4 files changed, 22 insertions, 5 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 6d5b6f0900e1..00f5962d82d0 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -108,6 +108,16 @@ extern void native_apic_icr_write(u32 low, u32 id);
 extern u64 native_apic_icr_read(void);
 
 #ifdef CONFIG_X86_X2APIC
+/*
+ * Make previous memory operations globally visible before
+ * sending the IPI through x2apic wrmsr. We need a serializing instruction or
+ * mfence for this.
+ */
+static inline void x2apic_wrmsr_fence(void)
+{
+        asm volatile("mfence" : : : "memory");
+}
+
 static inline void native_apic_msr_write(u32 reg, u32 v)
 {
         if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 8fb87b6dd633..4a903e2f0d17 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -57,6 +57,8 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
         unsigned long query_cpu;
         unsigned long flags;
 
+        x2apic_wrmsr_fence();
+
         local_irq_save(flags);
         for_each_cpu(query_cpu, mask) {
                 __x2apic_send_IPI_dest(
@@ -73,6 +75,8 @@ static void
         unsigned long query_cpu;
         unsigned long flags;
 
+        x2apic_wrmsr_fence();
+
         local_irq_save(flags);
         for_each_cpu(query_cpu, mask) {
                 if (query_cpu == this_cpu)
@@ -90,6 +94,8 @@ static void x2apic_send_IPI_allbutself(int vector)
         unsigned long query_cpu;
         unsigned long flags;
 
+        x2apic_wrmsr_fence();
+
         local_irq_save(flags);
         for_each_online_cpu(query_cpu) {
                 if (query_cpu == this_cpu)
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 23625b9f98b2..a284359627e7 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -58,6 +58,8 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
         unsigned long query_cpu;
         unsigned long flags;
 
+        x2apic_wrmsr_fence();
+
         local_irq_save(flags);
         for_each_cpu(query_cpu, mask) {
                 __x2apic_send_IPI_dest(per_cpu(x86_cpu_to_apicid, query_cpu),
@@ -73,6 +75,8 @@ static void
         unsigned long query_cpu;
         unsigned long flags;
 
+        x2apic_wrmsr_fence();
+
         local_irq_save(flags);
         for_each_cpu(query_cpu, mask) {
                 if (query_cpu != this_cpu)
@@ -89,6 +93,8 @@ static void x2apic_send_IPI_allbutself(int vector)
         unsigned long query_cpu;
         unsigned long flags;
 
+        x2apic_wrmsr_fence();
+
         local_irq_save(flags);
         for_each_online_cpu(query_cpu) {
                 if (query_cpu == this_cpu)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a654d59e4483..821e97017e95 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -187,11 +187,6 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
                        cpumask, cpumask_of(smp_processor_id()));
 
         /*
-         * Make the above memory operations globally visible before
-         * sending the IPI.
-         */
-        smp_mb();
-        /*
          * We have to send the IPI only to
          * CPUs affected.
          */