[Xen-devel] [PATCH 1/3] x86: avoid flush IPI when possible

["Jan Beulich" <JBeulich@xxxxxxxx>]

Since CLFLUSH, other than WBINVD, is a coherency domain wide flush,
there's no need to IPI other CPUs if this is the only flushing being
requested. (As a secondary change, move a local variable into the scope
where it's actually needed.)

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>

--- a/xen/arch/x86/flushtlb.c
+++ b/xen/arch/x86/flushtlb.c
@@ -91,9 +91,8 @@ void write_cr3(unsigned long cr3)
     local_irq_restore(flags);
 }
 
-void flush_area_local(const void *va, unsigned int flags)
+unsigned int flush_area_local(const void *va, unsigned int flags)
 {
-    const struct cpuinfo_x86 *c = &current_cpu_data;
     unsigned int order = (flags - 1) & FLUSH_ORDER_MASK;
     unsigned long irqfl;
 
@@ -130,6 +129,7 @@ void flush_area_local(const void *va, un
 
     if ( flags & FLUSH_CACHE )
     {
+        const struct cpuinfo_x86 *c = &current_cpu_data;
         unsigned long i, sz = 0;
 
         if ( order < (BITS_PER_LONG - PAGE_SHIFT) )
@@ -147,8 +147,11 @@ void flush_area_local(const void *va, un
         else
         {
             wbinvd();
+            flags &= ~FLUSH_CACHE;
         }
     }
 
     local_irq_restore(irqfl);
+
+    return flags & FLUSH_CACHE;
 }
--- a/xen/arch/x86/smp.c
+++ b/xen/arch/x86/smp.c
@@ -205,26 +205,30 @@ static unsigned int flush_flags;
 
 void invalidate_interrupt(struct cpu_user_regs *regs)
 {
+    unsigned int flags = flush_flags;
     ack_APIC_irq();
     perfc_incr(ipis);
-    if ( !__sync_local_execstate() ||
-         (flush_flags & (FLUSH_TLB_GLOBAL | FLUSH_CACHE)) )
-        flush_area_local(flush_va, flush_flags);
+    if ( __sync_local_execstate() )
+        flags &= ~FLUSH_TLB;
+    flush_area_local(flush_va, flags);
     cpumask_clear_cpu(smp_processor_id(), &flush_cpumask);
 }
 
 void flush_area_mask(const cpumask_t *mask, const void *va, unsigned int flags)
 {
+    unsigned int cpu = smp_processor_id();
+
     ASSERT(local_irq_is_enabled());
 
-    if ( cpumask_test_cpu(smp_processor_id(), mask) )
-        flush_area_local(va, flags);
+    if ( cpumask_test_cpu(cpu, mask) )
+        flags &= ~flush_area_local(va, flags);
 
-    if ( !cpumask_subset(mask, cpumask_of(smp_processor_id())) )
+    if ( (flags & ~FLUSH_ORDER_MASK) &&
+         !cpumask_subset(mask, cpumask_of(cpu)) )
     {
         spin_lock(&flush_lock);
         cpumask_and(&flush_cpumask, mask, &cpu_online_map);
-        cpumask_clear_cpu(smp_processor_id(), &flush_cpumask);
+        cpumask_clear_cpu(cpu, &flush_cpumask);
         flush_va      = va;
         flush_flags   = flags;
         send_IPI_mask(&flush_cpumask, INVALIDATE_TLB_VECTOR);
--- a/xen/include/asm-x86/flushtlb.h
+++ b/xen/include/asm-x86/flushtlb.h
@@ -87,7 +87,7 @@ void write_cr3(unsigned long cr3);
 #define FLUSH_CACHE      0x400
 
 /* Flush local TLBs/caches. */
-void flush_area_local(const void *va, unsigned int flags);
+unsigned int flush_area_local(const void *va, unsigned int flags);
 #define flush_local(flags) flush_area_local(NULL, flags)
 
 /* Flush specified CPUs' TLBs/caches */

Attachment: x86-flush-overhead.patch
Description: Text document

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel