From ca8a4ebcff4465f0272637433c789a5e4a272626 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:14 +0100
Subject: arm64/sme: Manually encode SME instructions

As with SVE rather than impose ambitious toolchain requirements for SME
we manually encode the few instructions which we require in order to
perform the work the kernel needs to do. The instructions used to save
and restore context are provided as assembler macros while those for
entering and leaving streaming mode are done in asm volatile blocks
since they are expected to be used from C.

We could do the SMSTART and SMSTOP operations with read/modify/write
cycles on SVCR but using the aliases provided for individual field
accesses should be slightly faster. These instructions are aliases for
MSR but since our minimum toolchain requirements are old enough to mean
that we can't use the sX_X_cX_cX_X form and they always use xzr rather
than taking a value like write_sysreg_s() wants we just use .inst.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-7-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index cb24385e3632..6e2dc9dcbf49 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -249,6 +249,31 @@ static inline void sve_setup(void) { }
 
 #endif /* ! CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static inline void sme_smstart_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop_sm(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr"));
+}
+
+static inline void sme_smstop(void)
+{
+	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr"));
+}
+
+#else
+
+static inline void sme_smstart_sm(void) { }
+static inline void sme_smstop_sm(void) { }
+static inline void sme_smstop(void) { }
+
+#endif /* ! CONFIG_ARM64_SME */
+
 /* For use by EFI runtime services calls only */
 extern void __efi_fpsimd_begin(void);
 extern void __efi_fpsimd_end(void);
-- 
cgit v1.2.3


From 5e64b862c4823ab53aac028042abd918c2f27041 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:16 +0100
Subject: arm64/sme: Basic enumeration support

This patch introduces basic cpufeature support for discovering the presence
of the Scalable Matrix Extension.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-9-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 Documentation/arm64/elf_hwcaps.rst  | 33 +++++++++++++++++++++
 arch/arm64/include/asm/cpu.h        |  1 +
 arch/arm64/include/asm/cpufeature.h | 12 ++++++++
 arch/arm64/include/asm/fpsimd.h     |  2 ++
 arch/arm64/include/asm/hwcap.h      |  8 +++++
 arch/arm64/include/uapi/asm/hwcap.h |  8 +++++
 arch/arm64/kernel/cpufeature.c      | 59 +++++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/cpuinfo.c         |  9 ++++++
 arch/arm64/kernel/fpsimd.c          | 30 +++++++++++++++++++
 arch/arm64/tools/cpucaps            |  2 ++
 10 files changed, 164 insertions(+)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index a8f30963e550..f8d818eaaff5 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -264,6 +264,39 @@ HWCAP2_MTE3
     Functionality implied by ID_AA64PFR1_EL1.MTE == 0b0011, as described
     by Documentation/arm64/memory-tagging-extension.rst.
 
+HWCAP2_SME
+
+    Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described
+    by Documentation/arm64/sme.rst.
+
+HWCAP2_SME_I16I64
+
+    Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111.
+
+HWCAP2_SME_F64F64
+
+    Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1.
+
+HWCAP2_SME_I8I32
+
+    Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111.
+
+HWCAP2_SME_F16F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1.
+
+HWCAP2_SME_B16F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1.
+
+HWCAP2_SME_F32F32
+
+    Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1.
+
+HWCAP2_SME_FA64
+
+    Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1.
+
 4. Unused AT_HWCAP bits
 -----------------------
 
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index a58e366f0b07..d08062bcb9c1 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -58,6 +58,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
 	u64		reg_id_aa64zfr0;
+	u64		reg_id_aa64smfr0;
 
 	struct cpuinfo_32bit	aarch32;
 
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index c62e7e5e2f0c..8ac12e4094aa 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -759,6 +759,18 @@ static __always_inline bool system_supports_sve(void)
 		cpus_have_const_cap(ARM64_SVE);
 }
 
+static __always_inline bool system_supports_sme(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME);
+}
+
+static __always_inline bool system_supports_fa64(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME_FA64);
+}
+
 static __always_inline bool system_supports_cnp(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_CNP) &&
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 6e2dc9dcbf49..2e8ef00e7520 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -74,6 +74,8 @@ extern void sve_set_vq(unsigned long vq_minus_1);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 
 extern u64 read_zcr_features(void);
 
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 8db5ec0089db..9f0ce004fdbc 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -109,6 +109,14 @@
 #define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
 #define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)
 #define KERNEL_HWCAP_MTE3		__khwcap2_feature(MTE3)
+#define KERNEL_HWCAP_SME		__khwcap2_feature(SME)
+#define KERNEL_HWCAP_SME_I16I64		__khwcap2_feature(SME_I16I64)
+#define KERNEL_HWCAP_SME_F64F64		__khwcap2_feature(SME_F64F64)
+#define KERNEL_HWCAP_SME_I8I32		__khwcap2_feature(SME_I8I32)
+#define KERNEL_HWCAP_SME_F16F32		__khwcap2_feature(SME_F16F32)
+#define KERNEL_HWCAP_SME_B16F32		__khwcap2_feature(SME_B16F32)
+#define KERNEL_HWCAP_SME_F32F32		__khwcap2_feature(SME_F32F32)
+#define KERNEL_HWCAP_SME_FA64		__khwcap2_feature(SME_FA64)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 99cb5d383048..b0256cec63b5 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -79,5 +79,13 @@
 #define HWCAP2_AFP		(1 << 20)
 #define HWCAP2_RPRES		(1 << 21)
 #define HWCAP2_MTE3		(1 << 22)
+#define HWCAP2_SME		(1 << 23)
+#define HWCAP2_SME_I16I64	(1 << 24)
+#define HWCAP2_SME_F64F64	(1 << 25)
+#define HWCAP2_SME_I8I32	(1 << 26)
+#define HWCAP2_SME_F16F32	(1 << 27)
+#define HWCAP2_SME_B16F32	(1 << 28)
+#define HWCAP2_SME_F32F32	(1 << 29)
+#define HWCAP2_SME_FA64		(1 << 30)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d72c4b4d389c..0f2d7ddd69ae 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -261,6 +261,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SME_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE),
@@ -293,6 +295,24 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_FA64_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I16I64_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F64F64_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I8I32_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F16F32_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_B16F32_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F32F32_SHIFT, 1, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0),
@@ -645,6 +665,7 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1,
 			       &id_aa64pfr1_override),
 	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
+	ARM64_FTR_REG(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
 	ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -960,6 +981,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
 	init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
+	init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0);
 
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
 		init_32bit_cpu_features(&info->aarch32);
@@ -2442,6 +2464,33 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.min_field_value = 1,
 	},
+#ifdef CONFIG_ARM64_SME
+	{
+		.desc = "Scalable Matrix Extension",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_SME,
+		.sys_reg = SYS_ID_AA64PFR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR1_SME_SHIFT,
+		.field_width = 4,
+		.min_field_value = ID_AA64PFR1_SME,
+		.matches = has_cpuid_feature,
+		.cpu_enable = sme_kernel_enable,
+	},
+	/* FA64 should be sorted after the base SME capability */
+	{
+		.desc = "FA64",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_SME_FA64,
+		.sys_reg = SYS_ID_AA64SMFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64SMFR0_FA64_SHIFT,
+		.field_width = 1,
+		.min_field_value = ID_AA64SMFR0_FA64,
+		.matches = has_cpuid_feature,
+		.cpu_enable = fa64_kernel_enable,
+	},
+#endif /* CONFIG_ARM64_SME */
 	{},
 };
 
@@ -2575,6 +2624,16 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
 	HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
 	HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
+#ifdef CONFIG_ARM64_SME
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SME, CAP_HWCAP, KERNEL_HWCAP_SME),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_FA64, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I16I64, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F64F64, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I8I32, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F16F32, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_B16F32, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+	HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F32F32, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+#endif /* CONFIG_ARM64_SME */
 	{},
 };
 
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 330b92ea863a..a73fe2888b7e 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -98,6 +98,14 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_AFP]		= "afp",
 	[KERNEL_HWCAP_RPRES]		= "rpres",
 	[KERNEL_HWCAP_MTE3]		= "mte3",
+	[KERNEL_HWCAP_SME]		= "sme",
+	[KERNEL_HWCAP_SME_I16I64]	= "smei16i64",
+	[KERNEL_HWCAP_SME_F64F64]	= "smef64f64",
+	[KERNEL_HWCAP_SME_I8I32]	= "smei8i32",
+	[KERNEL_HWCAP_SME_F16F32]	= "smef16f32",
+	[KERNEL_HWCAP_SME_B16F32]	= "smeb16f32",
+	[KERNEL_HWCAP_SME_F32F32]	= "smef32f32",
+	[KERNEL_HWCAP_SME_FA64]		= "smefa64",
 };
 
 #ifdef CONFIG_COMPAT
@@ -401,6 +409,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
 	info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1);
+	info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1);
 
 	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
 		info->reg_gmid = read_cpuid(GMID_EL1);
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 47af76e53221..e4fba0bfb55e 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -993,6 +993,32 @@ void fpsimd_release_task(struct task_struct *dead_task)
 
 #endif /* CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+	/* Set priority for all PEs to architecturally defined minimum */
+	write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK,
+		       SYS_SMPRI_EL1);
+
+	/* Allow SME in kernel */
+	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1);
+	isb();
+}
+
+/*
+ * This must be called after sme_kernel_enable(), we rely on the
+ * feature table being sorted to ensure this.
+ */
+void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+	/* Allow use of FA64 */
+	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK,
+		       SYS_SMCR_EL1);
+}
+
+#endif /* CONFIG_ARM64_SVE */
+
 /*
  * Trapped SVE access
  *
@@ -1538,6 +1564,10 @@ static int __init fpsimd_init(void)
 	if (!cpu_have_named_feature(ASIMD))
 		pr_notice("Advanced SIMD is not implemented\n");
 
+
+	if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE))
+		pr_notice("SME is implemented but not SVE\n");
+
 	return sve_sysctl_init();
 }
 core_initcall(fpsimd_init);
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 3ed418f70e3b..e52b289a27c2 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -43,6 +43,8 @@ KVM_PROTECTED_MODE
 MISMATCHED_CACHE_TYPE
 MTE
 MTE_ASYMM
+SME
+SME_FA64
 SPECTRE_V2
 SPECTRE_V3A
 SPECTRE_V4
-- 
cgit v1.2.3


From b42990d3bf77cc29d7c33e21518c1f806dae6b21 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:17 +0100
Subject: arm64/sme: Identify supported SME vector lengths at boot

The vector lengths used for SME are controlled through a similar set of
registers to those for SVE and enumerated using a similar algorithm with
some slight differences due to the fact that unlike SVE there are no
restrictions on which combinations of vector lengths can be supported
nor any mandatory vector lengths which must be implemented.  Add a new
vector type and implement support for enumerating it.

One slightly awkward feature is that we need to read the current vector
length using a different instruction (or enter streaming mode which
would have the same issue and be higher cost).  Rather than add an ops
structure we add special cases directly in the otherwise generic
vec_probe_vqs() function, this is a bit inelegant but it's the only
place where this is an issue.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-10-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/cpu.h        |   3 +
 arch/arm64/include/asm/cpufeature.h |   7 ++
 arch/arm64/include/asm/fpsimd.h     |  26 ++++++++
 arch/arm64/include/asm/processor.h  |   1 +
 arch/arm64/kernel/cpufeature.c      |  47 ++++++++++++++
 arch/arm64/kernel/cpuinfo.c         |   4 ++
 arch/arm64/kernel/entry-fpsimd.S    |   9 +++
 arch/arm64/kernel/fpsimd.c          | 123 +++++++++++++++++++++++++++++++++++-
 8 files changed, 218 insertions(+), 2 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index d08062bcb9c1..115cdec1ae87 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -64,6 +64,9 @@ struct cpuinfo_arm64 {
 
 	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
 	u64		reg_zcr;
+
+	/* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */
+	u64		reg_smcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 8ac12e4094aa..5ddfae233ea5 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -622,6 +622,13 @@ static inline bool id_aa64pfr0_sve(u64 pfr0)
 	return val > 0;
 }
 
+static inline bool id_aa64pfr1_sme(u64 pfr1)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_SME_SHIFT);
+
+	return val > 0;
+}
+
 static inline bool id_aa64pfr1_mte(u64 pfr1)
 {
 	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT);
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 2e8ef00e7520..32cd682258d9 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -78,6 +78,7 @@ extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 
 extern u64 read_zcr_features(void);
+extern u64 read_smcr_features(void);
 
 /*
  * Helpers to translate bit indices in sve_vq_map to VQ values (and
@@ -172,6 +173,12 @@ static inline void write_vl(enum vec_type type, u64 val)
 		tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK;
 		write_sysreg_s(tmp | val, SYS_ZCR_EL1);
 		break;
+#endif
+#ifdef CONFIG_ARM64_SME
+	case ARM64_VEC_SME:
+		tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK;
+		write_sysreg_s(tmp | val, SYS_SMCR_EL1);
+		break;
 #endif
 	default:
 		WARN_ON_ONCE(1);
@@ -268,12 +275,31 @@ static inline void sme_smstop(void)
 	asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr"));
 }
 
+extern void __init sme_setup(void);
+
+static inline int sme_max_vl(void)
+{
+	return vec_max_vl(ARM64_VEC_SME);
+}
+
+static inline int sme_max_virtualisable_vl(void)
+{
+	return vec_max_virtualisable_vl(ARM64_VEC_SME);
+}
+
+extern unsigned int sme_get_vl(void);
+
 #else
 
 static inline void sme_smstart_sm(void) { }
 static inline void sme_smstop_sm(void) { }
 static inline void sme_smstop(void) { }
 
+static inline void sme_setup(void) { }
+static inline unsigned int sme_get_vl(void) { return 0; }
+static inline int sme_max_vl(void) { return 0; }
+static inline int sme_max_virtualisable_vl(void) { return 0; }
+
 #endif /* ! CONFIG_ARM64_SME */
 
 /* For use by EFI runtime services calls only */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 73e38d9a540c..abf34a9c2eab 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -118,6 +118,7 @@ struct debug_info {
 
 enum vec_type {
 	ARM64_VEC_SVE = 0,
+	ARM64_VEC_SME,
 	ARM64_VEC_MAX,
 };
 
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0f2d7ddd69ae..082b3f48cbfd 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -581,6 +581,12 @@ static const struct arm64_ftr_bits ftr_zcr[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_smcr[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
+		SMCR_ELx_LEN_SHIFT, SMCR_ELx_LEN_SIZE, 0),	/* LEN */
+	ARM64_FTR_END,
+};
+
 /*
  * Common ftr bits for a 32bit register with all hidden, strict
  * attributes, with 4bit feature fields and a default safe value of
@@ -687,6 +693,7 @@ static const struct __ftr_reg_entry {
 
 	/* Op1 = 0, CRn = 1, CRm = 2 */
 	ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
+	ARM64_FTR_REG(SYS_SMCR_EL1, ftr_smcr),
 
 	/* Op1 = 1, CRn = 0, CRm = 0 */
 	ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid),
@@ -991,6 +998,12 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		vec_init_vq_map(ARM64_VEC_SVE);
 	}
 
+	if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) {
+		init_cpu_ftr_reg(SYS_SMCR_EL1, info->reg_smcr);
+		if (IS_ENABLED(CONFIG_ARM64_SME))
+			vec_init_vq_map(ARM64_VEC_SME);
+	}
+
 	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
 		init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid);
 
@@ -1217,6 +1230,9 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu,
 				      info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0);
 
+	taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu,
+				      info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0);
+
 	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
 		taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu,
 					info->reg_zcr, boot->reg_zcr);
@@ -1227,6 +1243,16 @@ void update_cpu_features(int cpu,
 			vec_update_vq_map(ARM64_VEC_SVE);
 	}
 
+	if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) {
+		taint |= check_update_ftr_reg(SYS_SMCR_EL1, cpu,
+					info->reg_smcr, boot->reg_smcr);
+
+		/* Probe vector lengths, unless we already gave up on SME */
+		if (id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1)) &&
+		    !system_capabilities_finalized())
+			vec_update_vq_map(ARM64_VEC_SME);
+	}
+
 	/*
 	 * The kernel uses the LDGM/STGM instructions and the number of tags
 	 * they read/write depends on the GMID_EL1.BS field. Check that the
@@ -2931,6 +2957,23 @@ static void verify_sve_features(void)
 	/* Add checks on other ZCR bits here if necessary */
 }
 
+static void verify_sme_features(void)
+{
+	u64 safe_smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1);
+	u64 smcr = read_smcr_features();
+
+	unsigned int safe_len = safe_smcr & SMCR_ELx_LEN_MASK;
+	unsigned int len = smcr & SMCR_ELx_LEN_MASK;
+
+	if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SME)) {
+		pr_crit("CPU%d: SME: vector length support mismatch\n",
+			smp_processor_id());
+		cpu_die_early();
+	}
+
+	/* Add checks on other SMCR bits here if necessary */
+}
+
 static void verify_hyp_capabilities(void)
 {
 	u64 safe_mmfr1, mmfr0, mmfr1;
@@ -2983,6 +3026,9 @@ static void verify_local_cpu_capabilities(void)
 	if (system_supports_sve())
 		verify_sve_features();
 
+	if (system_supports_sme())
+		verify_sme_features();
+
 	if (is_hyp_mode_available())
 		verify_hyp_capabilities();
 }
@@ -3100,6 +3146,7 @@ void __init setup_cpu_features(void)
 		pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n");
 
 	sve_setup();
+	sme_setup();
 	minsigstksz_setup();
 
 	/* Advertise that we have computed the system capabilities */
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index a73fe2888b7e..8a8136a096ac 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -421,6 +421,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	    id_aa64pfr0_sve(info->reg_id_aa64pfr0))
 		info->reg_zcr = read_zcr_features();
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) &&
+	    id_aa64pfr1_sme(info->reg_id_aa64pfr1))
+		info->reg_smcr = read_smcr_features();
+
 	cpuinfo_detect_icache_policy(info);
 }
 
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index dc242e269f9a..deee5f01462e 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -86,3 +86,12 @@ SYM_FUNC_START(sve_flush_live)
 SYM_FUNC_END(sve_flush_live)
 
 #endif /* CONFIG_ARM64_SVE */
+
+#ifdef CONFIG_ARM64_SME
+
+SYM_FUNC_START(sme_get_vl)
+	_sme_rdsvl	0, 1
+	ret
+SYM_FUNC_END(sme_get_vl)
+
+#endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index e4fba0bfb55e..5e5fbd9cba75 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -136,6 +136,12 @@ __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
 		.max_virtualisable_vl	= SVE_VL_MIN,
 	},
 #endif
+#ifdef CONFIG_ARM64_SME
+	[ARM64_VEC_SME] = {
+		.type			= ARM64_VEC_SME,
+		.name			= "SME",
+	},
+#endif
 };
 
 static unsigned int vec_vl_inherit_flag(enum vec_type type)
@@ -186,6 +192,20 @@ extern void __percpu *efi_sve_state;
 
 #endif /* ! CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static int get_sme_default_vl(void)
+{
+	return get_default_vl(ARM64_VEC_SME);
+}
+
+static void set_sme_default_vl(int val)
+{
+	set_default_vl(ARM64_VEC_SME, val);
+}
+
+#endif
+
 DEFINE_PER_CPU(bool, fpsimd_context_busy);
 EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy);
 
@@ -409,6 +429,8 @@ static unsigned int find_supported_vector_length(enum vec_type type,
 
 	if (vl > max_vl)
 		vl = max_vl;
+	if (vl < info->min_vl)
+		vl = info->min_vl;
 
 	bit = find_next_bit(info->vq_map, SVE_VQ_MAX,
 			    __vq_to_bit(sve_vq_from_vl(vl)));
@@ -770,7 +792,23 @@ static void vec_probe_vqs(struct vl_info *info,
 
 	for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) {
 		write_vl(info->type, vq - 1); /* self-syncing */
-		vl = sve_get_vl();
+
+		switch (info->type) {
+		case ARM64_VEC_SVE:
+			vl = sve_get_vl();
+			break;
+		case ARM64_VEC_SME:
+			vl = sme_get_vl();
+			break;
+		default:
+			vl = 0;
+			break;
+		}
+
+		/* Minimum VL identified? */
+		if (sve_vq_from_vl(vl) > vq)
+			break;
+
 		vq = sve_vq_from_vl(vl); /* skip intervening lengths */
 		set_bit(__vq_to_bit(vq), map);
 	}
@@ -1017,7 +1055,88 @@ void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
 		       SYS_SMCR_EL1);
 }
 
-#endif /* CONFIG_ARM64_SVE */
+/*
+ * Read the pseudo-SMCR used by cpufeatures to identify the supported
+ * vector length.
+ *
+ * Use only if SME is present.
+ * This function clobbers the SME vector length.
+ */
+u64 read_smcr_features(void)
+{
+	u64 smcr;
+	unsigned int vq_max;
+
+	sme_kernel_enable(NULL);
+	sme_smstart_sm();
+
+	/*
+	 * Set the maximum possible VL.
+	 */
+	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK,
+		       SYS_SMCR_EL1);
+
+	smcr = read_sysreg_s(SYS_SMCR_EL1);
+	smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */
+	vq_max = sve_vq_from_vl(sve_get_vl());
+	smcr |= vq_max - 1; /* set LEN field to maximum effective value */
+
+	sme_smstop_sm();
+
+	return smcr;
+}
+
+void __init sme_setup(void)
+{
+	struct vl_info *info = &vl_info[ARM64_VEC_SME];
+	u64 smcr;
+	int min_bit;
+
+	if (!system_supports_sme())
+		return;
+
+	/*
+	 * SME doesn't require any particular vector length be
+	 * supported but it does require at least one.  We should have
+	 * disabled the feature entirely while bringing up CPUs but
+	 * let's double check here.
+	 */
+	WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX));
+
+	min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX);
+	info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit));
+
+	smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1);
+	info->max_vl = sve_vl_from_vq((smcr & SMCR_ELx_LEN_MASK) + 1);
+
+	/*
+	 * Sanity-check that the max VL we determined through CPU features
+	 * corresponds properly to sme_vq_map.  If not, do our best:
+	 */
+	if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SME,
+								 info->max_vl)))
+		info->max_vl = find_supported_vector_length(ARM64_VEC_SME,
+							    info->max_vl);
+
+	WARN_ON(info->min_vl > info->max_vl);
+
+	/*
+	 * For the default VL, pick the maximum supported value <= 32
+	 * (256 bits) if there is one since this is guaranteed not to
+	 * grow the signal frame when in streaming mode, otherwise the
+	 * minimum available VL will be used.
+	 */
+	set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32));
+
+	pr_info("SME: minimum available vector length %u bytes per vector\n",
+		info->min_vl);
+	pr_info("SME: maximum available vector length %u bytes per vector\n",
+		info->max_vl);
+	pr_info("SME: default vector length %u bytes per vector\n",
+		get_sme_default_vl());
+}
+
+#endif /* CONFIG_ARM64_SME */
 
 /*
  * Trapped SVE access
-- 
cgit v1.2.3


From 9e4ab6c89109472082616f8d2f6ada7deaffe161 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:19 +0100
Subject: arm64/sme: Implement vector length configuration prctl()s

As for SVE provide a prctl() interface which allows processes to
configure their SME vector length.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-12-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h      |  4 ++++
 arch/arm64/include/asm/processor.h   |  4 +++-
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/kernel/fpsimd.c           | 32 ++++++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h           |  9 +++++++++
 kernel/sys.c                         | 12 ++++++++++++
 6 files changed, 61 insertions(+), 1 deletion(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 32cd682258d9..38fd6aab7feb 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -288,6 +288,8 @@ static inline int sme_max_virtualisable_vl(void)
 }
 
 extern unsigned int sme_get_vl(void);
+extern int sme_set_current_vl(unsigned long arg);
+extern int sme_get_current_vl(void);
 
 #else
 
@@ -299,6 +301,8 @@ static inline void sme_setup(void) { }
 static inline unsigned int sme_get_vl(void) { return 0; }
 static inline int sme_max_vl(void) { return 0; }
 static inline int sme_max_virtualisable_vl(void) { return 0; }
+static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
+static inline int sme_get_current_vl(void) { return -EINVAL; }
 
 #endif /* ! CONFIG_ARM64_SME */
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index abf34a9c2eab..7a57cbff8a03 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -355,9 +355,11 @@ extern void __init minsigstksz_setup(void);
  */
 #include <asm/fpsimd.h>
 
-/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
+/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */
 #define SVE_SET_VL(arg)	sve_set_current_vl(arg)
 #define SVE_GET_VL()	sve_get_current_vl()
+#define SME_SET_VL(arg)	sme_set_current_vl(arg)
+#define SME_GET_VL()	sme_get_current_vl()
 
 /* PR_PAC_RESET_KEYS prctl */
 #define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index e1317b7c4525..4e6b58dcd6f9 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -82,6 +82,7 @@ int arch_dup_task_struct(struct task_struct *dst,
 #define TIF_SVE_VL_INHERIT	24	/* Inherit SVE vl_onexec across exec */
 #define TIF_SSBD		25	/* Wants SSB mitigation */
 #define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
+#define TIF_SME_VL_INHERIT	28	/* Inherit SME vl_onexec across exec */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 754a96563f6f..39f44fcb9b99 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -149,6 +149,8 @@ static unsigned int vec_vl_inherit_flag(enum vec_type type)
 	switch (type) {
 	case ARM64_VEC_SVE:
 		return TIF_SVE_VL_INHERIT;
+	case ARM64_VEC_SME:
+		return TIF_SME_VL_INHERIT;
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -807,6 +809,36 @@ int sve_get_current_vl(void)
 	return vec_prctl_status(ARM64_VEC_SVE, 0);
 }
 
+#ifdef CONFIG_ARM64_SME
+/* PR_SME_SET_VL */
+int sme_set_current_vl(unsigned long arg)
+{
+	unsigned long vl, flags;
+	int ret;
+
+	vl = arg & PR_SME_VL_LEN_MASK;
+	flags = arg & ~vl;
+
+	if (!system_supports_sme() || is_compat_task())
+		return -EINVAL;
+
+	ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags);
+	if (ret)
+		return ret;
+
+	return vec_prctl_status(ARM64_VEC_SME, flags);
+}
+
+/* PR_SME_GET_VL */
+int sme_get_current_vl(void)
+{
+	if (!system_supports_sme() || is_compat_task())
+		return -EINVAL;
+
+	return vec_prctl_status(ARM64_VEC_SME, 0);
+}
+#endif /* CONFIG_ARM64_SME */
+
 static void vec_probe_vqs(struct vl_info *info,
 			  DECLARE_BITMAP(map, SVE_VQ_MAX))
 {
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index e998764f0262..a5e06dcbba13 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -272,6 +272,15 @@ struct prctl_mm_map {
 # define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
 
+/* arm64 Scalable Matrix Extension controls */
+/* Flag values must be in sync with SVE versions */
+#define PR_SME_SET_VL			63	/* set task vector length */
+# define PR_SME_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SME_GET_VL			64	/* get task vector length */
+/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */
+# define PR_SME_VL_LEN_MASK		0xffff
+# define PR_SME_VL_INHERIT		(1 << 17) /* inherit across exec */
+
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 374f83e95239..b911fa6d81ab 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -117,6 +117,12 @@
 #ifndef SVE_GET_VL
 # define SVE_GET_VL()		(-EINVAL)
 #endif
+#ifndef SME_SET_VL
+# define SME_SET_VL(a)		(-EINVAL)
+#endif
+#ifndef SME_GET_VL
+# define SME_GET_VL()		(-EINVAL)
+#endif
 #ifndef PAC_RESET_KEYS
 # define PAC_RESET_KEYS(a, b)	(-EINVAL)
 #endif
@@ -2541,6 +2547,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_SVE_GET_VL:
 		error = SVE_GET_VL();
 		break;
+	case PR_SME_SET_VL:
+		error = SME_SET_VL(arg2);
+		break;
+	case PR_SME_GET_VL:
+		error = SME_GET_VL();
+		break;
 	case PR_GET_SPECULATION_CTRL:
 		if (arg3 || arg4 || arg5)
 			return -EINVAL;
-- 
cgit v1.2.3


From b40c559b45bec736f588c57dd5be967fe573058b Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:21 +0100
Subject: arm64/sme: Implement SVCR context switching

In SME the use of both streaming SVE mode and ZA are tracked through
PSTATE.SM and PSTATE.ZA, visible through the system register SVCR.  In
order to context switch the floating point state for SME we need to
context switch the contents of this register as part of context
switching the floating point state.

Since changing the vector length exits streaming SVE mode and disables
ZA we also make sure we update SVCR appropriately when setting vector
length, and similarly ensure that new threads have streaming SVE mode
and ZA disabled.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-14-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h      |  3 ++-
 arch/arm64/include/asm/processor.h   |  1 +
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/kernel/fpsimd.c           | 18 +++++++++++++++++-
 arch/arm64/kernel/process.c          |  2 ++
 arch/arm64/kvm/fpsimd.c              |  7 ++++++-
 6 files changed, 29 insertions(+), 3 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 38fd6aab7feb..821d270980da 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -46,7 +46,8 @@ extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
-				     void *sve_state, unsigned int sve_vl);
+				     void *sve_state, unsigned int sve_vl,
+				     u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 849e97d418a8..22cd11e86854 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -169,6 +169,7 @@ struct thread_struct {
 	u64			mte_ctrl;
 #endif
 	u64			sctlr_user;
+	u64			svcr;
 	u64			tpidr2_el0;
 };
 
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 4e6b58dcd6f9..848739c15de8 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -82,6 +82,7 @@ int arch_dup_task_struct(struct task_struct *dst,
 #define TIF_SVE_VL_INHERIT	24	/* Inherit SVE vl_onexec across exec */
 #define TIF_SSBD		25	/* Wants SSB mitigation */
 #define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
+#define TIF_SME			27	/* SME in use */
 #define TIF_SME_VL_INHERIT	28	/* Inherit SME vl_onexec across exec */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 231f2d85b65e..1c113349f6cc 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -121,6 +121,7 @@
 struct fpsimd_last_state_struct {
 	struct user_fpsimd_state *st;
 	void *sve_state;
+	u64 *svcr;
 	unsigned int sve_vl;
 };
 
@@ -359,6 +360,9 @@ static void task_fpsimd_load(void)
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) && test_thread_flag(TIF_SME))
+		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
+
 	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
 		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
 		sve_load_state(sve_pffr(&current->thread),
@@ -390,6 +394,12 @@ static void fpsimd_save(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) &&
+	    test_thread_flag(TIF_SME)) {
+		u64 *svcr = last->svcr;
+		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+	}
+
 	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
 	    test_thread_flag(TIF_SVE)) {
 		if (WARN_ON(sve_get_vl() != last->sve_vl)) {
@@ -741,6 +751,10 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
 		sve_to_fpsimd(task);
 
+	if (system_supports_sme() && type == ARM64_VEC_SME)
+		task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK |
+				       SYS_SVCR_EL0_ZA_MASK);
+
 	if (task == current)
 		put_cpu_fpsimd_context();
 
@@ -1404,6 +1418,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
 	last->sve_vl = task_get_sve_vl(current);
+	last->svcr = &current->thread.svcr;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
 	if (system_supports_sve()) {
@@ -1418,7 +1433,7 @@ static void fpsimd_bind_task_to_cpu(void)
 }
 
 void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
-			      unsigned int sve_vl)
+			      unsigned int sve_vl, u64 *svcr)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1427,6 +1442,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	WARN_ON(!in_softirq() && !irqs_disabled());
 
 	last->st = st;
+	last->svcr = svcr;
 	last->sve_state = sve_state;
 	last->sve_vl = sve_vl;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index e20571f19718..07f235b46cf5 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -310,6 +310,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	dst->thread.sve_state = NULL;
 	clear_tsk_thread_flag(dst, TIF_SVE);
 
+	dst->thread.svcr = 0;
+
 	/* clear any pending asynchronous tag fault raised by the parent */
 	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
 
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 397fdac75cb1..ac09f1f682ff 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -109,9 +109,14 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 	WARN_ON_ONCE(!irqs_disabled());
 
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
+		/*
+		 * Currently we do not support SME guests so SVCR is
+		 * always 0 and we just need a variable to point to.
+		 */
 		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
 					 vcpu->arch.sve_state,
-					 vcpu->arch.sve_max_vl);
+					 vcpu->arch.sve_max_vl,
+					 NULL);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
-- 
cgit v1.2.3


From af7167d6d2675f3343eff3ad6c9b4a8e30122e2c Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:22 +0100
Subject: arm64/sme: Implement streaming SVE context switching

When in streaming mode we need to save and restore the streaming mode
SVE register state rather than the regular SVE register state. This uses
the streaming mode vector length and omits FFR but is otherwise identical,
if TIF_SVE is enabled when we are in streaming mode then streaming mode
takes precedence.

This does not handle use of streaming SVE state with KVM, ptrace or
signals. This will be updated in further patches.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-15-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h       |  22 ++++++-
 arch/arm64/include/asm/fpsimdmacros.h |  11 ++++
 arch/arm64/include/asm/processor.h    |  10 ++++
 arch/arm64/kernel/entry-fpsimd.S      |   5 ++
 arch/arm64/kernel/fpsimd.c            | 109 +++++++++++++++++++++++++++-------
 arch/arm64/kvm/fpsimd.c               |   2 +-
 6 files changed, 136 insertions(+), 23 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 821d270980da..cd94f5c5b516 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -47,11 +47,21 @@ extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 				     void *sve_state, unsigned int sve_vl,
-				     u64 *svcr);
+				     unsigned int sme_vl, u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
 
+static inline bool thread_sm_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK);
+}
+
+static inline bool thread_za_enabled(struct thread_struct *thread)
+{
+	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK);
+}
+
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
 #define VL_ARCH_MAX 0x100
 
@@ -63,7 +73,14 @@ static inline size_t sve_ffr_offset(int vl)
 
 static inline void *sve_pffr(struct thread_struct *thread)
 {
-	return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread));
+	unsigned int vl;
+
+	if (system_supports_sme() && thread_sm_enabled(thread))
+		vl = thread_get_sme_vl(thread);
+	else
+		vl = thread_get_sve_vl(thread);
+
+	return (char *)thread->sve_state + sve_ffr_offset(vl);
 }
 
 extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr);
@@ -72,6 +89,7 @@ extern void sve_load_state(void const *state, u32 const *pfpsr,
 extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
 extern unsigned int sve_get_vl(void);
 extern void sve_set_vq(unsigned long vq_minus_1);
+extern void sme_set_vq(unsigned long vq_minus_1);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 2e9a33155081..f6ab36e0cd8d 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -262,6 +262,17 @@
 921:
 .endm
 
+/* Update SMCR_EL1.LEN with the new VQ */
+.macro sme_load_vq xvqminus1, xtmp, xtmp2
+		mrs_s		\xtmp, SYS_SMCR_EL1
+		bic		\xtmp2, \xtmp, SMCR_ELx_LEN_MASK
+		orr		\xtmp2, \xtmp2, \xvqminus1
+		cmp		\xtmp2, \xtmp
+		b.eq		921f
+		msr_s		SYS_SMCR_EL1, \xtmp2	//self-synchronising
+921:
+.endm
+
 /* Preserve the first 128-bits of Znz and zero the rest. */
 .macro _sve_flush_z nz
 	_sve_check_zreg \nz
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 22cd11e86854..7542310b4e6b 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -184,6 +184,11 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread)
 	return thread_get_vl(thread, ARM64_VEC_SVE);
 }
 
+static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
+{
+	return thread_get_vl(thread, ARM64_VEC_SME);
+}
+
 unsigned int task_get_vl(const struct task_struct *task, enum vec_type type);
 void task_set_vl(struct task_struct *task, enum vec_type type,
 		 unsigned long vl);
@@ -197,6 +202,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task)
 	return task_get_vl(task, ARM64_VEC_SVE);
 }
 
+static inline unsigned int task_get_sme_vl(const struct task_struct *task)
+{
+	return task_get_vl(task, ARM64_VEC_SME);
+}
+
 static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl)
 {
 	task_set_vl(task, ARM64_VEC_SVE, vl);
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index deee5f01462e..6f88c0f86d50 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -94,4 +94,9 @@ SYM_FUNC_START(sme_get_vl)
 	ret
 SYM_FUNC_END(sme_get_vl)
 
+SYM_FUNC_START(sme_set_vq)
+	sme_load_vq x0, x1, x2
+	ret
+SYM_FUNC_END(sme_set_vq)
+
 #endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 1c113349f6cc..f8506a875eb2 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -123,6 +123,7 @@ struct fpsimd_last_state_struct {
 	void *sve_state;
 	u64 *svcr;
 	unsigned int sve_vl;
+	unsigned int sme_vl;
 };
 
 static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
@@ -301,17 +302,28 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
 	task->thread.vl_onexec[type] = vl;
 }
 
+/*
+ * TIF_SME controls whether a task can use SME without trapping while
+ * in userspace, when TIF_SME is set then we must have storage
+ * alocated in sve_state and za_state to store the contents of both ZA
+ * and the SVE registers for both streaming and non-streaming modes.
+ *
+ * If both SVCR.ZA and SVCR.SM are disabled then at any point we
+ * may disable TIF_SME and reenable traps.
+ */
+
+
 /*
  * TIF_SVE controls whether a task can use SVE without trapping while
- * in userspace, and also the way a task's FPSIMD/SVE state is stored
- * in thread_struct.
+ * in userspace, and also (together with TIF_SME) the way a task's
+ * FPSIMD/SVE state is stored in thread_struct.
  *
  * The kernel uses this flag to track whether a user task is actively
  * using SVE, and therefore whether full SVE register state needs to
  * be tracked.  If not, the cheaper FPSIMD context handling code can
  * be used instead of the more costly SVE equivalents.
  *
- *  * TIF_SVE set:
+ *  * TIF_SVE or SVCR.SM set:
  *
  *    The task can execute SVE instructions while in userspace without
  *    trapping to the kernel.
@@ -319,7 +331,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  *    When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
  *    corresponding Zn), P0-P15 and FFR are encoded in in
  *    task->thread.sve_state, formatted appropriately for vector
- *    length task->thread.sve_vl.
+ *    length task->thread.sve_vl or, if SVCR.SM is set,
+ *    task->thread.sme_vl.
  *
  *    task->thread.sve_state must point to a valid buffer at least
  *    sve_state_size(task) bytes in size.
@@ -357,19 +370,40 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
  */
 static void task_fpsimd_load(void)
 {
+	bool restore_sve_regs = false;
+	bool restore_ffr;
+
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
 
-	if (IS_ENABLED(CONFIG_ARM64_SME) && test_thread_flag(TIF_SME))
-		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
-
+	/* Check if we should restore SVE first */
 	if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
 		sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
+		restore_sve_regs = true;
+		restore_ffr = true;
+	}
+
+	/* Restore SME, override SVE register configuration if needed */
+	if (system_supports_sme()) {
+		unsigned long sme_vl = task_get_sme_vl(current);
+
+		if (test_thread_flag(TIF_SME))
+			sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
+
+		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
+
+		if (thread_sm_enabled(&current->thread)) {
+			restore_sve_regs = true;
+			restore_ffr = system_supports_fa64();
+		}
+	}
+
+	if (restore_sve_regs)
 		sve_load_state(sve_pffr(&current->thread),
-			       &current->thread.uw.fpsimd_state.fpsr, true);
-	} else {
+			       &current->thread.uw.fpsimd_state.fpsr,
+			       restore_ffr);
+	else
 		fpsimd_load_state(&current->thread.uw.fpsimd_state);
-	}
 }
 
 /*
@@ -387,6 +421,9 @@ static void fpsimd_save(void)
 	struct fpsimd_last_state_struct const *last =
 		this_cpu_ptr(&fpsimd_last_state);
 	/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
+	bool save_sve_regs = false;
+	bool save_ffr;
+	unsigned int vl;
 
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());
@@ -394,15 +431,33 @@ static void fpsimd_save(void)
 	if (test_thread_flag(TIF_FOREIGN_FPSTATE))
 		return;
 
-	if (IS_ENABLED(CONFIG_ARM64_SME) &&
-	    test_thread_flag(TIF_SME)) {
+	if (test_thread_flag(TIF_SVE)) {
+		save_sve_regs = true;
+		save_ffr = true;
+		vl = last->sve_vl;
+	}
+
+	if (system_supports_sme()) {
 		u64 *svcr = last->svcr;
 		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+		if (thread_za_enabled(&current->thread)) {
+			/* ZA state managment is not implemented yet */
+			force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
+			return;
+		}
+
+		/* If we are in streaming mode override regular SVE. */
+		if (*svcr & SYS_SVCR_EL0_SM_MASK) {
+			save_sve_regs = true;
+			save_ffr = system_supports_fa64();
+			vl = last->sme_vl;
+		}
 	}
 
-	if (IS_ENABLED(CONFIG_ARM64_SVE) &&
-	    test_thread_flag(TIF_SVE)) {
-		if (WARN_ON(sve_get_vl() != last->sve_vl)) {
+	if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) {
+		/* Get the configured VL from RDVL, will account for SM */
+		if (WARN_ON(sve_get_vl() != vl)) {
 			/*
 			 * Can't save the user regs, so current would
 			 * re-enter user with corrupt state.
@@ -413,8 +468,8 @@ static void fpsimd_save(void)
 		}
 
 		sve_save_state((char *)last->sve_state +
-					sve_ffr_offset(last->sve_vl),
-			       &last->st->fpsr, true);
+					sve_ffr_offset(vl),
+			       &last->st->fpsr, save_ffr);
 	} else {
 		fpsimd_save_state(last->st);
 	}
@@ -619,7 +674,14 @@ static void sve_to_fpsimd(struct task_struct *task)
  */
 static size_t sve_state_size(struct task_struct const *task)
 {
-	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task)));
+	unsigned int vl = 0;
+
+	if (system_supports_sve())
+		vl = task_get_sve_vl(task);
+	if (system_supports_sme())
+		vl = max(vl, task_get_sme_vl(task));
+
+	return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
 }
 
 /*
@@ -748,7 +810,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	}
 
 	fpsimd_flush_task_state(task);
-	if (test_and_clear_tsk_thread_flag(task, TIF_SVE))
+	if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
+	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 
 	if (system_supports_sme() && type == ARM64_VEC_SME)
@@ -1375,6 +1438,9 @@ void fpsimd_flush_thread(void)
 		fpsimd_flush_thread_vl(ARM64_VEC_SVE);
 	}
 
+	if (system_supports_sme())
+		fpsimd_flush_thread_vl(ARM64_VEC_SME);
+
 	put_cpu_fpsimd_context();
 }
 
@@ -1418,6 +1484,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
 	last->sve_vl = task_get_sve_vl(current);
+	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
@@ -1433,7 +1500,8 @@ static void fpsimd_bind_task_to_cpu(void)
 }
 
 void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
-			      unsigned int sve_vl, u64 *svcr)
+			      unsigned int sve_vl, unsigned int sme_vl,
+			      u64 *svcr)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1445,6 +1513,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	last->svcr = svcr;
 	last->sve_state = sve_state;
 	last->sve_vl = sve_vl;
+	last->sme_vl = sme_vl;
 }
 
 /*
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index ac09f1f682ff..394e583bb73e 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -116,7 +116,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
 					 vcpu->arch.sve_state,
 					 vcpu->arch.sve_max_vl,
-					 NULL);
+					 0, NULL);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
-- 
cgit v1.2.3


From 0033cd9339642f9b7bef23f96aa2e7277ab51cce Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:23 +0100
Subject: arm64/sme: Implement ZA context switching

Allocate space for storing ZA on first access to SME and use that to save
and restore ZA state when context switching. We do this by using the vector
form of the LDR and STR ZA instructions, these do not require streaming
mode and have implementation recommendations that they avoid contention
issues in shared SMCU implementations.

Since ZA is architecturally guaranteed to be zeroed when enabled we do not
need to explicitly zero ZA, either we will be restoring from a saved copy
or trapping on first use of SME so we know that ZA must be disabled.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-16-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h       |  5 ++++-
 arch/arm64/include/asm/fpsimdmacros.h | 22 ++++++++++++++++++++++
 arch/arm64/include/asm/kvm_host.h     |  3 +++
 arch/arm64/include/asm/processor.h    |  1 +
 arch/arm64/kernel/entry-fpsimd.S      | 22 ++++++++++++++++++++++
 arch/arm64/kernel/fpsimd.c            | 20 +++++++++++++-------
 arch/arm64/kvm/fpsimd.c               |  2 +-
 7 files changed, 66 insertions(+), 9 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index cd94f5c5b516..1a709c03bb6c 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -47,7 +47,8 @@ extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
 
 extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
 				     void *sve_state, unsigned int sve_vl,
-				     unsigned int sme_vl, u64 *svcr);
+				     void *za_state, unsigned int sme_vl,
+				     u64 *svcr);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);
@@ -90,6 +91,8 @@ extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1);
 extern unsigned int sve_get_vl(void);
 extern void sve_set_vq(unsigned long vq_minus_1);
 extern void sme_set_vq(unsigned long vq_minus_1);
+extern void za_save_state(void *state);
+extern void za_load_state(void const *state);
 
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index f6ab36e0cd8d..5e0910cf4832 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -319,3 +319,25 @@
 		ldr		w\nxtmp, [\xpfpsr, #4]
 		msr		fpcr, x\nxtmp
 .endm
+
+.macro sme_save_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_str_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
+
+.macro sme_load_za nxbase, xvl, nw
+	mov	w\nw, #0
+
+423:
+	_sme_ldr_zav \nw, \nxbase
+	add	x\nxbase, x\nxbase, \xvl
+	add	x\nw, x\nw, #1
+	cmp	\xvl, x\nw
+	bne	423b
+.endm
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 94a27a7520f4..8a7c442d5b57 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -295,8 +295,11 @@ struct vcpu_reset_state {
 
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
+
+	/* Guest floating point state */
 	void *sve_state;
 	unsigned int sve_max_vl;
+	u64 svcr;
 
 	/* Stage 2 paging state used by the hardware on next switch */
 	struct kvm_s2_mmu *hw_mmu;
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 7542310b4e6b..6a3a6c3dec90 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -154,6 +154,7 @@ struct thread_struct {
 
 	unsigned int		fpsimd_cpu;
 	void			*sve_state;	/* SVE registers, if any */
+	void			*za_state;	/* ZA register, if any */
 	unsigned int		vl[ARM64_VEC_MAX];	/* vector length */
 	unsigned int		vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */
 	unsigned long		fault_address;	/* fault info */
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 6f88c0f86d50..229436f33df5 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -99,4 +99,26 @@ SYM_FUNC_START(sme_set_vq)
 	ret
 SYM_FUNC_END(sme_set_vq)
 
+/*
+ * Save the SME state
+ *
+ * x0 - pointer to buffer for state
+ */
+SYM_FUNC_START(za_save_state)
+	_sme_rdsvl	1, 1		// x1 = VL/8
+	sme_save_za 0, x1, 12
+	ret
+SYM_FUNC_END(za_save_state)
+
+/*
+ * Load the SME state
+ *
+ * x0 - pointer to buffer for state
+ */
+SYM_FUNC_START(za_load_state)
+	_sme_rdsvl	1, 1		// x1 = VL/8
+	sme_load_za 0, x1, 12
+	ret
+SYM_FUNC_END(za_load_state)
+
 #endif /* CONFIG_ARM64_SME */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index f8506a875eb2..dc38f3f2a28a 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -121,6 +121,7 @@
 struct fpsimd_last_state_struct {
 	struct user_fpsimd_state *st;
 	void *sve_state;
+	void *za_state;
 	u64 *svcr;
 	unsigned int sve_vl;
 	unsigned int sme_vl;
@@ -387,11 +388,15 @@ static void task_fpsimd_load(void)
 	if (system_supports_sme()) {
 		unsigned long sme_vl = task_get_sme_vl(current);
 
+		/* Ensure VL is set up for restoring data */
 		if (test_thread_flag(TIF_SME))
 			sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
 
 		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
 
+		if (thread_za_enabled(&current->thread))
+			za_load_state(current->thread.za_state);
+
 		if (thread_sm_enabled(&current->thread)) {
 			restore_sve_regs = true;
 			restore_ffr = system_supports_fa64();
@@ -441,11 +446,10 @@ static void fpsimd_save(void)
 		u64 *svcr = last->svcr;
 		*svcr = read_sysreg_s(SYS_SVCR_EL0);
 
-		if (thread_za_enabled(&current->thread)) {
-			/* ZA state managment is not implemented yet */
-			force_signal_inject(SIGKILL, SI_KERNEL, 0, 0);
-			return;
-		}
+		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+		if (*svcr & SYS_SVCR_EL0_ZA_MASK)
+			za_save_state(last->za_state);
 
 		/* If we are in streaming mode override regular SVE. */
 		if (*svcr & SYS_SVCR_EL0_SM_MASK) {
@@ -1483,6 +1487,7 @@ static void fpsimd_bind_task_to_cpu(void)
 	WARN_ON(!system_supports_fpsimd());
 	last->st = &current->thread.uw.fpsimd_state;
 	last->sve_state = current->thread.sve_state;
+	last->za_state = current->thread.za_state;
 	last->sve_vl = task_get_sve_vl(current);
 	last->sme_vl = task_get_sme_vl(current);
 	last->svcr = &current->thread.svcr;
@@ -1500,8 +1505,8 @@ static void fpsimd_bind_task_to_cpu(void)
 }
 
 void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
-			      unsigned int sve_vl, unsigned int sme_vl,
-			      u64 *svcr)
+			      unsigned int sve_vl, void *za_state,
+			      unsigned int sme_vl, u64 *svcr)
 {
 	struct fpsimd_last_state_struct *last =
 		this_cpu_ptr(&fpsimd_last_state);
@@ -1512,6 +1517,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
 	last->st = st;
 	last->svcr = svcr;
 	last->sve_state = sve_state;
+	last->za_state = za_state;
 	last->sve_vl = sve_vl;
 	last->sme_vl = sme_vl;
 }
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 394e583bb73e..57d7ac3cfa0c 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -116,7 +116,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
 					 vcpu->arch.sve_state,
 					 vcpu->arch.sve_max_vl,
-					 0, NULL);
+					 NULL, 0, &vcpu->arch.svcr);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
-- 
cgit v1.2.3


From 8bd7f91c03d886f41d35f6108078d20be5a4a1bd Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:24 +0100
Subject: arm64/sme: Implement traps and syscall handling for SME

By default all SME operations in userspace will trap.  When this happens
we allocate storage space for the SME register state, set up the SVE
registers and disable traps.  We do not need to initialize ZA since the
architecture guarantees that it will be zeroed when enabled and when we
trap ZA is disabled.

On syscall we exit streaming mode if we were previously in it and ensure
that all but the lower 128 bits of the registers are zeroed while
preserving the state of ZA. This follows the aarch64 PCS for SME, ZA
state is preserved over a function call and streaming mode is exited.
Since the traps for SME do not distinguish between streaming mode SVE
and ZA usage if ZA is in use rather than reenabling traps we instead
zero the parts of the SVE registers not shared with FPSIMD and leave SME
enabled, this simplifies handling SME traps. If ZA is not in use then we
reenable SME traps and fall through to normal handling of SVE.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-17-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/esr.h       |   1 +
 arch/arm64/include/asm/exception.h |   1 +
 arch/arm64/include/asm/fpsimd.h    |  39 +++++++++
 arch/arm64/kernel/entry-common.c   |  11 +++
 arch/arm64/kernel/fpsimd.c         | 167 +++++++++++++++++++++++++++++++++----
 arch/arm64/kernel/process.c        |  30 ++++++-
 arch/arm64/kernel/syscall.c        |  29 ++++++-
 7 files changed, 255 insertions(+), 23 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 43872e0cfd1e..0467837fd66b 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -76,6 +76,7 @@
 #define ESR_ELx_IL_SHIFT	(25)
 #define ESR_ELx_IL		(UL(1) << ESR_ELx_IL_SHIFT)
 #define ESR_ELx_ISS_MASK	(ESR_ELx_IL - 1)
+#define ESR_ELx_ISS(esr)	((esr) & ESR_ELx_ISS_MASK)
 
 /* ISS field definitions shared by different classes */
 #define ESR_ELx_WNR_SHIFT	(6)
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 339477dca551..2add7f33b7c2 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -64,6 +64,7 @@ void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 			struct pt_regs *regs);
 void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs);
 void do_sve_acc(unsigned int esr, struct pt_regs *regs);
+void do_sme_acc(unsigned int esr, struct pt_regs *regs);
 void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs);
 void do_sysinstr(unsigned int esr, struct pt_regs *regs);
 void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 1a709c03bb6c..6c33bc832ed4 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -239,6 +239,8 @@ static inline bool sve_vq_available(unsigned int vq)
 	return vq_available(ARM64_VEC_SVE, vq);
 }
 
+size_t sve_state_size(struct task_struct const *task);
+
 #else /* ! CONFIG_ARM64_SVE */
 
 static inline void sve_alloc(struct task_struct *task) { }
@@ -278,10 +280,25 @@ static inline void vec_update_vq_map(enum vec_type t) { }
 static inline int vec_verify_vq_map(enum vec_type t) { return 0; }
 static inline void sve_setup(void) { }
 
+static inline size_t sve_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
 #endif /* ! CONFIG_ARM64_SVE */
 
 #ifdef CONFIG_ARM64_SME
 
+static inline void sme_user_disable(void)
+{
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0);
+}
+
+static inline void sme_user_enable(void)
+{
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN);
+}
+
 static inline void sme_smstart_sm(void)
 {
 	asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr"));
@@ -309,16 +326,33 @@ static inline int sme_max_virtualisable_vl(void)
 	return vec_max_virtualisable_vl(ARM64_VEC_SME);
 }
 
+extern void sme_alloc(struct task_struct *task);
 extern unsigned int sme_get_vl(void);
 extern int sme_set_current_vl(unsigned long arg);
 extern int sme_get_current_vl(void);
 
+/*
+ * Return how many bytes of memory are required to store the full SME
+ * specific state (currently just ZA) for task, given task's currently
+ * configured vector length.
+ */
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	unsigned int vl = task_get_sme_vl(task);
+
+	return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+}
+
 #else
 
+static inline void sme_user_disable(void) { BUILD_BUG(); }
+static inline void sme_user_enable(void) { BUILD_BUG(); }
+
 static inline void sme_smstart_sm(void) { }
 static inline void sme_smstop_sm(void) { }
 static inline void sme_smstop(void) { }
 
+static inline void sme_alloc(struct task_struct *task) { }
 static inline void sme_setup(void) { }
 static inline unsigned int sme_get_vl(void) { return 0; }
 static inline int sme_max_vl(void) { return 0; }
@@ -326,6 +360,11 @@ static inline int sme_max_virtualisable_vl(void) { return 0; }
 static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
 static inline int sme_get_current_vl(void) { return -EINVAL; }
 
+static inline size_t za_state_size(struct task_struct const *task)
+{
+	return 0;
+}
+
 #endif /* ! CONFIG_ARM64_SME */
 
 /* For use by EFI runtime services calls only */
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 878c65aa7206..29139e9a1517 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -537,6 +537,14 @@ static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr)
 	exit_to_user_mode(regs);
 }
 
+static void noinstr el0_sme_acc(struct pt_regs *regs, unsigned long esr)
+{
+	enter_from_user_mode(regs);
+	local_daif_restore(DAIF_PROCCTX);
+	do_sme_acc(esr, regs);
+	exit_to_user_mode(regs);
+}
+
 static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
 {
 	enter_from_user_mode(regs);
@@ -645,6 +653,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs)
 	case ESR_ELx_EC_SVE:
 		el0_sve_acc(regs, esr);
 		break;
+	case ESR_ELx_EC_SME:
+		el0_sme_acc(regs, esr);
+		break;
 	case ESR_ELx_EC_FP_EXC64:
 		el0_fpsimd_exc(regs, esr);
 		break;
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index dc38f3f2a28a..00a0cbd01ce5 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -209,6 +209,12 @@ static void set_sme_default_vl(int val)
 	set_default_vl(ARM64_VEC_SME, val);
 }
 
+static void sme_free(struct task_struct *);
+
+#else
+
+static inline void sme_free(struct task_struct *t) { }
+
 #endif
 
 DEFINE_PER_CPU(bool, fpsimd_context_busy);
@@ -676,7 +682,7 @@ static void sve_to_fpsimd(struct task_struct *task)
  * Return how many bytes of memory are required to store the full SVE
  * state for task, given task's currently configured vector length.
  */
-static size_t sve_state_size(struct task_struct const *task)
+size_t sve_state_size(struct task_struct const *task)
 {
 	unsigned int vl = 0;
 
@@ -818,18 +824,22 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 
-	if (system_supports_sme() && type == ARM64_VEC_SME)
+	if (system_supports_sme() && type == ARM64_VEC_SME) {
 		task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK |
 				       SYS_SVCR_EL0_ZA_MASK);
+		clear_thread_flag(TIF_SME);
+	}
 
 	if (task == current)
 		put_cpu_fpsimd_context();
 
 	/*
-	 * Force reallocation of task SVE state to the correct size
-	 * on next use:
+	 * Force reallocation of task SVE and SME state to the correct
+	 * size on next use:
 	 */
 	sve_free(task);
+	if (system_supports_sme() && type == ARM64_VEC_SME)
+		sme_free(task);
 
 	task_set_vl(task, type, vl);
 
@@ -1164,12 +1174,43 @@ void __init sve_setup(void)
 void fpsimd_release_task(struct task_struct *dead_task)
 {
 	__sve_free(dead_task);
+	sme_free(dead_task);
 }
 
 #endif /* CONFIG_ARM64_SVE */
 
 #ifdef CONFIG_ARM64_SME
 
+/* This will move to uapi/asm/sigcontext.h when signals are implemented */
+#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES))
+
+/*
+ * Ensure that task->thread.za_state is allocated and sufficiently large.
+ *
+ * This function should be used only in preparation for replacing
+ * task->thread.za_state with new data.  The memory is always zeroed
+ * here to prevent stale data from showing through: this is done in
+ * the interest of testability and predictability, the architecture
+ * guarantees that when ZA is enabled it will be zeroed.
+ */
+void sme_alloc(struct task_struct *task)
+{
+	if (task->thread.za_state) {
+		memset(task->thread.za_state, 0, za_state_size(task));
+		return;
+	}
+
+	/* This could potentially be up to 64K. */
+	task->thread.za_state =
+		kzalloc(za_state_size(task), GFP_KERNEL);
+}
+
+static void sme_free(struct task_struct *task)
+{
+	kfree(task->thread.za_state);
+	task->thread.za_state = NULL;
+}
+
 void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
 {
 	/* Set priority for all PEs to architecturally defined minimum */
@@ -1279,6 +1320,29 @@ void __init sme_setup(void)
 
 #endif /* CONFIG_ARM64_SME */
 
+static void sve_init_regs(void)
+{
+	/*
+	 * Convert the FPSIMD state to SVE, zeroing all the state that
+	 * is not shared with FPSIMD. If (as is likely) the current
+	 * state is live in the registers then do this there and
+	 * update our metadata for the current task including
+	 * disabling the trap, otherwise update our in-memory copy.
+	 * We are guaranteed to not be in streaming mode, we can only
+	 * take a SVE trap when not in streaming mode and we can't be
+	 * in streaming mode when taking a SME trap.
+	 */
+	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		unsigned long vq_minus_one =
+			sve_vq_from_vl(task_get_sve_vl(current)) - 1;
+		sve_set_vq(vq_minus_one);
+		sve_flush_live(true, vq_minus_one);
+		fpsimd_bind_task_to_cpu();
+	} else {
+		fpsimd_to_sve(current);
+	}
+}
+
 /*
  * Trapped SVE access
  *
@@ -1310,22 +1374,77 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs)
 		WARN_ON(1); /* SVE access shouldn't have trapped */
 
 	/*
-	 * Convert the FPSIMD state to SVE, zeroing all the state that
-	 * is not shared with FPSIMD. If (as is likely) the current
-	 * state is live in the registers then do this there and
-	 * update our metadata for the current task including
-	 * disabling the trap, otherwise update our in-memory copy.
+	 * Even if the task can have used streaming mode we can only
+	 * generate SVE access traps in normal SVE mode and
+	 * transitioning out of streaming mode may discard any
+	 * streaming mode state.  Always clear the high bits to avoid
+	 * any potential errors tracking what is properly initialised.
+	 */
+	sve_init_regs();
+
+	put_cpu_fpsimd_context();
+}
+
+/*
+ * Trapped SME access
+ *
+ * Storage is allocated for the full SVE and SME state, the current
+ * FPSIMD register contents are migrated to SVE if SVE is not already
+ * active, and the access trap is disabled.
+ *
+ * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state()
+ * would have disabled the SME access trap for userspace during
+ * ret_to_user, making an SVE access trap impossible in that case.
+ */
+void do_sme_acc(unsigned int esr, struct pt_regs *regs)
+{
+	/* Even if we chose not to use SME, the hardware could still trap: */
+	if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) {
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+		return;
+	}
+
+	/*
+	 * If this not a trap due to SME being disabled then something
+	 * is being used in the wrong mode, report as SIGILL.
 	 */
+	if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) {
+		force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
+		return;
+	}
+
+	sve_alloc(current);
+	sme_alloc(current);
+	if (!current->thread.sve_state || !current->thread.za_state) {
+		force_sig(SIGKILL);
+		return;
+	}
+
+	get_cpu_fpsimd_context();
+
+	/* With TIF_SME userspace shouldn't generate any traps */
+	if (test_and_set_thread_flag(TIF_SME))
+		WARN_ON(1);
+
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		unsigned long vq_minus_one =
-			sve_vq_from_vl(task_get_sve_vl(current)) - 1;
-		sve_set_vq(vq_minus_one);
-		sve_flush_live(true, vq_minus_one);
+			sve_vq_from_vl(task_get_sme_vl(current)) - 1;
+		sme_set_vq(vq_minus_one);
+
 		fpsimd_bind_task_to_cpu();
-	} else {
-		fpsimd_to_sve(current);
 	}
 
+	/*
+	 * If SVE was not already active initialise the SVE registers,
+	 * any non-shared state between the streaming and regular SVE
+	 * registers is architecturally guaranteed to be zeroed when
+	 * we enter streaming mode.  We do not need to initialize ZA
+	 * since ZA must be disabled at this point and enabling ZA is
+	 * architecturally defined to zero ZA.
+	 */
+	if (system_supports_sve() && !test_thread_flag(TIF_SVE))
+		sve_init_regs();
+
 	put_cpu_fpsimd_context();
 }
 
@@ -1442,8 +1561,12 @@ void fpsimd_flush_thread(void)
 		fpsimd_flush_thread_vl(ARM64_VEC_SVE);
 	}
 
-	if (system_supports_sme())
+	if (system_supports_sme()) {
+		clear_thread_flag(TIF_SME);
+		sme_free(current);
 		fpsimd_flush_thread_vl(ARM64_VEC_SME);
+		current->thread.svcr = 0;
+	}
 
 	put_cpu_fpsimd_context();
 }
@@ -1493,14 +1616,22 @@ static void fpsimd_bind_task_to_cpu(void)
 	last->svcr = &current->thread.svcr;
 	current->thread.fpsimd_cpu = smp_processor_id();
 
+	/*
+	 * Toggle SVE and SME trapping for userspace if needed, these
+	 * are serialsied by ret_to_user().
+	 */
+	if (system_supports_sme()) {
+		if (test_thread_flag(TIF_SME))
+			sme_user_enable();
+		else
+			sme_user_disable();
+	}
+
 	if (system_supports_sve()) {
-		/* Toggle SVE trapping for userspace if needed */
 		if (test_thread_flag(TIF_SVE))
 			sve_user_enable();
 		else
 			sve_user_disable();
-
-		/* Serialised by exception return to user */
 	}
 }
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 07f235b46cf5..99c293513817 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -300,17 +300,41 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	/*
 	 * Detach src's sve_state (if any) from dst so that it does not
-	 * get erroneously used or freed prematurely.  dst's sve_state
+	 * get erroneously used or freed prematurely.  dst's copies
 	 * will be allocated on demand later on if dst uses SVE.
 	 * For consistency, also clear TIF_SVE here: this could be done
 	 * later in copy_process(), but to avoid tripping up future
-	 * maintainers it is best not to leave TIF_SVE and sve_state in
+	 * maintainers it is best not to leave TIF flags and buffers in
 	 * an inconsistent state, even temporarily.
 	 */
 	dst->thread.sve_state = NULL;
 	clear_tsk_thread_flag(dst, TIF_SVE);
 
-	dst->thread.svcr = 0;
+	/*
+	 * In the unlikely event that we create a new thread with ZA
+	 * enabled we should retain the ZA state so duplicate it here.
+	 * This may be shortly freed if we exec() or if CLONE_SETTLS
+	 * but it's simpler to do it here. To avoid confusing the rest
+	 * of the code ensure that we have a sve_state allocated
+	 * whenever za_state is allocated.
+	 */
+	if (thread_za_enabled(&src->thread)) {
+		dst->thread.sve_state = kzalloc(sve_state_size(src),
+						GFP_KERNEL);
+		if (!dst->thread.za_state)
+			return -ENOMEM;
+		dst->thread.za_state = kmemdup(src->thread.za_state,
+					       za_state_size(src),
+					       GFP_KERNEL);
+		if (!dst->thread.za_state) {
+			kfree(dst->thread.sve_state);
+			dst->thread.sve_state = NULL;
+			return -ENOMEM;
+		}
+	} else {
+		dst->thread.za_state = NULL;
+		clear_tsk_thread_flag(dst, TIF_SME);
+	}
 
 	/* clear any pending asynchronous tag fault raised by the parent */
 	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index c938603b3ba0..92c69e5ac269 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -158,11 +158,36 @@ trace_exit:
 	syscall_trace_exit(regs);
 }
 
-static inline void sve_user_discard(void)
+/*
+ * As per the ABI exit SME streaming mode and clear the SVE state not
+ * shared with FPSIMD on syscall entry.
+ */
+static inline void fp_user_discard(void)
 {
+	/*
+	 * If SME is active then exit streaming mode.  If ZA is active
+	 * then flush the SVE registers but leave userspace access to
+	 * both SVE and SME enabled, otherwise disable SME for the
+	 * task and fall through to disabling SVE too.  This means
+	 * that after a syscall we never have any streaming mode
+	 * register state to track, if this changes the KVM code will
+	 * need updating.
+	 */
+	if (system_supports_sme() && test_thread_flag(TIF_SME)) {
+		u64 svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+		if (svcr & SYS_SVCR_EL0_SM_MASK)
+			sme_smstop_sm();
+	}
+
 	if (!system_supports_sve())
 		return;
 
+	/*
+	 * If SME is not active then disable SVE, the registers will
+	 * be cleared when userspace next attempts to access them and
+	 * we do not need to track the SVE register state until then.
+	 */
 	clear_thread_flag(TIF_SVE);
 
 	/*
@@ -177,7 +202,7 @@ static inline void sve_user_discard(void)
 
 void do_el0_svc(struct pt_regs *regs)
 {
-	sve_user_discard();
+	fp_user_discard();
 	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
 }
 
-- 
cgit v1.2.3


From e12310a0d30f260b26297bc8d7c95769489af038 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 19 Apr 2022 12:22:28 +0100
Subject: arm64/sme: Implement ptrace support for streaming mode SVE registers

The streaming mode SVE registers are represented using the same data
structures as for SVE but since the vector lengths supported and in use
may not be the same as SVE we represent them with a new type NT_ARM_SSVE.
Unfortunately we only have a single 16 bit reserved field available in
the header so there is no space to fit the current and maximum vector
length for both standard and streaming SVE mode without redefining the
structure in a way the creates a complicatd and fragile ABI. Since FFR
is not present in streaming mode it is read and written as zero.

Setting NT_ARM_SSVE registers will put the task into streaming mode,
similarly setting NT_ARM_SVE registers will exit it. Reads that do not
correspond to the current mode of the task will return the header with
no register data. For compatibility reasons on write setting no flag for
the register type will be interpreted as setting SVE registers, though
users can provide no register data as an alternative mechanism for doing
so.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20220419112247.711548-21-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h      |   1 +
 arch/arm64/include/uapi/asm/ptrace.h |  13 ++-
 arch/arm64/kernel/fpsimd.c           |  31 +++--
 arch/arm64/kernel/ptrace.c           | 214 +++++++++++++++++++++++++++--------
 include/uapi/linux/elf.h             |   1 +
 5 files changed, 201 insertions(+), 59 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 6c33bc832ed4..5afcd0709aae 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -144,6 +144,7 @@ struct vl_info {
 extern void sve_alloc(struct task_struct *task);
 extern void fpsimd_release_task(struct task_struct *task);
 extern void fpsimd_sync_to_sve(struct task_struct *task);
+extern void fpsimd_force_sync_to_sve(struct task_struct *task);
 extern void sve_sync_to_fpsimd(struct task_struct *task);
 extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
 
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 758ae984ff97..522b925a78c1 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -109,7 +109,7 @@ struct user_hwdebug_state {
 	}		dbg_regs[16];
 };
 
-/* SVE/FP/SIMD state (NT_ARM_SVE) */
+/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */
 
 struct user_sve_header {
 	__u32 size; /* total meaningful regset content in bytes */
@@ -220,6 +220,7 @@ struct user_sve_header {
 	(SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \
 		SVE_PT_SVE_PREGS_OFFSET(vq))
 
+/* For streaming mode SVE (SSVE) FFR must be read and written as zero */
 #define SVE_PT_SVE_FFR_OFFSET(vq) \
 	(SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq))
 
@@ -240,10 +241,12 @@ struct user_sve_header {
 			- SVE_PT_SVE_OFFSET + (__SVE_VQ_BYTES - 1))	\
 		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
 
-#define SVE_PT_SIZE(vq, flags)						\
-	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		\
-		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	\
-		: SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags))
+#define SVE_PT_SIZE(vq, flags)						  \
+	 (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ?		  \
+		  SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags)	  \
+		: ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ?  \
+		    SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \
+		  : SVE_PT_REGS_OFFSET)))
 
 /* pointer authentication masks (NT_ARM_PAC_MASK) */
 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 80f7ca12f855..94f06e9d37cf 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -643,7 +643,7 @@ static void fpsimd_to_sve(struct task_struct *task)
 	if (!system_supports_sve())
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
 	__fpsimd_to_sve(sst, fst, vq);
 }
 
@@ -660,7 +660,7 @@ static void fpsimd_to_sve(struct task_struct *task)
  */
 static void sve_to_fpsimd(struct task_struct *task)
 {
-	unsigned int vq;
+	unsigned int vq, vl;
 	void const *sst = task->thread.sve_state;
 	struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state;
 	unsigned int i;
@@ -669,7 +669,8 @@ static void sve_to_fpsimd(struct task_struct *task)
 	if (!system_supports_sve())
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vl = thread_get_cur_vl(&task->thread);
+	vq = sve_vq_from_vl(vl);
 	for (i = 0; i < SVE_NUM_ZREGS; ++i) {
 		p = (__uint128_t const *)ZREG(sst, vq, i);
 		fst->vregs[i] = arm64_le128_to_cpu(*p);
@@ -717,6 +718,19 @@ void sve_alloc(struct task_struct *task)
 }
 
 
+/*
+ * Force the FPSIMD state shared with SVE to be updated in the SVE state
+ * even if the SVE state is the current active state.
+ *
+ * This should only be called by ptrace.  task must be non-runnable.
+ * task->thread.sve_state must point to at least sve_state_size(task)
+ * bytes of allocated kernel memory.
+ */
+void fpsimd_force_sync_to_sve(struct task_struct *task)
+{
+	fpsimd_to_sve(task);
+}
+
 /*
  * Ensure that task->thread.sve_state is up to date with respect to
  * the user task, irrespective of when SVE is in use or not.
@@ -727,7 +741,8 @@ void sve_alloc(struct task_struct *task)
  */
 void fpsimd_sync_to_sve(struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SVE))
+	if (!test_tsk_thread_flag(task, TIF_SVE) &&
+	    !thread_sm_enabled(&task->thread))
 		fpsimd_to_sve(task);
 }
 
@@ -741,7 +756,8 @@ void fpsimd_sync_to_sve(struct task_struct *task)
  */
 void sve_sync_to_fpsimd(struct task_struct *task)
 {
-	if (test_tsk_thread_flag(task, TIF_SVE))
+	if (test_tsk_thread_flag(task, TIF_SVE) ||
+	    thread_sm_enabled(&task->thread))
 		sve_to_fpsimd(task);
 }
 
@@ -766,7 +782,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
 	if (!test_tsk_thread_flag(task, TIF_SVE))
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
 
 	memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
 	__fpsimd_to_sve(sst, fst, vq);
@@ -810,8 +826,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 	/*
 	 * To ensure the FPSIMD bits of the SVE vector registers are preserved,
 	 * write any live register state back to task_struct, and convert to a
-	 * regular FPSIMD thread.  Since the vector length can only be changed
-	 * with a syscall we can't be in streaming mode while reconfiguring.
+	 * regular FPSIMD thread.
 	 */
 	if (task == current) {
 		get_cpu_fpsimd_context();
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 230a47b9189e..60185c27b394 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -713,21 +713,51 @@ static int system_call_set(struct task_struct *target,
 #ifdef CONFIG_ARM64_SVE
 
 static void sve_init_header_from_task(struct user_sve_header *header,
-				      struct task_struct *target)
+				      struct task_struct *target,
+				      enum vec_type type)
 {
 	unsigned int vq;
+	bool active;
+	bool fpsimd_only;
+	enum vec_type task_type;
 
 	memset(header, 0, sizeof(*header));
 
-	header->flags = test_tsk_thread_flag(target, TIF_SVE) ?
-		SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD;
-	if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
-		header->flags |= SVE_PT_VL_INHERIT;
+	/* Check if the requested registers are active for the task */
+	if (thread_sm_enabled(&target->thread))
+		task_type = ARM64_VEC_SME;
+	else
+		task_type = ARM64_VEC_SVE;
+	active = (task_type == type);
+
+	switch (type) {
+	case ARM64_VEC_SVE:
+		if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
+			header->flags |= SVE_PT_VL_INHERIT;
+		fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE);
+		break;
+	case ARM64_VEC_SME:
+		if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
+			header->flags |= SVE_PT_VL_INHERIT;
+		fpsimd_only = false;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
 
-	header->vl = task_get_sve_vl(target);
+	if (active) {
+		if (fpsimd_only) {
+			header->flags |= SVE_PT_REGS_FPSIMD;
+		} else {
+			header->flags |= SVE_PT_REGS_SVE;
+		}
+	}
+
+	header->vl = task_get_vl(target, type);
 	vq = sve_vq_from_vl(header->vl);
 
-	header->max_vl = sve_max_vl();
+	header->max_vl = vec_max_vl(type);
 	header->size = SVE_PT_SIZE(vq, header->flags);
 	header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl),
 				      SVE_PT_REGS_SVE);
@@ -738,19 +768,17 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header)
 	return ALIGN(header->size, SVE_VQ_BYTES);
 }
 
-static int sve_get(struct task_struct *target,
-		   const struct user_regset *regset,
-		   struct membuf to)
+static int sve_get_common(struct task_struct *target,
+			  const struct user_regset *regset,
+			  struct membuf to,
+			  enum vec_type type)
 {
 	struct user_sve_header header;
 	unsigned int vq;
 	unsigned long start, end;
 
-	if (!system_supports_sve())
-		return -EINVAL;
-
 	/* Header */
-	sve_init_header_from_task(&header, target);
+	sve_init_header_from_task(&header, target, type);
 	vq = sve_vq_from_vl(header.vl);
 
 	membuf_write(&to, &header, sizeof(header));
@@ -758,49 +786,61 @@ static int sve_get(struct task_struct *target,
 	if (target == current)
 		fpsimd_preserve_current_state();
 
-	/* Registers: FPSIMD-only case */
-
 	BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
-	if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD)
+	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+
+	switch ((header.flags & SVE_PT_REGS_MASK)) {
+	case SVE_PT_REGS_FPSIMD:
 		return __fpr_get(target, regset, to);
 
-	/* Otherwise: full SVE case */
+	case SVE_PT_REGS_SVE:
+		start = SVE_PT_SVE_OFFSET;
+		end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
+		membuf_write(&to, target->thread.sve_state, end - start);
 
-	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
-	start = SVE_PT_SVE_OFFSET;
-	end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq);
-	membuf_write(&to, target->thread.sve_state, end - start);
+		start = end;
+		end = SVE_PT_SVE_FPSR_OFFSET(vq);
+		membuf_zero(&to, end - start);
 
-	start = end;
-	end = SVE_PT_SVE_FPSR_OFFSET(vq);
-	membuf_zero(&to, end - start);
+		/*
+		 * Copy fpsr, and fpcr which must follow contiguously in
+		 * struct fpsimd_state:
+		 */
+		start = end;
+		end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
+		membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr,
+			     end - start);
 
-	/*
-	 * Copy fpsr, and fpcr which must follow contiguously in
-	 * struct fpsimd_state:
-	 */
-	start = end;
-	end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE;
-	membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start);
+		start = end;
+		end = sve_size_from_header(&header);
+		return membuf_zero(&to, end - start);
 
-	start = end;
-	end = sve_size_from_header(&header);
-	return membuf_zero(&to, end - start);
+	default:
+		return 0;
+	}
 }
 
-static int sve_set(struct task_struct *target,
+static int sve_get(struct task_struct *target,
 		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
+		   struct membuf to)
+{
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	return sve_get_common(target, regset, to, ARM64_VEC_SVE);
+}
+
+static int sve_set_common(struct task_struct *target,
+			  const struct user_regset *regset,
+			  unsigned int pos, unsigned int count,
+			  const void *kbuf, const void __user *ubuf,
+			  enum vec_type type)
 {
 	int ret;
 	struct user_sve_header header;
 	unsigned int vq;
 	unsigned long start, end;
 
-	if (!system_supports_sve())
-		return -EINVAL;
-
 	/* Header */
 	if (count < sizeof(header))
 		return -EINVAL;
@@ -813,13 +853,37 @@ static int sve_set(struct task_struct *target,
 	 * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by
 	 * vec_set_vector_length(), which will also validate them for us:
 	 */
-	ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl,
+	ret = vec_set_vector_length(target, type, header.vl,
 		((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
 	if (ret)
 		goto out;
 
 	/* Actual VL set may be less than the user asked for: */
-	vq = sve_vq_from_vl(task_get_sve_vl(target));
+	vq = sve_vq_from_vl(task_get_vl(target, type));
+
+	/* Enter/exit streaming mode */
+	if (system_supports_sme()) {
+		u64 old_svcr = target->thread.svcr;
+
+		switch (type) {
+		case ARM64_VEC_SVE:
+			target->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK;
+			break;
+		case ARM64_VEC_SME:
+			target->thread.svcr |= SYS_SVCR_EL0_SM_MASK;
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
+
+		/*
+		 * If we switched then invalidate any existing SVE
+		 * state and ensure there's storage.
+		 */
+		if (target->thread.svcr != old_svcr)
+			sve_alloc(target);
+	}
 
 	/* Registers: FPSIMD-only case */
 
@@ -828,10 +892,15 @@ static int sve_set(struct task_struct *target,
 		ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
 				SVE_PT_FPSIMD_OFFSET);
 		clear_tsk_thread_flag(target, TIF_SVE);
+		if (type == ARM64_VEC_SME)
+			fpsimd_force_sync_to_sve(target);
 		goto out;
 	}
 
-	/* Otherwise: full SVE case */
+	/*
+	 * Otherwise: no registers or full SVE case.  For backwards
+	 * compatibility reasons we treat empty flags as SVE registers.
+	 */
 
 	/*
 	 * If setting a different VL from the requested VL and there is
@@ -852,8 +921,9 @@ static int sve_set(struct task_struct *target,
 
 	/*
 	 * Ensure target->thread.sve_state is up to date with target's
-	 * FPSIMD regs, so that a short copyin leaves trailing registers
-	 * unmodified.
+	 * FPSIMD regs, so that a short copyin leaves trailing
+	 * registers unmodified.  Always enable SVE even if going into
+	 * streaming mode.
 	 */
 	fpsimd_sync_to_sve(target);
 	set_tsk_thread_flag(target, TIF_SVE);
@@ -889,8 +959,46 @@ out:
 	return ret;
 }
 
+static int sve_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	if (!system_supports_sve())
+		return -EINVAL;
+
+	return sve_set_common(target, regset, pos, count, kbuf, ubuf,
+			      ARM64_VEC_SVE);
+}
+
 #endif /* CONFIG_ARM64_SVE */
 
+#ifdef CONFIG_ARM64_SME
+
+static int ssve_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	if (!system_supports_sme())
+		return -EINVAL;
+
+	return sve_get_common(target, regset, to, ARM64_VEC_SME);
+}
+
+static int ssve_set(struct task_struct *target,
+		    const struct user_regset *regset,
+		    unsigned int pos, unsigned int count,
+		    const void *kbuf, const void __user *ubuf)
+{
+	if (!system_supports_sme())
+		return -EINVAL;
+
+	return sve_set_common(target, regset, pos, count, kbuf, ubuf,
+			      ARM64_VEC_SME);
+}
+
+#endif /* CONFIG_ARM64_SME */
+
 #ifdef CONFIG_ARM64_PTR_AUTH
 static int pac_mask_get(struct task_struct *target,
 			const struct user_regset *regset,
@@ -1108,6 +1216,9 @@ enum aarch64_regset {
 #ifdef CONFIG_ARM64_SVE
 	REGSET_SVE,
 #endif
+#ifdef CONFIG_ARM64_SVE
+	REGSET_SSVE,
+#endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	REGSET_PAC_MASK,
 	REGSET_PAC_ENABLED_KEYS,
@@ -1188,6 +1299,17 @@ static const struct user_regset aarch64_regsets[] = {
 		.set = sve_set,
 	},
 #endif
+#ifdef CONFIG_ARM64_SME
+	[REGSET_SSVE] = { /* Streaming mode SVE */
+		.core_note_type = NT_ARM_SSVE,
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+				  SVE_VQ_BYTES),
+		.size = SVE_VQ_BYTES,
+		.align = SVE_VQ_BYTES,
+		.regset_get = ssve_get,
+		.set = ssve_set,
+	},
+#endif
 #ifdef CONFIG_ARM64_PTR_AUTH
 	[REGSET_PAC_MASK] = {
 		.core_note_type = NT_ARM_PAC_MASK,
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 787c657bfae8..a8dc688e1826 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -431,6 +431,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_PACG_KEYS	0x408	/* ARM pointer authentication generic key */
 #define NT_ARM_TAGGED_ADDR_CTRL	0x409	/* arm64 tagged address control (prctl()) */
 #define NT_ARM_PAC_ENABLED_KEYS	0x40a	/* arm64 ptr auth enabled keys (prctl()) */
+#define NT_ARM_SSVE	0x40b		/* ARM Streaming SVE registers */
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
 #define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
 #define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
-- 
cgit v1.2.3


From d158a0608eb85f29f98357b97d01b80250636613 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Thu, 5 May 2022 23:15:17 +0100
Subject: arm64/sme: More sensibly define the size for the ZA register set

Since the vector length configuration mechanism is identical between SVE
and SME we share large elements of the code including the definition for
the maximum vector length. Unfortunately when we were defining the ABI
for SVE we included not only the actual maximum vector length of 2048
bits but also the value possible if all the bits reserved in the
architecture for expansion of the LEN field were used, 16384 bits.

This starts creating problems if we try to allocate anything for the ZA
matrix based on the maximum possible vector length, as we do for the
regset used with ptrace during the process of generating a core dump.
While the maximum potential size for ZA with the current architecture is
a reasonably managable 64K with the higher reserved limit ZA would be
64M which leads to entirely reasonable complaints from the memory
management code when we try to allocate a buffer of that size. Avoid
these issues by defining the actual maximum vector length for the
architecture and using it for the SME regsets.

Also use the full ZA_PT_SIZE() with the header rather than just the
actual register payload when specifying the size, fixing support for the
largest vector lengths now that we have this new, lower define. With the
SVE maximum this did not cause problems due to the extra headroom we
had.

While we're at it add a comment clarifying why even though ZA is a
single register we tell the regset code that it is a multi-register
regset.

Reported-by: Qian Cai <quic_qiancai@quicinc.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Link: https://lore.kernel.org/r/20220505221517.1642014-1-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h | 12 ++++++++++++
 arch/arm64/kernel/ptrace.c      | 12 ++++++++++--
 2 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 5afcd0709aae..75caa2098d5b 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -32,6 +32,18 @@
 #define VFP_STATE_SIZE		((32 * 8) + 4)
 #endif
 
+/*
+ * When we defined the maximum SVE vector length we defined the ABI so
+ * that the maximum vector length included all the reserved for future
+ * expansion bits in ZCR rather than those just currently defined by
+ * the architecture. While SME follows a similar pattern the fact that
+ * it includes a square matrix means that any allocations that attempt
+ * to cover the maximum potential vector length (such as happen with
+ * the regset used for ptrace) end up being extremely large. Define
+ * the much lower actual limit for use in such situations.
+ */
+#define SME_VQ_MAX	16
+
 struct task_struct;
 
 extern void fpsimd_save_state(struct user_fpsimd_state *state);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 47d8a7472171..60ebc3060cf1 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1438,7 +1438,7 @@ static const struct user_regset aarch64_regsets[] = {
 #ifdef CONFIG_ARM64_SME
 	[REGSET_SSVE] = { /* Streaming mode SVE */
 		.core_note_type = NT_ARM_SSVE,
-		.n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE),
+		.n = DIV_ROUND_UP(SVE_PT_SIZE(SME_VQ_MAX, SVE_PT_REGS_SVE),
 				  SVE_VQ_BYTES),
 		.size = SVE_VQ_BYTES,
 		.align = SVE_VQ_BYTES,
@@ -1447,7 +1447,15 @@ static const struct user_regset aarch64_regsets[] = {
 	},
 	[REGSET_ZA] = { /* SME ZA */
 		.core_note_type = NT_ARM_ZA,
-		.n = DIV_ROUND_UP(ZA_PT_ZA_SIZE(SVE_VQ_MAX), SVE_VQ_BYTES),
+		/*
+		 * ZA is a single register but it's variably sized and
+		 * the ptrace core requires that the size of any data
+		 * be an exact multiple of the configured register
+		 * size so report as though we had SVE_VQ_BYTES
+		 * registers. These values aren't exposed to
+		 * userspace.
+		 */
+		.n = DIV_ROUND_UP(ZA_PT_SIZE(SME_VQ_MAX), SVE_VQ_BYTES),
 		.size = SVE_VQ_BYTES,
 		.align = SVE_VQ_BYTES,
 		.regset_get = za_get,
-- 
cgit v1.2.3


From e65fc01bf271cefa6269b7ab1badcf7cddae5d40 Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 10 May 2022 17:12:00 +0100
Subject: arm64/sme: Standardise bitfield names for SVCR

The bitfield definitions for SVCR have a SYS_ added to the names of the
constant which will be a problem for automatic generation. Remove the
prefixes, no functional change.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20220510161208.631259-5-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h    | 4 ++--
 arch/arm64/include/asm/processor.h | 2 +-
 arch/arm64/include/asm/sysreg.h    | 4 ++--
 arch/arm64/kernel/fpsimd.c         | 6 +++---
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 75caa2098d5b..aa11dbec0d70 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -67,12 +67,12 @@ extern void fpsimd_save_and_flush_cpu_state(void);
 
 static inline bool thread_sm_enabled(struct thread_struct *thread)
 {
-	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK);
+	return system_supports_sme() && (thread->svcr & SVCR_EL0_SM_MASK);
 }
 
 static inline bool thread_za_enabled(struct thread_struct *thread)
 {
-	return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK);
+	return system_supports_sme() && (thread->svcr & SVCR_EL0_ZA_MASK);
 }
 
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 1d2ca4870b84..69ce163d2fb2 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -192,7 +192,7 @@ static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
 
 static inline unsigned int thread_get_cur_vl(struct thread_struct *thread)
 {
-	if (system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK))
+	if (system_supports_sme() && (thread->svcr & SVCR_EL0_SM_MASK))
 		return thread_get_sme_vl(thread);
 	else
 		return thread_get_sve_vl(thread);
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index ab2d7cbc63fc..4459cd4a37f5 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -480,8 +480,8 @@
 #define SYS_RNDRRS_EL0			sys_reg(3, 3, 2, 4, 1)
 
 #define SYS_SVCR_EL0			sys_reg(3, 3, 4, 2, 2)
-#define SYS_SVCR_EL0_ZA_MASK		2
-#define SYS_SVCR_EL0_SM_MASK		1
+#define SVCR_EL0_ZA_MASK		2
+#define SVCR_EL0_SM_MASK		1
 
 #define SYS_PMCR_EL0			sys_reg(3, 3, 9, 12, 0)
 #define SYS_PMCNTENSET_EL0		sys_reg(3, 3, 9, 12, 1)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a568735b7c2e..a5f6d6d9f372 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1918,7 +1918,7 @@ void __efi_fpsimd_begin(void)
 				svcr = read_sysreg_s(SYS_SVCR_EL0);
 
 				if (!system_supports_fa64())
-					ffr = svcr & SYS_SVCR_EL0_SM_MASK;
+					ffr = svcr & SVCR_EL0_SM_MASK;
 
 				__this_cpu_write(efi_sm_state, ffr);
 			}
@@ -1929,7 +1929,7 @@ void __efi_fpsimd_begin(void)
 
 			if (system_supports_sme())
 				sysreg_clear_set_s(SYS_SVCR_EL0,
-						   SYS_SVCR_EL0_SM_MASK, 0);
+						   SVCR_EL0_SM_MASK, 0);
 
 		} else {
 			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
@@ -1964,7 +1964,7 @@ void __efi_fpsimd_end(void)
 				if (__this_cpu_read(efi_sm_state)) {
 					sysreg_clear_set_s(SYS_SVCR_EL0,
 							   0,
-							   SYS_SVCR_EL0_SM_MASK);
+							   SVCR_EL0_SM_MASK);
 					if (!system_supports_fa64())
 						ffr = efi_sm_state;
 				}
-- 
cgit v1.2.3


From ec0067a63e5a37de74025d46095cfe7a7af3114a Mon Sep 17 00:00:00 2001
From: Mark Brown
Date: Tue, 10 May 2022 17:12:01 +0100
Subject: arm64/sme: Remove _EL0 from name of SVCR - FIXME sysreg.h

The defines for SVCR call it SVCR_EL0 however the architecture calls the
register SVCR with no _EL0 suffix. In preparation for generating the sysreg
definitions rename to match the architecture, no functional change.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20220510161208.631259-6-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/fpsimd.h    |  4 ++--
 arch/arm64/include/asm/processor.h |  2 +-
 arch/arm64/include/asm/sysreg.h    |  6 +++---
 arch/arm64/kernel/fpsimd.c         | 26 +++++++++++++-------------
 arch/arm64/kernel/ptrace.c         |  8 ++++----
 arch/arm64/kernel/signal.c         | 14 +++++++-------
 arch/arm64/kernel/syscall.c        |  4 ++--
 arch/arm64/kvm/fpsimd.c            |  4 ++--
 arch/arm64/kvm/sys_regs.c          |  2 +-
 9 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'arch/arm64/include/asm/fpsimd.h')

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index aa11dbec0d70..9bb1873f5295 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -67,12 +67,12 @@ extern void fpsimd_save_and_flush_cpu_state(void);
 
 static inline bool thread_sm_enabled(struct thread_struct *thread)
 {
-	return system_supports_sme() && (thread->svcr & SVCR_EL0_SM_MASK);
+	return system_supports_sme() && (thread->svcr & SVCR_SM_MASK);
 }
 
 static inline bool thread_za_enabled(struct thread_struct *thread)
 {
-	return system_supports_sme() && (thread->svcr & SVCR_EL0_ZA_MASK);
+	return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK);
 }
 
 /* Maximum VL that SVE/SME VL-agnostic software can transparently support */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 69ce163d2fb2..8de5a4fc06e3 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -192,7 +192,7 @@ static inline unsigned int thread_get_sme_vl(struct thread_struct *thread)
 
 static inline unsigned int thread_get_cur_vl(struct thread_struct *thread)
 {
-	if (system_supports_sme() && (thread->svcr & SVCR_EL0_SM_MASK))
+	if (system_supports_sme() && (thread->svcr & SVCR_SM_MASK))
 		return thread_get_sme_vl(thread);
 	else
 		return thread_get_sve_vl(thread);
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 4459cd4a37f5..a2f0759f65b2 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -479,9 +479,9 @@
 #define SYS_RNDR_EL0			sys_reg(3, 3, 2, 4, 0)
 #define SYS_RNDRRS_EL0			sys_reg(3, 3, 2, 4, 1)
 
-#define SYS_SVCR_EL0			sys_reg(3, 3, 4, 2, 2)
-#define SVCR_EL0_ZA_MASK		2
-#define SVCR_EL0_SM_MASK		1
+#define SYS_SVCR			sys_reg(3, 3, 4, 2, 2)
+#define SVCR_ZA_MASK			2
+#define SVCR_SM_MASK			1
 
 #define SYS_PMCR_EL0			sys_reg(3, 3, 9, 12, 0)
 #define SYS_PMCNTENSET_EL0		sys_reg(3, 3, 9, 12, 1)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a5f6d6d9f372..759d40cac1fe 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -410,7 +410,7 @@ static void task_fpsimd_load(void)
 		if (test_thread_flag(TIF_SME))
 			sme_set_vq(sve_vq_from_vl(sme_vl) - 1);
 
-		write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0);
+		write_sysreg_s(current->thread.svcr, SYS_SVCR);
 
 		if (thread_za_enabled(&current->thread))
 			za_load_state(current->thread.za_state);
@@ -462,15 +462,15 @@ static void fpsimd_save(void)
 
 	if (system_supports_sme()) {
 		u64 *svcr = last->svcr;
-		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+		*svcr = read_sysreg_s(SYS_SVCR);
 
-		*svcr = read_sysreg_s(SYS_SVCR_EL0);
+		*svcr = read_sysreg_s(SYS_SVCR);
 
-		if (*svcr & SYS_SVCR_EL0_ZA_MASK)
+		if (*svcr & SVCR_ZA_MASK)
 			za_save_state(last->za_state);
 
 		/* If we are in streaming mode override regular SVE. */
-		if (*svcr & SYS_SVCR_EL0_SM_MASK) {
+		if (*svcr & SVCR_SM_MASK) {
 			save_sve_regs = true;
 			save_ffr = system_supports_fa64();
 			vl = last->sme_vl;
@@ -852,8 +852,8 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
 		sve_to_fpsimd(task);
 
 	if (system_supports_sme() && type == ARM64_VEC_SME) {
-		task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK |
-				       SYS_SVCR_EL0_ZA_MASK);
+		task->thread.svcr &= ~(SVCR_SM_MASK |
+				       SVCR_ZA_MASK);
 		clear_thread_flag(TIF_SME);
 	}
 
@@ -1915,10 +1915,10 @@ void __efi_fpsimd_begin(void)
 			__this_cpu_write(efi_sve_state_used, true);
 
 			if (system_supports_sme()) {
-				svcr = read_sysreg_s(SYS_SVCR_EL0);
+				svcr = read_sysreg_s(SYS_SVCR);
 
 				if (!system_supports_fa64())
-					ffr = svcr & SVCR_EL0_SM_MASK;
+					ffr = svcr & SVCR_SM_MASK;
 
 				__this_cpu_write(efi_sm_state, ffr);
 			}
@@ -1928,8 +1928,8 @@ void __efi_fpsimd_begin(void)
 				       ffr);
 
 			if (system_supports_sme())
-				sysreg_clear_set_s(SYS_SVCR_EL0,
-						   SVCR_EL0_SM_MASK, 0);
+				sysreg_clear_set_s(SYS_SVCR,
+						   SVCR_SM_MASK, 0);
 
 		} else {
 			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
@@ -1962,9 +1962,9 @@ void __efi_fpsimd_end(void)
 			 */
 			if (system_supports_sme()) {
 				if (__this_cpu_read(efi_sm_state)) {
-					sysreg_clear_set_s(SYS_SVCR_EL0,
+					sysreg_clear_set_s(SYS_SVCR,
 							   0,
-							   SVCR_EL0_SM_MASK);
+							   SVCR_SM_MASK);
 					if (!system_supports_fa64())
 						ffr = efi_sm_state;
 				}
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 60ebc3060cf1..21da83187a60 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -867,10 +867,10 @@ static int sve_set_common(struct task_struct *target,
 
 		switch (type) {
 		case ARM64_VEC_SVE:
-			target->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK;
+			target->thread.svcr &= ~SVCR_SM_MASK;
 			break;
 		case ARM64_VEC_SME:
-			target->thread.svcr |= SYS_SVCR_EL0_SM_MASK;
+			target->thread.svcr |= SVCR_SM_MASK;
 			break;
 		default:
 			WARN_ON_ONCE(1);
@@ -1100,7 +1100,7 @@ static int za_set(struct task_struct *target,
 
 	/* If there is no data then disable ZA */
 	if (!count) {
-		target->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK;
+		target->thread.svcr &= ~SVCR_ZA_MASK;
 		goto out;
 	}
 
@@ -1125,7 +1125,7 @@ static int za_set(struct task_struct *target,
 
 	/* Mark ZA as active and let userspace use it */
 	set_tsk_thread_flag(target, TIF_SME);
-	target->thread.svcr |= SYS_SVCR_EL0_ZA_MASK;
+	target->thread.svcr |= SVCR_ZA_MASK;
 
 out:
 	fpsimd_flush_task_state(target);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 2295948d97fd..18bf590dc1c7 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -288,7 +288,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 
 	if (sve.head.size <= sizeof(*user->sve)) {
 		clear_thread_flag(TIF_SVE);
-		current->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK;
+		current->thread.svcr &= ~SVCR_SM_MASK;
 		goto fpsimd_only;
 	}
 
@@ -321,7 +321,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 		return -EFAULT;
 
 	if (sve.flags & SVE_SIG_FLAG_SM)
-		current->thread.svcr |= SYS_SVCR_EL0_SM_MASK;
+		current->thread.svcr |= SVCR_SM_MASK;
 	else
 		set_thread_flag(TIF_SVE);
 
@@ -398,7 +398,7 @@ static int restore_za_context(struct user_ctxs __user *user)
 		return -EINVAL;
 
 	if (za.head.size <= sizeof(*user->za)) {
-		current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK;
+		current->thread.svcr &= ~SVCR_ZA_MASK;
 		return 0;
 	}
 
@@ -419,7 +419,7 @@ static int restore_za_context(struct user_ctxs __user *user)
 
 	sme_alloc(current);
 	if (!current->thread.za_state) {
-		current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK;
+		current->thread.svcr &= ~SVCR_ZA_MASK;
 		clear_thread_flag(TIF_SME);
 		return -ENOMEM;
 	}
@@ -432,7 +432,7 @@ static int restore_za_context(struct user_ctxs __user *user)
 		return -EFAULT;
 
 	set_thread_flag(TIF_SME);
-	current->thread.svcr |= SYS_SVCR_EL0_ZA_MASK;
+	current->thread.svcr |= SVCR_ZA_MASK;
 
 	return 0;
 }
@@ -922,8 +922,8 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 
 	/* Signal handlers are invoked with ZA and streaming mode disabled */
 	if (system_supports_sme()) {
-		current->thread.svcr &= ~(SYS_SVCR_EL0_ZA_MASK |
-					  SYS_SVCR_EL0_SM_MASK);
+		current->thread.svcr &= ~(SVCR_ZA_MASK |
+					  SVCR_SM_MASK);
 		sme_smstop();
 	}
 
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 92c69e5ac269..733451fe7e41 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -174,9 +174,9 @@ static inline void fp_user_discard(void)
 	 * need updating.
 	 */
 	if (system_supports_sme() && test_thread_flag(TIF_SME)) {
-		u64 svcr = read_sysreg_s(SYS_SVCR_EL0);
+		u64 svcr = read_sysreg_s(SYS_SVCR);
 
-		if (svcr & SYS_SVCR_EL0_SM_MASK)
+		if (svcr & SVCR_SM_MASK)
 			sme_smstop_sm();
 	}
 
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 441edb9c398c..3d251a4d2cf7 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -96,8 +96,8 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
 			vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED;
 
-		if (read_sysreg_s(SYS_SVCR_EL0) &
-		    (SYS_SVCR_EL0_SM_MASK | SYS_SVCR_EL0_ZA_MASK)) {
+		if (read_sysreg_s(SYS_SVCR) &
+		    (SVCR_SM_MASK | SVCR_ZA_MASK)) {
 			vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
 			fpsimd_save_and_flush_cpu_state();
 		}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 689e53dd4cb1..1cf01c022b30 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1685,7 +1685,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_SMIDR_EL1), undef_access },
 	{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
 	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
-	{ SYS_DESC(SYS_SVCR_EL0), undef_access },
+	{ SYS_DESC(SYS_SVCR), undef_access },
 
 	{ PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr,
 	  .reset = reset_pmcr, .reg = PMCR_EL0 },
-- 
cgit v1.2.3