Merge branch kvm-arm64/fgt-masks into kvmarm-master/next

* kvm-arm64/fgt-masks: (43 commits)
  : .
  : Large rework of the way KVM deals with trap bits in conjunction with
  : the CPU feature registers. It now draws a direct link between which
  : the feature set, the system registers that need to UNDEF to match
  : the configuration and bits that need to behave as RES0 or RES1 in
  : the trap registers that are visible to the guest.
  :
  : Best of all, these definitions are mostly automatically generated
  : from the JSON description published by ARM under a permissive
  : license.
  : .
  KVM: arm64: Handle TSB CSYNC traps
  KVM: arm64: Add FGT descriptors for FEAT_FGT2
  KVM: arm64: Allow sysreg ranges for FGT descriptors
  KVM: arm64: Add context-switch for FEAT_FGT2 registers
  KVM: arm64: Add trap routing for FEAT_FGT2 registers
  KVM: arm64: Add sanitisation for FEAT_FGT2 registers
  KVM: arm64: Add FEAT_FGT2 registers to the VNCR page
  KVM: arm64: Use HCR_EL2 feature map to drive fixed-value bits
  KVM: arm64: Use HCRX_EL2 feature map to drive fixed-value bits
  KVM: arm64: Allow kvm_has_feat() to take variable arguments
  KVM: arm64: Use FGT feature maps to drive RES0 bits
  KVM: arm64: Validate FGT register descriptions against RES0 masks
  KVM: arm64: Switch to table-driven FGU configuration
  KVM: arm64: Handle PSB CSYNC traps
  KVM: arm64: Use KVM-specific HCRX_EL2 RES0 mask
  KVM: arm64: Remove hand-crafted masks for FGT registers
  KVM: arm64: Use computed FGT masks to setup FGT registers
  KVM: arm64: Propagate FGT masks to the nVHE hypervisor
  KVM: arm64: Unconditionally configure fine-grain traps
  KVM: arm64: Use computed masks as sanitisers for FGT registers
  ...

Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/el2_setup.h

@@ -213,8 +213,8 @@
 	cbz	x1, .Lskip_debug_fgt_\@
 
 	/* Disable nVHE traps of TPIDR2 and SMPRI */
-	orr	x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK
-	orr	x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK
+	orr	x0, x0, #HFGRTR_EL2_nSMPRI_EL1_MASK
+	orr	x0, x0, #HFGRTR_EL2_nTPIDR2_EL0_MASK
 
 .Lskip_debug_fgt_\@:
 	mrs_s	x1, SYS_ID_AA64MMFR3_EL1
@@ -222,8 +222,8 @@
 	cbz	x1, .Lskip_pie_fgt_\@
 
 	/* Disable trapping of PIR_EL1 / PIRE0_EL1 */
-	orr	x0, x0, #HFGxTR_EL2_nPIR_EL1
-	orr	x0, x0, #HFGxTR_EL2_nPIRE0_EL1
+	orr	x0, x0, #HFGRTR_EL2_nPIR_EL1
+	orr	x0, x0, #HFGRTR_EL2_nPIRE0_EL1
 
 .Lskip_pie_fgt_\@:
 	mrs_s	x1, SYS_ID_AA64MMFR3_EL1
@@ -231,7 +231,7 @@
 	cbz	x1, .Lskip_poe_fgt_\@
 
 	/* Disable trapping of POR_EL0 */
-	orr	x0, x0, #HFGxTR_EL2_nPOR_EL0
+	orr	x0, x0, #HFGRTR_EL2_nPOR_EL0
 
 .Lskip_poe_fgt_\@:
 	/* GCS depends on PIE so we don't check it if PIE is absent */
@@ -240,8 +240,8 @@
 	cbz	x1, .Lset_fgt_\@
 
 	/* Disable traps of access to GCS registers at EL0 and EL1 */
-	orr	x0, x0, #HFGxTR_EL2_nGCS_EL1_MASK
-	orr	x0, x0, #HFGxTR_EL2_nGCS_EL0_MASK
+	orr	x0, x0, #HFGRTR_EL2_nGCS_EL1_MASK
+	orr	x0, x0, #HFGRTR_EL2_nGCS_EL0_MASK
 
 .Lset_fgt_\@:
 	msr_s	SYS_HFGRTR_EL2, x0

arch/arm64/include/asm/esr.h

@@ -20,7 +20,8 @@
 #define ESR_ELx_EC_FP_ASIMD	UL(0x07)
 #define ESR_ELx_EC_CP10_ID	UL(0x08)	/* EL2 only */
 #define ESR_ELx_EC_PAC		UL(0x09)	/* EL2 and above */
-/* Unallocated EC: 0x0A - 0x0B */
+#define ESR_ELx_EC_OTHER	UL(0x0A)
+/* Unallocated EC: 0x0B */
 #define ESR_ELx_EC_CP14_64	UL(0x0C)
 #define ESR_ELx_EC_BTI		UL(0x0D)
 #define ESR_ELx_EC_ILL		UL(0x0E)
@@ -181,6 +182,13 @@
 #define ESR_ELx_WFx_ISS_WFE	(UL(1) << 0)
 #define ESR_ELx_xVC_IMM_MASK	((UL(1) << 16) - 1)
 
+/* ISS definitions for LD64B/ST64B/{T,P}SBCSYNC instructions */
+#define ESR_ELx_ISS_OTHER_ST64BV	(0)
+#define ESR_ELx_ISS_OTHER_ST64BV0	(1)
+#define ESR_ELx_ISS_OTHER_LDST64B	(2)
+#define ESR_ELx_ISS_OTHER_TSBCSYNC	(3)
+#define ESR_ELx_ISS_OTHER_PSBCSYNC	(4)
+
 #define DISR_EL1_IDS		(UL(1) << 24)
 /*
  * DISR_EL1 and ESR_ELx share the bottom 13 bits, but the RES0 bits may mean

arch/arm64/include/asm/kvm_arm.h

@@ -12,67 +12,70 @@
 #include <asm/sysreg.h>
 #include <asm/types.h>
 
-/* Hyp Configuration Register (HCR) bits */
+/*
+ * Because I'm terribly lazy and that repainting the whole of the KVM
+ * code with the proper names is a pain, use a helper to map the names
+ * inherited from AArch32 with the new fancy nomenclature. One day...
+ */
+#define	__HCR(x)	HCR_EL2_##x
 
-#define HCR_TID5	(UL(1) << 58)
-#define HCR_DCT		(UL(1) << 57)
-#define HCR_ATA_SHIFT	56
-#define HCR_ATA		(UL(1) << HCR_ATA_SHIFT)
-#define HCR_TTLBOS	(UL(1) << 55)
-#define HCR_TTLBIS	(UL(1) << 54)
-#define HCR_ENSCXT	(UL(1) << 53)
-#define HCR_TOCU	(UL(1) << 52)
-#define HCR_AMVOFFEN	(UL(1) << 51)
-#define HCR_TICAB	(UL(1) << 50)
-#define HCR_TID4	(UL(1) << 49)
-#define HCR_FIEN	(UL(1) << 47)
-#define HCR_FWB		(UL(1) << 46)
-#define HCR_NV2		(UL(1) << 45)
-#define HCR_AT		(UL(1) << 44)
-#define HCR_NV1		(UL(1) << 43)
-#define HCR_NV		(UL(1) << 42)
-#define HCR_API		(UL(1) << 41)
-#define HCR_APK		(UL(1) << 40)
-#define HCR_TEA		(UL(1) << 37)
-#define HCR_TERR	(UL(1) << 36)
-#define HCR_TLOR	(UL(1) << 35)
-#define HCR_E2H		(UL(1) << 34)
-#define HCR_ID		(UL(1) << 33)
-#define HCR_CD		(UL(1) << 32)
-#define HCR_RW_SHIFT	31
-#define HCR_RW		(UL(1) << HCR_RW_SHIFT)
-#define HCR_TRVM	(UL(1) << 30)
-#define HCR_HCD		(UL(1) << 29)
-#define HCR_TDZ		(UL(1) << 28)
-#define HCR_TGE		(UL(1) << 27)
-#define HCR_TVM		(UL(1) << 26)
-#define HCR_TTLB	(UL(1) << 25)
-#define HCR_TPU		(UL(1) << 24)
-#define HCR_TPC		(UL(1) << 23) /* HCR_TPCP if FEAT_DPB */
-#define HCR_TSW		(UL(1) << 22)
-#define HCR_TACR	(UL(1) << 21)
-#define HCR_TIDCP	(UL(1) << 20)
-#define HCR_TSC		(UL(1) << 19)
-#define HCR_TID3	(UL(1) << 18)
-#define HCR_TID2	(UL(1) << 17)
-#define HCR_TID1	(UL(1) << 16)
-#define HCR_TID0	(UL(1) << 15)
-#define HCR_TWE		(UL(1) << 14)
-#define HCR_TWI		(UL(1) << 13)
-#define HCR_DC		(UL(1) << 12)
-#define HCR_BSU		(3 << 10)
-#define HCR_BSU_IS	(UL(1) << 10)
-#define HCR_FB		(UL(1) << 9)
-#define HCR_VSE		(UL(1) << 8)
-#define HCR_VI		(UL(1) << 7)
-#define HCR_VF		(UL(1) << 6)
-#define HCR_AMO		(UL(1) << 5)
-#define HCR_IMO		(UL(1) << 4)
-#define HCR_FMO		(UL(1) << 3)
-#define HCR_PTW		(UL(1) << 2)
-#define HCR_SWIO	(UL(1) << 1)
-#define HCR_VM		(UL(1) << 0)
-#define HCR_RES0	((UL(1) << 48) | (UL(1) << 39))
+#define HCR_TID5	__HCR(TID5)
+#define HCR_DCT		__HCR(DCT)
+#define HCR_ATA_SHIFT	__HCR(ATA_SHIFT)
+#define HCR_ATA		__HCR(ATA)
+#define HCR_TTLBOS	__HCR(TTLBOS)
+#define HCR_TTLBIS	__HCR(TTLBIS)
+#define HCR_ENSCXT	__HCR(EnSCXT)
+#define HCR_TOCU	__HCR(TOCU)
+#define HCR_AMVOFFEN	__HCR(AMVOFFEN)
+#define HCR_TICAB	__HCR(TICAB)
+#define HCR_TID4	__HCR(TID4)
+#define HCR_FIEN	__HCR(FIEN)
+#define HCR_FWB		__HCR(FWB)
+#define HCR_NV2		__HCR(NV2)
+#define HCR_AT		__HCR(AT)
+#define HCR_NV1		__HCR(NV1)
+#define HCR_NV		__HCR(NV)
+#define HCR_API		__HCR(API)
+#define HCR_APK		__HCR(APK)
+#define HCR_TEA		__HCR(TEA)
+#define HCR_TERR	__HCR(TERR)
+#define HCR_TLOR	__HCR(TLOR)
+#define HCR_E2H		__HCR(E2H)
+#define HCR_ID		__HCR(ID)
+#define HCR_CD		__HCR(CD)
+#define HCR_RW		__HCR(RW)
+#define HCR_TRVM	__HCR(TRVM)
+#define HCR_HCD		__HCR(HCD)
+#define HCR_TDZ		__HCR(TDZ)
+#define HCR_TGE		__HCR(TGE)
+#define HCR_TVM		__HCR(TVM)
+#define HCR_TTLB	__HCR(TTLB)
+#define HCR_TPU		__HCR(TPU)
+#define HCR_TPC		__HCR(TPCP)
+#define HCR_TSW		__HCR(TSW)
+#define HCR_TACR	__HCR(TACR)
+#define HCR_TIDCP	__HCR(TIDCP)
+#define HCR_TSC		__HCR(TSC)
+#define HCR_TID3	__HCR(TID3)
+#define HCR_TID2	__HCR(TID2)
+#define HCR_TID1	__HCR(TID1)
+#define HCR_TID0	__HCR(TID0)
+#define HCR_TWE		__HCR(TWE)
+#define HCR_TWI		__HCR(TWI)
+#define HCR_DC		__HCR(DC)
+#define HCR_BSU		__HCR(BSU)
+#define HCR_BSU_IS	__HCR(BSU_IS)
+#define HCR_FB		__HCR(FB)
+#define HCR_VSE		__HCR(VSE)
+#define HCR_VI		__HCR(VI)
+#define HCR_VF		__HCR(VF)
+#define HCR_AMO		__HCR(AMO)
+#define HCR_IMO		__HCR(IMO)
+#define HCR_FMO		__HCR(FMO)
+#define HCR_PTW		__HCR(PTW)
+#define HCR_SWIO	__HCR(SWIO)
+#define HCR_VM		__HCR(VM)
 
 /*
  * The bits we set in HCR:
@@ -313,56 +316,19 @@
 				 GENMASK(15, 0))
 
 /*
- * FGT register definitions
- *
- * RES0 and polarity masks as of DDI0487J.a, to be updated as needed.
- * We're not using the generated masks as they are usually ahead of
- * the published ARM ARM, which we use as a reference.
- *
- * Once we get to a point where the two describe the same thing, we'll
- * merge the definitions. One day.
+ * Polarity masks for HCRX_EL2, limited to the bits that we know about
+ * at this point in time. It doesn't mean that we actually *handle*
+ * them, but that at least those that are not advertised to a guest
+ * will be RES0 for that guest.
  */
-#define __HFGRTR_EL2_RES0	HFGxTR_EL2_RES0
-#define __HFGRTR_EL2_MASK	GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK	~(__HFGRTR_EL2_RES0 | __HFGRTR_EL2_MASK)
-
-/*
- * The HFGWTR bits are a subset of HFGRTR bits. To ensure we don't miss any
- * future additions, define __HFGWTR* macros relative to __HFGRTR* ones.
- */
-#define __HFGRTR_ONLY_MASK	(BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
-				 GENMASK(26, 25) | BIT(21) | BIT(18) | \
-				 GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
-#define __HFGWTR_EL2_RES0	(__HFGRTR_EL2_RES0 | __HFGRTR_ONLY_MASK)
-#define __HFGWTR_EL2_MASK	(__HFGRTR_EL2_MASK & ~__HFGRTR_ONLY_MASK)
-#define __HFGWTR_EL2_nMASK	~(__HFGWTR_EL2_RES0 | __HFGWTR_EL2_MASK)
-
-#define __HFGITR_EL2_RES0	HFGITR_EL2_RES0
-#define __HFGITR_EL2_MASK	(BIT(62) | BIT(60) | GENMASK(54, 0))
-#define __HFGITR_EL2_nMASK	~(__HFGITR_EL2_RES0 | __HFGITR_EL2_MASK)
-
-#define __HDFGRTR_EL2_RES0	HDFGRTR_EL2_RES0
-#define __HDFGRTR_EL2_MASK	(BIT(63) | GENMASK(58, 50) | GENMASK(48, 43) | \
-				 GENMASK(41, 40) | GENMASK(37, 22) | \
-				 GENMASK(19, 9) | GENMASK(7, 0))
-#define __HDFGRTR_EL2_nMASK	~(__HDFGRTR_EL2_RES0 | __HDFGRTR_EL2_MASK)
-
-#define __HDFGWTR_EL2_RES0	HDFGWTR_EL2_RES0
-#define __HDFGWTR_EL2_MASK	(GENMASK(57, 52) | GENMASK(50, 48) | \
-				 GENMASK(46, 44) | GENMASK(42, 41) | \
-				 GENMASK(37, 35) | GENMASK(33, 31) | \
-				 GENMASK(29, 23) | GENMASK(21, 10) | \
-				 GENMASK(8, 7) | GENMASK(5, 0))
-#define __HDFGWTR_EL2_nMASK	~(__HDFGWTR_EL2_RES0 | __HDFGWTR_EL2_MASK)
-
-#define __HAFGRTR_EL2_RES0	HAFGRTR_EL2_RES0
-#define __HAFGRTR_EL2_MASK	(GENMASK(49, 17) | GENMASK(4, 0))
-#define __HAFGRTR_EL2_nMASK	~(__HAFGRTR_EL2_RES0 | __HAFGRTR_EL2_MASK)
-
-/* Similar definitions for HCRX_EL2 */
-#define __HCRX_EL2_RES0         HCRX_EL2_RES0
-#define __HCRX_EL2_MASK		(BIT(6))
-#define __HCRX_EL2_nMASK	~(__HCRX_EL2_RES0 | __HCRX_EL2_MASK)
+#define __HCRX_EL2_MASK		(BIT_ULL(6))
+#define __HCRX_EL2_nMASK	(GENMASK_ULL(24, 14) | \
+				 GENMASK_ULL(11, 7)  | \
+				 GENMASK_ULL(5, 0))
+#define __HCRX_EL2_RES0		~(__HCRX_EL2_nMASK | __HCRX_EL2_MASK)
+#define __HCRX_EL2_RES1		~(__HCRX_EL2_nMASK | \
+				  __HCRX_EL2_MASK  | \
+				  __HCRX_EL2_RES0)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))

arch/arm64/include/asm/kvm_host.h

@@ -273,11 +273,17 @@ struct kvm_sysreg_masks;
 
 enum fgt_group_id {
 	__NO_FGT_GROUP__,
-	HFGxTR_GROUP,
+	HFGRTR_GROUP,
+	HFGWTR_GROUP = HFGRTR_GROUP,
 	HDFGRTR_GROUP,
 	HDFGWTR_GROUP = HDFGRTR_GROUP,
 	HFGITR_GROUP,
 	HAFGRTR_GROUP,
+	HFGRTR2_GROUP,
+	HFGWTR2_GROUP = HFGRTR2_GROUP,
+	HDFGRTR2_GROUP,
+	HDFGWTR2_GROUP = HDFGRTR2_GROUP,
+	HFGITR2_GROUP,
 
 	/* Must be last */
 	__NR_FGT_GROUP_IDS__
@@ -561,6 +567,11 @@ enum vcpu_sysreg {
 	VNCR(HDFGRTR_EL2),
 	VNCR(HDFGWTR_EL2),
 	VNCR(HAFGRTR_EL2),
+	VNCR(HFGRTR2_EL2),
+	VNCR(HFGWTR2_EL2),
+	VNCR(HFGITR2_EL2),
+	VNCR(HDFGRTR2_EL2),
+	VNCR(HDFGWTR2_EL2),
 
 	VNCR(CNTVOFF_EL2),
 	VNCR(CNTV_CVAL_EL0),
@@ -606,6 +617,37 @@ struct kvm_sysreg_masks {
 	} mask[NR_SYS_REGS - __SANITISED_REG_START__];
 };
 
+struct fgt_masks {
+	const char	*str;
+	u64		mask;
+	u64		nmask;
+	u64		res0;
+};
+
+extern struct fgt_masks hfgrtr_masks;
+extern struct fgt_masks hfgwtr_masks;
+extern struct fgt_masks hfgitr_masks;
+extern struct fgt_masks hdfgrtr_masks;
+extern struct fgt_masks hdfgwtr_masks;
+extern struct fgt_masks hafgrtr_masks;
+extern struct fgt_masks hfgrtr2_masks;
+extern struct fgt_masks hfgwtr2_masks;
+extern struct fgt_masks hfgitr2_masks;
+extern struct fgt_masks hdfgrtr2_masks;
+extern struct fgt_masks hdfgwtr2_masks;
+
+extern struct fgt_masks kvm_nvhe_sym(hfgrtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgwtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgitr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hdfgrtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hdfgwtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hafgrtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgrtr2_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgwtr2_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgitr2_masks);
+extern struct fgt_masks kvm_nvhe_sym(hdfgrtr2_masks);
+extern struct fgt_masks kvm_nvhe_sym(hdfgwtr2_masks);
+
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
@@ -1552,12 +1594,16 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 	 kvm_cmp_feat_signed(kvm, id, fld, op, limit) :			\
 	 kvm_cmp_feat_unsigned(kvm, id, fld, op, limit))
 
-#define kvm_has_feat(kvm, id, fld, limit)				\
+#define __kvm_has_feat(kvm, id, fld, limit)				\
 	kvm_cmp_feat(kvm, id, fld, >=, limit)
 
-#define kvm_has_feat_enum(kvm, id, fld, val)				\
+#define kvm_has_feat(kvm, ...) __kvm_has_feat(kvm, __VA_ARGS__)
+
+#define __kvm_has_feat_enum(kvm, id, fld, val)				\
 	kvm_cmp_feat_unsigned(kvm, id, fld, ==, val)
 
+#define kvm_has_feat_enum(kvm, ...) __kvm_has_feat_enum(kvm, __VA_ARGS__)
+
 #define kvm_has_feat_range(kvm, id, fld, min, max)			\
 	(kvm_cmp_feat(kvm, id, fld, >=, min) &&				\
 	kvm_cmp_feat(kvm, id, fld, <=, max))
@@ -1595,4 +1641,9 @@ static inline bool kvm_arch_has_irq_bypass(void)
 	return true;
 }
 
+void compute_fgu(struct kvm *kvm, enum fgt_group_id fgt);
+void get_reg_fixed_bits(struct kvm *kvm, enum vcpu_sysreg reg, u64 *res0, u64 *res1);
+void check_feature_map(void);
+
+
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/include/asm/sysreg.h

@@ -117,6 +117,7 @@
 
 #define SB_BARRIER_INSN			__SYS_BARRIER_INSN(0, 7, 31)
 
+/* Data cache zero operations */
 #define SYS_DC_ISW			sys_insn(1, 0, 7, 6, 2)
 #define SYS_DC_IGSW			sys_insn(1, 0, 7, 6, 4)
 #define SYS_DC_IGDSW			sys_insn(1, 0, 7, 6, 6)
@@ -153,11 +154,13 @@
 #define SYS_DC_CIGVAC			sys_insn(1, 3, 7, 14, 3)
 #define SYS_DC_CIGDVAC			sys_insn(1, 3, 7, 14, 5)
 
-/* Data cache zero operations */
 #define SYS_DC_ZVA			sys_insn(1, 3, 7, 4, 1)
 #define SYS_DC_GVA			sys_insn(1, 3, 7, 4, 3)
 #define SYS_DC_GZVA			sys_insn(1, 3, 7, 4, 4)
 
+#define SYS_DC_CIVAPS			sys_insn(1, 0, 7, 15, 1)
+#define SYS_DC_CIGDVAPS			sys_insn(1, 0, 7, 15, 5)
+
 /*
  * Automatically generated definitions for system registers, the
  * manual encodings below are in the process of being converted to
@@ -497,12 +500,22 @@
 
 #define __PMEV_op2(n)			((n) & 0x7)
 #define __CNTR_CRm(n)			(0x8 | (((n) >> 3) & 0x3))
+#define SYS_PMEVCNTSVRn_EL1(n)		sys_reg(2, 0, 14, __CNTR_CRm(n), __PMEV_op2(n))
 #define SYS_PMEVCNTRn_EL0(n)		sys_reg(3, 3, 14, __CNTR_CRm(n), __PMEV_op2(n))
 #define __TYPER_CRm(n)			(0xc | (((n) >> 3) & 0x3))
 #define SYS_PMEVTYPERn_EL0(n)		sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n))
 
 #define SYS_PMCCFILTR_EL0		sys_reg(3, 3, 14, 15, 7)
 
+#define	SYS_SPMCGCRn_EL1(n)		sys_reg(2, 0, 9, 13, ((n) & 1))
+
+#define __SPMEV_op2(n)			((n) & 0x7)
+#define __SPMEV_crm(p, n)		((((p) & 7) << 1) | (((n) >> 3) & 1))
+#define SYS_SPMEVCNTRn_EL0(n)		sys_reg(2, 3, 14, __SPMEV_crm(0b000, n), __SPMEV_op2(n))
+#define	SYS_SPMEVFILT2Rn_EL0(n)		sys_reg(2, 3, 14, __SPMEV_crm(0b011, n), __SPMEV_op2(n))
+#define	SYS_SPMEVFILTRn_EL0(n)		sys_reg(2, 3, 14, __SPMEV_crm(0b010, n), __SPMEV_op2(n))
+#define	SYS_SPMEVTYPERn_EL0(n)		sys_reg(2, 3, 14, __SPMEV_crm(0b001, n), __SPMEV_op2(n))
+
 #define SYS_VPIDR_EL2			sys_reg(3, 4, 0, 0, 0)
 #define SYS_VMPIDR_EL2			sys_reg(3, 4, 0, 0, 5)
 
@@ -522,7 +535,6 @@
 #define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
 
 #define SYS_VNCR_EL2			sys_reg(3, 4, 2, 2, 0)
-#define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
 #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
 #define SYS_SP_EL1			sys_reg(3, 4, 4, 1, 0)
@@ -608,28 +620,18 @@
 
 /* VHE encodings for architectural EL0/1 system registers */
 #define SYS_BRBCR_EL12			sys_reg(2, 5, 9, 0, 0)
-#define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
-#define SYS_CPACR_EL12			sys_reg(3, 5, 1, 0, 2)
-#define SYS_SCTLR2_EL12			sys_reg(3, 5, 1, 0, 3)
-#define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
-#define SYS_TRFCR_EL12			sys_reg(3, 5, 1, 2, 1)
-#define SYS_SMCR_EL12			sys_reg(3, 5, 1, 2, 6)
 #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
 #define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
-#define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
-#define SYS_TCR2_EL12			sys_reg(3, 5, 2, 0, 3)
 #define SYS_SPSR_EL12			sys_reg(3, 5, 4, 0, 0)
 #define SYS_ELR_EL12			sys_reg(3, 5, 4, 0, 1)
 #define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
 #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
 #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
 #define SYS_TFSR_EL12			sys_reg(3, 5, 5, 6, 0)
-#define SYS_FAR_EL12			sys_reg(3, 5, 6, 0, 0)
 #define SYS_PMSCR_EL12			sys_reg(3, 5, 9, 9, 0)
 #define SYS_MAIR_EL12			sys_reg(3, 5, 10, 2, 0)
 #define SYS_AMAIR_EL12			sys_reg(3, 5, 10, 3, 0)
 #define SYS_VBAR_EL12			sys_reg(3, 5, 12, 0, 0)
-#define SYS_CONTEXTIDR_EL12		sys_reg(3, 5, 13, 0, 1)
 #define SYS_SCXTNUM_EL12		sys_reg(3, 5, 13, 0, 7)
 #define SYS_CNTKCTL_EL12		sys_reg(3, 5, 14, 1, 0)
 #define SYS_CNTP_TVAL_EL02		sys_reg(3, 5, 14, 2, 0)

arch/arm64/include/asm/vncr_mapping.h

@@ -35,6 +35,8 @@
 #define VNCR_CNTP_CTL_EL0       0x180
 #define VNCR_SCXTNUM_EL1        0x188
 #define VNCR_TFSR_EL1		0x190
+#define VNCR_HDFGRTR2_EL2	0x1A0
+#define VNCR_HDFGWTR2_EL2	0x1B0
 #define VNCR_HFGRTR_EL2		0x1B8
 #define VNCR_HFGWTR_EL2		0x1C0
 #define VNCR_HFGITR_EL2		0x1C8
@@ -52,6 +54,9 @@
 #define VNCR_PIRE0_EL1		0x290
 #define VNCR_PIR_EL1		0x2A0
 #define VNCR_POR_EL1		0x2A8
+#define VNCR_HFGRTR2_EL2	0x2C0
+#define VNCR_HFGWTR2_EL2	0x2C8
+#define VNCR_HFGITR2_EL2	0x310
 #define VNCR_ICH_LR0_EL2        0x400
 #define VNCR_ICH_LR1_EL2        0x408
 #define VNCR_ICH_LR2_EL2        0x410

arch/arm64/kernel/cpufeature.c

@@ -2877,6 +2877,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, FGT, IMP)
 	},
+	{
+		.desc = "Fine Grained Traps 2",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_HAS_FGT2,
+		.matches = has_cpuid_feature,
+		ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, FGT, FGT2)
+	},
 #ifdef CONFIG_ARM64_SME
 	{
 		.desc = "Scalable Matrix Extension",

arch/arm64/kvm/Makefile

@@ -14,7 +14,7 @@ CFLAGS_sys_regs.o += -Wno-override-init
 CFLAGS_handle_exit.o += -Wno-override-init
 
 kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
-	 inject_fault.o va_layout.o handle_exit.o \
+	 inject_fault.o va_layout.o handle_exit.o config.o \
 	 guest.o debug.o reset.o sys_regs.o stacktrace.o \
 	 vgic-sys-reg-v3.o fpsimd.o pkvm.o \
 	 arch_timer.o trng.o vmid.o emulate-nested.o nested.o at.o \

arch/arm64/kvm/arm.c

@@ -2450,6 +2450,19 @@ static void kvm_hyp_init_symbols(void)
 	kvm_nvhe_sym(__icache_flags) = __icache_flags;
 	kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
 
+	/* Propagate the FGT state to the the nVHE side */
+	kvm_nvhe_sym(hfgrtr_masks)  = hfgrtr_masks;
+	kvm_nvhe_sym(hfgwtr_masks)  = hfgwtr_masks;
+	kvm_nvhe_sym(hfgitr_masks)  = hfgitr_masks;
+	kvm_nvhe_sym(hdfgrtr_masks) = hdfgrtr_masks;
+	kvm_nvhe_sym(hdfgwtr_masks) = hdfgwtr_masks;
+	kvm_nvhe_sym(hafgrtr_masks) = hafgrtr_masks;
+	kvm_nvhe_sym(hfgrtr2_masks) = hfgrtr2_masks;
+	kvm_nvhe_sym(hfgwtr2_masks) = hfgwtr2_masks;
+	kvm_nvhe_sym(hfgitr2_masks) = hfgitr2_masks;
+	kvm_nvhe_sym(hdfgrtr2_masks)= hdfgrtr2_masks;
+	kvm_nvhe_sym(hdfgwtr2_masks)= hdfgwtr2_masks;
+
 	/*
 	 * Flush entire BSS since part of its data containing init symbols is read
 	 * while the MMU is off.

arch/arm64/kvm/emulate-nested.c

@@ -622,6 +622,11 @@ struct encoding_to_trap_config {
 	const unsigned int		line;
 };
 
+/*
+ * WARNING: using ranges is a treacherous endeavour, as sysregs that
+ * are part of an architectural range are not necessarily contiguous
+ * in the [Op0,Op1,CRn,CRm,Ops] space. Tread carefully.
+ */
 #define SR_RANGE_TRAP(sr_start, sr_end, trap_id)			\
 	{								\
 		.encoding	= sr_start,				\
@@ -1279,98 +1284,128 @@ enum fg_filter_id {
 	__NR_FG_FILTER_IDS__
 };
 
-#define SR_FGF(sr, g, b, p, f)					\
-	{							\
-		.encoding	= sr,				\
-		.end		= sr,				\
-		.tc		= {				\
+#define __FGT(g, b, p, f)					\
+		{						\
 			.fgt = g ## _GROUP,			\
 			.bit = g ## _EL2_ ## b ## _SHIFT,	\
 			.pol = p,				\
 			.fgf = f,				\
-		},						\
+		}
+
+#define FGT(g, b, p)		__FGT(g, b, p, __NO_FGF__)
+
+/*
+ * See the warning next to SR_RANGE_TRAP(), and apply the same
+ * level of caution.
+ */
+#define SR_FGF_RANGE(sr, e, g, b, p, f)				\
+	{							\
+		.encoding	= sr,				\
+		.end		= e,				\
+		.tc		= __FGT(g, b, p, f),		\
 		.line = __LINE__,				\
 	}
 
-#define SR_FGT(sr, g, b, p)	SR_FGF(sr, g, b, p, __NO_FGF__)
+#define SR_FGF(sr, g, b, p, f) 	SR_FGF_RANGE(sr, sr, g, b, p, f)
+#define SR_FGT(sr, g, b, p)	SR_FGF_RANGE(sr, sr, g, b, p, __NO_FGF__)
+#define SR_FGT_RANGE(sr, end, g, b, p)	\
+				SR_FGF_RANGE(sr, end, g, b, p, __NO_FGF__)
 
 static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	/* HFGRTR_EL2, HFGWTR_EL2 */
-	SR_FGT(SYS_AMAIR2_EL1,		HFGxTR, nAMAIR2_EL1, 0),
-	SR_FGT(SYS_MAIR2_EL1,		HFGxTR, nMAIR2_EL1, 0),
-	SR_FGT(SYS_S2POR_EL1,		HFGxTR, nS2POR_EL1, 0),
-	SR_FGT(SYS_POR_EL1,		HFGxTR, nPOR_EL1, 0),
-	SR_FGT(SYS_POR_EL0,		HFGxTR, nPOR_EL0, 0),
-	SR_FGT(SYS_PIR_EL1,		HFGxTR, nPIR_EL1, 0),
-	SR_FGT(SYS_PIRE0_EL1,		HFGxTR, nPIRE0_EL1, 0),
-	SR_FGT(SYS_RCWMASK_EL1,		HFGxTR, nRCWMASK_EL1, 0),
-	SR_FGT(SYS_TPIDR2_EL0,		HFGxTR, nTPIDR2_EL0, 0),
-	SR_FGT(SYS_SMPRI_EL1,		HFGxTR, nSMPRI_EL1, 0),
-	SR_FGT(SYS_GCSCR_EL1,		HFGxTR, nGCS_EL1, 0),
-	SR_FGT(SYS_GCSPR_EL1,		HFGxTR, nGCS_EL1, 0),
-	SR_FGT(SYS_GCSCRE0_EL1,		HFGxTR, nGCS_EL0, 0),
-	SR_FGT(SYS_GCSPR_EL0,		HFGxTR, nGCS_EL0, 0),
-	SR_FGT(SYS_ACCDATA_EL1,		HFGxTR, nACCDATA_EL1, 0),
-	SR_FGT(SYS_ERXADDR_EL1,		HFGxTR, ERXADDR_EL1, 1),
-	SR_FGT(SYS_ERXPFGCDN_EL1,	HFGxTR, ERXPFGCDN_EL1, 1),
-	SR_FGT(SYS_ERXPFGCTL_EL1,	HFGxTR, ERXPFGCTL_EL1, 1),
-	SR_FGT(SYS_ERXPFGF_EL1,		HFGxTR, ERXPFGF_EL1, 1),
-	SR_FGT(SYS_ERXMISC0_EL1,	HFGxTR, ERXMISCn_EL1, 1),
-	SR_FGT(SYS_ERXMISC1_EL1,	HFGxTR, ERXMISCn_EL1, 1),
-	SR_FGT(SYS_ERXMISC2_EL1,	HFGxTR, ERXMISCn_EL1, 1),
-	SR_FGT(SYS_ERXMISC3_EL1,	HFGxTR, ERXMISCn_EL1, 1),
-	SR_FGT(SYS_ERXSTATUS_EL1,	HFGxTR, ERXSTATUS_EL1, 1),
-	SR_FGT(SYS_ERXCTLR_EL1,		HFGxTR, ERXCTLR_EL1, 1),
-	SR_FGT(SYS_ERXFR_EL1,		HFGxTR, ERXFR_EL1, 1),
-	SR_FGT(SYS_ERRSELR_EL1,		HFGxTR, ERRSELR_EL1, 1),
-	SR_FGT(SYS_ERRIDR_EL1,		HFGxTR, ERRIDR_EL1, 1),
-	SR_FGT(SYS_ICC_IGRPEN0_EL1,	HFGxTR, ICC_IGRPENn_EL1, 1),
-	SR_FGT(SYS_ICC_IGRPEN1_EL1,	HFGxTR, ICC_IGRPENn_EL1, 1),
-	SR_FGT(SYS_VBAR_EL1,		HFGxTR, VBAR_EL1, 1),
-	SR_FGT(SYS_TTBR1_EL1,		HFGxTR, TTBR1_EL1, 1),
-	SR_FGT(SYS_TTBR0_EL1,		HFGxTR, TTBR0_EL1, 1),
-	SR_FGT(SYS_TPIDR_EL0,		HFGxTR, TPIDR_EL0, 1),
-	SR_FGT(SYS_TPIDRRO_EL0,		HFGxTR, TPIDRRO_EL0, 1),
-	SR_FGT(SYS_TPIDR_EL1,		HFGxTR, TPIDR_EL1, 1),
-	SR_FGT(SYS_TCR_EL1,		HFGxTR, TCR_EL1, 1),
-	SR_FGT(SYS_TCR2_EL1,		HFGxTR, TCR_EL1, 1),
-	SR_FGT(SYS_SCXTNUM_EL0,		HFGxTR, SCXTNUM_EL0, 1),
-	SR_FGT(SYS_SCXTNUM_EL1, 	HFGxTR, SCXTNUM_EL1, 1),
-	SR_FGT(SYS_SCTLR_EL1, 		HFGxTR, SCTLR_EL1, 1),
-	SR_FGT(SYS_REVIDR_EL1, 		HFGxTR, REVIDR_EL1, 1),
-	SR_FGT(SYS_PAR_EL1, 		HFGxTR, PAR_EL1, 1),
-	SR_FGT(SYS_MPIDR_EL1, 		HFGxTR, MPIDR_EL1, 1),
-	SR_FGT(SYS_MIDR_EL1, 		HFGxTR, MIDR_EL1, 1),
-	SR_FGT(SYS_MAIR_EL1, 		HFGxTR, MAIR_EL1, 1),
-	SR_FGT(SYS_LORSA_EL1, 		HFGxTR, LORSA_EL1, 1),
-	SR_FGT(SYS_LORN_EL1, 		HFGxTR, LORN_EL1, 1),
-	SR_FGT(SYS_LORID_EL1, 		HFGxTR, LORID_EL1, 1),
-	SR_FGT(SYS_LOREA_EL1, 		HFGxTR, LOREA_EL1, 1),
-	SR_FGT(SYS_LORC_EL1, 		HFGxTR, LORC_EL1, 1),
-	SR_FGT(SYS_ISR_EL1, 		HFGxTR, ISR_EL1, 1),
-	SR_FGT(SYS_FAR_EL1, 		HFGxTR, FAR_EL1, 1),
-	SR_FGT(SYS_ESR_EL1, 		HFGxTR, ESR_EL1, 1),
-	SR_FGT(SYS_DCZID_EL0, 		HFGxTR, DCZID_EL0, 1),
-	SR_FGT(SYS_CTR_EL0, 		HFGxTR, CTR_EL0, 1),
-	SR_FGT(SYS_CSSELR_EL1, 		HFGxTR, CSSELR_EL1, 1),
-	SR_FGT(SYS_CPACR_EL1, 		HFGxTR, CPACR_EL1, 1),
-	SR_FGT(SYS_CONTEXTIDR_EL1, 	HFGxTR, CONTEXTIDR_EL1, 1),
-	SR_FGT(SYS_CLIDR_EL1, 		HFGxTR, CLIDR_EL1, 1),
-	SR_FGT(SYS_CCSIDR_EL1, 		HFGxTR, CCSIDR_EL1, 1),
-	SR_FGT(SYS_APIBKEYLO_EL1, 	HFGxTR, APIBKey, 1),
-	SR_FGT(SYS_APIBKEYHI_EL1, 	HFGxTR, APIBKey, 1),
-	SR_FGT(SYS_APIAKEYLO_EL1, 	HFGxTR, APIAKey, 1),
-	SR_FGT(SYS_APIAKEYHI_EL1, 	HFGxTR, APIAKey, 1),
-	SR_FGT(SYS_APGAKEYLO_EL1, 	HFGxTR, APGAKey, 1),
-	SR_FGT(SYS_APGAKEYHI_EL1, 	HFGxTR, APGAKey, 1),
-	SR_FGT(SYS_APDBKEYLO_EL1, 	HFGxTR, APDBKey, 1),
-	SR_FGT(SYS_APDBKEYHI_EL1, 	HFGxTR, APDBKey, 1),
-	SR_FGT(SYS_APDAKEYLO_EL1, 	HFGxTR, APDAKey, 1),
-	SR_FGT(SYS_APDAKEYHI_EL1, 	HFGxTR, APDAKey, 1),
-	SR_FGT(SYS_AMAIR_EL1, 		HFGxTR, AMAIR_EL1, 1),
-	SR_FGT(SYS_AIDR_EL1, 		HFGxTR, AIDR_EL1, 1),
-	SR_FGT(SYS_AFSR1_EL1, 		HFGxTR, AFSR1_EL1, 1),
-	SR_FGT(SYS_AFSR0_EL1, 		HFGxTR, AFSR0_EL1, 1),
+	SR_FGT(SYS_AMAIR2_EL1,		HFGRTR, nAMAIR2_EL1, 0),
+	SR_FGT(SYS_MAIR2_EL1,		HFGRTR, nMAIR2_EL1, 0),
+	SR_FGT(SYS_S2POR_EL1,		HFGRTR, nS2POR_EL1, 0),
+	SR_FGT(SYS_POR_EL1,		HFGRTR, nPOR_EL1, 0),
+	SR_FGT(SYS_POR_EL0,		HFGRTR, nPOR_EL0, 0),
+	SR_FGT(SYS_PIR_EL1,		HFGRTR, nPIR_EL1, 0),
+	SR_FGT(SYS_PIRE0_EL1,		HFGRTR, nPIRE0_EL1, 0),
+	SR_FGT(SYS_RCWMASK_EL1,		HFGRTR, nRCWMASK_EL1, 0),
+	SR_FGT(SYS_TPIDR2_EL0,		HFGRTR, nTPIDR2_EL0, 0),
+	SR_FGT(SYS_SMPRI_EL1,		HFGRTR, nSMPRI_EL1, 0),
+	SR_FGT(SYS_GCSCR_EL1,		HFGRTR, nGCS_EL1, 0),
+	SR_FGT(SYS_GCSPR_EL1,		HFGRTR, nGCS_EL1, 0),
+	SR_FGT(SYS_GCSCRE0_EL1,		HFGRTR, nGCS_EL0, 0),
+	SR_FGT(SYS_GCSPR_EL0,		HFGRTR, nGCS_EL0, 0),
+	SR_FGT(SYS_ACCDATA_EL1,		HFGRTR, nACCDATA_EL1, 0),
+	SR_FGT(SYS_ERXADDR_EL1,		HFGRTR, ERXADDR_EL1, 1),
+	SR_FGT(SYS_ERXPFGCDN_EL1,	HFGRTR, ERXPFGCDN_EL1, 1),
+	SR_FGT(SYS_ERXPFGCTL_EL1,	HFGRTR, ERXPFGCTL_EL1, 1),
+	SR_FGT(SYS_ERXPFGF_EL1,		HFGRTR, ERXPFGF_EL1, 1),
+	SR_FGT(SYS_ERXMISC0_EL1,	HFGRTR, ERXMISCn_EL1, 1),
+	SR_FGT(SYS_ERXMISC1_EL1,	HFGRTR, ERXMISCn_EL1, 1),
+	SR_FGT(SYS_ERXMISC2_EL1,	HFGRTR, ERXMISCn_EL1, 1),
+	SR_FGT(SYS_ERXMISC3_EL1,	HFGRTR, ERXMISCn_EL1, 1),
+	SR_FGT(SYS_ERXSTATUS_EL1,	HFGRTR, ERXSTATUS_EL1, 1),
+	SR_FGT(SYS_ERXCTLR_EL1,		HFGRTR, ERXCTLR_EL1, 1),
+	SR_FGT(SYS_ERXFR_EL1,		HFGRTR, ERXFR_EL1, 1),
+	SR_FGT(SYS_ERRSELR_EL1,		HFGRTR, ERRSELR_EL1, 1),
+	SR_FGT(SYS_ERRIDR_EL1,		HFGRTR, ERRIDR_EL1, 1),
+	SR_FGT(SYS_ICC_IGRPEN0_EL1,	HFGRTR, ICC_IGRPENn_EL1, 1),
+	SR_FGT(SYS_ICC_IGRPEN1_EL1,	HFGRTR, ICC_IGRPENn_EL1, 1),
+	SR_FGT(SYS_VBAR_EL1,		HFGRTR, VBAR_EL1, 1),
+	SR_FGT(SYS_TTBR1_EL1,		HFGRTR, TTBR1_EL1, 1),
+	SR_FGT(SYS_TTBR0_EL1,		HFGRTR, TTBR0_EL1, 1),
+	SR_FGT(SYS_TPIDR_EL0,		HFGRTR, TPIDR_EL0, 1),
+	SR_FGT(SYS_TPIDRRO_EL0,		HFGRTR, TPIDRRO_EL0, 1),
+	SR_FGT(SYS_TPIDR_EL1,		HFGRTR, TPIDR_EL1, 1),
+	SR_FGT(SYS_TCR_EL1,		HFGRTR, TCR_EL1, 1),
+	SR_FGT(SYS_TCR2_EL1,		HFGRTR, TCR_EL1, 1),
+	SR_FGT(SYS_SCXTNUM_EL0,		HFGRTR, SCXTNUM_EL0, 1),
+	SR_FGT(SYS_SCXTNUM_EL1, 	HFGRTR, SCXTNUM_EL1, 1),
+	SR_FGT(SYS_SCTLR_EL1, 		HFGRTR, SCTLR_EL1, 1),
+	SR_FGT(SYS_REVIDR_EL1, 		HFGRTR, REVIDR_EL1, 1),
+	SR_FGT(SYS_PAR_EL1, 		HFGRTR, PAR_EL1, 1),
+	SR_FGT(SYS_MPIDR_EL1, 		HFGRTR, MPIDR_EL1, 1),
+	SR_FGT(SYS_MIDR_EL1, 		HFGRTR, MIDR_EL1, 1),
+	SR_FGT(SYS_MAIR_EL1, 		HFGRTR, MAIR_EL1, 1),
+	SR_FGT(SYS_LORSA_EL1, 		HFGRTR, LORSA_EL1, 1),
+	SR_FGT(SYS_LORN_EL1, 		HFGRTR, LORN_EL1, 1),
+	SR_FGT(SYS_LORID_EL1, 		HFGRTR, LORID_EL1, 1),
+	SR_FGT(SYS_LOREA_EL1, 		HFGRTR, LOREA_EL1, 1),
+	SR_FGT(SYS_LORC_EL1, 		HFGRTR, LORC_EL1, 1),
+	SR_FGT(SYS_ISR_EL1, 		HFGRTR, ISR_EL1, 1),
+	SR_FGT(SYS_FAR_EL1, 		HFGRTR, FAR_EL1, 1),
+	SR_FGT(SYS_ESR_EL1, 		HFGRTR, ESR_EL1, 1),
+	SR_FGT(SYS_DCZID_EL0, 		HFGRTR, DCZID_EL0, 1),
+	SR_FGT(SYS_CTR_EL0, 		HFGRTR, CTR_EL0, 1),
+	SR_FGT(SYS_CSSELR_EL1, 		HFGRTR, CSSELR_EL1, 1),
+	SR_FGT(SYS_CPACR_EL1, 		HFGRTR, CPACR_EL1, 1),
+	SR_FGT(SYS_CONTEXTIDR_EL1, 	HFGRTR, CONTEXTIDR_EL1, 1),
+	SR_FGT(SYS_CLIDR_EL1, 		HFGRTR, CLIDR_EL1, 1),
+	SR_FGT(SYS_CCSIDR_EL1, 		HFGRTR, CCSIDR_EL1, 1),
+	SR_FGT(SYS_APIBKEYLO_EL1, 	HFGRTR, APIBKey, 1),
+	SR_FGT(SYS_APIBKEYHI_EL1, 	HFGRTR, APIBKey, 1),
+	SR_FGT(SYS_APIAKEYLO_EL1, 	HFGRTR, APIAKey, 1),
+	SR_FGT(SYS_APIAKEYHI_EL1, 	HFGRTR, APIAKey, 1),
+	SR_FGT(SYS_APGAKEYLO_EL1, 	HFGRTR, APGAKey, 1),
+	SR_FGT(SYS_APGAKEYHI_EL1, 	HFGRTR, APGAKey, 1),
+	SR_FGT(SYS_APDBKEYLO_EL1, 	HFGRTR, APDBKey, 1),
+	SR_FGT(SYS_APDBKEYHI_EL1, 	HFGRTR, APDBKey, 1),
+	SR_FGT(SYS_APDAKEYLO_EL1, 	HFGRTR, APDAKey, 1),
+	SR_FGT(SYS_APDAKEYHI_EL1, 	HFGRTR, APDAKey, 1),
+	SR_FGT(SYS_AMAIR_EL1, 		HFGRTR, AMAIR_EL1, 1),
+	SR_FGT(SYS_AIDR_EL1, 		HFGRTR, AIDR_EL1, 1),
+	SR_FGT(SYS_AFSR1_EL1, 		HFGRTR, AFSR1_EL1, 1),
+	SR_FGT(SYS_AFSR0_EL1, 		HFGRTR, AFSR0_EL1, 1),
+
+	/* HFGRTR2_EL2, HFGWTR2_EL2 */
+	SR_FGT(SYS_ACTLRALIAS_EL1,	HFGRTR2, nACTLRALIAS_EL1, 0),
+	SR_FGT(SYS_ACTLRMASK_EL1,	HFGRTR2, nACTLRMASK_EL1, 0),
+	SR_FGT(SYS_CPACRALIAS_EL1,	HFGRTR2, nCPACRALIAS_EL1, 0),
+	SR_FGT(SYS_CPACRMASK_EL1,	HFGRTR2, nCPACRMASK_EL1, 0),
+	SR_FGT(SYS_PFAR_EL1,		HFGRTR2, nPFAR_EL1, 0),
+	SR_FGT(SYS_RCWSMASK_EL1,	HFGRTR2, nRCWSMASK_EL1, 0),
+	SR_FGT(SYS_SCTLR2ALIAS_EL1,	HFGRTR2, nSCTLRALIAS2_EL1, 0),
+	SR_FGT(SYS_SCTLR2MASK_EL1,	HFGRTR2, nSCTLR2MASK_EL1, 0),
+	SR_FGT(SYS_SCTLRALIAS_EL1,	HFGRTR2, nSCTLRALIAS_EL1, 0),
+	SR_FGT(SYS_SCTLRMASK_EL1,	HFGRTR2, nSCTLRMASK_EL1, 0),
+	SR_FGT(SYS_TCR2ALIAS_EL1,	HFGRTR2, nTCR2ALIAS_EL1, 0),
+	SR_FGT(SYS_TCR2MASK_EL1,	HFGRTR2, nTCR2MASK_EL1, 0),
+	SR_FGT(SYS_TCRALIAS_EL1,	HFGRTR2, nTCRALIAS_EL1, 0),
+	SR_FGT(SYS_TCRMASK_EL1,		HFGRTR2, nTCRMASK_EL1, 0),
+	SR_FGT(SYS_ERXGSR_EL1,		HFGRTR2, nERXGSR_EL1, 0),
+
 	/* HFGITR_EL2 */
 	SR_FGT(OP_AT_S1E1A, 		HFGITR, ATS1E1A, 1),
 	SR_FGT(OP_COSP_RCTX, 		HFGITR, COSPRCTX, 1),
@@ -1480,6 +1515,11 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_IC_IVAU, 		HFGITR, ICIVAU, 1),
 	SR_FGT(SYS_IC_IALLU, 		HFGITR, ICIALLU, 1),
 	SR_FGT(SYS_IC_IALLUIS, 		HFGITR, ICIALLUIS, 1),
+
+	/* HFGITR2_EL2 */
+	SR_FGT(SYS_DC_CIGDVAPS,		HFGITR2, nDCCIVAPS, 0),
+	SR_FGT(SYS_DC_CIVAPS,		HFGITR2, nDCCIVAPS, 0),
+
 	/* HDFGRTR_EL2 */
 	SR_FGT(SYS_PMBIDR_EL1, 		HDFGRTR, PMBIDR_EL1, 1),
 	SR_FGT(SYS_PMSNEVFR_EL1, 	HDFGRTR, nPMSNEVFR_EL1, 0),
@@ -1789,68 +1829,12 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_PMCNTENSET_EL0, 	HDFGRTR, PMCNTEN, 1),
 	SR_FGT(SYS_PMCCNTR_EL0, 	HDFGRTR, PMCCNTR_EL0, 1),
 	SR_FGT(SYS_PMCCFILTR_EL0, 	HDFGRTR, PMCCFILTR_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(0), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(1), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(2), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(3), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(4), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(5), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(6), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(7), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(8), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(9), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(10), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(11), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(12), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(13), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(14), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(15), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(16), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(17), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(18), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(19), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(20), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(21), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(22), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(23), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(24), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(25), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(26), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(27), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(28), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(29), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVTYPERn_EL0(30), 	HDFGRTR, PMEVTYPERn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(0), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(1), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(2), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(3), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(4), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(5), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(6), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(7), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(8), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(9), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(10), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(11), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(12), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(13), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(14), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(15), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(16), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(17), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(18), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(19), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(20), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(21), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(22), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(23), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(24), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(25), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(26), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(27), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(28), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(29), 	HDFGRTR, PMEVCNTRn_EL0, 1),
-	SR_FGT(SYS_PMEVCNTRn_EL0(30), 	HDFGRTR, PMEVCNTRn_EL0, 1),
+	SR_FGT_RANGE(SYS_PMEVTYPERn_EL0(0),
+		     SYS_PMEVTYPERn_EL0(30),
+		     HDFGRTR, PMEVTYPERn_EL0, 1),
+	SR_FGT_RANGE(SYS_PMEVCNTRn_EL0(0),
+		     SYS_PMEVCNTRn_EL0(30),
+		     HDFGRTR, PMEVCNTRn_EL0, 1),
 	SR_FGT(SYS_OSDLR_EL1, 		HDFGRTR, OSDLR_EL1, 1),
 	SR_FGT(SYS_OSECCR_EL1, 		HDFGRTR, OSECCR_EL1, 1),
 	SR_FGT(SYS_OSLSR_EL1, 		HDFGRTR, OSLSR_EL1, 1),
@@ -1928,6 +1912,59 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_DBGBCRn_EL1(13), 	HDFGRTR, DBGBCRn_EL1, 1),
 	SR_FGT(SYS_DBGBCRn_EL1(14), 	HDFGRTR, DBGBCRn_EL1, 1),
 	SR_FGT(SYS_DBGBCRn_EL1(15), 	HDFGRTR, DBGBCRn_EL1, 1),
+
+	/* HDFGRTR2_EL2 */
+	SR_FGT(SYS_MDSELR_EL1,		HDFGRTR2, nMDSELR_EL1, 0),
+	SR_FGT(SYS_MDSTEPOP_EL1,	HDFGRTR2, nMDSTEPOP_EL1, 0),
+	SR_FGT(SYS_PMCCNTSVR_EL1,	HDFGRTR2, nPMSSDATA, 0),
+	SR_FGT_RANGE(SYS_PMEVCNTSVRn_EL1(0),
+		     SYS_PMEVCNTSVRn_EL1(30),
+		     HDFGRTR2, nPMSSDATA, 0),
+	SR_FGT(SYS_PMICNTSVR_EL1,	HDFGRTR2, nPMSSDATA, 0),
+	SR_FGT(SYS_PMECR_EL1,		HDFGRTR2, nPMECR_EL1, 0),
+	SR_FGT(SYS_PMIAR_EL1,		HDFGRTR2, nPMIAR_EL1, 0),
+	SR_FGT(SYS_PMICFILTR_EL0,	HDFGRTR2, nPMICFILTR_EL0, 0),
+	SR_FGT(SYS_PMICNTR_EL0,		HDFGRTR2, nPMICNTR_EL0, 0),
+	SR_FGT(SYS_PMSSCR_EL1,		HDFGRTR2, nPMSSCR_EL1, 0),
+	SR_FGT(SYS_PMUACR_EL1,		HDFGRTR2, nPMUACR_EL1, 0),
+	SR_FGT(SYS_SPMACCESSR_EL1,	HDFGRTR2, nSPMACCESSR_EL1, 0),
+	SR_FGT(SYS_SPMCFGR_EL1,		HDFGRTR2, nSPMID, 0),
+	SR_FGT(SYS_SPMDEVARCH_EL1,	HDFGRTR2, nSPMID, 0),
+	SR_FGT(SYS_SPMCGCRn_EL1(0),	HDFGRTR2, nSPMID, 0),
+	SR_FGT(SYS_SPMCGCRn_EL1(1),	HDFGRTR2, nSPMID, 0),
+	SR_FGT(SYS_SPMIIDR_EL1,		HDFGRTR2, nSPMID, 0),
+	SR_FGT(SYS_SPMCNTENCLR_EL0,	HDFGRTR2, nSPMCNTEN, 0),
+	SR_FGT(SYS_SPMCNTENSET_EL0,	HDFGRTR2, nSPMCNTEN, 0),
+	SR_FGT(SYS_SPMCR_EL0,		HDFGRTR2, nSPMCR_EL0, 0),
+	SR_FGT(SYS_SPMDEVAFF_EL1,	HDFGRTR2, nSPMDEVAFF_EL1, 0),
+	/*
+	 * We have up to 64 of these registers in ranges of 16, banked via
+	 * SPMSELR_EL0.BANK. We're only concerned with the accessors here,
+	 * not the architectural registers.
+	 */
+	SR_FGT_RANGE(SYS_SPMEVCNTRn_EL0(0),
+		     SYS_SPMEVCNTRn_EL0(15),
+		     HDFGRTR2, nSPMEVCNTRn_EL0, 0),
+	SR_FGT_RANGE(SYS_SPMEVFILT2Rn_EL0(0),
+		     SYS_SPMEVFILT2Rn_EL0(15),
+		     HDFGRTR2, nSPMEVTYPERn_EL0, 0),
+	SR_FGT_RANGE(SYS_SPMEVFILTRn_EL0(0),
+		     SYS_SPMEVFILTRn_EL0(15),
+		     HDFGRTR2, nSPMEVTYPERn_EL0, 0),
+	SR_FGT_RANGE(SYS_SPMEVTYPERn_EL0(0),
+		     SYS_SPMEVTYPERn_EL0(15),
+		     HDFGRTR2, nSPMEVTYPERn_EL0, 0),
+	SR_FGT(SYS_SPMINTENCLR_EL1,	HDFGRTR2, nSPMINTEN, 0),
+	SR_FGT(SYS_SPMINTENSET_EL1,	HDFGRTR2, nSPMINTEN, 0),
+	SR_FGT(SYS_SPMOVSCLR_EL0,	HDFGRTR2, nSPMOVS, 0),
+	SR_FGT(SYS_SPMOVSSET_EL0,	HDFGRTR2, nSPMOVS, 0),
+	SR_FGT(SYS_SPMSCR_EL1,		HDFGRTR2, nSPMSCR_EL1, 0),
+	SR_FGT(SYS_SPMSELR_EL0,		HDFGRTR2, nSPMSELR_EL0, 0),
+	SR_FGT(SYS_TRCITECR_EL1,	HDFGRTR2, nTRCITECR_EL1, 0),
+	SR_FGT(SYS_PMBMAR_EL1,		HDFGRTR2, nPMBMAR_EL1, 0),
+	SR_FGT(SYS_PMSDSFR_EL1,		HDFGRTR2, nPMSDSFR_EL1, 0),
+	SR_FGT(SYS_TRBMPAM_EL1,		HDFGRTR2, nTRBMPAM_EL1, 0),
+
 	/*
 	 * HDFGWTR_EL2
 	 *
@@ -1938,12 +1975,19 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	 * read-side mappings, and only the write-side mappings that
 	 * differ from the read side, and the trap handler will pick
 	 * the correct shadow register based on the access type.
+	 *
+	 * Same model applies to the FEAT_FGT2 registers.
 	 */
 	SR_FGT(SYS_TRFCR_EL1,		HDFGWTR, TRFCR_EL1, 1),
 	SR_FGT(SYS_TRCOSLAR,		HDFGWTR, TRCOSLAR, 1),
 	SR_FGT(SYS_PMCR_EL0,		HDFGWTR, PMCR_EL0, 1),
 	SR_FGT(SYS_PMSWINC_EL0,		HDFGWTR, PMSWINC_EL0, 1),
 	SR_FGT(SYS_OSLAR_EL1,		HDFGWTR, OSLAR_EL1, 1),
+
+	/* HDFGWTR2_EL2 */
+	SR_FGT(SYS_PMZR_EL0,		HDFGWTR2, nPMZR_EL0, 0),
+	SR_FGT(SYS_SPMZR_EL0,		HDFGWTR2, nSPMEVCNTRn_EL0, 0),
+
 	/*
 	 * HAFGRTR_EL2
 	 */
@@ -1989,6 +2033,20 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
 	SR_FGT(SYS_AMEVCNTR0_EL0(0),	HAFGRTR, AMEVCNTR00_EL0, 1),
 };
 
+/*
+ * Additional FGTs that do not fire with ESR_EL2.EC==0x18. This table
+ * isn't used for exception routing, but only as a promise that the
+ * trap is handled somewhere else.
+ */
+static const union trap_config non_0x18_fgt[] __initconst = {
+	FGT(HFGITR, PSBCSYNC, 1),
+	FGT(HFGITR, nGCSSTR_EL1, 0),
+	FGT(HFGITR, SVC_EL1, 1),
+	FGT(HFGITR, SVC_EL0, 1),
+	FGT(HFGITR, ERET, 1),
+	FGT(HFGITR2, TSBCSYNC, 1),
+};
+
 static union trap_config get_trap_config(u32 sysreg)
 {
 	return (union trap_config) {
@@ -2033,6 +2091,130 @@ static u32 encoding_next(u32 encoding)
 	return sys_reg(op0 + 1, 0, 0, 0, 0);
 }
 
+#define FGT_MASKS(__n, __m)						\
+	struct fgt_masks __n = { .str = #__m, .res0 = __m, }
+
+FGT_MASKS(hfgrtr_masks, HFGRTR_EL2_RES0);
+FGT_MASKS(hfgwtr_masks, HFGWTR_EL2_RES0);
+FGT_MASKS(hfgitr_masks, HFGITR_EL2_RES0);
+FGT_MASKS(hdfgrtr_masks, HDFGRTR_EL2_RES0);
+FGT_MASKS(hdfgwtr_masks, HDFGWTR_EL2_RES0);
+FGT_MASKS(hafgrtr_masks, HAFGRTR_EL2_RES0);
+FGT_MASKS(hfgrtr2_masks, HFGRTR2_EL2_RES0);
+FGT_MASKS(hfgwtr2_masks, HFGWTR2_EL2_RES0);
+FGT_MASKS(hfgitr2_masks, HFGITR2_EL2_RES0);
+FGT_MASKS(hdfgrtr2_masks, HDFGRTR2_EL2_RES0);
+FGT_MASKS(hdfgwtr2_masks, HDFGWTR2_EL2_RES0);
+
+static __init bool aggregate_fgt(union trap_config tc)
+{
+	struct fgt_masks *rmasks, *wmasks;
+
+	switch (tc.fgt) {
+	case HFGRTR_GROUP:
+		rmasks = &hfgrtr_masks;
+		wmasks = &hfgwtr_masks;
+		break;
+	case HDFGRTR_GROUP:
+		rmasks = &hdfgrtr_masks;
+		wmasks = &hdfgwtr_masks;
+		break;
+	case HAFGRTR_GROUP:
+		rmasks = &hafgrtr_masks;
+		wmasks = NULL;
+		break;
+	case HFGITR_GROUP:
+		rmasks = &hfgitr_masks;
+		wmasks = NULL;
+		break;
+	case HFGRTR2_GROUP:
+		rmasks = &hfgrtr2_masks;
+		wmasks = &hfgwtr2_masks;
+		break;
+	case HDFGRTR2_GROUP:
+		rmasks = &hdfgrtr2_masks;
+		wmasks = &hdfgwtr2_masks;
+		break;
+	case HFGITR2_GROUP:
+		rmasks = &hfgitr2_masks;
+		wmasks = NULL;
+		break;
+	}
+
+	/*
+	 * A bit can be reserved in either the R or W register, but
+	 * not both.
+	 */
+	if ((BIT(tc.bit) & rmasks->res0) &&
+	    (!wmasks || (BIT(tc.bit) & wmasks->res0)))
+		return false;
+
+	if (tc.pol)
+		rmasks->mask |= BIT(tc.bit) & ~rmasks->res0;
+	else
+		rmasks->nmask |= BIT(tc.bit) & ~rmasks->res0;
+
+	if (wmasks) {
+		if (tc.pol)
+			wmasks->mask |= BIT(tc.bit) & ~wmasks->res0;
+		else
+			wmasks->nmask |= BIT(tc.bit) & ~wmasks->res0;
+	}
+
+	return true;
+}
+
+static __init int check_fgt_masks(struct fgt_masks *masks)
+{
+	unsigned long duplicate = masks->mask & masks->nmask;
+	u64 res0 = masks->res0;
+	int ret = 0;
+
+	if (duplicate) {
+		int i;
+
+		for_each_set_bit(i, &duplicate, 64) {
+			kvm_err("%s[%d] bit has both polarities\n",
+				masks->str, i);
+		}
+
+		ret = -EINVAL;
+	}
+
+	masks->res0 = ~(masks->mask | masks->nmask);
+	if (masks->res0 != res0)
+		kvm_info("Implicit %s = %016llx, expecting %016llx\n",
+			 masks->str, masks->res0, res0);
+
+	return ret;
+}
+
+static __init int check_all_fgt_masks(int ret)
+{
+	static struct fgt_masks * const masks[] __initconst = {
+		&hfgrtr_masks,
+		&hfgwtr_masks,
+		&hfgitr_masks,
+		&hdfgrtr_masks,
+		&hdfgwtr_masks,
+		&hafgrtr_masks,
+		&hfgrtr2_masks,
+		&hfgwtr2_masks,
+		&hfgitr2_masks,
+		&hdfgrtr2_masks,
+		&hdfgwtr2_masks,
+	};
+	int err = 0;
+
+	for (int i = 0; i < ARRAY_SIZE(masks); i++)
+		err |= check_fgt_masks(masks[i]);
+
+	return ret ?: err;
+}
+
+#define for_each_encoding_in(__x, __s, __e)	\
+	for (u32 __x = __s; __x <= __e; __x = encoding_next(__x))
+
 int __init populate_nv_trap_config(void)
 {
 	int ret = 0;
@@ -2041,6 +2223,7 @@ int __init populate_nv_trap_config(void)
 	BUILD_BUG_ON(__NR_CGT_GROUP_IDS__ > BIT(TC_CGT_BITS));
 	BUILD_BUG_ON(__NR_FGT_GROUP_IDS__ > BIT(TC_FGT_BITS));
 	BUILD_BUG_ON(__NR_FG_FILTER_IDS__ > BIT(TC_FGF_BITS));
+	BUILD_BUG_ON(__HCRX_EL2_MASK & __HCRX_EL2_nMASK);
 
 	for (int i = 0; i < ARRAY_SIZE(encoding_to_cgt); i++) {
 		const struct encoding_to_trap_config *cgt = &encoding_to_cgt[i];
@@ -2051,7 +2234,7 @@ int __init populate_nv_trap_config(void)
 			ret = -EINVAL;
 		}
 
-		for (u32 enc = cgt->encoding; enc <= cgt->end; enc = encoding_next(enc)) {
+		for_each_encoding_in(enc, cgt->encoding, cgt->end) {
 			prev = xa_store(&sr_forward_xa, enc,
 					xa_mk_value(cgt->tc.val), GFP_KERNEL);
 			if (prev && !xa_is_err(prev)) {
@@ -2066,6 +2249,10 @@ int __init populate_nv_trap_config(void)
 		}
 	}
 
+	if (__HCRX_EL2_RES0 != HCRX_EL2_RES0)
+		kvm_info("Sanitised HCR_EL2_RES0 = %016llx, expecting %016llx\n",
+			 __HCRX_EL2_RES0, HCRX_EL2_RES0);
+
 	kvm_info("nv: %ld coarse grained trap handlers\n",
 		 ARRAY_SIZE(encoding_to_cgt));
 
@@ -2082,23 +2269,39 @@ int __init populate_nv_trap_config(void)
 			print_nv_trap_error(fgt, "Invalid FGT", ret);
 		}
 
-		tc = get_trap_config(fgt->encoding);
+		for_each_encoding_in(enc, fgt->encoding, fgt->end) {
+			tc = get_trap_config(enc);
 
-		if (tc.fgt) {
-			ret = -EINVAL;
-			print_nv_trap_error(fgt, "Duplicate FGT", ret);
-		}
+			if (tc.fgt) {
+				ret = -EINVAL;
+				print_nv_trap_error(fgt, "Duplicate FGT", ret);
+			}
 
-		tc.val |= fgt->tc.val;
-		prev = xa_store(&sr_forward_xa, fgt->encoding,
-				xa_mk_value(tc.val), GFP_KERNEL);
+			tc.val |= fgt->tc.val;
+			prev = xa_store(&sr_forward_xa, enc,
+					xa_mk_value(tc.val), GFP_KERNEL);
 
-		if (xa_is_err(prev)) {
-			ret = xa_err(prev);
-			print_nv_trap_error(fgt, "Failed FGT insertion", ret);
+			if (xa_is_err(prev)) {
+				ret = xa_err(prev);
+				print_nv_trap_error(fgt, "Failed FGT insertion", ret);
+			}
+
+			if (!aggregate_fgt(tc)) {
+				ret = -EINVAL;
+				print_nv_trap_error(fgt, "FGT bit is reserved", ret);
+			}
 		}
 	}
 
+	for (int i = 0; i < ARRAY_SIZE(non_0x18_fgt); i++) {
+		if (!aggregate_fgt(non_0x18_fgt[i])) {
+			ret = -EINVAL;
+			kvm_err("non_0x18_fgt[%d] is reserved\n", i);
+		}
+	}
+
+	ret = check_all_fgt_masks(ret);
+
 	kvm_info("nv: %ld fine grained trap handlers\n",
 		 ARRAY_SIZE(encoding_to_fgt));
 
@@ -2215,11 +2418,11 @@ static u64 kvm_get_sysreg_res0(struct kvm *kvm, enum vcpu_sysreg sr)
 	return masks->mask[sr - __VNCR_START__].res0;
 }
 
-static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read,
-			  u64 val, const union trap_config tc)
+static bool check_fgt_bit(struct kvm_vcpu *vcpu, enum vcpu_sysreg sr,
+			  const union trap_config tc)
 {
 	struct kvm *kvm = vcpu->kvm;
-	enum vcpu_sysreg sr;
+	u64 val;
 
 	/*
 	 * KVM doesn't know about any FGTs that apply to the host, and hopefully
@@ -2228,6 +2431,8 @@ static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read,
 	if (is_hyp_ctxt(vcpu))
 		return false;
 
+	val = __vcpu_sys_reg(vcpu, sr);
+
 	if (tc.pol)
 		return (val & BIT(tc.bit));
 
@@ -2242,38 +2447,17 @@ static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read,
 	if (val & BIT(tc.bit))
 		return false;
 
-	switch ((enum fgt_group_id)tc.fgt) {
-	case HFGxTR_GROUP:
-		sr = is_read ? HFGRTR_EL2 : HFGWTR_EL2;
-		break;
-
-	case HDFGRTR_GROUP:
-		sr = is_read ? HDFGRTR_EL2 : HDFGWTR_EL2;
-		break;
-
-	case HAFGRTR_GROUP:
-		sr = HAFGRTR_EL2;
-		break;
-
-	case HFGITR_GROUP:
-		sr = HFGITR_EL2;
-		break;
-
-	default:
-		WARN_ONCE(1, "Unhandled FGT group");
-		return false;
-	}
-
 	return !(kvm_get_sysreg_res0(kvm, sr) & BIT(tc.bit));
 }
 
 bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index)
 {
+	enum vcpu_sysreg fgtreg;
 	union trap_config tc;
 	enum trap_behaviour b;
 	bool is_read;
 	u32 sysreg;
-	u64 esr, val;
+	u64 esr;
 
 	esr = kvm_vcpu_get_esr(vcpu);
 	sysreg = esr_sys64_to_sysreg(esr);
@@ -2319,26 +2503,20 @@ bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index)
 	case __NO_FGT_GROUP__:
 		break;
 
-	case HFGxTR_GROUP:
-		if (is_read)
-			val = __vcpu_sys_reg(vcpu, HFGRTR_EL2);
-		else
-			val = __vcpu_sys_reg(vcpu, HFGWTR_EL2);
+	case HFGRTR_GROUP:
+		fgtreg = is_read ? HFGRTR_EL2 : HFGWTR_EL2;
 		break;
 
 	case HDFGRTR_GROUP:
-		if (is_read)
-			val = __vcpu_sys_reg(vcpu, HDFGRTR_EL2);
-		else
-			val = __vcpu_sys_reg(vcpu, HDFGWTR_EL2);
+		fgtreg = is_read ? HDFGRTR_EL2 : HDFGWTR_EL2;
 		break;
 
 	case HAFGRTR_GROUP:
-		val = __vcpu_sys_reg(vcpu, HAFGRTR_EL2);
+		fgtreg = HAFGRTR_EL2;
 		break;
 
 	case HFGITR_GROUP:
-		val = __vcpu_sys_reg(vcpu, HFGITR_EL2);
+		fgtreg = HFGITR_EL2;
 		switch (tc.fgf) {
 			u64 tmp;
 
@@ -2352,13 +2530,26 @@ bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index)
 		}
 		break;
 
-	case __NR_FGT_GROUP_IDS__:
+	case HFGRTR2_GROUP:
+		fgtreg = is_read ? HFGRTR2_EL2 : HFGWTR2_EL2;
+		break;
+
+	case HDFGRTR2_GROUP:
+		fgtreg = is_read ? HDFGRTR2_EL2 : HDFGWTR2_EL2;
+		break;
+
+	case HFGITR2_GROUP:
+		fgtreg = HFGITR2_EL2;
+		break;
+
+	default:
 		/* Something is really wrong, bail out */
-		WARN_ONCE(1, "__NR_FGT_GROUP_IDS__");
+		WARN_ONCE(1, "Bad FGT group (encoding %08x, config %016llx)\n",
+			  sysreg, tc.val);
 		goto local;
 	}
 
-	if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu, is_read, val, tc))
+	if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu, fgtreg, tc))
 		goto inject;
 
 	b = compute_trap_behaviour(vcpu, tc);

arch/arm64/kvm/handle_exit.c

@@ -299,6 +299,81 @@ static int handle_svc(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int kvm_handle_gcs(struct kvm_vcpu *vcpu)
+{
+	/* We don't expect GCS, so treat it with contempt */
+	if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, GCS, IMP))
+		WARN_ON_ONCE(1);
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+static int handle_other(struct kvm_vcpu *vcpu)
+{
+	bool is_l2 = vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu);
+	u64 hcrx = __vcpu_sys_reg(vcpu, HCRX_EL2);
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	u64 iss = ESR_ELx_ISS(esr);
+	struct kvm *kvm = vcpu->kvm;
+	bool allowed, fwd = false;
+
+	/*
+	 * We only trap for two reasons:
+	 *
+	 * - the feature is disabled, and the only outcome is to
+	 *   generate an UNDEF.
+	 *
+	 * - the feature is enabled, but a NV guest wants to trap the
+	 *   feature used by its L2 guest. We forward the exception in
+	 *   this case.
+	 *
+	 * What we don't expect is to end-up here if the guest is
+	 * expected be be able to directly use the feature, hence the
+	 * WARN_ON below.
+	 */
+	switch (iss) {
+	case ESR_ELx_ISS_OTHER_ST64BV:
+		allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V);
+		if (is_l2)
+			fwd = !(hcrx & HCRX_EL2_EnASR);
+		break;
+	case ESR_ELx_ISS_OTHER_ST64BV0:
+		allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA);
+		if (is_l2)
+			fwd = !(hcrx & HCRX_EL2_EnAS0);
+		break;
+	case ESR_ELx_ISS_OTHER_LDST64B:
+		allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64);
+		if (is_l2)
+			fwd = !(hcrx & HCRX_EL2_EnALS);
+		break;
+	case ESR_ELx_ISS_OTHER_TSBCSYNC:
+		allowed = kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, TRBE_V1P1);
+		if (is_l2)
+			fwd = (__vcpu_sys_reg(vcpu, HFGITR2_EL2) & HFGITR2_EL2_TSBCSYNC);
+		break;
+	case ESR_ELx_ISS_OTHER_PSBCSYNC:
+		allowed = kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P5);
+		if (is_l2)
+			fwd = (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_PSBCSYNC);
+		break;
+	default:
+		/* Clearly, we're missing something. */
+		WARN_ON_ONCE(1);
+		allowed = false;
+	}
+
+	WARN_ON_ONCE(allowed && !fwd);
+
+	if (allowed && fwd)
+		kvm_inject_nested_sync(vcpu, esr);
+	else
+		kvm_inject_undefined(vcpu);
+
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
@@ -308,6 +383,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_CP14_LS]	= kvm_handle_cp14_load_store,
 	[ESR_ELx_EC_CP10_ID]	= kvm_handle_cp10_id,
 	[ESR_ELx_EC_CP14_64]	= kvm_handle_cp14_64,
+	[ESR_ELx_EC_OTHER]	= handle_other,
 	[ESR_ELx_EC_HVC32]	= handle_hvc,
 	[ESR_ELx_EC_SMC32]	= handle_smc,
 	[ESR_ELx_EC_HVC64]	= handle_hvc,
@@ -325,6 +401,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_BRK64]	= kvm_handle_guest_debug,
 	[ESR_ELx_EC_FP_ASIMD]	= kvm_handle_fpasimd,
 	[ESR_ELx_EC_PAC]	= kvm_handle_ptrauth,
+	[ESR_ELx_EC_GCS]	= kvm_handle_gcs,
 };
 
 static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -65,12 +65,56 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	}
 }
 
+#define reg_to_fgt_masks(reg)						\
+	({								\
+		struct fgt_masks *m;					\
+		switch(reg) {						\
+		case HFGRTR_EL2:					\
+			m = &hfgrtr_masks;				\
+			break;						\
+		case HFGWTR_EL2:					\
+			m = &hfgwtr_masks;				\
+			break;						\
+		case HFGITR_EL2:					\
+			m = &hfgitr_masks;				\
+			break;						\
+		case HDFGRTR_EL2:					\
+			m = &hdfgrtr_masks;				\
+			break;						\
+		case HDFGWTR_EL2:					\
+			m = &hdfgwtr_masks;				\
+			break;						\
+		case HAFGRTR_EL2:					\
+			m = &hafgrtr_masks;				\
+			break;						\
+		case HFGRTR2_EL2:					\
+			m = &hfgrtr2_masks;				\
+			break;						\
+		case HFGWTR2_EL2:					\
+			m = &hfgwtr2_masks;				\
+			break;						\
+		case HFGITR2_EL2:					\
+			m = &hfgitr2_masks;				\
+			break;						\
+		case HDFGRTR2_EL2:					\
+			m = &hdfgrtr2_masks;				\
+			break;						\
+		case HDFGWTR2_EL2:					\
+			m = &hdfgwtr2_masks;				\
+			break;						\
+		default:						\
+			BUILD_BUG_ON(1);				\
+		}							\
+									\
+		m;							\
+	})
+
 #define compute_clr_set(vcpu, reg, clr, set)				\
 	do {								\
-		u64 hfg;						\
-		hfg = __vcpu_sys_reg(vcpu, reg) & ~__ ## reg ## _RES0;	\
-		set |= hfg & __ ## reg ## _MASK; 			\
-		clr |= ~hfg & __ ## reg ## _nMASK; 			\
+		u64 hfg = __vcpu_sys_reg(vcpu, reg);			\
+		struct fgt_masks *m = reg_to_fgt_masks(reg);		\
+		set |= hfg & m->mask;					\
+		clr |= ~hfg & m->nmask;					\
 	} while(0)
 
 #define reg_to_fgt_group_id(reg)					\
@@ -79,7 +123,7 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 		switch(reg) {						\
 		case HFGRTR_EL2:					\
 		case HFGWTR_EL2:					\
-			id = HFGxTR_GROUP;				\
+			id = HFGRTR_GROUP;				\
 			break;						\
 		case HFGITR_EL2:					\
 			id = HFGITR_GROUP;				\
@@ -91,6 +135,17 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 		case HAFGRTR_EL2:					\
 			id = HAFGRTR_GROUP;				\
 			break;						\
+		case HFGRTR2_EL2:					\
+		case HFGWTR2_EL2:					\
+			id = HFGRTR2_GROUP;				\
+			break;						\
+		case HFGITR2_EL2:					\
+			id = HFGITR2_GROUP;				\
+			break;						\
+		case HDFGRTR2_EL2:					\
+		case HDFGWTR2_EL2:					\
+			id = HDFGRTR2_GROUP;				\
+			break;						\
 		default:						\
 			BUILD_BUG_ON(1);				\
 		}							\
@@ -101,13 +156,16 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 #define compute_undef_clr_set(vcpu, kvm, reg, clr, set)			\
 	do {								\
 		u64 hfg = kvm->arch.fgu[reg_to_fgt_group_id(reg)];	\
-		set |= hfg & __ ## reg ## _MASK;			\
-		clr |= hfg & __ ## reg ## _nMASK; 			\
+		struct fgt_masks *m = reg_to_fgt_masks(reg);		\
+		set |= hfg & m->mask;					\
+		clr |= hfg & m->nmask;					\
 	} while(0)
 
 #define update_fgt_traps_cs(hctxt, vcpu, kvm, reg, clr, set)		\
 	do {								\
-		u64 c = 0, s = 0;					\
+		struct fgt_masks *m = reg_to_fgt_masks(reg);		\
+		u64 c = clr, s = set;					\
+		u64 val;						\
 									\
 		ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg);	\
 		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))		\
@@ -115,30 +173,15 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 									\
 		compute_undef_clr_set(vcpu, kvm, reg, c, s);		\
 									\
-		s |= set;						\
-		c |= clr;						\
-		if (c || s) {						\
-			u64 val = __ ## reg ## _nMASK;			\
-			val |= s;					\
-			val &= ~c;					\
-			write_sysreg_s(val, SYS_ ## reg);		\
-		}							\
+		val = m->nmask;						\
+		val |= s;						\
+		val &= ~c;						\
+		write_sysreg_s(val, SYS_ ## reg);			\
 	} while(0)
 
 #define update_fgt_traps(hctxt, vcpu, kvm, reg)		\
 	update_fgt_traps_cs(hctxt, vcpu, kvm, reg, 0, 0)
 
-/*
- * Validate the fine grain trap masks.
- * Check that the masks do not overlap and that all bits are accounted for.
- */
-#define CHECK_FGT_MASKS(reg)							\
-	do {									\
-		BUILD_BUG_ON((__ ## reg ## _MASK) & (__ ## reg ## _nMASK));	\
-		BUILD_BUG_ON(~((__ ## reg ## _RES0) ^ (__ ## reg ## _MASK) ^	\
-			       (__ ## reg ## _nMASK)));				\
-	} while(0)
-
 static inline bool cpu_has_amu(void)
 {
        u64 pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
@@ -152,56 +195,60 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 
-	CHECK_FGT_MASKS(HFGRTR_EL2);
-	CHECK_FGT_MASKS(HFGWTR_EL2);
-	CHECK_FGT_MASKS(HFGITR_EL2);
-	CHECK_FGT_MASKS(HDFGRTR_EL2);
-	CHECK_FGT_MASKS(HDFGWTR_EL2);
-	CHECK_FGT_MASKS(HAFGRTR_EL2);
-	CHECK_FGT_MASKS(HCRX_EL2);
-
 	if (!cpus_have_final_cap(ARM64_HAS_FGT))
 		return;
 
 	update_fgt_traps(hctxt, vcpu, kvm, HFGRTR_EL2);
 	update_fgt_traps_cs(hctxt, vcpu, kvm, HFGWTR_EL2, 0,
 			    cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38) ?
-			    HFGxTR_EL2_TCR_EL1_MASK : 0);
+			    HFGWTR_EL2_TCR_EL1_MASK : 0);
 	update_fgt_traps(hctxt, vcpu, kvm, HFGITR_EL2);
 	update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR_EL2);
 	update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR_EL2);
 
 	if (cpu_has_amu())
 		update_fgt_traps(hctxt, vcpu, kvm, HAFGRTR_EL2);
+
+	if (!cpus_have_final_cap(ARM64_HAS_FGT2))
+	    return;
+
+	update_fgt_traps(hctxt, vcpu, kvm, HFGRTR2_EL2);
+	update_fgt_traps(hctxt, vcpu, kvm, HFGWTR2_EL2);
+	update_fgt_traps(hctxt, vcpu, kvm, HFGITR2_EL2);
+	update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR2_EL2);
+	update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR2_EL2);
 }
 
-#define __deactivate_fgt(htcxt, vcpu, kvm, reg)				\
+#define __deactivate_fgt(htcxt, vcpu, reg)				\
 	do {								\
-		if ((vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) ||	\
-		    kvm->arch.fgu[reg_to_fgt_group_id(reg)])		\
-			write_sysreg_s(ctxt_sys_reg(hctxt, reg),	\
-				       SYS_ ## reg);			\
+		write_sysreg_s(ctxt_sys_reg(hctxt, reg),		\
+			       SYS_ ## reg);				\
 	} while(0)
 
 static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
-	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 
 	if (!cpus_have_final_cap(ARM64_HAS_FGT))
 		return;
 
-	__deactivate_fgt(hctxt, vcpu, kvm, HFGRTR_EL2);
-	if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
-		write_sysreg_s(ctxt_sys_reg(hctxt, HFGWTR_EL2), SYS_HFGWTR_EL2);
-	else
-		__deactivate_fgt(hctxt, vcpu, kvm, HFGWTR_EL2);
-	__deactivate_fgt(hctxt, vcpu, kvm, HFGITR_EL2);
-	__deactivate_fgt(hctxt, vcpu, kvm, HDFGRTR_EL2);
-	__deactivate_fgt(hctxt, vcpu, kvm, HDFGWTR_EL2);
+	__deactivate_fgt(hctxt, vcpu, HFGRTR_EL2);
+	__deactivate_fgt(hctxt, vcpu, HFGWTR_EL2);
+	__deactivate_fgt(hctxt, vcpu, HFGITR_EL2);
+	__deactivate_fgt(hctxt, vcpu, HDFGRTR_EL2);
+	__deactivate_fgt(hctxt, vcpu, HDFGWTR_EL2);
 
 	if (cpu_has_amu())
-		__deactivate_fgt(hctxt, vcpu, kvm, HAFGRTR_EL2);
+		__deactivate_fgt(hctxt, vcpu, HAFGRTR_EL2);
+
+	if (!cpus_have_final_cap(ARM64_HAS_FGT2))
+	    return;
+
+	__deactivate_fgt(hctxt, vcpu, HFGRTR2_EL2);
+	__deactivate_fgt(hctxt, vcpu, HFGWTR2_EL2);
+	__deactivate_fgt(hctxt, vcpu, HFGITR2_EL2);
+	__deactivate_fgt(hctxt, vcpu, HDFGRTR2_EL2);
+	__deactivate_fgt(hctxt, vcpu, HDFGWTR2_EL2);
 }
 
 static inline void  __activate_traps_mpam(struct kvm_vcpu *vcpu)
@@ -261,12 +308,9 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 	if (cpus_have_final_cap(ARM64_HAS_HCX)) {
 		u64 hcrx = vcpu->arch.hcrx_el2;
 		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
-			u64 clr = 0, set = 0;
-
-			compute_clr_set(vcpu, HCRX_EL2, clr, set);
-
-			hcrx |= set;
-			hcrx &= ~clr;
+			u64 val = __vcpu_sys_reg(vcpu, HCRX_EL2);
+			hcrx |= val & __HCRX_EL2_MASK;
+			hcrx &= ~(~val & __HCRX_EL2_nMASK);
 		}
 
 		write_sysreg_s(hcrx, SYS_HCRX_EL2);

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -33,6 +33,18 @@ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data);
 DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
 
+struct fgt_masks hfgrtr_masks;
+struct fgt_masks hfgwtr_masks;
+struct fgt_masks hfgitr_masks;
+struct fgt_masks hdfgrtr_masks;
+struct fgt_masks hdfgwtr_masks;
+struct fgt_masks hafgrtr_masks;
+struct fgt_masks hfgrtr2_masks;
+struct fgt_masks hfgwtr2_masks;
+struct fgt_masks hfgitr2_masks;
+struct fgt_masks hdfgrtr2_masks;
+struct fgt_masks hdfgwtr2_masks;
+
 extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc);
 
 static void __activate_cptr_traps(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/vgic-v3-sr.c

@@ -1052,11 +1052,11 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
 	switch (sysreg) {
 	case SYS_ICC_IGRPEN0_EL1:
 		if (is_read &&
-		    (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+		    (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1))
 			return true;
 
 		if (!is_read &&
-		    (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+		    (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1))
 			return true;
 
 		fallthrough;
@@ -1073,11 +1073,11 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
 
 	case SYS_ICC_IGRPEN1_EL1:
 		if (is_read &&
-		    (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+		    (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1))
 			return true;
 
 		if (!is_read &&
-		    (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+		    (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1))
 			return true;
 
 		fallthrough;

arch/arm64/kvm/nested.c

@@ -1018,216 +1018,49 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
 	set_sysreg_masks(kvm, VMPIDR_EL2, res0, res1);
 
 	/* HCR_EL2 */
-	res0 = BIT(48);
-	res1 = HCR_RW;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, TWED, IMP))
-		res0 |= GENMASK(63, 59);
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, MTE, MTE2))
-		res0 |= (HCR_TID5 | HCR_DCT | HCR_ATA);
-	if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, TTLBxS))
-		res0 |= (HCR_TTLBIS | HCR_TTLBOS);
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) &&
-	    !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2))
-		res0 |= HCR_ENSCXT;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, IMP))
-		res0 |= (HCR_TOCU | HCR_TICAB | HCR_TID4);
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1))
-		res0 |= HCR_AMVOFFEN;
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1))
-		res0 |= HCR_FIEN;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, FWB, IMP))
-		res0 |= HCR_FWB;
-	/* Implementation choice: NV2 is the only supported config */
-	if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
-		res0 |= (HCR_NV2 | HCR_NV | HCR_AT);
-	if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, NI))
-		res0 |= HCR_NV1;
-	if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
-	      kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
-		res0 |= (HCR_API | HCR_APK);
-	if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TME, IMP))
-		res0 |= BIT(39);
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP))
-		res0 |= (HCR_TEA | HCR_TERR);
-	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP))
-		res0 |= HCR_TLOR;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP))
-		res0 |= HCR_E2H;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, IMP))
-		res1 |= HCR_E2H;
+	get_reg_fixed_bits(kvm, HCR_EL2, &res0, &res1);
 	set_sysreg_masks(kvm, HCR_EL2, res0, res1);
 
 	/* HCRX_EL2 */
-	res0 = HCRX_EL2_RES0;
-	res1 = HCRX_EL2_RES1;
-	if (!kvm_has_feat(kvm, ID_AA64ISAR3_EL1, PACM, TRIVIAL_IMP))
-		res0 |= HCRX_EL2_PACMEn;
-	if (!kvm_has_feat(kvm, ID_AA64PFR2_EL1, FPMR, IMP))
-		res0 |= HCRX_EL2_EnFPM;
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
-		res0 |= HCRX_EL2_GCSEn;
-	if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, SYSREG_128, IMP))
-		res0 |= HCRX_EL2_EnIDCP128;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ADERR, DEV_ASYNC))
-		res0 |= (HCRX_EL2_EnSDERR | HCRX_EL2_EnSNERR);
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, DF2, IMP))
-		res0 |= HCRX_EL2_TMEA;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, D128, IMP))
-		res0 |= HCRX_EL2_D128En;
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
-		res0 |= HCRX_EL2_PTTWI;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SCTLRX, IMP))
-		res0 |= HCRX_EL2_SCTLR2En;
-	if (!kvm_has_tcr2(kvm))
-		res0 |= HCRX_EL2_TCR2En;
-	if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
-		res0 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);
-	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, CMOW, IMP))
-		res0 |= HCRX_EL2_CMOW;
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, NMI, IMP))
-		res0 |= (HCRX_EL2_VFNMI | HCRX_EL2_VINMI | HCRX_EL2_TALLINT);
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP) ||
-	    !(read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS))
-		res0 |= HCRX_EL2_SMPME;
-	if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
-		res0 |= (HCRX_EL2_FGTnXS | HCRX_EL2_FnXS);
-	if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V))
-		res0 |= HCRX_EL2_EnASR;
-	if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64))
-		res0 |= HCRX_EL2_EnALS;
-	if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA))
-		res0 |= HCRX_EL2_EnAS0;
+	get_reg_fixed_bits(kvm, HCRX_EL2, &res0, &res1);
 	set_sysreg_masks(kvm, HCRX_EL2, res0, res1);
 
 	/* HFG[RW]TR_EL2 */
-	res0 = res1 = 0;
-	if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
-	      kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
-		res0 |= (HFGxTR_EL2_APDAKey | HFGxTR_EL2_APDBKey |
-			 HFGxTR_EL2_APGAKey | HFGxTR_EL2_APIAKey |
-			 HFGxTR_EL2_APIBKey);
-	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP))
-		res0 |= (HFGxTR_EL2_LORC_EL1 | HFGxTR_EL2_LOREA_EL1 |
-			 HFGxTR_EL2_LORID_EL1 | HFGxTR_EL2_LORN_EL1 |
-			 HFGxTR_EL2_LORSA_EL1);
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) &&
-	    !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2))
-		res0 |= (HFGxTR_EL2_SCXTNUM_EL1 | HFGxTR_EL2_SCXTNUM_EL0);
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP))
-		res0 |= HFGxTR_EL2_ICC_IGRPENn_EL1;
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP))
-		res0 |= (HFGxTR_EL2_ERRIDR_EL1 | HFGxTR_EL2_ERRSELR_EL1 |
-			 HFGxTR_EL2_ERXFR_EL1 | HFGxTR_EL2_ERXCTLR_EL1 |
-			 HFGxTR_EL2_ERXSTATUS_EL1 | HFGxTR_EL2_ERXMISCn_EL1 |
-			 HFGxTR_EL2_ERXPFGF_EL1 | HFGxTR_EL2_ERXPFGCTL_EL1 |
-			 HFGxTR_EL2_ERXPFGCDN_EL1 | HFGxTR_EL2_ERXADDR_EL1);
-	if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA))
-		res0 |= HFGxTR_EL2_nACCDATA_EL1;
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
-		res0 |= (HFGxTR_EL2_nGCS_EL0 | HFGxTR_EL2_nGCS_EL1);
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP))
-		res0 |= (HFGxTR_EL2_nSMPRI_EL1 | HFGxTR_EL2_nTPIDR2_EL0);
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
-		res0 |= HFGxTR_EL2_nRCWMASK_EL1;
-	if (!kvm_has_s1pie(kvm))
-		res0 |= (HFGxTR_EL2_nPIRE0_EL1 | HFGxTR_EL2_nPIR_EL1);
-	if (!kvm_has_s1poe(kvm))
-		res0 |= (HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nPOR_EL1);
-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
-		res0 |= HFGxTR_EL2_nS2POR_EL1;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, AIE, IMP))
-		res0 |= (HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nAMAIR2_EL1);
-	set_sysreg_masks(kvm, HFGRTR_EL2, res0 | __HFGRTR_EL2_RES0, res1);
-	set_sysreg_masks(kvm, HFGWTR_EL2, res0 | __HFGWTR_EL2_RES0, res1);
+	get_reg_fixed_bits(kvm, HFGRTR_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HFGRTR_EL2, res0, res1);
+	get_reg_fixed_bits(kvm, HFGWTR_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HFGWTR_EL2, res0, res1);
 
 	/* HDFG[RW]TR_EL2 */
-	res0 = res1 = 0;
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DoubleLock, IMP))
-		res0 |= HDFGRTR_EL2_OSDLR_EL1;
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP))
-		res0 |= (HDFGRTR_EL2_PMEVCNTRn_EL0 | HDFGRTR_EL2_PMEVTYPERn_EL0 |
-			 HDFGRTR_EL2_PMCCFILTR_EL0 | HDFGRTR_EL2_PMCCNTR_EL0 |
-			 HDFGRTR_EL2_PMCNTEN | HDFGRTR_EL2_PMINTEN |
-			 HDFGRTR_EL2_PMOVS | HDFGRTR_EL2_PMSELR_EL0 |
-			 HDFGRTR_EL2_PMMIR_EL1 | HDFGRTR_EL2_PMUSERENR_EL0 |
-			 HDFGRTR_EL2_PMCEIDn_EL0);
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP))
-		res0 |= (HDFGRTR_EL2_PMBLIMITR_EL1 | HDFGRTR_EL2_PMBPTR_EL1 |
-			 HDFGRTR_EL2_PMBSR_EL1 | HDFGRTR_EL2_PMSCR_EL1 |
-			 HDFGRTR_EL2_PMSEVFR_EL1 | HDFGRTR_EL2_PMSFCR_EL1 |
-			 HDFGRTR_EL2_PMSICR_EL1 | HDFGRTR_EL2_PMSIDR_EL1 |
-			 HDFGRTR_EL2_PMSIRR_EL1 | HDFGRTR_EL2_PMSLATFR_EL1 |
-			 HDFGRTR_EL2_PMBIDR_EL1);
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP))
-		res0 |= (HDFGRTR_EL2_TRC | HDFGRTR_EL2_TRCAUTHSTATUS |
-			 HDFGRTR_EL2_TRCAUXCTLR | HDFGRTR_EL2_TRCCLAIM |
-			 HDFGRTR_EL2_TRCCNTVRn | HDFGRTR_EL2_TRCID |
-			 HDFGRTR_EL2_TRCIMSPECn | HDFGRTR_EL2_TRCOSLSR |
-			 HDFGRTR_EL2_TRCPRGCTLR | HDFGRTR_EL2_TRCSEQSTR |
-			 HDFGRTR_EL2_TRCSSCSRn | HDFGRTR_EL2_TRCSTATR |
-			 HDFGRTR_EL2_TRCVICTLR);
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP))
-		res0 |= (HDFGRTR_EL2_TRBBASER_EL1 | HDFGRTR_EL2_TRBIDR_EL1 |
-			 HDFGRTR_EL2_TRBLIMITR_EL1 | HDFGRTR_EL2_TRBMAR_EL1 |
-			 HDFGRTR_EL2_TRBPTR_EL1 | HDFGRTR_EL2_TRBSR_EL1 |
-			 HDFGRTR_EL2_TRBTRG_EL1);
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP))
-		res0 |= (HDFGRTR_EL2_nBRBIDR | HDFGRTR_EL2_nBRBCTL |
-			 HDFGRTR_EL2_nBRBDATA);
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P2))
-		res0 |= HDFGRTR_EL2_nPMSNEVFR_EL1;
-	set_sysreg_masks(kvm, HDFGRTR_EL2, res0 | HDFGRTR_EL2_RES0, res1);
-
-	/* Reuse the bits from the read-side and add the write-specific stuff */
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP))
-		res0 |= (HDFGWTR_EL2_PMCR_EL0 | HDFGWTR_EL2_PMSWINC_EL0);
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP))
-		res0 |= HDFGWTR_EL2_TRCOSLAR;
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP))
-		res0 |= HDFGWTR_EL2_TRFCR_EL1;
-	set_sysreg_masks(kvm, HFGWTR_EL2, res0 | HDFGWTR_EL2_RES0, res1);
+	get_reg_fixed_bits(kvm, HDFGRTR_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HDFGRTR_EL2, res0, res1);
+	get_reg_fixed_bits(kvm, HDFGWTR_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HDFGWTR_EL2, res0, res1);
 
 	/* HFGITR_EL2 */
-	res0 = HFGITR_EL2_RES0;
-	res1 = HFGITR_EL2_RES1;
-	if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, DPB, DPB2))
-		res0 |= HFGITR_EL2_DCCVADP;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN2))
-		res0 |= (HFGITR_EL2_ATS1E1RP | HFGITR_EL2_ATS1E1WP);
-	if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
-		res0 |= (HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS |
-			 HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS |
-			 HFGITR_EL2_TLBIVAALE1OS | HFGITR_EL2_TLBIVALE1OS |
-			 HFGITR_EL2_TLBIVAAE1OS | HFGITR_EL2_TLBIASIDE1OS |
-			 HFGITR_EL2_TLBIVAE1OS | HFGITR_EL2_TLBIVMALLE1OS);
-	if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
-		res0 |= (HFGITR_EL2_TLBIRVAALE1 | HFGITR_EL2_TLBIRVALE1 |
-			 HFGITR_EL2_TLBIRVAAE1 | HFGITR_EL2_TLBIRVAE1 |
-			 HFGITR_EL2_TLBIRVAALE1IS | HFGITR_EL2_TLBIRVALE1IS |
-			 HFGITR_EL2_TLBIRVAAE1IS | HFGITR_EL2_TLBIRVAE1IS |
-			 HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS |
-			 HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS);
-	if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, IMP))
-		res0 |= (HFGITR_EL2_CFPRCTX | HFGITR_EL2_DVPRCTX |
-			 HFGITR_EL2_CPPRCTX);
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP))
-		res0 |= (HFGITR_EL2_nBRBINJ | HFGITR_EL2_nBRBIALL);
-	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
-		res0 |= (HFGITR_EL2_nGCSPUSHM_EL1 | HFGITR_EL2_nGCSSTR_EL1 |
-			 HFGITR_EL2_nGCSEPP);
-	if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX))
-		res0 |= HFGITR_EL2_COSPRCTX;
-	if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, ATS1A, IMP))
-		res0 |= HFGITR_EL2_ATS1E1A;
+	get_reg_fixed_bits(kvm, HFGITR_EL2, &res0, &res1);
 	set_sysreg_masks(kvm, HFGITR_EL2, res0, res1);
 
 	/* HAFGRTR_EL2 - not a lot to see here */
-	res0 = HAFGRTR_EL2_RES0;
-	res1 = HAFGRTR_EL2_RES1;
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1))
-		res0 |= ~(res0 | res1);
+	get_reg_fixed_bits(kvm, HAFGRTR_EL2, &res0, &res1);
 	set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1);
 
+	/* HFG[RW]TR2_EL2 */
+	get_reg_fixed_bits(kvm, HFGRTR2_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HFGRTR2_EL2, res0, res1);
+	get_reg_fixed_bits(kvm, HFGWTR2_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HFGWTR2_EL2, res0, res1);
+
+	/* HDFG[RW]TR2_EL2 */
+	get_reg_fixed_bits(kvm, HDFGRTR2_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HDFGRTR2_EL2, res0, res1);
+	get_reg_fixed_bits(kvm, HDFGWTR2_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HDFGWTR2_EL2, res0, res1);
+
+	/* HFGITR2_EL2 */
+	get_reg_fixed_bits(kvm, HFGITR2_EL2, &res0, &res1);
+	set_sysreg_masks(kvm, HFGITR2_EL2, res0, res1);
+
 	/* TCR2_EL2 */
 	res0 = TCR2_EL2_RES0;
 	res1 = TCR2_EL2_RES1;

arch/arm64/kvm/sys_regs.c

@@ -5195,65 +5195,13 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
 	if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags))
 		goto out;
 
-	kvm->arch.fgu[HFGxTR_GROUP] = (HFGxTR_EL2_nAMAIR2_EL1		|
-				       HFGxTR_EL2_nMAIR2_EL1		|
-				       HFGxTR_EL2_nS2POR_EL1		|
-				       HFGxTR_EL2_nACCDATA_EL1		|
-				       HFGxTR_EL2_nSMPRI_EL1_MASK	|
-				       HFGxTR_EL2_nTPIDR2_EL0_MASK);
-
-	if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
-		kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_TLBIRVAALE1OS|
-						HFGITR_EL2_TLBIRVALE1OS	|
-						HFGITR_EL2_TLBIRVAAE1OS	|
-						HFGITR_EL2_TLBIRVAE1OS	|
-						HFGITR_EL2_TLBIVAALE1OS	|
-						HFGITR_EL2_TLBIVALE1OS	|
-						HFGITR_EL2_TLBIVAAE1OS	|
-						HFGITR_EL2_TLBIASIDE1OS	|
-						HFGITR_EL2_TLBIVAE1OS	|
-						HFGITR_EL2_TLBIVMALLE1OS);
-
-	if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
-		kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_TLBIRVAALE1	|
-						HFGITR_EL2_TLBIRVALE1	|
-						HFGITR_EL2_TLBIRVAAE1	|
-						HFGITR_EL2_TLBIRVAE1	|
-						HFGITR_EL2_TLBIRVAALE1IS|
-						HFGITR_EL2_TLBIRVALE1IS	|
-						HFGITR_EL2_TLBIRVAAE1IS	|
-						HFGITR_EL2_TLBIRVAE1IS	|
-						HFGITR_EL2_TLBIRVAALE1OS|
-						HFGITR_EL2_TLBIRVALE1OS	|
-						HFGITR_EL2_TLBIRVAAE1OS	|
-						HFGITR_EL2_TLBIRVAE1OS);
-
-	if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, ATS1A, IMP))
-		kvm->arch.fgu[HFGITR_GROUP] |= HFGITR_EL2_ATS1E1A;
-
-	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN2))
-		kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_ATS1E1RP |
-						HFGITR_EL2_ATS1E1WP);
-
-	if (!kvm_has_s1pie(kvm))
-		kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPIRE0_EL1 |
-						HFGxTR_EL2_nPIR_EL1);
-
-	if (!kvm_has_s1poe(kvm))
-		kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPOR_EL1 |
-						HFGxTR_EL2_nPOR_EL0);
-
-	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, IMP))
-		kvm->arch.fgu[HAFGRTR_GROUP] |= ~(HAFGRTR_EL2_RES0 |
-						  HAFGRTR_EL2_RES1);
-
-	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) {
-		kvm->arch.fgu[HDFGRTR_GROUP] |= (HDFGRTR_EL2_nBRBDATA  |
-						 HDFGRTR_EL2_nBRBCTL   |
-						 HDFGRTR_EL2_nBRBIDR);
-		kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_nBRBINJ |
-						HFGITR_EL2_nBRBIALL);
-	}
+	compute_fgu(kvm, HFGRTR_GROUP);
+	compute_fgu(kvm, HFGITR_GROUP);
+	compute_fgu(kvm, HDFGRTR_GROUP);
+	compute_fgu(kvm, HAFGRTR_GROUP);
+	compute_fgu(kvm, HFGRTR2_GROUP);
+	compute_fgu(kvm, HFGITR2_GROUP);
+	compute_fgu(kvm, HDFGRTR2_GROUP);
 
 	set_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags);
 out:
@@ -5311,6 +5259,8 @@ int __init kvm_sys_reg_table_init(void)
 
 	ret = populate_nv_trap_config();
 
+	check_feature_map();
+
 	for (i = 0; !ret && i < ARRAY_SIZE(sys_reg_descs); i++)
 		ret = populate_sysreg_config(sys_reg_descs + i, i);
 

arch/arm64/tools/cpucaps

@@ -28,6 +28,7 @@ HAS_EPAN
 HAS_EVT
 HAS_FPMR
 HAS_FGT
+HAS_FGT2
 HAS_FPSIMD
 HAS_GCS
 HAS_GENERIC_AUTH

tools/arch/arm64/include/asm/sysreg.h

@@ -117,6 +117,7 @@
 
 #define SB_BARRIER_INSN			__SYS_BARRIER_INSN(0, 7, 31)
 
+/* Data cache zero operations */
 #define SYS_DC_ISW			sys_insn(1, 0, 7, 6, 2)
 #define SYS_DC_IGSW			sys_insn(1, 0, 7, 6, 4)
 #define SYS_DC_IGDSW			sys_insn(1, 0, 7, 6, 6)
@@ -153,11 +154,13 @@
 #define SYS_DC_CIGVAC			sys_insn(1, 3, 7, 14, 3)
 #define SYS_DC_CIGDVAC			sys_insn(1, 3, 7, 14, 5)
 
-/* Data cache zero operations */
 #define SYS_DC_ZVA			sys_insn(1, 3, 7, 4, 1)
 #define SYS_DC_GVA			sys_insn(1, 3, 7, 4, 3)
 #define SYS_DC_GZVA			sys_insn(1, 3, 7, 4, 4)
 
+#define SYS_DC_CIVAPS			sys_insn(1, 0, 7, 15, 1)
+#define SYS_DC_CIGDVAPS			sys_insn(1, 0, 7, 15, 5)
+
 /*
  * Automatically generated definitions for system registers, the
  * manual encodings below are in the process of being converted to
@@ -475,6 +478,7 @@
 #define SYS_CNTFRQ_EL0			sys_reg(3, 3, 14, 0, 0)
 
 #define SYS_CNTPCT_EL0			sys_reg(3, 3, 14, 0, 1)
+#define SYS_CNTVCT_EL0			sys_reg(3, 3, 14, 0, 2)
 #define SYS_CNTPCTSS_EL0		sys_reg(3, 3, 14, 0, 5)
 #define SYS_CNTVCTSS_EL0		sys_reg(3, 3, 14, 0, 6)
 
@@ -482,23 +486,36 @@
 #define SYS_CNTP_CTL_EL0		sys_reg(3, 3, 14, 2, 1)
 #define SYS_CNTP_CVAL_EL0		sys_reg(3, 3, 14, 2, 2)
 
+#define SYS_CNTV_TVAL_EL0		sys_reg(3, 3, 14, 3, 0)
 #define SYS_CNTV_CTL_EL0		sys_reg(3, 3, 14, 3, 1)
 #define SYS_CNTV_CVAL_EL0		sys_reg(3, 3, 14, 3, 2)
 
 #define SYS_AARCH32_CNTP_TVAL		sys_reg(0, 0, 14, 2, 0)
 #define SYS_AARCH32_CNTP_CTL		sys_reg(0, 0, 14, 2, 1)
 #define SYS_AARCH32_CNTPCT		sys_reg(0, 0, 0, 14, 0)
+#define SYS_AARCH32_CNTVCT		sys_reg(0, 1, 0, 14, 0)
 #define SYS_AARCH32_CNTP_CVAL		sys_reg(0, 2, 0, 14, 0)
 #define SYS_AARCH32_CNTPCTSS		sys_reg(0, 8, 0, 14, 0)
+#define SYS_AARCH32_CNTVCTSS		sys_reg(0, 9, 0, 14, 0)
 
 #define __PMEV_op2(n)			((n) & 0x7)
 #define __CNTR_CRm(n)			(0x8 | (((n) >> 3) & 0x3))
+#define SYS_PMEVCNTSVRn_EL1(n)		sys_reg(2, 0, 14, __CNTR_CRm(n), __PMEV_op2(n))
 #define SYS_PMEVCNTRn_EL0(n)		sys_reg(3, 3, 14, __CNTR_CRm(n), __PMEV_op2(n))
 #define __TYPER_CRm(n)			(0xc | (((n) >> 3) & 0x3))
 #define SYS_PMEVTYPERn_EL0(n)		sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n))
 
 #define SYS_PMCCFILTR_EL0		sys_reg(3, 3, 14, 15, 7)
 
+#define	SYS_SPMCGCRn_EL1(n)		sys_reg(2, 0, 9, 13, ((n) & 1))
+
+#define __SPMEV_op2(n)			((n) & 0x7)
+#define __SPMEV_crm(p, n)		((((p) & 7) << 1) | (((n) >> 3) & 1))
+#define SYS_SPMEVCNTRn_EL0(n)		sys_reg(2, 3, 14, __SPMEV_crm(0b000, n), __SPMEV_op2(n))
+#define	SYS_SPMEVFILT2Rn_EL0(n)		sys_reg(2, 3, 14, __SPMEV_crm(0b011, n), __SPMEV_op2(n))
+#define	SYS_SPMEVFILTRn_EL0(n)		sys_reg(2, 3, 14, __SPMEV_crm(0b010, n), __SPMEV_op2(n))
+#define	SYS_SPMEVTYPERn_EL0(n)		sys_reg(2, 3, 14, __SPMEV_crm(0b001, n), __SPMEV_op2(n))
+
 #define SYS_VPIDR_EL2			sys_reg(3, 4, 0, 0, 0)
 #define SYS_VMPIDR_EL2			sys_reg(3, 4, 0, 0, 5)
 
@@ -518,7 +535,6 @@
 #define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
 
 #define SYS_VNCR_EL2			sys_reg(3, 4, 2, 2, 0)
-#define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
 #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
 #define SYS_SP_EL1			sys_reg(3, 4, 4, 1, 0)
@@ -604,28 +620,18 @@
 
 /* VHE encodings for architectural EL0/1 system registers */
 #define SYS_BRBCR_EL12			sys_reg(2, 5, 9, 0, 0)
-#define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
-#define SYS_CPACR_EL12			sys_reg(3, 5, 1, 0, 2)
-#define SYS_SCTLR2_EL12			sys_reg(3, 5, 1, 0, 3)
-#define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
-#define SYS_TRFCR_EL12			sys_reg(3, 5, 1, 2, 1)
-#define SYS_SMCR_EL12			sys_reg(3, 5, 1, 2, 6)
 #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
 #define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
-#define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
-#define SYS_TCR2_EL12			sys_reg(3, 5, 2, 0, 3)
 #define SYS_SPSR_EL12			sys_reg(3, 5, 4, 0, 0)
 #define SYS_ELR_EL12			sys_reg(3, 5, 4, 0, 1)
 #define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
 #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
 #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
 #define SYS_TFSR_EL12			sys_reg(3, 5, 5, 6, 0)
-#define SYS_FAR_EL12			sys_reg(3, 5, 6, 0, 0)
 #define SYS_PMSCR_EL12			sys_reg(3, 5, 9, 9, 0)
 #define SYS_MAIR_EL12			sys_reg(3, 5, 10, 2, 0)
 #define SYS_AMAIR_EL12			sys_reg(3, 5, 10, 3, 0)
 #define SYS_VBAR_EL12			sys_reg(3, 5, 12, 0, 0)
-#define SYS_CONTEXTIDR_EL12		sys_reg(3, 5, 13, 0, 1)
 #define SYS_SCXTNUM_EL12		sys_reg(3, 5, 13, 0, 7)
 #define SYS_CNTKCTL_EL12		sys_reg(3, 5, 14, 1, 0)
 #define SYS_CNTP_TVAL_EL02		sys_reg(3, 5, 14, 2, 0)
@@ -1028,8 +1034,11 @@
 #define PIE_RX		UL(0xa)
 #define PIE_RW		UL(0xc)
 #define PIE_RWX		UL(0xe)
+#define PIE_MASK	UL(0xf)
 
-#define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))
+#define PIRx_ELx_BITS_PER_IDX		4
+#define PIRx_ELx_PERM_SHIFT(idx)	((idx) * PIRx_ELx_BITS_PER_IDX)
+#define PIRx_ELx_PERM_PREP(idx, perm)	(((perm) & PIE_MASK) << PIRx_ELx_PERM_SHIFT(idx))
 
 /*
  * Permission Overlay Extension (POE) permission encodings.
@@ -1040,12 +1049,34 @@
 #define POE_RX		UL(0x3)
 #define POE_W		UL(0x4)
 #define POE_RW		UL(0x5)
-#define POE_XW		UL(0x6)
-#define POE_RXW		UL(0x7)
+#define POE_WX		UL(0x6)
+#define POE_RWX		UL(0x7)
 #define POE_MASK	UL(0xf)
 
-/* Initial value for Permission Overlay Extension for EL0 */
-#define POR_EL0_INIT	POE_RXW
+#define POR_ELx_BITS_PER_IDX		4
+#define POR_ELx_PERM_SHIFT(idx)		((idx) * POR_ELx_BITS_PER_IDX)
+#define POR_ELx_PERM_GET(idx, reg)	(((reg) >> POR_ELx_PERM_SHIFT(idx)) & POE_MASK)
+#define POR_ELx_PERM_PREP(idx, perm)	(((perm) & POE_MASK) << POR_ELx_PERM_SHIFT(idx))
+
+/*
+ * Definitions for Guarded Control Stack
+ */
+
+#define GCS_CAP_ADDR_MASK		GENMASK(63, 12)
+#define GCS_CAP_ADDR_SHIFT		12
+#define GCS_CAP_ADDR_WIDTH		52
+#define GCS_CAP_ADDR(x)			FIELD_GET(GCS_CAP_ADDR_MASK, x)
+
+#define GCS_CAP_TOKEN_MASK		GENMASK(11, 0)
+#define GCS_CAP_TOKEN_SHIFT		0
+#define GCS_CAP_TOKEN_WIDTH		12
+#define GCS_CAP_TOKEN(x)		FIELD_GET(GCS_CAP_TOKEN_MASK, x)
+
+#define GCS_CAP_VALID_TOKEN		0x1
+#define GCS_CAP_IN_PROGRESS_TOKEN	0x5
+
+#define GCS_CAP(x)	((((unsigned long)x) & GCS_CAP_ADDR_MASK) | \
+					       GCS_CAP_VALID_TOKEN)
 
 #define ARM64_FEATURE_FIELD_BITS	4