From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 25 Jan 2016 14:13:47 +0000 (+0100)
Subject: memory: add early bail out from cpu_physical_memory_set_dirty_range
X-Git-Url: http://git.osdn.net/view?a=commitdiff_plain;h=8bafcb21643a39a5b29109f8bd5ee5a6f0f6850b;p=qmiga%2Fqemu.git

memory: add early bail out from cpu_physical_memory_set_dirty_range

This condition is true in the common case, so we can cut out the body of
the function.  In addition, this makes it easier for the compiler to do
at least partial inlining, even if it decides that fully inlining the
function is unreasonable.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---

diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index 606e277092..f2e872d87a 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -165,6 +165,10 @@ static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start,
     unsigned long end, page;
     unsigned long **d = ram_list.dirty_memory;
 
+    if (!mask && !xen_enabled()) {
+        return;
+    }
+
     end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
     page = start >> TARGET_PAGE_BITS;
     if (likely(mask & (1 << DIRTY_MEMORY_MIGRATION))) {