6 files changed, 56 insertions, 15 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 5398db4dedb4..ccaa51ce63f6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1355,11 +1355,23 @@ static __init int print_s5_reset_status_mmio(void)
 		return 0;
 
 	value = ioread32(addr);
-	iounmap(addr);
 
 	/* Value with "all bits set" is an error response and should be ignored. */
-	if (value == U32_MAX)
+	if (value == U32_MAX) {
+		iounmap(addr);
 		return 0;
+	}
+
+	/*
+	 * Clear all reason bits so they won't be retained if the next reset
+	 * does not update the register. Besides, some bits are never cleared by
+	 * hardware so it's software's responsibility to clear them.
+	 *
+	 * Writing the value back effectively clears all reason bits as they are
+	 * write-1-to-clear.
+	 */
+	iowrite32(value, addr);
+	iounmap(addr);
 
 	for (i = 0; i < ARRAY_SIZE(s5_reset_reason_txt); i++) {
 		if (!(value & BIT(i)))
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index c8945610d455..2cd25a0d4637 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -242,7 +242,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
 			   u64 *val, void *ignored)
 {
+	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
 	int cpu = cpumask_any(&d->hdr.cpu_mask);
+	struct arch_mbm_state *am;
 	u64 msr_val;
 	u32 prmid;
 	int ret;
@@ -251,12 +253,16 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
 
 	prmid = logical_rmid_to_physical_rmid(cpu, rmid);
 	ret = __rmid_read_phys(prmid, eventid, &msr_val);
-	if (ret)
-		return ret;
 
-	*val = get_corrected_val(r, d, rmid, eventid, msr_val);
+	if (!ret) {
+		*val = get_corrected_val(r, d, rmid, eventid, msr_val);
+	} else if (ret == -EINVAL) {
+		am = get_arch_mbm_state(hw_dom, rmid, eventid);
+		if (am)
+			am->prev_msr = 0;
+	}
 
-	return 0;
+	return ret;
 }
 
 static int __cntr_id_read(u32 cntr_id, u64 *val)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 40ac4cb44ed2..487ad19a236e 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -108,16 +108,18 @@ void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops)
 	bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL;
 	int min_nr_gp_ctrs = pmu_ops->MIN_NR_GP_COUNTERS;
 
-	perf_get_x86_pmu_capability(&kvm_host_pmu);
-
 	/*
 	 * Hybrid PMUs don't play nice with virtualization without careful
 	 * configuration by userspace, and KVM's APIs for reporting supported
 	 * vPMU features do not account for hybrid PMUs.  Disable vPMU support
 	 * for hybrid PMUs until KVM gains a way to let userspace opt-in.
 	 */
-	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
 		enable_pmu = false;
+		memset(&kvm_host_pmu, 0, sizeof(kvm_host_pmu));
+	} else {
+		perf_get_x86_pmu_capability(&kvm_host_pmu);
+	}
 
 	if (enable_pmu) {
 		/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 42ecd093bb4c..b4b5d2d09634 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13941,10 +13941,11 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 
 #ifdef CONFIG_KVM_GUEST_MEMFD
 /*
- * KVM doesn't yet support mmap() on guest_memfd for VMs with private memory
- * (the private vs. shared tracking needs to be moved into guest_memfd).
+ * KVM doesn't yet support initializing guest_memfd memory as shared for VMs
+ * with private memory (the private vs. shared tracking needs to be moved into
+ * guest_memfd).
  */
-bool kvm_arch_supports_gmem_mmap(struct kvm *kvm)
+bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm)
 {
 	return !kvm_arch_has_private_mem(kvm);
 }
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index d2d54b8c4dbb..970981893c9b 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -446,7 +446,7 @@ static void cpa_flush(struct cpa_data *cpa, int cache)
 	}
 
 	start = fix_addr(__cpa_addr(cpa, 0));
-	end =   fix_addr(__cpa_addr(cpa, cpa->numpages));
+	end =   start + cpa->numpages * PAGE_SIZE;
 	if (cpa->force_flush_all)
 		end = TLB_FLUSH_ALL;
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 39f80111e6f1..5d221709353e 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -911,11 +911,31 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		 * CR3 and cpu_tlbstate.loaded_mm are not all in sync.
 		 */
 		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
-		barrier();
 
-		/* Start receiving IPIs and then read tlb_gen (and LAM below) */
+		/*
+		 * Make sure this CPU is set in mm_cpumask() such that we'll
+		 * receive invalidation IPIs.
+		 *
+		 * Rely on the smp_mb() implied by cpumask_set_cpu()'s atomic
+		 * operation, or explicitly provide one. Such that:
+		 *
+		 * switch_mm_irqs_off()				flush_tlb_mm_range()
+		 *   smp_store_release(loaded_mm, SWITCHING);     atomic64_inc_return(tlb_gen)
+		 *   smp_mb(); // here                            // smp_mb() implied
+		 *   atomic64_read(tlb_gen);                      this_cpu_read(loaded_mm);
+		 *
+		 * we properly order against flush_tlb_mm_range(), where the
+		 * loaded_mm load can happen in mative_flush_tlb_multi() ->
+		 * should_flush_tlb().
+		 *
+		 * This way switch_mm() must see the new tlb_gen or
+		 * flush_tlb_mm_range() must see the new loaded_mm, or both.
+		 */
 		if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
+		else
+			smp_mb();
+
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
 		ns = choose_new_asid(next, next_tlb_gen);