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, 34 insertions, 36 deletions

diff --git a/include/asm-generic/hash.h b/include/asm-generic/hash.h
index b6312843dbd9..3c82760ff2a4 100644
--- a/include/asm-generic/hash.h
+++ b/include/asm-generic/hash.h
@@ -1,9 +1,41 @@
 #ifndef __ASM_GENERIC_HASH_H
 #define __ASM_GENERIC_HASH_H
 
-struct fast_hash_ops;
-static inline void setup_arch_fast_hash(struct fast_hash_ops *ops)
+#include <linux/jhash.h>
+
+/**
+ *	arch_fast_hash - Caclulates a hash over a given buffer that can have
+ *			 arbitrary size. This function will eventually use an
+ *			 architecture-optimized hashing implementation if
+ *			 available, and trades off distribution for speed.
+ *
+ *	@data: buffer to hash
+ *	@len: length of buffer in bytes
+ *	@seed: start seed
+ *
+ *	Returns 32bit hash.
+ */
+static inline u32 arch_fast_hash(const void *data, u32 len, u32 seed)
+{
+	return jhash(data, len, seed);
+}
+
+/**
+ *	arch_fast_hash2 - Caclulates a hash over a given buffer that has a
+ *			  size that is of a multiple of 32bit words. This
+ *			  function will eventually use an architecture-
+ *			  optimized hashing implementation if available,
+ *			  and trades off distribution for speed.
+ *
+ *	@data: buffer to hash (must be 32bit padded)
+ *	@len: number of 32bit words
+ *	@seed: start seed
+ *
+ *	Returns 32bit hash.
+ */
+static inline u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed)
 {
+	return jhash2(data, len, seed);
 }
 
 #endif /* __ASM_GENERIC_HASH_H */
diff --git a/include/linux/hash.h b/include/linux/hash.h
index d0494c399392..6e8fb028848c 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -84,38 +84,4 @@ static inline u32 hash32_ptr(const void *ptr)
 	return (u32)val;
 }
 
-struct fast_hash_ops {
-	u32 (*hash)(const void *data, u32 len, u32 seed);
-	u32 (*hash2)(const u32 *data, u32 len, u32 seed);
-};
-
-/**
- *	arch_fast_hash - Caclulates a hash over a given buffer that can have
- *			 arbitrary size. This function will eventually use an
- *			 architecture-optimized hashing implementation if
- *			 available, and trades off distribution for speed.
- *
- *	@data: buffer to hash
- *	@len: length of buffer in bytes
- *	@seed: start seed
- *
- *	Returns 32bit hash.
- */
-extern u32 arch_fast_hash(const void *data, u32 len, u32 seed);
-
-/**
- *	arch_fast_hash2 - Caclulates a hash over a given buffer that has a
- *			  size that is of a multiple of 32bit words. This
- *			  function will eventually use an architecture-
- *			  optimized hashing implementation if available,
- *			  and trades off distribution for speed.
- *
- *	@data: buffer to hash (must be 32bit padded)
- *	@len: number of 32bit words
- *	@seed: start seed
- *
- *	Returns 32bit hash.
- */
-extern u32 arch_fast_hash2(const u32 *data, u32 len, u32 seed);
-
 #endif /* _LINUX_HASH_H */