KVM: arm64: Get rid of __kvm_get_mdcr_el2() and related warts

KVM caches MDCR_EL2 on a per-CPU basis in order to preserve the
configuration of MDCR_EL2.HPMN while running a guest. This is a bit
gross, since we're relying on some baked configuration rather than the
hardware definition of implemented counters.

Discover the number of implemented counters by reading PMCR_EL0.N
instead. This works because:

 - In VHE the kernel runs at EL2, and N always returns the number of
   counters implemented in hardware

 - In {n,h}VHE, the EL2 setup code programs MDCR_EL2.HPMN with the EL2
   view of PMCR_EL0.N for the host

Lastly, avoid traps under nested virtualization by saving PMCR_EL0.N in
host data.

Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20241219224116.3941496-3-oliver.upton@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>

Author: oupton

arch/arm64/include/asm/kvm_asm.h

@@ -53,8 +53,7 @@
 enum __kvm_host_smccc_func {
 	/* Hypercalls available only prior to pKVM finalisation */
 	/* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */
-	__KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
-	__KVM_HOST_SMCCC_FUNC___pkvm_init,
+	__KVM_HOST_SMCCC_FUNC___pkvm_init = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
 	__KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping,
 	__KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector,
 	__KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs,
@@ -247,8 +246,6 @@ extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
 extern u64 __vgic_v3_get_gic_config(void);
 extern void __vgic_v3_init_lrs(void);
 
-extern u64 __kvm_get_mdcr_el2(void);
-
 #define __KVM_EXTABLE(from, to)						\
 	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
 	"	.align		3\n"					\

arch/arm64/include/asm/kvm_host.h

@@ -642,7 +642,7 @@ struct kvm_host_data {
 	 * host_debug_state contains the host registers which are
 	 * saved and restored during world switches.
 	 */
-	 struct {
+	struct {
 		/* {Break,watch}point registers */
 		struct kvm_guest_debug_arch regs;
 		/* Statistical profiling extension */
@@ -652,6 +652,9 @@ struct kvm_host_data {
 		/* Values of trap registers for the host before guest entry. */
 		u64 mdcr_el2;
 	} host_debug_state;
+
+	/* Number of programmable event counters (PMCR_EL0.N) for this CPU */
+	unsigned int nr_event_counters;
 };
 
 struct kvm_host_psci_config {
@@ -1332,7 +1335,7 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 
-void kvm_arm_init_debug(void);
+void kvm_init_host_debug_data(void);
 void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);

arch/arm64/kvm/arm.c

@@ -2109,6 +2109,7 @@ static void cpu_set_hyp_vector(void)
 static void cpu_hyp_init_context(void)
 {
 	kvm_init_host_cpu_context(host_data_ptr(host_ctxt));
+	kvm_init_host_debug_data();
 
 	if (!is_kernel_in_hyp_mode())
 		cpu_init_hyp_mode();
@@ -2117,7 +2118,6 @@ static void cpu_hyp_init_context(void)
 static void cpu_hyp_init_features(void)
 {
 	cpu_set_hyp_vector();
-	kvm_arm_init_debug();
 
 	if (is_kernel_in_hyp_mode())
 		kvm_timer_init_vhe();

arch/arm64/kvm/debug.c

@@ -16,8 +16,6 @@
 
 #include "trace.h"
 
-static DEFINE_PER_CPU(u64, mdcr_el2);
-
 /*
  * save/restore_guest_debug_regs
  *
@@ -60,21 +58,6 @@ static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
 		*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
 }
 
-/**
- * kvm_arm_init_debug - grab what we need for debug
- *
- * Currently the sole task of this function is to retrieve the initial
- * value of mdcr_el2 so we can preserve MDCR_EL2.HPMN which has
- * presumably been set-up by some knowledgeable bootcode.
- *
- * It is called once per-cpu during CPU hyp initialisation.
- */
-
-void kvm_arm_init_debug(void)
-{
-	__this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2));
-}
-
 /**
  * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value
  *
@@ -94,7 +77,8 @@ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
 	 * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK
 	 * to disable guest access to the profiling and trace buffers
 	 */
-	vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK;
+	vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN,
+					 *host_data_ptr(nr_event_counters));
 	vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |
 				MDCR_EL2_TPMS |
 				MDCR_EL2_TTRF |
@@ -338,3 +322,12 @@ void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu)
 	vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_SPE);
 	vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRBE);
 }
+
+void kvm_init_host_debug_data(void)
+{
+	u64 dfr0 = read_sysreg(id_aa64dfr0_el1);
+
+	if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0)
+		*host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N,
+							      read_sysreg(pmcr_el0));
+}

arch/arm64/kvm/hyp/nvhe/debug-sr.c

@@ -106,8 +106,3 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
 	__debug_switch_to_host_common(vcpu);
 }
-
-u64 __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -264,11 +264,6 @@ static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt)
 	__vgic_v3_init_lrs();
 }
 
-static void handle___kvm_get_mdcr_el2(struct kvm_cpu_context *host_ctxt)
-{
-	cpu_reg(host_ctxt, 1) = __kvm_get_mdcr_el2();
-}
-
 static void handle___vgic_v3_save_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
@@ -384,7 +379,6 @@ typedef void (*hcall_t)(struct kvm_cpu_context *);
 
 static const hcall_t host_hcall[] = {
 	/* ___kvm_hyp_init */
-	HANDLE_FUNC(__kvm_get_mdcr_el2),
 	HANDLE_FUNC(__pkvm_init),
 	HANDLE_FUNC(__pkvm_create_private_mapping),
 	HANDLE_FUNC(__pkvm_cpu_set_vector),

arch/arm64/kvm/hyp/vhe/debug-sr.c

@@ -19,8 +19,3 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
 	__debug_switch_to_host_common(vcpu);
 }
-
-u64 __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}