Adding upstream version 6.6.15.upstream/6.6.15

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 1087 insertions, 0 deletions

diff --git a/tools/perf/util/arm-spe-decoder/Build b/tools/perf/util/arm-spe-decoder/Build
new file mode 100644
index 0000000000..f8dae13fc8
--- /dev/null
+++ b/tools/perf/util/arm-spe-decoder/Build
@@ -0,0 +1 @@
+perf-$(CONFIG_AUXTRACE) += arm-spe-pkt-decoder.o arm-spe-decoder.o
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
new file mode 100644
index 0000000000..ba807071d3
--- /dev/null
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -0,0 +1,267 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * arm_spe_decoder.c: ARM SPE support
+ */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <errno.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <string.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/zalloc.h>
+
+#include "../auxtrace.h"
+#include "../debug.h"
+#include "../util.h"
+
+#include "arm-spe-decoder.h"
+
+static u64 arm_spe_calc_ip(int index, u64 payload)
+{
+	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 = 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))
+			payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT;
+
+	/* Data access virtual address */
+	} else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT) {
+
+		/* 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/arch/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) {
+		/* Clean highest byte */
+		payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
+	} else {
+		static u32 seen_idx = 0;
+		if (!(seen_idx & BIT(index))) {
+			seen_idx |= BIT(index);
+			pr_warning("ignoring unsupported address packet index: 0x%x\n", index);
+		}
+	}
+
+	return payload;
+}
+
+struct arm_spe_decoder *arm_spe_decoder_new(struct arm_spe_params *params)
+{
+	struct arm_spe_decoder *decoder;
+
+	if (!params->get_trace)
+		return NULL;
+
+	decoder = zalloc(sizeof(struct arm_spe_decoder));
+	if (!decoder)
+		return NULL;
+
+	decoder->get_trace = params->get_trace;
+	decoder->data = params->data;
+
+	return decoder;
+}
+
+void arm_spe_decoder_free(struct arm_spe_decoder *decoder)
+{
+	free(decoder);
+}
+
+static int arm_spe_get_data(struct arm_spe_decoder *decoder)
+{
+	struct arm_spe_buffer buffer = { .buf = 0, };
+	int ret;
+
+	pr_debug("Getting more data\n");
+	ret = decoder->get_trace(&buffer, decoder->data);
+	if (ret < 0)
+		return ret;
+
+	decoder->buf = buffer.buf;
+	decoder->len = buffer.len;
+
+	if (!decoder->len)
+		pr_debug("No more data\n");
+
+	return decoder->len;
+}
+
+static int arm_spe_get_next_packet(struct arm_spe_decoder *decoder)
+{
+	int ret;
+
+	do {
+		if (!decoder->len) {
+			ret = arm_spe_get_data(decoder);
+
+			/* Failed to read out trace data */
+			if (ret <= 0)
+				return ret;
+		}
+
+		ret = arm_spe_get_packet(decoder->buf, decoder->len,
+					 &decoder->packet);
+		if (ret <= 0) {
+			/* Move forward for 1 byte */
+			decoder->buf += 1;
+			decoder->len -= 1;
+			return -EBADMSG;
+		}
+
+		decoder->buf += ret;
+		decoder->len -= ret;
+	} while (decoder->packet.type == ARM_SPE_PAD);
+
+	return 1;
+}
+
+static int arm_spe_read_record(struct arm_spe_decoder *decoder)
+{
+	int err;
+	int idx;
+	u64 payload, ip;
+
+	memset(&decoder->record, 0x0, sizeof(decoder->record));
+	decoder->record.context_id = (u64)-1;
+
+	while (1) {
+		err = arm_spe_get_next_packet(decoder);
+		if (err <= 0)
+			return err;
+
+		idx = decoder->packet.index;
+		payload = decoder->packet.payload;
+
+		switch (decoder->packet.type) {
+		case ARM_SPE_TIMESTAMP:
+			decoder->record.timestamp = payload;
+			return 1;
+		case ARM_SPE_END:
+			return 1;
+		case ARM_SPE_ADDRESS:
+			ip = arm_spe_calc_ip(idx, payload);
+			if (idx == SPE_ADDR_PKT_HDR_INDEX_INS)
+				decoder->record.from_ip = ip;
+			else if (idx == SPE_ADDR_PKT_HDR_INDEX_BRANCH)
+				decoder->record.to_ip = ip;
+			else if (idx == SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT)
+				decoder->record.virt_addr = ip;
+			else if (idx == SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS)
+				decoder->record.phys_addr = ip;
+			break;
+		case ARM_SPE_COUNTER:
+			if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT)
+				decoder->record.latency = payload;
+			break;
+		case ARM_SPE_CONTEXT:
+			decoder->record.context_id = payload;
+			break;
+		case ARM_SPE_OP_TYPE:
+			switch (idx) {
+			case SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC:
+				decoder->record.op |= ARM_SPE_OP_LDST;
+				if (payload & SPE_OP_PKT_ST)
+					decoder->record.op |= ARM_SPE_OP_ST;
+				else
+					decoder->record.op |= ARM_SPE_OP_LD;
+				if (SPE_OP_PKT_IS_LDST_SVE(payload))
+					decoder->record.op |= ARM_SPE_OP_SVE_LDST;
+				break;
+			case SPE_OP_PKT_HDR_CLASS_OTHER:
+				decoder->record.op |= ARM_SPE_OP_OTHER;
+				if (SPE_OP_PKT_IS_OTHER_SVE_OP(payload))
+					decoder->record.op |= ARM_SPE_OP_SVE_OTHER;
+				break;
+			case SPE_OP_PKT_HDR_CLASS_BR_ERET:
+				decoder->record.op |= ARM_SPE_OP_BRANCH_ERET;
+				break;
+			default:
+				pr_err("Get packet error!\n");
+				return -1;
+			}
+			break;
+		case ARM_SPE_EVENTS:
+			if (payload & BIT(EV_L1D_REFILL))
+				decoder->record.type |= ARM_SPE_L1D_MISS;
+
+			if (payload & BIT(EV_L1D_ACCESS))
+				decoder->record.type |= ARM_SPE_L1D_ACCESS;
+
+			if (payload & BIT(EV_TLB_WALK))
+				decoder->record.type |= ARM_SPE_TLB_MISS;
+
+			if (payload & BIT(EV_TLB_ACCESS))
+				decoder->record.type |= ARM_SPE_TLB_ACCESS;
+
+			if (payload & BIT(EV_LLC_MISS))
+				decoder->record.type |= ARM_SPE_LLC_MISS;
+
+			if (payload & BIT(EV_LLC_ACCESS))
+				decoder->record.type |= ARM_SPE_LLC_ACCESS;
+
+			if (payload & BIT(EV_REMOTE_ACCESS))
+				decoder->record.type |= ARM_SPE_REMOTE_ACCESS;
+
+			if (payload & BIT(EV_MISPRED))
+				decoder->record.type |= ARM_SPE_BRANCH_MISS;
+
+			if (payload & BIT(EV_PARTIAL_PREDICATE))
+				decoder->record.type |= ARM_SPE_SVE_PARTIAL_PRED;
+
+			if (payload & BIT(EV_EMPTY_PREDICATE))
+				decoder->record.type |= ARM_SPE_SVE_EMPTY_PRED;
+
+			break;
+		case ARM_SPE_DATA_SOURCE:
+			decoder->record.source = payload;
+			break;
+		case ARM_SPE_BAD:
+			break;
+		case ARM_SPE_PAD:
+			break;
+		default:
+			pr_err("Get packet error!\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+int arm_spe_decode(struct arm_spe_decoder *decoder)
+{
+	return arm_spe_read_record(decoder);
+}
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
new file mode 100644
index 0000000000..1443c28545
--- /dev/null
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * arm_spe_decoder.h: Arm Statistical Profiling Extensions support
+ * Copyright (c) 2019-2020, Arm Ltd.
+ */
+
+#ifndef INCLUDE__ARM_SPE_DECODER_H__
+#define INCLUDE__ARM_SPE_DECODER_H__
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+
+#include "arm-spe-pkt-decoder.h"
+
+enum arm_spe_sample_type {
+	ARM_SPE_L1D_ACCESS		= 1 << 0,
+	ARM_SPE_L1D_MISS		= 1 << 1,
+	ARM_SPE_LLC_ACCESS		= 1 << 2,
+	ARM_SPE_LLC_MISS		= 1 << 3,
+	ARM_SPE_TLB_ACCESS		= 1 << 4,
+	ARM_SPE_TLB_MISS		= 1 << 5,
+	ARM_SPE_BRANCH_MISS		= 1 << 6,
+	ARM_SPE_REMOTE_ACCESS		= 1 << 7,
+	ARM_SPE_SVE_PARTIAL_PRED	= 1 << 8,
+	ARM_SPE_SVE_EMPTY_PRED		= 1 << 9,
+};
+
+enum arm_spe_op_type {
+	/* First level operation type */
+	ARM_SPE_OP_OTHER	= 1 << 0,
+	ARM_SPE_OP_LDST		= 1 << 1,
+	ARM_SPE_OP_BRANCH_ERET	= 1 << 2,
+
+	/* Second level operation type for OTHER */
+	ARM_SPE_OP_SVE_OTHER		= 1 << 16,
+	ARM_SPE_OP_SVE_FP		= 1 << 17,
+	ARM_SPE_OP_SVE_PRED_OTHER	= 1 << 18,
+
+	/* Second level operation type for LDST */
+	ARM_SPE_OP_LD			= 1 << 16,
+	ARM_SPE_OP_ST			= 1 << 17,
+	ARM_SPE_OP_ATOMIC		= 1 << 18,
+	ARM_SPE_OP_EXCL			= 1 << 19,
+	ARM_SPE_OP_AR			= 1 << 20,
+	ARM_SPE_OP_SIMD_FP		= 1 << 21,
+	ARM_SPE_OP_GP_REG		= 1 << 22,
+	ARM_SPE_OP_UNSPEC_REG		= 1 << 23,
+	ARM_SPE_OP_NV_SYSREG		= 1 << 24,
+	ARM_SPE_OP_SVE_LDST		= 1 << 25,
+	ARM_SPE_OP_SVE_PRED_LDST	= 1 << 26,
+	ARM_SPE_OP_SVE_SG		= 1 << 27,
+
+	/* Second level operation type for BRANCH_ERET */
+	ARM_SPE_OP_BR_COND	= 1 << 16,
+	ARM_SPE_OP_BR_INDIRECT	= 1 << 17,
+};
+
+enum arm_spe_neoverse_data_source {
+	ARM_SPE_NV_L1D		 = 0x0,
+	ARM_SPE_NV_L2		 = 0x8,
+	ARM_SPE_NV_PEER_CORE	 = 0x9,
+	ARM_SPE_NV_LOCAL_CLUSTER = 0xa,
+	ARM_SPE_NV_SYS_CACHE	 = 0xb,
+	ARM_SPE_NV_PEER_CLUSTER	 = 0xc,
+	ARM_SPE_NV_REMOTE	 = 0xd,
+	ARM_SPE_NV_DRAM		 = 0xe,
+};
+
+struct arm_spe_record {
+	enum arm_spe_sample_type type;
+	int err;
+	u32 op;
+	u32 latency;
+	u64 from_ip;
+	u64 to_ip;
+	u64 timestamp;
+	u64 virt_addr;
+	u64 phys_addr;
+	u64 context_id;
+	u16 source;
+};
+
+struct arm_spe_insn;
+
+struct arm_spe_buffer {
+	const unsigned char *buf;
+	size_t len;
+	u64 offset;
+	u64 trace_nr;
+};
+
+struct arm_spe_params {
+	int (*get_trace)(struct arm_spe_buffer *buffer, void *data);
+	void *data;
+};
+
+struct arm_spe_decoder {
+	int (*get_trace)(struct arm_spe_buffer *buffer, void *data);
+	void *data;
+	struct arm_spe_record record;
+
+	const unsigned char *buf;
+	size_t len;
+
+	struct arm_spe_pkt packet;
+};
+
+struct arm_spe_decoder *arm_spe_decoder_new(struct arm_spe_params *params);
+void arm_spe_decoder_free(struct arm_spe_decoder *decoder);
+
+int arm_spe_decode(struct arm_spe_decoder *decoder);
+
+#endif
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
new file mode 100644
index 0000000000..a454c67375
--- /dev/null
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
@@ -0,0 +1,546 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+#include <linux/bitops.h>
+#include <stdarg.h>
+
+#include "arm-spe-pkt-decoder.h"
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#define le16_to_cpu bswap_16
+#define le32_to_cpu bswap_32
+#define le64_to_cpu bswap_64
+#define memcpy_le64(d, s, n) do { \
+	memcpy((d), (s), (n));    \
+	*(d) = le64_to_cpu(*(d)); \
+} while (0)
+#else
+#define le16_to_cpu
+#define le32_to_cpu
+#define le64_to_cpu
+#define memcpy_le64 memcpy
+#endif
+
+static const char * const arm_spe_packet_name[] = {
+	[ARM_SPE_PAD]		= "PAD",
+	[ARM_SPE_END]		= "END",
+	[ARM_SPE_TIMESTAMP]	= "TS",
+	[ARM_SPE_ADDRESS]	= "ADDR",
+	[ARM_SPE_COUNTER]	= "LAT",
+	[ARM_SPE_CONTEXT]	= "CONTEXT",
+	[ARM_SPE_OP_TYPE]	= "OP-TYPE",
+	[ARM_SPE_EVENTS]	= "EVENTS",
+	[ARM_SPE_DATA_SOURCE]	= "DATA-SOURCE",
+};
+
+const char *arm_spe_pkt_name(enum arm_spe_pkt_type type)
+{
+	return arm_spe_packet_name[type];
+}
+
+/*
+ * Extracts the field "sz" from header bits and converts to bytes:
+ *   00 : byte (1)
+ *   01 : halfword (2)
+ *   10 : word (4)
+ *   11 : doubleword (8)
+ */
+static unsigned int arm_spe_payload_len(unsigned char hdr)
+{
+	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 = arm_spe_payload_len(buf[ext_hdr]);
+
+	if (len < 1 + ext_hdr + payload_len)
+		return ARM_SPE_NEED_MORE_BYTES;
+
+	buf += 1 + ext_hdr;
+
+	switch (payload_len) {
+	case 1: packet->payload = *(uint8_t *)buf; break;
+	case 2: packet->payload = le16_to_cpu(*(uint16_t *)buf); break;
+	case 4: packet->payload = le32_to_cpu(*(uint32_t *)buf); break;
+	case 8: packet->payload = le64_to_cpu(*(uint64_t *)buf); break;
+	default: return ARM_SPE_BAD_PACKET;
+	}
+
+	return 1 + ext_hdr + payload_len;
+}
+
+static int arm_spe_get_pad(struct arm_spe_pkt *packet)
+{
+	packet->type = ARM_SPE_PAD;
+	return 1;
+}
+
+static int arm_spe_get_alignment(const unsigned char *buf, size_t len,
+				 struct arm_spe_pkt *packet)
+{
+	unsigned int alignment = 1 << ((buf[0] & 0xf) + 1);
+
+	if (len < alignment)
+		return ARM_SPE_NEED_MORE_BYTES;
+
+	packet->type = ARM_SPE_PAD;
+	return alignment - (((uintptr_t)buf) & (alignment - 1));
+}
+
+static int arm_spe_get_end(struct arm_spe_pkt *packet)
+{
+	packet->type = ARM_SPE_END;
+	return 1;
+}
+
+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, 0, packet);
+}
+
+static int arm_spe_get_events(const unsigned char *buf, size_t len,
+			      struct arm_spe_pkt *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 if
+	 * index > 1.
+	 */
+	packet->index = arm_spe_payload_len(buf[0]);
+
+	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, 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 = 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 = 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)
+{
+	packet->type = ARM_SPE_COUNTER;
+
+	if (ext_hdr)
+		packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]);
+	else
+		packet->index = SPE_HDR_SHORT_INDEX(buf[0]);
+
+	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)
+{
+	packet->type = ARM_SPE_ADDRESS;
+
+	if (ext_hdr)
+		packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]);
+	else
+		packet->index = SPE_HDR_SHORT_INDEX(buf[0]);
+
+	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 hdr;
+	unsigned char ext_hdr = 0;
+
+	memset(packet, 0, sizeof(struct arm_spe_pkt));
+
+	if (!len)
+		return ARM_SPE_NEED_MORE_BYTES;
+
+	hdr = buf[0];
+
+	if (hdr == SPE_HEADER0_PAD)
+		return arm_spe_get_pad(packet);
+
+	if (hdr == SPE_HEADER0_END) /* no timestamp at end of record */
+		return arm_spe_get_end(packet);
+
+	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 */
+		if (len == 1)
+			return ARM_SPE_BAD_PACKET;
+
+		ext_hdr = 1;
+		hdr = buf[1];
+		if (hdr == SPE_HEADER1_ALIGNMENT)
+			return arm_spe_get_alignment(buf, len, 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;
+}
+
+int arm_spe_get_packet(const unsigned char *buf, size_t len,
+		       struct arm_spe_pkt *packet)
+{
+	int ret;
+
+	ret = arm_spe_do_get_packet(buf, len, packet);
+	/* put multiple consecutive PADs on the same line, up to
+	 * the fixed-width output format of 16 bytes per line.
+	 */
+	if (ret > 0 && packet->type == ARM_SPE_PAD) {
+		while (ret < 16 && len > (size_t)ret && !buf[ret])
+			ret += 1;
+	}
+	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;
+		case SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG:
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " MTE-TAG");
+			break;
+		case SPE_OP_PKT_LDST_SUBCLASS_MEMCPY:
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " MEMCPY");
+			break;
+		case SPE_OP_PKT_LDST_SUBCLASS_MEMSET:
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " MEMSET");
+			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;
+	static const char *idx_name[] = {"PC", "TGT", "VA", "PA", "PBT"};
+
+	switch (idx) {
+	case SPE_ADDR_PKT_HDR_INDEX_INS:
+	case SPE_ADDR_PKT_HDR_INDEX_BRANCH:
+	case SPE_ADDR_PKT_HDR_INDEX_PREV_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_name[idx], 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 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:
+		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:
+		err = arm_spe_pkt_desc_op_type(packet, buf, buf_len);
+		break;
+	case ARM_SPE_DATA_SOURCE:
+	case ARM_SPE_TIMESTAMP:
+		arm_spe_pkt_out_string(&err, &buf, &blen, "%s %lld", name, payload);
+		break;
+	case ARM_SPE_ADDRESS:
+		err = arm_spe_pkt_desc_addr(packet, buf, buf_len);
+		break;
+	case ARM_SPE_CONTEXT:
+		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;
+	}
+
+	/* 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
new file mode 100644
index 0000000000..464a912b22
--- /dev/null
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Arm Statistical Profiling Extensions (SPE) support
+ * Copyright (c) 2017-2018, Arm Ltd.
+ */
+
+#ifndef INCLUDE__ARM_SPE_PKT_DECODER_H__
+#define INCLUDE__ARM_SPE_PKT_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+
+#define ARM_SPE_PKT_DESC_MAX		256
+
+#define ARM_SPE_NEED_MORE_BYTES		-1
+#define ARM_SPE_BAD_PACKET		-2
+
+#define ARM_SPE_PKT_MAX_SZ		16
+
+enum arm_spe_pkt_type {
+	ARM_SPE_BAD,
+	ARM_SPE_PAD,
+	ARM_SPE_END,
+	ARM_SPE_TIMESTAMP,
+	ARM_SPE_ADDRESS,
+	ARM_SPE_COUNTER,
+	ARM_SPE_CONTEXT,
+	ARM_SPE_OP_TYPE,
+	ARM_SPE_EVENTS,
+	ARM_SPE_DATA_SOURCE,
+};
+
+struct arm_spe_pkt {
+	enum arm_spe_pkt_type	type;
+	unsigned char		index;
+	uint64_t		payload;
+};
+
+/* 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
+#define SPE_ADDR_PKT_HDR_INDEX_PREV_BRANCH	0x4
+
+/* 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_LDST_SUBCLASS_MTE_TAG	0x14
+#define SPE_OP_PKT_LDST_SUBCLASS_MEMCPY		0x20
+#define SPE_OP_PKT_LDST_SUBCLASS_MEMSET		0x25
+
+#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);
+
+int arm_spe_get_packet(const unsigned char *buf, size_t len,
+		       struct arm_spe_pkt *packet);
+
+int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf, size_t len);
+#endif