[PATCH 01/23] KVM: arm64: Only sign-extend MMIO up to register width

[PATCH 01/23] KVM: arm64: Only sign-extend MMIO up to register width

[Marc Zyngier]

From: Christoffer Dall <christoffer.dall@arm.com>

On AArch64 you can do a sign-extended load to either a 32-bit or 64-bit
register, and we should only sign extend the register up to the width of
the register as specified in the operation (by using the 32-bit Wn or
64-bit Xn register specifier).

As it turns out, the architecture provides this decoding information in
the SF ("Sixty-Four" -- how cute...) bit.

Let's take advantage of this with the usual 32-bit/64-bit header file
dance and do the right thing on AArch64 hosts.

Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20191212195055.5541-1-christoffer.dall@arm.com
---
 arch/arm/include/asm/kvm_emulate.h   | 5 +++++
 arch/arm/include/asm/kvm_mmio.h      | 2 ++
 arch/arm64/include/asm/kvm_emulate.h | 5 +++++
 arch/arm64/include/asm/kvm_mmio.h    | 6 ++----
 virt/kvm/arm/mmio.c                  | 6 ++++++
 5 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 9b118516d2db..fe55d8737a11 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -182,6 +182,11 @@ static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_SSE;
 }
 
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu)
 {
 	return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h
index 7c0eddb0adb2..32fbf82e3ebc 100644
--- a/arch/arm/include/asm/kvm_mmio.h
+++ b/arch/arm/include/asm/kvm_mmio.h
@@ -14,6 +14,8 @@
 struct kvm_decode {
 	unsigned long rt;
 	bool sign_extend;
+	/* Not used on 32-bit arm */
+	bool sixty_four;
 };
 
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5efe5ca8fecf..f407b6bdad2e 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -283,6 +283,11 @@ static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
 }
 
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
+}
+
 static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 {
 	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
index 02b5c48fd467..b204501a0c39 100644
--- a/arch/arm64/include/asm/kvm_mmio.h
+++ b/arch/arm64/include/asm/kvm_mmio.h
@@ -10,13 +10,11 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_arm.h>
 
-/*
- * This is annoying. The mmio code requires this, even if we don't
- * need any decoding. To be fixed.
- */
 struct kvm_decode {
 	unsigned long rt;
 	bool sign_extend;
+	/* Witdth of the register accessed by the faulting instruction is 64-bits */
+	bool sixty_four;
 };
 
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c
index 70d3b449692c..1bb71acd53f2 100644
--- a/virt/kvm/arm/mmio.c
+++ b/virt/kvm/arm/mmio.c
@@ -105,6 +105,9 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			data = (data ^ mask) - mask;
 		}
 
+		if (!vcpu->arch.mmio_decode.sixty_four)
+			data = data & 0xffffffff;
+
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
 			       &data);
 		data = vcpu_data_host_to_guest(vcpu, data, len);
@@ -125,6 +128,7 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
 	unsigned long rt;
 	int access_size;
 	bool sign_extend;
+	bool sixty_four;
 
 	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
 		/* page table accesses IO mem: tell guest to fix its TTBR */
@@ -138,11 +142,13 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
 
 	*is_write = kvm_vcpu_dabt_iswrite(vcpu);
 	sign_extend = kvm_vcpu_dabt_issext(vcpu);
+	sixty_four = kvm_vcpu_dabt_issf(vcpu);
 	rt = kvm_vcpu_dabt_get_rd(vcpu);
 
 	*len = access_size;
 	vcpu->arch.mmio_decode.sign_extend = sign_extend;
 	vcpu->arch.mmio_decode.rt = rt;
+	vcpu->arch.mmio_decode.sixty_four = sixty_four;
 
 	return 0;
 }
-- 
2.20.1

[PATCH 08/23] KVM: arm64: Correct PSTATE on exception entry

[Marc Zyngier]

From: Mark Rutland <mark.rutland@arm.com>

When KVM injects an exception into a guest, it generates the PSTATE
value from scratch, configuring PSTATE.{M[4:0],DAIF}, and setting all
other bits to zero.

This isn't correct, as the architecture specifies that some PSTATE bits
are (conditionally) cleared or set upon an exception, and others are
unchanged from the original context.

This patch adds logic to match the architectural behaviour. To make this
simple to follow/audit/extend, documentation references are provided,
and bits are configured in order of their layout in SPSR_EL2. This
layout can be seen in the diagram on ARM DDI 0487E.a page C5-429.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200108134324.46500-2-mark.rutland@arm.com
---
 arch/arm64/include/uapi/asm/ptrace.h |  1 +
 arch/arm64/kvm/inject_fault.c        | 70 ++++++++++++++++++++++++++--
 2 files changed, 66 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 7ed9294e2004..d1bb5b69f1ce 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -49,6 +49,7 @@
 #define PSR_SSBS_BIT	0x00001000
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
+#define PSR_DIT_BIT	0x01000000
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index ccdb6a051ab2..6aafc2825c1c 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -14,9 +14,6 @@
 #include <asm/kvm_emulate.h>
 #include <asm/esr.h>
 
-#define PSTATE_FAULT_BITS_64 	(PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | \
-				 PSR_I_BIT | PSR_D_BIT)
-
 #define CURRENT_EL_SP_EL0_VECTOR	0x0
 #define CURRENT_EL_SP_ELx_VECTOR	0x200
 #define LOWER_EL_AArch64_VECTOR		0x400
@@ -50,6 +47,69 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
 	return vcpu_read_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
 }
 
+/*
+ * When an exception is taken, most PSTATE fields are left unchanged in the
+ * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all
+ * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx
+ * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0.
+ *
+ * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429.
+ * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426.
+ *
+ * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from
+ * MSB to LSB.
+ */
+static unsigned long get_except64_pstate(struct kvm_vcpu *vcpu)
+{
+	unsigned long sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+	unsigned long old, new;
+
+	old = *vcpu_cpsr(vcpu);
+	new = 0;
+
+	new |= (old & PSR_N_BIT);
+	new |= (old & PSR_Z_BIT);
+	new |= (old & PSR_C_BIT);
+	new |= (old & PSR_V_BIT);
+
+	// TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests)
+
+	new |= (old & PSR_DIT_BIT);
+
+	// PSTATE.UAO is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D5-2579.
+
+	// PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0
+	// SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented
+	// See ARM DDI 0487E.a, page D5-2578.
+	new |= (old & PSR_PAN_BIT);
+	if (!(sctlr & SCTLR_EL1_SPAN))
+		new |= PSR_PAN_BIT;
+
+	// PSTATE.SS is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D2-2452.
+
+	// PSTATE.IL is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D1-2306.
+
+	// PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D13-3258
+	if (sctlr & SCTLR_ELx_DSSBS)
+		new |= PSR_SSBS_BIT;
+
+	// PSTATE.BTYPE is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, pages D1-2293 to D1-2294.
+
+	new |= PSR_D_BIT;
+	new |= PSR_A_BIT;
+	new |= PSR_I_BIT;
+	new |= PSR_F_BIT;
+
+	new |= PSR_MODE_EL1h;
+
+	return new;
+}
+
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -59,7 +119,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 
-	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
 	vcpu_write_spsr(vcpu, cpsr);
 
 	vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
@@ -94,7 +154,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 
-	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
 	vcpu_write_spsr(vcpu, cpsr);
 
 	/*
-- 
2.20.1

[PATCH 09/23] KVM: arm/arm64: Correct CPSR on exception entry

[Marc Zyngier]

From: Mark Rutland <mark.rutland@arm.com>

When KVM injects an exception into a guest, it generates the CPSR value
from scratch, configuring CPSR.{M,A,I,T,E}, and setting all other
bits to zero.

This isn't correct, as the architecture specifies that some CPSR bits
are (conditionally) cleared or set upon an exception, and others are
unchanged from the original context.

This patch adds logic to match the architectural behaviour. To make this
simple to follow/audit/extend, documentation references are provided,
and bits are configured in order of their layout in SPSR_EL2. This
layout can be seen in the diagram on ARM DDI 0487E.a page C5-426.

Note that this code is used by both arm and arm64, and is intended to
fuction with the SPSR_EL2 and SPSR_HYP layouts.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200108134324.46500-3-mark.rutland@arm.com
---
 arch/arm/include/asm/kvm_emulate.h |  12 ++++
 arch/arm64/include/asm/ptrace.h    |   1 +
 virt/kvm/arm/aarch32.c             | 111 ++++++++++++++++++++++++++---
 3 files changed, 114 insertions(+), 10 deletions(-)

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index fe55d8737a11..c488c629e6c8 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -14,13 +14,25 @@
 #include <asm/cputype.h>
 
 /* arm64 compatibility macros */
+#define PSR_AA32_MODE_FIQ	FIQ_MODE
+#define PSR_AA32_MODE_SVC	SVC_MODE
 #define PSR_AA32_MODE_ABT	ABT_MODE
 #define PSR_AA32_MODE_UND	UND_MODE
 #define PSR_AA32_T_BIT		PSR_T_BIT
+#define PSR_AA32_F_BIT		PSR_F_BIT
 #define PSR_AA32_I_BIT		PSR_I_BIT
 #define PSR_AA32_A_BIT		PSR_A_BIT
 #define PSR_AA32_E_BIT		PSR_E_BIT
 #define PSR_AA32_IT_MASK	PSR_IT_MASK
+#define PSR_AA32_GE_MASK	0x000f0000
+#define PSR_AA32_DIT_BIT	0x00200000
+#define PSR_AA32_PAN_BIT	0x00400000
+#define PSR_AA32_SSBS_BIT	0x00800000
+#define PSR_AA32_Q_BIT		PSR_Q_BIT
+#define PSR_AA32_V_BIT		PSR_V_BIT
+#define PSR_AA32_C_BIT		PSR_C_BIT
+#define PSR_AA32_Z_BIT		PSR_Z_BIT
+#define PSR_AA32_N_BIT		PSR_N_BIT
 
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index fbebb411ae20..bf57308fcd63 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -62,6 +62,7 @@
 #define PSR_AA32_I_BIT		0x00000080
 #define PSR_AA32_A_BIT		0x00000100
 #define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_PAN_BIT	0x00400000
 #define PSR_AA32_SSBS_BIT	0x00800000
 #define PSR_AA32_DIT_BIT	0x01000000
 #define PSR_AA32_Q_BIT		0x08000000
diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c
index c4c57ba99e90..773cf1439081 100644
--- a/virt/kvm/arm/aarch32.c
+++ b/virt/kvm/arm/aarch32.c
@@ -10,6 +10,7 @@
  * Author: Christoffer Dall <c.dall@virtualopensystems.com>
  */
 
+#include <linux/bits.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
@@ -28,22 +29,112 @@ static const u8 return_offsets[8][2] = {
 	[7] = { 4, 4 },		/* FIQ, unused */
 };
 
+/*
+ * When an exception is taken, most CPSR fields are left unchanged in the
+ * handler. However, some are explicitly overridden (e.g. M[4:0]).
+ *
+ * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with
+ * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was
+ * obsoleted by the ARMv7 virtualization extensions and is RES0.
+ *
+ * For the SPSR layout seen from AArch32, see:
+ * - ARM DDI 0406C.d, page B1-1148
+ * - ARM DDI 0487E.a, page G8-6264
+ *
+ * For the SPSR_ELx layout for AArch32 seen from AArch64, see:
+ * - ARM DDI 0487E.a, page C5-426
+ *
+ * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from
+ * MSB to LSB.
+ */
+static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode)
+{
+	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
+	unsigned long old, new;
+
+	old = *vcpu_cpsr(vcpu);
+	new = 0;
+
+	new |= (old & PSR_AA32_N_BIT);
+	new |= (old & PSR_AA32_Z_BIT);
+	new |= (old & PSR_AA32_C_BIT);
+	new |= (old & PSR_AA32_V_BIT);
+	new |= (old & PSR_AA32_Q_BIT);
+
+	// CPSR.IT[7:0] are set to zero upon any exception
+	// See ARM DDI 0487E.a, section G1.12.3
+	// See ARM DDI 0406C.d, section B1.8.3
+
+	new |= (old & PSR_AA32_DIT_BIT);
+
+	// CPSR.SSBS is set to SCTLR.DSSBS upon any exception
+	// See ARM DDI 0487E.a, page G8-6244
+	if (sctlr & BIT(31))
+		new |= PSR_AA32_SSBS_BIT;
+
+	// CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0
+	// SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented
+	// See ARM DDI 0487E.a, page G8-6246
+	new |= (old & PSR_AA32_PAN_BIT);
+	if (!(sctlr & BIT(23)))
+		new |= PSR_AA32_PAN_BIT;
+
+	// SS does not exist in AArch32, so ignore
+
+	// CPSR.IL is set to zero upon any exception
+	// See ARM DDI 0487E.a, page G1-5527
+
+	new |= (old & PSR_AA32_GE_MASK);
+
+	// CPSR.IT[7:0] are set to zero upon any exception
+	// See prior comment above
+
+	// CPSR.E is set to SCTLR.EE upon any exception
+	// See ARM DDI 0487E.a, page G8-6245
+	// See ARM DDI 0406C.d, page B4-1701
+	if (sctlr & BIT(25))
+		new |= PSR_AA32_E_BIT;
+
+	// CPSR.A is unchanged upon an exception to Undefined, Supervisor
+	// CPSR.A is set upon an exception to other modes
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= (old & PSR_AA32_A_BIT);
+	if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC)
+		new |= PSR_AA32_A_BIT;
+
+	// CPSR.I is set upon any exception
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= PSR_AA32_I_BIT;
+
+	// CPSR.F is set upon an exception to FIQ
+	// CPSR.F is unchanged upon an exception to other modes
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= (old & PSR_AA32_F_BIT);
+	if (mode == PSR_AA32_MODE_FIQ)
+		new |= PSR_AA32_F_BIT;
+
+	// CPSR.T is set to SCTLR.TE upon any exception
+	// See ARM DDI 0487E.a, page G8-5514
+	// See ARM DDI 0406C.d, page B1-1181
+	if (sctlr & BIT(30))
+		new |= PSR_AA32_T_BIT;
+
+	new |= mode;
+
+	return new;
+}
+
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
-	unsigned long cpsr;
 	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
 	bool is_thumb = (new_spsr_value & PSR_AA32_T_BIT);
 	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
 	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
-	cpsr = mode | PSR_AA32_I_BIT;
-
-	if (sctlr & (1 << 30))
-		cpsr |= PSR_AA32_T_BIT;
-	if (sctlr & (1 << 25))
-		cpsr |= PSR_AA32_E_BIT;
-
-	*vcpu_cpsr(vcpu) = cpsr;
+	*vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode);
 
 	/* Note: These now point to the banked copies */
 	vcpu_write_spsr(vcpu, new_spsr_value);
@@ -84,7 +175,7 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		fsr = &vcpu_cp15(vcpu, c5_DFSR);
 	}
 
-	prepare_fault32(vcpu, PSR_AA32_MODE_ABT | PSR_AA32_A_BIT, vect_offset);
+	prepare_fault32(vcpu, PSR_AA32_MODE_ABT, vect_offset);
 
 	*far = addr;
 
-- 
2.20.1

[PATCH 10/23] KVM: arm/arm64: Correct AArch32 SPSR on exception entry

[Marc Zyngier]

From: Mark Rutland <mark.rutland@arm.com>

Confusingly, there are three SPSR layouts that a kernel may need to deal
with:

(1) An AArch64 SPSR_ELx view of an AArch64 pstate
(2) An AArch64 SPSR_ELx view of an AArch32 pstate
(3) An AArch32 SPSR_* view of an AArch32 pstate

When the KVM AArch32 support code deals with SPSR_{EL2,HYP}, it's either
dealing with #2 or #3 consistently. On arm64 the PSR_AA32_* definitions
match the AArch64 SPSR_ELx view, and on arm the PSR_AA32_* definitions
match the AArch32 SPSR_* view.

However, when we inject an exception into an AArch32 guest, we have to
synthesize the AArch32 SPSR_* that the guest will see. Thus, an AArch64
host needs to synthesize layout #3 from layout #2.

This patch adds a new host_spsr_to_spsr32() helper for this, and makes
use of it in the KVM AArch32 support code. For arm64 we need to shuffle
the DIT bit around, and remove the SS bit, while for arm we can use the
value as-is.

I've open-coded the bit manipulation for now to avoid having to rework
the existing PSR_* definitions into PSR64_AA32_* and PSR32_AA32_*
definitions. I hope to perform a more thorough refactoring in future so
that we can handle pstate view manipulation more consistently across the
kernel tree.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200108134324.46500-4-mark.rutland@arm.com
---
 arch/arm/include/asm/kvm_emulate.h   |  5 +++++
 arch/arm64/include/asm/kvm_emulate.h | 32 ++++++++++++++++++++++++++++
 virt/kvm/arm/aarch32.c               |  6 +++---
 3 files changed, 40 insertions(+), 3 deletions(-)

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index c488c629e6c8..08d9805f613b 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -53,6 +53,11 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	*__vcpu_spsr(vcpu) = v;
 }
 
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	return spsr;
+}
+
 static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu,
 					 u8 reg_num)
 {
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index f407b6bdad2e..53ea7637b7b2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -219,6 +219,38 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
 }
 
+/*
+ * The layout of SPSR for an AArch32 state is different when observed from an
+ * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
+ * view given an AArch64 view.
+ *
+ * In ARM DDI 0487E.a see:
+ *
+ * - The AArch64 view (SPSR_EL2) in section C5.2.18, page C5-426
+ * - The AArch32 view (SPSR_abt) in section G8.2.126, page G8-6256
+ * - The AArch32 view (SPSR_und) in section G8.2.132, page G8-6280
+ *
+ * Which show the following differences:
+ *
+ * | Bit | AA64 | AA32 | Notes                       |
+ * +-----+------+------+-----------------------------|
+ * | 24  | DIT  | J    | J is RES0 in ARMv8          |
+ * | 21  | SS   | DIT  | SS doesn't exist in AArch32 |
+ *
+ * ... and all other bits are (currently) common.
+ */
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	const unsigned long overlap = BIT(24) | BIT(21);
+	unsigned long dit = !!(spsr & PSR_AA32_DIT_BIT);
+
+	spsr &= ~overlap;
+
+	spsr |= dit << 21;
+
+	return spsr;
+}
+
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 {
 	u32 mode;
diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c
index 773cf1439081..631d397ac81b 100644
--- a/virt/kvm/arm/aarch32.c
+++ b/virt/kvm/arm/aarch32.c
@@ -129,15 +129,15 @@ static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode)
 
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
-	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
-	bool is_thumb = (new_spsr_value & PSR_AA32_T_BIT);
+	unsigned long spsr = *vcpu_cpsr(vcpu);
+	bool is_thumb = (spsr & PSR_AA32_T_BIT);
 	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
 	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
 	*vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode);
 
 	/* Note: These now point to the banked copies */
-	vcpu_write_spsr(vcpu, new_spsr_value);
+	vcpu_write_spsr(vcpu, host_spsr_to_spsr32(spsr));
 	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
-- 
2.20.1