Merge tag 'md/3.12' of git://neil.brown.name/md

Pull md update from Neil Brown:
 "Headline item is multithreading for RAID5 so that more IO/sec can be
  supported on fast (SSD) devices.  Also TILE-Gx SIMD suppor for RAID6
  calculations and an assortment of bug fixes"

* tag 'md/3.12' of git://neil.brown.name/md:
  raid5: only wakeup necessary threads
  md/raid5: flush out all pending requests before proceeding with reshape.
  md/raid5: use seqcount to protect access to shape in make_request.
  raid5: sysfs entry to control worker thread number
  raid5: offload stripe handle to workqueue
  raid5: fix stripe release order
  raid5: make release_stripe lockless
  md: avoid deadlock when dirty buffers during md_stop.
  md: Don't test all of mddev->flags at once.
  md: Fix apparent cut-and-paste error in super_90_validate
  raid6/test: replace echo -e with printf
  RAID: add tilegx SIMD implementation of raid6
  md: fix safe_mode buglet.
  md: don't call md_allow_write in get_bitmap_file.

4 files changed, 103 insertions, 1 deletions

diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index b462578..c7dab06 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -6,6 +6,7 @@ raid6_pq-y	+= algos.o recov.o tables.o int1.o int2.o int4.o \
 raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o
 raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
 raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o
+raid6_pq-$(CONFIG_TILEGX) += tilegx8.o
 
 hostprogs-y	+= mktables
 
@@ -110,6 +111,11 @@ $(obj)/neon8.c:   UNROLL := 8
 $(obj)/neon8.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
 
+targets += tilegx8.c
+$(obj)/tilegx8.c:   UNROLL := 8
+$(obj)/tilegx8.c:   $(src)/tilegx.uc $(src)/unroll.awk FORCE
+	$(call if_changed,unroll)
+
 quiet_cmd_mktable = TABLE   $@
       cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
 
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 74e6f56..f0b1aa3 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -66,6 +66,9 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_altivec4,
 	&raid6_altivec8,
 #endif
+#if defined(CONFIG_TILEGX)
+	&raid6_tilegx8,
+#endif
 	&raid6_intx1,
 	&raid6_intx2,
 	&raid6_intx4,
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index 28afa1a..29090f3 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -40,13 +40,16 @@ else ifeq ($(HAS_NEON),yes)
         OBJS   += neon.o neon1.o neon2.o neon4.o neon8.o
         CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1
 else
-        HAS_ALTIVEC := $(shell echo -e '\#include <altivec.h>\nvector int a;' |\
+        HAS_ALTIVEC := $(shell printf '\#include <altivec.h>\nvector int a;\n' |\
                          gcc -c -x c - >&/dev/null && \
                          rm ./-.o && echo yes)
         ifeq ($(HAS_ALTIVEC),yes)
                 OBJS += altivec1.o altivec2.o altivec4.o altivec8.o
         endif
 endif
+ifeq ($(ARCH),tilegx)
+OBJS += tilegx8.o
+endif
 
 .c.o:
 	$(CC) $(CFLAGS) -c -o $@ $<
@@ -109,11 +112,15 @@ int16.c: int.uc ../unroll.awk
 int32.c: int.uc ../unroll.awk
 	$(AWK) ../unroll.awk -vN=32 < int.uc > $@
 
+tilegx8.c: tilegx.uc ../unroll.awk
+	$(AWK) ../unroll.awk -vN=8 < tilegx.uc > $@
+
 tables.c: mktables
 	./mktables > tables.c
 
 clean:
 	rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test
+	rm -f tilegx*.c
 
 spotless: clean
 	rm -f *~
diff --git a/lib/raid6/tilegx.uc b/lib/raid6/tilegx.uc
new file mode 100644
index 0000000..e7c2945
--- /dev/null
+++ b/lib/raid6/tilegx.uc
@@ -0,0 +1,86 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright 2002 H. Peter Anvin - All Rights Reserved
+ *   Copyright 2012 Tilera Corporation - All Rights Reserved
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
+ *   (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * tilegx$#.c
+ *
+ * $#-way unrolled TILE-Gx SIMD for RAID-6 math.
+ *
+ * This file is postprocessed using unroll.awk.
+ *
+ */
+
+#include <linux/raid/pq.h>
+
+/* Create 8 byte copies of constant byte */
+# define NBYTES(x) (__insn_v1addi(0, x))
+# define NSIZE  8
+
+/*
+ * The SHLBYTE() operation shifts each byte left by 1, *not*
+ * rolling over into the next byte
+ */
+static inline __attribute_const__ u64 SHLBYTE(u64 v)
+{
+	/* Vector One Byte Shift Left Immediate. */
+	return __insn_v1shli(v, 1);
+}
+
+/*
+ * The MASK() operation returns 0xFF in any byte for which the high
+ * bit is 1, 0x00 for any byte for which the high bit is 0.
+ */
+static inline __attribute_const__ u64 MASK(u64 v)
+{
+	/* Vector One Byte Shift Right Signed Immediate. */
+	return __insn_v1shrsi(v, 7);
+}
+
+
+void raid6_tilegx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u64 *p, *q;
+	int d, z, z0;
+
+	u64 wd$$, wq$$, wp$$, w1$$, w2$$;
+	u64 x1d = NBYTES(0x1d);
+	u64 * z0ptr;
+
+	z0 = disks - 3;			/* Highest data disk */
+	p = (u64 *)dptr[z0+1];	/* XOR parity */
+	q = (u64 *)dptr[z0+2];	/* RS syndrome */
+
+	z0ptr = (u64 *)&dptr[z0][0];
+	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
+		wq$$ = wp$$ = *z0ptr++;
+		for ( z = z0-1 ; z >= 0 ; z-- ) {
+			wd$$ = *(u64 *)&dptr[z][d+$$*NSIZE];
+			wp$$ = wp$$ ^ wd$$;
+			w2$$ = MASK(wq$$);
+			w1$$ = SHLBYTE(wq$$);
+			w2$$ = w2$$ & x1d;
+			w1$$ = w1$$ ^ w2$$;
+			wq$$ = w1$$ ^ wd$$;
+		}
+		*p++ = wp$$;
+		*q++ = wq$$;
+	}
+}
+
+const struct raid6_calls raid6_tilegx$# = {
+	raid6_tilegx$#_gen_syndrome,
+	NULL,
+	"tilegx$#",
+	0
+};