Merge tag 'powerpc-4.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights:
   - Support for Power ISA 3.0 (Power9) Radix Tree MMU from Aneesh Kumar K.V
   - Live patching support for ppc64le (also merged via livepatching.git)

  Various cleanups & minor fixes from:
   - Aaro Koskinen, Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V,
     Chris Smart, Daniel Axtens, Frederic Barrat, Gavin Shan, Ian Munsie,
     Lennart Sorensen, Madhavan Srinivasan, Mahesh Salgaonkar, Markus Elfring,
     Michael Ellerman, Oliver O'Halloran, Paul Gortmaker, Paul Mackerras,
     Rashmica Gupta, Russell Currey, Suraj Jitindar Singh, Thiago Jung
     Bauermann, Valentin Rothberg, Vipin K Parashar.

  General:
   - Update LMB associativity index during DLPAR add/remove from Nathan
     Fontenot
   - Fix branching to OOL handlers in relocatable kernel from Hari Bathini
   - Add support for userspace Power9 copy/paste from Chris Smart
   - Always use STRICT_MM_TYPECHECKS from Michael Ellerman
   - Add mask of possible MMU features from Michael Ellerman

  PCI:
   - Enable pass through of NVLink to guests from Alexey Kardashevskiy
   - Cleanups in preparation for powernv PCI hotplug from Gavin Shan
   - Don't report error in eeh_pe_reset_and_recover() from Gavin Shan
   - Restore initial state in eeh_pe_reset_and_recover() from Gavin Shan
   - Revert "powerpc/eeh: Fix crash in eeh_add_device_early() on Cell"
     from Guilherme G Piccoli
   - Remove the dependency on EEH struct in DDW mechanism from Guilherme
     G Piccoli

  selftests:
   - Test cp_abort during context switch from Chris Smart
   - Add several tests for transactional memory support from Rashmica
     Gupta

  perf:
   - Add support for sampling interrupt register state from Anju T
   - Add support for unwinding perf-stackdump from Chandan Kumar

  cxl:
   - Configure the PSL for two CAPI ports on POWER8NVL from Philippe
     Bergheaud
   - Allow initialization on timebase sync failures from Frederic Barrat
   - Increase timeout for detection of AFU mmio hang from Frederic
     Barrat
   - Handle num_of_processes larger than can fit in the SPA from Ian
     Munsie
   - Ensure PSL interrupt is configured for contexts with no AFU IRQs
     from Ian Munsie
   - Add kernel API to allow a context to operate with relocate disabled
     from Ian Munsie
   - Check periodically the coherent platform function's state from
     Christophe Lombard

  Freescale:
   - Updates from Scott: "Contains 86xx fixes, minor device tree fixes,
     an erratum workaround, and a kconfig dependency fix."

* tag 'powerpc-4.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (192 commits)
  powerpc/86xx: Fix PCI interrupt map definition
  powerpc/86xx: Move pci1 definition to the include file
  powerpc/fsl: Fix build of the dtb embedded kernel images
  powerpc/fsl: Fix rcpm compatible string
  powerpc/fsl: Remove FSL_SOC dependency from FSL_LBC
  powerpc/fsl-pci: Add a workaround for PCI 5 errata
  powerpc/fsl: Fix SPI compatible on t208xrdb and t1040rdb
  powerpc/powernv/npu: Add PE to PHB's list
  powerpc/powernv: Fix insufficient memory allocation
  powerpc/iommu: Remove the dependency on EEH struct in DDW mechanism
  Revert "powerpc/eeh: Fix crash in eeh_add_device_early() on Cell"
  powerpc/eeh: Drop unnecessary label in eeh_pe_change_owner()
  powerpc/eeh: Ignore handlers in eeh_pe_reset_and_recover()
  powerpc/eeh: Restore initial state in eeh_pe_reset_and_recover()
  powerpc/eeh: Don't report error in eeh_pe_reset_and_recover()
  Revert "powerpc/powernv: Exclude root bus in pnv_pci_reset_secondary_bus()"
  powerpc/powernv/npu: Enable NVLink pass through
  powerpc/powernv/npu: Rework TCE Kill handling
  powerpc/powernv/npu: Add set/unset window helpers
  powerpc/powernv/ioda2: Export debug helper pe_level_printk()
  ...

22 files changed, 665 insertions, 34 deletions

diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
new file mode 100644
index 000000000000..75de0e92e71e
--- /dev/null
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -0,0 +1,69 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+#define PERF_REGS_MASK  ((1ULL << PERF_REG_POWERPC_MAX) - 1)
+#define PERF_REGS_MAX   PERF_REG_POWERPC_MAX
+#ifdef __powerpc64__
+	#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_64
+#else
+	#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
+#endif
+
+#define PERF_REG_IP     PERF_REG_POWERPC_NIP
+#define PERF_REG_SP     PERF_REG_POWERPC_R1
+
+static const char *reg_names[] = {
+	[PERF_REG_POWERPC_R0] = "r0",
+	[PERF_REG_POWERPC_R1] = "r1",
+	[PERF_REG_POWERPC_R2] = "r2",
+	[PERF_REG_POWERPC_R3] = "r3",
+	[PERF_REG_POWERPC_R4] = "r4",
+	[PERF_REG_POWERPC_R5] = "r5",
+	[PERF_REG_POWERPC_R6] = "r6",
+	[PERF_REG_POWERPC_R7] = "r7",
+	[PERF_REG_POWERPC_R8] = "r8",
+	[PERF_REG_POWERPC_R9] = "r9",
+	[PERF_REG_POWERPC_R10] = "r10",
+	[PERF_REG_POWERPC_R11] = "r11",
+	[PERF_REG_POWERPC_R12] = "r12",
+	[PERF_REG_POWERPC_R13] = "r13",
+	[PERF_REG_POWERPC_R14] = "r14",
+	[PERF_REG_POWERPC_R15] = "r15",
+	[PERF_REG_POWERPC_R16] = "r16",
+	[PERF_REG_POWERPC_R17] = "r17",
+	[PERF_REG_POWERPC_R18] = "r18",
+	[PERF_REG_POWERPC_R19] = "r19",
+	[PERF_REG_POWERPC_R20] = "r20",
+	[PERF_REG_POWERPC_R21] = "r21",
+	[PERF_REG_POWERPC_R22] = "r22",
+	[PERF_REG_POWERPC_R23] = "r23",
+	[PERF_REG_POWERPC_R24] = "r24",
+	[PERF_REG_POWERPC_R25] = "r25",
+	[PERF_REG_POWERPC_R26] = "r26",
+	[PERF_REG_POWERPC_R27] = "r27",
+	[PERF_REG_POWERPC_R28] = "r28",
+	[PERF_REG_POWERPC_R29] = "r29",
+	[PERF_REG_POWERPC_R30] = "r30",
+	[PERF_REG_POWERPC_R31] = "r31",
+	[PERF_REG_POWERPC_NIP] = "nip",
+	[PERF_REG_POWERPC_MSR] = "msr",
+	[PERF_REG_POWERPC_ORIG_R3] = "orig_r3",
+	[PERF_REG_POWERPC_CTR] = "ctr",
+	[PERF_REG_POWERPC_LINK] = "link",
+	[PERF_REG_POWERPC_XER] = "xer",
+	[PERF_REG_POWERPC_CCR] = "ccr",
+	[PERF_REG_POWERPC_SOFTE] = "softe",
+	[PERF_REG_POWERPC_TRAP] = "trap",
+	[PERF_REG_POWERPC_DAR] = "dar",
+	[PERF_REG_POWERPC_DSISR] = "dsisr"
+};
+
+static inline const char *perf_reg_name(int id)
+{
+	return reg_names[id];
+}
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index c8fe2074d217..90ad64b231cd 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,6 +1,8 @@
 libperf-y += header.o
 libperf-y += sym-handling.o
 libperf-y += kvm-stat.o
+libperf-y += perf_regs.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
+libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
new file mode 100644
index 000000000000..a3c3e1ce6807
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -0,0 +1,49 @@
+#include "../../perf.h"
+#include "../../util/perf_regs.h"
+
+const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG(r0, PERF_REG_POWERPC_R0),
+	SMPL_REG(r1, PERF_REG_POWERPC_R1),
+	SMPL_REG(r2, PERF_REG_POWERPC_R2),
+	SMPL_REG(r3, PERF_REG_POWERPC_R3),
+	SMPL_REG(r4, PERF_REG_POWERPC_R4),
+	SMPL_REG(r5, PERF_REG_POWERPC_R5),
+	SMPL_REG(r6, PERF_REG_POWERPC_R6),
+	SMPL_REG(r7, PERF_REG_POWERPC_R7),
+	SMPL_REG(r8, PERF_REG_POWERPC_R8),
+	SMPL_REG(r9, PERF_REG_POWERPC_R9),
+	SMPL_REG(r10, PERF_REG_POWERPC_R10),
+	SMPL_REG(r11, PERF_REG_POWERPC_R11),
+	SMPL_REG(r12, PERF_REG_POWERPC_R12),
+	SMPL_REG(r13, PERF_REG_POWERPC_R13),
+	SMPL_REG(r14, PERF_REG_POWERPC_R14),
+	SMPL_REG(r15, PERF_REG_POWERPC_R15),
+	SMPL_REG(r16, PERF_REG_POWERPC_R16),
+	SMPL_REG(r17, PERF_REG_POWERPC_R17),
+	SMPL_REG(r18, PERF_REG_POWERPC_R18),
+	SMPL_REG(r19, PERF_REG_POWERPC_R19),
+	SMPL_REG(r20, PERF_REG_POWERPC_R20),
+	SMPL_REG(r21, PERF_REG_POWERPC_R21),
+	SMPL_REG(r22, PERF_REG_POWERPC_R22),
+	SMPL_REG(r23, PERF_REG_POWERPC_R23),
+	SMPL_REG(r24, PERF_REG_POWERPC_R24),
+	SMPL_REG(r25, PERF_REG_POWERPC_R25),
+	SMPL_REG(r26, PERF_REG_POWERPC_R26),
+	SMPL_REG(r27, PERF_REG_POWERPC_R27),
+	SMPL_REG(r28, PERF_REG_POWERPC_R28),
+	SMPL_REG(r29, PERF_REG_POWERPC_R29),
+	SMPL_REG(r30, PERF_REG_POWERPC_R30),
+	SMPL_REG(r31, PERF_REG_POWERPC_R31),
+	SMPL_REG(nip, PERF_REG_POWERPC_NIP),
+	SMPL_REG(msr, PERF_REG_POWERPC_MSR),
+	SMPL_REG(orig_r3, PERF_REG_POWERPC_ORIG_R3),
+	SMPL_REG(ctr, PERF_REG_POWERPC_CTR),
+	SMPL_REG(link, PERF_REG_POWERPC_LINK),
+	SMPL_REG(xer, PERF_REG_POWERPC_XER),
+	SMPL_REG(ccr, PERF_REG_POWERPC_CCR),
+	SMPL_REG(softe, PERF_REG_POWERPC_SOFTE),
+	SMPL_REG(trap, PERF_REG_POWERPC_TRAP),
+	SMPL_REG(dar, PERF_REG_POWERPC_DAR),
+	SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR),
+	SMPL_REG_END
+};
diff --git a/tools/perf/arch/powerpc/util/unwind-libunwind.c b/tools/perf/arch/powerpc/util/unwind-libunwind.c
new file mode 100644
index 000000000000..9e15f92ae49f
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/unwind-libunwind.c
@@ -0,0 +1,96 @@
+/*
+ * Copyright 2016 Chandan Kumar, 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 <errno.h>
+#include <libunwind.h>
+#include <asm/perf_regs.h>
+#include "../../util/unwind.h"
+#include "../../util/debug.h"
+
+int libunwind__arch_reg_id(int regnum)
+{
+	switch (regnum) {
+	case UNW_PPC64_R0:
+		return PERF_REG_POWERPC_R0;
+	case UNW_PPC64_R1:
+		return PERF_REG_POWERPC_R1;
+	case UNW_PPC64_R2:
+		return PERF_REG_POWERPC_R2;
+	case UNW_PPC64_R3:
+		return PERF_REG_POWERPC_R3;
+	case UNW_PPC64_R4:
+		return PERF_REG_POWERPC_R4;
+	case UNW_PPC64_R5:
+		return PERF_REG_POWERPC_R5;
+	case UNW_PPC64_R6:
+		return PERF_REG_POWERPC_R6;
+	case UNW_PPC64_R7:
+		return PERF_REG_POWERPC_R7;
+	case UNW_PPC64_R8:
+		return PERF_REG_POWERPC_R8;
+	case UNW_PPC64_R9:
+		return PERF_REG_POWERPC_R9;
+	case UNW_PPC64_R10:
+		return PERF_REG_POWERPC_R10;
+	case UNW_PPC64_R11:
+		return PERF_REG_POWERPC_R11;
+	case UNW_PPC64_R12:
+		return PERF_REG_POWERPC_R12;
+	case UNW_PPC64_R13:
+		return PERF_REG_POWERPC_R13;
+	case UNW_PPC64_R14:
+		return PERF_REG_POWERPC_R14;
+	case UNW_PPC64_R15:
+		return PERF_REG_POWERPC_R15;
+	case UNW_PPC64_R16:
+		return PERF_REG_POWERPC_R16;
+	case UNW_PPC64_R17:
+		return PERF_REG_POWERPC_R17;
+	case UNW_PPC64_R18:
+		return PERF_REG_POWERPC_R18;
+	case UNW_PPC64_R19:
+		return PERF_REG_POWERPC_R19;
+	case UNW_PPC64_R20:
+		return PERF_REG_POWERPC_R20;
+	case UNW_PPC64_R21:
+		return PERF_REG_POWERPC_R21;
+	case UNW_PPC64_R22:
+		return PERF_REG_POWERPC_R22;
+	case UNW_PPC64_R23:
+		return PERF_REG_POWERPC_R23;
+	case UNW_PPC64_R24:
+		return PERF_REG_POWERPC_R24;
+	case UNW_PPC64_R25:
+		return PERF_REG_POWERPC_R25;
+	case UNW_PPC64_R26:
+		return PERF_REG_POWERPC_R26;
+	case UNW_PPC64_R27:
+		return PERF_REG_POWERPC_R27;
+	case UNW_PPC64_R28:
+		return PERF_REG_POWERPC_R28;
+	case UNW_PPC64_R29:
+		return PERF_REG_POWERPC_R29;
+	case UNW_PPC64_R30:
+		return PERF_REG_POWERPC_R30;
+	case UNW_PPC64_R31:
+		return PERF_REG_POWERPC_R31;
+	case UNW_PPC64_LR:
+		return PERF_REG_POWERPC_LINK;
+	case UNW_PPC64_CTR:
+		return PERF_REG_POWERPC_CTR;
+	case UNW_PPC64_XER:
+		return PERF_REG_POWERPC_XER;
+	case UNW_PPC64_NIP:
+		return PERF_REG_POWERPC_NIP;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+	return -EINVAL;
+}
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 1e46277286c2..5ad0255f8756 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -23,6 +23,12 @@ $(call detected_var,ARCH)
 
 NO_PERF_REGS := 1
 
+# Additional ARCH settings for ppc
+ifeq ($(ARCH),powerpc)
+  NO_PERF_REGS := 0
+  LIBUNWIND_LIBS := -lunwind -lunwind-ppc64
+endif
+
 # Additional ARCH settings for x86
 ifeq ($(ARCH),x86)
   $(call detected,CONFIG_X86)
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 6b8eb13e14e4..c4023f22f287 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -12,18 +12,18 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 	int i, idx = 0;
 	u64 mask = regs->mask;
 
-	if (regs->cache_mask & (1 << id))
+	if (regs->cache_mask & (1ULL << id))
 		goto out;
 
-	if (!(mask & (1 << id)))
+	if (!(mask & (1ULL << id)))
 		return -EINVAL;
 
 	for (i = 0; i < id; i++) {
-		if (mask & (1 << i))
+		if (mask & (1ULL << i))
 			idx++;
 	}
 
-	regs->cache_mask |= (1 << id);
+	regs->cache_mask |= (1ULL << id);
 	regs->cache_regs[id] = regs->regs[idx];
 
 out:
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index b08f77cbe31b..4ca83fe80654 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -14,6 +14,7 @@ export CFLAGS
 
 SUB_DIRS = benchmarks 		\
 	   copyloops		\
+	   context_switch	\
 	   dscr			\
 	   mm			\
 	   pmu			\
diff --git a/tools/testing/selftests/powerpc/context_switch/.gitignore b/tools/testing/selftests/powerpc/context_switch/.gitignore
new file mode 100644
index 000000000000..c1431af7b51c
--- /dev/null
+++ b/tools/testing/selftests/powerpc/context_switch/.gitignore
@@ -0,0 +1 @@
+cp_abort
diff --git a/tools/testing/selftests/powerpc/context_switch/Makefile b/tools/testing/selftests/powerpc/context_switch/Makefile
new file mode 100644
index 000000000000..e164d1466466
--- /dev/null
+++ b/tools/testing/selftests/powerpc/context_switch/Makefile
@@ -0,0 +1,10 @@
+TEST_PROGS := cp_abort
+
+all: $(TEST_PROGS)
+
+$(TEST_PROGS): ../harness.c ../utils.c
+
+include ../../lib.mk
+
+clean:
+	rm -f $(TEST_PROGS)
diff --git a/tools/testing/selftests/powerpc/context_switch/cp_abort.c b/tools/testing/selftests/powerpc/context_switch/cp_abort.c
new file mode 100644
index 000000000000..5a5b55afda0e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/context_switch/cp_abort.c
@@ -0,0 +1,110 @@
+/*
+ * Adapted from Anton Blanchard's context switch microbenchmark.
+ *
+ * Copyright 2009, Anton Blanchard, IBM Corporation.
+ * Copyright 2016, Mikey Neuling, Chris Smart, 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.
+ *
+ * This program tests the copy paste abort functionality of a P9
+ * (or later) by setting up two processes on the same CPU, one
+ * which executes the copy instruction and the other which
+ * executes paste.
+ *
+ * The paste instruction should never succeed, as the cp_abort
+ * instruction is called by the kernel during a context switch.
+ *
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include "utils.h"
+#include <sched.h>
+
+#define READ_FD 0
+#define WRITE_FD 1
+
+#define NUM_LOOPS 1000
+
+/* This defines the "paste" instruction from Power ISA 3.0 Book II, section 4.4. */
+#define PASTE(RA, RB, L, RC) \
+	.long (0x7c00070c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10) | (RC) << (31-31))
+
+int paste(void *i)
+{
+	int cr;
+
+	asm volatile(str(PASTE(0, %1, 1, 1))";"
+			"mfcr %0;"
+			: "=r" (cr)
+			: "b" (i)
+			: "memory"
+		    );
+	return cr;
+}
+
+/* This defines the "copy" instruction from Power ISA 3.0 Book II, section 4.4. */
+#define COPY(RA, RB, L) \
+	.long (0x7c00060c | (RA) << (31-15) | (RB) << (31-20) | (L) << (31-10))
+
+void copy(void *i)
+{
+	asm volatile(str(COPY(0, %0, 1))";"
+			:
+			: "b" (i)
+			: "memory"
+		    );
+}
+
+int test_cp_abort(void)
+{
+	/* 128 bytes for a full cache line */
+	char buf[128] __cacheline_aligned;
+	cpu_set_t cpuset;
+	int fd1[2], fd2[2], pid;
+	char c;
+
+	/* only run this test on a P9 or later */
+	SKIP_IF(!have_hwcap2(PPC_FEATURE2_ARCH_3_00));
+
+	/*
+	 * Run both processes on the same CPU, so that copy is more likely
+	 * to leak into a paste.
+	 */
+	CPU_ZERO(&cpuset);
+	CPU_SET(pick_online_cpu(), &cpuset);
+	FAIL_IF(sched_setaffinity(0, sizeof(cpuset), &cpuset));
+
+	FAIL_IF(pipe(fd1) || pipe(fd2));
+
+	pid = fork();
+	FAIL_IF(pid < 0);
+
+	if (!pid) {
+		for (int i = 0; i < NUM_LOOPS; i++) {
+			FAIL_IF((write(fd1[WRITE_FD], &c, 1)) != 1);
+			FAIL_IF((read(fd2[READ_FD], &c, 1)) != 1);
+			/* A paste succeeds if CR0 EQ bit is set */
+			FAIL_IF(paste(buf) & 0x20000000);
+		}
+	} else {
+		for (int i = 0; i < NUM_LOOPS; i++) {
+			FAIL_IF((read(fd1[READ_FD], &c, 1)) != 1);
+			copy(buf);
+			FAIL_IF((write(fd2[WRITE_FD], &c, 1) != 1));
+		}
+	}
+	return 0;
+
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_cp_abort, "cp_abort");
+}
diff --git a/tools/testing/selftests/powerpc/mm/subpage_prot.c b/tools/testing/selftests/powerpc/mm/subpage_prot.c
index 440180ff8089..35ade7406dcd 100644
--- a/tools/testing/selftests/powerpc/mm/subpage_prot.c
+++ b/tools/testing/selftests/powerpc/mm/subpage_prot.c
@@ -73,7 +73,7 @@ static inline void check_faulted(void *addr, long page, long subpage, int write)
 		want_fault |= (subpage == ((page + 1) % 16));
 
 	if (faulted != want_fault) {
-		printf("Failed at 0x%p (p=%ld,sp=%ld,w=%d), want=%s, got=%s !\n",
+		printf("Failed at %p (p=%ld,sp=%ld,w=%d), want=%s, got=%s !\n",
 		       addr, page, subpage, write,
 		       want_fault ? "fault" : "pass",
 		       faulted ? "fault" : "pass");
@@ -82,7 +82,7 @@ static inline void check_faulted(void *addr, long page, long subpage, int write)
 
 	if (faulted) {
 		if (dar != addr) {
-			printf("Fault expected at 0x%p and happened at 0x%p !\n",
+			printf("Fault expected at %p and happened at %p !\n",
 			       addr, dar);
 		}
 		faulted = 0;
@@ -162,7 +162,7 @@ int test_anon(void)
 
 	mallocblock = (void *)align;
 
-	printf("allocated malloc block of 0x%lx bytes at 0x%p\n",
+	printf("allocated malloc block of 0x%lx bytes at %p\n",
 	       mallocsize, mallocblock);
 
 	printf("testing malloc block...\n");
@@ -197,7 +197,7 @@ int test_file(void)
 		perror("failed to map file");
 		return 1;
 	}
-	printf("allocated %s for 0x%lx bytes at 0x%p\n",
+	printf("allocated %s for 0x%lx bytes at %p\n",
 	       file_name, filesize, fileblock);
 
 	printf("testing file map...\n");
@@ -207,14 +207,16 @@ int test_file(void)
 
 int main(int argc, char *argv[])
 {
-	test_harness(test_anon, "subpage_prot_anon");
+	int rc;
+
+	rc = test_harness(test_anon, "subpage_prot_anon");
+	if (rc)
+		return rc;
 
 	if (argc > 1)
 		file_name = argv[1];
 	else
 		file_name = "tempfile";
 
-	test_harness(test_file, "subpage_prot_file");
-
-	return 0;
+	return test_harness(test_file, "subpage_prot_file");
 }
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index e67452f1bcff..46681fec549b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -15,7 +15,6 @@
 #include <sys/ioctl.h>
 
 #include "trace.h"
-#include "reg.h"
 #include "ebb.h"
 
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c b/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c
index 5b1188f10c15..f923228bca22 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c
@@ -7,7 +7,6 @@
 #include <stdlib.h>
 
 #include "ebb.h"
-#include "reg.h"
 
 
 /*
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/reg.h b/tools/testing/selftests/powerpc/reg.h
index 5921b0dfe2e9..65bfdeeebdee 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/reg.h
+++ b/tools/testing/selftests/powerpc/reg.h
@@ -9,12 +9,12 @@
 #define __stringify_1(x)        #x
 #define __stringify(x)          __stringify_1(x)
 
-#define mfspr(rn)       ({unsigned long rval; \
-                         asm volatile("mfspr %0," __stringify(rn) \
-                                 : "=r" (rval)); rval; })
-#define mtspr(rn, v)    asm volatile("mtspr " __stringify(rn) ",%0" : \
-                                    : "r" ((unsigned long)(v)) \
-                                    : "memory")
+#define mfspr(rn)	({unsigned long rval; \
+			 asm volatile("mfspr %0," _str(rn) \
+				    : "=r" (rval)); rval; })
+#define mtspr(rn, v)	asm volatile("mtspr " _str(rn) ",%0" : \
+				    : "r" ((unsigned long)(v)) \
+				    : "memory")
 
 #define mb()		asm volatile("sync" : : : "memory");
 
@@ -46,4 +46,10 @@
 #define SPRN_SDAR      781
 #define SPRN_SIER      768
 
+#define SPRN_TEXASR     0x82
+#define SPRN_TFIAR      0x81    /* Transaction Failure Inst Addr    */
+#define SPRN_TFHAR      0x80    /* Transaction Failure Handler Addr */
+#define TEXASR_FS       0x08000000
+#define SPRN_TAR        0x32f
+
 #endif /* _SELFTESTS_POWERPC_REG_H */
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 7d0f14b8cb2e..bb942db845bf 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -3,3 +3,6 @@ tm-syscall
 tm-signal-msr-resv
 tm-signal-stack
 tm-vmxcopy
+tm-fork
+tm-tar
+tm-tmspr
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 737f72c964e6..d0505dbd22d5 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -1,4 +1,4 @@
-TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy
+TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy tm-fork tm-tar tm-tmspr
 
 all: $(TEST_PROGS)
 
@@ -6,6 +6,7 @@ $(TEST_PROGS): ../harness.c ../utils.c
 
 tm-syscall: tm-syscall-asm.S
 tm-syscall: CFLAGS += -mhtm -I../../../../../usr/include
+tm-tmspr: CFLAGS += -pthread
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/tm/tm-fork.c b/tools/testing/selftests/powerpc/tm/tm-fork.c
new file mode 100644
index 000000000000..8d48579b7778
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-fork.c
@@ -0,0 +1,42 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Edited: Rashmica Gupta, Nov 2015
+ *
+ * This test does a fork syscall inside a transaction. Basic sniff test
+ * to see if we can enter the kernel during a transaction.
+ */
+
+#include <errno.h>
+#include <inttypes.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "utils.h"
+#include "tm.h"
+
+int test_fork(void)
+{
+	SKIP_IF(!have_htm());
+
+	asm __volatile__(
+		"tbegin.;"
+		"blt    1f; "
+		"li     0, 2;"  /* fork syscall */
+		"sc  ;"
+		"tend.;"
+		"1: ;"
+		: : : "memory", "r0");
+	/* If we reach here, we've passed.  Otherwise we've probably crashed
+	 * the kernel */
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	return test_harness(test_fork, "tm_fork");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
index 8fde93d6021f..d9c49f41515e 100644
--- a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
@@ -31,12 +31,6 @@
 #include "utils.h"
 #include "tm.h"
 
-#define TBEGIN          ".long 0x7C00051D ;"
-#define TEND            ".long 0x7C00055D ;"
-#define TCHECK          ".long 0x7C00059C ;"
-#define TSUSPEND        ".long 0x7C0005DD ;"
-#define TRESUME         ".long 0x7C2005DD ;"
-#define SPRN_TEXASR     0x82
 #define SPRN_DSCR       0x03
 
 int test_body(void)
@@ -55,13 +49,13 @@ int test_body(void)
 			"mtspr   %[sprn_dscr], 3;"
 
 			/* start and suspend a transaction */
-			TBEGIN
+			"tbegin.;"
 			"beq     1f;"
-			TSUSPEND
+			"tsuspend.;"
 
 			/* hard loop until the transaction becomes doomed */
 			"2: ;"
-			TCHECK
+			"tcheck 0;"
 			"bc      4, 0, 2b;"
 
 			/* record DSCR and TEXASR */
@@ -70,8 +64,8 @@ int test_body(void)
 			"mfspr   3, %[sprn_texasr];"
 			"std     3, %[texasr];"
 
-			TRESUME
-			TEND
+			"tresume.;"
+			"tend.;"
 			"li      %[rv], 0;"
 			"1: ;"
 			: [rv]"=r"(rv), [dscr2]"=m"(dscr2), [texasr]"=m"(texasr)
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-stack.c b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
index e44a238c1d77..1f0eb567438d 100644
--- a/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
@@ -60,9 +60,9 @@ int tm_signal_stack()
 		exit(1);
 	asm volatile("li 1, 0 ;"		/* stack ptr == NULL */
 		     "1:"
-		     ".long 0x7C00051D ;"	/* tbegin */
+		     "tbegin.;"
 		     "beq 1b ;"			/* retry forever */
-		     ".long 0x7C0005DD ; ;"	/* tsuspend */
+		     "tsuspend.;"
 		     "ld 2, 0(1) ;"		/* trigger segv" */
 		     : : : "memory");
 
diff --git a/tools/testing/selftests/powerpc/tm/tm-tar.c b/tools/testing/selftests/powerpc/tm/tm-tar.c
new file mode 100644
index 000000000000..2d2fcc2b7a60
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-tar.c
@@ -0,0 +1,90 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ * Original: Michael Neuling 19/7/2013
+ * Edited: Rashmica Gupta 01/12/2015
+ *
+ * Do some transactions, see if the tar is corrupted.
+ * If the transaction is aborted, the TAR should be rolled back to the
+ * checkpointed value before the transaction began. The value written to
+ * TAR in suspended mode should only remain in TAR if the transaction
+ * completes.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+
+#include "tm.h"
+#include "utils.h"
+
+int	num_loops	= 10000;
+
+int test_tar(void)
+{
+	int i;
+
+	SKIP_IF(!have_htm());
+
+	for (i = 0; i < num_loops; i++)
+	{
+		uint64_t result = 0;
+		asm __volatile__(
+			"li	7, 1;"
+			"mtspr	%[tar], 7;"	/* tar = 1 */
+			"tbegin.;"
+			"beq	3f;"
+			"li	4, 0x7000;"	/* Loop lots, to use time */
+			"2:;"			/* Start loop */
+			"li	7, 2;"
+			"mtspr	%[tar], 7;"	/* tar = 2 */
+			"tsuspend.;"
+			"li	7, 3;"
+			"mtspr	%[tar], 7;"	/* tar = 3 */
+			"tresume.;"
+			"subi	4, 4, 1;"
+			"cmpdi	4, 0;"
+			"bne	2b;"
+			"tend.;"
+
+			/* Transaction sucess! TAR should be 3 */
+			"mfspr  7, %[tar];"
+			"ori	%[res], 7, 4;"  // res = 3|4 = 7
+			"b	4f;"
+
+			/* Abort handler. TAR should be rolled back to 1 */
+			"3:;"
+			"mfspr  7, %[tar];"
+			"ori	%[res], 7, 8;"	// res = 1|8 = 9
+			"4:;"
+
+			: [res]"=r"(result)
+			: [tar]"i"(SPRN_TAR)
+			   : "memory", "r0", "r4", "r7");
+
+		/* If result is anything else other than 7 or 9, the tar
+		 * value must have been corrupted. */
+		if ((result != 7) && (result != 9))
+			return 1;
+	}
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	/* A low number of iterations (eg 100) can cause a false pass */
+	if (argc > 1) {
+		if (strcmp(argv[1], "-h") == 0) {
+			printf("Syntax:\n\t%s [<num loops>]\n",
+			       argv[0]);
+			return 1;
+		} else {
+			num_loops = atoi(argv[1]);
+		}
+	}
+
+	printf("Starting, %d loops\n", num_loops);
+
+	return test_harness(test_tar, "tm_tar");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c
new file mode 100644
index 000000000000..2bda81c7bf23
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c
@@ -0,0 +1,143 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Original: Michael Neuling 3/4/2014
+ * Modified: Rashmica Gupta 8/12/2015
+ *
+ * Check if any of the Transaction Memory SPRs get corrupted.
+ * - TFIAR  - stores address of location of transaction failure
+ * - TFHAR  - stores address of software failure handler (if transaction
+ *   fails)
+ * - TEXASR - lots of info about the transacion(s)
+ *
+ * (1) create more threads than cpus
+ * (2) in each thread:
+ * 	(a) set TFIAR and TFHAR a unique value
+ * 	(b) loop for awhile, continually checking to see if
+ * 	either register has been corrupted.
+ *
+ * (3) Loop:
+ * 	(a) begin transaction
+ *    	(b) abort transaction
+ *	(c) check TEXASR to see if FS has been corrupted
+ *
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <pthread.h>
+#include <string.h>
+
+#include "utils.h"
+#include "tm.h"
+
+int	num_loops	= 10000;
+int	passed = 1;
+
+void tfiar_tfhar(void *in)
+{
+	int i, cpu;
+	unsigned long tfhar, tfhar_rd, tfiar, tfiar_rd;
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	cpu = (unsigned long)in >> 1;
+	CPU_SET(cpu, &cpuset);
+	sched_setaffinity(0, sizeof(cpuset), &cpuset);
+
+	/* TFIAR: Last bit has to be high so userspace can read register */
+	tfiar = ((unsigned long)in) + 1;
+	tfiar += 2;
+	mtspr(SPRN_TFIAR, tfiar);
+
+	/* TFHAR: Last two bits are reserved */
+	tfhar = ((unsigned long)in);
+	tfhar &= ~0x3UL;
+	tfhar += 4;
+	mtspr(SPRN_TFHAR, tfhar);
+
+	for (i = 0; i < num_loops; i++)	{
+		tfhar_rd = mfspr(SPRN_TFHAR);
+		tfiar_rd = mfspr(SPRN_TFIAR);
+		if ( (tfhar != tfhar_rd) || (tfiar != tfiar_rd) ) {
+			passed = 0;
+			return;
+		}
+	}
+	return;
+}
+
+void texasr(void *in)
+{
+	unsigned long i;
+	uint64_t result = 0;
+
+	for (i = 0; i < num_loops; i++) {
+		asm __volatile__(
+			"tbegin.;"
+			"beq    3f ;"
+			"tabort. 0 ;"
+			"tend.;"
+
+			/* Abort handler */
+			"3: ;"
+			::: "memory");
+
+                /* Check the TEXASR */
+                result = mfspr(SPRN_TEXASR);
+		if ((result & TEXASR_FS) == 0) {
+			passed = 0;
+			return;
+		}
+	}
+	return;
+}
+
+int test_tmspr()
+{
+	pthread_t 	thread;
+	int	   	thread_num;
+	unsigned long	i;
+
+	SKIP_IF(!have_htm());
+
+	/* To cause some context switching */
+	thread_num = 10 * sysconf(_SC_NPROCESSORS_ONLN);
+
+	/* Test TFIAR and TFHAR */
+	for (i = 0 ; i < thread_num ; i += 2){
+		if (pthread_create(&thread, NULL, (void*)tfiar_tfhar, (void *)i))
+			return EXIT_FAILURE;
+	}
+	if (pthread_join(thread, NULL) != 0)
+		return EXIT_FAILURE;
+
+	/* Test TEXASR */
+	for (i = 0 ; i < thread_num ; i++){
+		if (pthread_create(&thread, NULL, (void*)texasr, (void *)i))
+			return EXIT_FAILURE;
+	}
+	if (pthread_join(thread, NULL) != 0)
+		return EXIT_FAILURE;
+
+	if (passed)
+		return 0;
+	else
+		return 1;
+}
+
+int main(int argc, char *argv[])
+{
+	if (argc > 1) {
+		if (strcmp(argv[1], "-h") == 0) {
+			printf("Syntax:\t [<num loops>]\n");
+			return 0;
+		} else {
+			num_loops = atoi(argv[1]);
+		}
+	}
+	return test_harness(test_tmspr, "tm_tmspr");
+}
diff --git a/tools/testing/selftests/powerpc/utils.h b/tools/testing/selftests/powerpc/utils.h
index 175ac6ad10dd..a985cfaa535e 100644
--- a/tools/testing/selftests/powerpc/utils.h
+++ b/tools/testing/selftests/powerpc/utils.h
@@ -6,9 +6,12 @@
 #ifndef _SELFTESTS_POWERPC_UTILS_H
 #define _SELFTESTS_POWERPC_UTILS_H
 
+#define __cacheline_aligned __attribute__((aligned(128)))
+
 #include <stdint.h>
 #include <stdbool.h>
 #include <linux/auxvec.h>
+#include "reg.h"
 
 /* Avoid headaches with PRI?64 - just use %ll? always */
 typedef unsigned long long u64;
@@ -54,4 +57,9 @@ do {								\
 #define _str(s) #s
 #define str(s) _str(s)
 
+/* POWER9 feature */
+#ifndef PPC_FEATURE2_ARCH_3_00
+#define PPC_FEATURE2_ARCH_3_00 0x00800000
+#endif
+
 #endif /* _SELFTESTS_POWERPC_UTILS_H */