[PATCH] Check -non_temporal_store in GLIBC_IFUNC

["H.J. Lu" <hongjiu dot lu at intel dot com>]

The x86 non-temporal threshold is an approximate value.  This patch
checks -non_temporal_store in GLIBC_IFUNC to disable non-temporal store.

	* sysdeps/x86/cacheinfo.c (init_cacheinfo): Set
	__x86_shared_non_temporal_threshold only if it is not set.
	* sysdeps/x86/cpu-features.c (__x86_shared_non_temporal_threshold):
	New.
	(init_cpu_features): Check -non_temporal_store in GLIBC_IFUNC
	to disable non-temporal store.
---
 sysdeps/x86/cacheinfo.c    | 13 +++++++++----
 sysdeps/x86/cpu-features.c | 14 ++++++++++++++
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/sysdeps/x86/cacheinfo.c b/sysdeps/x86/cacheinfo.c
index cf4f64b..2291ad4 100644
--- a/sysdeps/x86/cacheinfo.c
+++ b/sysdeps/x86/cacheinfo.c
@@ -762,8 +762,13 @@ intel_bug_no_cache_info:
       __x86_shared_cache_size = shared;
     }
 
-  /* The large memcpy micro benchmark in glibc shows that 6 times of
-     shared cache size is the approximate value above which non-temporal
-     store becomes faster.  */
-  __x86_shared_non_temporal_threshold = __x86_shared_cache_size * 6;
+  /* Set non-temporal threshold to an approximate value if it hasn't
+     been set.  */
+  if (__x86_shared_non_temporal_threshold == 0)
+    {
+      /* The large memcpy microbenchmark in glibc shows that 6 times
+         of shared cache size is the approximate value above which
+	 non-temporal store becomes faster.  */
+      __x86_shared_non_temporal_threshold = __x86_shared_cache_size * 6;
+    }
 }
diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c
index 525b262..e53a302 100644
--- a/sysdeps/x86/cpu-features.c
+++ b/sysdeps/x86/cpu-features.c
@@ -220,6 +220,8 @@ equal (const char *a, const char *b, size_t len)
       break;								\
     }
 
+extern long int __x86_shared_non_temporal_threshold attribute_hidden;
+
 static inline void
 init_cpu_features (struct cpu_features *cpu_features, char **env)
 {
@@ -540,6 +542,18 @@ no_cpuid:
 		    CHECK_GLIBC_IFUNC_ARCH_BOTH (Fast_Rep_String, disable);
 		    break;
 		  case 18:
+		    if (disable)
+		      {
+			if (equal (n, "non_temporal_store",
+				   sizeof ("non_temporal_store") - 1))
+			  {
+			    /* Disable non-temporal store with
+			       "-non_temporal_store".  */
+			    __x86_shared_non_temporal_threshold
+			      = (long int) -1;
+			    break;
+			  }
+		      }
 		    CHECK_GLIBC_IFUNC_ARCH_BOTH (Fast_Copy_Backward,
 						 disable);
 		    break;
-- 
2.7.4