1 files changed, 197 insertions, 100 deletions

diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index aacfc55de44c..617ae6dea5d5 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -14,43 +14,46 @@
 #include <asm/esr.h>
 #include <asm/exception.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_nested.h>
 #include <asm/debug-monitors.h>
+#include <asm/stacktrace/nvhe.h>
 #include <asm/traps.h>
 
 #include <kvm/arm_hypercalls.h>
 
 #define CREATE_TRACE_POINTS
-#include "trace.h"
+#include "trace_handle_exit.h"
 
-typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
+typedef int (*exit_handle_fn)(struct kvm_vcpu *);
 
-static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u32 esr)
+static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u64 esr)
 {
 	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(NULL, esr))
 		kvm_inject_vabt(vcpu);
 }
 
-static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_hvc(struct kvm_vcpu *vcpu)
 {
-	int ret;
-
 	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0),
 			    kvm_vcpu_hvc_get_imm(vcpu));
 	vcpu->stat.hvc_exit_stat++;
 
-	ret = kvm_hvc_call_handler(vcpu);
-	if (ret < 0) {
-		vcpu_set_reg(vcpu, 0, ~0UL);
+	/* Forward hvc instructions to the virtual EL2 if the guest has EL2. */
+	if (vcpu_has_nv(vcpu)) {
+		if (vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_HCD)
+			kvm_inject_undefined(vcpu);
+		else
+			kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
 		return 1;
 	}
 
-	return ret;
+	return kvm_smccc_call_handler(vcpu);
 }
 
-static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_smc(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * "If an SMC instruction executed at Non-secure EL1 is
@@ -58,18 +61,36 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	 * Trap exception, not a Secure Monitor Call exception [...]"
 	 *
 	 * We need to advance the PC after the trap, as it would
-	 * otherwise return to the same address...
+	 * otherwise return to the same address. Furthermore, pre-incrementing
+	 * the PC before potentially exiting to userspace maintains the same
+	 * abstraction for both SMCs and HVCs.
 	 */
-	vcpu_set_reg(vcpu, 0, ~0UL);
-	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-	return 1;
+	kvm_incr_pc(vcpu);
+
+	/*
+	 * SMCs with a nonzero immediate are reserved according to DEN0028E 2.9
+	 * "SMC and HVC immediate value".
+	 */
+	if (kvm_vcpu_hvc_get_imm(vcpu)) {
+		vcpu_set_reg(vcpu, 0, ~0UL);
+		return 1;
+	}
+
+	/*
+	 * If imm is zero then it is likely an SMCCC call.
+	 *
+	 * Note that on ARMv8.3, even if EL3 is not implemented, SMC executed
+	 * at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than
+	 * being treated as UNDEFINED.
+	 */
+	return kvm_smccc_call_handler(vcpu);
 }
 
 /*
  * Guest access to FP/ASIMD registers are routed to this handler only
  * when the system doesn't support FP/ASIMD.
  */
-static int handle_no_fpsimd(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_no_fpsimd(struct kvm_vcpu *vcpu)
 {
 	kvm_inject_undefined(vcpu);
 	return 1;
@@ -81,26 +102,52 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu, struct kvm_run *run)
  *
  * @vcpu:	the vcpu pointer
  *
- * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * WFE[T]: Yield the CPU and come back to this vcpu when the scheduler
  * decides to.
- * WFI: Simply call kvm_vcpu_block(), which will halt execution of
+ * WFI: Simply call kvm_vcpu_halt(), which will halt execution of
  * world-switches and schedule other host processes until there is an
  * incoming IRQ or FIQ to the VM.
+ * WFIT: Same as WFI, with a timed wakeup implemented as a background timer
+ *
+ * WF{I,E}T can immediately return if the deadline has already expired.
  */
-static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 {
-	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+
+	if (esr & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
 		vcpu->stat.wfe_exit_stat++;
-		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
 	} else {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
 		vcpu->stat.wfi_exit_stat++;
-		kvm_vcpu_block(vcpu);
-		kvm_clear_request(KVM_REQ_UNHALT, vcpu);
 	}
 
-	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	if (esr & ESR_ELx_WFx_ISS_WFxT) {
+		if (esr & ESR_ELx_WFx_ISS_RV) {
+			u64 val, now;
+
+			now = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_TIMER_CNT);
+			val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
+
+			if (now >= val)
+				goto out;
+		} else {
+			/* Treat WFxT as WFx if RN is invalid */
+			esr &= ~ESR_ELx_WFx_ISS_WFxT;
+		}
+	}
+
+	if (esr & ESR_ELx_WFx_ISS_WFE) {
+		kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
+	} else {
+		if (esr & ESR_ELx_WFx_ISS_WFxT)
+			vcpu_set_flag(vcpu, IN_WFIT);
+
+		kvm_vcpu_wfi(vcpu);
+	}
+out:
+	kvm_incr_pc(vcpu);
 
 	return 1;
 }
@@ -109,93 +156,99 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * kvm_handle_guest_debug - handle a debug exception instruction
  *
  * @vcpu:	the vcpu pointer
- * @run:	access to the kvm_run structure for results
  *
  * We route all debug exceptions through the same handler. If both the
  * guest and host are using the same debug facilities it will be up to
  * userspace to re-inject the correct exception for guest delivery.
  *
- * @return: 0 (while setting run->exit_reason), -1 for error
+ * @return: 0 (while setting vcpu->run->exit_reason)
  */
-static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
-	int ret = 0;
+	struct kvm_run *run = vcpu->run;
+	u64 esr = kvm_vcpu_get_esr(vcpu);
 
 	run->exit_reason = KVM_EXIT_DEBUG;
-	run->debug.arch.hsr = hsr;
+	run->debug.arch.hsr = lower_32_bits(esr);
+	run->debug.arch.hsr_high = upper_32_bits(esr);
+	run->flags = KVM_DEBUG_ARCH_HSR_HIGH_VALID;
 
-	switch (ESR_ELx_EC(hsr)) {
+	switch (ESR_ELx_EC(esr)) {
 	case ESR_ELx_EC_WATCHPT_LOW:
 		run->debug.arch.far = vcpu->arch.fault.far_el2;
-		/* fall through */
-	case ESR_ELx_EC_SOFTSTP_LOW:
-	case ESR_ELx_EC_BREAKPT_LOW:
-	case ESR_ELx_EC_BKPT32:
-	case ESR_ELx_EC_BRK64:
 		break;
-	default:
-		kvm_err("%s: un-handled case hsr: %#08x\n",
-			__func__, (unsigned int) hsr);
-		ret = -1;
+	case ESR_ELx_EC_SOFTSTP_LOW:
+		vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING);
 		break;
 	}
 
-	return ret;
+	return 0;
 }
 
-static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	u64 esr = kvm_vcpu_get_esr(vcpu);
 
-	kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
-		      hsr, esr_get_class_string(hsr));
+	kvm_pr_unimpl("Unknown exception class: esr: %#016llx -- %s\n",
+		      esr, esr_get_class_string(esr));
 
 	kvm_inject_undefined(vcpu);
 	return 1;
 }
 
-static int handle_sve(struct kvm_vcpu *vcpu, struct kvm_run *run)
+/*
+ * Guest access to SVE registers should be routed to this handler only
+ * when the system doesn't support SVE.
+ */
+static int handle_sve(struct kvm_vcpu *vcpu)
 {
-	/* Until SVE is supported for guests: */
 	kvm_inject_undefined(vcpu);
 	return 1;
 }
 
-#define __ptrauth_save_key(regs, key)						\
-({										\
-	regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);	\
-	regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);	\
-})
-
 /*
- * Handle the guest trying to use a ptrauth instruction, or trying to access a
- * ptrauth register.
+ * Guest usage of a ptrauth instruction (which the guest EL1 did not turn into
+ * a NOP). If we get here, it is that we didn't fixup ptrauth on exit, and all
+ * that we can do is give the guest an UNDEF.
  */
-void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu)
+static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *ctxt;
-
-	if (vcpu_has_ptrauth(vcpu)) {
-		vcpu_ptrauth_enable(vcpu);
-		ctxt = vcpu->arch.host_cpu_context;
-		__ptrauth_save_key(ctxt->sys_regs, APIA);
-		__ptrauth_save_key(ctxt->sys_regs, APIB);
-		__ptrauth_save_key(ctxt->sys_regs, APDA);
-		__ptrauth_save_key(ctxt->sys_regs, APDB);
-		__ptrauth_save_key(ctxt->sys_regs, APGA);
-	} else {
-		kvm_inject_undefined(vcpu);
-	}
+	kvm_inject_undefined(vcpu);
+	return 1;
 }
 
-/*
- * Guest usage of a ptrauth instruction (which the guest EL1 did not turn into
- * a NOP).
- */
-static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_eret(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET)
+		return kvm_handle_ptrauth(vcpu);
+
+	/*
+	 * If we got here, two possibilities:
+	 *
+	 * - the guest is in EL2, and we need to fully emulate ERET
+	 *
+	 * - the guest is in EL1, and we need to reinject the
+         *   exception into the L1 hypervisor.
+	 *
+	 * If KVM ever traps ERET for its own use, we'll have to
+	 * revisit this.
+	 */
+	if (is_hyp_ctxt(vcpu))
+		kvm_emulate_nested_eret(vcpu);
+	else
+		kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
+
+	return 1;
+}
+
+static int handle_svc(struct kvm_vcpu *vcpu)
 {
-	kvm_arm_vcpu_ptrauth_trap(vcpu);
+	/*
+	 * So far, SVC traps only for NV via HFGITR_EL2. A SVC from a
+	 * 32bit guest would be caught by vpcu_mode_is_bad_32bit(), so
+	 * we should only have to deal with a 64 bit exception.
+	 */
+	kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
 	return 1;
 }
 
@@ -206,13 +259,16 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_CP15_64]	= kvm_handle_cp15_64,
 	[ESR_ELx_EC_CP14_MR]	= kvm_handle_cp14_32,
 	[ESR_ELx_EC_CP14_LS]	= kvm_handle_cp14_load_store,
+	[ESR_ELx_EC_CP10_ID]	= kvm_handle_cp10_id,
 	[ESR_ELx_EC_CP14_64]	= kvm_handle_cp14_64,
 	[ESR_ELx_EC_HVC32]	= handle_hvc,
 	[ESR_ELx_EC_SMC32]	= handle_smc,
 	[ESR_ELx_EC_HVC64]	= handle_hvc,
 	[ESR_ELx_EC_SMC64]	= handle_smc,
+	[ESR_ELx_EC_SVC64]	= handle_svc,
 	[ESR_ELx_EC_SYS64]	= kvm_handle_sys_reg,
 	[ESR_ELx_EC_SVE]	= handle_sve,
+	[ESR_ELx_EC_ERET]	= kvm_handle_eret,
 	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_DABT_LOW]	= kvm_handle_guest_abort,
 	[ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug,
@@ -226,10 +282,10 @@ static exit_handle_fn arm_exit_handlers[] = {
 
 static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 {
-	u32 hsr = kvm_vcpu_get_hsr(vcpu);
-	u8 hsr_ec = ESR_ELx_EC(hsr);
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	u8 esr_ec = ESR_ELx_EC(esr);
 
-	return arm_exit_handlers[hsr_ec];
+	return arm_exit_handlers[esr_ec];
 }
 
 /*
@@ -238,7 +294,7 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
  * KVM_EXIT_DEBUG, otherwise userspace needs to complete its
  * emulation first.
  */
-static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_trap_exceptions(struct kvm_vcpu *vcpu)
 {
 	int handled;
 
@@ -247,13 +303,13 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	 * that fail their condition code check"
 	 */
 	if (!kvm_condition_valid(vcpu)) {
-		kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		kvm_incr_pc(vcpu);
 		handled = 1;
 	} else {
 		exit_handle_fn exit_handler;
 
 		exit_handler = kvm_get_exit_handler(vcpu);
-		handled = exit_handler(vcpu, run);
+		handled = exit_handler(vcpu);
 	}
 
 	return handled;
@@ -263,23 +319,15 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
  * proper exit to userspace.
  */
-int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		       int exception_index)
+int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
 {
-	if (ARM_SERROR_PENDING(exception_index)) {
-		u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
+	struct kvm_run *run = vcpu->run;
 
+	if (ARM_SERROR_PENDING(exception_index)) {
 		/*
-		 * HVC/SMC already have an adjusted PC, which we need
-		 * to correct in order to return to after having
-		 * injected the SError.
+		 * The SError is handled by handle_exit_early(). If the guest
+		 * survives it will re-execute the original instruction.
 		 */
-		if (hsr_ec == ESR_ELx_EC_HVC32 || hsr_ec == ESR_ELx_EC_HVC64 ||
-		    hsr_ec == ESR_ELx_EC_SMC32 || hsr_ec == ESR_ELx_EC_SMC64) {
-			u32 adj =  kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2;
-			*vcpu_pc(vcpu) -= adj;
-		}
-
 		return 1;
 	}
 
@@ -291,11 +339,11 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	case ARM_EXCEPTION_EL1_SERROR:
 		return 1;
 	case ARM_EXCEPTION_TRAP:
-		return handle_trap_exceptions(vcpu, run);
+		return handle_trap_exceptions(vcpu);
 	case ARM_EXCEPTION_HYP_GONE:
 		/*
 		 * EL2 has been reset to the hyp-stub. This happens when a guest
-		 * is pre-empted by kvm_reboot()'s shutdown call.
+		 * is pre-emptied by kvm_reboot()'s shutdown call.
 		 */
 		run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		return 0;
@@ -315,8 +363,7 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 }
 
 /* For exit types that need handling before we can be preempted */
-void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		       int exception_index)
+void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
 {
 	if (ARM_SERROR_PENDING(exception_index)) {
 		if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN)) {
@@ -333,5 +380,55 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	exception_index = ARM_EXCEPTION_CODE(exception_index);
 
 	if (exception_index == ARM_EXCEPTION_EL1_SERROR)
-		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_hsr(vcpu));
+		kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
+}
+
+void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
+					      u64 elr_virt, u64 elr_phys,
+					      u64 par, uintptr_t vcpu,
+					      u64 far, u64 hpfar) {
+	u64 elr_in_kimg = __phys_to_kimg(elr_phys);
+	u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr_virt;
+	u64 mode = spsr & PSR_MODE_MASK;
+	u64 panic_addr = elr_virt + hyp_offset;
+
+	if (mode != PSR_MODE_EL2t && mode != PSR_MODE_EL2h) {
+		kvm_err("Invalid host exception to nVHE hyp!\n");
+	} else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
+		   (esr & ESR_ELx_BRK64_ISS_COMMENT_MASK) == BUG_BRK_IMM) {
+		const char *file = NULL;
+		unsigned int line = 0;
+
+		/* All hyp bugs, including warnings, are treated as fatal. */
+		if (!is_protected_kvm_enabled() ||
+		    IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
+			struct bug_entry *bug = find_bug(elr_in_kimg);
+
+			if (bug)
+				bug_get_file_line(bug, &file, &line);
+		}
+
+		if (file)
+			kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line);
+		else
+			kvm_err("nVHE hyp BUG at: [<%016llx>] %pB!\n", panic_addr,
+					(void *)(panic_addr + kaslr_offset()));
+	} else {
+		kvm_err("nVHE hyp panic at: [<%016llx>] %pB!\n", panic_addr,
+				(void *)(panic_addr + kaslr_offset()));
+	}
+
+	/* Dump the nVHE hypervisor backtrace */
+	kvm_nvhe_dump_backtrace(hyp_offset);
+
+	/*
+	 * Hyp has panicked and we're going to handle that by panicking the
+	 * kernel. The kernel offset will be revealed in the panic so we're
+	 * also safe to reveal the hyp offset as a debugging aid for translating
+	 * hyp VAs to vmlinux addresses.
+	 */
+	kvm_err("Hyp Offset: 0x%llx\n", hyp_offset);
+
+	panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%016llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%016lx\n",
+	      spsr, elr_virt, esr, far, hpfar, par, vcpu);
 }