powerpc/perf: Add basic assembly code to read BHRB entries on POWER8

This patch adds the basic assembly code to read BHRB buffer. BHRB entries
are valid only after a PMU interrupt has happened (when MMCR0[PMAO]=1)
and BHRB has been freezed. BHRB read should not be attempted when it is
still enabled (MMCR0[PMAE]=1) and getting updated, as this can produce
non-deterministic results.
Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/perf/Makefile

@@ -2,7 +2,7 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 obj-$(CONFIG_PERF_EVENTS)	+= callchain.o
 
-obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o
+obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o bhrb.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
 				   power5+-pmu.o power6-pmu.o power7-pmu.o \
 				   power8-pmu.o

arch/powerpc/perf/bhrb.S

+/*
+ * Basic assembly code to read BHRB entries
+ *
+ * Copyright 2013 Anshuman Khandual, IBM Corporation.
+ *
+ * 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; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+
+	.text
+
+.balign 8
+
+/* r3 = n  (where n = [0-31])
+ * The maximum number of BHRB entries supported with PPC_MFBHRBE instruction
+ * is 1024. We have limited number of table entries here as POWER8 implements
+ * 32 BHRB entries.
+ */
+
+/* .global read_bhrb */
+_GLOBAL(read_bhrb)
+	cmpldi	r3,31
+	bgt	1f
+	ld	r4,bhrb_table@got(r2)
+	sldi	r3,r3,3
+	add	r3,r4,r3
+	mtctr	r3
+	bctr
+1:	li	r3,0
+	blr
+
+#define MFBHRB_TABLE1(n) PPC_MFBHRBE(R3,n); blr
+#define MFBHRB_TABLE2(n) MFBHRB_TABLE1(n); MFBHRB_TABLE1(n+1)
+#define MFBHRB_TABLE4(n) MFBHRB_TABLE2(n); MFBHRB_TABLE2(n+2)
+#define MFBHRB_TABLE8(n) MFBHRB_TABLE4(n); MFBHRB_TABLE4(n+4)
+#define MFBHRB_TABLE16(n) MFBHRB_TABLE8(n); MFBHRB_TABLE8(n+8)
+#define MFBHRB_TABLE32(n) MFBHRB_TABLE16(n); MFBHRB_TABLE16(n+16)
+
+bhrb_table:
+	MFBHRB_TABLE32(0)