Merge branch kvm-arm64/nv-at-pan into kvmarm-master/next

* kvm-arm64/nv-at-pan:
  : .
  : Add NV support for the AT family of instructions, which mostly results
  : in adding a page table walker that deals with most of the complexity
  : of the architecture.
  :
  : From the cover letter:
  :
  : "Another task that a hypervisor supporting NV on arm64 has to deal with
  : is to emulate the AT instruction, because we multiplex all the S1
  : translations on a single set of registers, and the guest S2 is never
  : truly resident on the CPU.
  :
  : So given that we lie about page tables, we also have to lie about
  : translation instructions, hence the emulation. Things are made
  : complicated by the fact that guest S1 page tables can be swapped out,
  : and that our shadow S2 is likely to be incomplete. So while using AT
  : to emulate AT is tempting (and useful), it is not going to always
  : work, and we thus need a fallback in the shape of a SW S1 walker."
  : .
  KVM: arm64: nv: Add support for FEAT_ATS1A
  KVM: arm64: nv: Plumb handling of AT S1* traps from EL2
  KVM: arm64: nv: Make AT+PAN instructions aware of FEAT_PAN3
  KVM: arm64: nv: Sanitise SCTLR_EL1.EPAN according to VM configuration
  KVM: arm64: nv: Add SW walker for AT S1 emulation
  KVM: arm64: nv: Make ps_to_output_size() generally available
  KVM: arm64: nv: Add emulation of AT S12E{0,1}{R,W}
  KVM: arm64: nv: Add basic emulation of AT S1E2{R,W}
  KVM: arm64: nv: Add basic emulation of AT S1E1{R,W}P
  KVM: arm64: nv: Add basic emulation of AT S1E{0,1}{R,W}
  KVM: arm64: nv: Honor absence of FEAT_PAN2
  KVM: arm64: nv: Turn upper_attr for S2 walk into the full descriptor
  KVM: arm64: nv: Enforce S2 alignment when contiguous bit is set
  arm64: Add ESR_ELx_FSC_ADDRSZ_L() helper
  arm64: Add system register encoding for PSTATE.PAN
  arm64: Add PAR_EL1 field description
  arm64: Add missing APTable and TCR_ELx.HPD masks
  KVM: arm64: Make kvm_at() take an OP_AT_*

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

# Conflicts:
#	arch/arm64/kvm/nested.c

12 files changed, 1258 insertions, 32 deletions

diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 56c148890daf..d79308c23ddb 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -122,8 +122,8 @@
 #define ESR_ELx_FSC_SECC_TTW(n)	(0x1c + (n))
 
 /* Status codes for individual page table levels */
-#define ESR_ELx_FSC_ACCESS_L(n)	(ESR_ELx_FSC_ACCESS + n)
-#define ESR_ELx_FSC_PERM_L(n)	(ESR_ELx_FSC_PERM + n)
+#define ESR_ELx_FSC_ACCESS_L(n)	(ESR_ELx_FSC_ACCESS + (n))
+#define ESR_ELx_FSC_PERM_L(n)	(ESR_ELx_FSC_PERM + (n))
 
 #define ESR_ELx_FSC_FAULT_nL	(0x2C)
 #define ESR_ELx_FSC_FAULT_L(n)	(((n) < 0 ? ESR_ELx_FSC_FAULT_nL : \
@@ -161,6 +161,7 @@
 
 /* ISS field definitions for exceptions taken in to Hyp */
 #define ESR_ELx_FSC_ADDRSZ	(0x00)
+#define ESR_ELx_FSC_ADDRSZ_L(n)	(ESR_ELx_FSC_ADDRSZ + (n))
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index d81cc746e0eb..109a85ee6910 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -107,6 +107,7 @@
 /* TCR_EL2 Registers bits */
 #define TCR_EL2_DS		(1UL << 32)
 #define TCR_EL2_RES1		((1U << 31) | (1 << 23))
+#define TCR_EL2_HPD		(1 << 24)
 #define TCR_EL2_TBI		(1 << 20)
 #define TCR_EL2_PS_SHIFT	16
 #define TCR_EL2_PS_MASK		(7 << TCR_EL2_PS_SHIFT)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 2181a11b9d92..b36a3b6cc011 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -10,6 +10,7 @@
 #include <asm/hyp_image.h>
 #include <asm/insn.h>
 #include <asm/virt.h>
+#include <asm/sysreg.h>
 
 #define ARM_EXIT_WITH_SERROR_BIT  31
 #define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
@@ -235,6 +236,9 @@ extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 extern int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
+extern void __kvm_at_s1e01(struct kvm_vcpu *vcpu, u32 op, u64 vaddr);
+extern void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr);
+extern void __kvm_at_s12(struct kvm_vcpu *vcpu, u32 op, u64 vaddr);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
@@ -259,7 +263,7 @@ extern u64 __kvm_get_mdcr_el2(void);
 	asm volatile(							\
 	"	mrs	%1, spsr_el2\n"					\
 	"	mrs	%2, elr_el2\n"					\
-	"1:	at	"at_op", %3\n"					\
+	"1:	" __msr_s(at_op, "%3") "\n"				\
 	"	isb\n"							\
 	"	b	9f\n"						\
 	"2:	msr	spsr_el2, %1\n"					\
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 5b06c31035a2..e8bc6d67aba2 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -85,7 +85,7 @@ struct kvm_s2_trans {
 	bool readable;
 	int level;
 	u32 esr;
-	u64 upper_attr;
+	u64 desc;
 };
 
 static inline phys_addr_t kvm_s2_trans_output(struct kvm_s2_trans *trans)
@@ -115,7 +115,7 @@ static inline bool kvm_s2_trans_writable(struct kvm_s2_trans *trans)
 
 static inline bool kvm_s2_trans_executable(struct kvm_s2_trans *trans)
 {
-	return !(trans->upper_attr & BIT(54));
+	return !(trans->desc & BIT(54));
 }
 
 extern int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
@@ -205,4 +205,40 @@ static inline u64 kvm_encode_nested_level(struct kvm_s2_trans *trans)
 	return FIELD_PREP(KVM_NV_GUEST_MAP_SZ, trans->level);
 }
 
+/* Adjust alignment for the contiguous bit as per StageOA() */
+#define contiguous_bit_shift(d, wi, l)					\
+	({								\
+		u8 shift = 0;						\
+									\
+		if ((d) & PTE_CONT) {					\
+			switch (BIT((wi)->pgshift)) {			\
+			case SZ_4K:					\
+				shift = 4;				\
+				break;					\
+			case SZ_16K:					\
+				shift = (l) == 2 ? 5 : 7;		\
+				break;					\
+			case SZ_64K:					\
+				shift = 5;				\
+				break;					\
+			}						\
+		}							\
+									\
+		shift;							\
+	})
+
+static inline unsigned int ps_to_output_size(unsigned int ps)
+{
+	switch (ps) {
+	case 0: return 32;
+	case 1: return 36;
+	case 2: return 40;
+	case 3: return 42;
+	case 4: return 44;
+	case 5:
+	default:
+		return 48;
+	}
+}
+
 #endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 1f60aa1bc750..07dfbdb14bab 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -205,6 +205,11 @@
 #define PTE_S2_MEMATTR(t)	(_AT(pteval_t, (t)) << 2)
 
 /*
+ * Hierarchical permission for Stage-1 tables
+ */
+#define S1_TABLE_AP		(_AT(pmdval_t, 3) << 61)
+
+/*
  * Highest possible physical address supported.
  */
 #define PHYS_MASK_SHIFT		(CONFIG_ARM64_PA_BITS)
@@ -298,6 +303,10 @@
 #define TCR_TBI1		(UL(1) << 38)
 #define TCR_HA			(UL(1) << 39)
 #define TCR_HD			(UL(1) << 40)
+#define TCR_HPD0_SHIFT		41
+#define TCR_HPD0		(UL(1) << TCR_HPD0_SHIFT)
+#define TCR_HPD1_SHIFT		42
+#define TCR_HPD1		(UL(1) << TCR_HPD1_SHIFT)
 #define TCR_TBID0		(UL(1) << 51)
 #define TCR_TBID1		(UL(1) << 52)
 #define TCR_NFD0		(UL(1) << 53)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 4a9ea103817e..bc161f160854 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -109,6 +109,9 @@
 #define set_pstate_ssbs(x)		asm volatile(SET_PSTATE_SSBS(x))
 #define set_pstate_dit(x)		asm volatile(SET_PSTATE_DIT(x))
 
+/* Register-based PAN access, for save/restore purposes */
+#define SYS_PSTATE_PAN			sys_reg(3, 0, 4, 2, 3)
+
 #define __SYS_BARRIER_INSN(CRm, op2, Rt) \
 	__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
 
@@ -325,7 +328,25 @@
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
 #define SYS_PAR_EL1_F			BIT(0)
+/* When PAR_EL1.F == 1 */
 #define SYS_PAR_EL1_FST			GENMASK(6, 1)
+#define SYS_PAR_EL1_PTW			BIT(8)
+#define SYS_PAR_EL1_S			BIT(9)
+#define SYS_PAR_EL1_AssuredOnly		BIT(12)
+#define SYS_PAR_EL1_TopLevel		BIT(13)
+#define SYS_PAR_EL1_Overlay		BIT(14)
+#define SYS_PAR_EL1_DirtyBit		BIT(15)
+#define SYS_PAR_EL1_F1_IMPDEF		GENMASK_ULL(63, 48)
+#define SYS_PAR_EL1_F1_RES0		(BIT(7) | BIT(10) | GENMASK_ULL(47, 16))
+#define SYS_PAR_EL1_RES1		BIT(11)
+/* When PAR_EL1.F == 0 */
+#define SYS_PAR_EL1_SH			GENMASK_ULL(8, 7)
+#define SYS_PAR_EL1_NS			BIT(9)
+#define SYS_PAR_EL1_F0_IMPDEF		BIT(10)
+#define SYS_PAR_EL1_NSE			BIT(11)
+#define SYS_PAR_EL1_PA			GENMASK_ULL(51, 12)
+#define SYS_PAR_EL1_ATTR		GENMASK_ULL(63, 56)
+#define SYS_PAR_EL1_F0_RES0		(GENMASK_ULL(6, 1) | GENMASK_ULL(55, 52))
 
 /*** Statistical Profiling Extension ***/
 #define PMSEVFR_EL1_RES0_IMP	\
@@ -652,6 +673,7 @@
 #define OP_AT_S12E1W	sys_insn(AT_Op0, 4, AT_CRn, 8, 5)
 #define OP_AT_S12E0R	sys_insn(AT_Op0, 4, AT_CRn, 8, 6)
 #define OP_AT_S12E0W	sys_insn(AT_Op0, 4, AT_CRn, 8, 7)
+#define OP_AT_S1E2A	sys_insn(AT_Op0, 4, AT_CRn, 9, 2)
 
 /* TLBI instructions */
 #define TLBI_Op0	1
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 86a629aaf0a1..971258b025f9 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -17,7 +17,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 	 inject_fault.o va_layout.o handle_exit.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 \
+	 arch_timer.o trng.o vmid.o emulate-nested.o nested.o at.o \
 	 vgic/vgic.o vgic/vgic-init.o \
 	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
new file mode 100644
index 000000000000..39f0e87a340e
--- /dev/null
+++ b/arch/arm64/kvm/at.c
@@ -0,0 +1,1101 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 - Linaro Ltd
+ * Author: Jintack Lim <jintack.lim@linaro.org>
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/esr.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+enum trans_regime {
+	TR_EL10,
+	TR_EL20,
+	TR_EL2,
+};
+
+struct s1_walk_info {
+	u64	     		baddr;
+	enum trans_regime	regime;
+	unsigned int		max_oa_bits;
+	unsigned int		pgshift;
+	unsigned int		txsz;
+	int 	     		sl;
+	bool	     		hpd;
+	bool	     		be;
+	bool	     		s2;
+};
+
+struct s1_walk_result {
+	union {
+		struct {
+			u64	desc;
+			u64	pa;
+			s8	level;
+			u8	APTable;
+			bool	UXNTable;
+			bool	PXNTable;
+		};
+		struct {
+			u8	fst;
+			bool	ptw;
+			bool	s2;
+		};
+	};
+	bool	failed;
+};
+
+static void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool ptw, bool s2)
+{
+	wr->fst		= fst;
+	wr->ptw		= ptw;
+	wr->s2		= s2;
+	wr->failed	= true;
+}
+
+#define S1_MMU_DISABLED		(-127)
+
+static int get_ia_size(struct s1_walk_info *wi)
+{
+	return 64 - wi->txsz;
+}
+
+/* Return true if the IPA is out of the OA range */
+static bool check_output_size(u64 ipa, struct s1_walk_info *wi)
+{
+	return wi->max_oa_bits < 48 && (ipa & GENMASK_ULL(47, wi->max_oa_bits));
+}
+
+/* Return the translation regime that applies to an AT instruction */
+static enum trans_regime compute_translation_regime(struct kvm_vcpu *vcpu, u32 op)
+{
+	/*
+	 * We only get here from guest EL2, so the translation
+	 * regime AT applies to is solely defined by {E2H,TGE}.
+	 */
+	switch (op) {
+	case OP_AT_S1E2R:
+	case OP_AT_S1E2W:
+	case OP_AT_S1E2A:
+		return vcpu_el2_e2h_is_set(vcpu) ? TR_EL20 : TR_EL2;
+		break;
+	default:
+		return (vcpu_el2_e2h_is_set(vcpu) &&
+			vcpu_el2_tge_is_set(vcpu)) ? TR_EL20 : TR_EL10;
+	}
+}
+
+static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi,
+			 struct s1_walk_result *wr, u64 va)
+{
+	u64 hcr, sctlr, tcr, tg, ps, ia_bits, ttbr;
+	unsigned int stride, x;
+	bool va55, tbi, lva, as_el0;
+
+	hcr = __vcpu_sys_reg(vcpu, HCR_EL2);
+
+	wi->regime = compute_translation_regime(vcpu, op);
+	as_el0 = (op == OP_AT_S1E0R || op == OP_AT_S1E0W);
+
+	va55 = va & BIT(55);
+
+	if (wi->regime == TR_EL2 && va55)
+		goto addrsz;
+
+	wi->s2 = wi->regime == TR_EL10 && (hcr & (HCR_VM | HCR_DC));
+
+	switch (wi->regime) {
+	case TR_EL10:
+		sctlr	= vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+		tcr	= vcpu_read_sys_reg(vcpu, TCR_EL1);
+		ttbr	= (va55 ?
+			   vcpu_read_sys_reg(vcpu, TTBR1_EL1) :
+			   vcpu_read_sys_reg(vcpu, TTBR0_EL1));
+		break;
+	case TR_EL2:
+	case TR_EL20:
+		sctlr	= vcpu_read_sys_reg(vcpu, SCTLR_EL2);
+		tcr	= vcpu_read_sys_reg(vcpu, TCR_EL2);
+		ttbr	= (va55 ?
+			   vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
+			   vcpu_read_sys_reg(vcpu, TTBR0_EL2));
+		break;
+	default:
+		BUG();
+	}
+
+	tbi = (wi->regime == TR_EL2 ?
+	       FIELD_GET(TCR_EL2_TBI, tcr) :
+	       (va55 ?
+		FIELD_GET(TCR_TBI1, tcr) :
+		FIELD_GET(TCR_TBI0, tcr)));
+
+	if (!tbi && (u64)sign_extend64(va, 55) != va)
+		goto addrsz;
+
+	va = (u64)sign_extend64(va, 55);
+
+	/* Let's put the MMU disabled case aside immediately */
+	switch (wi->regime) {
+	case TR_EL10:
+		/*
+		 * If dealing with the EL1&0 translation regime, 3 things
+		 * can disable the S1 translation:
+		 *
+		 * - HCR_EL2.DC = 1
+		 * - HCR_EL2.{E2H,TGE} = {0,1}
+		 * - SCTLR_EL1.M = 0
+		 *
+		 * The TGE part is interesting. If we have decided that this
+		 * is EL1&0, then it means that either {E2H,TGE} == {1,0} or
+		 * {0,x}, and we only need to test for TGE == 1.
+		 */
+		if (hcr & (HCR_DC | HCR_TGE)) {
+			wr->level = S1_MMU_DISABLED;
+			break;
+		}
+		fallthrough;
+	case TR_EL2:
+	case TR_EL20:
+		if (!(sctlr & SCTLR_ELx_M))
+			wr->level = S1_MMU_DISABLED;
+		break;
+	}
+
+	if (wr->level == S1_MMU_DISABLED) {
+		if (va >= BIT(kvm_get_pa_bits(vcpu->kvm)))
+			goto addrsz;
+
+		wr->pa = va;
+		return 0;
+	}
+
+	wi->be = sctlr & SCTLR_ELx_EE;
+
+	wi->hpd  = kvm_has_feat(vcpu->kvm, ID_AA64MMFR1_EL1, HPDS, IMP);
+	wi->hpd &= (wi->regime == TR_EL2 ?
+		    FIELD_GET(TCR_EL2_HPD, tcr) :
+		    (va55 ?
+		     FIELD_GET(TCR_HPD1, tcr) :
+		     FIELD_GET(TCR_HPD0, tcr)));
+
+	/* Someone was silly enough to encode TG0/TG1 differently */
+	if (va55) {
+		wi->txsz = FIELD_GET(TCR_T1SZ_MASK, tcr);
+		tg = FIELD_GET(TCR_TG1_MASK, tcr);
+
+		switch (tg << TCR_TG1_SHIFT) {
+		case TCR_TG1_4K:
+			wi->pgshift = 12;	 break;
+		case TCR_TG1_16K:
+			wi->pgshift = 14;	 break;
+		case TCR_TG1_64K:
+		default:	    /* IMPDEF: treat any other value as 64k */
+			wi->pgshift = 16;	 break;
+		}
+	} else {
+		wi->txsz = FIELD_GET(TCR_T0SZ_MASK, tcr);
+		tg = FIELD_GET(TCR_TG0_MASK, tcr);
+
+		switch (tg << TCR_TG0_SHIFT) {
+		case TCR_TG0_4K:
+			wi->pgshift = 12;	 break;
+		case TCR_TG0_16K:
+			wi->pgshift = 14;	 break;
+		case TCR_TG0_64K:
+		default:	    /* IMPDEF: treat any other value as 64k */
+			wi->pgshift = 16;	 break;
+		}
+	}
+
+	/* R_PLCGL, R_YXNYW */
+	if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR2_EL1, ST, 48_47)) {
+		if (wi->txsz > 39)
+			goto transfault_l0;
+	} else {
+		if (wi->txsz > 48 || (BIT(wi->pgshift) == SZ_64K && wi->txsz > 47))
+			goto transfault_l0;
+	}
+
+	/* R_GTJBY, R_SXWGM */
+	switch (BIT(wi->pgshift)) {
+	case SZ_4K:
+		lva = kvm_has_feat(vcpu->kvm, ID_AA64MMFR0_EL1, TGRAN4, 52_BIT);
+		lva &= tcr & (wi->regime == TR_EL2 ? TCR_EL2_DS : TCR_DS);
+		break;
+	case SZ_16K:
+		lva = kvm_has_feat(vcpu->kvm, ID_AA64MMFR0_EL1, TGRAN16, 52_BIT);
+		lva &= tcr & (wi->regime == TR_EL2 ? TCR_EL2_DS : TCR_DS);
+		break;
+	case SZ_64K:
+		lva = kvm_has_feat(vcpu->kvm, ID_AA64MMFR2_EL1, VARange, 52);
+		break;
+	}
+
+	if ((lva && wi->txsz < 12) || (!lva && wi->txsz < 16))
+		goto transfault_l0;
+
+	ia_bits = get_ia_size(wi);
+
+	/* R_YYVYV, I_THCZK */
+	if ((!va55 && va > GENMASK(ia_bits - 1, 0)) ||
+	    (va55 && va < GENMASK(63, ia_bits)))
+		goto transfault_l0;
+
+	/* I_ZFSYQ */
+	if (wi->regime != TR_EL2 &&
+	    (tcr & (va55 ? TCR_EPD1_MASK : TCR_EPD0_MASK)))
+		goto transfault_l0;
+
+	/* R_BNDVG and following statements */
+	if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR2_EL1, E0PD, IMP) &&
+	    as_el0 && (tcr & (va55 ? TCR_E0PD1 : TCR_E0PD0)))
+		goto transfault_l0;
+
+	/* AArch64.S1StartLevel() */
+	stride = wi->pgshift - 3;
+	wi->sl = 3 - (((ia_bits - 1) - wi->pgshift) / stride);
+
+	ps = (wi->regime == TR_EL2 ?
+	      FIELD_GET(TCR_EL2_PS_MASK, tcr) : FIELD_GET(TCR_IPS_MASK, tcr));
+
+	wi->max_oa_bits = min(get_kvm_ipa_limit(), ps_to_output_size(ps));
+
+	/* Compute minimal alignment */
+	x = 3 + ia_bits - ((3 - wi->sl) * stride + wi->pgshift);
+
+	wi->baddr = ttbr & TTBRx_EL1_BADDR;
+
+	/* R_VPBBF */
+	if (check_output_size(wi->baddr, wi))
+		goto addrsz;
+
+	wi->baddr &= GENMASK_ULL(wi->max_oa_bits - 1, x);
+
+	return 0;
+
+addrsz:				/* Address Size Fault level 0 */
+	fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(0), false, false);
+	return -EFAULT;
+
+transfault_l0:			/* Translation Fault level 0 */
+	fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(0), false, false);
+	return -EFAULT;
+}
+
+static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
+		   struct s1_walk_result *wr, u64 va)
+{
+	u64 va_top, va_bottom, baddr, desc;
+	int level, stride, ret;
+
+	level = wi->sl;
+	stride = wi->pgshift - 3;
+	baddr = wi->baddr;
+
+	va_top = get_ia_size(wi) - 1;
+
+	while (1) {
+		u64 index, ipa;
+
+		va_bottom = (3 - level) * stride + wi->pgshift;
+		index = (va & GENMASK_ULL(va_top, va_bottom)) >> (va_bottom - 3);
+
+		ipa = baddr | index;
+
+		if (wi->s2) {
+			struct kvm_s2_trans s2_trans = {};
+
+			ret = kvm_walk_nested_s2(vcpu, ipa, &s2_trans);
+			if (ret) {
+				fail_s1_walk(wr,
+					     (s2_trans.esr & ~ESR_ELx_FSC_LEVEL) | level,
+					     true, true);
+				return ret;
+			}
+
+			if (!kvm_s2_trans_readable(&s2_trans)) {
+				fail_s1_walk(wr, ESR_ELx_FSC_PERM_L(level),
+					     true, true);
+
+				return -EPERM;
+			}
+
+			ipa = kvm_s2_trans_output(&s2_trans);
+		}
+
+		ret = kvm_read_guest(vcpu->kvm, ipa, &desc, sizeof(desc));
+		if (ret) {
+			fail_s1_walk(wr, ESR_ELx_FSC_SEA_TTW(level),
+				     true, false);
+			return ret;
+		}
+
+		if (wi->be)
+			desc = be64_to_cpu((__force __be64)desc);
+		else
+			desc = le64_to_cpu((__force __le64)desc);
+
+		/* Invalid descriptor */
+		if (!(desc & BIT(0)))
+			goto transfault;
+
+		/* Block mapping, check validity down the line */
+		if (!(desc & BIT(1)))
+			break;
+
+		/* Page mapping */
+		if (level == 3)
+			break;
+
+		/* Table handling */
+		if (!wi->hpd) {
+			wr->APTable  |= FIELD_GET(S1_TABLE_AP, desc);
+			wr->UXNTable |= FIELD_GET(PMD_TABLE_UXN, desc);
+			wr->PXNTable |= FIELD_GET(PMD_TABLE_PXN, desc);
+		}
+
+		baddr = desc & GENMASK_ULL(47, wi->pgshift);
+
+		/* Check for out-of-range OA */
+		if (check_output_size(baddr, wi))
+			goto addrsz;
+
+		/* Prepare for next round */
+		va_top = va_bottom - 1;
+		level++;
+	}
+
+	/* Block mapping, check the validity of the level */
+	if (!(desc & BIT(1))) {
+		bool valid_block = false;
+
+		switch (BIT(wi->pgshift)) {
+		case SZ_4K:
+			valid_block = level == 1 || level == 2;
+			break;
+		case SZ_16K:
+		case SZ_64K:
+			valid_block = level == 2;
+			break;
+		}
+
+		if (!valid_block)
+			goto transfault;
+	}
+
+	if (check_output_size(desc & GENMASK(47, va_bottom), wi))
+		goto addrsz;
+
+	va_bottom += contiguous_bit_shift(desc, wi, level);
+
+	wr->failed = false;
+	wr->level = level;
+	wr->desc = desc;
+	wr->pa = desc & GENMASK(47, va_bottom);
+	wr->pa |= va & GENMASK_ULL(va_bottom - 1, 0);
+
+	return 0;
+
+addrsz:
+	fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(level), true, false);
+	return -EINVAL;
+transfault:
+	fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(level), true, false);
+	return -ENOENT;
+}
+
+struct mmu_config {
+	u64	ttbr0;
+	u64	ttbr1;
+	u64	tcr;
+	u64	mair;
+	u64	sctlr;
+	u64	vttbr;
+	u64	vtcr;
+	u64	hcr;
+};
+
+static void __mmu_config_save(struct mmu_config *config)
+{
+	config->ttbr0	= read_sysreg_el1(SYS_TTBR0);
+	config->ttbr1	= read_sysreg_el1(SYS_TTBR1);
+	config->tcr	= read_sysreg_el1(SYS_TCR);
+	config->mair	= read_sysreg_el1(SYS_MAIR);
+	config->sctlr	= read_sysreg_el1(SYS_SCTLR);
+	config->vttbr	= read_sysreg(vttbr_el2);
+	config->vtcr	= read_sysreg(vtcr_el2);
+	config->hcr	= read_sysreg(hcr_el2);
+}
+
+static void __mmu_config_restore(struct mmu_config *config)
+{
+	write_sysreg(config->hcr,	hcr_el2);
+
+	/*
+	 * ARM errata 1165522 and 1530923 require TGE to be 1 before
+	 * we update the guest state.
+	 */
+	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
+
+	write_sysreg_el1(config->ttbr0,	SYS_TTBR0);
+	write_sysreg_el1(config->ttbr1,	SYS_TTBR1);
+	write_sysreg_el1(config->tcr,	SYS_TCR);
+	write_sysreg_el1(config->mair,	SYS_MAIR);
+	write_sysreg_el1(config->sctlr,	SYS_SCTLR);
+	write_sysreg(config->vttbr,	vttbr_el2);
+	write_sysreg(config->vtcr,	vtcr_el2);
+}
+
+static bool at_s1e1p_fast(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
+{
+	u64 host_pan;
+	bool fail;
+
+	host_pan = read_sysreg_s(SYS_PSTATE_PAN);
+	write_sysreg_s(*vcpu_cpsr(vcpu) & PSTATE_PAN, SYS_PSTATE_PAN);
+
+	switch (op) {
+	case OP_AT_S1E1RP:
+		fail = __kvm_at(OP_AT_S1E1RP, vaddr);
+		break;
+	case OP_AT_S1E1WP:
+		fail = __kvm_at(OP_AT_S1E1WP, vaddr);
+		break;
+	}
+
+	write_sysreg_s(host_pan, SYS_PSTATE_PAN);
+
+	return fail;
+}
+
+#define MEMATTR(ic, oc)		(MEMATTR_##oc << 4 | MEMATTR_##ic)
+#define MEMATTR_NC		0b0100
+#define MEMATTR_Wt		0b1000
+#define MEMATTR_Wb		0b1100
+#define MEMATTR_WbRaWa		0b1111
+
+#define MEMATTR_IS_DEVICE(m)	(((m) & GENMASK(7, 4)) == 0)
+
+static u8 s2_memattr_to_attr(u8 memattr)
+{
+	memattr &= 0b1111;
+
+	switch (memattr) {
+	case 0b0000:
+	case 0b0001:
+	case 0b0010:
+	case 0b0011:
+		return memattr << 2;
+	case 0b0100:
+		return MEMATTR(Wb, Wb);
+	case 0b0101:
+		return MEMATTR(NC, NC);
+	case 0b0110:
+		return MEMATTR(Wt, NC);
+	case 0b0111:
+		return MEMATTR(Wb, NC);
+	case 0b1000:
+		/* Reserved, assume NC */
+		return MEMATTR(NC, NC);
+	case 0b1001:
+		return MEMATTR(NC, Wt);
+	case 0b1010:
+		return MEMATTR(Wt, Wt);
+	case 0b1011:
+		return MEMATTR(Wb, Wt);
+	case 0b1100:
+		/* Reserved, assume NC */
+		return MEMATTR(NC, NC);
+	case 0b1101:
+		return MEMATTR(NC, Wb);
+	case 0b1110:
+		return MEMATTR(Wt, Wb);
+	case 0b1111:
+		return MEMATTR(Wb, Wb);
+	default:
+		unreachable();
+	}
+}
+
+static u8 combine_s1_s2_attr(u8 s1, u8 s2)
+{
+	bool transient;
+	u8 final = 0;
+
+	/* Upgrade transient s1 to non-transient to simplify things */
+	switch (s1) {
+	case 0b0001 ... 0b0011:	/* Normal, Write-Through Transient */
+		transient = true;
+		s1 = MEMATTR_Wt | (s1 & GENMASK(1,0));
+		break;
+	case 0b0101 ... 0b0111:	/* Normal, Write-Back Transient */
+		transient = true;
+		s1 = MEMATTR_Wb | (s1 & GENMASK(1,0));
+		break;
+	default:
+		transient = false;
+	}
+
+	/* S2CombineS1AttrHints() */
+	if ((s1 & GENMASK(3, 2)) == MEMATTR_NC ||
+	    (s2 & GENMASK(3, 2)) == MEMATTR_NC)
+		final = MEMATTR_NC;
+	else if ((s1 & GENMASK(3, 2)) == MEMATTR_Wt ||
+		 (s2 & GENMASK(3, 2)) == MEMATTR_Wt)
+		final = MEMATTR_Wt;
+	else
+		final = MEMATTR_Wb;
+
+	if (final != MEMATTR_NC) {
+		/* Inherit RaWa hints form S1 */
+		if (transient) {
+			switch (s1 & GENMASK(3, 2)) {
+			case MEMATTR_Wt:
+				final = 0;
+				break;
+			case MEMATTR_Wb:
+				final = MEMATTR_NC;
+				break;
+			}
+		}
+
+		final |= s1 & GENMASK(1, 0);
+	}
+
+	return final;
+}
+
+#define ATTR_NSH	0b00
+#define ATTR_RSV	0b01
+#define ATTR_OSH	0b10
+#define ATTR_ISH	0b11
+
+static u8 compute_sh(u8 attr, u64 desc)
+{
+	u8 sh;
+
+	/* Any form of device, as well as NC has SH[1:0]=0b10 */
+	if (MEMATTR_IS_DEVICE(attr) || attr == MEMATTR(NC, NC))
+		return ATTR_OSH;
+
+	sh = FIELD_GET(PTE_SHARED, desc);
+	if (sh == ATTR_RSV)		/* Reserved, mapped to NSH */
+		sh = ATTR_NSH;
+
+	return sh;
+}
+
+static u8 combine_sh(u8 s1_sh, u8 s2_sh)
+{
+	if (s1_sh == ATTR_OSH || s2_sh == ATTR_OSH)
+		return ATTR_OSH;
+	if (s1_sh == ATTR_ISH || s2_sh == ATTR_ISH)
+		return ATTR_ISH;
+
+	return ATTR_NSH;
+}
+
+static u64 compute_par_s12(struct kvm_vcpu *vcpu, u64 s1_par,
+			   struct kvm_s2_trans *tr)
+{
+	u8 s1_parattr, s2_memattr, final_attr;
+	u64 par;
+
+	/* If S2 has failed to translate, report the damage */
+	if (tr->esr) {
+		par = SYS_PAR_EL1_RES1;
+		par |= SYS_PAR_EL1_F;
+		par |= SYS_PAR_EL1_S;
+		par |= FIELD_PREP(SYS_PAR_EL1_FST, tr->esr);
+		return par;
+	}
+
+	s1_parattr = FIELD_GET(SYS_PAR_EL1_ATTR, s1_par);
+	s2_memattr = FIELD_GET(GENMASK(5, 2), tr->desc);
+
+	if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_FWB) {
+		if (!kvm_has_feat(vcpu->kvm, ID_AA64PFR2_EL1, MTEPERM, IMP))
+			s2_memattr &= ~BIT(3);
+
+		/* Combination of R_VRJSW and R_RHWZM */
+		switch (s2_memattr) {
+		case 0b0101:
+			if (MEMATTR_IS_DEVICE(s1_parattr))
+				final_attr = s1_parattr;
+			else
+				final_attr = MEMATTR(NC, NC);
+			break;
+		case 0b0110:
+		case 0b1110:
+			final_attr = MEMATTR(WbRaWa, WbRaWa);
+			break;
+		case 0b0111:
+		case 0b1111:
+			/* Preserve S1 attribute */
+			final_attr = s1_parattr;
+			break;
+		case 0b0100:
+		case 0b1100:
+		case 0b1101:
+			/* Reserved, do something non-silly */
+			final_attr = s1_parattr;
+			break;
+		default:
+			/* MemAttr[2]=0, Device from S2 */
+			final_attr = s2_memattr & GENMASK(1,0) << 2;
+		}
+	} else {
+		/* Combination of R_HMNDG, R_TNHFM and R_GQFSF */
+		u8 s2_parattr = s2_memattr_to_attr(s2_memattr);
+
+		if (MEMATTR_IS_DEVICE(s1_parattr) ||
+		    MEMATTR_IS_DEVICE(s2_parattr)) {
+			final_attr = min(s1_parattr, s2_parattr);
+		} else {
+			/* At this stage, this is memory vs memory */
+			final_attr  = combine_s1_s2_attr(s1_parattr & 0xf,
+							 s2_parattr & 0xf);
+			final_attr |= combine_s1_s2_attr(s1_parattr >> 4,
+							 s2_parattr >> 4) << 4;
+		}
+	}
+
+	if ((__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_CD) &&
+	    !MEMATTR_IS_DEVICE(final_attr))
+		final_attr = MEMATTR(NC, NC);
+
+	par  = FIELD_PREP(SYS_PAR_EL1_ATTR, final_attr);
+	par |= tr->output & GENMASK(47, 12);
+	par |= FIELD_PREP(SYS_PAR_EL1_SH,
+			  combine_sh(FIELD_GET(SYS_PAR_EL1_SH, s1_par),
+				     compute_sh(final_attr, tr->desc)));
+
+	return par;
+}
+
+static u64 compute_par_s1(struct kvm_vcpu *vcpu, struct s1_walk_result *wr,
+			  enum trans_regime regime)
+{
+	u64 par;
+
+	if (wr->failed) {
+		par = SYS_PAR_EL1_RES1;
+		par |= SYS_PAR_EL1_F;
+		par |= FIELD_PREP(SYS_PAR_EL1_FST, wr->fst);
+		par |= wr->ptw ? SYS_PAR_EL1_PTW : 0;
+		par |= wr->s2 ? SYS_PAR_EL1_S : 0;
+	} else if (wr->level == S1_MMU_DISABLED) {
+		/* MMU off or HCR_EL2.DC == 1 */
+		par  = SYS_PAR_EL1_NSE;
+		par |= wr->pa & GENMASK_ULL(47, 12);
+
+		if (regime == TR_EL10 &&
+		    (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_DC)) {
+			par |= FIELD_PREP(SYS_PAR_EL1_ATTR,
+					  MEMATTR(WbRaWa, WbRaWa));
+			par |= FIELD_PREP(SYS_PAR_EL1_SH, ATTR_NSH);
+		} else {
+			par |= FIELD_PREP(SYS_PAR_EL1_ATTR, 0); /* nGnRnE */
+			par |= FIELD_PREP(SYS_PAR_EL1_SH, ATTR_OSH);
+		}
+	} else {
+		u64 mair, sctlr;
+		u8 sh;
+
+		par  = SYS_PAR_EL1_NSE;
+
+		mair = (regime == TR_EL10 ?
+			vcpu_read_sys_reg(vcpu, MAIR_EL1) :
+			vcpu_read_sys_reg(vcpu, MAIR_EL2));
+
+		mair >>= FIELD_GET(PTE_ATTRINDX_MASK, wr->desc) * 8;
+		mair &= 0xff;
+
+		sctlr = (regime == TR_EL10 ?
+			 vcpu_read_sys_reg(vcpu, SCTLR_EL1) :
+			 vcpu_read_sys_reg(vcpu, SCTLR_EL2));
+
+		/* Force NC for memory if SCTLR_ELx.C is clear */
+		if (!(sctlr & SCTLR_EL1_C) && !MEMATTR_IS_DEVICE(mair))
+			mair = MEMATTR(NC, NC);
+
+		par |= FIELD_PREP(SYS_PAR_EL1_ATTR, mair);
+		par |= wr->pa & GENMASK_ULL(47, 12);
+
+		sh = compute_sh(mair, wr->desc);
+		par |= FIELD_PREP(SYS_PAR_EL1_SH, sh);
+	}
+
+	return par;
+}
+
+static bool pan3_enabled(struct kvm_vcpu *vcpu, enum trans_regime regime)
+{
+	u64 sctlr;
+
+	if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR1_EL1, PAN, PAN3))
+		return false;
+
+	if (regime == TR_EL10)
+		sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+	else
+		sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL2);
+
+	return sctlr & SCTLR_EL1_EPAN;
+}
+
+static u64 handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
+{
+	bool perm_fail, ur, uw, ux, pr, pw, px;
+	struct s1_walk_result wr = {};
+	struct s1_walk_info wi = {};
+	int ret, idx;
+
+	ret = setup_s1_walk(vcpu, op, &wi, &wr, vaddr);
+	if (ret)
+		goto compute_par;
+
+	if (wr.level == S1_MMU_DISABLED)
+		goto compute_par;
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+	ret = walk_s1(vcpu, &wi, &wr, vaddr);
+
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+	if (ret)
+		goto compute_par;
+
+	/* FIXME: revisit when adding indirect permission support */
+	/* AArch64.S1DirectBasePermissions() */
+	if (wi.regime != TR_EL2) {
+		switch (FIELD_GET(PTE_USER | PTE_RDONLY, wr.desc)) {
+		case 0b00:
+			pr = pw = true;
+			ur = uw = false;
+			break;
+		case 0b01:
+			pr = pw = ur = uw = true;
+			break;
+		case 0b10:
+			pr = true;
+			pw = ur = uw = false;
+			break;
+		case 0b11:
+			pr = ur = true;
+			pw = uw = false;
+			break;
+		}
+
+		switch (wr.APTable) {
+		case 0b00:
+			break;
+		case 0b01:
+			ur = uw = false;
+			break;