linux-stable/arch/arm64/kvm/inject_fault.c
Mark Rutland a425372e73 KVM: arm64: Correct PSTATE on exception entry
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
2020-01-19 18:06:13 +00:00

237 lines
6.5 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Fault injection for both 32 and 64bit guests.
*
* Copyright (C) 2012,2013 - ARM Ltd
* Author: Marc Zyngier <marc.zyngier@arm.com>
*
* Based on arch/arm/kvm/emulate.c
* Copyright (C) 2012 - Virtual Open Systems and Columbia University
* Author: Christoffer Dall <c.dall@virtualopensystems.com>
*/
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/esr.h>
#define CURRENT_EL_SP_EL0_VECTOR 0x0
#define CURRENT_EL_SP_ELx_VECTOR 0x200
#define LOWER_EL_AArch64_VECTOR 0x400
#define LOWER_EL_AArch32_VECTOR 0x600
enum exception_type {
except_type_sync = 0,
except_type_irq = 0x80,
except_type_fiq = 0x100,
except_type_serror = 0x180,
};
static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
{
u64 exc_offset;
switch (*vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT)) {
case PSR_MODE_EL1t:
exc_offset = CURRENT_EL_SP_EL0_VECTOR;
break;
case PSR_MODE_EL1h:
exc_offset = CURRENT_EL_SP_ELx_VECTOR;
break;
case PSR_MODE_EL0t:
exc_offset = LOWER_EL_AArch64_VECTOR;
break;
default:
exc_offset = LOWER_EL_AArch32_VECTOR;
}
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);
bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
u32 esr = 0;
vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
vcpu_write_spsr(vcpu, cpsr);
vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
/*
* Build an {i,d}abort, depending on the level and the
* instruction set. Report an external synchronous abort.
*/
if (kvm_vcpu_trap_il_is32bit(vcpu))
esr |= ESR_ELx_IL;
/*
* Here, the guest runs in AArch64 mode when in EL1. If we get
* an AArch32 fault, it means we managed to trap an EL0 fault.
*/
if (is_aarch32 || (cpsr & PSR_MODE_MASK) == PSR_MODE_EL0t)
esr |= (ESR_ELx_EC_IABT_LOW << ESR_ELx_EC_SHIFT);
else
esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);
if (!is_iabt)
esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;
vcpu_write_sys_reg(vcpu, esr | ESR_ELx_FSC_EXTABT, ESR_EL1);
}
static void inject_undef64(struct kvm_vcpu *vcpu)
{
unsigned long cpsr = *vcpu_cpsr(vcpu);
u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
vcpu_write_spsr(vcpu, cpsr);
/*
* Build an unknown exception, depending on the instruction
* set.
*/
if (kvm_vcpu_trap_il_is32bit(vcpu))
esr |= ESR_ELx_IL;
vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
}
/**
* kvm_inject_dabt - inject a data abort into the guest
* @vcpu: The VCPU to receive the data abort
* @addr: The address to report in the DFAR
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
*/
void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
{
if (vcpu_el1_is_32bit(vcpu))
kvm_inject_dabt32(vcpu, addr);
else
inject_abt64(vcpu, false, addr);
}
/**
* kvm_inject_pabt - inject a prefetch abort into the guest
* @vcpu: The VCPU to receive the prefetch abort
* @addr: The address to report in the DFAR
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
*/
void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
{
if (vcpu_el1_is_32bit(vcpu))
kvm_inject_pabt32(vcpu, addr);
else
inject_abt64(vcpu, true, addr);
}
/**
* kvm_inject_undefined - inject an undefined instruction into the guest
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
*/
void kvm_inject_undefined(struct kvm_vcpu *vcpu)
{
if (vcpu_el1_is_32bit(vcpu))
kvm_inject_undef32(vcpu);
else
inject_undef64(vcpu);
}
void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 esr)
{
vcpu_set_vsesr(vcpu, esr & ESR_ELx_ISS_MASK);
*vcpu_hcr(vcpu) |= HCR_VSE;
}
/**
* kvm_inject_vabt - inject an async abort / SError into the guest
* @vcpu: The VCPU to receive the exception
*
* It is assumed that this code is called from the VCPU thread and that the
* VCPU therefore is not currently executing guest code.
*
* Systems with the RAS Extensions specify an imp-def ESR (ISV/IDS = 1) with
* the remaining ISS all-zeros so that this error is not interpreted as an
* uncategorized RAS error. Without the RAS Extensions we can't specify an ESR
* value, so the CPU generates an imp-def value.
*/
void kvm_inject_vabt(struct kvm_vcpu *vcpu)
{
kvm_set_sei_esr(vcpu, ESR_ELx_ISV);
}