packages/kernel
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
kernel/patches/0040-perf-arm-spe-Add-support-for-ARMv8.3-SPE.patch
hongrongxuan c213868552 Add the feature of ARM SPE based on ARM v8.3
2023-10-31 11:32:10 +08:00

147 lines
5.7 KiB
Diff
Raw Permalink Blame History

From afde7e19070a48deaac649e0f16f19b164870af1 Mon Sep 17 00:00:00 2001
From: Wei Li <liwei391@huawei.com>
Date: Fri, 31 Dec 2021 13:32:17 +0800
Subject: [PATCH 20/21] perf arm-spe: Add support for ARMv8.3-SPE
mainline inclusion
from mainline-v5.11-rc1
commit 05e91e7fe26c6fb116fa16f43c1eed78020f9463
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I4NGPV
CVE: NA
-------------------------------------------------
This patch is to support Armv8.3 extension for SPE, it adds alignment
field in the Events packet and it supports the Scalable Vector Extension
(SVE) for Operation packet and Events packet with two additions:
- The vector length for SVE operations in the Operation Type packet;
- The incomplete predicate and empty predicate fields in the Events
packet.
Signed-off-by: Wei Li <liwei391@huawei.com>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Al Grant <Al.Grant@arm.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201119152441.6972-17-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: hongrongxuan <hongrongxuan@huawei.com>
---
.../arm-spe-decoder/arm-spe-pkt-decoder.c | 36 +++++++++++++++++--
.../arm-spe-decoder/arm-spe-pkt-decoder.h | 16 +++++++++
2 files changed, 50 insertions(+), 2 deletions(-)
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 57c01ce27915..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
@@ -317,6 +317,12 @@ static int arm_spe_pkt_desc_event(const struct arm_spe_pkt *packet,
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;
}
@@ -329,8 +335,23 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet,
switch (packet->index) {
case SPE_OP_PKT_HDR_CLASS_OTHER:
- arm_spe_pkt_out_string(&err, &buf, &buf_len,
- payload & SPE_OP_PKT_COND ? "COND-SELECT" : "INSN-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,
@@ -361,6 +382,17 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet,
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");
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 1ad14885c2a1..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
@@ -113,6 +113,8 @@ enum arm_spe_events {
#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))
@@ -128,6 +130,20 @@ enum arm_spe_events {
#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);
--
2.27.0
Reference in New Issue View Git Blame Copy Permalink