Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull RCU updates from Paul McKenney:

  1. Miscellaneous fixes.
  2. kfree_rcu() updates.
  3. Remove scheduler locking restriction
  4. RCU-tasks update, including addition of RCU Tasks Trace for
     BPF use and RCU Tasks Rude.  (This branch is on top of #3 due
     to overlap of changed code.)
  5. RCU CPU stall warning updates.
  6. Torture-test updates.

12 files changed, 159 insertions, 52 deletions

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index a475c68cbfec..449386d76441 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -64,6 +64,4 @@ config KVM_ARM_PMU
 config KVM_INDIRECT_VECTORS
        def_bool KVM && (HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS)
 
-source "drivers/vhost/Kconfig"
-
 endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 525010504f9d..e329a36b2bee 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -11,7 +11,6 @@
 #include <linux/kvm_host.h>
 #include <asm/fpsimd.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_host.h>
 #include <asm/kvm_mmu.h>
 #include <asm/sysreg.h>
 
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 2bd92301d32f..23ebe51410f0 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -25,7 +25,6 @@
 #include <asm/kvm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
-#include <asm/kvm_host.h>
 #include <asm/sigcontext.h>
 
 #include "trace.h"
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 160be2b4696d..6e6ed5581eed 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -18,7 +18,7 @@
 
 	.align	11
 
-ENTRY(__kvm_hyp_init)
+SYM_CODE_START(__kvm_hyp_init)
 	ventry	__invalid		// Synchronous EL2t
 	ventry	__invalid		// IRQ EL2t
 	ventry	__invalid		// FIQ EL2t
@@ -60,7 +60,7 @@ alternative_else_nop_endif
 	msr	ttbr0_el2, x4
 
 	mrs	x4, tcr_el1
-	ldr	x5, =TCR_EL2_MASK
+	mov_q	x5, TCR_EL2_MASK
 	and	x4, x4, x5
 	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
@@ -102,7 +102,7 @@ alternative_else_nop_endif
 	 * as well as the EE bit on BE. Drop the A flag since the compiler
 	 * is allowed to generate unaligned accesses.
 	 */
-	ldr	x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+	mov_q	x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
 CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	msr	sctlr_el2, x4
 	isb
@@ -117,9 +117,9 @@ CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 
 	/* Hello, World! */
 	eret
-ENDPROC(__kvm_hyp_init)
+SYM_CODE_END(__kvm_hyp_init)
 
-ENTRY(__kvm_handle_stub_hvc)
+SYM_CODE_START(__kvm_handle_stub_hvc)
 	cmp	x0, #HVC_SOFT_RESTART
 	b.ne	1f
 
@@ -142,7 +142,7 @@ reset:
 	 * case we coming via HVC_SOFT_RESTART.
 	 */
 	mrs	x5, sctlr_el2
-	ldr	x6, =SCTLR_ELx_FLAGS
+	mov_q	x6, SCTLR_ELx_FLAGS
 	bic	x5, x5, x6		// Clear SCTL_M and etc
 	pre_disable_mmu_workaround
 	msr	sctlr_el2, x5
@@ -155,11 +155,9 @@ reset:
 	eret
 
 1:	/* Bad stub call */
-	ldr	x0, =HVC_STUB_ERR
+	mov_q	x0, HVC_STUB_ERR
 	eret
 
-ENDPROC(__kvm_handle_stub_hvc)
-
-	.ltorg
+SYM_CODE_END(__kvm_handle_stub_hvc)
 
 	.popsection
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index c0094d520dff..3c79a1124af2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -28,7 +28,7 @@
  * and is used to implement hyp stubs in the same way as in
  * arch/arm64/kernel/hyp_stub.S.
  */
-ENTRY(__kvm_call_hyp)
+SYM_FUNC_START(__kvm_call_hyp)
 	hvc	#0
 	ret
-ENDPROC(__kvm_call_hyp)
+SYM_FUNC_END(__kvm_call_hyp)
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 78ff53225691..5b8ff517ff10 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -11,12 +11,12 @@
 	.text
 	.pushsection	.hyp.text, "ax"
 
-ENTRY(__fpsimd_save_state)
+SYM_FUNC_START(__fpsimd_save_state)
 	fpsimd_save	x0, 1
 	ret
-ENDPROC(__fpsimd_save_state)
+SYM_FUNC_END(__fpsimd_save_state)
 
-ENTRY(__fpsimd_restore_state)
+SYM_FUNC_START(__fpsimd_restore_state)
 	fpsimd_restore	x0, 1
 	ret
-ENDPROC(__fpsimd_restore_state)
+SYM_FUNC_END(__fpsimd_restore_state)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index ffa68d5713f1..c2a13ab3c471 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -180,7 +180,7 @@ el2_error:
 	eret
 	sb
 
-ENTRY(__hyp_do_panic)
+SYM_FUNC_START(__hyp_do_panic)
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
 	msr	spsr_el2, lr
@@ -188,18 +188,19 @@ ENTRY(__hyp_do_panic)
 	msr	elr_el2, lr
 	eret
 	sb
-ENDPROC(__hyp_do_panic)
+SYM_FUNC_END(__hyp_do_panic)
 
-ENTRY(__hyp_panic)
+SYM_CODE_START(__hyp_panic)
 	get_host_ctxt x0, x1
 	b	hyp_panic
-ENDPROC(__hyp_panic)
+SYM_CODE_END(__hyp_panic)
 
 .macro invalid_vector	label, target = __hyp_panic
 	.align	2
+SYM_CODE_START(\label)
 \label:
 	b \target
-ENDPROC(\label)
+SYM_CODE_END(\label)
 .endm
 
 	/* None of these should ever happen */
@@ -246,7 +247,7 @@ check_preamble_length 661b, 662b
 check_preamble_length 661b, 662b
 .endm
 
-ENTRY(__kvm_hyp_vector)
+SYM_CODE_START(__kvm_hyp_vector)
 	invalid_vect	el2t_sync_invalid	// Synchronous EL2t
 	invalid_vect	el2t_irq_invalid	// IRQ EL2t
 	invalid_vect	el2t_fiq_invalid	// FIQ EL2t
@@ -266,7 +267,7 @@ ENTRY(__kvm_hyp_vector)
 	valid_vect	el1_irq			// IRQ 32-bit EL1
 	invalid_vect	el1_fiq_invalid		// FIQ 32-bit EL1
 	valid_vect	el1_error		// Error 32-bit EL1
-ENDPROC(__kvm_hyp_vector)
+SYM_CODE_END(__kvm_hyp_vector)
 
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
 .macro hyp_ventry
@@ -311,15 +312,17 @@ alternative_cb_end
 .endm
 
 	.align	11
-ENTRY(__bp_harden_hyp_vecs_start)
+SYM_CODE_START(__bp_harden_hyp_vecs)
 	.rept BP_HARDEN_EL2_SLOTS
 	generate_vectors
 	.endr
-ENTRY(__bp_harden_hyp_vecs_end)
+1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
+	.org 1b
+SYM_CODE_END(__bp_harden_hyp_vecs)
 
 	.popsection
 
-ENTRY(__smccc_workaround_1_smc_start)
+SYM_CODE_START(__smccc_workaround_1_smc)
 	esb
 	sub	sp, sp, #(8 * 4)
 	stp	x2, x3, [sp, #(8 * 0)]
@@ -329,5 +332,7 @@ ENTRY(__smccc_workaround_1_smc_start)
 	ldp	x2, x3, [sp, #(8 * 0)]
 	ldp	x0, x1, [sp, #(8 * 2)]
 	add	sp, sp, #(8 * 4)
-ENTRY(__smccc_workaround_1_smc_end)
+1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
+	.org 1b
+SYM_CODE_END(__smccc_workaround_1_smc)
 #endif
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 925086b46136..8a1e81a400e0 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -17,7 +17,6 @@
 #include <asm/kprobes.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
-#include <asm/kvm_host.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 #include <asm/fpsimd.h>
@@ -98,6 +97,18 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu)
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
 	val &= ~CPACR_EL1_ZEN;
+
+	/*
+	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+	 * except for some missing controls, such as TAM.
+	 * In this case, CPTR_EL2.TAM has the same position with or without
+	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+	 * shift value for trapping the AMU accesses.
+	 */
+
+	val |= CPTR_EL2_TAM;
+
 	if (update_fp_enabled(vcpu)) {
 		if (vcpu_has_sve(vcpu))
 			val |= CPACR_EL1_ZEN;
@@ -119,7 +130,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 	__activate_traps_common(vcpu);
 
 	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TZ;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
 	if (!update_fp_enabled(vcpu)) {
 		val |= CPTR_EL2_TFP;
 		__activate_traps_fpsimd32(vcpu);
@@ -127,7 +138,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 
 	write_sysreg(val, cptr_el2);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
 
 		isb();
@@ -146,12 +157,12 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 hcr = vcpu->arch.hcr_el2;
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
 		hcr |= HCR_TVM;
 
 	write_sysreg(hcr, hcr_el2);
 
-	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
 		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
 
 	if (has_vhe())
@@ -181,7 +192,7 @@ static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	u64 mdcr_el2 = read_sysreg(mdcr_el2);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		u64 val;
 
 		/*
@@ -328,7 +339,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	 * resolve the IPA using the AT instruction.
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
-	    (cpus_have_const_cap(ARM64_WORKAROUND_834220) ||
+	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
 	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
@@ -498,7 +509,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (*exit_code != ARM_EXCEPTION_TRAP)
 		goto exit;
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
 	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
 	    handle_tx2_tvm(vcpu))
 		return true;
@@ -555,7 +566,7 @@ exit:
 
 static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
 {
-	if (!cpus_have_const_cap(ARM64_SSBD))
+	if (!cpus_have_final_cap(ARM64_SSBD))
 		return false;
 
 	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 7672a978926c..75b1925763f1 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -71,7 +71,7 @@ static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ct
 	ctxt->gp_regs.regs.pc		= read_sysreg_el2(SYS_ELR);
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(SYS_SPSR);
 
-	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
 }
 
@@ -118,7 +118,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
 	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
 
-	if (!cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (!cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	SYS_SCTLR);
 		write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	SYS_TCR);
 	} else	if (!ctxt->__hyp_running_vcpu) {
@@ -149,7 +149,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],		tpidr_el1);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) &&
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) &&
 	    ctxt->__hyp_running_vcpu) {
 		/*
 		 * Must only be done for host registers, hence the context
@@ -194,7 +194,7 @@ __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el2(ctxt->gp_regs.regs.pc,		SYS_ELR);
 	write_sysreg_el2(pstate,			SYS_SPSR);
 
-	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
 }
 
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 92f560e3e1aa..ceaddbe4279f 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -23,7 +23,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 
 	local_irq_save(cxt->flags);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
 		/*
 		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
 		 * we cannot trust stage-1 to be in a correct state at that
@@ -63,7 +63,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
 static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 						  struct tlb_inv_context *cxt)
 {
-	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		u64 val;
 
 		/*
@@ -103,7 +103,7 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
 	isb();
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
 		/* Restore the registers to what they were */
 		write_sysreg_el1(cxt->tcr, SYS_TCR);
 		write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
@@ -117,7 +117,7 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 {
 	write_sysreg(0, vttbr_el2);
 
-	if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
 		/* Ensure write of the host VMID */
 		isb();
 		/* Restore the host's TCR_EL1 */
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3e909b117f0c..51db934702b6 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -22,7 +22,6 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
-#include <asm/kvm_host.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 #include <asm/perf_event.h>
@@ -1003,6 +1002,20 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
 	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
 
+static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	kvm_inject_undefined(vcpu);
+
+	return false;
+}
+
+/* Macro to expand the AMU counter and type registers*/
+#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu }
+#define AMU_AMEVTYPE0_EL0(n) { SYS_DESC(SYS_AMEVTYPE0_EL0(n)), access_amu }
+#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu }
+#define AMU_AMEVTYPE1_EL0(n) { SYS_DESC(SYS_AMEVTYPE1_EL0(n)), access_amu }
+
 static bool trap_ptrauth(struct kvm_vcpu *vcpu,
 			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *rd)
@@ -1078,13 +1091,25 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
 	u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
 
-	if (id == SYS_ID_AA64PFR0_EL1 && !vcpu_has_sve(vcpu)) {
-		val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
+	if (id == SYS_ID_AA64PFR0_EL1) {
+		if (!vcpu_has_sve(vcpu))
+			val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
+		val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
 	} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
 		val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) |
 			 (0xfUL << ID_AA64ISAR1_API_SHIFT) |
 			 (0xfUL << ID_AA64ISAR1_GPA_SHIFT) |
 			 (0xfUL << ID_AA64ISAR1_GPI_SHIFT));
+	} else if (id == SYS_ID_AA64DFR0_EL1) {
+		/* Limit guests to PMUv3 for ARMv8.1 */
+		val = cpuid_feature_cap_perfmon_field(val,
+						ID_AA64DFR0_PMUVER_SHIFT,
+						ID_AA64DFR0_PMUVER_8_1);
+	} else if (id == SYS_ID_DFR0_EL1) {
+		/* Limit guests to PMUv3 for ARMv8.1 */
+		val = cpuid_feature_cap_perfmon_field(val,
+						ID_DFR0_PERFMON_SHIFT,
+						ID_DFR0_PERFMON_8_1);
 	}
 
 	return val;
@@ -1565,6 +1590,79 @@ 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_AMCR_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCFGR_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCGCR_EL0), access_amu },
+	{ SYS_DESC(SYS_AMUSERENR_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu },
+	{ SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu },
+	AMU_AMEVCNTR0_EL0(0),
+	AMU_AMEVCNTR0_EL0(1),
+	AMU_AMEVCNTR0_EL0(2),
+	AMU_AMEVCNTR0_EL0(3),
+	AMU_AMEVCNTR0_EL0(4),
+	AMU_AMEVCNTR0_EL0(5),
+	AMU_AMEVCNTR0_EL0(6),
+	AMU_AMEVCNTR0_EL0(7),
+	AMU_AMEVCNTR0_EL0(8),
+	AMU_AMEVCNTR0_EL0(9),
+	AMU_AMEVCNTR0_EL0(10),
+	AMU_AMEVCNTR0_EL0(11),
+	AMU_AMEVCNTR0_EL0(12),
+	AMU_AMEVCNTR0_EL0(13),
+	AMU_AMEVCNTR0_EL0(14),
+	AMU_AMEVCNTR0_EL0(15),
+	AMU_AMEVTYPE0_EL0(0),
+	AMU_AMEVTYPE0_EL0(1),
+	AMU_AMEVTYPE0_EL0(2),
+	AMU_AMEVTYPE0_EL0(3),
+	AMU_AMEVTYPE0_EL0(4),
+	AMU_AMEVTYPE0_EL0(5),
+	AMU_AMEVTYPE0_EL0(6),
+	AMU_AMEVTYPE0_EL0(7),
+	AMU_AMEVTYPE0_EL0(8),
+	AMU_AMEVTYPE0_EL0(9),
+	AMU_AMEVTYPE0_EL0(10),
+	AMU_AMEVTYPE0_EL0(11),
+	AMU_AMEVTYPE0_EL0(12),
+	AMU_AMEVTYPE0_EL0(13),
+	AMU_AMEVTYPE0_EL0(14),
+	AMU_AMEVTYPE0_EL0(15),
+	AMU_AMEVCNTR1_EL0(0),
+	AMU_AMEVCNTR1_EL0(1),
+	AMU_AMEVCNTR1_EL0(2),
+	AMU_AMEVCNTR1_EL0(3),
+	AMU_AMEVCNTR1_EL0(4),
+	AMU_AMEVCNTR1_EL0(5),
+	AMU_AMEVCNTR1_EL0(6),
+	AMU_AMEVCNTR1_EL0(7),
+	AMU_AMEVCNTR1_EL0(8),
+	AMU_AMEVCNTR1_EL0(9),
+	AMU_AMEVCNTR1_EL0(10),
+	AMU_AMEVCNTR1_EL0(11),
+	AMU_AMEVCNTR1_EL0(12),
+	AMU_AMEVCNTR1_EL0(13),
+	AMU_AMEVCNTR1_EL0(14),
+	AMU_AMEVCNTR1_EL0(15),
+	AMU_AMEVTYPE1_EL0(0),
+	AMU_AMEVTYPE1_EL0(1),
+	AMU_AMEVTYPE1_EL0(2),
+	AMU_AMEVTYPE1_EL0(3),
+	AMU_AMEVTYPE1_EL0(4),
+	AMU_AMEVTYPE1_EL0(5),
+	AMU_AMEVTYPE1_EL0(6),
+	AMU_AMEVTYPE1_EL0(7),
+	AMU_AMEVTYPE1_EL0(8),
+	AMU_AMEVTYPE1_EL0(9),
+	AMU_AMEVTYPE1_EL0(10),
+	AMU_AMEVTYPE1_EL0(11),
+	AMU_AMEVTYPE1_EL0(12),
+	AMU_AMEVTYPE1_EL0(13),
+	AMU_AMEVTYPE1_EL0(14),
+	AMU_AMEVTYPE1_EL0(15),
+
 	{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer },
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index 2b4a3e2d1b89..9cb6b4c8355a 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -12,7 +12,6 @@
 #include <asm/cputype.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 #include <asm/sysreg.h>