Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

6 files changed, 944 insertions, 0 deletions

diff --git a/tools/testing/selftests/ptp/.gitignore b/tools/testing/selftests/ptp/.gitignore
new file mode 100644
index 000000000..534ca26ee
--- /dev/null
+++ b/tools/testing/selftests/ptp/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+testptp
diff --git a/tools/testing/selftests/ptp/Makefile b/tools/testing/selftests/ptp/Makefile
new file mode 100644
index 000000000..8f57f88ec
--- /dev/null
+++ b/tools/testing/selftests/ptp/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += $(KHDR_INCLUDES)
+TEST_GEN_PROGS := testptp
+LDLIBS += -lrt
+TEST_PROGS = phc.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/ptp/phc.sh b/tools/testing/selftests/ptp/phc.sh
new file mode 100755
index 000000000..9f61c1579
--- /dev/null
+++ b/tools/testing/selftests/ptp/phc.sh
@@ -0,0 +1,194 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	settime
+	adjtime
+	adjfreq
+"
+DEV=$1
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+##############################################################################
+# Sanity checks
+
+if [[ "$(id -u)" -ne 0 ]]; then
+	echo "SKIP: need root privileges"
+	exit $ksft_skip
+fi
+
+if [[ "$DEV" == "" ]]; then
+	echo "SKIP: PTP device not provided"
+	exit $ksft_skip
+fi
+
+require_command()
+{
+	local cmd=$1; shift
+
+	if [[ ! -x "$(command -v "$cmd")" ]]; then
+		echo "SKIP: $cmd not installed"
+		exit $ksft_skip
+	fi
+}
+
+phc_sanity()
+{
+	phc_ctl $DEV get &> /dev/null
+
+	if [ $? != 0 ]; then
+		echo "SKIP: unknown clock $DEV: No such device"
+		exit $ksft_skip
+	fi
+}
+
+require_command phc_ctl
+phc_sanity
+
+##############################################################################
+# Helpers
+
+# Exit status to return at the end. Set in case one of the tests fails.
+EXIT_STATUS=0
+PASS_COUNT=0
+# Per-test return value. Clear at the beginning of each test.
+RET=0
+
+check_err()
+{
+	local err=$1
+
+	if [[ $RET -eq 0 && $err -ne 0 ]]; then
+		RET=$err
+	fi
+}
+
+log_test()
+{
+	local test_name=$1
+
+	if [[ $RET -eq $ksft_skip ]]; then
+		printf "TEST: %-60s  [SKIP]\n" "$test_name"
+		return 0
+	fi
+
+	if [[ $RET -ne 0 ]]; then
+		EXIT_STATUS=1
+		printf "TEST: %-60s  [FAIL]\n" "$test_name"
+		return 1
+	fi
+
+	((PASS_COUNT++))
+	printf "TEST: %-60s  [ OK ]\n" "$test_name"
+	return 0
+}
+
+tests_run()
+{
+	local current_test
+
+	for current_test in ${TESTS:-$ALL_TESTS}; do
+		$current_test
+	done
+}
+
+##############################################################################
+# Tests
+
+settime_do()
+{
+	local res out
+
+	out=$(LC_ALL=C phc_ctl $DEV set 0 wait 120.5 get 2>&1)
+	if [[ $? -ne 0 ]]; then
+		if echo "$out" | grep -qi "Operation not supported"; then
+			return $ksft_skip
+		fi
+		return 1
+	fi
+	res=$(echo "$out" | awk '/clock time is/{print $5}' | awk -F. '{print $1}')
+
+	(( res == 120 ))
+}
+
+adjtime_do()
+{
+	local res out
+
+	out=$(LC_ALL=C phc_ctl $DEV set 0 adj 10 get 2>&1)
+	if [[ $? -ne 0 ]]; then
+		if echo "$out" | grep -qi "Operation not supported"; then
+			return $ksft_skip
+		fi
+		return 1
+	fi
+	res=$(echo "$out" | awk '/clock time is/{print $5}' | awk -F. '{print $1}')
+
+	(( res == 10 ))
+}
+
+adjfreq_do()
+{
+	local res out
+
+	# Set the clock to be 1% faster
+	out=$(LC_ALL=C phc_ctl $DEV freq 10000000 set 0 wait 100.5 get 2>&1)
+	if [[ $? -ne 0 ]]; then
+		if echo "$out" | grep -qi "Operation not supported"; then
+			return $ksft_skip
+		fi
+		return 1
+	fi
+	res=$(echo "$out" | awk '/clock time is/{print $5}' | awk -F. '{print $1}')
+
+	(( res == 101 ))
+}
+
+##############################################################################
+
+cleanup()
+{
+	phc_ctl $DEV freq 0.0 &> /dev/null
+	phc_ctl $DEV set &> /dev/null
+}
+
+settime()
+{
+	RET=0
+
+	settime_do
+	check_err $?
+	log_test "settime"
+	cleanup
+}
+
+adjtime()
+{
+	RET=0
+
+	adjtime_do
+	check_err $?
+	log_test "adjtime"
+	cleanup
+}
+
+adjfreq()
+{
+	RET=0
+
+	adjfreq_do
+	check_err $?
+	log_test "adjfreq"
+	cleanup
+}
+
+trap cleanup EXIT
+
+tests_run
+
+if [[ $EXIT_STATUS -eq 0 && $PASS_COUNT -eq 0 ]]; then
+	exit $ksft_skip
+fi
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/ptp/ptpchmaskfmt.sh b/tools/testing/selftests/ptp/ptpchmaskfmt.sh
new file mode 100644
index 000000000..0a06ba8af
--- /dev/null
+++ b/tools/testing/selftests/ptp/ptpchmaskfmt.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Simple helper script to transform ptp debugfs timestamp event queue filtering
+# masks from decimal values to hexadecimal values
+
+# Only takes the debugfs mask file path as an argument
+DEBUGFS_MASKFILE="${1}"
+
+#shellcheck disable=SC2013,SC2086
+for int in $(cat "$DEBUGFS_MASKFILE") ; do
+    printf '0x%08X ' "$int"
+done
+echo
diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
new file mode 100644
index 000000000..ed1e2886b
--- /dev/null
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -0,0 +1,694 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PTP 1588 clock support - User space test program
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ */
+#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__        /* For PPC64, to get LL64 types */
+#include <errno.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <math.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/timex.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <linux/ptp_clock.h>
+
+#define DEVICE "/dev/ptp0"
+
+#ifndef ADJ_SETOFFSET
+#define ADJ_SETOFFSET 0x0100
+#endif
+
+#ifndef CLOCK_INVALID
+#define CLOCK_INVALID -1
+#endif
+
+#define NSEC_PER_SEC 1000000000LL
+
+/* clock_adjtime is not available in GLIBC < 2.14 */
+#if !__GLIBC_PREREQ(2, 14)
+#include <sys/syscall.h>
+static int clock_adjtime(clockid_t id, struct timex *tx)
+{
+	return syscall(__NR_clock_adjtime, id, tx);
+}
+#endif
+
+static void show_flag_test(int rq_index, unsigned int flags, int err)
+{
+	printf("PTP_EXTTS_REQUEST%c flags 0x%08x : (%d) %s\n",
+	       rq_index ? '1' + rq_index : ' ',
+	       flags, err, strerror(errno));
+	/* sigh, uClibc ... */
+	errno = 0;
+}
+
+static void do_flag_test(int fd, unsigned int index)
+{
+	struct ptp_extts_request extts_request;
+	unsigned long request[2] = {
+		PTP_EXTTS_REQUEST,
+		PTP_EXTTS_REQUEST2,
+	};
+	unsigned int enable_flags[5] = {
+		PTP_ENABLE_FEATURE,
+		PTP_ENABLE_FEATURE | PTP_RISING_EDGE,
+		PTP_ENABLE_FEATURE | PTP_FALLING_EDGE,
+		PTP_ENABLE_FEATURE | PTP_RISING_EDGE | PTP_FALLING_EDGE,
+		PTP_ENABLE_FEATURE | (PTP_EXTTS_VALID_FLAGS + 1),
+	};
+	int err, i, j;
+
+	memset(&extts_request, 0, sizeof(extts_request));
+	extts_request.index = index;
+
+	for (i = 0; i < 2; i++) {
+		for (j = 0; j < 5; j++) {
+			extts_request.flags = enable_flags[j];
+			err = ioctl(fd, request[i], &extts_request);
+			show_flag_test(i, extts_request.flags, err);
+
+			extts_request.flags = 0;
+			err = ioctl(fd, request[i], &extts_request);
+		}
+	}
+}
+
+static clockid_t get_clockid(int fd)
+{
+#define CLOCKFD 3
+	return (((unsigned int) ~fd) << 3) | CLOCKFD;
+}
+
+static long ppb_to_scaled_ppm(int ppb)
+{
+	/*
+	 * The 'freq' field in the 'struct timex' is in parts per
+	 * million, but with a 16 bit binary fractional field.
+	 * Instead of calculating either one of
+	 *
+	 *    scaled_ppm = (ppb / 1000) << 16  [1]
+	 *    scaled_ppm = (ppb << 16) / 1000  [2]
+	 *
+	 * we simply use double precision math, in order to avoid the
+	 * truncation in [1] and the possible overflow in [2].
+	 */
+	return (long) (ppb * 65.536);
+}
+
+static int64_t pctns(struct ptp_clock_time *t)
+{
+	return t->sec * NSEC_PER_SEC + t->nsec;
+}
+
+static void usage(char *progname)
+{
+	fprintf(stderr,
+		"usage: %s [options]\n"
+		" -c         query the ptp clock's capabilities\n"
+		" -d name    device to open\n"
+		" -e val     read 'val' external time stamp events\n"
+		" -E val     enable rising (1), falling (2), or both (3) edges\n"
+		" -f val     adjust the ptp clock frequency by 'val' ppb\n"
+		" -F chan    Enable single channel mask and keep device open for debugfs verification.\n"
+		" -g         get the ptp clock time\n"
+		" -h         prints this message\n"
+		" -i val     index for event/trigger\n"
+		" -k val     measure the time offset between system and phc clock\n"
+		"            for 'val' times (Maximum 25)\n"
+		" -l         list the current pin configuration\n"
+		" -L pin,val configure pin index 'pin' with function 'val'\n"
+		"            the channel index is taken from the '-i' option\n"
+		"            'val' specifies the auxiliary function:\n"
+		"            0 - none\n"
+		"            1 - external time stamp\n"
+		"            2 - periodic output\n"
+		" -n val     shift the ptp clock time by 'val' nanoseconds\n"
+		" -o val     phase offset (in nanoseconds) to be provided to the PHC servo\n"
+		" -p val     enable output with a period of 'val' nanoseconds\n"
+		" -H val     set output phase to 'val' nanoseconds (requires -p)\n"
+		" -w val     set output pulse width to 'val' nanoseconds (requires -p)\n"
+		" -P val     enable or disable (val=1|0) the system clock PPS\n"
+		" -r         open the ptp clock in readonly mode\n"
+		" -s         set the ptp clock time from the system time\n"
+		" -S         set the system time from the ptp clock time\n"
+		" -t val     shift the ptp clock time by 'val' seconds\n"
+		" -T val     set the ptp clock time to 'val' seconds\n"
+		" -x val     get an extended ptp clock time with the desired number of samples (up to %d)\n"
+		" -X         get a ptp clock cross timestamp\n"
+		" -y val     pre/post tstamp timebase to use {realtime|monotonic|monotonic-raw}\n"
+		" -z         test combinations of rising/falling external time stamp flags\n",
+		progname, PTP_MAX_SAMPLES);
+}
+
+int main(int argc, char *argv[])
+{
+	struct ptp_clock_caps caps;
+	struct ptp_extts_event event;
+	struct ptp_extts_request extts_request;
+	struct ptp_perout_request perout_request;
+	struct ptp_pin_desc desc;
+	struct timespec ts;
+	struct timex tx;
+	struct ptp_clock_time *pct;
+	struct ptp_sys_offset *sysoff;
+	struct ptp_sys_offset_extended *soe;
+	struct ptp_sys_offset_precise *xts;
+
+	char *progname;
+	unsigned int i;
+	int c, cnt, fd;
+
+	char *device = DEVICE;
+	clockid_t clkid;
+	int adjfreq = 0x7fffffff;
+	int adjtime = 0;
+	int adjns = 0;
+	int adjphase = 0;
+	int capabilities = 0;
+	int extts = 0;
+	int edge = 0;
+	int flagtest = 0;
+	int gettime = 0;
+	int index = 0;
+	int list_pins = 0;
+	int pct_offset = 0;
+	int getextended = 0;
+	int getcross = 0;
+	int n_samples = 0;
+	int pin_index = -1, pin_func;
+	int pps = -1;
+	int seconds = 0;
+	int readonly = 0;
+	int settime = 0;
+	int channel = -1;
+	clockid_t ext_clockid = CLOCK_REALTIME;
+
+	int64_t t1, t2, tp;
+	int64_t interval, offset;
+	int64_t perout_phase = -1;
+	int64_t pulsewidth = -1;
+	int64_t perout = -1;
+
+	progname = strrchr(argv[0], '/');
+	progname = progname ? 1+progname : argv[0];
+	while (EOF != (c = getopt(argc, argv, "cd:e:E:f:F:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xy:z"))) {
+		switch (c) {
+		case 'c':
+			capabilities = 1;
+			break;
+		case 'd':
+			device = optarg;
+			break;
+		case 'e':
+			extts = atoi(optarg);
+			break;
+		case 'E':
+			edge = atoi(optarg);
+			edge = (edge & 1 ? PTP_RISING_EDGE : 0) |
+				(edge & 2 ? PTP_FALLING_EDGE : 0);
+			break;
+		case 'f':
+			adjfreq = atoi(optarg);
+			break;
+		case 'F':
+			channel = atoi(optarg);
+			break;
+		case 'g':
+			gettime = 1;
+			break;
+		case 'H':
+			perout_phase = atoll(optarg);
+			break;
+		case 'i':
+			index = atoi(optarg);
+			break;
+		case 'k':
+			pct_offset = 1;
+			n_samples = atoi(optarg);
+			break;
+		case 'l':
+			list_pins = 1;
+			break;
+		case 'L':
+			cnt = sscanf(optarg, "%d,%d", &pin_index, &pin_func);
+			if (cnt != 2) {
+				usage(progname);
+				return -1;
+			}
+			break;
+		case 'n':
+			adjns = atoi(optarg);
+			break;
+		case 'o':
+			adjphase = atoi(optarg);
+			break;
+		case 'p':
+			perout = atoll(optarg);
+			break;
+		case 'P':
+			pps = atoi(optarg);
+			break;
+		case 'r':
+			readonly = 1;
+			break;
+		case 's':
+			settime = 1;
+			break;
+		case 'S':
+			settime = 2;
+			break;
+		case 't':
+			adjtime = atoi(optarg);
+			break;
+		case 'T':
+			settime = 3;
+			seconds = atoi(optarg);
+			break;
+		case 'w':
+			pulsewidth = atoi(optarg);
+			break;
+		case 'x':
+			getextended = atoi(optarg);
+			if (getextended < 1 || getextended > PTP_MAX_SAMPLES) {
+				fprintf(stderr,
+					"number of extended timestamp samples must be between 1 and %d; was asked for %d\n",
+					PTP_MAX_SAMPLES, getextended);
+				return -1;
+			}
+			break;
+		case 'X':
+			getcross = 1;
+			break;
+		case 'y':
+			if (!strcasecmp(optarg, "realtime"))
+				ext_clockid = CLOCK_REALTIME;
+			else if (!strcasecmp(optarg, "monotonic"))
+				ext_clockid = CLOCK_MONOTONIC;
+			else if (!strcasecmp(optarg, "monotonic-raw"))
+				ext_clockid = CLOCK_MONOTONIC_RAW;
+			else {
+				fprintf(stderr,
+					"type needs to be realtime, monotonic or monotonic-raw; was given %s\n",
+					optarg);
+				return -1;
+			}
+			break;
+
+		case 'z':
+			flagtest = 1;
+			break;
+		case 'h':
+			usage(progname);
+			return 0;
+		case '?':
+		default:
+			usage(progname);
+			return -1;
+		}
+	}
+
+	fd = open(device, readonly ? O_RDONLY : O_RDWR);
+	if (fd < 0) {
+		fprintf(stderr, "opening %s: %s\n", device, strerror(errno));
+		return -1;
+	}
+
+	clkid = get_clockid(fd);
+	if (CLOCK_INVALID == clkid) {
+		fprintf(stderr, "failed to read clock id\n");
+		return -1;
+	}
+
+	if (capabilities) {
+		if (ioctl(fd, PTP_CLOCK_GETCAPS, &caps)) {
+			perror("PTP_CLOCK_GETCAPS");
+		} else {
+			printf("capabilities:\n"
+			       "  %d maximum frequency adjustment (ppb)\n"
+			       "  %d programmable alarms\n"
+			       "  %d external time stamp channels\n"
+			       "  %d programmable periodic signals\n"
+			       "  %d pulse per second\n"
+			       "  %d programmable pins\n"
+			       "  %d cross timestamping\n"
+			       "  %d adjust_phase\n"
+			       "  %d maximum phase adjustment (ns)\n",
+			       caps.max_adj,
+			       caps.n_alarm,
+			       caps.n_ext_ts,
+			       caps.n_per_out,
+			       caps.pps,
+			       caps.n_pins,
+			       caps.cross_timestamping,
+			       caps.adjust_phase,
+			       caps.max_phase_adj);
+		}
+	}
+
+	if (0x7fffffff != adjfreq) {
+		memset(&tx, 0, sizeof(tx));
+		tx.modes = ADJ_FREQUENCY;
+		tx.freq = ppb_to_scaled_ppm(adjfreq);
+		if (clock_adjtime(clkid, &tx)) {
+			perror("clock_adjtime");
+		} else {
+			puts("frequency adjustment okay");
+		}
+	}
+
+	if (adjtime || adjns) {
+		memset(&tx, 0, sizeof(tx));
+		tx.modes = ADJ_SETOFFSET | ADJ_NANO;
+		tx.time.tv_sec = adjtime;
+		tx.time.tv_usec = adjns;
+		while (tx.time.tv_usec < 0) {
+			tx.time.tv_sec  -= 1;
+			tx.time.tv_usec += NSEC_PER_SEC;
+		}
+
+		if (clock_adjtime(clkid, &tx) < 0) {
+			perror("clock_adjtime");
+		} else {
+			puts("time shift okay");
+		}
+	}
+
+	if (adjphase) {
+		memset(&tx, 0, sizeof(tx));
+		tx.modes = ADJ_OFFSET | ADJ_NANO;
+		tx.offset = adjphase;
+
+		if (clock_adjtime(clkid, &tx) < 0) {
+			perror("clock_adjtime");
+		} else {
+			puts("phase adjustment okay");
+		}
+	}
+
+	if (gettime) {
+		if (clock_gettime(clkid, &ts)) {
+			perror("clock_gettime");
+		} else {
+			printf("clock time: %ld.%09ld or %s",
+			       ts.tv_sec, ts.tv_nsec, ctime(&ts.tv_sec));
+		}
+	}
+
+	if (settime == 1) {
+		clock_gettime(CLOCK_REALTIME, &ts);
+		if (clock_settime(clkid, &ts)) {
+			perror("clock_settime");
+		} else {
+			puts("set time okay");
+		}
+	}
+
+	if (settime == 2) {
+		clock_gettime(clkid, &ts);
+		if (clock_settime(CLOCK_REALTIME, &ts)) {
+			perror("clock_settime");
+		} else {
+			puts("set time okay");
+		}
+	}
+
+	if (settime == 3) {
+		ts.tv_sec = seconds;
+		ts.tv_nsec = 0;
+		if (clock_settime(clkid, &ts)) {
+			perror("clock_settime");
+		} else {
+			puts("set time okay");
+		}
+	}
+
+	if (pin_index >= 0) {
+		memset(&desc, 0, sizeof(desc));
+		desc.index = pin_index;
+		desc.func = pin_func;
+		desc.chan = index;
+		if (ioctl(fd, PTP_PIN_SETFUNC, &desc)) {
+			perror("PTP_PIN_SETFUNC");
+		} else {
+			puts("set pin function okay");
+		}
+	}
+
+	if (extts) {
+		if (!readonly) {
+			memset(&extts_request, 0, sizeof(extts_request));
+			extts_request.index = index;
+			extts_request.flags = PTP_ENABLE_FEATURE | edge;
+			if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
+				perror("PTP_EXTTS_REQUEST");
+				extts = 0;
+			} else {
+				puts("external time stamp request okay");
+			}
+		}
+		for (; extts; extts--) {
+			cnt = read(fd, &event, sizeof(event));
+			if (cnt != sizeof(event)) {
+				perror("read");
+				break;
+			}
+			printf("event index %u at %lld.%09u\n", event.index,
+			       event.t.sec, event.t.nsec);
+			fflush(stdout);
+		}
+		if (!readonly) {
+			/* Disable the feature again. */
+			extts_request.flags = 0;
+			if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
+				perror("PTP_EXTTS_REQUEST");
+			}
+		}
+	}
+
+	if (flagtest) {
+		do_flag_test(fd, index);
+	}
+
+	if (list_pins) {
+		int n_pins = 0;
+		if (ioctl(fd, PTP_CLOCK_GETCAPS, &caps)) {
+			perror("PTP_CLOCK_GETCAPS");
+		} else {
+			n_pins = caps.n_pins;
+		}
+		for (i = 0; i < n_pins; i++) {
+			desc.index = i;
+			if (ioctl(fd, PTP_PIN_GETFUNC, &desc)) {
+				perror("PTP_PIN_GETFUNC");
+				break;
+			}
+			printf("name %s index %u func %u chan %u\n",
+			       desc.name, desc.index, desc.func, desc.chan);
+		}
+	}
+
+	if (pulsewidth >= 0 && perout < 0) {
+		puts("-w can only be specified together with -p");
+		return -1;
+	}
+
+	if (perout_phase >= 0 && perout < 0) {
+		puts("-H can only be specified together with -p");
+		return -1;
+	}
+
+	if (perout >= 0) {
+		if (clock_gettime(clkid, &ts)) {
+			perror("clock_gettime");
+			return -1;
+		}
+		memset(&perout_request, 0, sizeof(perout_request));
+		perout_request.index = index;
+		perout_request.period.sec = perout / NSEC_PER_SEC;
+		perout_request.period.nsec = perout % NSEC_PER_SEC;
+		perout_request.flags = 0;
+		if (pulsewidth >= 0) {
+			perout_request.flags |= PTP_PEROUT_DUTY_CYCLE;
+			perout_request.on.sec = pulsewidth / NSEC_PER_SEC;
+			perout_request.on.nsec = pulsewidth % NSEC_PER_SEC;
+		}
+		if (perout_phase >= 0) {
+			perout_request.flags |= PTP_PEROUT_PHASE;
+			perout_request.phase.sec = perout_phase / NSEC_PER_SEC;
+			perout_request.phase.nsec = perout_phase % NSEC_PER_SEC;
+		} else {
+			perout_request.start.sec = ts.tv_sec + 2;
+			perout_request.start.nsec = 0;
+		}
+
+		if (ioctl(fd, PTP_PEROUT_REQUEST2, &perout_request)) {
+			perror("PTP_PEROUT_REQUEST");
+		} else {
+			puts("periodic output request okay");
+		}
+	}
+
+	if (pps != -1) {
+		int enable = pps ? 1 : 0;
+		if (ioctl(fd, PTP_ENABLE_PPS, enable)) {
+			perror("PTP_ENABLE_PPS");
+		} else {
+			puts("pps for system time request okay");
+		}
+	}
+
+	if (pct_offset) {
+		if (n_samples <= 0 || n_samples > 25) {
+			puts("n_samples should be between 1 and 25");
+			usage(progname);
+			return -1;
+		}
+
+		sysoff = calloc(1, sizeof(*sysoff));
+		if (!sysoff) {
+			perror("calloc");
+			return -1;
+		}
+		sysoff->n_samples = n_samples;
+
+		if (ioctl(fd, PTP_SYS_OFFSET, sysoff))
+			perror("PTP_SYS_OFFSET");
+		else
+			puts("system and phc clock time offset request okay");
+
+		pct = &sysoff->ts[0];
+		for (i = 0; i < sysoff->n_samples; i++) {
+			t1 = pctns(pct+2*i);
+			tp = pctns(pct+2*i+1);
+			t2 = pctns(pct+2*i+2);
+			interval = t2 - t1;
+			offset = (t2 + t1) / 2 - tp;
+
+			printf("system time: %lld.%09u\n",
+				(pct+2*i)->sec, (pct+2*i)->nsec);
+			printf("phc    time: %lld.%09u\n",
+				(pct+2*i+1)->sec, (pct+2*i+1)->nsec);
+			printf("system time: %lld.%09u\n",
+				(pct+2*i+2)->sec, (pct+2*i+2)->nsec);
+			printf("system/phc clock time offset is %" PRId64 " ns\n"
+			       "system     clock time delay  is %" PRId64 " ns\n",
+				offset, interval);
+		}
+
+		free(sysoff);
+	}
+
+	if (getextended) {
+		soe = calloc(1, sizeof(*soe));
+		if (!soe) {
+			perror("calloc");
+			return -1;
+		}
+
+		soe->n_samples = getextended;
+		soe->clockid = ext_clockid;
+
+		if (ioctl(fd, PTP_SYS_OFFSET_EXTENDED, soe)) {
+			perror("PTP_SYS_OFFSET_EXTENDED");
+		} else {
+			printf("extended timestamp request returned %d samples\n",
+			       getextended);
+
+			for (i = 0; i < getextended; i++) {
+				switch (ext_clockid) {
+				case CLOCK_REALTIME:
+					printf("sample #%2d: real time before: %lld.%09u\n",
+					       i, soe->ts[i][0].sec,
+					       soe->ts[i][0].nsec);
+					break;
+				case CLOCK_MONOTONIC:
+					printf("sample #%2d: monotonic time before: %lld.%09u\n",
+					       i, soe->ts[i][0].sec,
+					       soe->ts[i][0].nsec);
+					break;
+				case CLOCK_MONOTONIC_RAW:
+					printf("sample #%2d: monotonic-raw time before: %lld.%09u\n",
+					       i, soe->ts[i][0].sec,
+					       soe->ts[i][0].nsec);
+					break;
+				default:
+					break;
+				}
+				printf("            phc time: %lld.%09u\n",
+				       soe->ts[i][1].sec, soe->ts[i][1].nsec);
+				switch (ext_clockid) {
+				case CLOCK_REALTIME:
+					printf("            real time after: %lld.%09u\n",
+					       soe->ts[i][2].sec,
+					       soe->ts[i][2].nsec);
+					break;
+				case CLOCK_MONOTONIC:
+					printf("            monotonic time after: %lld.%09u\n",
+					       soe->ts[i][2].sec,
+					       soe->ts[i][2].nsec);
+					break;
+				case CLOCK_MONOTONIC_RAW:
+					printf("            monotonic-raw time after: %lld.%09u\n",
+					       soe->ts[i][2].sec,
+					       soe->ts[i][2].nsec);
+					break;
+				default:
+					break;
+				}
+			}
+		}
+
+		free(soe);
+	}
+
+	if (getcross) {
+		xts = calloc(1, sizeof(*xts));
+		if (!xts) {
+			perror("calloc");
+			return -1;
+		}
+
+		if (ioctl(fd, PTP_SYS_OFFSET_PRECISE, xts)) {
+			perror("PTP_SYS_OFFSET_PRECISE");
+		} else {
+			puts("system and phc crosstimestamping request okay");
+
+			printf("device time: %lld.%09u\n",
+			       xts->device.sec, xts->device.nsec);
+			printf("system time: %lld.%09u\n",
+			       xts->sys_realtime.sec, xts->sys_realtime.nsec);
+			printf("monoraw time: %lld.%09u\n",
+			       xts->sys_monoraw.sec, xts->sys_monoraw.nsec);
+		}
+
+		free(xts);
+	}
+
+	if (channel >= 0) {
+		if (ioctl(fd, PTP_MASK_CLEAR_ALL)) {
+			perror("PTP_MASK_CLEAR_ALL");
+		} else if (ioctl(fd, PTP_MASK_EN_SINGLE, (unsigned int *)&channel)) {
+			perror("PTP_MASK_EN_SINGLE");
+		} else {
+			printf("Channel %d exclusively enabled. Check on debugfs.\n", channel);
+			printf("Press any key to continue\n.");
+			getchar();
+		}
+	}
+
+	close(fd);
+	return 0;
+}
diff --git a/tools/testing/selftests/ptp/testptp.mk b/tools/testing/selftests/ptp/testptp.mk
new file mode 100644
index 000000000..4ef2d9755
--- /dev/null
+++ b/tools/testing/selftests/ptp/testptp.mk
@@ -0,0 +1,33 @@
+# PTP 1588 clock support - User space test program
+#
+# Copyright (C) 2010 OMICRON electronics GmbH
+#
+#  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 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.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with this program; if not, write to the Free Software
+#  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+CC        = $(CROSS_COMPILE)gcc
+INC       = -I$(KBUILD_OUTPUT)/usr/include
+CFLAGS    = -Wall $(INC)
+LDLIBS    = -lrt
+PROGS     = testptp
+
+all: $(PROGS)
+
+testptp: testptp.o
+
+clean:
+	rm -f testptp.o
+
+distclean: clean
+	rm -f $(PROGS)