diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 0c1c680..22bfebe 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -112,7 +112,10 @@ 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 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);
@@ -148,10 +151,24 @@ 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 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)
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index ecda17e..fde2bd7 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -104,9 +104,36 @@ 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.
+ */
 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)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 93636f7..f2a57a1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8295,8 +8295,7 @@ 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
diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
index 7af743b..c5c60d0 100644
--- a/arch/x86/lib/cache-smp.c
+++ b/arch/x86/lib/cache-smp.c
@@ -14,9 +14,31 @@ 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);
+
+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();
+}
+
+void wbnoinvd_on_all_cpus(void)
+{
+	on_each_cpu(__wbnoinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(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);
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index 7051c9c..ea1d2d5 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -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
