arm64/sme: Initial support for the Scalable Matrix Extension

index ef6be92b1921..2728abd9cae4 100644
@@ -356,6 +356,7 @@ struct arm64_cpu_capabilities {
 		struct {	/* Feature register checking */
 			u32 sys_reg;
 			u8 field_pos;
+			u8 field_width;
 			u8 min_field_value;
 			u8 hwcap_type;
 			bool sign;

417 lines not on this page · raw message

index d9f09e40aaf6..ec060db1dcf0 100644
@@ -2400,6 +2400,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.min_field_value = 1,
 	},
+	{
+		.desc = "Fine Grained Traps",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_HAS_FGT,
+		.sys_reg = SYS_ID_AA64MMFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR0_FGT_SHIFT,
+		.field_width = 4,
+		.min_field_value = 1,
+		.matches = has_cpuid_feature,
+	},
 	{},
 };
 

index d8eeeafb50dc..1e13b7523918 100644
@@ -18,7 +18,6 @@
 
 #include "../../kselftest.h"
 
-#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
 #define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
 
 extern void do_syscall(int sve_vl);

index af798b9d232c..90ba1d6a6781 100644
@@ -21,8 +21,6 @@
 
 #include "../../kselftest.h"
 
-#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
-
 /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
 #ifndef NT_ARM_SVE
 #define NT_ARM_SVE 0x405

index d52a0b269ee8..43872e0cfd1e 100644
@@ -37,7 +37,8 @@
 #define ESR_ELx_EC_ERET		(0x1a)	/* EL2 only */
 /* Unallocated EC: 0x1B */
 #define ESR_ELx_EC_FPAC		(0x1C)	/* EL1 and above */
-/* Unallocated EC: 0x1D - 0x1E */
+#define ESR_ELx_EC_SME		(0x1D)
+/* Unallocated EC: 0x1E */
 #define ESR_ELx_EC_IMP_DEF	(0x1f)	/* EL3 only */
 #define ESR_ELx_EC_IABT_LOW	(0x20)
 #define ESR_ELx_EC_IABT_CUR	(0x21)

@@ -327,6 +328,15 @@
 #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ	(ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\
 					 ESR_ELx_CP15_32_ISS_DIR_READ)
 
+/*
+ * ISS values for SME traps
+ */
+
+#define ESR_ELx_SME_ISS_SME_DISABLED	0
+#define ESR_ELx_SME_ISS_ILL		1
+#define ESR_ELx_SME_ISS_SM_DISABLED	2
+#define ESR_ELx_SME_ISS_ZA_DISABLED	3
+
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 

index 01d47c5886dc..a741b1e7823c 100644
@@ -279,6 +279,7 @@
 #define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
+#define CPTR_EL2_TSM	(1 << 12)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
 #define CPTR_NVHE_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */

162 lines not on this page · raw message

index 70fc42470f13..88effb25c399 100644
@@ -822,6 +822,7 @@ static const char *esr_class_str[] = {
 	[ESR_ELx_EC_SVE]		= "SVE",
 	[ESR_ELx_EC_ERET]		= "ERET/ERETAA/ERETAB",
 	[ESR_ELx_EC_FPAC]		= "FPAC",
+	[ESR_ELx_EC_SME]		= "SME",
 	[ESR_ELx_EC_IMP_DEF]		= "EL3 IMP DEF",
 	[ESR_ELx_EC_IABT_LOW]		= "IABT (lower EL)",
 	[ESR_ELx_EC_IABT_CUR]		= "IABT (current EL)",

index cb24385e3632..c90f7f99a768 100644
@@ -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(".inst 0xd503437f");
+}
+
+static inline void sme_smstop_sm(void)
+{
+	asm volatile(".inst 0xd503427f");
+}
+
+static inline void sme_smstop(void)
+{
+	asm volatile(".inst 0xd503467f");
+}
+
+#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);

65 lines not on this page · raw message

index 3198acb2aad8..0e68b478bd94 100644
@@ -143,6 +143,50 @@
 .Lskip_sve_\@:
 .endm
 
+/* SME register access and priority mapping */
+.macro __init_el2_nvhe_sme
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_SME_SHIFT, #4
+	cbz	x1, .Lskip_sme_\@
+
+	bic	x0, x0, #CPTR_EL2_TSM		// Also disable SME traps
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+	isb
+
+	mrs	x1, sctlr_el2
+	orr	x1, x1, #SCTLR_ELx_ENTP2	// Disable TPIDR2 traps
+	msr	sctlr_el2, x1
+	isb
+
+	mov	x1, #0				// SMCR controls
+
+	mrs_s	x2, SYS_ID_AA64SMFR0_EL1
+	ubfx	x2, x2, #ID_AA64SMFR0_FA64_SHIFT, #1 // Full FP in SM?
+	cbz	x2, .Lskip_sme_fa64_\@
+
+	orr	x1, x1, SMCR_ELx_FA64_MASK
+.Lskip_sme_fa64_\@:
+
+	orr	x1, x1, #SMCR_ELx_LEN_MASK	// Enable full SME vector
+	msr_s	SYS_SMCR_EL2, x1		// length for EL1.
+
+	mrs_s	x1, SYS_SMIDR_EL1		// Priority mapping supported?
+	ubfx    x1, x1, #SYS_SMIDR_EL1_SMPS_SHIFT, #1
+	cbz     x1, .Lskip_sme_\@
+
+	msr_s	SYS_SMPRIMAP_EL2, xzr		// Make all priorities equal
+
+	mrs	x1, id_aa64mmfr1_el1		// HCRX_EL2 present?
+	ubfx	x1, x1, #ID_AA64MMFR1_HCX_SHIFT, #4
+	cbz	x1, .Lskip_sme_\@
+
+	mrs_s	x1, SYS_HCRX_EL2
+	orr	x1, x1, #HCRX_EL2_SMPME_MASK	// Enable priority mapping
+	msr_s	SYS_HCRX_EL2, x1
+
+.Lskip_sme_\@:
+.endm
+
 /* Disable any fine grained traps */
 .macro __init_el2_fgt
 	mrs	x1, id_aa64mmfr0_el1

@@ -153,15 +197,26 @@
 	mrs	x1, id_aa64dfr0_el1
 	ubfx	x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
 	cmp	x1, #3
-	b.lt	.Lset_fgt_\@
+	b.lt	.Lset_debug_fgt_\@
 	/* Disable PMSNEVFR_EL1 read and write traps */
 	orr	x0, x0, #(1 << 62)
 
-.Lset_fgt_\@:
+.Lset_debug_fgt_\@:
 	msr_s	SYS_HDFGRTR_EL2, x0
 	msr_s	SYS_HDFGWTR_EL2, x0
-	msr_s	SYS_HFGRTR_EL2, xzr
-	msr_s	SYS_HFGWTR_EL2, xzr
+
+	mov	x0, xzr
+	mrs	x1, id_aa64pfr1_el1
+	ubfx	x1, x1, #ID_AA64PFR1_SME_SHIFT, #4
+	cbz	x1, .Lset_fgt_\@
+
+	/* Disable nVHE traps of TPIDR2 and SMPRI */
+	orr	x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK
+	orr	x0, x0, #HFGxTR_EL2_nTPIDR_EL0_MASK
+
+.Lset_fgt_\@:
+	msr_s	SYS_HFGRTR_EL2, x0
+	msr_s	SYS_HFGWTR_EL2, x0
 	msr_s	SYS_HFGITR_EL2, xzr
 
 	mrs	x1, id_aa64pfr0_el1		// AMU traps UNDEF without AMU

@@ -196,6 +251,7 @@
 	__init_el2_nvhe_idregs
 	__init_el2_nvhe_cptr
 	__init_el2_nvhe_sve
+	__init_el2_nvhe_sme
 	__init_el2_fgt
 	__init_el2_nvhe_prepare_eret
 .endm

index a58e366f0b07..d08062bcb9c1 100644
@@ -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;
 

index 2728abd9cae4..f93b1442143f 100644
@@ -728,6 +728,18 @@ 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) &&

index c90f7f99a768..6b7eb6f2cecd 100644
@@ -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);
 

index f68fbb207473..76d9999527c5 100644
@@ -108,6 +108,14 @@
 #define KERNEL_HWCAP_ECV		__khwcap2_feature(ECV)
 #define KERNEL_HWCAP_AFP		__khwcap2_feature(AFP)
 #define KERNEL_HWCAP_RPRES		__khwcap2_feature(RPRES)
+#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

index f03731847d9d..60de5626f8fb 100644
@@ -78,5 +78,13 @@
 #define HWCAP2_ECV		(1 << 19)
 #define HWCAP2_AFP		(1 << 20)
 #define HWCAP2_RPRES		(1 << 21)
+#define HWCAP2_SME		(1 << 22)
+#define HWCAP2_SME_I16I64	(1 << 23)
+#define HWCAP2_SME_F64F64	(1 << 24)
+#define HWCAP2_SME_I8I32	(1 << 25)
+#define HWCAP2_SME_F16F32	(1 << 26)
+#define HWCAP2_SME_B16F32	(1 << 27)
+#define HWCAP2_SME_F32F32	(1 << 28)
+#define HWCAP2_SME_FA64		(1 << 29)
 
 #endif /* _UAPI__ASM_HWCAP_H */

93 lines not on this page · raw message

index 591c18a889a5..33ec182e872e 100644
@@ -97,6 +97,14 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_ECV]		= "ecv",
 	[KERNEL_HWCAP_AFP]		= "afp",
 	[KERNEL_HWCAP_RPRES]		= "rpres",
+	[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

@@ -400,6 +408,7 @@ 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);

index 5280e098cfb5..576490be3c2b 100644
@@ -987,6 +987,32 @@ 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
  *

@@ -1532,6 +1558,10 @@ 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);

index d08062bcb9c1..550e1fc4ae6c 100644
@@ -64,6 +64,9 @@ struct cpuinfo_arm64 {
 
 	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
 	u64		reg_zcr;
+
+	/* pseudo-SMCR for recording maximum ZCR_EL1 LEN value: */
+	u64		reg_smcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);

index f93b1442143f..9d36035acce3 100644
@@ -620,6 +620,13 @@ 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);

index 6b7eb6f2cecd..8cb99b6fe565 100644
@@ -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(".inst 0xd503467f");
 }
 
+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 */

index 6f41b65f9962..df68f0fb0ded 100644
@@ -117,6 +117,7 @@ struct debug_info {
 
 enum vec_type {
 	ARM64_VEC_SVE = 0,
+	ARM64_VEC_SME,
 	ARM64_VEC_MAX,
 };
 

97 lines not on this page · raw message

index 33ec182e872e..72dc155719b0 100644
@@ -420,6 +420,10 @@ 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);
 }
 

153 lines not on this page · raw message

index 3fb2167f8af7..841b9609342f 100644
@@ -483,6 +483,30 @@ static int __init sve_sysctl_init(void)
 static int __init sve_sysctl_init(void) { return 0; }
 #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
+#if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL)
+static struct ctl_table sme_default_vl_table[] = {
+	{
+		.procname	= "sme_default_vector_length",
+		.mode		= 0644,
+		.proc_handler	= vec_proc_do_default_vl,
+		.extra1		= &vl_info[ARM64_VEC_SME],
+	},
+	{ }
+};
+
+static int __init sme_sysctl_init(void)
+{
+	if (system_supports_sme())
+		if (!register_sysctl("abi", sme_default_vl_table))
+			return -EINVAL;
+
+	return 0;
+}
+
+#else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */
+static int __init sme_sysctl_init(void) { return 0; }
+#endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */
+
 #define ZREG(sve_state, vq, n) ((char *)(sve_state) +		\
 	(SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET))
 

@@ -1681,6 +1705,9 @@ static int __init fpsimd_init(void)
 	if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE))
 		pr_notice("SME is implemented but not SVE\n");
 
-	return sve_sysctl_init();
+	sve_sysctl_init();
+	sme_sysctl_init();
+
+	return 0;
 }
 core_initcall(fpsimd_init);

index 8cb99b6fe565..babf944e7c0c 100644
@@ -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 */
 

index df68f0fb0ded..f2c2ebd440e2 100644
@@ -354,9 +354,11 @@ 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)

index e1317b7c4525..4e6b58dcd6f9 100644
@@ -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)

index 841b9609342f..1edb3996f9cf 100644
@@ -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;

@@ -801,6 +803,36 @@ 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))
 {

index e998764f0262..a5e06dcbba13 100644
@@ -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
 

index ecc4cf019242..5cd4fffc7cd0 100644
@@ -116,6 +116,12 @@
 #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

@@ -2523,6 +2529,12 @@ 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;

index 9d36035acce3..12252352d2ee 100644
@@ -747,6 +747,11 @@ static __always_inline bool system_supports_fa64(void)
 		cpus_have_const_cap(ARM64_SME_FA64);
 }
 
+static __always_inline bool system_supports_tpidr2(void)
+{
+	return system_supports_sme();
+}
+
 static __always_inline bool system_supports_cnp(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_CNP) &&

index f2c2ebd440e2..008a1767ebff 100644
@@ -168,6 +168,7 @@ struct thread_struct {
 	u64			mte_ctrl;
 #endif
 	u64			sctlr_user;
+	u64			tpidr2_el0;
 };
 
 static inline unsigned int thread_get_vl(struct thread_struct *thread,

index 1edb3996f9cf..40ef89120774 100644
@@ -1092,6 +1092,10 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
 	/* Allow SME in kernel */
 	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1);
 	isb();
+
+	/* Allow EL0 to access TPIDR2 */
+	write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1);
+	isb();
 }
 
 /*

index 5369e649fa79..e69a3dcdb0d9 100644
@@ -250,6 +250,8 @@ void show_regs(struct pt_regs *regs)
 static void tls_thread_flush(void)
 {
 	write_sysreg(0, tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(0, SYS_TPIDR2_EL0);
 
 	if (is_compat_task()) {
 		current->thread.uw.tp_value = 0;

@@ -343,6 +345,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		 * out-of-sync with the saved value.
 		 */
 		*task_user_tls(p) = read_sysreg(tpidr_el0);
+		if (system_supports_tpidr2())
+			p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 
 		if (stack_start) {
 			if (is_compat_thread(task_thread_info(p)))

@@ -353,10 +357,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 		/*
 		 * If a TLS pointer was passed to clone, use it for the new
-		 * thread.
+		 * thread.  We also reset TPIDR2 if it's in use.
 		 */
-		if (clone_flags & CLONE_SETTLS)
+		if (clone_flags & CLONE_SETTLS) {
 			p->thread.uw.tp_value = tls;
+			p->thread.tpidr2_el0 = 0;
+		}
 	} else {
 		/*
 		 * A kthread has no context to ERET to, so ensure any buggy

@@ -387,6 +393,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 void tls_preserve_current_state(void)
 {
 	*task_user_tls(current) = read_sysreg(tpidr_el0);
+	if (system_supports_tpidr2() && !is_compat_task())
+		current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 }
 
 static void tls_thread_switch(struct task_struct *next)

@@ -399,6 +407,8 @@ static void tls_thread_switch(struct task_struct *next)
 		write_sysreg(0, tpidrro_el0);
 
 	write_sysreg(*task_user_tls(next), tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0);
 }
 
 /*

index babf944e7c0c..d1bae65d3dba 100644
@@ -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);

index 008a1767ebff..7e08a4d48c24 100644
@@ -168,6 +168,7 @@ struct thread_struct {
 	u64			mte_ctrl;
 #endif
 	u64			sctlr_user;
+	u64			svcr;
 	u64			tpidr2_el0;
 };
 

index 4e6b58dcd6f9..848739c15de8 100644
@@ -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)

index 40ef89120774..a1918b71d335 100644
@@ -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),

@@ -384,6 +388,12 @@ 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)) {

@@ -735,6 +745,10 @@ 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();
 

@@ -1398,6 +1412,7 @@ 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()) {

@@ -1412,7 +1427,7 @@ 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);

@@ -1421,6 +1436,7 @@ 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;
 }

index e69a3dcdb0d9..f2d32a29641c 100644
@@ -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);
 

index 2f48fd362a8c..04698c4bcd30 100644
@@ -103,6 +103,10 @@ 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);

index d1bae65d3dba..650ec642159c 100644
@@ -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);

index 11c426ddd62c..a50fa1eab730 100644
@@ -261,6 +261,17 @@
 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

index 7e08a4d48c24..6e2af9de153c 100644
@@ -183,6 +183,11 @@ 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);

@@ -196,6 +201,11 @@ 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);

206 lines not on this page · raw message

index 04698c4bcd30..902c598b7ed2 100644
@@ -109,7 +109,8 @@ 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);
+					 vcpu->arch.sve_max_vl,
+					 0);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));

index 650ec642159c..af404e5b8d82 100644
@@ -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);

index a50fa1eab730..35d67e393519 100644
@@ -318,3 +318,25 @@
 		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

index 5bc01e62c08a..7dc85d5a6552 100644
@@ -280,8 +280,11 @@ 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;

index 6e2af9de153c..5a5c5edd76df 100644
@@ -153,6 +153,7 @@ 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 */

index 12fef62cf07a..c9e8186e69c0 100644
@@ -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();

@@ -435,11 +440,10 @@ 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) {

@@ -1477,6 +1481,7 @@ 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;

@@ -1494,8 +1499,8 @@ 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);

@@ -1506,6 +1511,7 @@ 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;
 }

index 902c598b7ed2..338733ac63f8 100644
@@ -110,7 +110,7 @@ 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, 0, &vcpu->arch.svcr);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
 		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));

index 43872e0cfd1e..0467837fd66b 100644
@@ -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)

index 339477dca551..2add7f33b7c2 100644
@@ -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);

index af404e5b8d82..3ca152aaf7c9 100644
@@ -282,6 +282,16 @@ static inline void sve_setup(void) { }
 
 #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(".inst 0xd503437f");

@@ -309,16 +319,33 @@ 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; }

index ef7fcefb96bd..b2ad525d6c87 100644
@@ -524,6 +524,14 @@ 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);

@@ -632,6 +640,9 @@ 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;

256 lines not on this page · raw message

index f2d32a29641c..f7fcc625ea0e 100644
@@ -299,17 +299,19 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK));
 
 	/*
-	 * Detach src's sve_state (if any) from dst so that it does not
-	 * get erroneously used or freed prematurely.  dst's sve_state
-	 * will be allocated on demand later on if dst uses SVE.
-	 * For consistency, also clear TIF_SVE here: this could be done
+	 * Detach src's sve/za_state (if any) from dst so that it does not
+	 * get erroneously used or freed prematurely.  dst's copies
+	 * will be allocated on demand later on if dst uses SVE/SME.
+	 * For consistency, also clear TIF_SVE/SME 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.za_state = NULL;
+	clear_tsk_thread_flag(dst, TIF_SME);
 	dst->thread.svcr = 0;
 
 	/* clear any pending asynchronous tag fault raised by the parent */

index c938603b3ba0..958b2d926354 100644
@@ -158,11 +158,41 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	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 SME 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 (!(svcr & SYS_SVCR_EL0_ZA_MASK)) {
+			clear_thread_flag(TIF_SME);
+			sme_user_disable();
+		}
+	}
+
+
 	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 +207,7 @@ 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);
 }
 

index d8aaf4b6f432..cda04fd73333 100644
@@ -758,6 +758,13 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 	/* TCO (Tag Check Override) always cleared for signal handlers */
 	regs->pstate &= ~PSR_TCO_BIT;
 
+	/* 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);
+		sme_smstop();
+	}
+
 	if (ka->sa.sa_flags & SA_RESTORER)
 		sigtramp = ka->sa.sa_restorer;
 	else

index 0c796c795dbe..3a3366d4fbc2 100644
@@ -134,9 +134,12 @@ struct extra_context {
 struct sve_context {
 	struct _aarch64_ctx head;
 	__u16 vl;
-	__u16 __reserved[3];
+	__u16 flags;
+	__u16 __reserved[2];
 };
 
+#define SVE_SIG_FLAG_SM	0x1	/* Context describes streaming mode */
+
 #endif /* !__ASSEMBLY__ */
 
 #include <asm/sve_context.h>

@@ -186,9 +189,16 @@ struct sve_context {
  * sve_context.vl must equal the thread's current vector length when
  * doing a sigreturn.
  *
+ * On systems with support for SME the SVE register state may reflect either
+ * streaming or non-streaming mode.  In streaming mode the streaming mode
+ * vector length will be used and the flag SVE_SIG_FLAG_SM will be set in
+ * the flags field. It is permitted to enter or leave streaming mode in
+ * a signal return, applications should take care to ensure that any difference
+ * in vector length between the two modes is handled, including any resixing
+ * and movement of context blocks.
  *
- * Note: for all these macros, the "vq" argument denotes the SVE
- * vector length in quadwords (i.e., units of 128 bits).
+ * Note: for all these macros, the "vq" argument denotes the vector length
+ * in quadwords (i.e., units of 128 bits).
  *
  * The correct way to obtain vq is to use sve_vq_from_vl(vl).  The
  * result is valid if and only if sve_vl_valid(vl) is true.  This is

105 lines not on this page · raw message

index 3a3366d4fbc2..d45bdf2c8b26 100644
@@ -140,6 +140,14 @@ struct sve_context {
 
 #define SVE_SIG_FLAG_SM	0x1	/* Context describes streaming mode */
 
+#define ZA_MAGIC	0x54366345
+
+struct za_context {
+	struct _aarch64_ctx head;
+	__u16 vl;
+	__u16 __reserved[3];
+};
+
 #endif /* !__ASSEMBLY__ */
 
 #include <asm/sve_context.h>

@@ -259,4 +267,37 @@ struct sve_context {
 #define SVE_SIG_CONTEXT_SIZE(vq) \
 		(SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq))
 
+/*
+ * If the ZA register is enabled for the thread at signal delivery then,
+ * za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl))
+ * and the register data may be accessed using the ZA_SIG_*() macros.
+ *
+ * If za_context.head.size < ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl))
+ * then ZA was not enabled and no register data was included in which case
+ * ZA register was not enabled for the thread and no register data
+ * the ZA_SIG_*() macros should not be used except for this check.
+ *
+ * The same convention applies when returning from a signal: a caller
+ * will need to remove or resize the za_context block if it wants to
+ * enable the ZA register when it was previously non-live or vice-versa.
+ * This may require the caller to allocate fresh memory and/or move other
+ * context blocks in the signal frame.
+ *
+ * Changing the vector length during signal return is not permitted:
+ * za_context.vl must equal the thread's current SME vector length when
+ * doing a sigreturn.
+ */
+
+#define ZA_SIG_REGS_OFFSET					\
+	((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1))	\
+		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
+
+#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES))
+
+#define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \
+				  (SVE_SIG_ZREG_SIZE(vq) * n))
+
+#define ZA_SIG_CONTEXT_SIZE(vq) \
+		(ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq))
+
 #endif /* _UAPI__ASM_SIGCONTEXT_H */

index 33f80512753d..2242c14a5a05 100644
@@ -1190,9 +1190,6 @@ void fpsimd_release_task(struct task_struct *dead_task)
 
 #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.
  *

187 lines not on this page · raw message

index 758ae984ff97..522b925a78c1 100644
@@ -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) */
 

index 2242c14a5a05..8b111b7f2006 100644
@@ -645,14 +645,19 @@ static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
  */
 static void fpsimd_to_sve(struct task_struct *task)
 {
-	unsigned int vq;
+	unsigned int vq, vl;
 	void *sst = task->thread.sve_state;
 	struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
 
 	if (!system_supports_sve())
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	if (thread_sm_enabled(&task->thread))
+		vl = task_get_sme_vl(task);
+	else
+		vl = task_get_sve_vl(task);
+
+	vq = sve_vq_from_vl(vl);
 	__fpsimd_to_sve(sst, fst, vq);
 }
 

@@ -669,7 +674,7 @@ 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;

@@ -678,7 +683,12 @@ static void sve_to_fpsimd(struct task_struct *task)
 	if (!system_supports_sve())
 		return;
 
-	vq = sve_vq_from_vl(task_get_sve_vl(task));
+	if (thread_sm_enabled(&task->thread))
+		vl = task_get_sme_vl(task);
+	else
+		vl = task_get_sve_vl(task);
+
+	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);

@@ -819,8 +829,7 @@ 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();

303 lines not on this page · raw message

index 61bf4774b8f2..61502388683f 100644
@@ -427,6 +427,7 @@ 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 */

index 522b925a78c1..7fa2f7036aa7 100644
@@ -268,6 +268,62 @@ struct user_pac_generic_keys {
 	__uint128_t	apgakey;
 };
 
+/* ZA state (NT_ARM_ZA) */
+
+struct user_za_header {
+	__u32 size; /* total meaningful regset content in bytes */
+	__u32 max_size; /* maxmium possible size for this thread */
+	__u16 vl; /* current vector length */
+	__u16 max_vl; /* maximum possible vector length */
+	__u16 flags;
+	__u16 __reserved;
+};
+
+/*
+ * Common ZA_PT_* flags:
+ * These must be kept in sync with prctl interface in <linux/prctl.h>
+ */
+#define ZA_PT_VL_INHERIT		((1 << 17) /* PR_SME_VL_INHERIT */ >> 16)
+#define ZA_PT_VL_ONEXEC			((1 << 18) /* PR_SME_SET_VL_ONEXEC */ >> 16)
+
+
+/*
+ * The remainder of the ZA state follows struct user_za_header.  The
+ * total size of the ZA state (including header) depends on the
+ * metadata in the header:  ZA_PT_SIZE(vq, flags) gives the total size
+ * of the state in bytes, including the header.
+ *
+ * Refer to <asm/sigcontext.h> for details of how to pass the correct
+ * "vq" argument to these macros.
+ */
+
+/* Offset from the start of struct user_za_header to the register data */
+#define ZA_PT_ZA_OFFSET						\
+	((sizeof(struct user_za_header) + (__SVE_VQ_BYTES - 1))	\
+		/ __SVE_VQ_BYTES * __SVE_VQ_BYTES)
+
+/*
+ * The payload starts at offset ZA_PT_ZA_OFFSET, and is of size
+ * ZA_PT_ZA_SIZE(vq, flags).
+ *
+ * The ZA array is stored as a sequence of horizontal vectors ZAV of SVL/8
+ * bytes each, starting from vector 0.
+ *
+ * Additional data might be appended in the future.
+ *
+ * The ZA matrix is represented in memory in an endianness-invariant layout
+ * which differs from the layout used for the FPSIMD V-registers on big-endian
+ * systems: see sigcontext.h for more explanation.
+ */
+
+#define ZA_PT_ZAV_OFFSET(vq, n) \
+	(ZA_PT_ZA_OFFSET + ((vq * __SVE_VQ_BYTES) * n))
+
+#define ZA_PT_ZA_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES))
+
+#define ZA_PT_SIZE(vq)						\
+	(ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq))
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI__ASM_PTRACE_H */

162 lines not on this page · raw message

index 61502388683f..7ef574f3256a 100644
@@ -428,6 +428,7 @@ typedef struct elf64_shdr {
 #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_ARM_ZA	0x40c		/* ARM SME ZA 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 */

index 8b111b7f2006..e00d3a9e919c 100644
@@ -1762,6 +1762,15 @@ static void fpsimd_flush_cpu_state(void)
 {
 	WARN_ON(!system_supports_fpsimd());
 	__this_cpu_write(fpsimd_last_state.st, NULL);
+
+	/*
+	 * Leaving streaming mode enabled will cause issues for any kernel
+	 * NEON and leaving streaming mode or ZA enabled may increase power
+	 * consumption.
+	 */
+	if (system_supports_sme())
+		sme_smstop();
+
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
 }
 

index e00d3a9e919c..a7077a5d1ed2 100644
@@ -1059,21 +1059,25 @@ int vec_verify_vq_map(enum vec_type type)
 
 static void __init sve_efi_setup(void)
 {
-	struct vl_info *info = &vl_info[ARM64_VEC_SVE];
+	int max_vl = 0;
+	int i;
 
 	if (!IS_ENABLED(CONFIG_EFI))
 		return;
 
+	for (i = 0; i < ARRAY_SIZE(vl_info); i++)
+		max_vl = max(vl_info[i].max_vl, max_vl);
+
 	/*
 	 * alloc_percpu() warns and prints a backtrace if this goes wrong.
 	 * This is evidence of a crippled system and we are returning void,
 	 * so no attempt is made to handle this situation here.
 	 */
-	if (!sve_vl_valid(info->max_vl))
+	if (!sve_vl_valid(max_vl))
 		goto fail;
 
 	efi_sve_state = __alloc_percpu(
-		SVE_SIG_REGS_SIZE(sve_vq_from_vl(info->max_vl)), SVE_VQ_BYTES);
+		SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES);
 	if (!efi_sve_state)
 		goto fail;
 

@@ -1848,6 +1852,7 @@ EXPORT_SYMBOL(kernel_neon_end);
 static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state);
 static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
 static DEFINE_PER_CPU(bool, efi_sve_state_used);
+static DEFINE_PER_CPU(bool, efi_sm_state);
 
 /*
  * EFI runtime services support functions

@@ -1882,12 +1887,28 @@ void __efi_fpsimd_begin(void)
 		 */
 		if (system_supports_sve() && likely(efi_sve_state)) {
 			char *sve_state = this_cpu_ptr(efi_sve_state);
+			bool ffr = true;
+			u64 svcr;
 
 			__this_cpu_write(efi_sve_state_used, true);
 
+			/* If we are in streaming mode don't touch FFR */
+			if (system_supports_sme()) {
+				svcr = read_sysreg_s(SYS_SVCR_EL0);
+
+				ffr = svcr & SYS_SVCR_EL0_SM_MASK;
+
+				__this_cpu_write(efi_sm_state, ffr);
+			}
+
 			sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()),
 				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
-				       true);
+				       ffr);
+
+			if (system_supports_sme())
+				sysreg_clear_set_s(SYS_SVCR_EL0,
+						   SYS_SVCR_EL0_SM_MASK, 0);
+
 		} else {
 			fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
 		}

@@ -1910,11 +1931,25 @@ void __efi_fpsimd_end(void)
 		if (system_supports_sve() &&
 		    likely(__this_cpu_read(efi_sve_state_used))) {
 			char const *sve_state = this_cpu_ptr(efi_sve_state);
+			bool ffr = true;
+
+			/*
+			 * Restore streaming mode; EFI calls are
+			 * normal function calls so should not return in
+			 * streaming mode.
+			 */
+			if (system_supports_sme()) {
+				if (__this_cpu_read(efi_sm_state)) {
+					sysreg_clear_set_s(SYS_SVCR_EL0,
+							   0,
+							   SYS_SVCR_EL0_SM_MASK);
+					ffr = false;
+				}
+			}
 
-			sve_set_vq(sve_vq_from_vl(sve_get_vl()) - 1);
 			sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()),
 				       &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
-				       true);
+				       ffr);
 
 			__this_cpu_write(efi_sve_state_used, false);
 		} else {

index 4dc2fba316ff..43516eda9143 100644
@@ -1089,6 +1089,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 	case SYS_ID_AA64PFR1_EL1:
 		if (!kvm_has_mte(vcpu->kvm))
 			val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
+
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_SME);
 		break;
 	case SYS_ID_AA64ISAR1_EL1:
 		if (!vcpu_has_ptrauth(vcpu))

@@ -1508,7 +1510,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_UNALLOCATED(4,2),
 	ID_UNALLOCATED(4,3),
 	ID_SANITISED(ID_AA64ZFR0_EL1),
-	ID_UNALLOCATED(4,5),
+	ID_HIDDEN(ID_AA64SMFR0_EL1),
 	ID_UNALLOCATED(4,6),
 	ID_UNALLOCATED(4,7),
 

@@ -1551,6 +1553,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
 	{ SYS_DESC(SYS_TRFCR_EL1), undef_access },
+	{ SYS_DESC(SYS_SMPRI_EL1), undef_access },
+	{ SYS_DESC(SYS_SMCR_EL1), undef_access },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
 	{ SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 },
 	{ SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 },

@@ -1633,8 +1637,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
 	{ SYS_DESC(SYS_CLIDR_EL1), access_clidr },
+	{ 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 },
 
 	{ PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr,
 	  .reset = reset_pmcr, .reg = PMCR_EL0 },

@@ -1674,6 +1680,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
+	{ SYS_DESC(SYS_TPIDR2_EL0), undef_access },
 
 	{ SYS_DESC(SYS_SCXTNUM_EL0), undef_access },
 

index 6410d21d8695..184bf6bd79b9 100644
@@ -47,10 +47,25 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
 		__activate_traps_fpsimd32(vcpu);
 	}
+	if (IS_ENABLED(CONFIG_ARM64_SME) && cpus_have_final_cap(ARM64_SME))
+		val |= CPTR_EL2_TSM;
 
 	write_sysreg(val, cptr_el2);
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) && cpus_have_final_cap(ARM64_SME) &&
+	    cpus_have_final_cap(ARM64_HAS_FGT)) {
+		val = read_sysreg_s(SYS_HFGRTR_EL2);
+		val &= ~(HFGxTR_EL2_nTPIDR_EL0_MASK |
+			 HFGxTR_EL2_nSMPRI_EL1_MASK);
+		write_sysreg_s(val, SYS_HFGRTR_EL2);
+
+		val = read_sysreg_s(SYS_HFGWTR_EL2);
+		val &= ~(HFGxTR_EL2_nTPIDR_EL0_MASK |
+			 HFGxTR_EL2_nSMPRI_EL1_MASK);
+		write_sysreg_s(val, SYS_HFGWTR_EL2);
+	}
+
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
 

@@ -94,9 +109,24 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 
 	write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) && cpus_have_final_cap(ARM64_SME) &&
+	    cpus_have_final_cap(ARM64_HAS_FGT)) {
+		u64 val;
+
+		val = read_sysreg_s(SYS_HFGRTR_EL2);
+		val |= HFGxTR_EL2_nTPIDR_EL0_MASK | HFGxTR_EL2_nSMPRI_EL1_MASK;
+		write_sysreg_s(val, SYS_HFGRTR_EL2);
+
+		val = read_sysreg_s(SYS_HFGWTR_EL2);
+		val |= HFGxTR_EL2_nTPIDR_EL0_MASK | HFGxTR_EL2_nSMPRI_EL1_MASK;
+		write_sysreg_s(val, SYS_HFGWTR_EL2);
+	}
+
 	cptr = CPTR_EL2_DEFAULT;
 	if (vcpu_has_sve(vcpu) && (vcpu->arch.flags & KVM_ARM64_FP_ENABLED))
 		cptr |= CPTR_EL2_TZ;
+	if (IS_ENABLED(CONFIG_ARM64_SME) && cpus_have_final_cap(ARM64_SME))
+		cptr &= ~CPTR_EL2_TSM;
 
 	write_sysreg(cptr, cptr_el2);
 	write_sysreg(__kvm_hyp_host_vector, vbar_el2);

index 11d053fdd604..f5630579f577 100644
@@ -38,7 +38,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
-	val &= ~CPACR_EL1_ZEN;
+	val &= ~(CPACR_EL1_ZEN | CPACR_EL1_SMEN);
 
 	/*
 	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to

@@ -59,6 +59,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		__activate_traps_fpsimd32(vcpu);
 	}
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) && cpus_have_final_cap(ARM64_SME))
+		write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2,
+			     sctlr_el2);
+
 	write_sysreg(val, cpacr_el1);
 
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);

@@ -80,6 +84,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	 */
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
+	if (IS_ENABLED(CONFIG_ARM64_SME) && cpus_have_final_cap(ARM64_SME))
+		write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2,
+			     sctlr_el2);
+
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 	write_sysreg(vectors, vbar_el1);
 }

index 7dc85d5a6552..404b7358ba96 100644
@@ -438,6 +438,7 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_DEBUG_STATE_SAVE_SPE	(1 << 12) /* Save SPE context if active  */
 #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE	(1 << 13) /* Save TRBE context if active  */
 #define KVM_ARM64_FP_FOREIGN_FPSTATE	(1 << 14)
+#define KVM_ARM64_HOST_SME_ENABLED	(1 << 15) /* SME enabled for EL0 */
 
 #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
 				 KVM_GUESTDBG_USE_SW_BP | \

index 338733ac63f8..cecaddb644ce 100644
@@ -82,6 +82,26 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
 		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
+
+	/*
+	 * We don't currently support SME guests but if we leave
+	 * things in streaming mode then when the guest starts running
+	 * FPSIMD or SVE code it may generate SME traps so as a
+	 * special case if we are in streaming mode we force the host
+	 * state to be saved now and exit streaming mode so that we
+	 * don't have to handle any SME traps for valid guest
+	 * operations. Do this for ZA as well for now for simplicity.
+	 */
+	if (system_supports_sme()) {
+		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)) {
+			vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
+			fpsimd_save_and_flush_cpu_state();
+		}
+	}
 }
 
 void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu)

@@ -129,6 +149,24 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 
 	local_irq_save(flags);
 
+	/*
+	 * If we have VHE then the Hyp code will reset CPACR_EL1 to
+	 * CPACR_EL1_DEFAULT and we need to reenable SME.
+	 */
+	if (has_vhe()) {
+		if (system_supports_sme()) {
+			/* Also restore EL0 state seen on entry */
+			if (vcpu->arch.flags & KVM_ARM64_HOST_SME_ENABLED)
+				sysreg_clear_set(CPACR_EL1, 0,
+						 CPACR_EL1_SMEN_EL0EN |
+						 CPACR_EL1_SMEN_EL1EN);
+			else
+				sysreg_clear_set(CPACR_EL1,
+						 CPACR_EL1_SMEN_EL0EN,
+						 CPACR_EL1_SMEN_EL1EN);
+		}
+	}
+
 	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
 		if (vcpu_has_sve(vcpu)) {
 			__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);

index 308d27a68226..76912a581a95 100644
@@ -22,12 +22,15 @@ static int inherit = 0;
 static int no_inherit = 0;
 static int force = 0;
 static unsigned long vl;
+static int set_ctl = PR_SVE_SET_VL;
+static int get_ctl = PR_SVE_GET_VL;
 
 static const struct option options[] = {
 	{ "force",	no_argument, NULL, 'f' },
 	{ "inherit",	no_argument, NULL, 'i' },
 	{ "max",	no_argument, NULL, 'M' },
 	{ "no-inherit",	no_argument, &no_inherit, 1 },
+	{ "sme",	no_argument, NULL, 's' },
 	{ "help",	no_argument, NULL, '?' },
 	{}
 };

@@ -50,6 +53,9 @@ static int parse_options(int argc, char **argv)
 		case 'M':	vl = SVE_VL_MAX; break;
 		case 'f':	force = 1; break;
 		case 'i':	inherit = 1; break;
+		case 's':	set_ctl = PR_SME_SET_VL;
+				get_ctl = PR_SME_GET_VL;
+				break;
 		case 0:		break;
 		default:	goto error;
 		}

@@ -125,14 +131,14 @@ int main(int argc, char **argv)
 	if (inherit)
 		flags |= PR_SVE_VL_INHERIT;
 
-	t = prctl(PR_SVE_SET_VL, vl | flags);
+	t = prctl(set_ctl, vl | flags);
 	if (t < 0) {
 		fprintf(stderr, "%s: PR_SVE_SET_VL: %s\n",
 			program_name, strerror(errno));
 		goto error;
 	}
 
-	t = prctl(PR_SVE_GET_VL);
+	t = prctl(get_ctl);
 	if (t == -1) {
 		fprintf(stderr, "%s: PR_SVE_GET_VL: %s\n",
 			program_name, strerror(errno));

298 lines not on this page · raw message

new file mode 100644
index 000000000000..49b0b2e08bac
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <stdio.h>
+
+#include "rdvl.h"
+
+int main(void)
+{
+	int vl = rdvl_sme();
+
+	printf("%d\n", vl);
+
+	return 0;
+}

index 7c9d953fc9e7..5d323679fbc9 100644
@@ -3,6 +3,7 @@
 #ifndef RDVL_H
 #define RDVL_H
 
+int rdvl_sme(void);
 int rdvl_sve(void);
 
 #endif

index c90658811a83..9bcfcdc34ee9 100644
@@ -51,6 +51,16 @@ static struct vec_data vec_data[] = {
 		.prctl_set = PR_SVE_SET_VL,
 		.default_vl_file = "/proc/sys/abi/sve_default_vector_length",
 	},
+	{
+		.name = "SME",
+		.hwcap_type = AT_HWCAP2,
+		.hwcap = HWCAP2_SME,
+		.rdvl = rdvl_sme,
+		.rdvl_binary = "./rdvl-sme",
+		.prctl_get = PR_SME_GET_VL,
+		.prctl_set = PR_SME_SET_VL,
+		.default_vl_file = "/proc/sys/abi/sme_default_vector_length",
+	},
 };
 
 static int stdio_read_integer(FILE *f, const char *what, int *val)

index ebe8694dbef0..f909b70d9e98 100644
@@ -53,6 +53,7 @@ struct tdescr {
 	char			*name;
 	char			*descr;
 	unsigned long		feats_required;
+	unsigned long		feats_incompatible;
 	/* bitmask of effectively supported feats: populated at run-time */
 	unsigned long		feats_supported;
 	bool			initialized;

index 2f8c23af3b5e..5743897984b0 100644
@@ -36,6 +36,8 @@ static inline char *feats_to_string(unsigned long feats)
 {
 	size_t flen = MAX_FEATS_SZ - 1;
 
+	feats_string[0] = '\0';
+
 	for (int i = 0; i < FMAX_END; i++) {
 		if (feats & (1UL << i)) {
 			size_t tlen = strlen(feats_names[i]);

@@ -256,7 +258,7 @@ int test_init(struct tdescr *td)
 		td->minsigstksz = MINSIGSTKSZ;
 	fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz);
 
-	if (td->feats_required) {
+	if (td->feats_required || td->feats_incompatible) {
 		td->feats_supported = 0;
 		/*
 		 * Checking for CPU required features using both the

@@ -267,15 +269,29 @@ int test_init(struct tdescr *td)
 		if (getauxval(AT_HWCAP) & HWCAP_SVE)
 			td->feats_supported |= FEAT_SVE;
 		if (feats_ok(td)) {
-			fprintf(stderr,
-				"Required Features: [%s] supported\n",
-				feats_to_string(td->feats_required &
-						td->feats_supported));
+			if (td->feats_required & td->feats_supported)
+				fprintf(stderr,
+					"Required Features: [%s] supported\n",
+					feats_to_string(td->feats_required &
+							td->feats_supported));
+			if (!(td->feats_incompatible & td->feats_supported))
+				fprintf(stderr,
+					"Incompatible Features: [%s] absent\n",
+					feats_to_string(td->feats_incompatible));
 		} else {
-			fprintf(stderr,
-				"Required Features: [%s] NOT supported\n",
-				feats_to_string(td->feats_required &
-						~td->feats_supported));
+			if ((td->feats_required & td->feats_supported) !=
+			    td->feats_supported)
+				fprintf(stderr,
+					"Required Features: [%s] NOT supported\n",
+					feats_to_string(td->feats_required &
+							~td->feats_supported));
+			if (td->feats_incompatible & td->feats_supported)
+				fprintf(stderr,
+					"Incompatible Features: [%s] supported\n",
+					feats_to_string(td->feats_incompatible &
+							~td->feats_supported));
+
+
 			td->result = KSFT_SKIP;
 			return 0;
 		}

index 6772b5c8d274..f3aa99ba67bb 100644
@@ -18,6 +18,8 @@ void test_result(struct tdescr *td);
 
 static inline bool feats_ok(struct tdescr *td)
 {
+	if (td->feats_incompatible & td->feats_supported)
+		return false;
 	return (td->feats_required & td->feats_supported) == td->feats_required;
 }
 

index 8c2a57fc2f9c..84c36bee4d82 100644
@@ -75,6 +75,31 @@ bool validate_sve_context(struct sve_context *sve, char **err)
 	return true;
 }
 
+bool validate_za_context(struct za_context *za, char **err)
+{
+	/* Size will be rounded up to a multiple of 16 bytes */
+	size_t regs_size
+		= ((ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za->vl)) + 15) / 16) * 16;
+
+	if (!za || !err)
+		return false;
+
+	/* Either a bare za_context or a za_context followed by regs data */
+	if ((za->head.size != sizeof(struct za_context)) &&
+	    (za->head.size != regs_size)) {
+		*err = "bad size for ZA context";
+		return false;
+	}
+
+	if (!sve_vl_valid(za->vl)) {
+		*err = "SME VL in ZA context invalid";
+
+		return false;
+	}
+
+	return true;
+}
+
 bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 {
 	bool terminated = false;