Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "PPC changes will come next week.

   - s390: Support for runtime instrumentation within guests, support of
     248 VCPUs.

   - ARM: rewrite of the arm64 world switch in C, support for 16-bit VM
     identifiers.  Performance counter virtualization missed the boat.

   - x86: Support for more Hyper-V features (synthetic interrupt
     controller), MMU cleanups"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (115 commits)
  kvm: x86: Fix vmwrite to SECONDARY_VM_EXEC_CONTROL
  kvm/x86: Hyper-V SynIC timers tracepoints
  kvm/x86: Hyper-V SynIC tracepoints
  kvm/x86: Update SynIC timers on guest entry only
  kvm/x86: Skip SynIC vector check for QEMU side
  kvm/x86: Hyper-V fix SynIC timer disabling condition
  kvm/x86: Reorg stimer_expiration() to better control timer restart
  kvm/x86: Hyper-V unify stimer_start() and stimer_restart()
  kvm/x86: Drop stimer_stop() function
  kvm/x86: Hyper-V timers fix incorrect logical operation
  KVM: move architecture-dependent requests to arch/
  KVM: renumber vcpu->request bits
  KVM: document which architecture uses each request bit
  KVM: Remove unused KVM_REQ_KICK to save a bit in vcpu->requests
  kvm: x86: Check kvm_write_guest return value in kvm_write_wall_clock
  KVM: s390: implement the RI support of guest
  kvm/s390: drop unpaired smp_mb
  kvm: x86: fix comment about {mmu,nested_mmu}.gva_to_gpa
  KVM: x86: MMU: Use clear_page() instead of init_shadow_page_table()
  arm/arm64: KVM: Detect vGIC presence at runtime
  ...

9 files changed, 117 insertions, 60 deletions

diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index dc641dd..e22089f 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -19,6 +19,7 @@
 #ifndef __ARM_KVM_ARM_H__
 #define __ARM_KVM_ARM_H__
 
+#include <linux/const.h>
 #include <linux/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -132,10 +133,9 @@
  * space.
  */
 #define KVM_PHYS_SHIFT	(40)
-#define KVM_PHYS_SIZE	(1ULL << KVM_PHYS_SHIFT)
-#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1ULL)
-#define PTRS_PER_S2_PGD	(1ULL << (KVM_PHYS_SHIFT - 30))
-#define S2_PGD_ORDER	get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+#define KVM_PHYS_SIZE	(_AC(1, ULL) << KVM_PHYS_SHIFT)
+#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - _AC(1, ULL))
+#define PTRS_PER_S2_PGD	(_AC(1, ULL) << (KVM_PHYS_SHIFT - 30))
 
 /* Virtualization Translation Control Register (VTCR) bits */
 #define VTCR_SH0	(3 << 12)
@@ -162,17 +162,17 @@
 #define VTTBR_X		(5 - KVM_T0SZ)
 #endif
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  _AC(48, ULL)
+#define VTTBR_VMID_MASK(size)	(_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
 /* Hyp Syndrome Register (HSR) bits */
 #define HSR_EC_SHIFT	(26)
-#define HSR_EC		(0x3fU << HSR_EC_SHIFT)
-#define HSR_IL		(1U << 25)
+#define HSR_EC		(_AC(0x3f, UL) << HSR_EC_SHIFT)
+#define HSR_IL		(_AC(1, UL) << 25)
 #define HSR_ISS		(HSR_IL - 1)
 #define HSR_ISV_SHIFT	(24)
-#define HSR_ISV		(1U << HSR_ISV_SHIFT)
+#define HSR_ISV		(_AC(1, UL) << HSR_ISV_SHIFT)
 #define HSR_SRT_SHIFT	(16)
 #define HSR_SRT_MASK	(0xf << HSR_SRT_SHIFT)
 #define HSR_FSC		(0x3f)
@@ -180,9 +180,9 @@
 #define HSR_SSE		(1 << 21)
 #define HSR_WNR		(1 << 6)
 #define HSR_CV_SHIFT	(24)
-#define HSR_CV		(1U << HSR_CV_SHIFT)
+#define HSR_CV		(_AC(1, UL) << HSR_CV_SHIFT)
 #define HSR_COND_SHIFT	(20)
-#define HSR_COND	(0xfU << HSR_COND_SHIFT)
+#define HSR_COND	(_AC(0xf, UL) << HSR_COND_SHIFT)
 
 #define FSC_FAULT	(0x04)
 #define FSC_ACCESS	(0x08)
@@ -210,13 +210,13 @@
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
 
-#define HSR_WFI_IS_WFE		(1U << 0)
+#define HSR_WFI_IS_WFE		(_AC(1, UL) << 0)
 
-#define HSR_HVC_IMM_MASK	((1UL << 16) - 1)
+#define HSR_HVC_IMM_MASK	((_AC(1, UL) << 16) - 1)
 
-#define HSR_DABT_S1PTW		(1U << 7)
-#define HSR_DABT_CM		(1U << 8)
-#define HSR_DABT_EA		(1U << 9)
+#define HSR_DABT_S1PTW		(_AC(1, UL) << 7)
+#define HSR_DABT_CM		(_AC(1, UL) << 8)
+#define HSR_DABT_EA		(_AC(1, UL) << 9)
 
 #define kvm_arm_exception_type	\
 	{0, "RESET" }, 		\
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 6692982..f9f2779 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -150,6 +150,12 @@ struct kvm_vcpu_stat {
 	u32 halt_successful_poll;
 	u32 halt_attempted_poll;
 	u32 halt_wakeup;
+	u32 hvc_exit_stat;
+	u64 wfe_exit_stat;
+	u64 wfi_exit_stat;
+	u64 mmio_exit_user;
+	u64 mmio_exit_kernel;
+	u64 exits;
 };
 
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 405aa18..9203c21 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -279,6 +279,11 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
 				       pgd_t *merged_hyp_pgd,
 				       unsigned long hyp_idmap_start) { }
 
+static inline unsigned int kvm_get_vmid_bits(void)
+{
+	return 8;
+}
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index e06fd29..dda1959 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 d6c0052..dc99159 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 96e935b..5fa69d7 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 95f12b2..3ede90d 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 3a10c9f..7f33b20 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -210,8 +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 61d96a6..22f7fa0 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -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.