x2apic: Clean up send_IPI_mask_x2apic() and add a memory barrier.

The barrier is required to prevent the WRMSR from executing before the
processor has written synchronising data to be received by remote
CPUs.

At the same time remove needless wmb() from on_selected_cpus(). We now
assume send_IPI_mask() is a sufficient compiler and CPU memory
barrier.

Original patch by Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Keir Fraser <keir.fraser@citrix.com>

diff --git a/xen/arch/x86/genapic/x2apic.c b/xen/arch/x86/genapic/x2apic.c
index bfd3a286e3f0fbf4265e549346cd457d517611c4..3dd97250c7ca9f584ffb8862a36a5e2fcb26c912 100644 (file)
--- a/xen/arch/x86/genapic/x2apic.c
+++ b/xen/arch/x86/genapic/x2apic.c
@@ -58,21 +58,26 @@ unsigned int cpu_mask_to_apicid_x2apic(cpumask_t cpumask)
 
 void send_IPI_mask_x2apic(cpumask_t cpumask, int vector)
 {
-    unsigned int query_cpu;
-    u32 cfg, dest;
+    unsigned int cpu, cfg;
     unsigned long flags;
 
-    ASSERT(cpus_subset(cpumask, cpu_online_map));
-    ASSERT(!cpus_empty(cpumask));
+    /*
+     * Ensure that any synchronisation data written in program order by this
+     * CPU is seen by notified remote CPUs. The WRMSR contained within
+     * apic_icr_write() can otherwise be executed early.
+     * 
+     * The reason mb() is sufficient here is subtle: the register arguments
+     * to WRMSR must depend on a memory read executed after the barrier. This
+     * is guaranteed by cpu_physical_id(), which reads from a global array (and
+     * so cannot be hoisted above the barrier even by a clever compiler).
+     */
+    mb();
 
     local_irq_save(flags);
 
     cfg = APIC_DM_FIXED | 0 /* no shorthand */ | APIC_DEST_PHYSICAL | vector;
-    for_each_cpu_mask(query_cpu, cpumask)
-    {
-        dest =  cpu_physical_id(query_cpu);
-        apic_icr_write(cfg, dest);
-    }
+    for_each_cpu_mask ( cpu, cpumask )
+        apic_wrmsr(APIC_ICR, cfg, cpu_physical_id(cpu));
 
     local_irq_restore(flags);
 }

diff --git a/xen/arch/x86/smp.c b/xen/arch/x86/smp.c
index 497468bf8b03a6b3b795244692096fc7752d3d14..dba5cb58b666709e467042113d6446b5edfa4c91 100644 (file)
--- a/xen/arch/x86/smp.c
+++ b/xen/arch/x86/smp.c
@@ -280,7 +280,6 @@ int on_selected_cpus(
     spin_lock(&call_lock);
 
     call_data = &data;
-    wmb();
 
     send_IPI_mask(selected, CALL_FUNCTION_VECTOR);