1 files changed, 317 insertions, 166 deletions

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index aea43ec60f37..1c87699fd886 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -18,31 +18,48 @@
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
-#include <kvm/arm_psci.h>
+#include <kvm/arm_hypercalls.h>
 #include <asm/cputype.h>
 #include <linux/uaccess.h>
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_emulate.h>
-#include <asm/kvm_coproc.h>
+#include <asm/kvm_nested.h>
 #include <asm/sigcontext.h>
 
 #include "trace.h"
 
-struct kvm_stats_debugfs_item debugfs_entries[] = {
-	VCPU_STAT("halt_successful_poll", halt_successful_poll),
-	VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
-	VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
-	VCPU_STAT("halt_wakeup", halt_wakeup),
-	VCPU_STAT("hvc_exit_stat", hvc_exit_stat),
-	VCPU_STAT("wfe_exit_stat", wfe_exit_stat),
-	VCPU_STAT("wfi_exit_stat", wfi_exit_stat),
-	VCPU_STAT("mmio_exit_user", mmio_exit_user),
-	VCPU_STAT("mmio_exit_kernel", mmio_exit_kernel),
-	VCPU_STAT("exits", exits),
-	VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
-	VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
-	{ NULL }
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS()
+};
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset =  sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
+const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+	KVM_GENERIC_VCPU_STATS(),
+	STATS_DESC_COUNTER(VCPU, hvc_exit_stat),
+	STATS_DESC_COUNTER(VCPU, wfe_exit_stat),
+	STATS_DESC_COUNTER(VCPU, wfi_exit_stat),
+	STATS_DESC_COUNTER(VCPU, mmio_exit_user),
+	STATS_DESC_COUNTER(VCPU, mmio_exit_kernel),
+	STATS_DESC_COUNTER(VCPU, signal_exits),
+	STATS_DESC_COUNTER(VCPU, exits)
+};
+
+const struct kvm_stats_header kvm_vcpu_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vcpu_stats_desc),
 };
 
 static bool core_reg_offset_is_vreg(u64 off)
@@ -101,19 +118,69 @@ static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off)
 	return size;
 }
 
-static int validate_core_offset(const struct kvm_vcpu *vcpu,
-				const struct kvm_one_reg *reg)
+static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	u64 off = core_reg_offset_from_id(reg->id);
 	int size = core_reg_size_from_offset(vcpu, off);
 
 	if (size < 0)
-		return -EINVAL;
+		return NULL;
 
 	if (KVM_REG_SIZE(reg->id) != size)
-		return -EINVAL;
+		return NULL;
 
-	return 0;
+	switch (off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+		off -= KVM_REG_ARM_CORE_REG(regs.regs[0]);
+		off /= 2;
+		return &vcpu->arch.ctxt.regs.regs[off];
+
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+		return &vcpu->arch.ctxt.regs.sp;
+
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+		return &vcpu->arch.ctxt.regs.pc;
+
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+		return &vcpu->arch.ctxt.regs.pstate;
+
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, SP_EL1);
+
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1);
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]):
+		return __ctxt_sys_reg(&vcpu->arch.ctxt, SPSR_EL1);
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]):
+		return &vcpu->arch.ctxt.spsr_abt;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_UND]):
+		return &vcpu->arch.ctxt.spsr_und;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_IRQ]):
+		return &vcpu->arch.ctxt.spsr_irq;
+
+	case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_FIQ]):
+		return &vcpu->arch.ctxt.spsr_fiq;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		off -= KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]);
+		off /= 4;
+		return &vcpu->arch.ctxt.fp_regs.vregs[off];
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+		return &vcpu->arch.ctxt.fp_regs.fpsr;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		return &vcpu->arch.ctxt.fp_regs.fpcr;
+
+	default:
+		return NULL;
+	}
 }
 
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
@@ -125,8 +192,8 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	 * off the index in the "array".
 	 */
 	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
-	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
-	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32);
+	void *addr;
 	u32 off;
 
 	/* Our ID is an index into the kvm_regs struct. */
@@ -135,10 +202,11 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(vcpu, reg))
+	addr = core_reg_addr(vcpu, reg);
+	if (!addr)
 		return -EINVAL;
 
-	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
+	if (copy_to_user(uaddr, addr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
 	return 0;
@@ -147,10 +215,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	__u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
-	struct kvm_regs *regs = vcpu_gp_regs(vcpu);
-	int nr_regs = sizeof(*regs) / sizeof(__u32);
+	int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32);
 	__uint128_t tmp;
-	void *valp = &tmp;
+	void *valp = &tmp, *addr;
 	u64 off;
 	int err = 0;
 
@@ -160,7 +227,8 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
-	if (validate_core_offset(vcpu, reg))
+	addr = core_reg_addr(vcpu, reg);
+	if (!addr)
 		return -EINVAL;
 
 	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
@@ -175,7 +243,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
 		case PSR_AA32_MODE_USR:
-			if (!system_supports_32bit_el0())
+			if (!kvm_supports_32bit_el0())
 				return -EINVAL;
 			break;
 		case PSR_AA32_MODE_FIQ:
@@ -183,9 +251,15 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		case PSR_AA32_MODE_SVC:
 		case PSR_AA32_MODE_ABT:
 		case PSR_AA32_MODE_UND:
+		case PSR_AA32_MODE_SYS:
 			if (!vcpu_el1_is_32bit(vcpu))
 				return -EINVAL;
 			break;
+		case PSR_MODE_EL2h:
+		case PSR_MODE_EL2t:
+			if (!vcpu_has_nv(vcpu))
+				return -EINVAL;
+			fallthrough;
 		case PSR_MODE_EL0t:
 		case PSR_MODE_EL1t:
 		case PSR_MODE_EL1h:
@@ -198,13 +272,35 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		}
 	}
 
-	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+	memcpy(addr, valp, KVM_REG_SIZE(reg->id));
 
 	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
-		int i;
+		int i, nr_reg;
+
+		switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) {
+		/*
+		 * Either we are dealing with user mode, and only the
+		 * first 15 registers (+ PC) must be narrowed to 32bit.
+		 * AArch32 r0-r14 conveniently map to AArch64 x0-x14.
+		 */
+		case PSR_AA32_MODE_USR:
+		case PSR_AA32_MODE_SYS:
+			nr_reg = 15;
+			break;
 
-		for (i = 0; i < 16; i++)
-			*vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i);
+		/*
+		 * Otherwise, this is a privileged mode, and *all* the
+		 * registers must be narrowed to 32bit.
+		 */
+		default:
+			nr_reg = 31;
+			break;
+		}
+
+		for (i = 0; i < nr_reg; i++)
+			vcpu_set_reg(vcpu, i, (u32)vcpu_get_reg(vcpu, i));
+
+		*vcpu_pc(vcpu) = (u32)*vcpu_pc(vcpu);
 	}
 out:
 	return err;
@@ -227,7 +323,7 @@ static int get_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	memset(vqs, 0, sizeof(vqs));
 
-	max_vq = sve_vq_from_vl(vcpu->arch.sve_max_vl);
+	max_vq = vcpu_sve_max_vq(vcpu);
 	for (vq = SVE_VQ_MIN; vq <= max_vq; ++vq)
 		if (sve_vq_available(vq))
 			vqs[vq_word(vq)] |= vq_mask(vq);
@@ -355,7 +451,7 @@ static int sve_reg_to_region(struct sve_state_reg_region *region,
 		if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0)
 			return -ENOENT;
 
-		vq = sve_vq_from_vl(vcpu->arch.sve_max_vl);
+		vq = vcpu_sve_max_vq(vcpu);
 
 		reqoffset = SVE_SIG_ZREG_OFFSET(vq, reg_num) -
 				SVE_SIG_REGS_OFFSET;
@@ -365,7 +461,7 @@ static int sve_reg_to_region(struct sve_state_reg_region *region,
 		if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0)
 			return -ENOENT;
 
-		vq = sve_vq_from_vl(vcpu->arch.sve_max_vl);
+		vq = vcpu_sve_max_vq(vcpu);
 
 		reqoffset = SVE_SIG_PREG_OFFSET(vq, reg_num) -
 				SVE_SIG_REGS_OFFSET;
@@ -495,59 +591,6 @@ static unsigned long num_core_regs(const struct kvm_vcpu *vcpu)
 	return copy_core_reg_indices(vcpu, NULL);
 }
 
-/**
- * ARM64 versions of the TIMER registers, always available on arm64
- */
-
-#define NUM_TIMER_REGS 3
-
-static bool is_timer_reg(u64 index)
-{
-	switch (index) {
-	case KVM_REG_ARM_TIMER_CTL:
-	case KVM_REG_ARM_TIMER_CNT:
-	case KVM_REG_ARM_TIMER_CVAL:
-		return true;
-	}
-	return false;
-}
-
-static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
-{
-	if (put_user(KVM_REG_ARM_TIMER_CTL, uindices))
-		return -EFAULT;
-	uindices++;
-	if (put_user(KVM_REG_ARM_TIMER_CNT, uindices))
-		return -EFAULT;
-	uindices++;
-	if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices))
-		return -EFAULT;
-
-	return 0;
-}
-
-static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
-{
-	void __user *uaddr = (void __user *)(long)reg->addr;
-	u64 val;
-	int ret;
-
-	ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
-	if (ret != 0)
-		return -EFAULT;
-
-	return kvm_arm_timer_set_reg(vcpu, reg->id, val);
-}
-
-static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
-{
-	void __user *uaddr = (void __user *)(long)reg->addr;
-	u64 val;
-
-	val = kvm_arm_timer_get_reg(vcpu, reg->id);
-	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
-}
-
 static unsigned long num_sve_regs(const struct kvm_vcpu *vcpu)
 {
 	const unsigned int slices = vcpu_sve_slices(vcpu);
@@ -611,6 +654,7 @@ static int copy_sve_reg_indices(const struct kvm_vcpu *vcpu,
 
 /**
  * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG
+ * @vcpu: the vCPU pointer
  *
  * This is for all registers.
  */
@@ -622,13 +666,14 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 	res += num_sve_regs(vcpu);
 	res += kvm_arm_num_sys_reg_descs(vcpu);
 	res += kvm_arm_get_fw_num_regs(vcpu);
-	res += NUM_TIMER_REGS;
 
 	return res;
 }
 
 /**
  * kvm_arm_copy_reg_indices - get indices of all registers.
+ * @vcpu: the vCPU pointer
+ * @uindices: register list to copy
  *
  * We do core registers right here, then we append system regs.
  */
@@ -651,11 +696,6 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 		return ret;
 	uindices += kvm_arm_get_fw_num_regs(vcpu);
 
-	ret = copy_timer_indices(vcpu, uindices);
-	if (ret < 0)
-		return ret;
-	uindices += NUM_TIMER_REGS;
-
 	return kvm_arm_copy_sys_reg_indices(vcpu, uindices);
 }
 
@@ -667,13 +707,12 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	switch (reg->id & KVM_REG_ARM_COPROC_MASK) {
 	case KVM_REG_ARM_CORE:	return get_core_reg(vcpu, reg);
-	case KVM_REG_ARM_FW:	return kvm_arm_get_fw_reg(vcpu, reg);
+	case KVM_REG_ARM_FW:
+	case KVM_REG_ARM_FW_FEAT_BMAP:
+		return kvm_arm_get_fw_reg(vcpu, reg);
 	case KVM_REG_ARM64_SVE:	return get_sve_reg(vcpu, reg);
 	}
 
-	if (is_timer_reg(reg->id))
-		return get_timer_reg(vcpu, reg);
-
 	return kvm_arm_sys_reg_get_reg(vcpu, reg);
 }
 
@@ -685,13 +724,12 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	switch (reg->id & KVM_REG_ARM_COPROC_MASK) {
 	case KVM_REG_ARM_CORE:	return set_core_reg(vcpu, reg);
-	case KVM_REG_ARM_FW:	return kvm_arm_set_fw_reg(vcpu, reg);
+	case KVM_REG_ARM_FW:
+	case KVM_REG_ARM_FW_FEAT_BMAP:
+		return kvm_arm_set_fw_reg(vcpu, reg);
 	case KVM_REG_ARM64_SVE:	return set_sve_reg(vcpu, reg);
 	}
 
-	if (is_timer_reg(reg->id))
-		return set_timer_reg(vcpu, reg);
-
 	return kvm_arm_sys_reg_set_reg(vcpu, reg);
 }
 
@@ -710,8 +748,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events)
 {
-	events->exception.serror_pending = !!(vcpu->arch.hcr_el2 & HCR_VSE);
-	events->exception.serror_has_esr = cpus_have_const_cap(ARM64_HAS_RAS_EXTN);
+	events->exception.serror_has_esr = cpus_have_final_cap(ARM64_HAS_RAS_EXTN);
+	events->exception.serror_pending = (vcpu->arch.hcr_el2 & HCR_VSE) ||
+					   vcpu_get_flag(vcpu, NESTED_SERROR_PENDING);
 
 	if (events->exception.serror_pending && events->exception.serror_has_esr)
 		events->exception.serror_esr = vcpu_get_vsesr(vcpu);
@@ -725,32 +764,65 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static void commit_pending_events(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu_get_flag(vcpu, PENDING_EXCEPTION))
+		return;
+
+	/*
+	 * Reset the MMIO emulation state to avoid stepping PC after emulating
+	 * the exception entry.
+	 */
+	vcpu->mmio_needed = false;
+	kvm_call_hyp(__kvm_adjust_pc, vcpu);
+}
+
 int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events)
 {
 	bool serror_pending = events->exception.serror_pending;
 	bool has_esr = events->exception.serror_has_esr;
 	bool ext_dabt_pending = events->exception.ext_dabt_pending;
+	u64 esr = events->exception.serror_esr;
+	int ret = 0;
 
-	if (serror_pending && has_esr) {
-		if (!cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
-			return -EINVAL;
-
-		if (!((events->exception.serror_esr) & ~ESR_ELx_ISS_MASK))
-			kvm_set_sei_esr(vcpu, events->exception.serror_esr);
-		else
-			return -EINVAL;
-	} else if (serror_pending) {
-		kvm_inject_vabt(vcpu);
+	/*
+	 * Immediately commit the pending SEA to the vCPU's architectural
+	 * state which is necessary since we do not return a pending SEA
+	 * to userspace via KVM_GET_VCPU_EVENTS.
+	 */
+	if (ext_dabt_pending) {
+		ret = kvm_inject_sea_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+		commit_pending_events(vcpu);
 	}
 
-	if (ext_dabt_pending)
-		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+	if (ret < 0)
+		return ret;
 
-	return 0;
+	if (!serror_pending)
+		return 0;
+
+	if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && has_esr)
+		return -EINVAL;
+
+	if (has_esr && (esr & ~ESR_ELx_ISS_MASK))
+		return -EINVAL;
+
+	if (has_esr)
+		ret = kvm_inject_serror_esr(vcpu, esr);
+	else
+		ret = kvm_inject_serror(vcpu);
+
+	/*
+	 * We could've decided that the SError is due for immediate software
+	 * injection; commit the exception in case userspace decides it wants
+	 * to inject more exceptions for some strange reason.
+	 */
+	commit_pending_events(vcpu);
+	return (ret < 0) ? ret : 0;
 }
 
-int __attribute_const__ kvm_target_cpu(void)
+u32 __attribute_const__ kvm_target_cpu(void)
 {
 	unsigned long implementor = read_cpuid_implementor();
 	unsigned long part_number = read_cpuid_part_number();
@@ -770,7 +842,7 @@ int __attribute_const__ kvm_target_cpu(void)
 		break;
 	case ARM_CPU_IMP_APM:
 		switch (part_number) {
-		case APM_CPU_PART_POTENZA:
+		case APM_CPU_PART_XGENE:
 			return KVM_ARM_TARGET_XGENE_POTENZA;
 		}
 		break;
@@ -780,26 +852,6 @@ int __attribute_const__ kvm_target_cpu(void)
 	return KVM_ARM_TARGET_GENERIC_V8;
 }
 
-int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
-{
-	int target = kvm_target_cpu();
-
-	if (target < 0)
-		return -ENODEV;
-
-	memset(init, 0, sizeof(*init));
-
-	/*
-	 * For now, we don't return any features.
-	 * In future, we might use features to return target
-	 * specific features available for the preferred
-	 * target type.
-	 */
-	init->target = (__u32)target;
-
-	return 0;
-}
-
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -EINVAL;
@@ -816,15 +868,10 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
-#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE |    \
-			    KVM_GUESTDBG_USE_SW_BP | \
-			    KVM_GUESTDBG_USE_HW | \
-			    KVM_GUESTDBG_SINGLESTEP)
-
 /**
  * kvm_arch_vcpu_ioctl_set_guest_debug - set up guest debugging
- * @kvm:	pointer to the KVM struct
- * @kvm_guest_debug: the ioctl data buffer
+ * @vcpu: the vCPU pointer
+ * @dbg: the ioctl data buffer
  *
  * This sets up and enables the VM for guest debugging. Userspace
  * passes in a control flag to enable different debug types and
@@ -834,30 +881,24 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg)
 {
-	int ret = 0;
-
 	trace_kvm_set_guest_debug(vcpu, dbg->control);
 
-	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (dbg->control & KVM_GUESTDBG_ENABLE) {
-		vcpu->guest_debug = dbg->control;
-
-		/* Hardware assisted Break and Watch points */
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) {
-			vcpu->arch.external_debug_state = dbg->arch;
-		}
+	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK)
+		return -EINVAL;
 
-	} else {
-		/* If not enabled clear all flags */
+	if (!(dbg->control & KVM_GUESTDBG_ENABLE)) {
 		vcpu->guest_debug = 0;
+		vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING);
+		return 0;
 	}
 
-out:
-	return ret;
+	vcpu->guest_debug = dbg->control;
+
+	/* Hardware assisted Break and Watch points */
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW)
+		vcpu->arch.external_debug_state = dbg->arch;
+
+	return 0;
 }
 
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
@@ -867,7 +908,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 
 	switch (attr->group) {
 	case KVM_ARM_VCPU_PMU_V3_CTRL:
+		mutex_lock(&vcpu->kvm->arch.config_lock);
 		ret = kvm_arm_pmu_v3_set_attr(vcpu, attr);
+		mutex_unlock(&vcpu->kvm->arch.config_lock);
 		break;
 	case KVM_ARM_VCPU_TIMER_CTRL:
 		ret = kvm_arm_timer_set_attr(vcpu, attr);
@@ -928,3 +971,111 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 
 	return ret;
 }
+
+int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
+			       struct kvm_arm_copy_mte_tags *copy_tags)
+{
+	gpa_t guest_ipa = copy_tags->guest_ipa;
+	size_t length = copy_tags->length;
+	void __user *tags = copy_tags->addr;
+	gpa_t gfn;
+	bool write = !(copy_tags->flags & KVM_ARM_TAGS_FROM_GUEST);
+	int ret = 0;
+
+	if (!kvm_has_mte(kvm))
+		return -EINVAL;
+
+	if (copy_tags->reserved[0] || copy_tags->reserved[1])
+		return -EINVAL;
+
+	if (copy_tags->flags & ~KVM_ARM_TAGS_FROM_GUEST)
+		return -EINVAL;
+
+	if (length & ~PAGE_MASK || guest_ipa & ~PAGE_MASK)
+		return -EINVAL;
+
+	/* Lengths above INT_MAX cannot be represented in the return value */
+	if (length > INT_MAX)
+		return -EINVAL;
+
+	gfn = gpa_to_gfn(guest_ipa);
+
+	mutex_lock(&kvm->slots_lock);
+
+	if (write && atomic_read(&kvm->nr_memslots_dirty_logging)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	while (length > 0) {
+		struct page *page = __gfn_to_page(kvm, gfn, write);
+		void *maddr;
+		unsigned long num_tags;
+		struct folio *folio;
+
+		if (!page) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		if (!pfn_to_online_page(page_to_pfn(page))) {
+			/* Reject ZONE_DEVICE memory */
+			kvm_release_page_unused(page);
+			ret = -EFAULT;
+			goto out;
+		}
+		folio = page_folio(page);
+		maddr = page_address(page);
+
+		if (!write) {
+			if ((folio_test_hugetlb(folio) &&
+			     folio_test_hugetlb_mte_tagged(folio)) ||
+			     page_mte_tagged(page))
+				num_tags = mte_copy_tags_to_user(tags, maddr,
+							MTE_GRANULES_PER_PAGE);
+			else
+				/* No tags in memory, so write zeros */
+				num_tags = MTE_GRANULES_PER_PAGE -
+					clear_user(tags, MTE_GRANULES_PER_PAGE);
+			kvm_release_page_clean(page);
+		} else {
+			/*
+			 * Only locking to serialise with a concurrent
+			 * __set_ptes() in the VMM but still overriding the
+			 * tags, hence ignoring the return value.
+			 */
+			if (folio_test_hugetlb(folio))
+				folio_try_hugetlb_mte_tagging(folio);
+			else
+				try_page_mte_tagging(page);
+			num_tags = mte_copy_tags_from_user(maddr, tags,
+							MTE_GRANULES_PER_PAGE);
+
+			/* uaccess failed, don't leave stale tags */
+			if (num_tags != MTE_GRANULES_PER_PAGE)
+				mte_clear_page_tags(maddr);
+			if (folio_test_hugetlb(folio))
+				folio_set_hugetlb_mte_tagged(folio);
+			else
+				set_page_mte_tagged(page);
+
+			kvm_release_page_dirty(page);
+		}
+
+		if (num_tags != MTE_GRANULES_PER_PAGE) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		gfn++;
+		tags += num_tags;
+		length -= PAGE_SIZE;
+	}
+
+out:
+	mutex_unlock(&kvm->slots_lock);
+	/* If some data has been copied report the number of bytes copied */
+	if (length != copy_tags->length)
+		return copy_tags->length - length;
+	return ret;
+}