Merge tag 'kvmarm-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 6.7

 - Generalized infrastructure for 'writable' ID registers, effectively
   allowing userspace to opt-out of certain vCPU features for its guest

 - Optimization for vSGI injection, opportunistically compressing MPIDR
   to vCPU mapping into a table

 - Improvements to KVM's PMU emulation, allowing userspace to select
   the number of PMCs available to a VM

 - Guest support for memory operation instructions (FEAT_MOPS)

 - Cleanups to handling feature flags in KVM_ARM_VCPU_INIT, squashing
   bugs and getting rid of useless code

 - Changes to the way the SMCCC filter is constructed, avoiding wasted
   memory allocations when not in use

 - Load the stage-2 MMU context at vcpu_load() for VHE systems, reducing
   the overhead of errata mitigations

 - Miscellaneous kernel and selftest fixes

9 files changed, 68 insertions, 33 deletions

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 9cfe6bd1dbe4..f99d8af0b9af 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/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);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
index 37440e1dda93..e91922daa8ca 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
+++ b/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);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 9d703441278b..8d0a5834e883 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -129,8 +129,8 @@ static void prepare_host_vtcr(void)
 	parange = kvm_get_parange(id_aa64mmfr0_el1_sys_val);
 	phys_shift = id_aa64mmfr0_parange_to_phys_shift(parange);
 
-	host_mmu.arch.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val,
-					  id_aa64mmfr1_el1_sys_val, phys_shift);
+	host_mmu.arch.mmu.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val,
+					      id_aa64mmfr1_el1_sys_val, phys_shift);
 }
 
 static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot);
@@ -235,7 +235,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
 	unsigned long nr_pages;
 	int ret;
 
-	nr_pages = kvm_pgtable_stage2_pgd_size(vm->kvm.arch.vtcr) >> PAGE_SHIFT;
+	nr_pages = kvm_pgtable_stage2_pgd_size(mmu->vtcr) >> PAGE_SHIFT;
 	ret = hyp_pool_init(&vm->pool, hyp_virt_to_pfn(pgd), nr_pages, 0);
 	if (ret)
 		return ret;
@@ -295,7 +295,7 @@ int __pkvm_prot_finalize(void)
 		return -EPERM;
 
 	params->vttbr = kvm_get_vttbr(mmu);
-	params->vtcr = host_mmu.arch.vtcr;
+	params->vtcr = mmu->vtcr;
 	params->hcr_el2 |= HCR_VM;
 
 	/*
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 8033ef353a5d..9d23a51d7f75 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -303,7 +303,7 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
 {
 	hyp_vm->host_kvm = host_kvm;
 	hyp_vm->kvm.created_vcpus = nr_vcpus;
-	hyp_vm->kvm.arch.vtcr = host_mmu.arch.vtcr;
+	hyp_vm->kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr;
 }
 
 static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
@@ -483,7 +483,7 @@ int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
 	}
 
 	vm_size = pkvm_get_hyp_vm_size(nr_vcpus);
-	pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.vtcr);
+	pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.mmu.vtcr);
 
 	ret = -ENOMEM;
 
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index c353a06ee7e6..c50f8459e4fc 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/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)
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index f155b8c9e98c..66b30ef88434 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1314,7 +1314,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level,
 				       KVM_PGTABLE_WALK_HANDLE_FAULT |
 				       KVM_PGTABLE_WALK_SHARED);
-	if (!ret)
+	if (!ret || ret == -EAGAIN)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level);
 	return ret;
 }
@@ -1511,7 +1511,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			      kvm_pgtable_force_pte_cb_t force_pte_cb)
 {
 	size_t pgd_sz;
-	u64 vtcr = mmu->arch->vtcr;
+	u64 vtcr = mmu->vtcr;
 	u32 ia_bits = VTCR_EL2_IPA(vtcr);
 	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
 	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 448b17080d36..1581df6aec87 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -137,12 +137,12 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 NOKPROBE_SYMBOL(__deactivate_traps);
 
 /*
- * Disable IRQs in {activate,deactivate}_traps_vhe_{load,put}() to
+ * Disable IRQs in __vcpu_{load,put}_{activate,deactivate}_traps() to
  * prevent a race condition between context switching of PMUSERENR_EL0
  * in __{activate,deactivate}_traps_common() and IPIs that attempts to
  * update PMUSERENR_EL0. See also kvm_set_pmuserenr().
  */
-void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
+static void __vcpu_load_activate_traps(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
 
@@ -151,7 +151,7 @@ void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
 	local_irq_restore(flags);
 }
 
-void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
+static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
 
@@ -160,6 +160,19 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
 	local_irq_restore(flags);
 }
 
+void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu)
+{
+	__vcpu_load_switch_sysregs(vcpu);
+	__vcpu_load_activate_traps(vcpu);
+	__load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
+}
+
+void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu)
+{
+	__vcpu_put_deactivate_traps(vcpu);
+	__vcpu_put_switch_sysregs(vcpu);
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
@@ -170,6 +183,7 @@ 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)
@@ -214,17 +228,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	sysreg_save_host_state_vhe(host_ctxt);
 
 	/*
-	 * ARM erratum 1165522 requires us to configure both stage 1 and
-	 * stage 2 translation for the guest context before we clear
-	 * HCR_EL2.TGE.
-	 *
-	 * We have already configured the guest's stage 1 translation in
-	 * kvm_vcpu_load_sysregs_vhe above.  We must now call
-	 * __load_stage2 before __activate_traps, because
-	 * __load_stage2 configures stage 2 translation, and
-	 * __activate_traps clear HCR_EL2.TGE (among other things).
+	 * Note that ARM erratum 1165522 requires us to configure both stage 1
+	 * and stage 2 translation for the guest context before we clear
+	 * HCR_EL2.TGE. The stage 1 and stage 2 guest context has already been
+	 * loaded on the CPU in kvm_vcpu_load_vhe().
 	 */
-	__load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
 	__activate_traps(vcpu);
 
 	__kvm_adjust_pc(vcpu);
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index b35a178e7e0d..8e1e0d5033b6 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -52,7 +52,7 @@ void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
 NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
 
 /**
- * kvm_vcpu_load_sysregs_vhe - Load guest system registers to the physical CPU
+ * __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU
  *
  * @vcpu: The VCPU pointer
  *
@@ -62,7 +62,7 @@ NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
  * and loading system register state early avoids having to load them on
  * every entry to the VM.
  */
-void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
+void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
@@ -92,12 +92,10 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
 	__sysreg_restore_el1_state(guest_ctxt);
 
 	vcpu_set_flag(vcpu, SYSREGS_ON_CPU);
-
-	activate_traps_vhe_load(vcpu);
 }
 
 /**
- * kvm_vcpu_put_sysregs_vhe - Restore host system registers to the physical CPU
+ * __vcpu_put_switch_syregs - Restore host system registers to the physical CPU
  *
  * @vcpu: The VCPU pointer
  *
@@ -107,13 +105,12 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
  * and deferring saving system register state until we're no longer running the
  * VCPU avoids having to save them on every exit from the VM.
  */
-void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu)
+void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
 
 	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
-	deactivate_traps_vhe_put(vcpu);
 
 	__sysreg_save_el1_state(guest_ctxt);
 	__sysreg_save_user_state(guest_ctxt);
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 46bd43f61d76..b636b4111dbf 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -11,18 +11,25 @@
 #include <asm/tlbflush.h>
 
 struct tlb_inv_context {
-	unsigned long	flags;
-	u64		tcr;
-	u64		sctlr;
+	struct kvm_s2_mmu	*mmu;
+	unsigned long		flags;
+	u64			tcr;
+	u64			sctlr;
 };
 
 static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 				  struct tlb_inv_context *cxt)
 {
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 	u64 val;
 
 	local_irq_save(cxt->flags);
 
+	if (vcpu && mmu != vcpu->arch.hw_mmu)
+		cxt->mmu = vcpu->arch.hw_mmu;
+	else
+		cxt->mmu = NULL;
+
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		/*
 		 * For CPUs that are affected by ARM errata 1165522 or 1530923,
@@ -66,10 +73,13 @@ static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
 	 * We're done with the TLB operation, let's restore the host's
 	 * view of HCR_EL2.
 	 */
-	write_sysreg(0, vttbr_el2);
 	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
 	isb();
 
+	/* ... and the stage-2 MMU context that we switched away from */
+	if (cxt->mmu)
+		__load_stage2(cxt->mmu, cxt->mmu->arch);
+
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		/* Restore the registers to what they were */
 		write_sysreg_el1(cxt->tcr, SYS_TCR);