1 files changed, 75 insertions, 27 deletions

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..ba807071d3c1 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>
 
@@ -21,44 +22,57 @@
 
 #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/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) {
-		/* 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);
+		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;
@@ -141,6 +155,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
 	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);
@@ -162,12 +177,41 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
 				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))
@@ -182,23 +226,27 @@ 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))
 				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;