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

Pull KVM fixes from Paolo Bonzini:
 "The usual smattering of fixes and tunings that came in too late for
  the merge window, but should not wait four months before they appear
  in a release.

  I also travelled a bit more than usual in the first part of May, which
  didn't help with picking up patches and reports promptly"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (33 commits)
  KVM: x86: fix return value for reserved EFER
  tools/kvm_stat: fix fields filter for child events
  KVM: selftests: Wrap vcpu_nested_state_get/set functions with x86 guard
  kvm: selftests: aarch64: compile with warnings on
  kvm: selftests: aarch64: fix default vm mode
  kvm: selftests: aarch64: dirty_log_test: fix unaligned memslot size
  KVM: s390: fix memory slot handling for KVM_SET_USER_MEMORY_REGION
  KVM: x86/pmu: do not mask the value that is written to fixed PMUs
  KVM: x86/pmu: mask the result of rdpmc according to the width of the counters
  x86/kvm/pmu: Set AMD's virt PMU version to 1
  KVM: x86: do not spam dmesg with VMCS/VMCB dumps
  kvm: Check irqchip mode before assign irqfd
  kvm: svm/avic: fix off-by-one in checking host APIC ID
  KVM: selftests: do not blindly clobber registers in guest asm
  KVM: selftests: Remove duplicated TEST_ASSERT in hyperv_cpuid.c
  KVM: LAPIC: Expose per-vCPU timer_advance_ns to userspace
  KVM: LAPIC: Fix lapic_timer_advance_ns parameter overflow
  kvm: vmx: Fix -Wmissing-prototypes warnings
  KVM: nVMX: Fix using __this_cpu_read() in preemptible context
  kvm: fix compilation on s390
  ...

MAINTAINERS

@@ -8611,14 +8611,12 @@ F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
 KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64)
-M:	Christoffer Dall <[email protected]>
 M:	Marc Zyngier <[email protected]>
 R:	James Morse <[email protected]>
 R:	Julien Thierry <[email protected]>
 R:	Suzuki K Pouloze <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 L:	[email protected]
-W:	http://systems.cs.columbia.edu/projects/kvm-arm
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git
 S:	Maintained
 F:	arch/arm/include/uapi/asm/kvm*

arch/arm/kvm/hyp/Makefile

@@ -11,6 +11,7 @@ CFLAGS_ARMV7VE		   :=$(call cc-option, -march=armv7ve)
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/aarch32.o
 
 obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
 obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o

arch/arm64/include/asm/kvm_host.h

@@ -592,9 +592,6 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
 void kvm_clr_pmu_events(u32 clr);
 
-void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt);
-bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt);
-
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu);
 void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
 #else

arch/arm64/kvm/hyp/Makefile

@@ -10,6 +10,7 @@ KVM=../../../../virt/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/aarch32.o
 
 obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-cpuif-proxy.o
 obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o

arch/arm64/kvm/hyp/switch.c

@@ -16,6 +16,7 @@
  */
 
 #include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
 #include <linux/types.h>
 #include <linux/jump_label.h>
 #include <uapi/linux/psci.h>
@@ -505,6 +506,44 @@ static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
 #endif
 }
 
+/**
+ * Disable host events, enable guest events
+ */
+static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenclr_el0);
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenset_el0);
+
+	return (pmu->events_host || pmu->events_guest);
+}
+
+/**
+ * Disable guest events, enable host events
+ */
+static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+{
+	struct kvm_host_data *host;
+	struct kvm_pmu_events *pmu;
+
+	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+	pmu = &host->pmu_events;
+
+	if (pmu->events_guest)
+		write_sysreg(pmu->events_guest, pmcntenclr_el0);
+
+	if (pmu->events_host)
+		write_sysreg(pmu->events_host, pmcntenset_el0);
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {

arch/arm64/kvm/pmu.c

@@ -53,44 +53,6 @@ void kvm_clr_pmu_events(u32 clr)
 	ctx->pmu_events.events_guest &= ~clr;
 }
 
-/**
- * Disable host events, enable guest events
- */
-bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
-
-	if (pmu->events_host)
-		write_sysreg(pmu->events_host, pmcntenclr_el0);
-
-	if (pmu->events_guest)
-		write_sysreg(pmu->events_guest, pmcntenset_el0);
-
-	return (pmu->events_host || pmu->events_guest);
-}
-
-/**
- * Disable guest events, enable host events
- */
-void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
-{
-	struct kvm_host_data *host;
-	struct kvm_pmu_events *pmu;
-
-	host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
-	pmu = &host->pmu_events;
-
-	if (pmu->events_guest)
-		write_sysreg(pmu->events_guest, pmcntenclr_el0);
-
-	if (pmu->events_host)
-		write_sysreg(pmu->events_host, pmcntenset_el0);
-}
-
 #define PMEVTYPER_READ_CASE(idx)				\
 	case idx:						\
 		return read_sysreg(pmevtyper##idx##_el0)

arch/s390/include/asm/kvm_host.h

@@ -36,7 +36,7 @@
  */
 #define KVM_NR_IRQCHIPS 1
 #define KVM_IRQCHIP_NUM_PINS 4096
-#define KVM_HALT_POLL_NS_DEFAULT 80000
+#define KVM_HALT_POLL_NS_DEFAULT 50000
 
 /* s390-specific vcpu->requests bit members */
 #define KVM_REQ_ENABLE_IBS	KVM_ARCH_REQ(0)

arch/s390/kvm/kvm-s390.c

@@ -181,7 +181,7 @@ MODULE_PARM_DESC(hpage, "1m huge page backing support");
 /* maximum percentage of steal time for polling.  >100 is treated like 100 */
 static u8 halt_poll_max_steal = 10;
 module_param(halt_poll_max_steal, byte, 0644);
-MODULE_PARM_DESC(hpage, "Maximum percentage of steal time to allow polling");
+MODULE_PARM_DESC(halt_poll_max_steal, "Maximum percentage of steal time to allow polling");
 
 /*
  * For now we handle at most 16 double words as this is what the s390 base
@@ -4524,21 +4524,28 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
-	int rc;
-
-	/* If the basics of the memslot do not change, we do not want
-	 * to update the gmap. Every update causes several unnecessary
-	 * segment translation exceptions. This is usually handled just
-	 * fine by the normal fault handler + gmap, but it will also
-	 * cause faults on the prefix page of running guest CPUs.
-	 */
-	if (old->userspace_addr == mem->userspace_addr &&
-	    old->base_gfn * PAGE_SIZE == mem->guest_phys_addr &&
-	    old->npages * PAGE_SIZE == mem->memory_size)
-		return;
+	int rc = 0;
 
-	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
-		mem->guest_phys_addr, mem->memory_size);
+	switch (change) {
+	case KVM_MR_DELETE:
+		rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,
+					old->npages * PAGE_SIZE);
+		break;
+	case KVM_MR_MOVE:
+		rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,
+					old->npages * PAGE_SIZE);
+		if (rc)
+			break;
+		/* FALLTHROUGH */
+	case KVM_MR_CREATE:
+		rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
+				      mem->guest_phys_addr, mem->memory_size);
+		break;
+	case KVM_MR_FLAGS_ONLY:
+		break;
+	default:
+		WARN(1, "Unknown KVM MR CHANGE: %d\n", change);
+	}
 	if (rc)
 		pr_warn("failed to commit memory region\n");
 	return;

arch/x86/kvm/cpuid.c

@@ -456,8 +456,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		}
 		break;
 	}
-	/* function 4 has additional index. */
-	case 4: {
+	/* functions 4 and 0x8000001d have additional index. */
+	case 4:
+	case 0x8000001d: {
 		int i, cache_type;
 
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
@@ -701,8 +702,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		entry->ecx = entry->edx = 0;
 		break;
 	case 0x8000001a:
-		break;
-	case 0x8000001d:
+	case 0x8000001e:
 		break;
 	/*Add support for Centaur's CPUID instruction*/
 	case 0xC0000000:

arch/x86/kvm/debugfs.c

@@ -9,12 +9,22 @@
  */
 #include <linux/kvm_host.h>
 #include <linux/debugfs.h>
+#include "lapic.h"
 
 bool kvm_arch_has_vcpu_debugfs(void)
 {
 	return true;
 }
 
+static int vcpu_get_timer_advance_ns(void *data, u64 *val)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
+	*val = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_timer_advance_ns_fops, vcpu_get_timer_advance_ns, NULL, "%llu\n");
+
 static int vcpu_get_tsc_offset(void *data, u64 *val)
 {
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
@@ -51,6 +61,14 @@ int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 	if (!ret)
 		return -ENOMEM;
 
+	if (lapic_in_kernel(vcpu)) {
+		ret = debugfs_create_file("lapic_timer_advance_ns", 0444,
+								vcpu->debugfs_dentry,
+								vcpu, &vcpu_timer_advance_ns_fops);
+		if (!ret)
+			return -ENOMEM;
+	}
+
 	if (kvm_has_tsc_control) {
 		ret = debugfs_create_file("tsc-scaling-ratio", 0444,
 							vcpu->debugfs_dentry,

arch/x86/kvm/irq.c

@@ -172,3 +172,10 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
 	__kvm_migrate_apic_timer(vcpu);
 	__kvm_migrate_pit_timer(vcpu);
 }
+
+bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
+{
+	bool resample = args->flags & KVM_IRQFD_FLAG_RESAMPLE;
+
+	return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm);
+}

arch/x86/kvm/irq.h

@@ -114,6 +114,7 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
 	return mode != KVM_IRQCHIP_NONE;
 }
 
+bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);

arch/x86/kvm/pmu.c

@@ -283,23 +283,19 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 	bool fast_mode = idx & (1u << 31);
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
-	u64 ctr_val;
+	u64 mask = fast_mode ? ~0u : ~0ull;
 
 	if (!pmu->version)
 		return 1;
 
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 
-	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx);
+	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask);
 	if (!pmc)
 		return 1;
 
-	ctr_val = pmc_read_counter(pmc);
-	if (fast_mode)
-		ctr_val = (u32)ctr_val;
-
-	*data = ctr_val;
+	*data = pmc_read_counter(pmc) & mask;
 	return 0;
 }
 

arch/x86/kvm/pmu.h

@@ -25,7 +25,8 @@ struct kvm_pmu_ops {
 	unsigned (*find_fixed_event)(int idx);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
-	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx);
+	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx,
+					  u64 *mask);
 	int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);

arch/x86/kvm/pmu_amd.c

@@ -186,7 +186,7 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 }
 
 /* idx is the ECX register of RDPMC instruction */
-static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx)
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *counters;
@@ -269,10 +269,10 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
 	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->nr_arch_fixed_counters = 0;
-	pmu->version = 0;
 	pmu->global_status = 0;
 }
 

arch/x86/kvm/svm.c

@@ -379,6 +379,9 @@ module_param(vgif, int, 0444);
 static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
 module_param(sev, int, 0444);
 
+static bool __read_mostly dump_invalid_vmcb = 0;
+module_param(dump_invalid_vmcb, bool, 0644);
+
 static u8 rsm_ins_bytes[] = "\x0f\xaa";
 
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
@@ -2024,7 +2027,11 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
-	if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
+	/*
+	 * Since the host physical APIC id is 8 bits,
+	 * we can support host APIC ID upto 255.
+	 */
+	if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
 		return;
 
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
@@ -4824,6 +4831,11 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct vmcb_save_area *save = &svm->vmcb->save;
 
+	if (!dump_invalid_vmcb) {
+		pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
+		return;
+	}
+
 	pr_err("VMCB Control Area:\n");
 	pr_err("%-20s%04x\n", "cr_read:", control->intercept_cr & 0xffff);
 	pr_err("%-20s%04x\n", "cr_write:", control->intercept_cr >> 16);
@@ -4982,7 +4994,6 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		kvm_run->fail_entry.hardware_entry_failure_reason
 			= svm->vmcb->control.exit_code;
-		pr_err("KVM: FAILED VMRUN WITH VMCB:\n");
 		dump_vmcb(vcpu);
 		return 0;
 	}