load debuginfo from debuginfod (%s)\n", path);
+
+ nsinfo__mountns_enter(nsi, &nsc);
+ ret = debuginfo__new((const char *)path);
+ nsinfo__mountns_exit(&nsc);
+ return ret;
+}
+#else
+static inline
+struct debuginfo *open_from_debuginfod(struct dso *dso __maybe_unused,
+ struct nsinfo *nsi __maybe_unused,
+ bool silent __maybe_unused)
+{
+ return NULL;
+}
+#endif
+
/* Open new debuginfo of given module */
static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi,
bool silent)
@@ -471,6 +521,10 @@ static struct debuginfo *open_debuginfo(const char *module, struct nsinfo *nsi,
strcpy(reason, "(unknown)");
} else
dso__strerror_load(dso, reason, STRERR_BUFSIZE);
+ if (dso)
+ ret = open_from_debuginfod(dso, nsi, silent);
+ if (ret)
+ return ret;
if (!silent) {
if (module)
pr_err("Module %s is not loaded, please specify its full path name.\n", module);
@@ -795,7 +849,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
free(tevs[i].point.symbol);
tevs[i].point.symbol = tmp;
tevs[i].point.offset = tevs[i].point.address -
- reloc_sym->unrelocated_addr;
+ (map->reloc ? reloc_sym->unrelocated_addr :
+ reloc_sym->addr);
}
return skipped;
}
@@ -950,6 +1005,7 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num)
static int __show_line_range(struct line_range *lr, const char *module,
bool user)
{
+ struct build_id bid;
int l = 1;
struct int_node *ln;
struct debuginfo *dinfo;
@@ -957,6 +1013,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
int ret;
char *tmp;
char sbuf[STRERR_BUFSIZE];
+ char sbuild_id[SBUILD_ID_SIZE] = "";
/* Search a line range */
dinfo = open_debuginfo(module, NULL, false);
@@ -969,6 +1026,10 @@ static int __show_line_range(struct line_range *lr, const char *module,
if (!ret)
ret = debuginfo__find_line_range(dinfo, lr);
}
+ if (dinfo->build_id) {
+ build_id__init(&bid, dinfo->build_id, BUILD_ID_SIZE);
+ build_id__sprintf(&bid, sbuild_id);
+ }
debuginfo__delete(dinfo);
if (ret == 0 || ret == -ENOENT) {
pr_warning("Specified source line is not found.\n");
@@ -980,7 +1041,7 @@ static int __show_line_range(struct line_range *lr, const char *module,
/* Convert source file path */
tmp = lr->path;
- ret = get_real_path(tmp, lr->comp_dir, &lr->path);
+ ret = find_source_path(tmp, sbuild_id, lr->comp_dir, &lr->path);
/* Free old path when new path is assigned */
if (tmp != lr->path)
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 064b63a6a3f3..bbecb449ea94 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -791,7 +791,7 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note,
const char *sdtgrp)
{
struct strbuf buf;
- char *ret = NULL, **args;
+ char *ret = NULL;
int i, args_count, err;
unsigned long long ref_ctr_offset;
@@ -813,12 +813,19 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note,
goto out;
if (note->args) {
- args = argv_split(note->args, &args_count);
+ char **args = argv_split(note->args, &args_count);
+
+ if (args == NULL)
+ goto error;
for (i = 0; i < args_count; ++i) {
- if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0)
+ if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) {
+ argv_free(args);
goto error;
+ }
}
+
+ argv_free(args);
}
out:
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 659024342e9a..76dd349aa48d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -31,6 +31,10 @@
#include "probe-file.h"
#include "string2.h"
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+#include <elfutils/debuginfod.h>
+#endif
+
/* Kprobe tracer basic type is up to u64 */
#define MAX_BASIC_TYPE_BITS 64
@@ -51,6 +55,7 @@ static const Dwfl_Callbacks offline_callbacks = {
static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
const char *path)
{
+ GElf_Addr dummy;
int fd;
fd = open(path, O_RDONLY);
@@ -70,6 +75,8 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
if (!dbg->dbg)
goto error;
+ dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
+
dwfl_report_end(dbg->dwfl, NULL, NULL);
return 0;
@@ -942,6 +949,8 @@ static int probe_point_lazy_walker(const char *fname, int lineno,
/* Find probe points from lazy pattern */
static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
{
+ struct build_id bid;
+ char sbuild_id[SBUILD_ID_SIZE] = "";
int ret = 0;
char *fpath;
@@ -949,7 +958,11 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
const char *comp_dir;
comp_dir = cu_get_comp_dir(&pf->cu_die);
- ret = get_real_path(pf->fname, comp_dir, &fpath);
+ if (pf->dbg->build_id) {
+ build_id__init(&bid, pf->dbg->build_id, BUILD_ID_SIZE);
+ build_id__sprintf(&bid, sbuild_id);
+ }
+ ret = find_source_path(pf->fname, sbuild_id, comp_dir, &fpath);
if (ret < 0) {
pr_warning("Failed to find source file path.\n");
return ret;
@@ -1448,7 +1461,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
struct probe_trace_event **tevs)
{
struct trace_event_finder tf = {
- .pf = {.pev = pev, .callback = add_probe_trace_event},
+ .pf = {.pev = pev, .dbg = dbg, .callback = add_probe_trace_event},
.max_tevs = probe_conf.max_probes, .mod = dbg->mod};
int ret, i;
@@ -1618,7 +1631,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
struct variable_list **vls)
{
struct available_var_finder af = {
- .pf = {.pev = pev, .callback = add_available_vars},
+ .pf = {.pev = pev, .dbg = dbg, .callback = add_available_vars},
.mod = dbg->mod,
.max_vls = probe_conf.max_probes};
int ret;
@@ -1872,8 +1885,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
return DWARF_CB_OK;
- if (die_is_func_def(sp_die) &&
- die_match_name(sp_die, lr->function)) {
+ if (die_match_name(sp_die, lr->function) && die_is_func_def(sp_die)) {
lf->fname = dwarf_decl_file(sp_die);
dwarf_decl_line(sp_die, &lr->offset);
pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
@@ -1973,17 +1985,57 @@ found:
return (ret < 0) ? ret : lf.found;
}
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+/* debuginfod doesn't require the comp_dir but buildid is required */
+static int get_source_from_debuginfod(const char *raw_path,
+ const char *sbuild_id, char **new_path)
+{
+ debuginfod_client *c = debuginfod_begin();
+ const char *p = raw_path;
+ int fd;
+
+ if (!c)
+ return -ENOMEM;
+
+ fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id,
+ 0, p, new_path);
+ pr_debug("Search %s from debuginfod -> %d\n", p, fd);
+ if (fd >= 0)
+ close(fd);
+ debuginfod_end(c);
+ if (fd < 0) {
+ pr_debug("Failed to find %s in debuginfod (%s)\n",
+ raw_path, sbuild_id);
+ return -ENOENT;
+ }
+ pr_debug("Got a source %s\n", *new_path);
+
+ return 0;
+}
+#else
+static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused,
+ const char *sbuild_id __maybe_unused,
+ char **new_path __maybe_unused)
+{
+ return -ENOTSUP;
+}
+#endif
/*
* Find a src file from a DWARF tag path. Prepend optional source path prefix
* and chop off leading directories that do not exist. Result is passed back as
* a newly allocated path on success.
* Return 0 if file was found and readable, -errno otherwise.
*/
-int get_real_path(const char *raw_path, const char *comp_dir,
- char **new_path)
+int find_source_path(const char *raw_path, const char *sbuild_id,
+ const char *comp_dir, char **new_path)
{
const char *prefix = symbol_conf.source_prefix;
+ if (sbuild_id && !prefix) {
+ if (!get_source_from_debuginfod(raw_path, sbuild_id, new_path))
+ return 0;
+ }
+
if (!prefix) {
if (raw_path[0] != '/' && comp_dir)
/* If not an absolute path, try to use comp_dir */
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 11be10080613..2febb5875678 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -4,6 +4,7 @@
#include <stdbool.h>
#include "intlist.h"
+#include "build-id.h"
#include "probe-event.h"
#include <linux/ctype.h>
@@ -32,6 +33,7 @@ struct debuginfo {
Dwfl_Module *mod;
Dwfl *dwfl;
Dwarf_Addr bias;
+ const unsigned char *build_id;
};
/* This also tries to open distro debuginfo */
@@ -59,11 +61,12 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
struct variable_list **vls);
/* Find a src file from a DWARF tag path */
-int get_real_path(const char *raw_path, const char *comp_dir,
- char **new_path);
+int find_source_path(const char *raw_path, const char *sbuild_id,
+ const char *comp_dir, char **new_path);
struct probe_finder {
struct perf_probe_event *pev; /* Target probe event */
+ struct debuginfo *dbg;
/* Callback when a probe point is found */
int (*callback)(Dwarf_Die *sc_die, struct probe_finder *pf);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 75a9b1d62bba..cc5ade85a33f 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -15,9 +15,11 @@
#include "thread_map.h"
#include "trace-event.h"
#include "mmap.h"
+#include "stat.h"
+#include "metricgroup.h"
#include "util/env.h"
#include <internal/lib.h>
-#include "../perf-sys.h"
+#include "util.h"
#if PY_MAJOR_VERSION < 3
#define _PyUnicode_FromString(arg) \
@@ -61,6 +63,23 @@ int parse_callchain_record(const char *arg __maybe_unused,
struct perf_env perf_env;
/*
+ * Add this one here not to drag util/stat-shadow.c
+ */
+void perf_stat__collect_metric_expr(struct evlist *evsel_list)
+{
+}
+
+/*
+ * Add this one here not to drag util/metricgroup.c
+ */
+int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp,
+ struct rblist *new_metric_events,
+ struct rblist *old_metric_events)
+{
+ return 0;
+}
+
+/*
* Support debug printing even though util/debug.c is not linked. That means
* implementing 'verbose' and 'eprintf'.
*/
@@ -1036,7 +1055,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
if (pyevent == NULL)
return PyErr_NoMemory();
- evsel = perf_evlist__event2evsel(evlist, event);
+ evsel = evlist__event2evsel(evlist, event);
if (!evsel) {
Py_INCREF(Py_None);
return Py_None;
@@ -1070,7 +1089,7 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
return NULL;
if (group)
- perf_evlist__set_leader(evlist);
+ evlist__set_leader(evlist);
if (evlist__open(evlist) < 0) {
PyErr_SetFromErrno(PyExc_OSError);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index ea9aa1d7cf50..e70c9dd04567 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -14,6 +14,7 @@
#include "util/perf_api_probe.h"
#include "record.h"
#include "../perf-sys.h"
+#include "topdown.h"
/*
* evsel__config_leader_sampling() uses special rules for leader sampling.
@@ -24,7 +25,7 @@ static struct evsel *evsel__read_sampler(struct evsel *evsel, struct evlist *evl
{
struct evsel *leader = evsel->leader;
- if (evsel__is_aux_event(leader)) {
+ if (evsel__is_aux_event(leader) || arch_topdown_sample_read(leader)) {
evlist__for_each_entry(evlist, evsel) {
if (evsel->leader == leader && evsel != evsel->leader)
return evsel;
@@ -88,8 +89,7 @@ static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *ev
leader->core.attr.sample_type;
}
-void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
- struct callchain_param *callchain)
+void evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain)
{
struct evsel *evsel;
bool use_sample_identifier = false;
@@ -101,7 +101,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
* since some might depend on this info.
*/
if (opts->group)
- perf_evlist__set_leader(evlist);
+ evlist__set_leader(evlist);
if (evlist->core.cpus->map[0] < 0)
opts->no_inherit = true;
@@ -143,7 +143,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
evsel__set_sample_id(evsel, use_sample_identifier);
}
- perf_evlist__set_id_pos(evlist);
+ evlist__set_id_pos(evlist);
}
static int get_max_rate(unsigned int *rate)
@@ -216,7 +216,7 @@ int record_opts__config(struct record_opts *opts)
return record_opts__config_freq(opts);
}
-bool perf_evlist__can_select_event(struct evlist *evlist, const char *str)
+bool evlist__can_select_event(struct evlist *evlist, const char *str)
{
struct evlist *temp_evlist;
struct evsel *evsel;
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index 03678ff25539..694b351dcd27 100644
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -22,6 +22,7 @@ struct record_opts {
bool raw_samples;
bool sample_address;
bool sample_phys_addr;
+ bool sample_data_page_size;
bool sample_weight;
bool sample_time;
bool sample_time_set;
@@ -73,6 +74,7 @@ struct record_opts {
unsigned int nr_threads_synthesize;
int ctl_fd;
int ctl_fd_ack;
+ bool ctl_fd_close;
};
extern const char * const *record_usage;
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index f8861998e5bd..078a71773565 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -96,9 +96,9 @@
* | than PERF_RECORD_USER_TYPE_START) are handled by
* | perf_session__process_user_event(see below)
* | - Those generated by the kernel are handled by
- * | perf_evlist__parse_sample_timestamp()
+ * | evlist__parse_sample_timestamp()
* |
- * perf_evlist__parse_sample_timestamp()
+ * evlist__parse_sample_timestamp()
* | Extract time stamp from sample data.
* |
* perf_session__queue_event()
@@ -932,7 +932,7 @@ s390_cpumsf_process_event(struct perf_session *session,
if (event->header.type == PERF_RECORD_SAMPLE &&
sample->raw_size) {
/* Handle event with raw data */
- ev_bc000 = perf_evlist__event2evsel(session->evlist, event);
+ ev_bc000 = evlist__event2evsel(session->evlist, event);
if (ev_bc000 &&
ev_bc000->core.attr.config == PERF_EVENT_CPUM_CF_DIAG)
err = s390_cpumcf_dumpctr(sf, sample);
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index 05b43ab4eeef..cfcf8d534d76 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -197,15 +197,14 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample)
* its raw data.
* The function is only invoked when the dump flag -D is set.
*/
-void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event,
- struct perf_sample *sample)
+void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
{
struct evsel *ev_bc000;
if (event->header.type != PERF_RECORD_SAMPLE)
return;
- ev_bc000 = perf_evlist__event2evsel(evlist, event);
+ ev_bc000 = evlist__event2evsel(evlist, event);
if (ev_bc000 == NULL ||
ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG)
return;
diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c
index e84bbe0e441a..cde5cd3ce49b 100644
--- a/tools/perf/util/sample-raw.c
+++ b/tools/perf/util/sample-raw.c
@@ -9,10 +9,10 @@
* Check platform the perf data file was created on and perform platform
* specific interpretation.
*/
-void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist)
+void evlist__init_trace_event_sample_raw(struct evlist *evlist)
{
const char *arch_pf = perf_env__arch(evlist->env);
if (arch_pf && !strcmp("s390", arch_pf))
- evlist->trace_event_sample_raw = perf_evlist__s390_sample_raw;
+ evlist->trace_event_sample_raw = evlist__s390_sample_raw;
}
diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h
index afe1491a117e..4be84a5510cf 100644
--- a/tools/perf/util/sample-raw.h
+++ b/tools/perf/util/sample-raw.h
@@ -6,9 +6,6 @@ struct evlist;
union perf_event;
struct perf_sample;
-void perf_evlist__s390_sample_raw(struct evlist *evlist,
- union perf_event *event,
- struct perf_sample *sample);
-
-void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist);
+void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample);
+void evlist__init_trace_event_sample_raw(struct evlist *evlist);
#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 739516fdf6e3..c83c2c6564e0 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1064,7 +1064,7 @@ static int python_export_dso(struct db_export *dbe, struct dso *dso,
char sbuild_id[SBUILD_ID_SIZE];
PyObject *t;
- build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+ build_id__sprintf(&dso->bid, sbuild_id);
t = tuple_new(5);
@@ -1592,7 +1592,6 @@ static void _free_command_line(wchar_t **command_line, int num)
static int python_start_script(const char *script, int argc, const char **argv)
{
struct tables *tables = &tables_global;
- PyMODINIT_FUNC (*initfunc)(void);
#if PY_MAJOR_VERSION < 3
const char **command_line;
#else
@@ -1607,20 +1606,18 @@ static int python_start_script(const char *script, int argc, const char **argv)
FILE *fp;
#if PY_MAJOR_VERSION < 3
- initfunc = initperf_trace_context;
command_line = malloc((argc + 1) * sizeof(const char *));
command_line[0] = script;
for (i = 1; i < argc + 1; i++)
command_line[i] = argv[i - 1];
+ PyImport_AppendInittab(name, initperf_trace_context);
#else
- initfunc = PyInit_perf_trace_context;
command_line = malloc((argc + 1) * sizeof(wchar_t *));
command_line[0] = Py_DecodeLocale(script, NULL);
for (i = 1; i < argc + 1; i++)
command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+ PyImport_AppendInittab(name, PyInit_perf_trace_context);
#endif
-
- PyImport_AppendInittab(name, initfunc);
Py_Initialize();
#if PY_MAJOR_VERSION < 3
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7a5f03764702..25adbcce0281 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -32,6 +32,7 @@
#include "ui/progress.h"
#include "../perf.h"
#include "arch/common.h"
+#include "units.h"
#include <internal/lib.h>
#ifdef HAVE_ZSTD_SUPPORT
@@ -125,7 +126,7 @@ static int perf_session__open(struct perf_session *session)
return -1;
}
- if (!perf_evlist__valid_read_format(session->evlist)) {
+ if (!evlist__valid_read_format(session->evlist)) {
pr_err("non matching read_format\n");
return -1;
}
@@ -135,7 +136,7 @@ static int perf_session__open(struct perf_session *session)
void perf_session__set_id_hdr_size(struct perf_session *session)
{
- u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);
+ u16 id_hdr_size = evlist__id_hdr_size(session->evlist);
machines__set_id_hdr_size(&session->machines, id_hdr_size);
}
@@ -221,7 +222,7 @@ struct perf_session *perf_session__new(struct perf_data *data,
perf_session__set_comm_exec(session);
}
- perf_evlist__init_trace_event_sample_raw(session->evlist);
+ evlist__init_trace_event_sample_raw(session->evlist);
/* Open the directory data. */
if (data->is_dir) {
@@ -595,6 +596,7 @@ static void perf_event__mmap2_swap(union perf_event *event,
event->mmap2.maj = bswap_32(event->mmap2.maj);
event->mmap2.min = bswap_32(event->mmap2.min);
event->mmap2.ino = bswap_64(event->mmap2.ino);
+ event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation);
if (sample_id_all) {
void *data = &event->mmap2.filename;
@@ -710,6 +712,18 @@ static void perf_event__namespaces_swap(union perf_event *event,
swap_sample_id_all(event, &event->namespaces.link_info[i]);
}
+static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all)
+{
+ event->cgroup.id = bswap_64(event->cgroup.id);
+
+ if (sample_id_all) {
+ void *data = &event->cgroup.path;
+
+ data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
+}
+
static u8 revbyte(u8 b)
{
int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -952,6 +966,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_SWITCH] = perf_event__switch_swap,
[PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap,
[PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap,
+ [PERF_RECORD_CGROUP] = perf_event__cgroup_swap,
[PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
@@ -1177,9 +1192,7 @@ static void stack_user__printf(struct stack_dump *dump)
dump->size, dump->offset);
}
-static void perf_evlist__print_tstamp(struct evlist *evlist,
- union perf_event *event,
- struct perf_sample *sample)
+static void evlist__print_tstamp(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
{
u64 sample_type = __evlist__combined_sample_type(evlist);
@@ -1240,16 +1253,25 @@ static void dump_event(struct evlist *evlist, union perf_event *event,
evlist->trace_event_sample_raw(evlist, event, sample);
if (sample)
- perf_evlist__print_tstamp(evlist, event, sample);
+ evlist__print_tstamp(evlist, event, sample);
printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
event->header.size, perf_event__name(event->header.type));
}
+char *get_page_size_name(u64 size, char *str)
+{
+ if (!size || !unit_number__scnprintf(str, PAGE_SIZE_NAME_LEN, size))
+ snprintf(str, PAGE_SIZE_NAME_LEN, "%s", "N/A");
+
+ return str;
+}
+
static void dump_sample(struct evsel *evsel, union perf_event *event,
struct perf_sample *sample)
{
u64 sample_type;
+ char str[PAGE_SIZE_NAME_LEN];
if (!dump_trace)
return;
@@ -1284,6 +1306,9 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
if (sample_type & PERF_SAMPLE_PHYS_ADDR)
printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr);
+ if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+ printf(" .. data page size: %s\n", get_page_size_name(sample->data_page_size, str));
+
if (sample_type & PERF_SAMPLE_TRANSACTION)
printf("... transaction: %" PRIx64 "\n", sample->transaction);
@@ -1350,7 +1375,7 @@ static int deliver_sample_value(struct evlist *evlist,
struct sample_read_value *v,
struct machine *machine)
{
- struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id);
+ struct perf_sample_id *sid = evlist__id2sid(evlist, v->id);
struct evsel *evsel;
if (sid) {
@@ -1395,13 +1420,9 @@ static int deliver_sample_group(struct evlist *evlist,
return ret;
}
-static int
- perf_evlist__deliver_sample(struct evlist *evlist,
- struct perf_tool *tool,
- union perf_event *event,
- struct perf_sample *sample,
- struct evsel *evsel,
- struct machine *machine)
+static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool,
+ union perf_event *event, struct perf_sample *sample,
+ struct evsel *evsel, struct machine *machine)
{
/* We know evsel != NULL. */
u64 sample_type = evsel->core.attr.sample_type;
@@ -1431,7 +1452,7 @@ static int machines__deliver_event(struct machines *machines,
dump_event(evlist, event, file_offset, sample);
- evsel = perf_evlist__id2evsel(evlist, sample->id);
+ evsel = evlist__id2evsel(evlist, sample->id);
machine = machines__find_for_cpumode(machines, event, sample);
@@ -1446,7 +1467,7 @@ static int machines__deliver_event(struct machines *machines,
++evlist->stats.nr_unprocessable_samples;
return 0;
}
- return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
+ return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
case PERF_RECORD_MMAP:
return tool->mmap(tool, event, sample, machine);
case PERF_RECORD_MMAP2:
@@ -1509,9 +1530,8 @@ static int perf_session__deliver_event(struct perf_session *session,
u64 file_offset)
{
struct perf_sample sample;
- int ret;
+ int ret = evlist__parse_sample(session->evlist, event, &sample);
- ret = perf_evlist__parse_sample(session->evlist, event, &sample);
if (ret) {
pr_err("Can't parse sample, err = %d\n", ret);
return ret;
@@ -1683,7 +1703,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
out_parse_sample:
if (sample && event->header.type < PERF_RECORD_USER_TYPE_START &&
- perf_evlist__parse_sample(session->evlist, event, sample))
+ evlist__parse_sample(session->evlist, event, sample))
return -1;
*event_ptr = event;
@@ -1740,7 +1760,7 @@ static s64 perf_session__process_event(struct perf_session *session,
if (tool->ordered_events) {
u64 timestamp = -1ULL;
- ret = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
+ ret = evlist__parse_sample_timestamp(evlist, event, &timestamp);
if (ret && ret != -1)
return ret;
@@ -1923,7 +1943,6 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
{
struct ordered_events *oe = &session->ordered_events;
struct perf_tool *tool = session->tool;
- int fd = perf_data__fd(session->data);
union perf_event *event;
uint32_t size, cur_size = 0;
void *buf = NULL;
@@ -1943,7 +1962,8 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
ordered_events__set_copy_on_queue(oe, true);
more:
event = buf;
- err = readn(fd, event, sizeof(struct perf_event_header));
+ err = perf_data__read(session->data, event,
+ sizeof(struct perf_event_header));
if (err <= 0) {
if (err == 0)
goto done;
@@ -1975,7 +1995,8 @@ more:
p += sizeof(struct perf_event_header);
if (size - sizeof(struct perf_event_header)) {
- err = readn(fd, p, size - sizeof(struct perf_event_header));
+ err = perf_data__read(session->data, p,
+ size - sizeof(struct perf_event_header));
if (err <= 0) {
if (err == 0) {
pr_err("unexpected end of event stream\n");
@@ -2383,7 +2404,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
{
int i, err = -1;
struct perf_cpu_map *map;
- int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
for (i = 0; i < PERF_TYPE_MAX; ++i) {
struct evsel *evsel;
@@ -2462,7 +2483,7 @@ int perf_event__process_id_index(struct perf_session *session,
fprintf(stdout, " tid: %"PRI_ld64"\n", e->tid);
}
- sid = perf_evlist__id2sid(evlist, e->id);
+ sid = evlist__id2sid(evlist, e->id);
if (!sid)
return -ENOENT;
sid->idx = e->idx;
diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c
index ded9ced02797..748371ac22be 100644
--- a/tools/perf/util/sideband_evlist.c
+++ b/tools/perf/util/sideband_evlist.c
@@ -12,8 +12,8 @@
#include <sched.h>
#include <stdbool.h>
-int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
- evsel__sb_cb_t cb, void *data)
+int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
+ evsel__sb_cb_t cb, void *data)
{
struct evsel *evsel;
@@ -62,7 +62,7 @@ static void *perf_evlist__poll_thread(void *arg)
if (perf_mmap__read_init(&map->core))
continue;
while ((event = perf_mmap__read_event(&map->core)) != NULL) {
- struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+ struct evsel *evsel = evlist__event2evsel(evlist, event);
if (evsel && evsel->side_band.cb)
evsel->side_band.cb(event, evsel->side_band.data);
@@ -94,14 +94,14 @@ void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data)
}
}
-int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target)
+int evlist__start_sb_thread(struct evlist *evlist, struct target *target)
{
struct evsel *counter;
if (!evlist)
return 0;
- if (perf_evlist__create_maps(evlist, target))
+ if (evlist__create_maps(evlist, target))
goto out_delete_evlist;
if (evlist->core.nr_entries > 1) {
@@ -110,7 +110,7 @@ int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target)
evlist__for_each_entry(evlist, counter)
evsel__set_sample_id(counter, can_sample_identifier);
- perf_evlist__set_id_pos(evlist);
+ evlist__set_id_pos(evlist);
}
evlist__for_each_entry(evlist, counter) {
@@ -138,7 +138,7 @@ out_delete_evlist:
return -1;
}
-void perf_evlist__stop_sb_thread(struct evlist *evlist)
+void evlist__stop_sb_thread(struct evlist *evlist)
{
if (!evlist)
return;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d42339df20f8..80907bc32683 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1463,6 +1463,35 @@ struct sort_entry sort_mem_phys_daddr = {
};
static int64_t
+sort__data_page_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ uint64_t l = 0, r = 0;
+
+ if (left->mem_info)
+ l = left->mem_info->daddr.data_page_size;
+ if (right->mem_info)
+ r = right->mem_info->daddr.data_page_size;
+
+ return (int64_t)(r - l);
+}
+
+static int hist_entry__data_page_size_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ char str[PAGE_SIZE_NAME_LEN];
+
+ return repsep_snprintf(bf, size, "%-*s", width,
+ get_page_size_name(he->mem_info->daddr.data_page_size, str));
+}
+
+struct sort_entry sort_mem_data_page_size = {
+ .se_header = "Data Page Size",
+ .se_cmp = sort__data_page_size_cmp,
+ .se_snprintf = hist_entry__data_page_size_snprintf,
+ .se_width_idx = HISTC_MEM_DATA_PAGE_SIZE,
+};
+
+static int64_t
sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
{
if (!left->branch_info || !right->branch_info)
@@ -1740,6 +1769,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr),
+ DIM(SORT_MEM_DATA_PAGE_SIZE, "data_page_size", sort_mem_data_page_size),
};
#undef DIM
@@ -2756,7 +2786,7 @@ static const char *get_default_sort_order(struct evlist *evlist)
BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
- if (evlist == NULL || perf_evlist__empty(evlist))
+ if (evlist == NULL || evlist__empty(evlist))
goto out_no_evlist;
evlist__for_each_entry(evlist, evsel) {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 66d39c4cfe2b..e50f2b695bc4 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -255,6 +255,7 @@ enum sort_type {
SORT_MEM_DCACHELINE,
SORT_MEM_IADDR_SYMBOL,
SORT_MEM_PHYS_DADDR,
+ SORT_MEM_DATA_PAGE_SIZE,
};
/*
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 493ec372fdec..583ae4f09c5d 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -68,15 +68,15 @@ static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel)
static void aggr_printout(struct perf_stat_config *config,
- struct evsel *evsel, int id, int nr)
+ struct evsel *evsel, struct aggr_cpu_id id, int nr)
{
switch (config->aggr_mode) {
case AGGR_CORE:
fprintf(config->output, "S%d-D%d-C%*d%s%*d%s",
- cpu_map__id_to_socket(id),
- cpu_map__id_to_die(id),
+ id.socket,
+ id.die,
config->csv_output ? 0 : -8,
- cpu_map__id_to_cpu(id),
+ id.core,
config->csv_sep,
config->csv_output ? 0 : 4,
nr,
@@ -84,9 +84,9 @@ static void aggr_printout(struct perf_stat_config *config,
break;
case AGGR_DIE:
fprintf(config->output, "S%d-D%*d%s%*d%s",
- cpu_map__id_to_socket(id << 16),
+ id.socket,
config->csv_output ? 0 : -8,
- cpu_map__id_to_die(id << 16),
+ id.die,
config->csv_sep,
config->csv_output ? 0 : 4,
nr,
@@ -95,7 +95,7 @@ static void aggr_printout(struct perf_stat_config *config,
case AGGR_SOCKET:
fprintf(config->output, "S%*d%s%*d%s",
config->csv_output ? 0 : -5,
- id,
+ id.socket,
config->csv_sep,
config->csv_output ? 0 : 4,
nr,
@@ -104,7 +104,7 @@ static void aggr_printout(struct perf_stat_config *config,
case AGGR_NODE:
fprintf(config->output, "N%*d%s%*d%s",
config->csv_output ? 0 : -5,
- id,
+ id.node,
config->csv_sep,
config->csv_output ? 0 : 4,
nr,
@@ -113,23 +113,23 @@ static void aggr_printout(struct perf_stat_config *config,
case AGGR_NONE:
if (evsel->percore && !config->percore_show_thread) {
fprintf(config->output, "S%d-D%d-C%*d%s",
- cpu_map__id_to_socket(id),
- cpu_map__id_to_die(id),
+ id.socket,
+ id.die,
config->csv_output ? 0 : -3,
- cpu_map__id_to_cpu(id), config->csv_sep);
- } else if (id > -1) {
+ id.core, config->csv_sep);
+ } else if (id.core > -1) {
fprintf(config->output, "CPU%*d%s",
config->csv_output ? 0 : -7,
- evsel__cpus(evsel)->map[id],
+ evsel__cpus(evsel)->map[id.core],
config->csv_sep);
}
break;
case AGGR_THREAD:
fprintf(config->output, "%*s-%*d%s",
config->csv_output ? 0 : 16,
- perf_thread_map__comm(evsel->core.threads, id),
+ perf_thread_map__comm(evsel->core.threads, id.thread),
config->csv_output ? 0 : -8,
- perf_thread_map__pid(evsel->core.threads, id),
+ perf_thread_map__pid(evsel->core.threads, id.thread),
config->csv_sep);
break;
case AGGR_GLOBAL:
@@ -144,7 +144,8 @@ struct outstate {
bool newline;
const char *prefix;
int nfields;
- int id, nr;
+ int nr;
+ struct aggr_cpu_id id;
struct evsel *evsel;
};
@@ -319,31 +320,31 @@ static void print_metric_header(struct perf_stat_config *config,
}
static int first_shadow_cpu(struct perf_stat_config *config,
- struct evsel *evsel, int id)
+ struct evsel *evsel, struct aggr_cpu_id id)
{
struct evlist *evlist = evsel->evlist;
int i;
- if (!config->aggr_get_id)
- return 0;
-
if (config->aggr_mode == AGGR_NONE)
- return id;
+ return id.core;
- if (config->aggr_mode == AGGR_GLOBAL)
+ if (!config->aggr_get_id)
return 0;
for (i = 0; i < evsel__nr_cpus(evsel); i++) {
int cpu2 = evsel__cpus(evsel)->map[i];
- if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id)
+ if (cpu_map__compare_aggr_cpu_id(
+ config->aggr_get_id(config, evlist->core.cpus, cpu2),
+ id)) {
return cpu2;
+ }
}
return 0;
}
static void abs_printout(struct perf_stat_config *config,
- int id, int nr, struct evsel *evsel, double avg)
+ struct aggr_cpu_id id, int nr, struct evsel *evsel, double avg)
{
FILE *output = config->output;
double sc = evsel->scale;
@@ -396,7 +397,7 @@ static bool is_mixed_hw_group(struct evsel *counter)
return false;
}
-static void printout(struct perf_stat_config *config, int id, int nr,
+static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr,
struct evsel *counter, double uval,
char *prefix, u64 run, u64 ena, double noise,
struct runtime_stat *st)
@@ -499,7 +500,8 @@ static void printout(struct perf_stat_config *config, int id, int nr,
static void aggr_update_shadow(struct perf_stat_config *config,
struct evlist *evlist)
{
- int cpu, s2, id, s;
+ int cpu, s;
+ struct aggr_cpu_id s2, id;
u64 val;
struct evsel *counter;
@@ -509,7 +511,7 @@ static void aggr_update_shadow(struct perf_stat_config *config,
val = 0;
for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
s2 = config->aggr_get_id(config, evlist->core.cpus, cpu);
- if (s2 != id)
+ if (!cpu_map__compare_aggr_cpu_id(s2, id))
continue;
val += perf_counts(counter->counts, cpu, 0)->val;
}
@@ -587,7 +589,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
struct aggr_data {
u64 ena, run, val;
- int id;
+ struct aggr_cpu_id id;
int nr;
int cpu;
};
@@ -596,13 +598,14 @@ static void aggr_cb(struct perf_stat_config *config,
struct evsel *counter, void *data, bool first)
{
struct aggr_data *ad = data;
- int cpu, s2;
+ int cpu;
+ struct aggr_cpu_id s2;
for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
struct perf_counts_values *counts;
s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
- if (s2 != ad->id)
+ if (!cpu_map__compare_aggr_cpu_id(s2, ad->id))
continue;
if (first)
ad->nr++;
@@ -631,7 +634,8 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
struct aggr_data ad;
FILE *output = config->output;
u64 ena, run, val;
- int id, nr;
+ int nr;
+ struct aggr_cpu_id id;
double uval;
ad.id = id = config->aggr_map->map[s];
@@ -652,8 +656,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- printout(config, cpu != -1 ? cpu : id, nr, counter, uval, prefix,
- run, ena, 1.0, &rt_stat);
+ if (cpu != -1) {
+ id = cpu_map__empty_aggr_cpu_id();
+ id.core = cpu;
+ }
+ printout(config, id, nr, counter, uval,
+ prefix, run, ena, 1.0, &rt_stat);
if (!metric_only)
fputc('\n', output);
}
@@ -731,7 +739,8 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
continue;
buf[i].counter = counter;
- buf[i].id = thread;
+ buf[i].id = cpu_map__empty_aggr_cpu_id();
+ buf[i].id.thread = thread;
buf[i].uval = uval;
buf[i].val = val;
buf[i].run = run;
@@ -754,7 +763,8 @@ static void print_aggr_thread(struct perf_stat_config *config,
FILE *output = config->output;
int nthreads = perf_thread_map__nr(counter->core.threads);
int ncpus = perf_cpu_map__nr(counter->core.cpus);
- int thread, sorted_threads, id;
+ int thread, sorted_threads;
+ struct aggr_cpu_id id;
struct perf_aggr_thread_value *buf;
buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
@@ -771,7 +781,7 @@ static void print_aggr_thread(struct perf_stat_config *config,
if (config->stats)
printout(config, id, 0, buf[thread].counter, buf[thread].uval,
prefix, buf[thread].run, buf[thread].ena, 1.0,
- &config->stats[id]);
+ &config->stats[id.thread]);
else
printout(config, id, 0, buf[thread].counter, buf[thread].uval,
prefix, buf[thread].run, buf[thread].ena, 1.0,
@@ -817,8 +827,8 @@ static void print_counter_aggr(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = cd.avg * counter->scale;
- printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
- cd.avg, &rt_stat);
+ printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running,
+ cd.avg_enabled, cd.avg, &rt_stat);
if (!metric_only)
fprintf(output, "\n");
}
@@ -845,6 +855,7 @@ static void print_counter(struct perf_stat_config *config,
u64 ena, run, val;
double uval;
int cpu;
+ struct aggr_cpu_id id;
for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
struct aggr_data ad = { .cpu = cpu };
@@ -859,8 +870,10 @@ static void print_counter(struct perf_stat_config *config,
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
- &rt_stat);
+ id = cpu_map__empty_aggr_cpu_id();
+ id.core = cpu;
+ printout(config, id, 0, counter, uval, prefix,
+ run, ena, 1.0, &rt_stat);
fputc('\n', output);
}
@@ -875,6 +888,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
struct evsel *counter;
u64 ena, run, val;
double uval;
+ struct aggr_cpu_id id;
nrcpus = evlist->core.cpus->nr;
for (cpu = 0; cpu < nrcpus; cpu++) {
@@ -883,8 +897,10 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
if (prefix)
fputs(prefix, config->output);
evlist__for_each_entry(evlist, counter) {
+ id = cpu_map__empty_aggr_cpu_id();
+ id.core = cpu;
if (first) {
- aggr_printout(config, counter, cpu, 0);
+ aggr_printout(config, counter, id, 0);
first = false;
}
val = perf_counts(counter->counts, cpu, 0)->val;
@@ -892,8 +908,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
run = perf_counts(counter->counts, cpu, 0)->run;
uval = val * counter->scale;
- printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
- &rt_stat);
+ printout(config, id, 0, counter, uval, prefix,
+ run, ena, 1.0, &rt_stat);
}
fputc('\n', config->output);
}
@@ -946,7 +962,6 @@ static void print_metric_headers(struct perf_stat_config *config,
out.print_metric = print_metric_header;
out.new_line = new_line_metric;
out.force_header = true;
- os.evsel = counter;
perf_stat__print_shadow_stats(config, counter, 0,
0,
&out,
@@ -1144,14 +1159,15 @@ static void print_footer(struct perf_stat_config *config)
static void print_percore_thread(struct perf_stat_config *config,
struct evsel *counter, char *prefix)
{
- int s, s2, id;
+ int s;
+ struct aggr_cpu_id s2, id;
bool first = true;
for (int i = 0; i < evsel__nr_cpus(counter); i++) {
s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
for (s = 0; s < config->aggr_map->nr; s++) {
id = config->aggr_map->map[s];
- if (s2 == id)
+ if (cpu_map__compare_aggr_cpu_id(s2, id))
break;
}
@@ -1188,12 +1204,8 @@ static void print_percore(struct perf_stat_config *config,
fputc('\n', output);
}
-void
-perf_evlist__print_counters(struct evlist *evlist,
- struct perf_stat_config *config,
- struct target *_target,
- struct timespec *ts,
- int argc, const char **argv)
+void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
+ struct target *_target, struct timespec *ts, int argc, const char **argv)
{
bool metric_only = config->metric_only;
int interval = config->interval;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 924b54d15d54..12eafd12a693 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -8,6 +8,7 @@
#include "evlist.h"
#include "expr.h"
#include "metricgroup.h"
+#include "cgroup.h"
#include <linux/zalloc.h>
/*
@@ -28,6 +29,7 @@ struct saved_value {
enum stat_type type;
int ctx;
int cpu;
+ struct cgroup *cgrp;
struct runtime_stat *stat;
struct stats stats;
u64 metric_total;
@@ -57,6 +59,9 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
if (a->ctx != b->ctx)
return a->ctx - b->ctx;
+ if (a->cgrp != b->cgrp)
+ return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1;
+
if (a->evsel == NULL && b->evsel == NULL) {
if (a->stat == b->stat)
return 0;
@@ -100,7 +105,8 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
bool create,
enum stat_type type,
int ctx,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct cgroup *cgrp)
{
struct rblist *rblist;
struct rb_node *nd;
@@ -110,10 +116,15 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
.type = type,
.ctx = ctx,
.stat = st,
+ .cgrp = cgrp,
};
rblist = &st->value_list;
+ /* don't use context info for clock events */
+ if (type == STAT_NSECS)
+ dm.ctx = 0;
+
nd = rblist__find(rblist, &dm);
if (nd)
return container_of(nd, struct saved_value, rb_node);
@@ -191,12 +202,18 @@ void perf_stat__reset_shadow_per_stat(struct runtime_stat *st)
reset_stat(st);
}
+struct runtime_stat_data {
+ int ctx;
+ struct cgroup *cgrp;
+};
+
static void update_runtime_stat(struct runtime_stat *st,
enum stat_type type,
- int ctx, int cpu, u64 count)
+ int cpu, u64 count,
+ struct runtime_stat_data *rsd)
{
- struct saved_value *v = saved_value_lookup(NULL, cpu, true,
- type, ctx, st);
+ struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
+ rsd->ctx, st, rsd->cgrp);
if (v)
update_stats(&v->stats, count);
@@ -210,70 +227,86 @@ static void update_runtime_stat(struct runtime_stat *st,
void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
int cpu, struct runtime_stat *st)
{
- int ctx = evsel_context(counter);
u64 count_ns = count;
struct saved_value *v;
+ struct runtime_stat_data rsd = {
+ .ctx = evsel_context(counter),
+ .cgrp = counter->cgrp,
+ };
count *= counter->scale;
if (evsel__is_clock(counter))
- update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns);
+ update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_runtime_stat(st, STAT_TRANSACTION, ctx, cpu, count);
+ update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, ELISION_START))
- update_runtime_stat(st, STAT_ELISION, ctx, cpu, count);
+ update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
- ctx, cpu, count);
+ cpu, count, &rsd);
+ else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
+ update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
+ cpu, count, &rsd);
+ else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
+ update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
+ cpu, count, &rsd);
+ else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
+ update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
+ cpu, count, &rsd);
+ else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
+ update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
+ update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, SMI_NUM))
- update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
+ update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, APERF))
- update_runtime_stat(st, STAT_APERF, ctx, cpu, count);
+ update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
if (counter->collect_stat) {
- v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st);
+ v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+ rsd.cgrp);
update_stats(&v->stats, count);
if (counter->metric_leader)
v->metric_total += count;
} else if (counter->metric_leader) {
v = saved_value_lookup(counter->metric_leader,
- cpu, true, STAT_NONE, 0, st);
+ cpu, true, STAT_NONE, 0, st, rsd.cgrp);
v->metric_total += count;
v->metric_other++;
}
@@ -410,11 +443,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
}
static double runtime_stat_avg(struct runtime_stat *st,
- enum stat_type type, int ctx, int cpu)
+ enum stat_type type, int cpu,
+ struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+ v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
@@ -422,11 +456,12 @@ static double runtime_stat_avg(struct runtime_stat *st,
}
static double runtime_stat_n(struct runtime_stat *st,
- enum stat_type type, int ctx, int cpu)
+ enum stat_type type, int cpu,
+ struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+ v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
@@ -434,16 +469,15 @@ static double runtime_stat_n(struct runtime_stat *st,
}
static void print_stalled_cycles_frontend(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel, double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -458,16 +492,15 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
}
static void print_stalled_cycles_backend(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel, double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -478,17 +511,15 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
}
static void print_branch_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_BRANCHES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -499,18 +530,15 @@ static void print_branch_misses(struct perf_stat_config *config,
}
static void print_l1_dcache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
-
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_L1_DCACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -521,18 +549,15 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
}
static void print_l1_icache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
-
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_L1_ICACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -542,17 +567,15 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
}
static void print_dtlb_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_DTLB_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -562,17 +585,15 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
}
static void print_itlb_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_ITLB_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -582,17 +603,15 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
}
static void print_ll_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_LL_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -650,73 +669,118 @@ static double sanitize_val(double x)
return x;
}
-static double td_total_slots(int ctx, int cpu, struct runtime_stat *st)
+static double td_total_slots(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
- return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu);
+ return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd);
}
-static double td_bad_spec(int ctx, int cpu, struct runtime_stat *st)
+static double td_bad_spec(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double bad_spec = 0;
double total_slots;
double total;
- total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
- runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
- runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) -
+ runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) +
+ runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd);
- total_slots = td_total_slots(ctx, cpu, st);
+ total_slots = td_total_slots(cpu, st, rsd);
if (total_slots)
bad_spec = total / total_slots;
return sanitize_val(bad_spec);
}
-static double td_retiring(int ctx, int cpu, struct runtime_stat *st)
+static double td_retiring(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double retiring = 0;
- double total_slots = td_total_slots(ctx, cpu, st);
+ double total_slots = td_total_slots(cpu, st, rsd);
double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
- ctx, cpu);
+ cpu, rsd);
if (total_slots)
retiring = ret_slots / total_slots;
return retiring;
}
-static double td_fe_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_fe_bound(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double fe_bound = 0;
- double total_slots = td_total_slots(ctx, cpu, st);
+ double total_slots = td_total_slots(cpu, st, rsd);
double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
- ctx, cpu);
+ cpu, rsd);
if (total_slots)
fe_bound = fetch_bub / total_slots;
return fe_bound;
}
-static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_be_bound(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
- double sum = (td_fe_bound(ctx, cpu, st) +
- td_bad_spec(ctx, cpu, st) +
- td_retiring(ctx, cpu, st));
+ double sum = (td_fe_bound(cpu, st, rsd) +
+ td_bad_spec(cpu, st, rsd) +
+ td_retiring(cpu, st, rsd));
if (sum == 0)
return 0;
return sanitize_val(1.0 - sum);
}
-static void print_smi_cost(struct perf_stat_config *config,
- int cpu, struct evsel *evsel,
+/*
+ * Kernel reports metrics multiplied with slots. To get back
+ * the ratios we need to recreate the sum.
+ */
+
+static double td_metric_ratio(int cpu, enum stat_type type,
+ struct runtime_stat *stat,
+ struct runtime_stat_data *rsd)
+{
+ double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd);
+ double d = runtime_stat_avg(stat, type, cpu, rsd);
+
+ if (sum)
+ return d / sum;
+ return 0;
+}
+
+/*
+ * ... but only if most of the values are actually available.
+ * We allow two missing.
+ */
+
+static bool full_td(int cpu, struct runtime_stat *stat,
+ struct runtime_stat_data *rsd)
+{
+ int c = 0;
+
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0)
+ c++;
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0)
+ c++;
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0)
+ c++;
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0)
+ c++;
+ return c >= 2;
+}
+
+static void print_smi_cost(struct perf_stat_config *config, int cpu,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double smi_num, aperf, cycles, cost = 0.0;
- int ctx = evsel_context(evsel);
const char *color = NULL;
- smi_num = runtime_stat_avg(st, STAT_SMI_NUM, ctx, cpu);
- aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu);
- cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd);
+ aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd);
+ cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if ((cycles == 0) || (aperf == 0))
return;
@@ -751,7 +815,8 @@ static int prepare_metric(struct evsel **metric_events,
scale = 1e-9;
} else {
v = saved_value_lookup(metric_events[i], cpu, false,
- STAT_NONE, 0, st);
+ STAT_NONE, 0, st,
+ metric_events[i]->cgrp);
if (!v)
break;
stats = &v->stats;
@@ -877,12 +942,15 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric_t print_metric = out->print_metric;
double total, ratio = 0.0, total2;
const char *color = NULL;
- int ctx = evsel_context(evsel);
+ struct runtime_stat_data rsd = {
+ .ctx = evsel_context(evsel),
+ .cgrp = evsel->cgrp,
+ };
struct metric_event *me;
int num = 1;
if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
if (total) {
ratio = avg / total;
@@ -892,12 +960,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
}
- total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd);
total = max(total, runtime_stat_avg(st,
STAT_STALLED_CYCLES_BACK,
- ctx, cpu));
+ cpu, &rsd));
if (total && avg) {
out->new_line(config, ctxp);
@@ -907,8 +974,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
ratio);
}
} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
- if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
- print_branch_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0)
+ print_branch_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
} else if (
@@ -917,8 +984,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
- print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0)
+ print_l1_dcache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
} else if (
@@ -927,8 +994,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
- print_l1_icache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0)
+ print_l1_icache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
} else if (
@@ -937,8 +1004,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
- print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0)
+ print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
} else if (
@@ -947,8 +1014,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
- print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0)
+ print_itlb_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
} else if (
@@ -957,27 +1024,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
- print_ll_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0)
+ print_ll_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
- total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd);
if (total)
ratio = avg * 100 / total;
- if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
+ if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.3f %%",
"of all cache refs", ratio);
else
print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
+ print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
+ print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
if (total) {
ratio = avg / total;
@@ -986,7 +1053,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
if (total)
print_metric(config, ctxp, NULL,
@@ -996,8 +1063,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "transactional cycles",
0);
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
- total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+ total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (total2 < avg)
total2 = avg;
@@ -1007,21 +1074,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
else
print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (avg)
ratio = total / avg;
- if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
+ if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.0f",
"cycles / transaction", ratio);
else
print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
0);
} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (avg)
ratio = total / avg;
@@ -1034,28 +1099,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
else
print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
- double fe_bound = td_fe_bound(ctx, cpu, st);
+ double fe_bound = td_fe_bound(cpu, st, &rsd);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
- double retiring = td_retiring(ctx, cpu, st);
+ double retiring = td_retiring(cpu, st, &rsd);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
- double bad_spec = td_bad_spec(ctx, cpu, st);
+ double bad_spec = td_bad_spec(cpu, st, &rsd);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
- double be_bound = td_be_bound(ctx, cpu, st);
+ double be_bound = td_be_bound(cpu, st, &rsd);
const char *name = "backend bound";
static int have_recovery_bubbles = -1;
@@ -1068,19 +1133,55 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (be_bound > 0.2)
color = PERF_COLOR_RED;
- if (td_total_slots(ctx, cpu, st) > 0)
+ if (td_total_slots(cpu, st, &rsd) > 0)
print_metric(config, ctxp, color, "%8.1f%%", name,
be_bound * 100.);
else
print_metric(config, ctxp, NULL, NULL, name, 0);
+ } else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
+ full_td(cpu, st, &rsd)) {
+ double retiring = td_metric_ratio(cpu,
+ STAT_TOPDOWN_RETIRING, st,
+ &rsd);
+ if (retiring > 0.7)
+ color = PERF_COLOR_GREEN;
+ print_metric(config, ctxp, color, "%8.1f%%", "retiring",
+ retiring * 100.);
+ } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
+ full_td(cpu, st, &rsd)) {
+ double fe_bound = td_metric_ratio(cpu,
+ STAT_TOPDOWN_FE_BOUND, st,
+ &rsd);
+ if (fe_bound > 0.2)
+ color = PERF_COLOR_RED;
+ print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
+ fe_bound * 100.);
+ } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
+ full_td(cpu, st, &rsd)) {
+ double be_bound = td_metric_ratio(cpu,
+ STAT_TOPDOWN_BE_BOUND, st,
+ &rsd);
+ if (be_bound > 0.2)
+ color = PERF_COLOR_RED;
+ print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
+ be_bound * 100.);
+ } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
+ full_td(cpu, st, &rsd)) {
+ double bad_spec = td_metric_ratio(cpu,
+ STAT_TOPDOWN_BAD_SPEC, st,
+ &rsd);
+ if (bad_spec > 0.1)
+ color = PERF_COLOR_RED;
+ print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
+ bad_spec * 100.);
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
- } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
+ } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) {
char unit = 'M';
char unit_buf[10];
- total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
if (total)
ratio = 1000.0 * avg / total;
@@ -1091,7 +1192,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
- print_smi_cost(config, cpu, evsel, out, st);
+ print_smi_cost(config, cpu, out, st, &rsd);
} else {
num = 0;
}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index cdb154381a87..8ce1479c98f0 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -95,6 +95,10 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
+ ID(TOPDOWN_RETIRING, topdown-retiring),
+ ID(TOPDOWN_BAD_SPEC, topdown-bad-spec),
+ ID(TOPDOWN_FE_BOUND, topdown-fe-bound),
+ ID(TOPDOWN_BE_BOUND, topdown-be-bound),
ID(SMI_NUM, msr/smi/),
ID(APERF, msr/aperf/),
};
@@ -180,7 +184,7 @@ static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
return 0;
}
-int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
+int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
{
struct evsel *evsel;
@@ -192,11 +196,11 @@ int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
return 0;
out_free:
- perf_evlist__free_stats(evlist);
+ evlist__free_stats(evlist);
return -1;
}
-void perf_evlist__free_stats(struct evlist *evlist)
+void evlist__free_stats(struct evlist *evlist)
{
struct evsel *evsel;
@@ -207,7 +211,7 @@ void perf_evlist__free_stats(struct evlist *evlist)
}
}
-void perf_evlist__reset_stats(struct evlist *evlist)
+void evlist__reset_stats(struct evlist *evlist)
{
struct evsel *evsel;
@@ -217,7 +221,7 @@ void perf_evlist__reset_stats(struct evlist *evlist)
}
}
-void perf_evlist__reset_prev_raw_counts(struct evlist *evlist)
+void evlist__reset_prev_raw_counts(struct evlist *evlist)
{
struct evsel *evsel;
@@ -225,7 +229,7 @@ void perf_evlist__reset_prev_raw_counts(struct evlist *evlist)
evsel__reset_prev_raw_counts(evsel);
}
-static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel)
+static void evsel__copy_prev_raw_counts(struct evsel *evsel)
{
int ncpus = evsel__nr_cpus(evsel);
int nthreads = perf_thread_map__nr(evsel->core.threads);
@@ -241,15 +245,15 @@ static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel)
evsel->counts->aggr = evsel->prev_raw_counts->aggr;
}
-void perf_evlist__copy_prev_raw_counts(struct evlist *evlist)
+void evlist__copy_prev_raw_counts(struct evlist *evlist)
{
struct evsel *evsel;
evlist__for_each_entry(evlist, evsel)
- perf_evsel__copy_prev_raw_counts(evsel);
+ evsel__copy_prev_raw_counts(evsel);
}
-void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
+void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
{
struct evsel *evsel;
@@ -309,7 +313,7 @@ static int check_per_pkg(struct evsel *counter,
if (!(vals->run && vals->ena))
return 0;
- s = cpu_map__get_socket(cpus, cpu, NULL);
+ s = cpu_map__get_socket(cpus, cpu, NULL).socket;
if (s < 0)
return -1;
@@ -454,7 +458,7 @@ int perf_event__process_stat_event(struct perf_session *session,
count.ena = st->ena;
count.run = st->run;
- counter = perf_evlist__id2evsel(session->evlist, st->id);
+ counter = evlist__id2evsel(session->evlist, st->id);
if (!counter) {
pr_err("Failed to resolve counter for stat event.\n");
return -EINVAL;
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index aa3bed48511b..b5369730b4a2 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -6,6 +6,7 @@
#include <stdio.h>
#include <sys/types.h>
#include <sys/resource.h>
+#include "cpumap.h"
#include "rblist.h"
struct perf_cpu_map;
@@ -28,6 +29,10 @@ enum perf_stat_evsel_id {
PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
+ PERF_STAT_EVSEL_ID__TOPDOWN_RETIRING,
+ PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC,
+ PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND,
+ PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND,
PERF_STAT_EVSEL_ID__SMI_NUM,
PERF_STAT_EVSEL_ID__APERF,
PERF_STAT_EVSEL_ID__MAX,
@@ -82,6 +87,10 @@ enum stat_type {
STAT_TOPDOWN_SLOTS_RETIRED,
STAT_TOPDOWN_FETCH_BUBBLES,
STAT_TOPDOWN_RECOVERY_BUBBLES,
+ STAT_TOPDOWN_RETIRING,
+ STAT_TOPDOWN_BAD_SPEC,
+ STAT_TOPDOWN_FE_BOUND,
+ STAT_TOPDOWN_BE_BOUND,
STAT_SMI_NUM,
STAT_APERF,
STAT_MAX
@@ -91,7 +100,7 @@ struct runtime_stat {
struct rblist value_list;
};
-typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
+typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config,
struct perf_cpu_map *m, int cpu);
struct perf_stat_config {
@@ -114,6 +123,7 @@ struct perf_stat_config {
bool metric_no_group;
bool metric_no_merge;
bool stop_read_counter;
+ bool quiet;
FILE *output;
unsigned int interval;
unsigned int timeout;
@@ -129,13 +139,15 @@ struct perf_stat_config {
const char *csv_sep;
struct stats *walltime_nsecs_stats;
struct rusage ru_data;
- struct perf_cpu_map *aggr_map;
+ struct cpu_aggr_map *aggr_map;
aggr_get_id_t aggr_get_id;
- struct perf_cpu_map *cpus_aggr_map;
+ struct cpu_aggr_map *cpus_aggr_map;
u64 *walltime_run;
struct rblist metric_events;
int ctl_fd;
int ctl_fd_ack;
+ bool ctl_fd_close;
+ const char *cgroup_list;
};
void perf_stat__set_big_num(int set);
@@ -159,7 +171,7 @@ struct evlist;
struct perf_aggr_thread_value {
struct evsel *counter;
- int id;
+ struct aggr_cpu_id id;
double uval;
u64 val;
u64 run;
@@ -202,12 +214,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
struct runtime_stat *st);
void perf_stat__collect_metric_expr(struct evlist *);
-int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
-void perf_evlist__free_stats(struct evlist *evlist);
-void perf_evlist__reset_stats(struct evlist *evlist);
-void perf_evlist__reset_prev_raw_counts(struct evlist *evlist);
-void perf_evlist__copy_prev_raw_counts(struct evlist *evlist);
-void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist);
+int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
+void evlist__free_stats(struct evlist *evlist);
+void evlist__reset_stats(struct evlist *evlist);
+void evlist__reset_prev_raw_counts(struct evlist *evlist);
+void evlist__copy_prev_raw_counts(struct evlist *evlist);
+void evlist__save_aggr_prev_raw_counts(struct evlist *evlist);
int perf_stat_process_counter(struct perf_stat_config *config,
struct evsel *counter);
@@ -227,12 +239,8 @@ int create_perf_stat_counter(struct evsel *evsel,
struct perf_stat_config *config,
struct target *target,
int cpu);
-void
-perf_evlist__print_counters(struct evlist *evlist,
- struct perf_stat_config *config,
- struct target *_target,
- struct timespec *ts,
- int argc, const char **argv);
+void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
+ struct target *_target, struct timespec *ts, int argc, const char **argv);
struct metric_expr;
double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st);
diff --git a/tools/perf/util/stream.c b/tools/perf/util/stream.c
new file mode 100644
index 000000000000..4bd5e5a00aa5
--- /dev/null
+++ b/tools/perf/util/stream.c
@@ -0,0 +1,342 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Compare and figure out the top N hottest streams
+ * Copyright (c) 2020, Intel Corporation.
+ * Author: Jin Yao
+ */
+
+#include <inttypes.h>
+#include <stdlib.h>
+#include <linux/zalloc.h>
+#include "debug.h"
+#include "hist.h"
+#include "sort.h"
+#include "stream.h"
+#include "evlist.h"
+
+static void evsel_streams__delete(struct evsel_streams *es, int nr_evsel)
+{
+ for (int i = 0; i < nr_evsel; i++)
+ zfree(&es[i].streams);
+
+ free(es);
+}
+
+void evlist_streams__delete(struct evlist_streams *els)
+{
+ evsel_streams__delete(els->ev_streams, els->nr_evsel);
+ free(els);
+}
+
+static struct evlist_streams *evlist_streams__new(int nr_evsel,
+ int nr_streams_max)
+{
+ struct evlist_streams *els;
+ struct evsel_streams *es;
+
+ els = zalloc(sizeof(*els));
+ if (!els)
+ return NULL;
+
+ es = calloc(nr_evsel, sizeof(struct evsel_streams));
+ if (!es) {
+ free(els);
+ return NULL;
+ }
+
+ for (int i = 0; i < nr_evsel; i++) {
+ struct evsel_streams *s = &es[i];
+
+ s->streams = calloc(nr_streams_max, sizeof(struct stream));
+ if (!s->streams)
+ goto err;
+
+ s->nr_streams_max = nr_streams_max;
+ s->evsel_idx = -1;
+ }
+
+ els->ev_streams = es;
+ els->nr_evsel = nr_evsel;
+ return els;
+
+err:
+ evsel_streams__delete(es, nr_evsel);
+ return NULL;
+}
+
+/*
+ * The cnodes with high hit number are hot callchains.
+ */
+static void evsel_streams__set_hot_cnode(struct evsel_streams *es,
+ struct callchain_node *cnode)
+{
+ int i, idx = 0;
+ u64 hit;
+
+ if (es->nr_streams < es->nr_streams_max) {
+ i = es->nr_streams;
+ es->streams[i].cnode = cnode;
+ es->nr_streams++;
+ return;
+ }
+
+ /*
+ * Considering a few number of hot streams, only use simple
+ * way to find the cnode with smallest hit number and replace.
+ */
+ hit = (es->streams[0].cnode)->hit;
+ for (i = 1; i < es->nr_streams; i++) {
+ if ((es->streams[i].cnode)->hit < hit) {
+ hit = (es->streams[i].cnode)->hit;
+ idx = i;
+ }
+ }
+
+ if (cnode->hit > hit)
+ es->streams[idx].cnode = cnode;
+}
+
+static void update_hot_callchain(struct hist_entry *he,
+ struct evsel_streams *es)
+{
+ struct rb_root *root = &he->sorted_chain;
+ struct rb_node *rb_node = rb_first(root);
+ struct callchain_node *cnode;
+
+ while (rb_node) {
+ cnode = rb_entry(rb_node, struct callchain_node, rb_node);
+ evsel_streams__set_hot_cnode(es, cnode);
+ rb_node = rb_next(rb_node);
+ }
+}
+
+static void init_hot_callchain(struct hists *hists, struct evsel_streams *es)
+{
+ struct rb_node *next = rb_first_cached(&hists->entries);
+
+ while (next) {
+ struct hist_entry *he;
+
+ he = rb_entry(next, struct hist_entry, rb_node);
+ update_hot_callchain(he, es);
+ next = rb_next(&he->rb_node);
+ }
+
+ es->streams_hits = callchain_total_hits(hists);
+}
+
+static int evlist__init_callchain_streams(struct evlist *evlist,
+ struct evlist_streams *els)
+{
+ struct evsel_streams *es = els->ev_streams;
+ struct evsel *pos;
+ int i = 0;
+
+ BUG_ON(els->nr_evsel < evlist->core.nr_entries);
+
+ evlist__for_each_entry(evlist, pos) {
+ struct hists *hists = evsel__hists(pos);
+
+ hists__output_resort(hists, NULL);
+ init_hot_callchain(hists, &es[i]);
+ es[i].evsel_idx = pos->idx;
+ i++;
+ }
+
+ return 0;
+}
+
+struct evlist_streams *evlist__create_streams(struct evlist *evlist,
+ int nr_streams_max)
+{
+ int nr_evsel = evlist->core.nr_entries, ret = -1;
+ struct evlist_streams *els = evlist_streams__new(nr_evsel,
+ nr_streams_max);
+
+ if (!els)
+ return NULL;
+
+ ret = evlist__init_callchain_streams(evlist, els);
+ if (ret) {
+ evlist_streams__delete(els);
+ return NULL;
+ }
+
+ return els;
+}
+
+struct evsel_streams *evsel_streams__entry(struct evlist_streams *els,
+ int evsel_idx)
+{
+ struct evsel_streams *es = els->ev_streams;
+
+ for (int i = 0; i < els->nr_evsel; i++) {
+ if (es[i].evsel_idx == evsel_idx)
+ return &es[i];
+ }
+
+ return NULL;
+}
+
+static struct stream *stream__callchain_match(struct stream *base_stream,
+ struct evsel_streams *es_pair)
+{
+ for (int i = 0; i < es_pair->nr_streams; i++) {
+ struct stream *pair_stream = &es_pair->streams[i];
+
+ if (callchain_cnode_matched(base_stream->cnode,
+ pair_stream->cnode)) {
+ return pair_stream;
+ }
+ }
+
+ return NULL;
+}
+
+static struct stream *stream__match(struct stream *base_stream,
+ struct evsel_streams *es_pair)
+{
+ return stream__callchain_match(base_stream, es_pair);
+}
+
+static void stream__link(struct stream *base_stream, struct stream *pair_stream)
+{
+ base_stream->pair_cnode = pair_stream->cnode;
+ pair_stream->pair_cnode = base_stream->cnode;
+}
+
+void evsel_streams__match(struct evsel_streams *es_base,
+ struct evsel_streams *es_pair)
+{
+ for (int i = 0; i < es_base->nr_streams; i++) {
+ struct stream *base_stream = &es_base->streams[i];
+ struct stream *pair_stream;
+
+ pair_stream = stream__match(base_stream, es_pair);
+ if (pair_stream)
+ stream__link(base_stream, pair_stream);
+ }
+}
+
+static void print_callchain_pair(struct stream *base_stream, int idx,
+ struct evsel_streams *es_base,
+ struct evsel_streams *es_pair)
+{
+ struct callchain_node *base_cnode = base_stream->cnode;
+ struct callchain_node *pair_cnode = base_stream->pair_cnode;
+ struct callchain_list *base_chain, *pair_chain;
+ char buf1[512], buf2[512], cbuf1[256], cbuf2[256];
+ char *s1, *s2;
+ double pct;
+
+ printf("\nhot chain pair %d:\n", idx);
+
+ pct = (double)base_cnode->hit / (double)es_base->streams_hits;
+ scnprintf(buf1, sizeof(buf1), "cycles: %ld, hits: %.2f%%",
+ callchain_avg_cycles(base_cnode), pct * 100.0);
+
+ pct = (double)pair_cnode->hit / (double)es_pair->streams_hits;
+ scnprintf(buf2, sizeof(buf2), "cycles: %ld, hits: %.2f%%",
+ callchain_avg_cycles(pair_cnode), pct * 100.0);
+
+ printf("%35s\t%35s\n", buf1, buf2);
+
+ printf("%35s\t%35s\n",
+ "---------------------------",
+ "--------------------------");
+
+ pair_chain = list_first_entry(&pair_cnode->val,
+ struct callchain_list,
+ list);
+
+ list_for_each_entry(base_chain, &base_cnode->val, list) {
+ if (&pair_chain->list == &pair_cnode->val)
+ return;
+
+ s1 = callchain_list__sym_name(base_chain, cbuf1, sizeof(cbuf1),
+ false);
+ s2 = callchain_list__sym_name(pair_chain, cbuf2, sizeof(cbuf2),
+ false);
+
+ scnprintf(buf1, sizeof(buf1), "%35s\t%35s", s1, s2);
+ printf("%s\n", buf1);
+ pair_chain = list_next_entry(pair_chain, list);
+ }
+}
+
+static void print_stream_callchain(struct stream *stream, int idx,
+ struct evsel_streams *es, bool pair)
+{
+ struct callchain_node *cnode = stream->cnode;
+ struct callchain_list *chain;
+ char buf[512], cbuf[256], *s;
+ double pct;
+
+ printf("\nhot chain %d:\n", idx);
+
+ pct = (double)cnode->hit / (double)es->streams_hits;
+ scnprintf(buf, sizeof(buf), "cycles: %ld, hits: %.2f%%",
+ callchain_avg_cycles(cnode), pct * 100.0);
+
+ if (pair) {
+ printf("%35s\t%35s\n", "", buf);
+ printf("%35s\t%35s\n",
+ "", "--------------------------");
+ } else {
+ printf("%35s\n", buf);
+ printf("%35s\n", "--------------------------");
+ }
+
+ list_for_each_entry(chain, &cnode->val, list) {
+ s = callchain_list__sym_name(chain, cbuf, sizeof(cbuf), false);
+
+ if (pair)
+ scnprintf(buf, sizeof(buf), "%35s\t%35s", "", s);
+ else
+ scnprintf(buf, sizeof(buf), "%35s", s);
+
+ printf("%s\n", buf);
+ }
+}
+
+static void callchain_streams_report(struct evsel_streams *es_base,
+ struct evsel_streams *es_pair)
+{
+ struct stream *base_stream;
+ int i, idx = 0;
+
+ printf("[ Matched hot streams ]\n");
+ for (i = 0; i < es_base->nr_streams; i++) {
+ base_stream = &es_base->streams[i];
+ if (base_stream->pair_cnode) {
+ print_callchain_pair(base_stream, ++idx,
+ es_base, es_pair);
+ }
+ }
+
+ idx = 0;
+ printf("\n[ Hot streams in old perf data only ]\n");
+ for (i = 0; i < es_base->nr_streams; i++) {
+ base_stream = &es_base->streams[i];
+ if (!base_stream->pair_cnode) {
+ print_stream_callchain(base_stream, ++idx,
+ es_base, false);
+ }
+ }
+
+ idx = 0;
+ printf("\n[ Hot streams in new perf data only ]\n");
+ for (i = 0; i < es_pair->nr_streams; i++) {
+ base_stream = &es_pair->streams[i];
+ if (!base_stream->pair_cnode) {
+ print_stream_callchain(base_stream, ++idx,
+ es_pair, true);
+ }
+ }
+}
+
+void evsel_streams__report(struct evsel_streams *es_base,
+ struct evsel_streams *es_pair)
+{
+ return callchain_streams_report(es_base, es_pair);
+}
diff --git a/tools/perf/util/stream.h b/tools/perf/util/stream.h
new file mode 100644
index 000000000000..bee768874fea
--- /dev/null
+++ b/tools/perf/util/stream.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_STREAM_H
+#define __PERF_STREAM_H
+
+#include "callchain.h"
+
+struct stream {
+ struct callchain_node *cnode;
+ struct callchain_node *pair_cnode;
+};
+
+struct evsel_streams {
+ struct stream *streams;
+ int nr_streams_max;
+ int nr_streams;
+ int evsel_idx;
+ u64 streams_hits;
+};
+
+struct evlist_streams {
+ struct evsel_streams *ev_streams;
+ int nr_evsel;
+};
+
+struct evlist;
+
+void evlist_streams__delete(struct evlist_streams *els);
+
+struct evlist_streams *evlist__create_streams(struct evlist *evlist,
+ int nr_streams_max);
+
+struct evsel_streams *evsel_streams__entry(struct evlist_streams *els,
+ int evsel_idx);
+
+void evsel_streams__match(struct evsel_streams *es_base,
+ struct evsel_streams *es_pair);
+
+void evsel_streams__report(struct evsel_streams *es_base,
+ struct evsel_streams *es_pair);
+
+#endif /* __PERF_STREAM_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 8cc4b0059fb0..f3577f7d72fe 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -50,6 +50,10 @@ typedef Elf64_Nhdr GElf_Nhdr;
#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */
#endif
+#ifdef HAVE_LIBBFD_SUPPORT
+#define PACKAGE 'perf'
+#include <bfd.h>
+#else
#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
extern char *cplus_demangle(const char *, int);
@@ -65,9 +69,7 @@ static inline char *bfd_demangle(void __maybe_unused *v,
{
return NULL;
}
-#else
-#define PACKAGE 'perf'
-#include <bfd.h>
+#endif
#endif
#endif
@@ -530,8 +532,40 @@ out:
return err;
}
-int filename__read_build_id(const char *filename, void *bf, size_t size)
+#ifdef HAVE_LIBBFD_BUILDID_SUPPORT
+
+static int read_build_id(const char *filename, struct build_id *bid)
+{
+ size_t size = sizeof(bid->data);
+ int err = -1;
+ bfd *abfd;
+
+ abfd = bfd_openr(filename, NULL);
+ if (!abfd)
+ return -1;
+
+ if (!bfd_check_format(abfd, bfd_object)) {
+ pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename);
+ goto out_close;
+ }
+
+ if (!abfd->build_id || abfd->build_id->size > size)
+ goto out_close;
+
+ memcpy(bid->data, abfd->build_id->data, abfd->build_id->size);
+ memset(bid->data + abfd->build_id->size, 0, size - abfd->build_id->size);
+ err = bid->size = abfd->build_id->size;
+
+out_close:
+ bfd_close(abfd);
+ return err;
+}
+
+#else // HAVE_LIBBFD_BUILDID_SUPPORT
+
+static int read_build_id(const char *filename, struct build_id *bid)
{
+ size_t size = sizeof(bid->data);
int fd, err = -1;
Elf *elf;
@@ -548,7 +582,9 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
goto out_close;
}
- err = elf_read_build_id(elf, bf, size);
+ err = elf_read_build_id(elf, bid->data, size);
+ if (err > 0)
+ bid->size = err;
elf_end(elf);
out_close:
@@ -557,12 +593,45 @@ out:
return err;
}
-int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
+#endif // HAVE_LIBBFD_BUILDID_SUPPORT
+
+int filename__read_build_id(const char *filename, struct build_id *bid)
{
- int fd, err = -1;
+ struct kmod_path m = { .name = NULL, };
+ char path[PATH_MAX];
+ int err;
- if (size < BUILD_ID_SIZE)
- goto out;
+ if (!filename)
+ return -EFAULT;
+
+ err = kmod_path__parse(&m, filename);
+ if (err)
+ return -1;
+
+ if (m.comp) {
+ int error = 0, fd;
+
+ fd = filename__decompress(filename, path, sizeof(path), m.comp, &error);
+ if (fd < 0) {
+ pr_debug("Failed to decompress (error %d) %s\n",
+ error, filename);
+ return -1;
+ }
+ close(fd);
+ filename = path;
+ }
+
+ err = read_build_id(filename, bid);
+
+ if (m.comp)
+ unlink(filename);
+ return err;
+}
+
+int sysfs__read_build_id(const char *filename, struct build_id *bid)
+{
+ size_t size = sizeof(bid->data);
+ int fd, err = -1;
fd = open(filename, O_RDONLY);
if (fd < 0)
@@ -584,8 +653,9 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
break;
if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
size_t sz = min(descsz, size);
- if (read(fd, build_id, sz) == (ssize_t)sz) {
- memset(build_id + sz, 0, size - sz);
+ if (read(fd, bid->data, sz) == (ssize_t)sz) {
+ memset(bid->data + sz, 0, size - sz);
+ bid->size = sz;
err = 0;
break;
}
@@ -608,6 +678,44 @@ out:
return err;
}
+#ifdef HAVE_LIBBFD_SUPPORT
+
+int filename__read_debuglink(const char *filename, char *debuglink,
+ size_t size)
+{
+ int err = -1;
+ asection *section;
+ bfd *abfd;
+
+ abfd = bfd_openr(filename, NULL);
+ if (!abfd)
+ return -1;
+
+ if (!bfd_check_format(abfd, bfd_object)) {
+ pr_debug2("%s: cannot read %s bfd file.\n", __func__, filename);
+ goto out_close;
+ }
+
+ section = bfd_get_section_by_name(abfd, ".gnu_debuglink");
+ if (!section)
+ goto out_close;
+
+ if (section->size > size)
+ goto out_close;
+
+ if (!bfd_get_section_contents(abfd, section, debuglink, 0,
+ section->size))
+ goto out_close;
+
+ err = 0;
+
+out_close:
+ bfd_close(abfd);
+ return err;
+}
+
+#else
+
int filename__read_debuglink(const char *filename, char *debuglink,
size_t size)
{
@@ -660,6 +768,8 @@ out:
return err;
}
+#endif
+
static int dso__swap_init(struct dso *dso, unsigned char eidata)
{
static unsigned int const endian = 1;
@@ -757,13 +867,17 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
/* Always reject images with a mismatched build-id: */
if (dso->has_build_id && !symbol_conf.ignore_vmlinux_buildid) {
u8 build_id[BUILD_ID_SIZE];
+ struct build_id bid;
+ int size;
- if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) {
+ size = elf_read_build_id(elf, build_id, BUILD_ID_SIZE);
+ if (size <= 0) {
dso->load_errno = DSO_LOAD_ERRNO__CANNOT_READ_BUILDID;
goto out_elf_end;
}
- if (!dso__build_id_equal(dso, build_id)) {
+ build_id__init(&bid, build_id, size);
+ if (!dso__build_id_equal(dso, &bid)) {
pr_debug("%s: build id mismatch for %s.\n", __func__, name);
dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
goto out_elf_end;
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index d6e99af263ec..f9eb0bee7f15 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -31,9 +31,10 @@ static bool check_need_swap(int file_endian)
#define NT_GNU_BUILD_ID 3
-static int read_build_id(void *note_data, size_t note_len, void *bf,
- size_t size, bool need_swap)
+static int read_build_id(void *note_data, size_t note_len, struct build_id *bid,
+ bool need_swap)
{
+ size_t size = sizeof(bid->data);
struct {
u32 n_namesz;
u32 n_descsz;
@@ -63,8 +64,9 @@ static int read_build_id(void *note_data, size_t note_len, void *bf,
nhdr->n_namesz == sizeof("GNU")) {
if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
size_t sz = min(size, descsz);
- memcpy(bf, ptr, sz);
- memset(bf + sz, 0, size - sz);
+ memcpy(bid->data, ptr, sz);
+ memset(bid->data + sz, 0, size - sz);
+ bid->size = sz;
return 0;
}
}
@@ -84,7 +86,7 @@ int filename__read_debuglink(const char *filename __maybe_unused,
/*
* Just try PT_NOTE header otherwise fails
*/
-int filename__read_build_id(const char *filename, void *bf, size_t size)
+int filename__read_build_id(const char *filename, struct build_id *bid)
{
FILE *fp;
int ret = -1;
@@ -156,9 +158,9 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
if (fread(buf, buf_size, 1, fp) != 1)
goto out_free;
- ret = read_build_id(buf, buf_size, bf, size, need_swap);
+ ret = read_build_id(buf, buf_size, bid, need_swap);
if (ret == 0)
- ret = size;
+ ret = bid->size;
break;
}
} else {
@@ -207,9 +209,9 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
if (fread(buf, buf_size, 1, fp) != 1)
goto out_free;
- ret = read_build_id(buf, buf_size, bf, size, need_swap);
+ ret = read_build_id(buf, buf_size, bid, need_swap);
if (ret == 0)
- ret = size;
+ ret = bid->size;
break;
}
}
@@ -220,7 +222,7 @@ out:
return ret;
}
-int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
+int sysfs__read_build_id(const char *filename, struct build_id *bid)
{
int fd;
int ret = -1;
@@ -243,7 +245,7 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
if (read(fd, buf, buf_size) != (ssize_t) buf_size)
goto out_free;
- ret = read_build_id(buf, buf_size, build_id, size, false);
+ ret = read_build_id(buf, buf_size, bid, false);
out_free:
free(buf);
out:
@@ -339,16 +341,15 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
struct symsrc *runtime_ss __maybe_unused,
int kmodule __maybe_unused)
{
- unsigned char build_id[BUILD_ID_SIZE];
+ struct build_id bid;
int ret;
ret = fd__is_64_bit(ss->fd);
if (ret >= 0)
dso->is_64_bit = ret;
- if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
- dso__set_build_id(dso, build_id);
- }
+ if (filename__read_build_id(ss->name, &bid) > 0)
+ dso__set_build_id(dso, &bid);
return 0;
}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 5151a8c0b791..64a039cbba1b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -515,6 +515,13 @@ void dso__insert_symbol(struct dso *dso, struct symbol *sym)
}
}
+void dso__delete_symbol(struct dso *dso, struct symbol *sym)
+{
+ rb_erase_cached(&sym->rb_node, &dso->symbols);
+ symbol__delete(sym);
+ dso__reset_find_symbol_cache(dso);
+}
+
struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
{
if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
@@ -1526,6 +1533,138 @@ out_failure:
return -1;
}
+#ifdef HAVE_LIBBFD_SUPPORT
+#define PACKAGE 'perf'
+#include <bfd.h>
+
+static int bfd_symbols__cmpvalue(const void *a, const void *b)
+{
+ const asymbol *as = *(const asymbol **)a, *bs = *(const asymbol **)b;
+
+ if (bfd_asymbol_value(as) != bfd_asymbol_value(bs))
+ return bfd_asymbol_value(as) - bfd_asymbol_value(bs);
+
+ return bfd_asymbol_name(as)[0] - bfd_asymbol_name(bs)[0];
+}
+
+static int bfd2elf_binding(asymbol *symbol)
+{
+ if (symbol->flags & BSF_WEAK)
+ return STB_WEAK;
+ if (symbol->flags & BSF_GLOBAL)
+ return STB_GLOBAL;
+ if (symbol->flags & BSF_LOCAL)
+ return STB_LOCAL;
+ return -1;
+}
+
+int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
+{
+ int err = -1;
+ long symbols_size, symbols_count;
+ asection *section;
+ asymbol **symbols, *sym;
+ struct symbol *symbol;
+ bfd *abfd;
+ u_int i;
+ u64 start, len;
+
+ abfd = bfd_openr(dso->long_name, NULL);
+ if (!abfd)
+ return -1;
+
+ if (!bfd_check_format(abfd, bfd_object)) {
+ pr_debug2("%s: cannot read %s bfd file.\n", __func__,
+ dso->long_name);
+ goto out_close;
+ }
+
+ if (bfd_get_flavour(abfd) == bfd_target_elf_flavour)
+ goto out_close;
+
+ section = bfd_get_section_by_name(abfd, ".text");
+ if (section)
+ dso->text_offset = section->vma - section->filepos;
+
+ bfd_close(abfd);
+
+ abfd = bfd_openr(debugfile, NULL);
+ if (!abfd)
+ return -1;
+
+ if (!bfd_check_format(abfd, bfd_object)) {
+ pr_debug2("%s: cannot read %s bfd file.\n", __func__,
+ debugfile);
+ goto out_close;
+ }
+
+ if (bfd_get_flavour(abfd) == bfd_target_elf_flavour)
+ goto out_close;
+
+ symbols_size = bfd_get_symtab_upper_bound(abfd);
+ if (symbols_size == 0) {
+ bfd_close(abfd);
+ return 0;
+ }
+
+ if (symbols_size < 0)
+ goto out_close;
+
+ symbols = malloc(symbols_size);
+ if (!symbols)
+ goto out_close;
+
+ symbols_count = bfd_canonicalize_symtab(abfd, symbols);
+ if (symbols_count < 0)
+ goto out_free;
+
+ qsort(symbols, symbols_count, sizeof(asymbol *), bfd_symbols__cmpvalue);
+
+#ifdef bfd_get_section
+#define bfd_asymbol_section bfd_get_section
+#endif
+ for (i = 0; i < symbols_count; ++i) {
+ sym = symbols[i];
+ section = bfd_asymbol_section(sym);
+ if (bfd2elf_binding(sym) < 0)
+ continue;
+
+ while (i + 1 < symbols_count &&
+ bfd_asymbol_section(symbols[i + 1]) == section &&
+ bfd2elf_binding(symbols[i + 1]) < 0)
+ i++;
+
+ if (i + 1 < symbols_count &&
+ bfd_asymbol_section(symbols[i + 1]) == section)
+ len = symbols[i + 1]->value - sym->value;
+ else
+ len = section->size - sym->value;
+
+ start = bfd_asymbol_value(sym) - dso->text_offset;
+ symbol = symbol__new(start, len, bfd2elf_binding(sym), STT_FUNC,
+ bfd_asymbol_name(sym));
+ if (!symbol)
+ goto out_free;
+
+ symbols__insert(&dso->symbols, symbol);
+ }
+#ifdef bfd_get_section
+#undef bfd_asymbol_section
+#endif
+
+ symbols__fixup_end(&dso->symbols);
+ symbols__fixup_duplicate(&dso->symbols);
+ dso->adjust_symbols = 1;
+
+ err = 0;
+out_free:
+ free(symbols);
+out_close:
+ bfd_close(abfd);
+ return err;
+}
+#endif
+
static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
enum dso_binary_type type)
{
@@ -1623,7 +1762,7 @@ int dso__load(struct dso *dso, struct map *map)
struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
bool kmod;
bool perfmap;
- unsigned char build_id[BUILD_ID_SIZE];
+ struct build_id bid;
struct nscookie nsc;
char newmapname[PATH_MAX];
const char *map_path = dso->long_name;
@@ -1685,8 +1824,8 @@ int dso__load(struct dso *dso, struct map *map)
if (!dso->has_build_id &&
is_regular_file(dso->long_name)) {
__symbol__join_symfs(name, PATH_MAX, dso->long_name);
- if (filename__read_build_id(name, build_id, BUILD_ID_SIZE) > 0)
- dso__set_build_id(dso, build_id);
+ if (filename__read_build_id(name, &bid) > 0)
+ dso__set_build_id(dso, &bid);
}
/*
@@ -1699,6 +1838,7 @@ int dso__load(struct dso *dso, struct map *map)
bool next_slot = false;
bool is_reg;
bool nsexit;
+ int bfdrc = -1;
int sirc = -1;
enum dso_binary_type symtab_type = binary_type_symtab[i];
@@ -1717,12 +1857,19 @@ int dso__load(struct dso *dso, struct map *map)
nsinfo__mountns_exit(&nsc);
is_reg = is_regular_file(name);
+#ifdef HAVE_LIBBFD_SUPPORT
if (is_reg)
+ bfdrc = dso__load_bfd_symbols(dso, name);
+#endif
+ if (is_reg && bfdrc < 0)
sirc = symsrc__init(ss, dso, name, symtab_type);
if (nsexit)
nsinfo__mountns_enter(dso->nsinfo, &nsc);
+ if (bfdrc == 0)
+ break;
+
if (!is_reg || sirc < 0)
continue;
@@ -1982,7 +2129,7 @@ static bool filename__readable(const char *file)
static char *dso__find_kallsyms(struct dso *dso, struct map *map)
{
- u8 host_build_id[BUILD_ID_SIZE];
+ struct build_id bid;
char sbuild_id[SBUILD_ID_SIZE];
bool is_host = false;
char path[PATH_MAX];
@@ -1995,9 +2142,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
goto proc_kallsyms;
}
- if (sysfs__read_build_id("/sys/kernel/notes", host_build_id,
- sizeof(host_build_id)) == 0)
- is_host = dso__build_id_equal(dso, host_build_id);
+ if (sysfs__read_build_id("/sys/kernel/notes", &bid) == 0)
+ is_host = dso__build_id_equal(dso, &bid);
/* Try a fast path for /proc/kallsyms if possible */
if (is_host) {
@@ -2013,7 +2159,7 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
goto proc_kallsyms;
}
- build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+ build_id__sprintf(&dso->bid, sbuild_id);
/* Find kallsyms in build-id cache with kcore */
scnprintf(path, sizeof(path), "%s/%s/%s",
@@ -2043,6 +2189,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map)
int err;
const char *kallsyms_filename = NULL;
char *kallsyms_allocated_filename = NULL;
+ char *filename = NULL;
+
/*
* Step 1: if the user specified a kallsyms or vmlinux filename, use
* it and only it, reporting errors to the user if it cannot be used.
@@ -2067,6 +2215,20 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map)
return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, false);
}
+ /*
+ * Before checking on common vmlinux locations, check if it's
+ * stored as standard build id binary (not kallsyms) under
+ * .debug cache.
+ */
+ if (!symbol_conf.ignore_vmlinux_buildid)
+ filename = __dso__build_id_filename(dso, NULL, 0, false, false);
+ if (filename != NULL) {
+ err = dso__load_vmlinux(dso, map, filename, true);
+ if (err > 0)
+ return err;
+ free(filename);
+ }
+
if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
err = dso__load_vmlinux_path(dso, map);
if (err > 0)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ff4f4c47e148..954d6a049ee2 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -23,12 +23,13 @@ struct dso;
struct map;
struct maps;
struct option;
+struct build_id;
/*
* libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
* for newer versions we can use mmap to reduce memory usage:
*/
-#ifdef HAVE_LIBELF_MMAP_SUPPORT
+#ifdef ELF_C_READ_MMAP
# define PERF_ELF_C_READ_MMAP ELF_C_READ_MMAP
#else
# define PERF_ELF_C_READ_MMAP ELF_C_READ
@@ -130,6 +131,8 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
void dso__insert_symbol(struct dso *dso,
struct symbol *sym);
+void dso__delete_symbol(struct dso *dso,
+ struct symbol *sym);
struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
@@ -142,8 +145,8 @@ struct symbol *dso__next_symbol(struct symbol *sym);
enum dso_type dso__type_fd(int fd);
-int filename__read_build_id(const char *filename, void *bf, size_t size);
-int sysfs__read_build_id(const char *filename, void *bf, size_t size);
+int filename__read_build_id(const char *filename, struct build_id *id);
+int sysfs__read_build_id(const char *filename, struct build_id *bid);
int modules__parse(const char *filename, void *arg,
int (*process_module)(void *arg, const char *name,
u64 start, u64 size));
@@ -175,6 +178,10 @@ int symbol__config_symfs(const struct option *opt __maybe_unused,
struct symsrc;
+#ifdef HAVE_LIBBFD_SUPPORT
+int dso__load_bfd_symbols(struct dso *dso, const char *debugfile);
+#endif
+
int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
struct symsrc *runtime_ss, int kmodule);
int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss);
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 89b390623b63..2947e3f3c6d9 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -563,6 +563,9 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool,
char cgrp_root[PATH_MAX];
size_t mount_len; /* length of mount point in the path */
+ if (!tool || !tool->cgroup_events)
+ return 0;
+
if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) {
pr_debug("cannot find cgroup mount point\n");
return -1;
@@ -1406,6 +1409,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
if (type & PERF_SAMPLE_CGROUP)
result += sizeof(u64);
+ if (type & PERF_SAMPLE_DATA_PAGE_SIZE)
+ result += sizeof(u64);
+
if (type & PERF_SAMPLE_AUX) {
result += sizeof(u64);
result += sample->aux_sample.size;
@@ -1585,6 +1591,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
array++;
}
+ if (type & PERF_SAMPLE_DATA_PAGE_SIZE) {
+ *array = sample->data_page_size;
+ array++;
+ }
+
if (type & PERF_SAMPLE_AUX) {
sz = sample->aux_sample.size;
*array++ = sz;
@@ -1640,7 +1651,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_
e->id = evsel->core.id[j];
- sid = perf_evlist__id2sid(evlist, e->id);
+ sid = evlist__id2sid(evlist, e->id);
if (!sid) {
free(ev);
return -ENOENT;
@@ -1961,7 +1972,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16
len = pos->long_name_len + 1;
len = PERF_ALIGN(len, NAME_ALIGN);
- memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
+ memcpy(&ev.build_id.build_id, pos->bid.data, sizeof(pos->bid.data));
ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
ev.build_id.header.misc = misc;
ev.build_id.pid = machine->pid;
@@ -2006,14 +2017,6 @@ int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct p
return 0;
}
-int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
- struct perf_tool *tool __maybe_unused,
- perf_event__handler_t process __maybe_unused,
- struct machine *machine __maybe_unused)
-{
- return 0;
-}
-
extern const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE];
int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session,
diff --git a/tools/perf/util/topdown.c b/tools/perf/util/topdown.c
new file mode 100644
index 000000000000..1081b20f9891
--- /dev/null
+++ b/tools/perf/util/topdown.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include "pmu.h"
+#include "topdown.h"
+
+int topdown_filter_events(const char **attr, char **str, bool use_group)
+{
+ int off = 0;
+ int i;
+ int len = 0;
+ char *s;
+
+ for (i = 0; attr[i]; i++) {
+ if (pmu_have_event("cpu", attr[i])) {
+ len += strlen(attr[i]) + 1;
+ attr[i - off] = attr[i];
+ } else
+ off++;
+ }
+ attr[i - off] = NULL;
+
+ *str = malloc(len + 1 + 2);
+ if (!*str)
+ return -1;
+ s = *str;
+ if (i - off == 0) {
+ *s = 0;
+ return 0;
+ }
+ if (use_group)
+ *s++ = '{';
+ for (i = 0; attr[i]; i++) {
+ strcpy(s, attr[i]);
+ s += strlen(s);
+ *s++ = ',';
+ }
+ if (use_group) {
+ s[-1] = '}';
+ *s = 0;
+ } else
+ s[-1] = 0;
+ return 0;
+}
+
+__weak bool arch_topdown_check_group(bool *warn)
+{
+ *warn = false;
+ return false;
+}
+
+__weak void arch_topdown_group_warn(void)
+{
+}
+
+__weak bool arch_topdown_sample_read(struct evsel *leader __maybe_unused)
+{
+ return false;
+}
diff --git a/tools/perf/util/topdown.h b/tools/perf/util/topdown.h
new file mode 100644
index 000000000000..2f0d0b887639
--- /dev/null
+++ b/tools/perf/util/topdown.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef TOPDOWN_H
+#define TOPDOWN_H 1
+#include "evsel.h"
+
+bool arch_topdown_check_group(bool *warn);
+void arch_topdown_group_warn(void);
+bool arch_topdown_sample_read(struct evsel *leader);
+
+int topdown_filter_events(const char **attr, char **str, bool use_group);
+
+#endif
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index bfa782421cbd..62b4c75c966c 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -1,7 +1,16 @@
// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+
#include <linux/compiler.h>
+#include <linux/perf_event.h>
+#include <linux/stddef.h>
#include <linux/types.h>
+#include <asm/barrier.h>
+
+#include "event.h"
+#include "synthetic-events.h"
+#include "debug.h"
#include "tsc.h"
u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
@@ -19,12 +28,84 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
{
u64 quot, rem;
+ if (tc->cap_user_time_short)
+ cyc = tc->time_cycles +
+ ((cyc - tc->time_cycles) & tc->time_mask);
+
quot = cyc >> tc->time_shift;
rem = cyc & (((u64)1 << tc->time_shift) - 1);
return tc->time_zero + quot * tc->time_mult +
((rem * tc->time_mult) >> tc->time_shift);
}
+int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
+ struct perf_tsc_conversion *tc)
+{
+ u32 seq;
+ int i = 0;
+
+ while (1) {
+ seq = pc->lock;
+ rmb();
+ tc->time_mult = pc->time_mult;
+ tc->time_shift = pc->time_shift;
+ tc->time_zero = pc->time_zero;
+ tc->time_cycles = pc->time_cycles;
+ tc->time_mask = pc->time_mask;
+ tc->cap_user_time_zero = pc->cap_user_time_zero;
+ tc->cap_user_time_short = pc->cap_user_time_short;
+ rmb();
+ if (pc->lock == seq && !(seq & 1))
+ break;
+ if (++i > 10000) {
+ pr_debug("failed to get perf_event_mmap_page lock\n");
+ return -EINVAL;
+ }
+ }
+
+ if (!tc->cap_user_time_zero)
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc,
+ struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine)
+{
+ union perf_event event = {
+ .time_conv = {
+ .header = {
+ .type = PERF_RECORD_TIME_CONV,
+ .size = sizeof(struct perf_record_time_conv),
+ },
+ },
+ };
+ struct perf_tsc_conversion tc;
+ int err;
+
+ if (!pc)
+ return 0;
+ err = perf_read_tsc_conversion(pc, &tc);
+ if (err == -EOPNOTSUPP)
+ return 0;
+ if (err)
+ return err;
+
+ pr_debug2("Synthesizing TSC conversion information\n");
+
+ event.time_conv.time_mult = tc.time_mult;
+ event.time_conv.time_shift = tc.time_shift;
+ event.time_conv.time_zero = tc.time_zero;
+ event.time_conv.time_cycles = tc.time_cycles;
+ event.time_conv.time_mask = tc.time_mask;
+ event.time_conv.cap_user_time_zero = tc.cap_user_time_zero;
+ event.time_conv.cap_user_time_short = tc.cap_user_time_short;
+
+ return process(tool, &event, NULL, machine);
+}
+
u64 __weak rdtsc(void)
{
return 0;
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
index 3c5a632ee57c..72a15419f3b3 100644
--- a/tools/perf/util/tsc.h
+++ b/tools/perf/util/tsc.h
@@ -8,6 +8,11 @@ struct perf_tsc_conversion {
u16 time_shift;
u32 time_mult;
u64 time_zero;
+ u64 time_cycles;
+ u64 time_mask;
+
+ bool cap_user_time_zero;
+ bool cap_user_time_short;
};
struct perf_event_mmap_page;
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7a3dbc259cec..0ada907c60d4 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -20,10 +20,24 @@
static char *debuginfo_path;
+static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
+ const char *modname __maybe_unused, Dwarf_Addr base __maybe_unused,
+ const char *file_name, const char *debuglink_file __maybe_unused,
+ GElf_Word debuglink_crc __maybe_unused, char **debuginfo_file_name)
+{
+ const struct dso *dso = *userdata;
+
+ assert(dso);
+ if (dso->symsrc_filename && strcmp (file_name, dso->symsrc_filename))
+ *debuginfo_file_name = strdup(dso->symsrc_filename);
+ return -1;
+}
+
static const Dwfl_Callbacks offline_callbacks = {
- .find_debuginfo = dwfl_standard_find_debuginfo,
+ .find_debuginfo = __find_debuginfo,
.debuginfo_path = &debuginfo_path,
.section_address = dwfl_offline_section_address,
+ // .find_elf is not set as we use dwfl_report_elf() instead.
};
static int __report_module(struct addr_location *al, u64 ip,
@@ -46,16 +60,24 @@ static int __report_module(struct addr_location *al, u64 ip,
mod = dwfl_addrmodule(ui->dwfl, ip);
if (mod) {
Dwarf_Addr s;
+ void **userdatap;
- dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
+ dwfl_module_info(mod, &userdatap, &s, NULL, NULL, NULL, NULL, NULL);
+ *userdatap = dso;
if (s != al->map->start - al->map->pgoff)
mod = 0;
}
if (!mod)
- mod = dwfl_report_elf(ui->dwfl, dso->short_name,
- (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
- false);
+ mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1,
+ al->map->start - al->map->pgoff, false);
+ if (!mod) {
+ char filename[PATH_MAX];
+
+ if (dso__build_id_filename(dso, filename, sizeof(filename), false))
+ mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
+ al->map->start - al->map->pgoff, false);
+ }
return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index f486fdd3a538..ad737052e597 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -62,4 +62,10 @@ char *perf_exe(char *buf, int len);
#endif
#endif
+extern bool test_attr__enabled;
+void test_attr__ready(void);
+void test_attr__init(void);
+struct perf_event_attr;
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+ int fd, int group_fd, unsigned long flags);
#endif /* GIT_COMPAT_UTIL_H */