arm64: cpufeature: Export matrix and other features to userspace

mainline inclusion
from mainline-v5.9-rc1
commit d4209d8b
category: feature
bugzilla: NA
CVE: NA

-------------------------------------------------

Export the features introduced as part of ARMv8.6 exposed in the
ID_AA64ISAR1_EL1 and ID_AA64ZFR0_EL1 registers. This introduces the
Matrix features (ARMv8.2-I8MM, ARMv8.2-F64MM and ARMv8.2-F32MM) along
with BFloat16 (Armv8.2-BF16), speculation invalidation (SPECRES) and
Data Gathering Hint (ARMv8.0-DGH).

conflict:
Documentation/arm64/cpu-feature-registers.txt
Signed-off-by: NJulien Grall <julien.grall@arm.com>
[Added other features in those registers]
Signed-off-by: NSteven Price <steven.price@arm.com>
[will: Don't advertise SPECRES to userspace]
Signed-off-by: NWill Deacon <will@kernel.org>
Signed-off-by: NWang Faren <wangfaren@huawei.com>
Reviewed-by: NXie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

Documentation/arm64/cpu-feature-registers.txt

@@ -184,6 +184,12 @@ infrastructure:
      x--------------------------------------------------x
      | Name                         |  bits   | visible |
      |--------------------------------------------------|
+     | I8MM                         | [55-52] |    y    |
+     |--------------------------------------------------|
+     | DGH                          | [51-48] |    y    |
+     |--------------------------------------------------|
+     | BF16                         | [47-44] |    y    |
+     |--------------------------------------------------|
      | GPI                          | [31-28] |    y    |
      |--------------------------------------------------|
      | GPA                          | [27-24] |    y    |
@@ -214,10 +220,18 @@ infrastructure:
      x--------------------------------------------------x
      | Name                         |  bits   | visible |
      |--------------------------------------------------|
+     | F64MM                        | [59-56] |    y    |
+     |--------------------------------------------------|
+     | F32MM                        | [55-52] |    y    |
+     |--------------------------------------------------|
+     | I8MM                         | [47-44] |    y    |
+     |--------------------------------------------------|
      | SM4                          | [43-40] |    y    |
      |--------------------------------------------------|
      | SHA3                         | [35-32] |    y    |
      |--------------------------------------------------|
+     | BF16                         | [23-20] |    y    |
+     |--------------------------------------------------|
      | BitPerm                      | [19-16] |    y    |
      |--------------------------------------------------|
      | AES                          | [7-4]   |    y    |

Documentation/arm64/elf_hwcaps.txt

@@ -231,6 +231,33 @@ HWCAP2_FRINT
 
     Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001.
 
+HWCAP2_SVEI8MM
+
+    Functionality implied by ID_AA64ZFR0_EL1.I8MM == 0b0001.
+
+HWCAP2_SVEF32MM
+
+    Functionality implied by ID_AA64ZFR0_EL1.F32MM == 0b0001.
+
+HWCAP2_SVEF64MM
+
+    Functionality implied by ID_AA64ZFR0_EL1.F64MM == 0b0001.
+
+HWCAP2_SVEBF16
+
+    Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0001.
+
+HWCAP2_I8MM
+
+    Functionality implied by ID_AA64ISAR1_EL1.I8MM == 0b0001.
+
+HWCAP2_BF16
+
+    Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0001.
+
+HWCAP2_DGH
+
+    Functionality implied by ID_AA64ISAR1_EL1.DGH == 0b0001.
 
 4. Unused AT_HWCAP bits
 -----------------------

arch/arm64/include/asm/hwcap.h

@@ -97,6 +97,13 @@
 #define KERNEL_HWCAP_SVESM4		__khwcap2_feature(SVESM4)
 #define KERNEL_HWCAP_FLAGM2		__khwcap2_feature(FLAGM2)
 #define KERNEL_HWCAP_FRINT		__khwcap2_feature(FRINT)
+#define KERNEL_HWCAP_SVEI8MM		__khwcap2_feature(SVEI8MM)
+#define KERNEL_HWCAP_SVEF32MM		__khwcap2_feature(SVEF32MM)
+#define KERNEL_HWCAP_SVEF64MM		__khwcap2_feature(SVEF64MM)
+#define KERNEL_HWCAP_SVEBF16		__khwcap2_feature(SVEBF16)
+#define KERNEL_HWCAP_I8MM		__khwcap2_feature(I8MM)
+#define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
+#define KERNEL_HWCAP_BF16		__khwcap2_feature(BF16)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/sysreg.h

@@ -550,6 +550,10 @@
 #define ID_AA64ISAR0_TLB_RANGE		0x2
 
 /* id_aa64isar1 */
+#define ID_AA64ISAR1_I8MM_SHIFT		52
+#define ID_AA64ISAR1_DGH_SHIFT		48
+#define ID_AA64ISAR1_BF16_SHIFT		44
+#define ID_AA64ISAR1_SPECRES_SHIFT	40
 #define ID_AA64ISAR1_SB_SHIFT		36
 #define ID_AA64ISAR1_FRINTTS_SHIFT	32
 #define ID_AA64ISAR1_GPI_SHIFT		28
@@ -604,12 +608,20 @@
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 
 /* id_aa64zfr0 */
+#define ID_AA64ZFR0_F64MM_SHIFT		56
+#define ID_AA64ZFR0_F32MM_SHIFT		52
+#define ID_AA64ZFR0_I8MM_SHIFT		44
 #define ID_AA64ZFR0_SM4_SHIFT		40
 #define ID_AA64ZFR0_SHA3_SHIFT		32
+#define ID_AA64ZFR0_BF16_SHIFT		20
 #define ID_AA64ZFR0_BITPERM_SHIFT	16
 #define ID_AA64ZFR0_AES_SHIFT		4
 #define ID_AA64ZFR0_SVEVER_SHIFT	0
 
+#define ID_AA64ZFR0_F64MM		0x1
+#define ID_AA64ZFR0_F32MM		0x1
+#define ID_AA64ZFR0_I8MM		0x1
+#define ID_AA64ZFR0_BF16		0x1
 #define ID_AA64ZFR0_SM4			0x1
 #define ID_AA64ZFR0_SHA3		0x1
 #define ID_AA64ZFR0_BITPERM		0x1

arch/arm64/include/uapi/asm/hwcap.h

@@ -65,5 +65,12 @@
 #define HWCAP2_SVESM4		(1 << 6)
 #define HWCAP2_FLAGM2		(1 << 7)
 #define HWCAP2_FRINT		(1 << 8)
+#define HWCAP2_SVEI8MM		(1 << 9)
+#define HWCAP2_SVEF32MM		(1 << 10)
+#define HWCAP2_SVEF64MM		(1 << 11)
+#define HWCAP2_SVEBF16		(1 << 12)
+#define HWCAP2_I8MM		(1 << 13)
+#define HWCAP2_BF16		(1 << 14)
+#define HWCAP2_DGH		(1 << 15)
 
 #endif /* _UAPI__ASM_HWCAP_H */

arch/arm64/kernel/cpufeature.c

@@ -147,6 +147,10 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_I8MM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DGH_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_BF16_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SPECRES_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FRINTTS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
@@ -189,10 +193,18 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_F64MM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_F32MM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_I8MM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BF16_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
@@ -1828,6 +1840,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_BF16_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DGH_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_I8MM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM),
 	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE),
@@ -1835,8 +1850,12 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BF16_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BF16, CAP_HWCAP, KERNEL_HWCAP_SVEBF16),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
 	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_I8MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_I8MM, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F32MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F32MM, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F64MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F64MM, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
 #endif
 	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS),
 #ifdef CONFIG_ARM64_PTR_AUTH

arch/arm64/kernel/cpuinfo.c

@@ -94,6 +94,13 @@ static const char *const hwcap_str[] = {
 	"svesm4",
 	"flagm2",
 	"frint",
+	"svei8mm",
+	"svef32mm",
+	"svef64mm",
+	"svebf16",
+	"i8mm",
+	"bf16",
+	"dgh",
 	NULL
 };