Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md into for-linus

Pull the pending 4.21 changes for md from Shaohua.

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  md: fix raid10 hang issue caused by barrier
  raid10: refactor common wait code from regular read/write request
  md: remvoe redundant condition check
  lib/raid6: add option to skip algo benchmarking
  lib/raid6: sort algos in rough performance order
  lib/raid6: check for assembler SSSE3 support
  lib/raid6: avoid __attribute_const__ redefinition
  lib/raid6: add missing include for raid6test
  md: remove set but not used variable 'bi_rdev'

3 files changed, 54 insertions, 38 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 79bc2eef9c14..a9e56539bd11 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -10,6 +10,14 @@ menu "Library routines"
 config RAID6_PQ
 	tristate
 
+config RAID6_PQ_BENCHMARK
+	bool "Automatically choose fastest RAID6 PQ functions"
+	depends on RAID6_PQ
+	default y
+	help
+	  Benchmark all available RAID6 PQ functions on init and choose the
+	  fastest one.
+
 config BITREVERSE
 	tristate
 
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 5065b1e7e327..7e4f7a8ffa8e 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -34,64 +34,64 @@ struct raid6_calls raid6_call;
 EXPORT_SYMBOL_GPL(raid6_call);
 
 const struct raid6_calls * const raid6_algos[] = {
-#if defined(__ia64__)
-	&raid6_intx16,
-	&raid6_intx32,
-#endif
 #if defined(__i386__) && !defined(__arch_um__)
-	&raid6_mmxx1,
-	&raid6_mmxx2,
-	&raid6_sse1x1,
-	&raid6_sse1x2,
-	&raid6_sse2x1,
-	&raid6_sse2x2,
-#ifdef CONFIG_AS_AVX2
-	&raid6_avx2x1,
-	&raid6_avx2x2,
-#endif
 #ifdef CONFIG_AS_AVX512
-	&raid6_avx512x1,
 	&raid6_avx512x2,
+	&raid6_avx512x1,
 #endif
-#endif
-#if defined(__x86_64__) && !defined(__arch_um__)
-	&raid6_sse2x1,
-	&raid6_sse2x2,
-	&raid6_sse2x4,
 #ifdef CONFIG_AS_AVX2
-	&raid6_avx2x1,
 	&raid6_avx2x2,
-	&raid6_avx2x4,
+	&raid6_avx2x1,
+#endif
+	&raid6_sse2x2,
+	&raid6_sse2x1,
+	&raid6_sse1x2,
+	&raid6_sse1x1,
+	&raid6_mmxx2,
+	&raid6_mmxx1,
 #endif
+#if defined(__x86_64__) && !defined(__arch_um__)
 #ifdef CONFIG_AS_AVX512
-	&raid6_avx512x1,
-	&raid6_avx512x2,
 	&raid6_avx512x4,
+	&raid6_avx512x2,
+	&raid6_avx512x1,
 #endif
+#ifdef CONFIG_AS_AVX2
+	&raid6_avx2x4,
+	&raid6_avx2x2,
+	&raid6_avx2x1,
+#endif
+	&raid6_sse2x4,
+	&raid6_sse2x2,
+	&raid6_sse2x1,
 #endif
 #ifdef CONFIG_ALTIVEC
-	&raid6_altivec1,
-	&raid6_altivec2,
-	&raid6_altivec4,
-	&raid6_altivec8,
-	&raid6_vpermxor1,
-	&raid6_vpermxor2,
-	&raid6_vpermxor4,
 	&raid6_vpermxor8,
+	&raid6_vpermxor4,
+	&raid6_vpermxor2,
+	&raid6_vpermxor1,
+	&raid6_altivec8,
+	&raid6_altivec4,
+	&raid6_altivec2,
+	&raid6_altivec1,
 #endif
 #if defined(CONFIG_S390)
 	&raid6_s390vx8,
 #endif
-	&raid6_intx1,
-	&raid6_intx2,
-	&raid6_intx4,
-	&raid6_intx8,
 #ifdef CONFIG_KERNEL_MODE_NEON
-	&raid6_neonx1,
-	&raid6_neonx2,
-	&raid6_neonx4,
 	&raid6_neonx8,
+	&raid6_neonx4,
+	&raid6_neonx2,
+	&raid6_neonx1,
 #endif
+#if defined(__ia64__)
+	&raid6_intx32,
+	&raid6_intx16,
+#endif
+	&raid6_intx8,
+	&raid6_intx4,
+	&raid6_intx2,
+	&raid6_intx1,
 	NULL
 };
 
@@ -163,6 +163,11 @@ static inline const struct raid6_calls *raid6_choose_gen(
 			if ((*algo)->valid && !(*algo)->valid())
 				continue;
 
+			if (!IS_ENABLED(CONFIG_RAID6_PQ_BENCHMARK)) {
+				best = *algo;
+				break;
+			}
+
 			perf = 0;
 
 			preempt_disable();
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index 79777645cac9..3ab8720aa2f8 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -34,6 +34,9 @@ endif
 
 ifeq ($(IS_X86),yes)
         OBJS   += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o avx512.o recov_avx512.o
+        CFLAGS += $(shell echo "pshufb %xmm0, %xmm0" |		\
+                    gcc -c -x assembler - >&/dev/null &&	\
+                    rm ./-.o && echo -DCONFIG_AS_SSSE3=1)
         CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" |	\
                     gcc -c -x assembler - >&/dev/null &&	\
                     rm ./-.o && echo -DCONFIG_AS_AVX2=1)