arm64: KVM: Move most of the fault decoding to C

The fault decoding process (including computing the IPA in the case
of a permission fault) would be much better done in C code, as we
have a reasonable infrastructure to deal with the VHE/non-VHE
differences.

Let's move the whole thing to C, including the workaround for
erratum 834220, and just patch the odd ESR_EL2 access remaining
in hyp-entry.S.

Reviewed-by: Christoffer Dall <[e-mail]>
Acked-by: Catalin Marinas <[e-mail]>
Signed-off-by: Marc Zyngier <[e-mail]>

arch/arm64/kernel/asm-offsets.c

···
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
   DEFINE(VCPU_FPEXC32_EL2,	offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
-  DEFINE(VCPU_ESR_EL2,		offsetof(struct kvm_vcpu, arch.fault.esr_el2));
-  DEFINE(VCPU_FAR_EL2,		offsetof(struct kvm_vcpu, arch.fault.far_el2));
-  DEFINE(VCPU_HPFAR_EL2,	offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
 #endif
 #ifdef CONFIG_CPU_PM

arch/arm64/kvm/hyp/hyp-entry.S

···
 
 #include <asm/alternative.h>
 #include <asm/assembler.h>
-#include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
···
 el1_sync:				// Guest trapped into EL2
 	save_x0_to_x3
 
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	x1, esr_el2
+alternative_else
+	mrs	x1, esr_el1
+alternative_endif
 	lsr	x2, x1, #ESR_ELx_EC_SHIFT
 
 	cmp	x2, #ESR_ELx_EC_HVC64
···
 	cmp	x2, #ESR_ELx_EC_FP_ASIMD
 	b.eq	__fpsimd_guest_restore
 
-	cmp	x2, #ESR_ELx_EC_DABT_LOW
-	mov	x0, #ESR_ELx_EC_IABT_LOW
-	ccmp	x2, x0, #4, ne
-	b.ne	1f		// Not an abort we care about
-
-	/* This is an abort. Check for permission fault */
-alternative_if_not ARM64_WORKAROUND_834220
-	and	x2, x1, #ESR_ELx_FSC_TYPE
-	cmp	x2, #FSC_PERM
-	b.ne	1f		// Not a permission fault
-alternative_else
-	nop			// Use the permission fault path to
-	nop			// check for a valid S1 translation,
-	nop			// regardless of the ESR value.
-alternative_endif
-
-	/*
-	 * Check for Stage-1 page table walk, which is guaranteed
-	 * to give a valid HPFAR_EL2.
-	 */
-	tbnz	x1, #7, 1f	// S1PTW is set
-
-	/* Preserve PAR_EL1 */
-	mrs	x3, par_el1
-	stp	x3, xzr, [sp, #-16]!
-
-	/*
-	 * Permission fault, HPFAR_EL2 is invalid.
-	 * Resolve the IPA the hard way using the guest VA.
-	 * Stage-1 translation already validated the memory access rights.
-	 * As such, we can use the EL1 translation regime, and don't have
-	 * to distinguish between EL0 and EL1 access.
-	 */
-	mrs	x2, far_el2
-	at	s1e1r, x2
-	isb
-
-	/* Read result */
-	mrs	x3, par_el1
-	ldp	x0, xzr, [sp], #16	// Restore PAR_EL1 from the stack
-	msr	par_el1, x0
-	tbnz	x3, #0, 3f		// Bail out if we failed the translation
-	ubfx	x3, x3, #12, #36	// Extract IPA
-	lsl	x3, x3, #4		// and present it like HPFAR
-	b	2f
-
-1:	mrs	x3, hpfar_el2
-	mrs	x2, far_el2
-
-2:	mrs	x0, tpidr_el2
-	str	w1, [x0, #VCPU_ESR_EL2]
-	str	x2, [x0, #VCPU_FAR_EL2]
-	str	x3, [x0, #VCPU_HPFAR_EL2]
-
+	mrs	x0, tpidr_el2
 	mov	x1, #ARM_EXCEPTION_TRAP
 	b	__guest_exit
-
-	/*
-	 * Translation failed. Just return to the guest and
-	 * let it fault again. Another CPU is probably playing
-	 * behind our back.
-	 */
-3:	restore_x0_to_x3
-
-	eret
 
 el1_irq:
 	save_x0_to_x3

arch/arm64/kvm/hyp/switch.c

···
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/types.h>
 #include <asm/kvm_asm.h>
 
 #include "hyp.h"
···
 	__vgic_call_restore_state()(vcpu);
 }
 
+static bool __hyp_text __true_value(void)
+{
+	return true;
+}
+
+static bool __hyp_text __false_value(void)
+{
+	return false;
+}
+
+static hyp_alternate_select(__check_arm_834220,
+			    __false_value, __true_value,
+			    ARM64_WORKAROUND_834220);
+
+static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+	u64 par, tmp;
+
+	/*
+	 * Resolve the IPA the hard way using the guest VA.
+	 *
+	 * Stage-1 translation already validated the memory access
+	 * rights. As such, we can use the EL1 translation regime, and
+	 * don't have to distinguish between EL0 and EL1 access.
+	 *
+	 * We do need to save/restore PAR_EL1 though, as we haven't
+	 * saved the guest context yet, and we may return early...
+	 */
+	par = read_sysreg(par_el1);
+	asm volatile("at s1e1r, %0" : : "r" (far));
+	isb();
+
+	tmp = read_sysreg(par_el1);
+	write_sysreg(par, par_el1);
+
+	if (unlikely(tmp & 1))
+		return false; /* Translation failed, back to guest */
+
+	/* Convert PAR to HPFAR format */
+	*hpfar = ((tmp >> 12) & ((1UL << 36) - 1)) << 4;
+	return true;
+}
+
+static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+	u64 esr = read_sysreg_el2(esr);
+	u8 ec = esr >> ESR_ELx_EC_SHIFT;
+	u64 hpfar, far;
+
+	vcpu->arch.fault.esr_el2 = esr;
+
+	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
+		return true;
+
+	far = read_sysreg_el2(far);
+
+	/*
+	 * The HPFAR can be invalid if the stage 2 fault did not
+	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+	 * bit is clear) and one of the two following cases are true:
+	 *   1. The fault was due to a permission fault
+	 *   2. The processor carries errata 834220
+	 *
+	 * Therefore, for all non S1PTW faults where we either have a
+	 * permission fault or the errata workaround is enabled, we
+	 * resolve the IPA using the AT instruction.
+	 */
+	if (!(esr & ESR_ELx_S1PTW) &&
+	    (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+		if (!__translate_far_to_hpfar(far, &hpfar))
+			return false;
+	} else {
+		hpfar = read_sysreg(hpfar_el2);
+	}
+
+	vcpu->arch.fault.far_el2 = far;
+	vcpu->arch.fault.hpfar_el2 = hpfar;
+	return true;
+}
+
 static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
···
 	__debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
 
 	/* Jump in the fire! */
+again:
 	exit_code = __guest_enter(vcpu, host_ctxt);
 	/* And we're baaack! */
+
+	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
+		goto again;
 
 	fp_enabled = __fpsimd_enabled();