| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <c4baccf4-2ecd-1633-ec87-0f4911cbdc50@arm.com>
Date: Mon, 26 Oct 2020 18:17:20 +0000
From: André Przywara <andre.przywara@....com>
To: Leo Yan <leo.yan@...aro.org>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...hat.com>,
Namhyung Kim <namhyung@...nel.org>,
Wei Li <liwei391@...wei.com>,
James Clark <james.clark@....com>, Al Grant <Al.Grant@....com>,
Dave Martin <Dave.Martin@....com>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3 20/20] perf arm-spe: Add support for ARMv8.3-SPE
On 22/10/2020 15:58, Leo Yan wrote:
Hi,
> From: Wei Li <liwei391@...wei.com>
>
> 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@...wei.com>
> Signed-off-by: Leo Yan <leo.yan@...aro.org>
> ---
> .../arm-spe-decoder/arm-spe-pkt-decoder.c | 74 ++++++++++++++++++-
> .../arm-spe-decoder/arm-spe-pkt-decoder.h | 18 +++++
> 2 files changed, 90 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 74ac12cbec69..6da4cfbc9914 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
> @@ -332,6 +332,21 @@ static int arm_spe_pkt_desc_event(const struct arm_spe_pkt *packet,
> if (ret < 0)
> return ret;
> }
> + if (payload & BIT(EV_ALIGNMENT)) {
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " ALIGNMENT");
> + if (ret < 0)
> + return ret;
> + }
> + if (payload & BIT(EV_PARTIAL_PREDICATE)) {
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " SVE-PARTIAL-PRED");
> + if (ret < 0)
> + return ret;
> + }
> + if (payload & BIT(EV_EMPTY_PREDICATE)) {
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " SVE-EMPTY-PRED");
> + if (ret < 0)
> + return ret;
> + }
>
> return buf_len - blen;
> }
> @@ -345,8 +360,43 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet,
>
> switch (class) {
> case SPE_OP_PKT_HDR_CLASS_OTHER:
> - return arm_spe_pkt_snprintf(&buf, &blen,
> - payload & SPE_OP_PKT_COND ? "COND-SELECT" : "INSN-OTHER");
> + if (SPE_OP_PKT_OTHER_SUBCLASS_SVE_OP_GET(payload) ==
> + SPE_OP_PKT_OTHER_SUBCLASS_SVE_OP) {
Same comment as in the other patch, can you combine those two into one
symbol?
> +
> + ret = arm_spe_pkt_snprintf(&buf, &blen, "SVE-OTHER");
> + if (ret < 0)
> + return ret;
> +
> + /* SVE effective vector length */
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " EVLEN %d",
> + SPE_OP_PKG_SVE_EVL(payload));
> + if (ret < 0)
> + return ret;
> +
> + if (payload & SPE_OP_PKT_SVE_FP) {
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " FP");
> + if (ret < 0)
> + return ret;
> + }
> + if (payload & SPE_OP_PKT_SVE_PRED) {
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " PRED");
> + if (ret < 0)
> + return ret;
> + }
> + } else {
> + ret = arm_spe_pkt_snprintf(&buf, &blen, "OTHER");
> + if (ret < 0)
> + return ret;
> +
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " %s",
> + payload & SPE_OP_PKT_COND ?
> + "COND-SELECT" : "INSN-OTHER");
> + if (ret < 0)
> + return ret;
> + }
> +
> + return buf_len - blen;
> +
> case SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC:
> ret = arm_spe_pkt_snprintf(&buf, &blen,
> payload & SPE_OP_PKT_ST ? "ST" : "LD");
> @@ -401,6 +451,26 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet,
> break;
> }
>
> + if (SPE_OP_PKT_LDST_SUBCLASS_SVE_GET(payload) ==
> + SPE_OP_PKT_LDST_SUBCLASS_SVE) {
Same here, could be combined into one symbol.
> + /* SVE effective vector length */
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " EVLEN %d",
> + SPE_OP_PKG_SVE_EVL(payload));
> + if (ret < 0)
> + return ret;
> +
> + if (payload & SPE_OP_PKT_SVE_PRED) {
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " PRED");
> + if (ret < 0)
> + return ret;
> + }
> + if (payload & SPE_OP_PKT_SVE_SG) {
> + ret = arm_spe_pkt_snprintf(&buf, &blen, " SG");
> + if (ret < 0)
> + return ret;
> + }
> + }
> +
> return buf_len - blen;
>
> case SPE_OP_PKT_HDR_CLASS_BR_ERET:
> 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 d69af0d618ea..04bc09f3ea17 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
> @@ -118,6 +118,9 @@ 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_OTHER_SUBCLASS_SVE_OP_GET(v) ((v) & (BIT(7) | BIT(3) | BIT(0)))
> +#define SPE_OP_PKT_OTHER_SUBCLASS_SVE_OP 0x8
> +
> #define SPE_OP_PKT_COND BIT(0)
>
> #define SPE_OP_PKT_LDST_SUBCLASS_GET(v) ((v) & GENMASK_ULL(7, 1))
> @@ -134,6 +137,21 @@ enum arm_spe_events {
> #define SPE_OP_PKT_AT BIT(2)
> #define SPE_OP_PKT_ST BIT(0)
>
> +#define SPE_OP_PKT_LDST_SUBCLASS_SVE_GET(v) ((v) & (GENMASK_ULL(3, 3) | GENMASK_ULL(1, 1)))
> +#define SPE_OP_PKT_LDST_SUBCLASS_SVE 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])
> + */
Thanks for adding the comment!
Cheers,
Andre
> +#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_BRANCH_SUBCLASS_GET(v) ((v) & GENMASK_ULL(7, 1))
> #define SPE_OP_PKT_BRANCH_SUBCLASS_DIRECT 0x0
> #define SPE_OP_PKT_BRANCH_SUBCLASS_INDIRECT 0x2
>
Powered by blists - more mailing lists