fast_hash: avoid indirect function calls

By default the arch_fast_hash hashing function pointers are initialized
to jhash(2). If during boot-up a CPU with SSE4.2 is detected they get
updated to the CRC32 ones. This dispatching scheme incurs a function
pointer lookup and indirect call for every hashing operation.

rhashtable as a user of arch_fast_hash e.g. stores pointers to hashing
functions in its structure, too, causing two indirect branches per
hashing operation.

Using alternative_call we can get away with one of those indirect branches.

Acked-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 63 insertions, 17 deletions

diff --git a/arch/x86/include/asm/hash.h b/arch/x86/include/asm/hash.h
index e8c58f88b1d4..a881d784f044 100644
--- a/arch/x86/include/asm/hash.h
+++ b/arch/x86/include/asm/hash.h
@@ -1,7 +1,48 @@
-#ifndef _ASM_X86_HASH_H
-#define _ASM_X86_HASH_H
+#ifndef __ASM_X86_HASH_H
+#define __ASM_X86_HASH_H
 
-struct fast_hash_ops;
-extern void setup_arch_fast_hash(struct fast_hash_ops *ops);
+#include <linux/cpufeature.h>
+#include <asm/alternative.h>
 
-#endif /* _ASM_X86_HASH_H */
+u32 __intel_crc4_2_hash(const void *data, u32 len, u32 seed);
+u32 __intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed);
+
+/*
+ * non-inline versions of jhash so gcc does not need to generate
+ * duplicate code in every object file
+ */
+u32 __jhash(const void *data, u32 len, u32 seed);
+u32 __jhash2(const u32 *data, u32 len, u32 seed);
+
+/*
+ * for documentation of these functions please look into
+ * <include/asm-generic/hash.h>
+ */
+
+static inline u32 arch_fast_hash(const void *data, u32 len, u32 seed)
+{
+	u32 hash;
+
+	alternative_call(__jhash, __intel_crc4_2_hash, X86_FEATURE_XMM4_2,
+#ifdef CONFIG_X86_64
+			 "=a" (hash), "D" (data), "S" (len), "d" (seed));
+#else
+			 "=a" (hash), "a" (data), "d" (len), "c" (seed));
+#endif
+	return hash;
+}
+
+static inline u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
+{
+	u32 hash;
+
+	alternative_call(__jhash2, __intel_crc4_2_hash2, X86_FEATURE_XMM4_2,
+#ifdef CONFIG_X86_64
+			 "=a" (hash), "D" (data), "S" (len), "d" (seed));
+#else
+			 "=a" (hash), "a" (data), "d" (len), "c" (seed));
+#endif
+	return hash;
+}
+
+#endif /* __ASM_X86_HASH_H */
diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c
index ff4fa51a5b1f..e14327198835 100644
--- a/arch/x86/lib/hash.c
+++ b/arch/x86/lib/hash.c
@@ -31,13 +31,13 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include <linux/hash.h>
-#include <linux/init.h>
-
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/hash.h>
 
+#include <linux/hash.h>
+#include <linux/jhash.h>
+
 static inline u32 crc32_u32(u32 crc, u32 val)
 {
 #ifdef CONFIG_AS_CRC32
@@ -48,7 +48,7 @@ static inline u32 crc32_u32(u32 crc, u32 val)
 	return crc;
 }
 
-static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed)
+u32 __intel_crc4_2_hash(const void *data, u32 len, u32 seed)
 {
 	const u32 *p32 = (const u32 *) data;
 	u32 i, tmp = 0;
@@ -71,22 +71,27 @@ static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed)
 
 	return seed;
 }
+EXPORT_SYMBOL(__intel_crc4_2_hash);
 
-static u32 intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
+u32 __intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
 {
-	const u32 *p32 = (const u32 *) data;
 	u32 i;
 
 	for (i = 0; i < len; i++)
-		seed = crc32_u32(seed, *p32++);
+		seed = crc32_u32(seed, *data++);
 
 	return seed;
 }
+EXPORT_SYMBOL(__intel_crc4_2_hash2);
 
-void __init setup_arch_fast_hash(struct fast_hash_ops *ops)
+u32 __jhash(const void *data, u32 len, u32 seed)
 {
-	if (cpu_has_xmm4_2) {
-		ops->hash  = intel_crc4_2_hash;
-		ops->hash2 = intel_crc4_2_hash2;
-	}
+	return jhash(data, len, seed);
+}
+EXPORT_SYMBOL(__jhash);
+
+u32 __jhash2(const u32 *data, u32 len, u32 seed)
+{
+	return jhash2(data, len, seed);
 }
+EXPORT_SYMBOL(__jhash2);