Merge tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Core:
   - Ground work for the new Power9 MMU from Aneesh Kumar K.V
   - Optimise FP/VMX/VSX context switching from Anton Blanchard

  Misc:
   - Various cleanups from Krzysztof Kozlowski, John Ogness, Rashmica
     Gupta, Russell Currey, Gavin Shan, Daniel Axtens, Michael Neuling,
     Andrew Donnellan
   - Allow wrapper to work on non-english system from Laurent Vivier
   - Add rN aliases to the pt_regs_offset table from Rashmica Gupta
   - Fix module autoload for rackmeter & axonram drivers from Luis de
     Bethencourt
   - Include KVM guest test in all interrupt vectors from Paul Mackerras
   - Fix DSCR inheritance over fork() from Anton Blanchard
   - Make value-returning atomics & {cmp}xchg* & their atomic_ versions
     fully ordered from Boqun Feng
   - Print MSR TM bits in oops messages from Michael Neuling
   - Add TM signal return & invalid stack selftests from Michael Neuling
   - Limit EPOW reset event warnings from Vipin K Parashar
   - Remove the Cell QPACE code from Rashmica Gupta
   - Append linux_banner to exception information in xmon from Rashmica
     Gupta
   - Add selftest to check if VSRs are corrupted from Rashmica Gupta
   - Remove broken GregorianDay() from Daniel Axtens
   - Import Anton's context_switch2 benchmark into selftests from
     Michael Ellerman
   - Add selftest script to test HMI functionality from Daniel Axtens
   - Remove obsolete OPAL v2 support from Stewart Smith
   - Make enter_rtas() private from Michael Ellerman
   - PPR exception cleanups from Michael Ellerman
   - Add page soft dirty tracking from Laurent Dufour
   - Add support for Nvlink NPUs from Alistair Popple
   - Add support for kexec on 476fpe from Alistair Popple
   - Enable kernel CPU dlpar from sysfs from Nathan Fontenot
   - Copy only required pieces of the mm_context_t to the paca from
     Michael Neuling
   - Add a kmsg_dumper that flushes OPAL console output on panic from
     Russell Currey
   - Implement save_stack_trace_regs() to enable kprobe stack tracing
     from Steven Rostedt
   - Add HWCAP bits for Power9 from Michael Ellerman
   - Fix _PAGE_PTE breaking swapoff from Aneesh Kumar K.V
   - Fix _PAGE_SWP_SOFT_DIRTY breaking swapoff from Hugh Dickins
   - scripts/recordmcount.pl: support data in text section on powerpc
     from Ulrich Weigand
   - Handle R_PPC64_ENTRY relocations in modules from Ulrich Weigand

  cxl:
   - cxl: Fix possible idr warning when contexts are released from
     Vaibhav Jain
   - cxl: use correct operator when writing pcie config space values
     from Andrew Donnellan
   - cxl: Fix DSI misses when the context owning task exits from Vaibhav
     Jain
   - cxl: fix build for GCC 4.6.x from Brian Norris
   - cxl: use -Werror only with CONFIG_PPC_WERROR from Brian Norris
   - cxl: Enable PCI device ID for future IBM CXL adapter from Uma
     Krishnan

  Freescale:
   - Freescale updates from Scott: Highlights include moving QE code out
     of arch/powerpc (to be shared with arm), device tree updates, and
     minor fixes"

* tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (149 commits)
  powerpc/module: Handle R_PPC64_ENTRY relocations
  scripts/recordmcount.pl: support data in text section on powerpc
  powerpc/powernv: Fix OPAL_CONSOLE_FLUSH prototype and usages
  powerpc/mm: fix _PAGE_SWP_SOFT_DIRTY breaking swapoff
  powerpc/mm: Fix _PAGE_PTE breaking swapoff
  cxl: Enable PCI device ID for future IBM CXL adapter
  cxl: use -Werror only with CONFIG_PPC_WERROR
  cxl: fix build for GCC 4.6.x
  powerpc: Add HWCAP bits for Power9
  powerpc/powernv: Reserve PE#0 on NPU
  powerpc/powernv: Change NPU PE# assignment
  powerpc/powernv: Fix update of NVLink DMA mask
  powerpc/powernv: Remove misleading comment in pci.c
  powerpc: Implement save_stack_trace_regs() to enable kprobe stack tracing
  powerpc: Fix build break due to paca mm_context_t changes
  cxl: Fix DSI misses when the context owning task exits
  MAINTAINERS: Update Scott Wood's e-mail address
  powerpc/powernv: Fix minor off-by-one error in opal_mce_check_early_recovery()
  powerpc: Fix style of self-test config prompts
  powerpc/powernv: Only delay opal_rtc_read() retry when necessary
  ...

22 files changed, 956 insertions, 105 deletions

diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore
index b4709ea588c1..6fa673316ac2 100644
--- a/tools/testing/selftests/powerpc/benchmarks/.gitignore
+++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore
@@ -1 +1,2 @@
 gettimeofday
+context_switch
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile
index 5fa48702070d..912445ff7ce7 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -1,4 +1,4 @@
-TEST_PROGS := gettimeofday
+TEST_PROGS := gettimeofday context_switch
 
 CFLAGS += -O2
 
@@ -6,6 +6,9 @@ all: $(TEST_PROGS)
 
 $(TEST_PROGS): ../harness.c
 
+context_switch: ../utils.c
+context_switch: LDLIBS += -lpthread
+
 include ../../lib.mk
 
 clean:
diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
new file mode 100644
index 000000000000..7b785941adec
--- /dev/null
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -0,0 +1,466 @@
+/*
+ * Context switch microbenchmark.
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * 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.
+ */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <getopt.h>
+#include <signal.h>
+#include <assert.h>
+#include <pthread.h>
+#include <limits.h>
+#include <sys/time.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/shm.h>
+#include <linux/futex.h>
+
+#include "../utils.h"
+
+static unsigned int timeout = 30;
+
+static int touch_vdso;
+struct timeval tv;
+
+static int touch_fp = 1;
+double fp;
+
+static int touch_vector = 1;
+typedef int v4si __attribute__ ((vector_size (16)));
+v4si a, b, c;
+
+#ifdef __powerpc__
+static int touch_altivec = 1;
+
+static void __attribute__((__target__("no-vsx"))) altivec_touch_fn(void)
+{
+	c = a + b;
+}
+#endif
+
+static void touch(void)
+{
+	if (touch_vdso)
+		gettimeofday(&tv, NULL);
+
+	if (touch_fp)
+		fp += 0.1;
+
+#ifdef __powerpc__
+	if (touch_altivec)
+		altivec_touch_fn();
+#endif
+
+	if (touch_vector)
+		c = a + b;
+
+	asm volatile("# %0 %1 %2": : "r"(&tv), "r"(&fp), "r"(&c));
+}
+
+static void start_thread_on(void *(*fn)(void *), void *arg, unsigned long cpu)
+{
+	pthread_t tid;
+	cpu_set_t cpuset;
+	pthread_attr_t attr;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+
+	pthread_attr_init(&attr);
+
+	if (pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpuset)) {
+		perror("pthread_attr_setaffinity_np");
+		exit(1);
+	}
+
+	if (pthread_create(&tid, &attr, fn, arg)) {
+		perror("pthread_create");
+		exit(1);
+	}
+}
+
+static void start_process_on(void *(*fn)(void *), void *arg, unsigned long cpu)
+{
+	int pid;
+	cpu_set_t cpuset;
+
+	pid = fork();
+	if (pid == -1) {
+		perror("fork");
+		exit(1);
+	}
+
+	if (pid)
+		return;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset)) {
+		perror("sched_setaffinity");
+		exit(1);
+	}
+
+	fn(arg);
+
+	exit(0);
+}
+
+static unsigned long iterations;
+static unsigned long iterations_prev;
+
+static void sigalrm_handler(int junk)
+{
+	unsigned long i = iterations;
+
+	printf("%ld\n", i - iterations_prev);
+	iterations_prev = i;
+
+	if (--timeout == 0)
+		kill(0, SIGUSR1);
+
+	alarm(1);
+}
+
+static void sigusr1_handler(int junk)
+{
+	exit(0);
+}
+
+struct actions {
+	void (*setup)(int, int);
+	void *(*thread1)(void *);
+	void *(*thread2)(void *);
+};
+
+#define READ 0
+#define WRITE 1
+
+static int pipe_fd1[2];
+static int pipe_fd2[2];
+
+static void pipe_setup(int cpu1, int cpu2)
+{
+	if (pipe(pipe_fd1) || pipe(pipe_fd2))
+		exit(1);
+}
+
+static void *pipe_thread1(void *arg)
+{
+	signal(SIGALRM, sigalrm_handler);
+	alarm(1);
+
+	while (1) {
+		assert(read(pipe_fd1[READ], &c, 1) == 1);
+		touch();
+
+		assert(write(pipe_fd2[WRITE], &c, 1) == 1);
+		touch();
+
+		iterations += 2;
+	}
+
+	return NULL;
+}
+
+static void *pipe_thread2(void *arg)
+{
+	while (1) {
+		assert(write(pipe_fd1[WRITE], &c, 1) == 1);
+		touch();
+
+		assert(read(pipe_fd2[READ], &c, 1) == 1);
+		touch();
+	}
+
+	return NULL;
+}
+
+static struct actions pipe_actions = {
+	.setup = pipe_setup,
+	.thread1 = pipe_thread1,
+	.thread2 = pipe_thread2,
+};
+
+static void yield_setup(int cpu1, int cpu2)
+{
+	if (cpu1 != cpu2) {
+		fprintf(stderr, "Both threads must be on the same CPU for yield test\n");
+		exit(1);
+	}
+}
+
+static void *yield_thread1(void *arg)
+{
+	signal(SIGALRM, sigalrm_handler);
+	alarm(1);
+
+	while (1) {
+		sched_yield();
+		touch();
+
+		iterations += 2;
+	}
+
+	return NULL;
+}
+
+static void *yield_thread2(void *arg)
+{
+	while (1) {
+		sched_yield();
+		touch();
+	}
+
+	return NULL;
+}
+
+static struct actions yield_actions = {
+	.setup = yield_setup,
+	.thread1 = yield_thread1,
+	.thread2 = yield_thread2,
+};
+
+static long sys_futex(void *addr1, int op, int val1, struct timespec *timeout,
+		      void *addr2, int val3)
+{
+	return syscall(SYS_futex, addr1, op, val1, timeout, addr2, val3);
+}
+
+static unsigned long cmpxchg(unsigned long *p, unsigned long expected,
+			     unsigned long desired)
+{
+	unsigned long exp = expected;
+
+	__atomic_compare_exchange_n(p, &exp, desired, 0,
+				    __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST);
+	return exp;
+}
+
+static unsigned long xchg(unsigned long *p, unsigned long val)
+{
+	return __atomic_exchange_n(p, val, __ATOMIC_SEQ_CST);
+}
+
+static int mutex_lock(unsigned long *m)
+{
+	int c;
+
+	c = cmpxchg(m, 0, 1);
+	if (!c)
+		return 0;
+
+	if (c == 1)
+		c = xchg(m, 2);
+
+	while (c) {
+		sys_futex(m, FUTEX_WAIT, 2, NULL, NULL, 0);
+		c = xchg(m, 2);
+	}
+
+	return 0;
+}
+
+static int mutex_unlock(unsigned long *m)
+{
+	if (*m == 2)
+		*m = 0;
+	else if (xchg(m, 0) == 1)
+		return 0;
+
+	sys_futex(m, FUTEX_WAKE, 1, NULL, NULL, 0);
+
+	return 0;
+}
+
+static unsigned long *m1, *m2;
+
+static void futex_setup(int cpu1, int cpu2)
+{
+	int shmid;
+	void *shmaddr;
+
+	shmid = shmget(IPC_PRIVATE, getpagesize(), SHM_R | SHM_W);
+	if (shmid < 0) {
+		perror("shmget");
+		exit(1);
+	}
+
+	shmaddr = shmat(shmid, NULL, 0);
+	if (shmaddr == (char *)-1) {
+		perror("shmat");
+		shmctl(shmid, IPC_RMID, NULL);
+		exit(1);
+	}
+
+	shmctl(shmid, IPC_RMID, NULL);
+
+	m1 = shmaddr;
+	m2 = shmaddr + sizeof(*m1);
+
+	*m1 = 0;
+	*m2 = 0;
+
+	mutex_lock(m1);
+	mutex_lock(m2);
+}
+
+static void *futex_thread1(void *arg)
+{
+	signal(SIGALRM, sigalrm_handler);
+	alarm(1);
+
+	while (1) {
+		mutex_lock(m2);
+		mutex_unlock(m1);
+
+		iterations += 2;
+	}
+
+	return NULL;
+}
+
+static void *futex_thread2(void *arg)
+{
+	while (1) {
+		mutex_unlock(m2);
+		mutex_lock(m1);
+	}
+
+	return NULL;
+}
+
+static struct actions futex_actions = {
+	.setup = futex_setup,
+	.thread1 = futex_thread1,
+	.thread2 = futex_thread2,
+};
+
+static int processes;
+
+static struct option options[] = {
+	{ "test", required_argument, 0, 't' },
+	{ "process", no_argument, &processes, 1 },
+	{ "timeout", required_argument, 0, 's' },
+	{ "vdso", no_argument, &touch_vdso, 1 },
+	{ "no-fp", no_argument, &touch_fp, 0 },
+#ifdef __powerpc__
+	{ "no-altivec", no_argument, &touch_altivec, 0 },
+#endif
+	{ "no-vector", no_argument, &touch_vector, 0 },
+	{ 0, },
+};
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: context_switch2 <options> CPU1 CPU2\n\n");
+	fprintf(stderr, "\t\t--test=X\tpipe, futex or yield (default)\n");
+	fprintf(stderr, "\t\t--process\tUse processes (default threads)\n");
+	fprintf(stderr, "\t\t--timeout=X\tDuration in seconds to run (default 30)\n");
+	fprintf(stderr, "\t\t--vdso\t\ttouch VDSO\n");
+	fprintf(stderr, "\t\t--fp\t\ttouch FP\n");
+#ifdef __powerpc__
+	fprintf(stderr, "\t\t--altivec\ttouch altivec\n");
+#endif
+	fprintf(stderr, "\t\t--vector\ttouch vector\n");
+}
+
+int main(int argc, char *argv[])
+{
+	signed char c;
+	struct actions *actions = &yield_actions;
+	int cpu1;
+	int cpu2;
+	static void (*start_fn)(void *(*fn)(void *), void *arg, unsigned long cpu);
+
+	while (1) {
+		int option_index = 0;
+
+		c = getopt_long(argc, argv, "", options, &option_index);
+
+		if (c == -1)
+			break;
+
+		switch (c) {
+		case 0:
+			if (options[option_index].flag != 0)
+				break;
+
+			usage();
+			exit(1);
+			break;
+
+		case 't':
+			if (!strcmp(optarg, "pipe")) {
+				actions = &pipe_actions;
+			} else if (!strcmp(optarg, "yield")) {
+				actions = &yield_actions;
+			} else if (!strcmp(optarg, "futex")) {
+				actions = &futex_actions;
+			} else {
+				usage();
+				exit(1);
+			}
+			break;
+
+		case 's':
+			timeout = atoi(optarg);
+			break;
+
+		default:
+			usage();
+			exit(1);
+		}
+	}
+
+	if (processes)
+		start_fn = start_process_on;
+	else
+		start_fn = start_thread_on;
+
+	if (((argc - optind) != 2)) {
+		cpu1 = cpu2 = pick_online_cpu();
+	} else {
+		cpu1 = atoi(argv[optind++]);
+		cpu2 = atoi(argv[optind++]);
+	}
+
+	printf("Using %s with ", processes ? "processes" : "threads");
+
+	if (actions == &pipe_actions)
+		printf("pipe");
+	else if (actions == &yield_actions)
+		printf("yield");
+	else
+		printf("futex");
+
+	printf(" on cpus %d/%d touching FP:%s altivec:%s vector:%s vdso:%s\n",
+	       cpu1, cpu2, touch_fp ?  "yes" : "no", touch_altivec ? "yes" : "no",
+	       touch_vector ? "yes" : "no", touch_vdso ? "yes" : "no");
+
+	/* Create a new process group so we can signal everyone for exit */
+	setpgid(getpid(), getpid());
+
+	signal(SIGUSR1, sigusr1_handler);
+
+	actions->setup(cpu1, cpu2);
+
+	start_fn(actions->thread1, NULL, cpu1);
+	start_fn(actions->thread2, NULL, cpu2);
+
+	while (1)
+		sleep(3600);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c
index 8265504de571..08a8b95e3bc1 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c
+++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_exec_test.c
@@ -60,14 +60,6 @@ int dscr_inherit_exec(void)
 		else
 			set_dscr(dscr);
 
-		/*
-		 * XXX: Force a context switch out so that DSCR
-		 * current value is copied into the thread struct
-		 * which is required for the child to inherit the
-		 * changed value.
-		 */
-		sleep(1);
-
 		pid = fork();
 		if (pid == -1) {
 			perror("fork() failed");
diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c
index 4e414caf7f40..3e5a6d195e9a 100644
--- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c
+++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c
@@ -40,14 +40,6 @@ int dscr_inherit(void)
 		else
 			set_dscr(dscr);
 
-		/*
-		 * XXX: Force a context switch out so that DSCR
-		 * current value is copied into the thread struct
-		 * which is required for the child to inherit the
-		 * changed value.
-		 */
-		sleep(1);
-
 		pid = fork();
 		if (pid == -1) {
 			perror("fork() failed");
diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c
index f7997affd143..52f9be7f61f0 100644
--- a/tools/testing/selftests/powerpc/harness.c
+++ b/tools/testing/selftests/powerpc/harness.c
@@ -116,46 +116,3 @@ int test_harness(int (test_function)(void), char *name)
 
 	return rc;
 }
-
-static char auxv[4096];
-
-void *get_auxv_entry(int type)
-{
-	ElfW(auxv_t) *p;
-	void *result;
-	ssize_t num;
-	int fd;
-
-	fd = open("/proc/self/auxv", O_RDONLY);
-	if (fd == -1) {
-		perror("open");
-		return NULL;
-	}
-
-	result = NULL;
-
-	num = read(fd, auxv, sizeof(auxv));
-	if (num < 0) {
-		perror("read");
-		goto out;
-	}
-
-	if (num > sizeof(auxv)) {
-		printf("Overflowed auxv buffer\n");
-		goto out;
-	}
-
-	p = (ElfW(auxv_t) *)auxv;
-
-	while (p->a_type != AT_NULL) {
-		if (p->a_type == type) {
-			result = (void *)p->a_un.a_val;
-			break;
-		}
-
-		p++;
-	}
-out:
-	close(fd);
-	return result;
-}
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index a9099d9f8f39..ac41a7177f2e 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -2,7 +2,7 @@ noarg:
 	$(MAKE) -C ../
 
 TEST_PROGS := count_instructions l3_bank_test per_event_excludes
-EXTRA_SOURCES := ../harness.c event.c lib.c
+EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c
 
 all: $(TEST_PROGS) ebb
 
@@ -12,6 +12,8 @@ $(TEST_PROGS): $(EXTRA_SOURCES)
 count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES)
 	$(CC) $(CFLAGS) -m64 -o $@ $^
 
+per_event_excludes: ../utils.c
+
 include ../../lib.mk
 
 DEFAULT_RUN_TESTS := $(RUN_TESTS)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
index 5cdc9dbf2b27..8d2279c4bb4b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -18,7 +18,8 @@ TEST_PROGS := reg_access_test event_attributes_test cycles_test	\
 
 all: $(TEST_PROGS)
 
-$(TEST_PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S
+$(TEST_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c \
+	       ebb.c ebb_handler.S trace.c busy_loop.S
 
 instruction_count_test: ../loop.S
 
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index 9729d9f90218..e67452f1bcff 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -13,7 +13,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/ioctl.h>
-#include <linux/auxvec.h>
 
 #include "trace.h"
 #include "reg.h"
@@ -324,7 +323,7 @@ bool ebb_is_supported(void)
 {
 #ifdef PPC_FEATURE2_EBB
 	/* EBB requires at least POWER8 */
-	return ((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_EBB);
+	return have_hwcap2(PPC_FEATURE2_EBB);
 #else
 	return false;
 #endif
diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c
index a07104c2afe6..a361ad3334ce 100644
--- a/tools/testing/selftests/powerpc/pmu/lib.c
+++ b/tools/testing/selftests/powerpc/pmu/lib.c
@@ -15,32 +15,6 @@
 #include "lib.h"
 
 
-int pick_online_cpu(void)
-{
-	cpu_set_t mask;
-	int cpu;
-
-	CPU_ZERO(&mask);
-
-	if (sched_getaffinity(0, sizeof(mask), &mask)) {
-		perror("sched_getaffinity");
-		return -1;
-	}
-
-	/* We prefer a primary thread, but skip 0 */
-	for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8)
-		if (CPU_ISSET(cpu, &mask))
-			return cpu;
-
-	/* Search for anything, but in reverse */
-	for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--)
-		if (CPU_ISSET(cpu, &mask))
-			return cpu;
-
-	printf("No cpus in affinity mask?!\n");
-	return -1;
-}
-
 int bind_to_cpu(int cpu)
 {
 	cpu_set_t mask;
diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h
index ca5d72ae3be6..0213af4ff332 100644
--- a/tools/testing/selftests/powerpc/pmu/lib.h
+++ b/tools/testing/selftests/powerpc/pmu/lib.h
@@ -19,7 +19,6 @@ union pipe {
 	int fds[2];
 };
 
-extern int pick_online_cpu(void);
 extern int bind_to_cpu(int cpu);
 extern int kill_child_and_wait(pid_t child_pid);
 extern int wait_for_child(pid_t child_pid);
diff --git a/tools/testing/selftests/powerpc/scripts/hmi.sh b/tools/testing/selftests/powerpc/scripts/hmi.sh
new file mode 100755
index 000000000000..83fb253ae3bd
--- /dev/null
+++ b/tools/testing/selftests/powerpc/scripts/hmi.sh
@@ -0,0 +1,89 @@
+#!/bin/sh
+#
+# Copyright 2015, Daniel Axtens, 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; version 2 of the License.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+
+
+# do we have ./getscom, ./putscom?
+if [ -x ./getscom ] && [ -x ./putscom ]; then
+	GETSCOM=./getscom
+	PUTSCOM=./putscom
+elif which getscom > /dev/null; then
+	GETSCOM=$(which getscom)
+	PUTSCOM=$(which putscom)
+else
+	cat <<EOF
+Can't find getscom/putscom in . or \$PATH.
+See https://github.com/open-power/skiboot.
+The tool is in external/xscom-utils
+EOF
+	exit 1
+fi
+
+# We will get 8 HMI events per injection
+# todo: deal with things being offline
+expected_hmis=8
+COUNT_HMIS() {
+    dmesg | grep -c 'Harmless Hypervisor Maintenance interrupt'
+}
+
+# massively expand snooze delay, allowing injection on all cores
+ppc64_cpu --smt-snooze-delay=1000000000
+
+# when we exit, restore it
+trap "ppc64_cpu --smt-snooze-delay=100" 0 1
+
+# for each chip+core combination
+# todo - less fragile parsing
+egrep -o 'OCC: Chip [0-9a-f]+ Core [0-9a-f]' < /sys/firmware/opal/msglog |
+while read chipcore; do
+	chip=$(echo "$chipcore"|awk '{print $3}')
+	core=$(echo "$chipcore"|awk '{print $5}')
+	fir="0x1${core}013100"
+
+	# verify that Core FIR is zero as expected
+	if [ "$($GETSCOM -c 0x${chip} $fir)" != 0 ]; then
+		echo "FIR was not zero before injection for chip $chip, core $core. Aborting!"
+		echo "Result of $GETSCOM -c 0x${chip} $fir:"
+		$GETSCOM -c 0x${chip} $fir
+		echo "If you get a -5 error, the core may be in idle state. Try stress-ng."
+		echo "Otherwise, try $PUTSCOM -c 0x${chip} $fir 0"
+		exit 1
+	fi
+
+	# keep track of the number of HMIs handled
+	old_hmis=$(COUNT_HMIS)
+
+	# do injection, adding a marker to dmesg for clarity
+	echo "Injecting HMI on core $core, chip $chip" | tee /dev/kmsg
+	# inject a RegFile recoverable error
+	if ! $PUTSCOM -c 0x${chip} $fir 2000000000000000 > /dev/null; then
+		echo "Error injecting. Aborting!"
+		exit 1
+	fi
+
+	# now we want to wait for all the HMIs to be processed
+	# we expect one per thread on the core
+	i=0;
+	new_hmis=$(COUNT_HMIS)
+	while [ $new_hmis -lt $((old_hmis + expected_hmis)) ] && [ $i -lt 12 ]; do
+	    echo "Seen $((new_hmis - old_hmis)) HMI(s) out of $expected_hmis expected, sleeping"
+	    sleep 5;
+	    i=$((i + 1))
+	    new_hmis=$(COUNT_HMIS)
+	done
+	if [ $i = 12 ]; then
+	    echo "Haven't seen expected $expected_hmis recoveries after 1 min. Aborting."
+	    exit 1
+	fi
+	echo "Processed $expected_hmis events; presumed success. Check dmesg."
+	echo ""
+done
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 2699635d2cd9..7d0f14b8cb2e 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -1,2 +1,5 @@
 tm-resched-dscr
 tm-syscall
+tm-signal-msr-resv
+tm-signal-stack
+tm-vmxcopy
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 4bea62a319dc..737f72c964e6 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -1,8 +1,8 @@
-TEST_PROGS := tm-resched-dscr tm-syscall
+TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack tm-vmxcopy
 
 all: $(TEST_PROGS)
 
-$(TEST_PROGS): ../harness.c
+$(TEST_PROGS): ../harness.c ../utils.c
 
 tm-syscall: tm-syscall-asm.S
 tm-syscall: CFLAGS += -mhtm -I../../../../../usr/include
diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
index 42d4c8caad81..8fde93d6021f 100644
--- a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
+++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
@@ -29,6 +29,7 @@
 #include <asm/tm.h>
 
 #include "utils.h"
+#include "tm.h"
 
 #define TBEGIN          ".long 0x7C00051D ;"
 #define TEND            ".long 0x7C00055D ;"
@@ -42,6 +43,8 @@ int test_body(void)
 {
 	uint64_t rv, dscr1 = 1, dscr2, texasr;
 
+	SKIP_IF(!have_htm());
+
 	printf("Check DSCR TM context switch: ");
 	fflush(stdout);
 	for (;;) {
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c b/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c
new file mode 100644
index 000000000000..d86653f282b1
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-msr-resv.c
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Test the kernel's signal return code to ensure that it doesn't
+ * crash when both the transactional and suspend MSR bits are set in
+ * the signal context.
+ *
+ * For this test, we send ourselves a SIGUSR1.  In the SIGUSR1 handler
+ * we modify the signal context to set both MSR TM S and T bits (which
+ * is "reserved" by the PowerISA). When we return from the signal
+ * handler (implicit sigreturn), the kernel should detect reserved MSR
+ * value and send us with a SIGSEGV.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include "utils.h"
+#include "tm.h"
+
+int segv_expected = 0;
+
+void signal_segv(int signum)
+{
+	if (segv_expected && (signum == SIGSEGV))
+		_exit(0);
+	_exit(1);
+}
+
+void signal_usr1(int signum, siginfo_t *info, void *uc)
+{
+	ucontext_t *ucp = uc;
+
+	/* Link tm checkpointed context to normal context */
+	ucp->uc_link = ucp;
+	/* Set all TM bits so that the context is now invalid */
+#ifdef __powerpc64__
+	ucp->uc_mcontext.gp_regs[PT_MSR] |= (7ULL << 32);
+#else
+	ucp->uc_mcontext.regs->gpr[PT_MSR] |= (7ULL);
+#endif
+	/* Should segv on return becuase of invalid context */
+	segv_expected = 1;
+}
+
+int tm_signal_msr_resv()
+{
+	struct sigaction act;
+
+	SKIP_IF(!have_htm());
+
+	act.sa_sigaction = signal_usr1;
+	sigemptyset(&act.sa_mask);
+	act.sa_flags = SA_SIGINFO;
+	if (sigaction(SIGUSR1, &act, NULL) < 0) {
+		perror("sigaction sigusr1");
+		exit(1);
+	}
+	if (signal(SIGSEGV, signal_segv) == SIG_ERR)
+		exit(1);
+
+	raise(SIGUSR1);
+
+	/* We shouldn't get here as we exit in the segv handler */
+	return 1;
+}
+
+int main(void)
+{
+	return test_harness(tm_signal_msr_resv, "tm_signal_msr_resv");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-stack.c b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
new file mode 100644
index 000000000000..e44a238c1d77
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-signal-stack.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Test the kernel's signal delievery code to ensure that we don't
+ * trelaim twice in the kernel signal delivery code.  This can happen
+ * if we trigger a signal when in a transaction and the stack pointer
+ * is bogus.
+ *
+ * This test case registers a SEGV handler, sets the stack pointer
+ * (r1) to NULL, starts a transaction and then generates a SEGV.  The
+ * SEGV should be handled but we exit here as the stack pointer is
+ * invalid and hance we can't sigreturn.  We only need to check that
+ * this flow doesn't crash the kernel.
+ */
+
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <signal.h>
+
+#include "utils.h"
+#include "tm.h"
+
+void signal_segv(int signum)
+{
+	/* This should never actually run since stack is foobar */
+	exit(1);
+}
+
+int tm_signal_stack()
+{
+	int pid;
+
+	SKIP_IF(!have_htm());
+
+	pid = fork();
+	if (pid < 0)
+		exit(1);
+
+	if (pid) { /* Parent */
+		/*
+		 * It's likely the whole machine will crash here so if
+		 * the child ever exits, we are good.
+		 */
+		wait(NULL);
+		return 0;
+	}
+
+	/*
+	 * The flow here is:
+	 * 1) register a signal handler (so signal delievery occurs)
+	 * 2) make stack pointer (r1) = NULL
+	 * 3) start transaction
+	 * 4) cause segv
+	 */
+	if (signal(SIGSEGV, signal_segv) == SIG_ERR)
+		exit(1);
+	asm volatile("li 1, 0 ;"		/* stack ptr == NULL */
+		     "1:"
+		     ".long 0x7C00051D ;"	/* tbegin */
+		     "beq 1b ;"			/* retry forever */
+		     ".long 0x7C0005DD ; ;"	/* tsuspend */
+		     "ld 2, 0(1) ;"		/* trigger segv" */
+		     : : : "memory");
+
+	/* This should never get here due to above segv */
+	return 1;
+}
+
+int main(void)
+{
+	return test_harness(tm_signal_stack, "tm_signal_stack");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c
index e835bf7ec7ae..60560cb20e38 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall.c
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c
@@ -13,12 +13,11 @@
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <asm/tm.h>
-#include <asm/cputable.h>
-#include <linux/auxvec.h>
 #include <sys/time.h>
 #include <stdlib.h>
 
 #include "utils.h"
+#include "tm.h"
 
 extern int getppid_tm_active(void);
 extern int getppid_tm_suspended(void);
@@ -77,16 +76,6 @@ pid_t getppid_tm(bool suspend)
 	exit(-1);
 }
 
-static inline bool have_htm_nosc(void)
-{
-#ifdef PPC_FEATURE2_HTM_NOSC
-	return ((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_HTM_NOSC);
-#else
-	printf("PPC_FEATURE2_HTM_NOSC not defined, can't check AT_HWCAP2\n");
-	return false;
-#endif
-}
-
 int tm_syscall(void)
 {
 	unsigned count = 0;
diff --git a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
new file mode 100644
index 000000000000..0274de7b11f3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
@@ -0,0 +1,103 @@
+/*
+ * Copyright 2015, Michael Neuling, IBM Corp.
+ * Licensed under GPLv2.
+ *
+ * Original: Michael Neuling 4/12/2013
+ * Edited: Rashmica Gupta 4/12/2015
+ *
+ * See if the altivec state is leaked out of an aborted transaction due to
+ * kernel vmx copy loops.
+ *
+ * When the transaction aborts, VSR values should rollback to the values
+ * they held before the transaction commenced. Using VSRs while transaction
+ * is suspended should not affect the checkpointed values.
+ *
+ * (1) write A to a VSR
+ * (2) start transaction
+ * (3) suspend transaction
+ * (4) change the VSR to B
+ * (5) trigger kernel vmx copy loop
+ * (6) abort transaction
+ * (7) check that the VSR value is A
+ */
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <string.h>
+#include <assert.h>
+
+#include "tm.h"
+#include "utils.h"
+
+int test_vmxcopy()
+{
+	long double vecin = 1.3;
+	long double vecout;
+	unsigned long pgsize = getpagesize();
+	int i;
+	int fd;
+	int size = pgsize*16;
+	char tmpfile[] = "/tmp/page_faultXXXXXX";
+	char buf[pgsize];
+	char *a;
+	uint64_t aborted = 0;
+
+	SKIP_IF(!have_htm());
+
+	fd = mkstemp(tmpfile);
+	assert(fd >= 0);
+
+	memset(buf, 0, pgsize);
+	for (i = 0; i < size; i += pgsize)
+		assert(write(fd, buf, pgsize) == pgsize);
+
+	unlink(tmpfile);
+
+	a = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0);
+	assert(a != MAP_FAILED);
+
+	asm __volatile__(
+		"lxvd2x 40,0,%[vecinptr];"	/* set 40 to initial value*/
+		"tbegin.;"
+		"beq	3f;"
+		"tsuspend.;"
+		"xxlxor 40,40,40;"		/* set 40 to 0 */
+		"std	5, 0(%[map]);"		/* cause kernel vmx copy page */
+		"tabort. 0;"
+		"tresume.;"
+		"tend.;"
+		"li	%[res], 0;"
+		"b	5f;"
+
+		/* Abort handler */
+		"3:;"
+		"li	%[res], 1;"
+
+		"5:;"
+		"stxvd2x 40,0,%[vecoutptr];"
+		: [res]"=r"(aborted)
+		: [vecinptr]"r"(&vecin),
+		  [vecoutptr]"r"(&vecout),
+		  [map]"r"(a)
+		: "memory", "r0", "r3", "r4", "r5", "r6", "r7");
+
+	if (aborted && (vecin != vecout)){
+		printf("FAILED: vector state leaked on abort %f != %f\n",
+		       (double)vecin, (double)vecout);
+		return 1;
+	}
+
+	munmap(a, size);
+
+	close(fd);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_vmxcopy, "tm_vmxcopy");
+}
diff --git a/tools/testing/selftests/powerpc/tm/tm.h b/tools/testing/selftests/powerpc/tm/tm.h
new file mode 100644
index 000000000000..24144b25772c
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2015, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#ifndef _SELFTESTS_POWERPC_TM_TM_H
+#define _SELFTESTS_POWERPC_TM_TM_H
+
+#include <stdbool.h>
+#include <asm/cputable.h>
+
+#include "../utils.h"
+
+static inline bool have_htm(void)
+{
+#ifdef PPC_FEATURE2_HTM
+	return have_hwcap2(PPC_FEATURE2_HTM);
+#else
+	printf("PPC_FEATURE2_HTM not defined, can't check AT_HWCAP2\n");
+	return false;
+#endif
+}
+
+static inline bool have_htm_nosc(void)
+{
+#ifdef PPC_FEATURE2_HTM_NOSC
+	return have_hwcap2(PPC_FEATURE2_HTM_NOSC);
+#else
+	printf("PPC_FEATURE2_HTM_NOSC not defined, can't check AT_HWCAP2\n");
+	return false;
+#endif
+}
+
+#endif /* _SELFTESTS_POWERPC_TM_TM_H */
diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c
new file mode 100644
index 000000000000..dcf74184bfd0
--- /dev/null
+++ b/tools/testing/selftests/powerpc/utils.c
@@ -0,0 +1,87 @@
+/*
+ * Copyright 2013-2015, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#define _GNU_SOURCE	/* For CPU_ZERO etc. */
+
+#include <elf.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <link.h>
+#include <sched.h>
+#include <stdio.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+static char auxv[4096];
+
+void *get_auxv_entry(int type)
+{
+	ElfW(auxv_t) *p;
+	void *result;
+	ssize_t num;
+	int fd;
+
+	fd = open("/proc/self/auxv", O_RDONLY);
+	if (fd == -1) {
+		perror("open");
+		return NULL;
+	}
+
+	result = NULL;
+
+	num = read(fd, auxv, sizeof(auxv));
+	if (num < 0) {
+		perror("read");
+		goto out;
+	}
+
+	if (num > sizeof(auxv)) {
+		printf("Overflowed auxv buffer\n");
+		goto out;
+	}
+
+	p = (ElfW(auxv_t) *)auxv;
+
+	while (p->a_type != AT_NULL) {
+		if (p->a_type == type) {
+			result = (void *)p->a_un.a_val;
+			break;
+		}
+
+		p++;
+	}
+out:
+	close(fd);
+	return result;
+}
+
+int pick_online_cpu(void)
+{
+	cpu_set_t mask;
+	int cpu;
+
+	CPU_ZERO(&mask);
+
+	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+		perror("sched_getaffinity");
+		return -1;
+	}
+
+	/* We prefer a primary thread, but skip 0 */
+	for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8)
+		if (CPU_ISSET(cpu, &mask))
+			return cpu;
+
+	/* Search for anything, but in reverse */
+	for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--)
+		if (CPU_ISSET(cpu, &mask))
+			return cpu;
+
+	printf("No cpus in affinity mask?!\n");
+	return -1;
+}
diff --git a/tools/testing/selftests/powerpc/utils.h b/tools/testing/selftests/powerpc/utils.h
index b7d41086bb0a..175ac6ad10dd 100644
--- a/tools/testing/selftests/powerpc/utils.h
+++ b/tools/testing/selftests/powerpc/utils.h
@@ -8,6 +8,7 @@
 
 #include <stdint.h>
 #include <stdbool.h>
+#include <linux/auxvec.h>
 
 /* Avoid headaches with PRI?64 - just use %ll? always */
 typedef unsigned long long u64;
@@ -21,6 +22,12 @@ typedef uint8_t u8;
 
 int test_harness(int (test_function)(void), char *name);
 extern void *get_auxv_entry(int type);
+int pick_online_cpu(void);
+
+static inline bool have_hwcap2(unsigned long ftr2)
+{
+	return ((unsigned long)get_auxv_entry(AT_HWCAP2) & ftr2) == ftr2;
+}
 
 /* Yes, this is evil */
 #define FAIL_IF(x)						\