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

Pull KVM fixes from Paolo Bonzini:
 "AMD fixes for bugs introduced in the 4.2 merge window, and a few PPC
  bug fixes too"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: disable halt_poll_ns as default for s390x
  KVM: x86: fix off-by-one in reserved bits check
  KVM: x86: use correct page table format to check nested page table reserved bits
  KVM: svm: do not call kvm_set_cr0 from init_vmcb
  KVM: x86: trap AMD MSRs for the TSeg base and mask
  KVM: PPC: Book3S: Take the kvm->srcu lock in kvmppc_h_logical_ci_load/store()
  KVM: PPC: Book3S HV: Pass the correct trap argument to kvmhv_commence_exit
  KVM: PPC: Book3S HV: Fix handling of interrupted VCPUs
  kvm: svm: reset mmu on VCPU reset

arch/arm/include/asm/kvm_host.h

@@ -33,6 +33,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #define KVM_VCPU_MAX_FEATURES 2
 

arch/arm64/include/asm/kvm_host.h

@@ -33,6 +33,7 @@
 #define KVM_USER_MEM_SLOTS 32
 #define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #include <kvm/arm_vgic.h>
 #include <kvm/arm_arch_timer.h>

arch/mips/include/asm/kvm_host.h

@@ -61,6 +61,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 	0
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 
 

arch/powerpc/include/asm/kvm_host.h

@@ -44,6 +44,7 @@
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 /* These values are internal and can be increased later */
 #define KVM_NR_IRQCHIPS          1

arch/powerpc/kvm/book3s.c

@@ -829,12 +829,15 @@ int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
 	unsigned long size = kvmppc_get_gpr(vcpu, 4);
 	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
 	u64 buf;
+	int srcu_idx;
 	int ret;
 
 	if (!is_power_of_2(size) || (size > sizeof(buf)))
 		return H_TOO_HARD;
 
+	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, size, &buf);
+	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 	if (ret != 0)
 		return H_TOO_HARD;
 
@@ -869,6 +872,7 @@ int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu)
 	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
 	unsigned long val = kvmppc_get_gpr(vcpu, 6);
 	u64 buf;
+	int srcu_idx;
 	int ret;
 
 	switch (size) {
@@ -892,7 +896,9 @@ int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu)
 		return H_TOO_HARD;
 	}
 
+	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, size, &buf);
+	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 	if (ret != 0)
 		return H_TOO_HARD;
 

arch/powerpc/kvm/book3s_hv.c

@@ -2692,9 +2692,13 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
 	       (vc->vcore_state == VCORE_RUNNING ||
-		vc->vcore_state == VCORE_EXITING))
+		vc->vcore_state == VCORE_EXITING ||
+		vc->vcore_state == VCORE_PIGGYBACK))
 		kvmppc_wait_for_exec(vc, vcpu, TASK_UNINTERRUPTIBLE);
 
+	if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL)
+		kvmppc_vcore_end_preempt(vc);
+
 	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
 		kvmppc_remove_runnable(vc, vcpu);
 		vcpu->stat.signal_exits++;

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1257,6 +1257,7 @@ mc_cont:
 	bl	kvmhv_accumulate_time
 #endif
 
+	mr 	r3, r12
 	/* Increment exit count, poke other threads to exit */
 	bl	kvmhv_commence_exit
 	nop

arch/s390/include/asm/kvm_host.h

@@ -35,6 +35,7 @@
  */
 #define KVM_NR_IRQCHIPS 1
 #define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_HALT_POLL_NS_DEFAULT 0
 
 #define SIGP_CTRL_C		0x80
 #define SIGP_CTRL_SCN_MASK	0x3f

arch/x86/include/asm/kvm_host.h

@@ -40,6 +40,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 

arch/x86/include/asm/msr-index.h

@@ -331,6 +331,7 @@
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
 #define MSR_K8_TSEG_ADDR		0xc0010112
+#define MSR_K8_TSEG_MASK		0xc0010113
 #define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
 #define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
 #define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */

arch/x86/kvm/mmu.c

@@ -3322,7 +3322,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 			break;
 
 		reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
-						    leaf);
+						    iterator.level);
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3614,7 +3614,7 @@ static void
 __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			struct rsvd_bits_validate *rsvd_check,
 			int maxphyaddr, int level, bool nx, bool gbpages,
-			bool pse)
+			bool pse, bool amd)
 {
 	u64 exb_bit_rsvd = 0;
 	u64 gbpages_bit_rsvd = 0;
@@ -3631,7 +3631,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	 * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
 	 * leaf entries) on AMD CPUs only.
 	 */
-	if (guest_cpuid_is_amd(vcpu))
+	if (amd)
 		nonleaf_bit8_rsvd = rsvd_bits(8, 8);
 
 	switch (level) {
@@ -3699,7 +3699,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
 				cpuid_maxphyaddr(vcpu), context->root_level,
 				context->nx, guest_cpuid_has_gbpages(vcpu),
-				is_pse(vcpu));
+				is_pse(vcpu), guest_cpuid_is_amd(vcpu));
 }
 
 static void
@@ -3749,13 +3749,24 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
+	/*
+	 * Passing "true" to the last argument is okay; it adds a check
+	 * on bit 8 of the SPTEs which KVM doesn't use anyway.
+	 */
 	__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 				boot_cpu_data.x86_phys_bits,
 				context->shadow_root_level, context->nx,
-				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
+				true);
 }
 EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
 
+static inline bool boot_cpu_is_amd(void)
+{
+	WARN_ON_ONCE(!tdp_enabled);
+	return shadow_x_mask == 0;
+}
+
 /*
  * the direct page table on host, use as much mmu features as
  * possible, however, kvm currently does not do execution-protection.
@@ -3764,11 +3775,11 @@ static void
 reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context)
 {
-	if (guest_cpuid_is_amd(vcpu))
+	if (boot_cpu_is_amd())
 		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 					boot_cpu_data.x86_phys_bits,
 					context->shadow_root_level, false,
-					cpu_has_gbpages, true);
+					cpu_has_gbpages, true, true);
 	else
 		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
 					    boot_cpu_data.x86_phys_bits,

arch/x86/kvm/svm.c

@@ -202,6 +202,7 @@ module_param(npt, int, S_IRUGO);
 static int nested = true;
 module_param(nested, int, S_IRUGO);
 
+static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
 
@@ -1263,7 +1264,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
 	 * It also updates the guest-visible cr0 value.
 	 */
-	(void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	kvm_mmu_reset_context(&svm->vcpu);
 
 	save->cr4 = X86_CR4_PAE;
 	/* rdx = ?? */

arch/x86/kvm/x86.c

@@ -2190,6 +2190,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
 	case MSR_K8_SYSCFG:
+	case MSR_K8_TSEG_ADDR:
+	case MSR_K8_TSEG_MASK:
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_K8_INT_PENDING_MSG:

virt/kvm/kvm_main.c

@@ -66,8 +66,8 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
-/* halt polling only reduces halt latency by 5-7 us, 500us is enough */
-static unsigned int halt_poll_ns = 500000;
+/* Architectures should define their poll value according to the halt latency */
+static unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
 module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
 
 /* Default doubles per-vcpu halt_poll_ns. */