KVM: ARM: Emulation framework and CP15 emulation

Adds a new important function in the main KVM/ARM code called
handle_exit() which is called from kvm_arch_vcpu_ioctl_run() on returns
from guest execution. This function examines the Hyp-Syndrome-Register
(HSR), which contains information telling KVM what caused the exit from
the guest.

Some of the reasons for an exit are CP15 accesses, which are
not allowed from the guest and this commit handles these exits by
emulating the intended operation in software and skipping the guest
instruction.

Minor notes about the coproc register reset:
1) We reserve a value of 0 as an invalid cp15 offset, to catch bugs in our
   table, at cost of 4 bytes per vcpu.

2) Added comments on the table indicating how we handle each register, for
   simplicity of understanding.

Reviewed-by: Will Deacon <will.deacon@arm.com>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Christoffer Dall <c.dall@virtualopensystems.com>

arch/arm/include/asm/kvm_arm.h

@@ -70,6 +70,11 @@
 			HCR_SWIO | HCR_TIDCP)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
 
+/* System Control Register (SCTLR) bits */
+#define SCTLR_TE	(1 << 30)
+#define SCTLR_EE	(1 << 25)
+#define SCTLR_V		(1 << 13)
+
 /* Hyp System Control Register (HSCTLR) bits */
 #define HSCTLR_TE	(1 << 30)
 #define HSCTLR_EE	(1 << 25)
@@ -171,6 +176,10 @@
 #define HSR_FSC		(0x3f)
 #define HSR_FSC_TYPE	(0x3c)
 #define HSR_WNR		(1 << 6)
+#define HSR_CV_SHIFT	(24)
+#define HSR_CV		(1U << HSR_CV_SHIFT)
+#define HSR_COND_SHIFT	(20)
+#define HSR_COND	(0xfU << HSR_COND_SHIFT)
 
 #define FSC_FAULT	(0x04)
 #define FSC_PERM	(0x0c)
@@ -197,4 +206,6 @@
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
 
+#define HSR_HVC_IMM_MASK	((1UL << 16) - 1)
+
 #endif /* __ARM_KVM_ARM_H__ */

arch/arm/include/asm/kvm_coproc.h

@@ -21,4 +21,18 @@
 
 void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
 
+struct kvm_coproc_target_table {
+	unsigned target;
+	const struct coproc_reg *table;
+	size_t num;
+};
+void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table);
+
+int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp_0_13_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
+void kvm_coproc_table_init(void);
 #endif /* __ARM_KVM_COPROC_H__ */

arch/arm/include/asm/kvm_emulate.h

@@ -25,6 +25,12 @@
 u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 u32 *vcpu_spsr(struct kvm_vcpu *vcpu);
 
+int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run);
+void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr);
+void kvm_inject_undefined(struct kvm_vcpu *vcpu);
+void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
+
 static inline u32 *vcpu_pc(struct kvm_vcpu *vcpu)
 {
 	return (u32 *)&vcpu->arch.regs.usr_regs.ARM_pc;

arch/arm/include/asm/kvm_host.h

@@ -94,6 +94,10 @@ struct kvm_vcpu_arch {
 	 * Anything that is not used directly from assembly code goes
 	 * here.
 	 */
+	/* dcache set/way operation pending */
+	int last_pcpu;
+	cpumask_t require_dcache_flush;
+
 	/* Interrupt related fields */
 	u32 irq_lines;		/* IRQ and FIQ levels */
 

arch/arm/kvm/Makefile

@@ -18,4 +18,4 @@ kvm-arm-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o guest.o mmu.o emulate.o reset.o
-obj-y += coproc.o
+obj-y += coproc.o coproc_a15.o

arch/arm/kvm/arm.c

@@ -36,11 +36,14 @@
 #include <asm/mman.h>
 #include <asm/cputype.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
 #include <asm/virt.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <asm/opcodes.h>
 
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
@@ -294,6 +297,15 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	vcpu->cpu = cpu;
 	vcpu->arch.vfp_host = this_cpu_ptr(kvm_host_vfp_state);
+
+	/*
+	 * Check whether this vcpu requires the cache to be flushed on
+	 * this physical CPU. This is a consequence of doing dcache
+	 * operations by set/way on this vcpu. We do it here to be in
+	 * a non-preemptible section.
+	 */
+	if (cpumask_test_and_clear_cpu(cpu, &vcpu->arch.require_dcache_flush))
+		flush_cache_all(); /* We'd really want v7_flush_dcache_all() */
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -319,9 +331,16 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
+/**
+ * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled
+ * @v:		The VCPU pointer
+ *
+ * If the guest CPU is not waiting for interrupts or an interrupt line is
+ * asserted, the CPU is by definition runnable.
+ */
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return 0;
+	return !!v->arch.irq_lines;
 }
 
 /* Just ensure a guest exit from a particular CPU */
@@ -411,15 +430,157 @@ static void update_vttbr(struct kvm *kvm)
 	spin_unlock(&kvm_vmid_lock);
 }
 
+static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* SVC called from Hyp mode should never get here */
+	kvm_debug("SVC called from Hyp mode shouldn't go here\n");
+	BUG();
+	return -EINVAL; /* Squash warning */
+}
+
+static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+		      vcpu->arch.hsr & HSR_HVC_IMM_MASK);
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* We don't support SMC; don't do that. */
+	kvm_debug("smc: at %08x", *vcpu_pc(vcpu));
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* The hypervisor should never cause aborts */
+	kvm_err("Prefetch Abort taken from Hyp mode at %#08x (HSR: %#08x)\n",
+		vcpu->arch.hxfar, vcpu->arch.hsr);
+	return -EFAULT;
+}
+
+static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* This is either an error in the ws. code or an external abort */
+	kvm_err("Data Abort taken from Hyp mode at %#08x (HSR: %#08x)\n",
+		vcpu->arch.hxfar, vcpu->arch.hsr);
+	return -EFAULT;
+}
+
+typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
+static exit_handle_fn arm_exit_handlers[] = {
+	[HSR_EC_WFI]		= kvm_handle_wfi,
+	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
+	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
+	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_LS]	= kvm_handle_cp14_load_store,
+	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
+	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
+	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
+	[HSR_EC_SVC_HYP]	= handle_svc_hyp,
+	[HSR_EC_HVC]		= handle_hvc,
+	[HSR_EC_SMC]		= handle_smc,
+	[HSR_EC_IABT]		= kvm_handle_guest_abort,
+	[HSR_EC_IABT_HYP]	= handle_pabt_hyp,
+	[HSR_EC_DABT]		= kvm_handle_guest_abort,
+	[HSR_EC_DABT_HYP]	= handle_dabt_hyp,
+};
+
+/*
+ * A conditional instruction is allowed to trap, even though it
+ * wouldn't be executed.  So let's re-implement the hardware, in
+ * software!
+ */
+static bool kvm_condition_valid(struct kvm_vcpu *vcpu)
+{
+	unsigned long cpsr, cond, insn;
+
+	/*
+	 * Exception Code 0 can only happen if we set HCR.TGE to 1, to
+	 * catch undefined instructions, and then we won't get past
+	 * the arm_exit_handlers test anyway.
+	 */
+	BUG_ON(((vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT) == 0);
+
+	/* Top two bits non-zero?  Unconditional. */
+	if (vcpu->arch.hsr >> 30)
+		return true;
+
+	cpsr = *vcpu_cpsr(vcpu);
+
+	/* Is condition field valid? */
+	if ((vcpu->arch.hsr & HSR_CV) >> HSR_CV_SHIFT)
+		cond = (vcpu->arch.hsr & HSR_COND) >> HSR_COND_SHIFT;
+	else {
+		/* This can happen in Thumb mode: examine IT state. */
+		unsigned long it;
+
+		it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
+
+		/* it == 0 => unconditional. */
+		if (it == 0)
+			return true;
+
+		/* The cond for this insn works out as the top 4 bits. */
+		cond = (it >> 4);
+	}
+
+	/* Shift makes it look like an ARM-mode instruction */
+	insn = cond << 28;
+	return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL;
+}
+
 /*
  * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
  * proper exit to QEMU.
  */
 static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		       int exception_index)
 {
-	run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	return 0;
+	unsigned long hsr_ec;
+
+	switch (exception_index) {
+	case ARM_EXCEPTION_IRQ:
+		return 1;
+	case ARM_EXCEPTION_UNDEFINED:
+		kvm_err("Undefined exception in Hyp mode at: %#08x\n",
+			vcpu->arch.hyp_pc);
+		BUG();
+		panic("KVM: Hypervisor undefined exception!\n");
+	case ARM_EXCEPTION_DATA_ABORT:
+	case ARM_EXCEPTION_PREF_ABORT:
+	case ARM_EXCEPTION_HVC:
+		hsr_ec = (vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT;
+
+		if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers)
+		    || !arm_exit_handlers[hsr_ec]) {
+			kvm_err("Unkown exception class: %#08lx, "
+				"hsr: %#08x\n", hsr_ec,
+				(unsigned int)vcpu->arch.hsr);
+			BUG();
+		}
+
+		/*
+		 * See ARM ARM B1.14.1: "Hyp traps on instructions
+		 * that fail their condition code check"
+		 */
+		if (!kvm_condition_valid(vcpu)) {
+			bool is_wide = vcpu->arch.hsr & HSR_IL;
+			kvm_skip_instr(vcpu, is_wide);
+			return 1;
+		}
+
+		return arm_exit_handlers[hsr_ec](vcpu, run);
+	default:
+		kvm_pr_unimpl("Unsupported exception type: %d",
+			      exception_index);
+		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		return 0;
+	}
 }
 
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
@@ -493,6 +654,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
+		vcpu->arch.last_pcpu = smp_processor_id();
 		kvm_guest_exit();
 		trace_kvm_exit(*vcpu_pc(vcpu));
 		/*
@@ -801,6 +963,7 @@ int kvm_arch_init(void *opaque)
 	if (err)
 		goto out_err;
 
+	kvm_coproc_table_init();
 	return 0;
 out_err:
 	return err;