x86, KVM: Optimize SEV cache flushing

index 7051c9c909c2..ea1d2d5d2c66 100644
@@ -93,8 +93,7 @@ drm_clflush_pages(struct page *pages[], unsigned long num_pages)
 		return;
 	}
 
-	if (wbinvd_on_all_cpus())
-		pr_err("Timed out waiting for cache flush\n");
+	wbinvd_on_all_cpus();
 
 #elif defined(__powerpc__)
 	unsigned long i;

@@ -139,8 +138,7 @@ drm_clflush_sg(struct sg_table *st)
 		return;
 	}
 
-	if (wbinvd_on_all_cpus())
-		pr_err("Timed out waiting for cache flush\n");
+	wbinvd_on_all_cpus();
 #else
 	WARN_ONCE(1, "Architecture has no drm_cache.c support\n");
 #endif

@@ -172,8 +170,7 @@ drm_clflush_virt_range(void *addr, unsigned long length)
 		return;
 	}
 
-	if (wbinvd_on_all_cpus())
-		pr_err("Timed out waiting for cache flush\n");
+	wbinvd_on_all_cpus();
 #else
 	WARN_ONCE(1, "Architecture has no drm_cache.c support\n");
 #endif

index 0c1c68039d6f..028f126018c9 100644
@@ -112,7 +112,7 @@ void __noreturn hlt_play_dead(void);
 void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
-int wbinvd_on_all_cpus(void);
+void wbinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
 void __noreturn mwait_play_dead(unsigned int eax_hint);

@@ -148,10 +148,9 @@ static inline struct cpumask *cpu_l2c_shared_mask(int cpu)
 
 #else /* !CONFIG_SMP */
 #define wbinvd_on_cpu(cpu)     wbinvd()
-static inline int wbinvd_on_all_cpus(void)
+static inline void wbinvd_on_all_cpus(void)
 {
 	wbinvd();
-	return 0;
 }
 
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)

index 7af743bd3b13..079c3f3cd32c 100644
@@ -14,9 +14,8 @@ void wbinvd_on_cpu(int cpu)
 }
 EXPORT_SYMBOL(wbinvd_on_cpu);
 
-int wbinvd_on_all_cpus(void)
+void wbinvd_on_all_cpus(void)
 {
 	on_each_cpu(__wbinvd, NULL, 1);
-	return 0;
 }
 EXPORT_SYMBOL(wbinvd_on_all_cpus);

index 028f126018c9..e08f1ae25401 100644
@@ -113,6 +113,7 @@ void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
 void wbinvd_on_all_cpus(void);
+void wbnoinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
 void __noreturn mwait_play_dead(unsigned int eax_hint);

@@ -153,6 +154,11 @@ static inline void wbinvd_on_all_cpus(void)
 	wbinvd();
 }
 
+static inline void wbnoinvd_on_all_cpus(void)
+{
+	wbnoinvd();
+}
+
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return (struct cpumask *)cpumask_of(0);

index 6266d6b9e0b8..f2240c4ac0ea 100644
@@ -115,9 +115,39 @@ static inline void wrpkru(u32 pkru)
 }
 #endif
 
+/*
+ * Write back all modified lines in all levels of cache associated with this
+ * logical processor to main memory, and then invalidate all caches.  Depending
+ * on the micro-architecture, WBINVD (and WBNOINVD below) may or may not affect
+ * lower level caches associated with another logical processor that shares any
+ * level of this processor’s cache hierarchy.
+ *
+ * Note, AMD CPUs enumerate the behavior or WB{NO}{INVD} with respect to other
+ * logical, non-originating processors in CPUID 0x8000001D.EAX[N:0].
+ */
 static __always_inline void wbinvd(void)
 {
-	asm volatile("wbinvd": : :"memory");
+	asm volatile("wbinvd" : : : "memory");
+}
+
+/* Instruction encoding provided for binutils backwards compatibility. */
+#define ASM_WBNOINVD _ASM_BYTES(0xf3,0x0f,0x09)
+
+/*
+ * Write back all modified lines in all levels of cache associated with this
+ * logical processor to main memory, but do NOT explicitly invalidate caches,
+ * i.e. leave all/most cache lines in the hierarchy in non-modified state.
+ */
+static __always_inline void wbnoinvd(void)
+{
+	/*
+	 * Explicitly encode WBINVD if X86_FEATURE_WBNOINVD is unavailable even
+	 * though WBNOINVD is backwards compatible (it's simply WBINVD with an
+	 * ignored REP prefix), to guarantee that WBNOINVD isn't used if it
+	 * needs to be avoided for any reason.  For all supported usage in the
+	 * kernel, WBINVD is functionally a superset of WBNOINVD.
+	 */
+	alternative("wbinvd", ASM_WBNOINVD, X86_FEATURE_WBNOINVD);
 }
 
 static inline unsigned long __read_cr4(void)

index 079c3f3cd32c..1789db5d8825 100644
@@ -19,3 +19,14 @@ void wbinvd_on_all_cpus(void)
 	on_each_cpu(__wbinvd, NULL, 1);
 }
 EXPORT_SYMBOL(wbinvd_on_all_cpus);
+
+static void __wbnoinvd(void *dummy)
+{
+	wbnoinvd();
+}
+
+void wbnoinvd_on_all_cpus(void)
+{
+	on_each_cpu(__wbnoinvd, NULL, 1);
+}
+EXPORT_SYMBOL(wbnoinvd_on_all_cpus);

index c5c60d07308c..ac3cc32a4054 100644
@@ -12,19 +12,19 @@ void wbinvd_on_cpu(int cpu)
 {
 	smp_call_function_single(cpu, __wbinvd, NULL, 1);
 }
-EXPORT_SYMBOL(wbinvd_on_cpu);
+EXPORT_SYMBOL_GPL_FOR_MODULES(wbinvd_on_cpu, "kvm-amd,agpgart,ccp,drm,i915");
 
 void wbinvd_on_all_cpus(void)
 {
 	on_each_cpu(__wbinvd, NULL, 1);
 }
-EXPORT_SYMBOL(wbinvd_on_all_cpus);
+EXPORT_SYMBOL_GPL_FOR_MODULES(wbinvd_on_all_cpus, "kvm-amd,agpgart,ccp,drm,i915,intel-gtt");
 
 void wbinvd_on_cpus_mask(struct cpumask *cpus)
 {
 	on_each_cpu_mask(cpus, __wbinvd, NULL, 1);
 }
-EXPORT_SYMBOL_GPL(wbinvd_on_cpus_mask);
+EXPORT_SYMBOL_GPL_FOR_MODULES(wbinvd_on_cpus_mask, "kvm,kvm-amd,agpgart,ccp,drm,i915");
 
 static void __wbnoinvd(void *dummy)
 {

@@ -35,10 +35,10 @@ void wbnoinvd_on_all_cpus(void)
 {
 	on_each_cpu(__wbnoinvd, NULL, 1);
 }
-EXPORT_SYMBOL_GPL(wbnoinvd_on_all_cpus);
+EXPORT_SYMBOL_GPL_FOR_MODULES(wbnoinvd_on_all_cpus, "kvm-amd,agpgart,ccp,drm,i915");
 
 void wbnoinvd_on_cpus_mask(struct cpumask *cpus)
 {
 	on_each_cpu_mask(cpus, __wbnoinvd, NULL, 1);
 }
-EXPORT_SYMBOL_GPL(wbnoinvd_on_cpus_mask);
+EXPORT_SYMBOL_GPL_FOR_MODULES(wbnoinvd_on_cpus_mask, "kvm-amd,agpgart,ccp,drm,i915");

index e08f1ae25401..22bfebe6776d 100644
@@ -113,7 +113,9 @@ void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
 void wbinvd_on_all_cpus(void);
+void wbinvd_on_cpus_mask(struct cpumask *cpus);
 void wbnoinvd_on_all_cpus(void);
+void wbnoinvd_on_cpus_mask(struct cpumask *cpus);
 
 void smp_kick_mwait_play_dead(void);
 void __noreturn mwait_play_dead(unsigned int eax_hint);

@@ -154,11 +156,21 @@ static inline void wbinvd_on_all_cpus(void)
 	wbinvd();
 }
 
+static inline void wbinvd_on_cpus_mask(struct cpumask *cpus)
+{
+	wbinvd();
+}
+
 static inline void wbnoinvd_on_all_cpus(void)
 {
 	wbnoinvd();
 }
 
+static inline void wbnoinvd_on_cpus_mask(struct cpumask *cpus)
+{
+	wbnoinvd();
+}
+
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return (struct cpumask *)cpumask_of(0);

index be7bb6d20129..1d0e9180148d 100644
@@ -8245,8 +8245,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
 		int cpu = get_cpu();
 
 		cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
-		on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,
-				wbinvd_ipi, NULL, 1);
+		wbinvd_on_cpus_mask(vcpu->arch.wbinvd_dirty_mask);
 		put_cpu();
 		cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
 	} else

index 1789db5d8825..b45e8baa69bb 100644
@@ -20,6 +20,12 @@ void wbinvd_on_all_cpus(void)
 }
 EXPORT_SYMBOL(wbinvd_on_all_cpus);
 
+void wbinvd_on_cpus_mask(struct cpumask *cpus)
+{
+	on_each_cpu_mask(cpus, __wbinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(wbinvd_on_cpus_mask);
+
 static void __wbnoinvd(void *dummy)
 {
 	wbnoinvd();

@@ -30,3 +36,9 @@ void wbnoinvd_on_all_cpus(void)
 	on_each_cpu(__wbnoinvd, NULL, 1);
 }
 EXPORT_SYMBOL(wbnoinvd_on_all_cpus);
+
+void wbnoinvd_on_cpus_mask(struct cpumask *cpus)
+{
+	on_each_cpu_mask(cpus, __wbnoinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(wbnoinvd_on_cpus_mask);

index 1d0e9180148d..d63a2c27e058 100644
@@ -4965,11 +4965,6 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return r;
 }
 
-static void wbinvd_ipi(void *garbage)
-{
-	wbinvd();
-}
-
 static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 {
 	return kvm_arch_has_noncoherent_dma(vcpu->kvm);

@@ -4991,8 +4986,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		if (kvm_x86_call(has_wbinvd_exit)())
 			cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
 		else if (vcpu->cpu != -1 && vcpu->cpu != cpu)
-			smp_call_function_single(vcpu->cpu,
-					wbinvd_ipi, NULL, 1);
+			wbinvd_on_cpu(vcpu->cpu);
 	}
 
 	kvm_x86_call(vcpu_load)(vcpu, cpu);

index a7a7dc507336..be70c8401c9b 100644
@@ -2879,12 +2879,6 @@ void sev_vm_destroy(struct kvm *kvm)
 		return;
 	}
 
-	/*
-	 * Ensure that all guest tagged cache entries are flushed before
-	 * releasing the pages back to the system for use. CLFLUSH will
-	 * not do this, so issue a WBINVD.
-	 */
-	wbinvd_on_all_cpus();
 
 	/*
 	 * if userspace was terminated before unregistering the memory regions

index be70c8401c9b..2676be2b121d 100644
@@ -116,6 +116,7 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
 	 */
 	down_write(&sev_deactivate_lock);
 
+	/* SNP firmware requires use of WBINVD for ASID recycling. */
 	wbinvd_on_all_cpus();
 
 	if (sev_snp_enabled)

@@ -705,6 +706,18 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
 	}
 }
 
+static void sev_writeback_caches(void)
+{
+	/*
+	 * Ensure that all dirty guest tagged cache entries are written back
+	 * before releasing the pages back to the system for use.  CLFLUSH will
+	 * not do this without SME_COHERENT, and flushing many cache lines
+	 * individually is slower than blasting WBINVD for large VMs, so issue
+	 * WBNOINVD (or WBINVD if the "no invalidate" variant is unsupported).
+	 */
+	wbnoinvd_on_all_cpus();
+}
+
 static unsigned long get_num_contig_pages(unsigned long idx,
 				struct page **inpages, unsigned long npages)
 {

@@ -2753,12 +2766,7 @@ int sev_mem_enc_unregister_region(struct kvm *kvm,
 		goto failed;
 	}
 
-	/*
-	 * Ensure that all guest tagged cache entries are flushed before
-	 * releasing the pages back to the system for use. CLFLUSH will
-	 * not do this, so issue a WBINVD.
-	 */
-	wbinvd_on_all_cpus();
+	sev_writeback_caches();
 
 	__unregister_enc_region_locked(kvm, region);
 

@@ -3110,30 +3118,29 @@ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
 
 	/*
 	 * VM Page Flush takes a host virtual address and a guest ASID.  Fall
-	 * back to WBINVD if this faults so as not to make any problems worse
-	 * by leaving stale encrypted data in the cache.
+	 * back to full writeback of caches if this faults so as not to make
+	 * any problems worse by leaving stale encrypted data in the cache.
 	 */
 	if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid)))
-		goto do_wbinvd;
+		goto do_sev_writeback_caches;
 
 	return;
 
-do_wbinvd:
-	wbinvd_on_all_cpus();
+do_sev_writeback_caches:
+	sev_writeback_caches();
 }
 
 void sev_guest_memory_reclaimed(struct kvm *kvm)
 {
 	/*
 	 * With SNP+gmem, private/encrypted memory is unreachable via the
-	 * hva-based mmu notifiers, so these events are only actually
-	 * pertaining to shared pages where there is no need to perform
-	 * the WBINVD to flush associated caches.
+	 * hva-based mmu notifiers, i.e. these events are explicitly scoped to
+	 * shared pages, where there's no need to flush caches.
 	 */
 	if (!sev_guest(kvm) || sev_snp_guest(kvm))
 		return;
 
-	wbinvd_on_all_cpus();
+	sev_writeback_caches();
 }
 
 void sev_free_vcpu(struct kvm_vcpu *vcpu)

@@ -3897,9 +3904,9 @@ void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
 	 * From this point forward, the VMSA will always be a guest-mapped page
 	 * rather than the initial one allocated by KVM in svm->sev_es.vmsa. In
 	 * theory, svm->sev_es.vmsa could be free'd and cleaned up here, but
-	 * that involves cleanups like wbinvd_on_all_cpus() which would ideally
-	 * be handled during teardown rather than guest boot.  Deferring that
-	 * also allows the existing logic for SEV-ES VMSAs to be re-used with
+	 * that involves cleanups like flushing caches, which would ideally be
+	 * handled during teardown rather than guest boot.  Deferring that also
+	 * allows the existing logic for SEV-ES VMSAs to be re-used with
 	 * minimal SNP-specific changes.
 	 */
 	svm->sev_es.snp_has_guest_vmsa = true;

@@ -4892,7 +4899,7 @@ void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 
 		/*
 		 * SEV-ES avoids host/guest cache coherency issues through
-		 * WBINVD hooks issued via MMU notifiers during run-time, and
+		 * WBNOINVD hooks issued via MMU notifiers during run-time, and
 		 * KVM's VM destroy path at shutdown. Those MMU notifier events
 		 * don't cover gmem since there is no requirement to map pages
 		 * to a HVA in order to use them for a running guest. While the

index 2676be2b121d..c3ddcca9fdce 100644
@@ -446,7 +446,12 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
 	init_args.probe = false;
 	ret = sev_platform_init(&init_args);
 	if (ret)
-		goto e_free;
+		goto e_free_asid;
+
+	if (!zalloc_cpumask_var(&sev->have_run_cpus, GFP_KERNEL_ACCOUNT)) {
+		ret = -ENOMEM;
+		goto e_free_asid;
+	}
 
 	/* This needs to happen after SEV/SNP firmware initialization. */
 	if (vm_type == KVM_X86_SNP_VM) {

@@ -464,6 +469,8 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
 	return 0;
 
 e_free:
+	free_cpumask_var(sev->have_run_cpus);
+e_free_asid:
 	argp->error = init_args.error;
 	sev_asid_free(sev);
 	sev->asid = 0;

@@ -706,16 +713,31 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
 	}
 }
 
-static void sev_writeback_caches(void)
+static void sev_writeback_caches(struct kvm *kvm)
 {
+	/*
+	 * Note, the caller is responsible for ensuring correctness if the mask
+	 * can be modified, e.g. if a CPU could be doing VMRUN.
+	 */
+	if (cpumask_empty(to_kvm_sev_info(kvm)->have_run_cpus))
+		return;
+
 	/*
 	 * Ensure that all dirty guest tagged cache entries are written back
 	 * before releasing the pages back to the system for use.  CLFLUSH will
 	 * not do this without SME_COHERENT, and flushing many cache lines
 	 * individually is slower than blasting WBINVD for large VMs, so issue
-	 * WBNOINVD (or WBINVD if the "no invalidate" variant is unsupported).
+	 * WBNOINVD (or WBINVD if the "no invalidate" variant is unsupported)
+	 * on CPUs that have done VMRUN, i.e. may have dirtied data using the
+	 * VM's ASID.
+	 *
+	 * For simplicity, never remove CPUs from the bitmap.  Ideally, KVM
+	 * would clear the mask when flushing caches, but doing so requires
+	 * serializing multiple calls and having responding CPUs (to the IPI)
+	 * mark themselves as still running if they are running (or about to
+	 * run) a vCPU for the VM.
 	 */
-	wbnoinvd_on_all_cpus();
+	wbnoinvd_on_cpus_mask(to_kvm_sev_info(kvm)->have_run_cpus);
 }
 
 static unsigned long get_num_contig_pages(unsigned long idx,

@@ -2766,7 +2788,7 @@ int sev_mem_enc_unregister_region(struct kvm *kvm,
 		goto failed;
 	}
 
-	sev_writeback_caches();
+	sev_writeback_caches(kvm);
 
 	__unregister_enc_region_locked(kvm, region);
 

@@ -2914,6 +2936,7 @@ void sev_vm_destroy(struct kvm *kvm)
 	}
 
 	sev_asid_free(sev);
+	free_cpumask_var(sev->have_run_cpus);
 }
 
 void __init sev_set_cpu_caps(void)

@@ -3127,7 +3150,7 @@ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
 	return;
 
 do_sev_writeback_caches:
-	sev_writeback_caches();
+	sev_writeback_caches(vcpu->kvm);
 }
 
 void sev_guest_memory_reclaimed(struct kvm *kvm)

@@ -3140,7 +3163,7 @@ void sev_guest_memory_reclaimed(struct kvm *kvm)
 	if (!sev_guest(kvm) || sev_snp_guest(kvm))
 		return;
 
-	sev_writeback_caches();
+	sev_writeback_caches(kvm);
 }
 
 void sev_free_vcpu(struct kvm_vcpu *vcpu)

@@ -3472,6 +3495,15 @@ int pre_sev_run(struct vcpu_svm *svm, int cpu)
 	if (sev_es_guest(kvm) && !VALID_PAGE(svm->vmcb->control.vmsa_pa))
 		return -EINVAL;
 
+	/*
+	 * To optimize cache flushes when memory is reclaimed from an SEV VM,
+	 * track physical CPUs that enter the guest for SEV VMs and thus can
+	 * have encrypted, dirty data in the cache, and flush caches only for
+	 * CPUs that have entered the guest.
+	 */
+	if (!cpumask_test_cpu(cpu, to_kvm_sev_info(kvm)->have_run_cpus))
+		cpumask_set_cpu(cpu, to_kvm_sev_info(kvm)->have_run_cpus);
+
 	/* Assign the asid allocated with this SEV guest */
 	svm->asid = asid;
 

index f16b068c4228..45d564c674ef 100644
@@ -112,6 +112,7 @@ struct kvm_sev_info {
 	void *guest_req_buf;    /* Bounce buffer for SNP Guest Request input */
 	void *guest_resp_buf;   /* Bounce buffer for SNP Guest Request output */
 	struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */
+	cpumask_var_t have_run_cpus; /* CPUs that have done VMRUN for this VM. */
 };
 
 struct kvm_svm {