Merge tag 'kvmarm-6.9' of https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 6.9

 - Infrastructure for building KVM's trap configuration based on the
   architectural features (or lack thereof) advertised in the VM's ID
   registers

 - Support for mapping vfio-pci BARs as Normal-NC (vaguely similar to
   x86's WC) at stage-2, improving the performance of interacting with
   assigned devices that can tolerate it

 - Conversion of KVM's representation of LPIs to an xarray, utilized to
   address serialization some of the serialization on the LPI injection
   path

 - Support for _architectural_ VHE-only systems, advertised through the
   absence of FEAT_E2H0 in the CPU's ID register

 - Miscellaneous cleanups, fixes, and spelling corrections to KVM and
   selftests

Author: bonzini

arch/arm64/include/asm/cpu.h

@@ -56,6 +56,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64mmfr1;
 	u64		reg_id_aa64mmfr2;
 	u64		reg_id_aa64mmfr3;
+	u64		reg_id_aa64mmfr4;
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
 	u64		reg_id_aa64zfr0;

arch/arm64/include/asm/cpufeature.h

@@ -363,6 +363,7 @@ struct arm64_cpu_capabilities {
 			u8 field_pos;
 			u8 field_width;
 			u8 min_field_value;
+			u8 max_field_value;
 			u8 hwcap_type;
 			bool sign;
 			unsigned long hwcap;

arch/arm64/include/asm/kvm_arm.h

@@ -102,9 +102,7 @@
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
-#define HCRX_GUEST_FLAGS \
-	(HCRX_EL2_SMPME | HCRX_EL2_TCR2En | \
-	 (cpus_have_final_cap(ARM64_HAS_MOPS) ? (HCRX_EL2_MSCEn | HCRX_EL2_MCE2) : 0))
+#define HCRX_GUEST_FLAGS (HCRX_EL2_SMPME | HCRX_EL2_TCR2En)
 #define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En)
 
 /* TCR_EL2 Registers bits */

arch/arm64/include/asm/kvm_emulate.h

@@ -209,7 +209,8 @@ static inline bool vcpu_is_el2(const struct kvm_vcpu *vcpu)
 
 static inline bool __vcpu_el2_e2h_is_set(const struct kvm_cpu_context *ctxt)
 {
-	return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H;
+	return (!cpus_have_final_cap(ARM64_HAS_HCR_NV1) ||
+		(ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H));
 }
 
 static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu)

arch/arm64/include/asm/kvm_host.h

@@ -238,9 +238,32 @@ static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr)
 	return index;
 }
 
+struct kvm_sysreg_masks;
+
+enum fgt_group_id {
+	__NO_FGT_GROUP__,
+	HFGxTR_GROUP,
+	HDFGRTR_GROUP,
+	HDFGWTR_GROUP = HDFGRTR_GROUP,
+	HFGITR_GROUP,
+	HAFGRTR_GROUP,
+
+	/* Must be last */
+	__NR_FGT_GROUP_IDS__
+};
+
 struct kvm_arch {
 	struct kvm_s2_mmu mmu;
 
+	/*
+	 * Fine-Grained UNDEF, mimicking the FGT layout defined by the
+	 * architecture. We track them globally, as we present the
+	 * same feature-set to all vcpus.
+	 *
+	 * Index 0 is currently spare.
+	 */
+	u64 fgu[__NR_FGT_GROUP_IDS__];
+
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 
@@ -274,6 +297,8 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE		6
 	/* Initial ID reg values loaded */
 #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		7
+	/* Fine-Grained UNDEF initialised */
+#define KVM_ARCH_FLAG_FGU_INITIALIZED			8
 	unsigned long flags;
 
 	/* VM-wide vCPU feature set */
@@ -294,6 +319,9 @@ struct kvm_arch {
 	/* PMCR_EL0.N value for the guest */
 	u8 pmcr_n;
 
+	/* Iterator for idreg debugfs */
+	u8	idreg_debugfs_iter;
+
 	/* Hypercall features firmware registers' descriptor */
 	struct kvm_smccc_features smccc_feat;
 	struct maple_tree smccc_filter;
@@ -312,6 +340,9 @@ struct kvm_arch {
 #define KVM_ARM_ID_REG_NUM	(IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
 	u64 id_regs[KVM_ARM_ID_REG_NUM];
 
+	/* Masks for VNCR-baked sysregs */
+	struct kvm_sysreg_masks	*sysreg_masks;
+
 	/*
 	 * For an untrusted host VM, 'pkvm.handle' is used to lookup
 	 * the associated pKVM instance in the hypervisor.
@@ -474,6 +505,13 @@ enum vcpu_sysreg {
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 
+struct kvm_sysreg_masks {
+	struct {
+		u64	res0;
+		u64	res1;
+	} mask[NR_SYS_REGS - __VNCR_START__];
+};
+
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
@@ -549,6 +587,7 @@ struct kvm_vcpu_arch {
 
 	/* Values of trap registers for the guest. */
 	u64 hcr_el2;
+	u64 hcrx_el2;
 	u64 mdcr_el2;
 	u64 cptr_el2;
 
@@ -868,7 +907,15 @@ 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))
 
-#define __vcpu_sys_reg(v,r)	(ctxt_sys_reg(&(v)->arch.ctxt, (r)))
+u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
+#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));	\
+		__r;							\
+	}))
 
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
@@ -1055,14 +1102,20 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu);
 int kvm_handle_sys_reg(struct kvm_vcpu *vcpu);
 int kvm_handle_cp10_id(struct kvm_vcpu *vcpu);
 
+void kvm_sys_regs_create_debugfs(struct kvm *kvm);
 void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
 
 int __init kvm_sys_reg_table_init(void);
+struct sys_reg_desc;
+int __init populate_sysreg_config(const struct sys_reg_desc *sr,
+				  unsigned int idx);
 int __init populate_nv_trap_config(void);
 
 bool lock_all_vcpus(struct kvm *kvm);
 void unlock_all_vcpus(struct kvm *kvm);
 
+void kvm_init_sysreg(struct kvm_vcpu *);
+
 /* MMIO helpers */
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
 unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
@@ -1233,4 +1286,48 @@ static inline void kvm_hyp_reserve(void) { }
 void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu);
 bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu);
 
+#define __expand_field_sign_unsigned(id, fld, val)			\
+	((u64)SYS_FIELD_VALUE(id, fld, val))
+
+#define __expand_field_sign_signed(id, fld, val)			\
+	({								\
+		u64 __val = SYS_FIELD_VALUE(id, fld, val);		\
+		sign_extend64(__val, id##_##fld##_WIDTH - 1);		\
+	})
+
+#define expand_field_sign(id, fld, val)					\
+	(id##_##fld##_SIGNED ?						\
+	 __expand_field_sign_signed(id, fld, val) :			\
+	 __expand_field_sign_unsigned(id, fld, val))
+
+#define get_idreg_field_unsigned(kvm, id, fld)				\
+	({								\
+		u64 __val = IDREG((kvm), SYS_##id);			\
+		FIELD_GET(id##_##fld##_MASK, __val);			\
+	})
+
+#define get_idreg_field_signed(kvm, id, fld)				\
+	({								\
+		u64 __val = get_idreg_field_unsigned(kvm, id, fld);	\
+		sign_extend64(__val, id##_##fld##_WIDTH - 1);		\
+	})
+
+#define get_idreg_field_enum(kvm, id, fld)				\
+	get_idreg_field_unsigned(kvm, id, fld)
+
+#define get_idreg_field(kvm, id, fld)					\
+	(id##_##fld##_SIGNED ?						\
+	 get_idreg_field_signed(kvm, id, fld) :				\
+	 get_idreg_field_unsigned(kvm, id, fld))
+
+#define kvm_has_feat(kvm, id, fld, limit)				\
+	(get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, limit))
+
+#define kvm_has_feat_enum(kvm, id, fld, val)				\
+	(get_idreg_field_unsigned((kvm), id, fld) == __expand_field_sign_unsigned(id, fld, val))
+
+#define kvm_has_feat_range(kvm, id, fld, min, max)			\
+	(get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \
+	 get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max))
+
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/include/asm/kvm_hyp.h

@@ -70,7 +70,7 @@ DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 /*
  * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the
  * static inline can allow the compiler to out-of-line this. KVM always wants
- * the macro version as its always inlined.
+ * the macro version as it's always inlined.
  */
 #define __kvm_swab32(x)	___constant_swab32(x)
 

arch/arm64/include/asm/kvm_mmu.h

@@ -53,27 +53,6 @@
 
 #include <asm/alternative.h>
 
-/*
- * Convert a kernel VA into a HYP VA.
- * reg: VA to be converted.
- *
- * The actual code generation takes place in kvm_update_va_mask, and
- * the instructions below are only there to reserve the space and
- * perform the register allocation (kvm_update_va_mask uses the
- * specific registers encoded in the instructions).
- */
-.macro kern_hyp_va	reg
-#ifndef __KVM_VHE_HYPERVISOR__
-alternative_cb ARM64_ALWAYS_SYSTEM, kvm_update_va_mask
-	and     \reg, \reg, #1		/* mask with va_mask */
-	ror	\reg, \reg, #1		/* rotate to the first tag bit */
-	add	\reg, \reg, #0		/* insert the low 12 bits of the tag */
-	add	\reg, \reg, #0, lsl 12	/* insert the top 12 bits of the tag */
-	ror	\reg, \reg, #63		/* rotate back */
-alternative_cb_end
-#endif
-.endm
-
 /*
  * Convert a hypervisor VA to a PA
  * reg: hypervisor address to be converted in place
@@ -127,14 +106,29 @@ void kvm_apply_hyp_relocations(void);
 
 #define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
 
+/*
+ * Convert a kernel VA into a HYP VA.
+ *
+ * Can be called from hyp or non-hyp context.
+ *
+ * The actual code generation takes place in kvm_update_va_mask(), and
+ * the instructions below are only there to reserve the space and
+ * perform the register allocation (kvm_update_va_mask() uses the
+ * specific registers encoded in the instructions).
+ */
 static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 {
+/*
+ * This #ifndef is an optimisation for when this is called from VHE hyp
+ * context.  When called from a VHE non-hyp context, kvm_update_va_mask() will
+ * replace the instructions with `nop`s.
+ */
 #ifndef __KVM_VHE_HYPERVISOR__
-	asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"
-				    "ror %0, %0, #1\n"
-				    "add %0, %0, #0\n"
-				    "add %0, %0, #0, lsl 12\n"
-				    "ror %0, %0, #63\n",
+	asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"         /* mask with va_mask */
+				    "ror %0, %0, #1\n"         /* rotate to the first tag bit */
+				    "add %0, %0, #0\n"         /* insert the low 12 bits of the tag */
+				    "add %0, %0, #0, lsl 12\n" /* insert the top 12 bits of the tag */
+				    "ror %0, %0, #63\n",       /* rotate back */
 				    ARM64_ALWAYS_SYSTEM,
 				    kvm_update_va_mask)
 		     : "+r" (v));

arch/arm64/include/asm/kvm_nested.h

@@ -60,7 +60,6 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
 	return ttbr0 & ~GENMASK_ULL(63, 48);
 }
 
-extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
 
 int kvm_init_nv_sysregs(struct kvm *kvm);
 

arch/arm64/include/asm/kvm_pgtable.h

@@ -197,6 +197,7 @@ enum kvm_pgtable_stage2_flags {
  * @KVM_PGTABLE_PROT_W:		Write permission.
  * @KVM_PGTABLE_PROT_R:		Read permission.
  * @KVM_PGTABLE_PROT_DEVICE:	Device attributes.
+ * @KVM_PGTABLE_PROT_NORMAL_NC:	Normal noncacheable attributes.
  * @KVM_PGTABLE_PROT_SW0:	Software bit 0.
  * @KVM_PGTABLE_PROT_SW1:	Software bit 1.
  * @KVM_PGTABLE_PROT_SW2:	Software bit 2.
@@ -208,6 +209,7 @@ enum kvm_pgtable_prot {
 	KVM_PGTABLE_PROT_R			= BIT(2),
 
 	KVM_PGTABLE_PROT_DEVICE			= BIT(3),
+	KVM_PGTABLE_PROT_NORMAL_NC		= BIT(4),
 
 	KVM_PGTABLE_PROT_SW0			= BIT(55),
 	KVM_PGTABLE_PROT_SW1			= BIT(56),

arch/arm64/include/asm/memory.h

@@ -173,13 +173,15 @@
  * Memory types for Stage-2 translation
  */
 #define MT_S2_NORMAL		0xf
+#define MT_S2_NORMAL_NC		0x5
 #define MT_S2_DEVICE_nGnRE	0x1
 
 /*
  * Memory types for Stage-2 translation when ID_AA64MMFR2_EL1.FWB is 0001
  * Stage-2 enforces Normal-WB and Device-nGnRE
  */
 #define MT_S2_FWB_NORMAL	6
+#define MT_S2_FWB_NORMAL_NC	5
 #define MT_S2_FWB_DEVICE_nGnRE	1
 
 #ifdef CONFIG_ARM64_4K_PAGES