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

Pull first batch of KVM updates from Paolo Bonzini:
 "The bulk of the changes here is for x86.  And for once it's not for
  silicon that no one owns: these are really new features for everyone.

  Details:

   - ARM:
        several features are in progress but missed the 4.2 deadline.
        So here is just a smattering of bug fixes, plus enabling the
        VFIO integration.

   - s390:
        Some fixes/refactorings/optimizations, plus support for 2GB
        pages.

   - x86:
        * host and guest support for marking kvmclock as a stable
          scheduler clock.
        * support for write combining.
        * support for system management mode, needed for secure boot in
          guests.
        * a bunch of cleanups required for the above
        * support for virtualized performance counters on AMD
        * legacy PCI device assignment is deprecated and defaults to "n"
          in Kconfig; VFIO replaces it

        On top of this there are also bug fixes and eager FPU context
        loading for FPU-heavy guests.

   - Common code:
        Support for multiple address spaces; for now it is used only for
        x86 SMM but the s390 folks also have plans"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (124 commits)
  KVM: s390: clear floating interrupt bitmap and parameters
  KVM: x86/vPMU: Enable PMU handling for AMD PERFCTRn and EVNTSELn MSRs
  KVM: x86/vPMU: Implement AMD vPMU code for KVM
  KVM: x86/vPMU: Define kvm_pmu_ops to support vPMU function dispatch
  KVM: x86/vPMU: introduce kvm_pmu_msr_idx_to_pmc
  KVM: x86/vPMU: reorder PMU functions
  KVM: x86/vPMU: whitespace and stylistic adjustments in PMU code
  KVM: x86/vPMU: use the new macros to go between PMC, PMU and VCPU
  KVM: x86/vPMU: introduce pmu.h header
  KVM: x86/vPMU: rename a few PMU functions
  KVM: MTRR: do not map huge page for non-consistent range
  KVM: MTRR: simplify kvm_mtrr_get_guest_memory_type
  KVM: MTRR: introduce mtrr_for_each_mem_type
  KVM: MTRR: introduce fixed_mtrr_addr_* functions
  KVM: MTRR: sort variable MTRRs
  KVM: MTRR: introduce var_mtrr_range
  KVM: MTRR: introduce fixed_mtrr_segment table
  KVM: MTRR: improve kvm_mtrr_get_guest_memory_type
  KVM: MTRR: do not split 64 bits MSR content
  KVM: MTRR: clean up mtrr default type
  ...

7 files changed, 53 insertions, 37 deletions

diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index f1f79d104309..bfb915d05665 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -28,6 +28,7 @@ config KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
 	select MMU_NOTIFIER
+	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 139e46c08b6e..c5eef02c52ba 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -15,7 +15,7 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
 AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
 
 KVM := ../../../virt/kvm
-kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o
+kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index d9631ecddd56..bc738d2b8392 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -171,7 +171,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	int r;
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
@@ -532,6 +531,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		kvm_vgic_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
 
+		preempt_disable();
 		local_irq_disable();
 
 		/*
@@ -544,6 +544,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
 			local_irq_enable();
+			preempt_enable();
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			continue;
@@ -553,14 +554,16 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * Enter the guest
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
-		kvm_guest_enter();
+		__kvm_guest_enter();
 		vcpu->mode = IN_GUEST_MODE;
 
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
-		kvm_guest_exit();
-		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+		/*
+		 * Back from guest
+		 *************************************************************/
+
 		/*
 		 * We may have taken a host interrupt in HYP mode (ie
 		 * while executing the guest). This interrupt is still
@@ -574,8 +577,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		local_irq_enable();
 
 		/*
-		 * Back from guest
-		 *************************************************************/
+		 * We do local_irq_enable() before calling kvm_guest_exit() so
+		 * that if a timer interrupt hits while running the guest we
+		 * account that tick as being spent in the guest.  We enable
+		 * preemption after calling kvm_guest_exit() so that if we get
+		 * preempted we make sure ticks after that is not counted as
+		 * guest time.
+		 */
+		kvm_guest_exit();
+		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+		preempt_enable();
+
 
 		kvm_timer_sync_hwstate(vcpu);
 		kvm_vgic_sync_hwstate(vcpu);
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 79caf79b304a..f7db3a5d80e3 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -170,13 +170,9 @@ __kvm_vcpu_return:
 	@ Don't trap coprocessor accesses for host kernel
 	set_hstr vmexit
 	set_hdcr vmexit
-	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
 
 #ifdef CONFIG_VFPv3
-	@ Save floating point registers we if let guest use them.
-	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
-	bne	after_vfp_restore
-
 	@ Switch VFP/NEON hardware state to the host's
 	add	r7, vcpu, #VCPU_VFP_GUEST
 	store_vfp_state r7
@@ -188,6 +184,8 @@ after_vfp_restore:
 	@ Restore FPEXC_EN which we clobbered on entry
 	pop	{r2}
 	VFPFMXR FPEXC, r2
+#else
+after_vfp_restore:
 #endif
 
 	@ Reset Hyp-role
@@ -483,7 +481,7 @@ switch_to_guest_vfp:
 	push	{r3-r7}
 
 	@ NEON/VFP used.  Turn on VFP access.
-	set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
 
 	@ Switch VFP/NEON hardware state to the guest's
 	add	r7, r0, #VCPU_VFP_HOST
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 35e4a3a0c476..702740d37465 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -412,7 +412,6 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	add	r11, vcpu, #VCPU_VGIC_CPU
 
 	/* Save all interesting registers */
-	ldr	r3, [r2, #GICH_HCR]
 	ldr	r4, [r2, #GICH_VMCR]
 	ldr	r5, [r2, #GICH_MISR]
 	ldr	r6, [r2, #GICH_EISR0]
@@ -420,7 +419,6 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	ldr	r8, [r2, #GICH_ELRSR0]
 	ldr	r9, [r2, #GICH_ELRSR1]
 	ldr	r10, [r2, #GICH_APR]
-ARM_BE8(rev	r3, r3	)
 ARM_BE8(rev	r4, r4	)
 ARM_BE8(rev	r5, r5	)
 ARM_BE8(rev	r6, r6	)
@@ -429,7 +427,6 @@ ARM_BE8(rev	r8, r8	)
 ARM_BE8(rev	r9, r9	)
 ARM_BE8(rev	r10, r10	)
 
-	str	r3, [r11, #VGIC_V2_CPU_HCR]
 	str	r4, [r11, #VGIC_V2_CPU_VMCR]
 	str	r5, [r11, #VGIC_V2_CPU_MISR]
 #ifdef CONFIG_CPU_ENDIAN_BE8
@@ -591,8 +588,13 @@ ARM_BE8(rev	r6, r6  )
 .endm
 
 /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2. */
-.macro set_hcptr operation, mask
+ * (hardware reset value is 0). Keep previous value in r2.
+ * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
+ * VFP wasn't already enabled (always executed on vmtrap).
+ * If a label is specified with vmexit, it is branched to if VFP wasn't
+ * enabled.
+ */
+.macro set_hcptr operation, mask, label = none
 	mrc	p15, 4, r2, c1, c1, 2
 	ldr	r3, =\mask
 	.if \operation == vmentry
@@ -601,6 +603,17 @@ ARM_BE8(rev	r6, r6  )
 	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
 	.endif
 	mcr	p15, 4, r3, c1, c1, 2
+	.if \operation != vmentry
+	.if \operation == vmexit
+	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	beq	1f
+	.endif
+	isb
+	.if \label != none
+	b	\label
+	.endif
+1:
+	.endif
 .endm
 
 /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 1d5accbd3dcf..7b4201294187 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -691,8 +691,8 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 		 * work.  This is not used by the hardware and we have no
 		 * alignment requirement for this allocation.
 		 */
-		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
-				       GFP_KERNEL | __GFP_ZERO);
+		pgd = kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
+				GFP_KERNEL | __GFP_ZERO);
 
 		if (!pgd) {
 			kvm_free_hwpgd(hwpgd);
@@ -1155,7 +1155,8 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
  */
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 {
-	struct kvm_memory_slot *memslot = id_to_memslot(kvm->memslots, slot);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
 	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
@@ -1718,8 +1719,9 @@ out:
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   const struct kvm_memory_slot *old,
+				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
 	/*
@@ -1733,7 +1735,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
 	hva_t hva = mem->userspace_addr;
@@ -1838,7 +1840,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 	return 0;
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
 {
 }
 
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 02fa8eff6ae1..531e922486b2 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -230,10 +230,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	case PSCI_0_2_FN64_AFFINITY_INFO:
 		val = kvm_psci_vcpu_affinity_info(vcpu);
 		break;
-	case PSCI_0_2_FN_MIGRATE:
-	case PSCI_0_2_FN64_MIGRATE:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
 		/*
 		 * Trusted OS is MP hence does not require migration
@@ -242,10 +238,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		 */
 		val = PSCI_0_2_TOS_MP;
 		break;
-	case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
-	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_SYSTEM_OFF:
 		kvm_psci_system_off(vcpu);
 		/*
@@ -271,7 +263,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		ret = 0;
 		break;
 	default:
-		return -EINVAL;
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
@@ -291,12 +284,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 	case KVM_PSCI_FN_CPU_ON:
 		val = kvm_psci_vcpu_on(vcpu);
 		break;
-	case KVM_PSCI_FN_CPU_SUSPEND:
-	case KVM_PSCI_FN_MIGRATE:
+	default:
 		val = PSCI_RET_NOT_SUPPORTED;
 		break;
-	default:
-		return -EINVAL;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;