From 956ca3a4eb81c1b8cc3226af3083847544dcb098 Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap <amit.kachhap@arm.com>
Date: Thu, 17 Nov 2022 06:58:31 +0100
Subject: [PATCH] ARM: 9272/1: vfp: Add hwcap for FEAT_AA32I8MM
Int8 matrix multiplication (FEAT_AA32I8MM) is a feature present in AArch32 state for Armv8 and is represented by ISAR6.I8MM identification register.
This feature denotes the presence of VSMMLA, VSUDOT, VUMMLA, VUSMMLA and
VUSDOT instructions and hence adding a hwcap will enable the userspace
to check it before trying to use those instructions.
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
arch/arm/include/uapi/asm/hwcap.h | 1 +
arch/arm/kernel/setup.c | 1 +
arch/arm/vfp/vfpmodule.c | 6 ++++++
3 files changed, 8 insertions(+)
diff --git a/arch/arm/include/uapi/asm/hwcap.h b/arch/arm/include/uapi/asm/hwcap.h
index 14e260e2d6d0c..46833c668ec2f 100644
--- a/arch/arm/include/uapi/asm/hwcap.h
+++ b/arch/arm/include/uapi/asm/hwcap.h
@@ -33,6 +33,7 @@
#define HWCAP_ASIMDDP (1 << 24)
#define HWCAP_ASIMDFHM (1 << 25)
#define HWCAP_ASIMDBF16 (1 << 26)
+#define HWCAP_I8MM (1 << 27)
/*
* HWCAP2 flags - for elf_hwcap2 (in kernel) and AT_HWCAP2
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 070067cb6c77a..5807fa0217853 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1254,6 +1254,7 @@ static const char *hwcap_str[] = {
"asimddp",
"asimdfhm",
"asimdbf16",
+ "i8mm",
NULL
};
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index ff574cb8a0b92..281110423871c 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -857,6 +857,12 @@ static int __init vfp_init(void)
*/
if (cpuid_feature_extract_field(isar6, 20) == 0x1)
elf_hwcap |= HWCAP_ASIMDBF16;
+ /*
+ * Check for the presence of Advanced SIMD and floating point
+ * Int8 matrix multiplication instructions instructions.
+ */
+ if (cpuid_feature_extract_field(isar6, 24) == 0x1)
+ elf_hwcap |= HWCAP_I8MM;
/* Extract the architecture version on pre-cpuid scheme */
} else {
--
2.30.2