KVM: arm64: nVHE: Handle hyp panics

Restore the host context when panicking from hyp to give the best chance
of the panic being clean.

The host requires that registers be preserved such as x18 for the shadow
callstack. If the panic is caused by an exception from EL1, the host
context is still valid so the panic can return straight back to the
host. If the panic comes from EL2 then it's most likely that the hyp
context is active and the host context needs to be restored.

There are windows before and after the host context is saved and
restored that restoration is attempted incorrectly and the panic won't
be clean.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200915104643.2543892-14-ascull@google.com

2 files changed, 63 insertions, 33 deletions

diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index d26e41773dc4..ff9a0f547b9f 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -47,6 +47,9 @@ SYM_FUNC_START(__host_exit)
 	ldp	x2, x3,   [x29, #CPU_XREG_OFFSET(2)]
 	ldp	x4, x5,   [x29, #CPU_XREG_OFFSET(4)]
 	ldp	x6, x7,   [x29, #CPU_XREG_OFFSET(6)]
+
+	/* x0-7 are use for panic arguments */
+__host_enter_for_panic:
 	ldp	x8, x9,   [x29, #CPU_XREG_OFFSET(8)]
 	ldp	x10, x11, [x29, #CPU_XREG_OFFSET(10)]
 	ldp	x12, x13, [x29, #CPU_XREG_OFFSET(12)]
@@ -57,18 +60,38 @@ SYM_FUNC_START(__host_exit)
 	restore_callee_saved_regs x29
 
 	/* Do not touch any register after this! */
+__host_enter_without_restoring:
 	eret
 	sb
 SYM_FUNC_END(__host_exit)
 
+/*
+ * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+ */
 SYM_FUNC_START(__hyp_do_panic)
+	/* Load the format arguments into x1-7 */
+	mov	x6, x3
+	get_vcpu_ptr x7, x3
+
+	mrs	x3, esr_el2
+	mrs	x4, far_el2
+	mrs	x5, hpfar_el2
+
+	/* Prepare and exit to the host's panic funciton. */
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
 	msr	spsr_el2, lr
 	ldr	lr, =panic
 	msr	elr_el2, lr
-	eret
-	sb
+
+	/*
+	 * Set the panic format string and enter the host, conditionally
+	 * restoring the host context.
+	 */
+	cmp	x0, xzr
+	ldr	x0, =__hyp_panic_string
+	b.eq	__host_enter_without_restoring
+	b	__host_enter_for_panic
 SYM_FUNC_END(__hyp_do_panic)
 
 .macro host_el1_sync_vect
@@ -79,7 +102,7 @@ SYM_FUNC_END(__hyp_do_panic)
 	lsr	x0, x0, #ESR_ELx_EC_SHIFT
 	cmp	x0, #ESR_ELx_EC_HVC64
 	ldp	x0, x1, [sp], #16
-	b.ne	hyp_panic
+	b.ne	__host_exit
 
 	/* Check for a stub HVC call */
 	cmp	x0, #HVC_STUB_HCALL_NR
@@ -105,16 +128,31 @@ SYM_FUNC_END(__hyp_do_panic)
 .endif
 .endm
 
-.macro invalid_host_vect
+.macro invalid_host_el2_vect
 	.align 7
 	/* If a guest is loaded, panic out of it. */
 	stp	x0, x1, [sp, #-16]!
 	get_loaded_vcpu x0, x1
 	cbnz	x0, __guest_exit_panic
 	add	sp, sp, #16
+
+	/*
+	 * The panic may not be clean if the exception is taken before the host
+	 * context has been saved by __host_exit or after the hyp context has
+	 * been partially clobbered by __host_enter.
+	 */
 	b	hyp_panic
 .endm
 
+.macro invalid_host_el1_vect
+	.align 7
+	mov	x0, xzr		/* restore_host = false */
+	mrs	x1, spsr_el2
+	mrs	x2, elr_el2
+	mrs	x3, par_el1
+	b	__hyp_do_panic
+.endm
+
 /*
  * The host vector does not use an ESB instruction in order to avoid consuming
  * SErrors that should only be consumed by the host. Guest entry is deferred by
@@ -127,23 +165,23 @@ SYM_FUNC_END(__hyp_do_panic)
  */
 	.align 11
 SYM_CODE_START(__kvm_hyp_host_vector)
-	invalid_host_vect			// Synchronous EL2t
-	invalid_host_vect			// IRQ EL2t
-	invalid_host_vect			// FIQ EL2t
-	invalid_host_vect			// Error EL2t
+	invalid_host_el2_vect			// Synchronous EL2t
+	invalid_host_el2_vect			// IRQ EL2t
+	invalid_host_el2_vect			// FIQ EL2t
+	invalid_host_el2_vect			// Error EL2t
 
-	invalid_host_vect			// Synchronous EL2h
-	invalid_host_vect			// IRQ EL2h
-	invalid_host_vect			// FIQ EL2h
-	invalid_host_vect			// Error EL2h
+	invalid_host_el2_vect			// Synchronous EL2h
+	invalid_host_el2_vect			// IRQ EL2h
+	invalid_host_el2_vect			// FIQ EL2h
+	invalid_host_el2_vect			// Error EL2h
 
 	host_el1_sync_vect			// Synchronous 64-bit EL1
-	invalid_host_vect			// IRQ 64-bit EL1
-	invalid_host_vect			// FIQ 64-bit EL1
-	invalid_host_vect			// Error 64-bit EL1
-
-	invalid_host_vect			// Synchronous 32-bit EL1
-	invalid_host_vect			// IRQ 32-bit EL1
-	invalid_host_vect			// FIQ 32-bit EL1
-	invalid_host_vect			// Error 32-bit EL1
+	invalid_host_el1_vect			// IRQ 64-bit EL1
+	invalid_host_el1_vect			// FIQ 64-bit EL1
+	invalid_host_el1_vect			// Error 64-bit EL1
+
+	invalid_host_el1_vect			// Synchronous 32-bit EL1
+	invalid_host_el1_vect			// IRQ 32-bit EL1
+	invalid_host_el1_vect			// FIQ 32-bit EL1
+	invalid_host_el1_vect			// Error 32-bit EL1
 SYM_CODE_END(__kvm_hyp_host_vector)
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index c99945cda779..29febf9a93f2 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -242,6 +242,8 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (system_uses_irq_prio_masking())
 		gic_write_pmr(GIC_PRIO_IRQOFF);
 
+	host_ctxt->__hyp_running_vcpu = NULL;
+
 	return exit_code;
 }
 
@@ -250,31 +252,21 @@ void __noreturn hyp_panic(void)
 	u64 spsr = read_sysreg_el2(SYS_SPSR);
 	u64 elr = read_sysreg_el2(SYS_ELR);
 	u64 par = read_sysreg(par_el1);
+	bool restore_host = true;
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
-	unsigned long str_va;
 
 	host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
 	vcpu = host_ctxt->__hyp_running_vcpu;
 
-	if (read_sysreg(vttbr_el2)) {
+	if (vcpu) {
 		__timer_disable_traps(vcpu);
 		__deactivate_traps(vcpu);
 		__load_host_stage2();
 		__sysreg_restore_state_nvhe(host_ctxt);
 	}
 
-	/*
-	 * Force the panic string to be loaded from the literal pool,
-	 * making sure it is a kernel address and not a PC-relative
-	 * reference.
-	 */
-	asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
-
-	__hyp_do_panic(str_va,
-		       spsr, elr,
-		       read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
-		       read_sysreg(hpfar_el2), par, vcpu);
+	__hyp_do_panic(restore_host, spsr, elr, par);
 	unreachable();
 }