Merge branch 'kvm-updates/3.4' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Avi Kivity:
 "Changes include timekeeping improvements, support for assigning host
  PCI devices that share interrupt lines, s390 user-controlled guests, a
  large ppc update, and random fixes."

This is with the sign-off's fixed, hopefully next merge window we won't
have rebased commits.

* 'kvm-updates/3.4' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
  KVM: Convert intx_mask_lock to spin lock
  KVM: x86: fix kvm_write_tsc() TSC matching thinko
  x86: kvmclock: abstract save/restore sched_clock_state
  KVM: nVMX: Fix erroneous exception bitmap check
  KVM: Ignore the writes to MSR_K7_HWCR(3)
  KVM: MMU: make use of ->root_level in reset_rsvds_bits_mask
  KVM: PMU: add proper support for fixed counter 2
  KVM: PMU: Fix raw event check
  KVM: PMU: warn when pin control is set in eventsel msr
  KVM: VMX: Fix delayed load of shared MSRs
  KVM: use correct tlbs dirty type in cmpxchg
  KVM: Allow host IRQ sharing for assigned PCI 2.3 devices
  KVM: Ensure all vcpus are consistent with in-kernel irqchip settings
  KVM: x86 emulator: Allow PM/VM86 switch during task switch
  KVM: SVM: Fix CPL updates
  KVM: x86 emulator: VM86 segments must have DPL 3
  KVM: x86 emulator: Fix task switch privilege checks
  arch/powerpc/kvm/book3s_hv.c: included linux/sched.h twice
  KVM: x86 emulator: correctly mask pmc index bits in RDPMC instruction emulation
  KVM: mmu_notifier: Flush TLBs before releasing mmu_lock
  ...

1 files changed, 151 insertions, 27 deletions

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 220fcdf2697..7340e1090b7 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -51,15 +51,19 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #define MSR_USER32 MSR_USER
 #define MSR_USER64 MSR_USER
 #define HW_PAGE_SIZE PAGE_SIZE
+#define __hard_irq_disable local_irq_disable
+#define __hard_irq_enable local_irq_enable
 #endif
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
-	memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb));
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
 	memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
 	       sizeof(get_paca()->shadow_vcpu));
-	to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max;
+	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+	svcpu_put(svcpu);
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_32
@@ -70,10 +74,12 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
-	memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb));
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
 	memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
 	       sizeof(get_paca()->shadow_vcpu));
-	to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max;
+	to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
+	svcpu_put(svcpu);
 #endif
 
 	kvmppc_giveup_ext(vcpu, MSR_FP);
@@ -151,14 +157,16 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 #ifdef CONFIG_PPC_BOOK3S_64
 	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
 		kvmppc_mmu_book3s_64_init(vcpu);
-		to_book3s(vcpu)->hior = 0xfff00000;
+		if (!to_book3s(vcpu)->hior_explicit)
+			to_book3s(vcpu)->hior = 0xfff00000;
 		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
 		vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	} else
 #endif
 	{
 		kvmppc_mmu_book3s_32_init(vcpu);
-		to_book3s(vcpu)->hior = 0;
+		if (!to_book3s(vcpu)->hior_explicit)
+			to_book3s(vcpu)->hior = 0;
 		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
 		vcpu->arch.cpu_type = KVM_CPU_3S_32;
 	}
@@ -308,19 +316,22 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	if (page_found == -ENOENT) {
 		/* Page not found in guest PTE entries */
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+		vcpu->arch.shared->dsisr = svcpu->fault_dsisr;
 		vcpu->arch.shared->msr |=
-			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+			(svcpu->shadow_srr1 & 0x00000000f8000000ULL);
+		svcpu_put(svcpu);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr =
-			to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
+		vcpu->arch.shared->dsisr = svcpu->fault_dsisr & ~DSISR_NOHPTE;
 		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
 		vcpu->arch.shared->msr |=
-			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+			svcpu->shadow_srr1 & 0x00000000f8000000ULL;
+		svcpu_put(svcpu);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
@@ -517,24 +528,29 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	run->ready_for_interrupt_injection = 1;
 
 	trace_kvm_book3s_exit(exit_nr, vcpu);
+	preempt_enable();
 	kvm_resched(vcpu);
 	switch (exit_nr) {
 	case BOOK3S_INTERRUPT_INST_STORAGE:
+	{
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		ulong shadow_srr1 = svcpu->shadow_srr1;
 		vcpu->stat.pf_instruc++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 		/* We set segments as unused segments when invalidating them. So
 		 * treat the respective fault as segment fault. */
-		if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT]
-		    == SR_INVALID) {
+		if (svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] == SR_INVALID) {
 			kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
 			r = RESUME_GUEST;
+			svcpu_put(svcpu);
 			break;
 		}
 #endif
+		svcpu_put(svcpu);
 
 		/* only care about PTEG not found errors, but leave NX alone */
-		if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) {
+		if (shadow_srr1 & 0x40000000) {
 			r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
 			vcpu->stat.sp_instruc++;
 		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
@@ -547,33 +563,37 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
 			r = RESUME_GUEST;
 		} else {
-			vcpu->arch.shared->msr |=
-				to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
+			vcpu->arch.shared->msr |= shadow_srr1 & 0x58000000;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			r = RESUME_GUEST;
 		}
 		break;
+	}
 	case BOOK3S_INTERRUPT_DATA_STORAGE:
 	{
 		ulong dar = kvmppc_get_fault_dar(vcpu);
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		u32 fault_dsisr = svcpu->fault_dsisr;
 		vcpu->stat.pf_storage++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
 		/* We set segments as unused segments when invalidating them. So
 		 * treat the respective fault as segment fault. */
-		if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) {
+		if ((svcpu->sr[dar >> SID_SHIFT]) == SR_INVALID) {
 			kvmppc_mmu_map_segment(vcpu, dar);
 			r = RESUME_GUEST;
+			svcpu_put(svcpu);
 			break;
 		}
 #endif
+		svcpu_put(svcpu);
 
 		/* The only case we need to handle is missing shadow PTEs */
-		if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
+		if (fault_dsisr & DSISR_NOHPTE) {
 			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
 		} else {
 			vcpu->arch.shared->dar = dar;
-			vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+			vcpu->arch.shared->dsisr = fault_dsisr;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			r = RESUME_GUEST;
 		}
@@ -609,10 +629,13 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_PROGRAM:
 	{
 		enum emulation_result er;
+		struct kvmppc_book3s_shadow_vcpu *svcpu;
 		ulong flags;
 
 program_interrupt:
-		flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;
+		svcpu = svcpu_get(vcpu);
+		flags = svcpu->shadow_srr1 & 0x1f0000ull;
+		svcpu_put(svcpu);
 
 		if (vcpu->arch.shared->msr & MSR_PR) {
 #ifdef EXIT_DEBUG
@@ -740,20 +763,33 @@ program_interrupt:
 		r = RESUME_GUEST;
 		break;
 	default:
+	{
+		struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+		ulong shadow_srr1 = svcpu->shadow_srr1;
+		svcpu_put(svcpu);
 		/* Ugh - bork here! What did we get? */
 		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
-			exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1);
+			exit_nr, kvmppc_get_pc(vcpu), shadow_srr1);
 		r = RESUME_HOST;
 		BUG();
 		break;
 	}
-
+	}
 
 	if (!(r & RESUME_HOST)) {
 		/* To avoid clobbering exit_reason, only check for signals if
 		 * we aren't already exiting to userspace for some other
 		 * reason. */
+
+		/*
+		 * Interrupts could be timers for the guest which we have to
+		 * inject again, so let's postpone them until we're in the guest
+		 * and if we really did time things so badly, then we just exit
+		 * again due to a host external interrupt.
+		 */
+		__hard_irq_disable();
 		if (signal_pending(current)) {
+			__hard_irq_enable();
 #ifdef EXIT_DEBUG
 			printk(KERN_EMERG "KVM: Going back to host\n");
 #endif
@@ -761,10 +797,12 @@ program_interrupt:
 			run->exit_reason = KVM_EXIT_INTR;
 			r = -EINTR;
 		} else {
+			preempt_disable();
+
 			/* In case an interrupt came in that was triggered
 			 * from userspace (like DEC), we need to check what
 			 * to inject now! */
-			kvmppc_core_deliver_interrupts(vcpu);
+			kvmppc_core_prepare_to_enter(vcpu);
 		}
 	}
 
@@ -836,6 +874,38 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_PPC_HIOR:
+		r = put_user(to_book3s(vcpu)->hior, (u64 __user *)reg->addr);
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_PPC_HIOR:
+		r = get_user(to_book3s(vcpu)->hior, (u64 __user *)reg->addr);
+		if (!r)
+			to_book3s(vcpu)->hior_explicit = true;
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
 int kvmppc_core_check_processor_compat(void)
 {
 	return 0;
@@ -923,16 +993,31 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
 	ulong ext_msr;
 
+	preempt_disable();
+
 	/* Check if we can run the vcpu at all */
 	if (!vcpu->arch.sane) {
 		kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
+	kvmppc_core_prepare_to_enter(vcpu);
+
+	/*
+	 * Interrupts could be timers for the guest which we have to inject
+	 * again, so let's postpone them until we're in the guest and if we
+	 * really did time things so badly, then we just exit again due to
+	 * a host external interrupt.
+	 */
+	__hard_irq_disable();
+
 	/* No need to go into the guest when all we do is going out */
 	if (signal_pending(current)) {
+		__hard_irq_enable();
 		kvm_run->exit_reason = KVM_EXIT_INTR;
-		return -EINTR;
+		ret = -EINTR;
+		goto out;
 	}
 
 	/* Save FPU state in stack */
@@ -974,8 +1059,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	kvm_guest_exit();
 
-	local_irq_disable();
-
 	current->thread.regs->msr = ext_msr;
 
 	/* Make sure we save the guest FPU/Altivec/VSX state */
@@ -1002,9 +1085,50 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	current->thread.used_vsr = used_vsr;
 #endif
 
+out:
+	preempt_enable();
 	return ret;
 }
 
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+				      struct kvm_dirty_log *log)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm_vcpu *vcpu;
+	ulong ga, ga_end;
+	int is_dirty = 0;
+	int r;
+	unsigned long n;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = kvm_get_dirty_log(kvm, log, &is_dirty);
+	if (r)
+		goto out;
+
+	/* If nothing is dirty, don't bother messing with page tables. */
+	if (is_dirty) {
+		memslot = id_to_memslot(kvm->memslots, log->slot);
+
+		ga = memslot->base_gfn << PAGE_SHIFT;
+		ga_end = ga + (memslot->npages << PAGE_SHIFT);
+
+		kvm_for_each_vcpu(n, vcpu, kvm)
+			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
+
+		n = kvm_dirty_bitmap_bytes(memslot);
+		memset(memslot->dirty_bitmap, 0, n);
+	}
+
+	r = 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				      struct kvm_userspace_memory_region *mem)
 {