NO MERGE: TEST ONLY: 5.15 velinux combine all PRs.

Documentation/admin-guide/hw-vuln/spectre.rst

@@ -484,11 +484,14 @@ Spectre variant 2
 
    Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at
    boot, by setting the IBRS bit, and they're automatically protected against
-   Spectre v2 variant attacks, including cross-thread branch target injections
-   on SMT systems (STIBP). In other words, eIBRS enables STIBP too.
+   Spectre v2 variant attacks.
 
-   Legacy IBRS systems clear the IBRS bit on exit to userspace and
-   therefore explicitly enable STIBP for that
+   On Intel's enhanced IBRS systems, this includes cross-thread branch target
+   injections on SMT systems (STIBP). In other words, Intel eIBRS enables
+   STIBP, too.
+
+   AMD Automatic IBRS does not protect userspace, and Legacy IBRS systems clear
+   the IBRS bit on exit to userspace, therefore both explicitly enable STIBP.
 
    The retpoline mitigation is turned on by default on vulnerable
    CPUs. It can be forced on or off by the administrator
@@ -622,9 +625,9 @@ kernel command line.
                 retpoline,generic       Retpolines
                 retpoline,lfence        LFENCE; indirect branch
                 retpoline,amd           alias for retpoline,lfence
-                eibrs                   enhanced IBRS
-                eibrs,retpoline         enhanced IBRS + Retpolines
-                eibrs,lfence            enhanced IBRS + LFENCE
+                eibrs                   Enhanced/Auto IBRS
+                eibrs,retpoline         Enhanced/Auto IBRS + Retpolines
+                eibrs,lfence            Enhanced/Auto IBRS + LFENCE
 
 		Not specifying this option is equivalent to
 		spectre_v2=auto.

Documentation/admin-guide/kernel-parameters.txt

@@ -5403,9 +5403,9 @@
 			retpoline,generic - Retpolines
 			retpoline,lfence  - LFENCE; indirect branch
 			retpoline,amd     - alias for retpoline,lfence
-			eibrs		  - enhanced IBRS
-			eibrs,retpoline   - enhanced IBRS + Retpolines
-			eibrs,lfence      - enhanced IBRS + LFENCE
+			eibrs		  - Enhanced/Auto IBRS
+			eibrs,retpoline   - Enhanced/Auto IBRS + Retpolines
+			eibrs,lfence      - Enhanced/Auto IBRS + LFENCE
 			ibrs		  - use IBRS to protect kernel
 
 			Not specifying this option is equivalent to

Documentation/virt/kvm/api.rst

@@ -7424,6 +7424,28 @@ of the result of KVM_CHECK_EXTENSION.  KVM will forward to userspace
 the hypercalls whose corresponding bit is in the argument, and return
 ENOSYS for the others.
 
+8.35 KVM_CAP_PMU_CAPABILITY
+---------------------------
+
+:Capability: KVM_CAP_PMU_CAPABILITY
+:Architectures: x86
+:Type: vm
+:Parameters: arg[0] is bitmask of PMU virtualization capabilities.
+:Returns: 0 on success, -EINVAL when arg[0] contains invalid bits
+
+This capability alters PMU virtualization in KVM.
+
+Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
+PMU virtualization capabilities that can be adjusted on a VM.
+
+The argument to KVM_ENABLE_CAP is also a bitmask and selects specific
+PMU virtualization capabilities to be applied to the VM.  This can
+only be invoked on a VM prior to the creation of VCPUs.
+
+At this time, KVM_PMU_CAP_DISABLE is the only capability.  Setting
+this capability will disable PMU virtualization for that VM.  Usermode
+should adjust CPUID leaf 0xA to reflect that the PMU is disabled.
+
 9. Known KVM API problems
 =========================
 

Documentation/virt/kvm/locking.rst

@@ -257,3 +257,9 @@ time it will be set using the Dirty tracking mechanism described above.
 		wakeup notification event since external interrupts from the
 		assigned devices happens, we will find the vCPU on the list to
 		wakeup.
+
+``vendor_module_lock``
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+:Type:		mutex
+:Arch:		x86
+:Protects:	loading a vendor module (kvm_amd or kvm_intel)

arch/arm64/include/asm/kvm_host.h

@@ -765,6 +765,16 @@ int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa);
 void kvm_perf_init(void);
 void kvm_perf_teardown(void);
 
+/*
+ * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event,
+ * arrived in guest context.  For arm64, any event that arrives while a vCPU is
+ * loaded is considered to be "in guest".
+ */
+static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
+{
+	return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
+}
+
 long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
 gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu);

arch/arm64/kvm/arm.c

@@ -505,6 +505,11 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 	return vcpu_mode_priv(vcpu);
 }
 
+unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
+{
+	return *vcpu_pc(vcpu);
+}
+
 /* Just ensure a guest exit from a particular CPU */
 static void exit_vm_noop(void *info)
 {

arch/x86/events/amd/core.c

@@ -433,7 +433,7 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
 	 * be removed on one CPU at a time AND PMU is disabled
 	 * when we come here
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (cmpxchg(nb->owners + i, event, NULL) == event)
 			break;
 	}
@@ -500,7 +500,7 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
 	 * because of successive calls to x86_schedule_events() from
 	 * hw_perf_group_sched_in() without hw_perf_enable()
 	 */
-	for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
+	for_each_set_bit(idx, c->idxmsk, x86_pmu_max_num_counters(NULL)) {
 		if (new == -1 || hwc->idx == idx)
 			/* assign free slot, prefer hwc->idx */
 			old = cmpxchg(nb->owners + idx, NULL, event);
@@ -543,7 +543,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
 	/*
 	 * initialize all possible NB constraints
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
@@ -739,7 +739,7 @@ static void amd_pmu_check_overflow(void)
 	 * counters are always enabled when this function is called and
 	 * ARCH_PERFMON_EVENTSEL_INT is always set.
 	 */
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -760,7 +760,7 @@ static void amd_pmu_enable_all(int added)
 
 	amd_brs_enable_all();
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		hwc = &cpuc->events[idx]->hw;
 
 		/* only activate events which are marked as active */
@@ -954,7 +954,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	/* Clear any reserved bits set by buggy microcode */
 	status &= amd_pmu_global_cntr_mask;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -1289,7 +1289,7 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.addr_offset            = amd_pmu_addr_offset,
 	.event_map		= amd_pmu_event_map,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_counters		= AMD64_NUM_COUNTERS,
+	.cntr_mask64		= GENMASK_ULL(AMD64_NUM_COUNTERS - 1, 0),
 	.add			= amd_pmu_add_event,
 	.del			= amd_pmu_del_event,
 	.cntval_bits		= 48,
@@ -1388,7 +1388,7 @@ static int __init amd_core_pmu_init(void)
 	 */
 	x86_pmu.eventsel	= MSR_F15H_PERF_CTL;
 	x86_pmu.perfctr		= MSR_F15H_PERF_CTR;
-	x86_pmu.num_counters	= AMD64_NUM_COUNTERS_CORE;
+	x86_pmu.cntr_mask64	= GENMASK_ULL(AMD64_NUM_COUNTERS_CORE - 1, 0);
 
 	/* Check for Performance Monitoring v2 support */
 	if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) {
@@ -1398,9 +1398,9 @@ static int __init amd_core_pmu_init(void)
 		x86_pmu.version = 2;
 
 		/* Find the number of available Core PMCs */
-		x86_pmu.num_counters = ebx.split.num_core_pmc;
+		x86_pmu.cntr_mask64 = GENMASK_ULL(ebx.split.num_core_pmc - 1, 0);
 
-		amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
+		amd_pmu_global_cntr_mask = x86_pmu.cntr_mask64;
 
 		/* Update PMC handling functions */
 		x86_pmu.enable_all = amd_pmu_v2_enable_all;
@@ -1428,12 +1428,12 @@ static int __init amd_core_pmu_init(void)
 		 * even numbered counter that has a consecutive adjacent odd
 		 * numbered counter following it.
 		 */
-		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
+		for (i = 0; i < x86_pmu_max_num_counters(NULL) - 1; i += 2)
 			even_ctr_mask |= BIT_ULL(i);
 
 		pair_constraint = (struct event_constraint)
 				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
-				    x86_pmu.num_counters / 2, 0,
+				    x86_pmu_max_num_counters(NULL) / 2, 0,
 				    PERF_X86_EVENT_PAIR);
 
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;