Merge tag 'kvmarm-6.13' of https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 changes for 6.13, part #1

 - Support for stage-1 permission indirection (FEAT_S1PIE) and
   permission overlays (FEAT_S1POE), including nested virt + the
   emulated page table walker

 - Introduce PSCI SYSTEM_OFF2 support to KVM + client driver. This call
   was introduced in PSCIv1.3 as a mechanism to request hibernation,
   similar to the S4 state in ACPI

 - Explicitly trap + hide FEAT_MPAM (QoS controls) from KVM guests. As
   part of it, introduce trivial initialization of the host's MPAM
   context so KVM can use the corresponding traps

 - PMU support under nested virtualization, honoring the guest
   hypervisor's trap configuration and event filtering when running a
   nested guest

 - Fixes to vgic ITS serialization where stale device/interrupt table
   entries are not zeroed when the mapping is invalidated by the VM

 - Avoid emulated MMIO completion if userspace has requested synchronous
   external abort injection

 - Various fixes and cleanups affecting pKVM, vCPU initialization, and
   selftests

Author: bonzini

Documentation/arch/arm64/cpu-feature-registers.rst

@@ -152,6 +152,8 @@ infrastructure:
      +------------------------------+---------+---------+
      | DIT                          | [51-48] |    y    |
      +------------------------------+---------+---------+
+     | MPAM                         | [43-40] |    n    |
+     +------------------------------+---------+---------+
      | SVE                          | [35-32] |    y    |
      +------------------------------+---------+---------+
      | GIC                          | [27-24] |    n    |

Documentation/virt/kvm/api.rst

@@ -6857,6 +6857,10 @@ the first `ndata` items (possibly zero) of the data array are valid.
    the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI
    specification.
 
+ - for arm64, data[0] is set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2
+   if the guest issued a SYSTEM_OFF2 call according to v1.3 of the PSCI
+   specification.
+
  - for RISC-V, data[0] is set to the value of the second argument of the
    ``sbi_system_reset`` call.
 
@@ -6890,6 +6894,12 @@ either:
  - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2
    "Caller responsibilities" for possible return values.
 
+Hibernation using the PSCI SYSTEM_OFF2 call is enabled when PSCI v1.3
+is enabled. If a guest invokes the PSCI SYSTEM_OFF2 function, KVM will
+exit to userspace with the KVM_SYSTEM_EVENT_SHUTDOWN event type and with
+data[0] set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2. The only
+supported hibernate type for the SYSTEM_OFF2 function is HIBERNATE_OFF.
+
 ::
 
 		/* KVM_EXIT_IOAPIC_EOI */

arch/arm64/include/asm/cpu.h

@@ -46,6 +46,7 @@ struct cpuinfo_arm64 {
 	u64		reg_revidr;
 	u64		reg_gmid;
 	u64		reg_smidr;
+	u64		reg_mpamidr;
 
 	u64		reg_id_aa64dfr0;
 	u64		reg_id_aa64dfr1;

arch/arm64/include/asm/cpucaps.h

@@ -60,6 +60,11 @@ cpucap_is_possible(const unsigned int cap)
 		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI);
 	case ARM64_WORKAROUND_SPECULATIVE_SSBS:
 		return IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386);
+	case ARM64_MPAM:
+		/*
+		 * KVM MPAM support doesn't rely on the host kernel supporting MPAM.
+		*/
+		return true;
 	}
 
 	return true;

arch/arm64/include/asm/cpufeature.h

@@ -612,6 +612,13 @@ static inline bool id_aa64pfr1_sme(u64 pfr1)
 	return val > 0;
 }
 
+static inline bool id_aa64pfr0_mpam(u64 pfr0)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_MPAM_SHIFT);
+
+	return val > 0;
+}
+
 static inline bool id_aa64pfr1_mte(u64 pfr1)
 {
 	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT);
@@ -838,6 +845,16 @@ static inline bool system_supports_poe(void)
 		alternative_has_cap_unlikely(ARM64_HAS_S1POE);
 }
 
+static __always_inline bool system_supports_mpam(void)
+{
+	return alternative_has_cap_unlikely(ARM64_MPAM);
+}
+
+static __always_inline bool system_supports_mpam_hcr(void)
+{
+	return alternative_has_cap_unlikely(ARM64_MPAM_HCR);
+}
+
 int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
 

arch/arm64/include/asm/el2_setup.h

@@ -220,6 +220,19 @@
 	msr	spsr_el2, x0
 .endm
 
+.macro __init_el2_mpam
+	/* Memory Partitioning And Monitoring: disable EL2 traps */
+	mrs	x1, id_aa64pfr0_el1
+	ubfx	x0, x1, #ID_AA64PFR0_EL1_MPAM_SHIFT, #4
+	cbz	x0, .Lskip_mpam_\@		// skip if no MPAM
+	msr_s	SYS_MPAM2_EL2, xzr		// use the default partition
+						// and disable lower traps
+	mrs_s	x0, SYS_MPAMIDR_EL1
+	tbz	x0, #MPAMIDR_EL1_HAS_HCR_SHIFT, .Lskip_mpam_\@	// skip if no MPAMHCR reg
+	msr_s	SYS_MPAMHCR_EL2, xzr		// clear TRAP_MPAMIDR_EL1 -> EL2
+.Lskip_mpam_\@:
+.endm
+
 /**
  * Initialize EL2 registers to sane values. This should be called early on all
  * cores that were booted in EL2. Note that everything gets initialised as
@@ -237,6 +250,7 @@
 	__init_el2_stage2
 	__init_el2_gicv3
 	__init_el2_hstr
+	__init_el2_mpam
 	__init_el2_nvhe_idregs
 	__init_el2_cptr
 	__init_el2_fgt

arch/arm64/include/asm/kvm_arm.h

@@ -103,6 +103,7 @@
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 #define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM)
+#define MPAMHCR_HOST_FLAGS	0
 
 /* TCR_EL2 Registers bits */
 #define TCR_EL2_DS		(1UL << 32)
@@ -311,35 +312,6 @@
 				 GENMASK(19, 18) |	\
 				 GENMASK(15, 0))
 
-/* Hyp Debug Configuration Register bits */
-#define MDCR_EL2_E2TB_MASK	(UL(0x3))
-#define MDCR_EL2_E2TB_SHIFT	(UL(24))
-#define MDCR_EL2_HPMFZS		(UL(1) << 36)
-#define MDCR_EL2_HPMFZO		(UL(1) << 29)
-#define MDCR_EL2_MTPME		(UL(1) << 28)
-#define MDCR_EL2_TDCC		(UL(1) << 27)
-#define MDCR_EL2_HLP		(UL(1) << 26)
-#define MDCR_EL2_HCCD		(UL(1) << 23)
-#define MDCR_EL2_TTRF		(UL(1) << 19)
-#define MDCR_EL2_HPMD		(UL(1) << 17)
-#define MDCR_EL2_TPMS		(UL(1) << 14)
-#define MDCR_EL2_E2PB_MASK	(UL(0x3))
-#define MDCR_EL2_E2PB_SHIFT	(UL(12))
-#define MDCR_EL2_TDRA		(UL(1) << 11)
-#define MDCR_EL2_TDOSA		(UL(1) << 10)
-#define MDCR_EL2_TDA		(UL(1) << 9)
-#define MDCR_EL2_TDE		(UL(1) << 8)
-#define MDCR_EL2_HPME		(UL(1) << 7)
-#define MDCR_EL2_TPM		(UL(1) << 6)
-#define MDCR_EL2_TPMCR		(UL(1) << 5)
-#define MDCR_EL2_HPMN_MASK	(UL(0x1F))
-#define MDCR_EL2_RES0		(GENMASK(63, 37) |	\
-				 GENMASK(35, 30) |	\
-				 GENMASK(25, 24) |	\
-				 GENMASK(22, 20) |	\
-				 BIT(18) |		\
-				 GENMASK(16, 15))
-
 /*
  * FGT register definitions
  *

arch/arm64/include/asm/kvm_asm.h

@@ -76,7 +76,6 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_save_vmcr_aprs,
 	__KVM_HOST_SMCCC_FUNC___vgic_v3_restore_vmcr_aprs,
-	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
 	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,

arch/arm64/include/asm/kvm_emulate.h

@@ -225,6 +225,11 @@ static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
 	return vcpu_has_nv(vcpu) && __is_hyp_ctxt(&vcpu->arch.ctxt);
 }
 
+static inline bool vcpu_is_host_el0(const struct kvm_vcpu *vcpu)
+{
+	return is_hyp_ctxt(vcpu) && !vcpu_is_el2(vcpu);
+}
+
 /*
  * The layout of SPSR for an AArch32 state is different when observed from an
  * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
@@ -693,4 +698,8 @@ static inline bool guest_hyp_sve_traps_enabled(const struct kvm_vcpu *vcpu)
 	return __guest_hyp_cptr_xen_trap_enabled(vcpu, ZEN);
 }
 
+static inline void kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
+{
+	vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH);
+}
 #endif /* __ARM64_KVM_EMULATE_H__ */

arch/arm64/include/asm/kvm_host.h

@@ -74,8 +74,6 @@ enum kvm_mode kvm_get_mode(void);
 static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; };
 #endif
 
-DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
-
 extern unsigned int __ro_after_init kvm_sve_max_vl;
 extern unsigned int __ro_after_init kvm_host_sve_max_vl;
 int __init kvm_arm_init_sve(void);
@@ -374,7 +372,7 @@ struct kvm_arch {
 
 	u64 ctr_el0;
 
-	/* Masks for VNCR-baked sysregs */
+	/* Masks for VNCR-backed and general EL2 sysregs */
 	struct kvm_sysreg_masks	*sysreg_masks;
 
 	/*
@@ -408,6 +406,9 @@ struct kvm_vcpu_fault_info {
 	r = __VNCR_START__ + ((VNCR_ ## r) / 8),	\
 	__after_##r = __MAX__(__before_##r - 1, r)
 
+#define MARKER(m)				\
+	m, __after_##m = m - 1
+
 enum vcpu_sysreg {
 	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
 	MPIDR_EL1,	/* MultiProcessor Affinity Register */
@@ -468,13 +469,15 @@ enum vcpu_sysreg {
 	/* EL2 registers */
 	SCTLR_EL2,	/* System Control Register (EL2) */
 	ACTLR_EL2,	/* Auxiliary Control Register (EL2) */
-	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
 	CPTR_EL2,	/* Architectural Feature Trap Register (EL2) */
 	HACR_EL2,	/* Hypervisor Auxiliary Control Register */
 	ZCR_EL2,	/* SVE Control Register (EL2) */
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
+	PIRE0_EL2,	/* Permission Indirection Register 0 (EL2) */
+	PIR_EL2,	/* Permission Indirection Register 1 (EL2) */
+	POR_EL2,	/* Permission Overlay Register 2 (EL2) */
 	SPSR_EL2,	/* EL2 saved program status register */
 	ELR_EL2,	/* EL2 exception link register */
 	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
@@ -494,7 +497,13 @@ enum vcpu_sysreg {
 	CNTHV_CTL_EL2,
 	CNTHV_CVAL_EL2,
 
-	__VNCR_START__,	/* Any VNCR-capable reg goes after this point */
+	/* Anything from this can be RES0/RES1 sanitised */
+	MARKER(__SANITISED_REG_START__),
+	TCR2_EL2,	/* Extended Translation Control Register (EL2) */
+	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
+
+	/* Any VNCR-capable reg goes after this point */
+	MARKER(__VNCR_START__),
 
 	VNCR(SCTLR_EL1),/* System Control Register */
 	VNCR(ACTLR_EL1),/* Auxiliary Control Register */
@@ -554,7 +563,7 @@ struct kvm_sysreg_masks {
 	struct {
 		u64	res0;
 		u64	res1;
-	} mask[NR_SYS_REGS - __VNCR_START__];
+	} mask[NR_SYS_REGS - __SANITISED_REG_START__];
 };
 
 struct kvm_cpu_context {
@@ -1002,13 +1011,13 @@ static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
 
 #define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
 
-u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
+u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
 #define __vcpu_sys_reg(v,r)						\
 	(*({								\
 		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
 		u64 *__r = __ctxt_sys_reg(ctxt, (r));			\
-		if (vcpu_has_nv((v)) && (r) >= __VNCR_START__)		\
-			*__r = kvm_vcpu_sanitise_vncr_reg((v), (r));	\
+		if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__)	\
+			*__r = kvm_vcpu_apply_reg_masks((v), (r), *__r);\
 		__r;							\
 	}))
 
@@ -1037,6 +1046,10 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
 	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
 	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
+	case TCR2_EL1:		*val = read_sysreg_s(SYS_TCR2_EL12);	break;
+	case PIR_EL1:		*val = read_sysreg_s(SYS_PIR_EL12);	break;
+	case PIRE0_EL1:		*val = read_sysreg_s(SYS_PIRE0_EL12);	break;
+	case POR_EL1:		*val = read_sysreg_s(SYS_POR_EL12);	break;
 	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
 	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
 	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
@@ -1083,6 +1096,10 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
 	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
 	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
+	case TCR2_EL1:		write_sysreg_s(val, SYS_TCR2_EL12);	break;
+	case PIR_EL1:		write_sysreg_s(val, SYS_PIR_EL12);	break;
+	case PIRE0_EL1:		write_sysreg_s(val, SYS_PIRE0_EL12);	break;
+	case POR_EL1:		write_sysreg_s(val, SYS_POR_EL12);	break;
 	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
 	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
 	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
@@ -1503,4 +1520,13 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 	(system_supports_fpmr() &&			\
 	 kvm_has_feat((k), ID_AA64PFR2_EL1, FPMR, IMP))
 
+#define kvm_has_tcr2(k)				\
+	(kvm_has_feat((k), ID_AA64MMFR3_EL1, TCRX, IMP))
+
+#define kvm_has_s1pie(k)				\
+	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP))
+
+#define kvm_has_s1poe(k)				\
+	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
+
 #endif /* __ARM64_KVM_HOST_H__ */