Merge branch kvm-arm64/mops into kvmarm/next

* kvm-arm64/mops:
  : KVM support for MOPS, courtesy of Kristina Martsenko
  :
  : MOPS adds new instructions for accelerating memcpy(), memset(), and
  : memmove() operations in hardware. This series brings virtualization
  : support for KVM guests, and allows VMs to run on asymmetrict systems
  : that may have different MOPS implementations.
  KVM: arm64: Expose MOPS instructions to guests
  KVM: arm64: Add handler for MOPS exceptions

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

Author: oupton

arch/arm64/include/asm/kvm_arm.h

@@ -102,7 +102,9 @@
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
-#define HCRX_GUEST_FLAGS (HCRX_EL2_SMPME | HCRX_EL2_TCR2En)
+#define HCRX_GUEST_FLAGS \
+	(HCRX_EL2_SMPME | HCRX_EL2_TCR2En | \
+	 (cpus_have_final_cap(ARM64_HAS_MOPS) ? (HCRX_EL2_MSCEn | HCRX_EL2_MCE2) : 0))
 #define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En)
 
 /* TCR_EL2 Registers bits */

arch/arm64/include/asm/traps.h

@@ -9,10 +9,9 @@
 
 #include <linux/list.h>
 #include <asm/esr.h>
+#include <asm/ptrace.h>
 #include <asm/sections.h>
 
-struct pt_regs;
-
 #ifdef CONFIG_ARMV8_DEPRECATED
 bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn);
 #else
@@ -101,4 +100,55 @@ static inline unsigned long arm64_ras_serror_get_severity(unsigned long esr)
 
 bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr);
 void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr);
+
+static inline void arm64_mops_reset_regs(struct user_pt_regs *regs, unsigned long esr)
+{
+	bool wrong_option = esr & ESR_ELx_MOPS_ISS_WRONG_OPTION;
+	bool option_a = esr & ESR_ELx_MOPS_ISS_OPTION_A;
+	int dstreg = ESR_ELx_MOPS_ISS_DESTREG(esr);
+	int srcreg = ESR_ELx_MOPS_ISS_SRCREG(esr);
+	int sizereg = ESR_ELx_MOPS_ISS_SIZEREG(esr);
+	unsigned long dst, src, size;
+
+	dst = regs->regs[dstreg];
+	src = regs->regs[srcreg];
+	size = regs->regs[sizereg];
+
+	/*
+	 * Put the registers back in the original format suitable for a
+	 * prologue instruction, using the generic return routine from the
+	 * Arm ARM (DDI 0487I.a) rules CNTMJ and MWFQH.
+	 */
+	if (esr & ESR_ELx_MOPS_ISS_MEM_INST) {
+		/* SET* instruction */
+		if (option_a ^ wrong_option) {
+			/* Format is from Option A; forward set */
+			regs->regs[dstreg] = dst + size;
+			regs->regs[sizereg] = -size;
+		}
+	} else {
+		/* CPY* instruction */
+		if (!(option_a ^ wrong_option)) {
+			/* Format is from Option B */
+			if (regs->pstate & PSR_N_BIT) {
+				/* Backward copy */
+				regs->regs[dstreg] = dst - size;
+				regs->regs[srcreg] = src - size;
+			}
+		} else {
+			/* Format is from Option A */
+			if (size & BIT(63)) {
+				/* Forward copy */
+				regs->regs[dstreg] = dst + size;
+				regs->regs[srcreg] = src + size;
+				regs->regs[sizereg] = -size;
+			}
+		}
+	}
+
+	if (esr & ESR_ELx_MOPS_ISS_FROM_EPILOGUE)
+		regs->pc -= 8;
+	else
+		regs->pc -= 4;
+}
 #endif

arch/arm64/kernel/traps.c

@@ -516,53 +516,7 @@ void do_el1_fpac(struct pt_regs *regs, unsigned long esr)
 
 void do_el0_mops(struct pt_regs *regs, unsigned long esr)
 {
-	bool wrong_option = esr & ESR_ELx_MOPS_ISS_WRONG_OPTION;
-	bool option_a = esr & ESR_ELx_MOPS_ISS_OPTION_A;
-	int dstreg = ESR_ELx_MOPS_ISS_DESTREG(esr);
-	int srcreg = ESR_ELx_MOPS_ISS_SRCREG(esr);
-	int sizereg = ESR_ELx_MOPS_ISS_SIZEREG(esr);
-	unsigned long dst, src, size;
-
-	dst = pt_regs_read_reg(regs, dstreg);
-	src = pt_regs_read_reg(regs, srcreg);
-	size = pt_regs_read_reg(regs, sizereg);
-
-	/*
-	 * Put the registers back in the original format suitable for a
-	 * prologue instruction, using the generic return routine from the
-	 * Arm ARM (DDI 0487I.a) rules CNTMJ and MWFQH.
-	 */
-	if (esr & ESR_ELx_MOPS_ISS_MEM_INST) {
-		/* SET* instruction */
-		if (option_a ^ wrong_option) {
-			/* Format is from Option A; forward set */
-			pt_regs_write_reg(regs, dstreg, dst + size);
-			pt_regs_write_reg(regs, sizereg, -size);
-		}
-	} else {
-		/* CPY* instruction */
-		if (!(option_a ^ wrong_option)) {
-			/* Format is from Option B */
-			if (regs->pstate & PSR_N_BIT) {
-				/* Backward copy */
-				pt_regs_write_reg(regs, dstreg, dst - size);
-				pt_regs_write_reg(regs, srcreg, src - size);
-			}
-		} else {
-			/* Format is from Option A */
-			if (size & BIT(63)) {
-				/* Forward copy */
-				pt_regs_write_reg(regs, dstreg, dst + size);
-				pt_regs_write_reg(regs, srcreg, src + size);
-				pt_regs_write_reg(regs, sizereg, -size);
-			}
-		}
-	}
-
-	if (esr & ESR_ELx_MOPS_ISS_FROM_EPILOGUE)
-		regs->pc -= 8;
-	else
-		regs->pc -= 4;
+	arm64_mops_reset_regs(&regs->user_regs, esr);
 
 	/*
 	 * If single stepping then finish the step before executing the

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -30,6 +30,7 @@
 #include <asm/fpsimd.h>
 #include <asm/debug-monitors.h>
 #include <asm/processor.h>
+#include <asm/traps.h>
 
 struct kvm_exception_table_entry {
 	int insn, fixup;
@@ -265,6 +266,22 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
 	return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault);
 }
 
+static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
+	arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2);
+	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
+
+	/*
+	 * Finish potential single step before executing the prologue
+	 * instruction.
+	 */
+	*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
+	write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
+
+	return true;
+}
+
 static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 {
 	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);

arch/arm64/kvm/hyp/include/nvhe/fixed_config.h

@@ -197,7 +197,8 @@
 
 #define PVM_ID_AA64ISAR2_ALLOW (\
 	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) \
+	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) | \
+	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_MOPS) \
 	)
 
 u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id);

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -192,6 +192,7 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
 	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
 	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
 };
 
 static const exit_handler_fn pvm_exit_handlers[] = {
@@ -203,6 +204,7 @@ static const exit_handler_fn pvm_exit_handlers[] = {
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
 	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
 	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
 };
 
 static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/vhe/switch.c

@@ -139,6 +139,7 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
 	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
 	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
 };
 
 static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)

arch/arm64/kvm/sys_regs.c

@@ -1348,7 +1348,6 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 				 ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3));
 		if (!cpus_have_final_cap(ARM64_HAS_WFXT))
 			val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_WFxT);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_MOPS);
 		break;
 	case SYS_ID_AA64MMFR2_EL1:
 		val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
@@ -2099,7 +2098,6 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 					ID_AA64ISAR1_EL1_API |
 					ID_AA64ISAR1_EL1_APA)),
 	ID_WRITABLE(ID_AA64ISAR2_EL1, ~(ID_AA64ISAR2_EL1_RES0 |
-					ID_AA64ISAR2_EL1_MOPS |
 					ID_AA64ISAR2_EL1_APA3 |
 					ID_AA64ISAR2_EL1_GPA3)),
 	ID_UNALLOCATED(6,3),