Merge tag 'kvm-arm-for-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-next

KVM/ARM changes for Linux v4.5

- Complete rewrite of the arm64 world switch in C, hopefully
  paving the way for more sharing with the 32bit code, better
  maintainability and easier integration of new features.
  Also smaller and slightly faster in some cases...
- Support for 16bit VM identifiers
- Various cleanups

7 files changed, 104 insertions, 57 deletions

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index e06fd299de08..dda1959f0dde 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -44,6 +44,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_psci.h>
+#include <asm/sections.h>
 
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
@@ -58,9 +59,12 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
 
 /* The VMID used in the VTTBR */
 static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
-static u8 kvm_next_vmid;
+static u32 kvm_next_vmid;
+static unsigned int kvm_vmid_bits __read_mostly;
 static DEFINE_SPINLOCK(kvm_vmid_lock);
 
+static bool vgic_present;
+
 static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(preemptible());
@@ -132,7 +136,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.vmid_gen = 0;
 
 	/* The maximum number of VCPUs is limited by the host's GIC model */
-	kvm->arch.max_vcpus = kvm_vgic_get_max_vcpus();
+	kvm->arch.max_vcpus = vgic_present ?
+				kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
 
 	return ret;
 out_free_stage2_pgd:
@@ -172,6 +177,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	int r;
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
+		r = vgic_present;
+		break;
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
@@ -433,11 +440,12 @@ static void update_vttbr(struct kvm *kvm)
 	kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen);
 	kvm->arch.vmid = kvm_next_vmid;
 	kvm_next_vmid++;
+	kvm_next_vmid &= (1 << kvm_vmid_bits) - 1;
 
 	/* update vttbr to be used with the new vmid */
 	pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm));
 	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
-	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
+	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
 	kvm->arch.vttbr = pgd_phys | vmid;
 
 	spin_unlock(&kvm_vmid_lock);
@@ -603,6 +611,7 @@ 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->stat.exits++;
 		/*
 		 * Back from guest
 		 *************************************************************/
@@ -913,6 +922,8 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
 
 	switch (dev_id) {
 	case KVM_ARM_DEVICE_VGIC_V2:
+		if (!vgic_present)
+			return -ENXIO;
 		return kvm_vgic_addr(kvm, type, &dev_addr->addr, true);
 	default:
 		return -ENODEV;
@@ -927,6 +938,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
+		if (!vgic_present)
+			return -ENXIO;
 		return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
 	}
 	case KVM_ARM_SET_DEVICE_ADDR: {
@@ -1067,6 +1080,12 @@ static int init_hyp_mode(void)
 		goto out_free_mappings;
 	}
 
+	err = create_hyp_mappings(__start_rodata, __end_rodata);
+	if (err) {
+		kvm_err("Cannot map rodata section\n");
+		goto out_free_mappings;
+	}
+
 	/*
 	 * Map the Hyp stack pages
 	 */
@@ -1111,8 +1130,17 @@ static int init_hyp_mode(void)
 	 * Init HYP view of VGIC
 	 */
 	err = kvm_vgic_hyp_init();
-	if (err)
+	switch (err) {
+	case 0:
+		vgic_present = true;
+		break;
+	case -ENODEV:
+	case -ENXIO:
+		vgic_present = false;
+		break;
+	default:
 		goto out_free_context;
+	}
 
 	/*
 	 * Init HYP architected timer support
@@ -1127,6 +1155,10 @@ static int init_hyp_mode(void)
 
 	kvm_perf_init();
 
+	/* set size of VMID supported by CPU */
+	kvm_vmid_bits = kvm_get_vmid_bits();
+	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
 	kvm_info("Hyp mode initialized successfully\n");
 
 	return 0;
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index d6c005283678..dc99159857b4 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -275,6 +275,40 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu)
 		return vbar;
 }
 
+/*
+ * Switch to an exception mode, updating both CPSR and SPSR. Follow
+ * the logic described in AArch32.EnterMode() from the ARMv8 ARM.
+ */
+static void kvm_update_psr(struct kvm_vcpu *vcpu, unsigned long mode)
+{
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
+	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
+
+	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | mode;
+
+	switch (mode) {
+	case FIQ_MODE:
+		*vcpu_cpsr(vcpu) |= PSR_F_BIT;
+		/* Fall through */
+	case ABT_MODE:
+	case IRQ_MODE:
+		*vcpu_cpsr(vcpu) |= PSR_A_BIT;
+		/* Fall through */
+	default:
+		*vcpu_cpsr(vcpu) |= PSR_I_BIT;
+	}
+
+	*vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT);
+
+	if (sctlr & SCTLR_TE)
+		*vcpu_cpsr(vcpu) |= PSR_T_BIT;
+	if (sctlr & SCTLR_EE)
+		*vcpu_cpsr(vcpu) |= PSR_E_BIT;
+
+	/* Note: These now point to the mode banked copies */
+	*vcpu_spsr(vcpu) = cpsr;
+}
+
 /**
  * kvm_inject_undefined - inject an undefined exception into the guest
  * @vcpu: The VCPU to receive the undefined exception
@@ -286,29 +320,13 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu)
  */
 void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 {
-	unsigned long new_lr_value;
-	unsigned long new_spsr_value;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
 	bool is_thumb = (cpsr & PSR_T_BIT);
 	u32 vect_offset = 4;
 	u32 return_offset = (is_thumb) ? 2 : 4;
 
-	new_spsr_value = cpsr;
-	new_lr_value = *vcpu_pc(vcpu) - return_offset;
-
-	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | UND_MODE;
-	*vcpu_cpsr(vcpu) |= PSR_I_BIT;
-	*vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT);
-
-	if (sctlr & SCTLR_TE)
-		*vcpu_cpsr(vcpu) |= PSR_T_BIT;
-	if (sctlr & SCTLR_EE)
-		*vcpu_cpsr(vcpu) |= PSR_E_BIT;
-
-	/* Note: These now point to UND banked copies */
-	*vcpu_spsr(vcpu) = cpsr;
-	*vcpu_reg(vcpu, 14) = new_lr_value;
+	kvm_update_psr(vcpu, UND_MODE);
+	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) - return_offset;
 
 	/* Branch to exception vector */
 	*vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset;
@@ -320,30 +338,14 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
  */
 static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
 {
-	unsigned long new_lr_value;
-	unsigned long new_spsr_value;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
 	bool is_thumb = (cpsr & PSR_T_BIT);
 	u32 vect_offset;
 	u32 return_offset = (is_thumb) ? 4 : 0;
 	bool is_lpae;
 
-	new_spsr_value = cpsr;
-	new_lr_value = *vcpu_pc(vcpu) + return_offset;
-
-	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | ABT_MODE;
-	*vcpu_cpsr(vcpu) |= PSR_I_BIT | PSR_A_BIT;
-	*vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT);
-
-	if (sctlr & SCTLR_TE)
-		*vcpu_cpsr(vcpu) |= PSR_T_BIT;
-	if (sctlr & SCTLR_EE)
-		*vcpu_cpsr(vcpu) |= PSR_E_BIT;
-
-	/* Note: These now point to ABT banked copies */
-	*vcpu_spsr(vcpu) = cpsr;
-	*vcpu_reg(vcpu, 14) = new_lr_value;
+	kvm_update_psr(vcpu, ABT_MODE);
+	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	if (is_pabt)
 		vect_offset = 12;
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 96e935bbc38c..5fa69d7bae58 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -33,6 +33,12 @@
 #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU }
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
+	VCPU_STAT(hvc_exit_stat),
+	VCPU_STAT(wfe_exit_stat),
+	VCPU_STAT(wfi_exit_stat),
+	VCPU_STAT(mmio_exit_user),
+	VCPU_STAT(mmio_exit_kernel),
+	VCPU_STAT(exits),
 	{ NULL }
 };
 
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 95f12b2ccdcb..3ede90d8b20b 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -42,6 +42,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
 		      kvm_vcpu_hvc_get_imm(vcpu));
+	vcpu->stat.hvc_exit_stat++;
 
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
@@ -89,9 +90,11 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) {
 		trace_kvm_wfx(*vcpu_pc(vcpu), true);
+		vcpu->stat.wfe_exit_stat++;
 		kvm_vcpu_on_spin(vcpu);
 	} else {
 		trace_kvm_wfx(*vcpu_pc(vcpu), false);
+		vcpu->stat.wfi_exit_stat++;
 		kvm_vcpu_block(vcpu);
 	}
 
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 974b1c606d04..7f33b2056ae6 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -115,7 +115,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
 			       data);
 		data = vcpu_data_host_to_guest(vcpu, data, len);
-		*vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data;
+		vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
 	}
 
 	return 0;
@@ -186,7 +186,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	rt = vcpu->arch.mmio_decode.rt;
 
 	if (is_write) {
-		data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len);
+		data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt),
+					       len);
 
 		trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data);
 		mmio_write_buf(data_buf, len, data);
@@ -209,8 +210,11 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	if (!ret) {
 		/* We handled the access successfully in the kernel. */
+		vcpu->stat.mmio_exit_kernel++;
 		kvm_handle_mmio_return(vcpu, run);
 		return 1;
+	} else {
+		vcpu->stat.mmio_exit_user++;
 	}
 
 	run->exit_reason	= KVM_EXIT_MMIO;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 7dace909d5cf..22f7fa0124ec 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -218,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 			kvm_tlb_flush_vmid_ipa(kvm, addr);
 
 			/* No need to invalidate the cache for device mappings */
-			if (!kvm_is_device_pfn(__phys_to_pfn(addr)))
+			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
 				kvm_flush_dcache_pte(old_pte);
 
 			put_page(virt_to_page(pte));
@@ -310,7 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		if (!pte_none(*pte) && !kvm_is_device_pfn(__phys_to_pfn(addr)))
+		if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte)))
 			kvm_flush_dcache_pte(*pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
@@ -656,9 +656,9 @@ static void *kvm_alloc_hwpgd(void)
  * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
  * @kvm:	The KVM struct pointer for the VM.
  *
- * Allocates the 1st level table only of size defined by S2_PGD_ORDER (can
- * support either full 40-bit input addresses or limited to 32-bit input
- * addresses). Clears the allocated pages.
+ * Allocates only the stage-2 HW PGD level table(s) (can support either full
+ * 40-bit input addresses or limited to 32-bit input addresses). Clears the
+ * allocated pages.
  *
  * Note we don't need locking here as this is only called when the VM is
  * created, which can only be done once.
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 0b556968a6da..a9b3b905e661 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -75,7 +75,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	unsigned long context_id;
 	phys_addr_t target_pc;
 
-	cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+	cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
@@ -94,8 +94,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 			return PSCI_RET_INVALID_PARAMS;
 	}
 
-	target_pc = *vcpu_reg(source_vcpu, 2);
-	context_id = *vcpu_reg(source_vcpu, 3);
+	target_pc = vcpu_get_reg(source_vcpu, 2);
+	context_id = vcpu_get_reg(source_vcpu, 3);
 
 	kvm_reset_vcpu(vcpu);
 
@@ -114,7 +114,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
 	 * the general puspose registers are undefined upon CPU_ON.
 	 */
-	*vcpu_reg(vcpu, 0) = context_id;
+	vcpu_set_reg(vcpu, 0, context_id);
 	vcpu->arch.power_off = false;
 	smp_mb();		/* Make sure the above is visible */
 
@@ -134,8 +134,8 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu *tmp;
 
-	target_affinity = *vcpu_reg(vcpu, 1);
-	lowest_affinity_level = *vcpu_reg(vcpu, 2);
+	target_affinity = vcpu_get_reg(vcpu, 1);
+	lowest_affinity_level = vcpu_get_reg(vcpu, 2);
 
 	/* Determine target affinity mask */
 	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
@@ -209,7 +209,7 @@ int kvm_psci_version(struct kvm_vcpu *vcpu)
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
 	int ret = 1;
-	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
 
 	switch (psci_fn) {
@@ -273,13 +273,13 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	*vcpu_reg(vcpu, 0) = val;
+	vcpu_set_reg(vcpu, 0, val);
 	return ret;
 }
 
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
-	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
 
 	switch (psci_fn) {
@@ -295,7 +295,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	*vcpu_reg(vcpu, 0) = val;
+	vcpu_set_reg(vcpu, 0, val);
 	return 1;
 }