Merge branch 'for-next/cpufeature' into for-next/core

* for-next/cpufeature:
  arm64/hwcap: Support FEAT_EBF16
  arm64/cpufeature: Store elf_hwcaps as a bitmap rather than unsigned long
  arm64/hwcap: Document allocation of upper bits of AT_HWCAP
  arm64: trap implementation defined functionality in userspace

8 files changed, 41 insertions, 9 deletions

diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index 3d116fb536c5..31fc10b833dd 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -301,6 +301,10 @@ HWCAP2_WFXT
 
     Functionality implied by ID_AA64ISAR2_EL1.WFXT == 0b0010.
 
+HWCAP2_EBF16
+
+    Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0010.
+
 4. Unused AT_HWCAP bits
 -----------------------
 
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index fe59035bdc22..f7f2227db56f 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -11,7 +11,7 @@
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
-#define MAX_CPU_FEATURES	64
+#define MAX_CPU_FEATURES	128
 #define cpu_feature(x)		KERNEL_HWCAP_ ## x
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index aa443d8f8cfb..cef4ae7a3d8b 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -85,7 +85,7 @@
 #define KERNEL_HWCAP_PACA		__khwcap_feature(PACA)
 #define KERNEL_HWCAP_PACG		__khwcap_feature(PACG)
 
-#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 32)
+#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 64)
 #define KERNEL_HWCAP_DCPODP		__khwcap2_feature(DCPODP)
 #define KERNEL_HWCAP_SVE2		__khwcap2_feature(SVE2)
 #define KERNEL_HWCAP_SVEAES		__khwcap2_feature(SVEAES)
@@ -118,6 +118,7 @@
 #define KERNEL_HWCAP_SME_F32F32		__khwcap2_feature(SME_F32F32)
 #define KERNEL_HWCAP_SME_FA64		__khwcap2_feature(SME_FA64)
 #define KERNEL_HWCAP_WFXT		__khwcap2_feature(WFXT)
+#define KERNEL_HWCAP_EBF16		__khwcap2_feature(EBF16)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index d7f115368197..7c71358d44c4 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -788,6 +788,7 @@
 
 /* id_aa64mmfr1 */
 #define ID_AA64MMFR1_ECBHB_SHIFT	60
+#define ID_AA64MMFR1_TIDCP1_SHIFT	52
 #define ID_AA64MMFR1_HCX_SHIFT		40
 #define ID_AA64MMFR1_AFP_SHIFT		44
 #define ID_AA64MMFR1_ETS_SHIFT		36
@@ -804,6 +805,9 @@
 #define ID_AA64MMFR1_VMIDBITS_8		0
 #define ID_AA64MMFR1_VMIDBITS_16	2
 
+#define ID_AA64MMFR1_TIDCP1_NI		0
+#define ID_AA64MMFR1_TIDCP1_IMP		1
+
 /* id_aa64mmfr2 */
 #define ID_AA64MMFR2_E0PD_SHIFT		60
 #define ID_AA64MMFR2_EVT_SHIFT		56
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 4bb2cc8ac446..1ad2568a2569 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -19,6 +19,9 @@
 
 /*
  * HWCAP flags - for AT_HWCAP
+ *
+ * Bits 62 and 63 are reserved for use by libc.
+ * Bits 32-61 are unallocated for potential use by libc.
  */
 #define HWCAP_FP		(1 << 0)
 #define HWCAP_ASIMD		(1 << 1)
@@ -88,5 +91,6 @@
 #define HWCAP2_SME_F32F32	(1 << 29)
 #define HWCAP2_SME_FA64		(1 << 30)
 #define HWCAP2_WFXT		(1UL << 31)
+#define HWCAP2_EBF16		(1UL << 32)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index e221bb3650fc..cb0ae19d23bb 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -92,7 +92,7 @@
 #include <asm/virt.h>
 
 /* Kernel representation of AT_HWCAP and AT_HWCAP2 */
-static unsigned long elf_hwcap __read_mostly;
+static DECLARE_BITMAP(elf_hwcap, MAX_CPU_FEATURES) __read_mostly;
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP_DEFAULT	\
@@ -362,6 +362,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TIDCP1_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_AFP_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_ETS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TWED_SHIFT, 4, 0),
@@ -2035,6 +2036,11 @@ static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, in
 }
 #endif /* CONFIG_KVM */
 
+static void cpu_trap_el0_impdef(const struct arm64_cpu_capabilities *__unused)
+{
+	sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_TIDCP);
+}
+
 /* Internal helper functions to match cpu capability type */
 static bool
 cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -2578,6 +2584,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.min_field_value = ID_AA64ISAR2_EL1_WFxT_IMP,
 	},
+	{
+		.desc = "Trap EL0 IMPLEMENTATION DEFINED functionality",
+		.capability = ARM64_HAS_TIDCP1,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.sys_reg = SYS_ID_AA64MMFR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR1_TIDCP1_SHIFT,
+		.field_width = 4,
+		.min_field_value = ID_AA64MMFR1_TIDCP1_IMP,
+		.matches = has_cpuid_feature,
+		.cpu_enable = cpu_trap_el0_impdef,
+	},
 	{},
 };
 
@@ -2680,6 +2698,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_FRINTTS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_SB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_EBF16),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DGH_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_I8MM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM),
 	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
@@ -3155,14 +3174,12 @@ static bool __maybe_unused __system_matches_cap(unsigned int n)
 
 void cpu_set_feature(unsigned int num)
 {
-	WARN_ON(num >= MAX_CPU_FEATURES);
-	elf_hwcap |= BIT(num);
+	set_bit(num, elf_hwcap);
 }
 
 bool cpu_have_feature(unsigned int num)
 {
-	WARN_ON(num >= MAX_CPU_FEATURES);
-	return elf_hwcap & BIT(num);
+	return test_bit(num, elf_hwcap);
 }
 EXPORT_SYMBOL_GPL(cpu_have_feature);
 
@@ -3173,12 +3190,12 @@ unsigned long cpu_get_elf_hwcap(void)
 	 * note that for userspace compatibility we guarantee that bits 62
 	 * and 63 will always be returned as 0.
 	 */
-	return lower_32_bits(elf_hwcap);
+	return elf_hwcap[0];
 }
 
 unsigned long cpu_get_elf_hwcap2(void)
 {
-	return upper_32_bits(elf_hwcap);
+	return elf_hwcap[1];
 }
 
 static void __init setup_system_capabilities(void)
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 3628b8a28e92..26baa87e8fe7 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -114,6 +114,7 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_SME_F32F32]	= "smef32f32",
 	[KERNEL_HWCAP_SME_FA64]		= "smefa64",
 	[KERNEL_HWCAP_WFXT]		= "wfxt",
+	[KERNEL_HWCAP_EBF16]		= "ebf16",
 };
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 8809e14cf86a..779653771507 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -36,6 +36,7 @@ HAS_RNG
 HAS_SB
 HAS_STAGE2_FWB
 HAS_SYSREG_GIC_CPUIF
+HAS_TIDCP1
 HAS_TLB_RANGE
 HAS_VIRT_HOST_EXTN
 HAS_WFXT