[PATCH] util: optimise flush_idcache_range when the ppc host has coherent icache

[Nicholas Piggin]

dcache writeback and icache invalidate is not required when icache is
coherent, a shorter fixed-length sequence can be used which just has to
flush and re-fetch instructions that were in-flight.

Signed-off-by: Nicholas Piggin <npig...@gmail.com>
---

I haven't been able to measure a significant performance difference
with this, qemu isn't flushing large ranges frequently so the old sequence
is not that slow.

 include/qemu/cacheflush.h |  4 ++++
 util/cacheflush.c         |  9 +++++++++
 util/cacheinfo.c          | 16 ++++++++++++++--
 3 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/include/qemu/cacheflush.h b/include/qemu/cacheflush.h
index ae20bcda73..f65349ce3c 100644
--- a/include/qemu/cacheflush.h
+++ b/include/qemu/cacheflush.h
@@ -28,6 +28,10 @@ static inline void flush_idcache_range(uintptr_t rx, 
uintptr_t rw, size_t len)
 
 #else
 
+#if defined(__powerpc__)
+extern bool have_coherent_icache;
+#endif
+
 void flush_idcache_range(uintptr_t rx, uintptr_t rw, size_t len);
 
 #endif
diff --git a/util/cacheflush.c b/util/cacheflush.c
index 4b57186d89..15060f78b8 100644
--- a/util/cacheflush.c
+++ b/util/cacheflush.c
@@ -108,7 +108,16 @@ void flush_idcache_range(uintptr_t rx, uintptr_t rw, 
size_t len)
     size_t isize = qemu_icache_linesize;
 
     b = rw & ~(dsize - 1);
+
+    if (have_coherent_icache) {
+        asm volatile ("sync" : : : "memory");
+        asm volatile ("icbi 0,%0" : : "r"(b) : "memory");
+        asm volatile ("isync" : : : "memory");
+        return;
+    }
+
     e = (rw + len + dsize - 1) & ~(dsize - 1);
+
     for (p = b; p < e; p += dsize) {
         asm volatile ("dcbst 0,%0" : : "r"(p) : "memory");
     }
diff --git a/util/cacheinfo.c b/util/cacheinfo.c
index ab1644d490..b632ff47ae 100644
--- a/util/cacheinfo.c
+++ b/util/cacheinfo.c
@@ -133,18 +133,30 @@ static void arch_cache_info(int *isize, int *dsize)
     }
 }
 
-#elif defined(_ARCH_PPC) && defined(__linux__)
-# include "elf.h"
+#elif defined(__powerpc__)
 
+bool have_coherent_icache = false;
+
+# if defined(_ARCH_PPC) && defined(__linux__)
+#  include "elf.h"
 static void arch_cache_info(int *isize, int *dsize)
 {
+#  ifdef PPC_FEATURE_ICACHE_SNOOP
+    unsigned long hwcap = qemu_getauxval(AT_HWCAP);
+#  endif
+
     if (*isize == 0) {
         *isize = qemu_getauxval(AT_ICACHEBSIZE);
     }
     if (*dsize == 0) {
         *dsize = qemu_getauxval(AT_DCACHEBSIZE);
     }
+
+#  ifdef PPC_FEATURE_ICACHE_SNOOP
+    have_coherent_icache = (hwcap & PPC_FEATURE_ICACHE_SNOOP) != 0;
+#  endif
 }
+# endif
 
 #else
 static void arch_cache_info(int *isize, int *dsize) { }
-- 
2.35.1