From 36dacddbf0bdba86cd00f066b4d724157eeb63f1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dirk=20M=C3=BCller?= <dmueller@suse.de>
Date: Wed, 5 Jan 2022 17:38:47 +0100
Subject: [PATCH] lib/raid6: Use strict priority ranking for pq gen()
 benchmarking
Git-commit: 36dacddbf0bdba86cd00f066b4d724157eeb63f1
Patch-mainline: v5.17-rc1
References: jsc#PED-2766

On x86_64, currently 3 variants of AVX512, 3 variants of AVX2
and 3 variants of SSE2 are benchmarked on initialization, taking
between 144-153 jiffies. Testing across a hardware pool of
various generations of intel cpus I could not find a single
case where SSE2 won over AVX2 or AVX512. There are cases where
AVX2 wins over AVX512 however.

Change "prefer" into an integer priority field (similar to
how recov selection works) to have more than one ranking level
available, which is backwards compatible with existing behavior.

Give AVX2/512 variants higher priority over SSE2 in order to skip
SSE testing when AVX is available. in a AVX2/x86_64/HZ=250 case this
saves in the order of 200ms of initialization time.

(Coly Li: Rebased for Linux v5.14 based SUSE kernel)

Signed-off-by: Dirk Müller <dmueller@suse.de>
Acked-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Coly Li <colyli@suse.de>

---
 include/linux/raid/pq.h |    2 +-
 lib/raid6/algos.c       |    2 +-
 lib/raid6/avx2.c        |    8 ++++----
 lib/raid6/avx512.c      |    6 +++---
 4 files changed, 9 insertions(+), 9 deletions(-)

--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -81,7 +81,7 @@ struct raid6_calls {
 	void (*xor_syndrome)(int, int, int, size_t, void **);
 	int  (*valid)(void);	/* Returns 1 if this routine set is usable */
 	const char *name;	/* Name of this routine set */
-	int prefer;		/* Has special performance attribute */
+	int priority;		/* Relative priority ranking if non-zero */
 };
 
 /* Selected algorithm */
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -151,7 +151,7 @@ static inline const struct raid6_calls *
 	const struct raid6_calls *best;
 
 	for (bestgenperf = 0, bestxorperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
-		if (!best || (*algo)->prefer >= best->prefer) {
+		if (!best || (*algo)->priority >= best->priority) {
 			if ((*algo)->valid && !(*algo)->valid())
 				continue;
 
--- a/lib/raid6/avx2.c
+++ b/lib/raid6/avx2.c
@@ -132,7 +132,7 @@ const struct raid6_calls raid6_avx2x1 =
 	raid6_avx21_xor_syndrome,
 	raid6_have_avx2,
 	"avx2x1",
-	1			/* Has cache hints */
+	.priority = 2		/* Prefer AVX2 over priority 1 (SSE2 and others) */
 };
 
 /*
@@ -262,7 +262,7 @@ const struct raid6_calls raid6_avx2x2 =
 	raid6_avx22_xor_syndrome,
 	raid6_have_avx2,
 	"avx2x2",
-	1			/* Has cache hints */
+	.priority = 2		/* Prefer AVX2 over priority 1 (SSE2 and others) */
 };
 
 #ifdef CONFIG_X86_64
@@ -465,6 +465,6 @@ const struct raid6_calls raid6_avx2x4 =
 	raid6_avx24_xor_syndrome,
 	raid6_have_avx2,
 	"avx2x4",
-	1			/* Has cache hints */
+	.priority = 2		/* Prefer AVX2 over priority 1 (SSE2 and others) */
 };
-#endif
+#endif /* CONFIG_X86_64 */
--- a/lib/raid6/avx512.c
+++ b/lib/raid6/avx512.c
@@ -162,7 +162,7 @@ const struct raid6_calls raid6_avx512x1
 	raid6_avx5121_xor_syndrome,
 	raid6_have_avx512,
 	"avx512x1",
-	1                       /* Has cache hints */
+	.priority = 2		/* Prefer AVX512 over priority 1 (SSE2 and others) */
 };
 
 /*
@@ -319,7 +319,7 @@ const struct raid6_calls raid6_avx512x2
 	raid6_avx5122_xor_syndrome,
 	raid6_have_avx512,
 	"avx512x2",
-	1                       /* Has cache hints */
+	.priority = 2		/* Prefer AVX512 over priority 1 (SSE2 and others) */
 };
 
 #ifdef CONFIG_X86_64
@@ -557,7 +557,7 @@ const struct raid6_calls raid6_avx512x4
 	raid6_avx5124_xor_syndrome,
 	raid6_have_avx512,
 	"avx512x4",
-	1                       /* Has cache hints */
+	.priority = 2		/* Prefer AVX512 over priority 1 (SSE2 and others) */
 };
 #endif