Implementation of AVX2 optimized Fletcher-4

New functionality:
- Preserves existing scalar implementation.
- Adds AVX2 optimized Fletcher-4 computation.
- Fastest routines selected on module load (benchmark).
- Test case for Fletcher-4 added to ztest.

New zcommon module parameters:
-  zfs_fletcher_4_impl (str): selects the implementation to use.
    "fastest" - use the fastest version available
    "cycle"   - cycle trough all available impl for ztest
    "scalar"  - use the original version
    "avx2"    - new AVX2 implementation if available

Performance comparison (Intel i7 CPU, 1MB data buffers):
- Scalar:  4216 MB/s
- AVX2:   14499 MB/s

See contents of `/sys/module/zcommon/parameters/zfs_fletcher_4_impl`
to get list of supported values. If an implementation is not supported
on the system, it will not be shown. Currently selected option is
enclosed in `[]`.

Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Signed-off-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #4330

include/sys/Makefile.am

@@ -50,6 +50,7 @@ COMMON_H = \
 	$(top_srcdir)/include/sys/space_reftree.h \
 	$(top_srcdir)/include/sys/spa.h \
 	$(top_srcdir)/include/sys/spa_impl.h \
+	$(top_srcdir)/include/sys/spa_checksum.h \
 	$(top_srcdir)/include/sys/trace.h \
 	$(top_srcdir)/include/sys/trace_acl.h \
 	$(top_srcdir)/include/sys/trace_arc.h \

include/sys/spa.h

@@ -35,6 +35,7 @@
 #include <sys/sysmacros.h>
 #include <sys/types.h>
 #include <sys/fs/zfs.h>
+#include <sys/spa_checksum.h>
 
 #ifdef	__cplusplus
 extern "C" {
@@ -142,12 +143,6 @@ typedef struct dva {
 	uint64_t	dva_word[2];
 } dva_t;
 
-/*
- * Each block has a 256-bit checksum -- strong enough for cryptographic hashes.
- */
-typedef struct zio_cksum {
-	uint64_t	zc_word[4];
-} zio_cksum_t;
 
 /*
  * Each block is described by its DVAs, time of birth, checksum, etc.
@@ -440,35 +435,9 @@ _NOTE(CONSTCOND) } while (0)
 	DVA_EQUAL(&(bp1)->blk_dva[1], &(bp2)->blk_dva[1]) &&	\
 	DVA_EQUAL(&(bp1)->blk_dva[2], &(bp2)->blk_dva[2]))
 
-#define	ZIO_CHECKSUM_EQUAL(zc1, zc2) \
-	(0 == (((zc1).zc_word[0] - (zc2).zc_word[0]) | \
-	((zc1).zc_word[1] - (zc2).zc_word[1]) | \
-	((zc1).zc_word[2] - (zc2).zc_word[2]) | \
-	((zc1).zc_word[3] - (zc2).zc_word[3])))
-
-#define	ZIO_CHECKSUM_IS_ZERO(zc) \
-	(0 == ((zc)->zc_word[0] | (zc)->zc_word[1] | \
-	(zc)->zc_word[2] | (zc)->zc_word[3]))
-
-#define	ZIO_CHECKSUM_BSWAP(zcp)					\
-{								\
-	(zcp)->zc_word[0] = BSWAP_64((zcp)->zc_word[0]);	\
-	(zcp)->zc_word[1] = BSWAP_64((zcp)->zc_word[1]);	\
-	(zcp)->zc_word[2] = BSWAP_64((zcp)->zc_word[2]);	\
-	(zcp)->zc_word[3] = BSWAP_64((zcp)->zc_word[3]);	\
-}
-
 
 #define	DVA_IS_VALID(dva)	(DVA_GET_ASIZE(dva) != 0)
 
-#define	ZIO_SET_CHECKSUM(zcp, w0, w1, w2, w3)	\
-{						\
-	(zcp)->zc_word[0] = w0;			\
-	(zcp)->zc_word[1] = w1;			\
-	(zcp)->zc_word[2] = w2;			\
-	(zcp)->zc_word[3] = w3;			\
-}
-
 #define	BP_IDENTITY(bp)		(ASSERT(!BP_IS_EMBEDDED(bp)), &(bp)->blk_dva[0])
 #define	BP_IS_GANG(bp)		\
 	(BP_IS_EMBEDDED(bp) ? B_FALSE : DVA_GET_GANG(BP_IDENTITY(bp)))

include/sys/spa_checksum.h

@@ -0,0 +1,72 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+ * or http://www.opensolaris.org/os/licensing.
+ * See the License for the specific language governing permissions
+ * and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+/*
+ * Copyright 2009 Sun Microsystems, Inc.  All rights reserved.
+ * Use is subject to license terms.
+ */
+
+#ifndef	_SPA_CHECKSUM_H
+#define	_SPA_CHECKSUM_H
+
+#include <sys/types.h>
+
+#ifdef	__cplusplus
+extern "C" {
+#endif
+
+/*
+ * Each block has a 256-bit checksum -- strong enough for cryptographic hashes.
+ */
+typedef struct zio_cksum {
+	uint64_t	zc_word[4];
+} zio_cksum_t;
+
+#define	ZIO_SET_CHECKSUM(zcp, w0, w1, w2, w3)	\
+{						\
+	(zcp)->zc_word[0] = w0;			\
+	(zcp)->zc_word[1] = w1;			\
+	(zcp)->zc_word[2] = w2;			\
+	(zcp)->zc_word[3] = w3;			\
+}
+
+#define	ZIO_CHECKSUM_EQUAL(zc1, zc2) \
+	(0 == (((zc1).zc_word[0] - (zc2).zc_word[0]) | \
+	((zc1).zc_word[1] - (zc2).zc_word[1]) | \
+	((zc1).zc_word[2] - (zc2).zc_word[2]) | \
+	((zc1).zc_word[3] - (zc2).zc_word[3])))
+
+#define	ZIO_CHECKSUM_IS_ZERO(zc) \
+	(0 == ((zc)->zc_word[0] | (zc)->zc_word[1] | \
+	(zc)->zc_word[2] | (zc)->zc_word[3]))
+
+#define	ZIO_CHECKSUM_BSWAP(zcp)					\
+{								\
+	(zcp)->zc_word[0] = BSWAP_64((zcp)->zc_word[0]);	\
+	(zcp)->zc_word[1] = BSWAP_64((zcp)->zc_word[1]);	\
+	(zcp)->zc_word[2] = BSWAP_64((zcp)->zc_word[2]);	\
+	(zcp)->zc_word[3] = BSWAP_64((zcp)->zc_word[3]);	\
+}
+
+#ifdef	__cplusplus
+}
+#endif
+
+#endif

include/zfs_fletcher.h

@@ -27,7 +27,7 @@
 #define	_ZFS_FLETCHER_H
 
 #include <sys/types.h>
-#include <sys/spa.h>
+#include <sys/spa_checksum.h>
 
 #ifdef	__cplusplus
 extern "C" {
@@ -45,6 +45,25 @@ void fletcher_4_incremental_native(const void *, uint64_t,
     zio_cksum_t *);
 void fletcher_4_incremental_byteswap(const void *, uint64_t,
     zio_cksum_t *);
+int fletcher_4_impl_set(const char *selector);
+void fletcher_4_init(void);
+void fletcher_4_fini(void);
+
+/*
+ * fletcher checksum struct
+ */
+typedef struct fletcher_4_func {
+	void (*init)(zio_cksum_t *);
+	void (*fini)(zio_cksum_t *);
+	void (*compute)(const void *, uint64_t, zio_cksum_t *);
+	void (*compute_byteswap)(const void *, uint64_t, zio_cksum_t *);
+	boolean_t (*valid)(void);
+	const char *name;
+} fletcher_4_ops_t;
+
+#if defined(HAVE_AVX) && defined(HAVE_AVX2)
+extern const fletcher_4_ops_t fletcher_4_avx2_ops;
+#endif
 
 #ifdef	__cplusplus
 }