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
  ...

1 files changed, 311 insertions, 0 deletions

diff --git a/Documentation/driver-api/pps.rst b/Documentation/driver-api/pps.rst
new file mode 100644
index 000000000..598729f9c
--- /dev/null
+++ b/Documentation/driver-api/pps.rst
@@ -0,0 +1,311 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================
+PPS - Pulse Per Second
+======================
+
+Copyright (C) 2007 Rodolfo Giometti <giometti@enneenne.com>
+
+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.
+
+
+
+Overview
+--------
+
+LinuxPPS provides a programming interface (API) to define in the
+system several PPS sources.
+
+PPS means "pulse per second" and a PPS source is just a device which
+provides a high precision signal each second so that an application
+can use it to adjust system clock time.
+
+A PPS source can be connected to a serial port (usually to the Data
+Carrier Detect pin) or to a parallel port (ACK-pin) or to a special
+CPU's GPIOs (this is the common case in embedded systems) but in each
+case when a new pulse arrives the system must apply to it a timestamp
+and record it for userland.
+
+Common use is the combination of the NTPD as userland program, with a
+GPS receiver as PPS source, to obtain a wallclock-time with
+sub-millisecond synchronisation to UTC.
+
+
+RFC considerations
+------------------
+
+While implementing a PPS API as RFC 2783 defines and using an embedded
+CPU GPIO-Pin as physical link to the signal, I encountered a deeper
+problem:
+
+   At startup it needs a file descriptor as argument for the function
+   time_pps_create().
+
+This implies that the source has a /dev/... entry. This assumption is
+OK for the serial and parallel port, where you can do something
+useful besides(!) the gathering of timestamps as it is the central
+task for a PPS API. But this assumption does not work for a single
+purpose GPIO line. In this case even basic file-related functionality
+(like read() and write()) makes no sense at all and should not be a
+precondition for the use of a PPS API.
+
+The problem can be simply solved if you consider that a PPS source is
+not always connected with a GPS data source.
+
+So your programs should check if the GPS data source (the serial port
+for instance) is a PPS source too, and if not they should provide the
+possibility to open another device as PPS source.
+
+In LinuxPPS the PPS sources are simply char devices usually mapped
+into files /dev/pps0, /dev/pps1, etc.
+
+
+PPS with USB to serial devices
+------------------------------
+
+It is possible to grab the PPS from an USB to serial device. However,
+you should take into account the latencies and jitter introduced by
+the USB stack. Users have reported clock instability around +-1ms when
+synchronized with PPS through USB. With USB 2.0, jitter may decrease
+down to the order of 125 microseconds.
+
+This may be suitable for time server synchronization with NTP because
+of its undersampling and algorithms.
+
+If your device doesn't report PPS, you can check that the feature is
+supported by its driver. Most of the time, you only need to add a call
+to usb_serial_handle_dcd_change after checking the DCD status (see
+ch341 and pl2303 examples).
+
+
+Coding example
+--------------
+
+To register a PPS source into the kernel you should define a struct
+pps_source_info as follows::
+
+    static struct pps_source_info pps_ktimer_info = {
+	    .name         = "ktimer",
+	    .path         = "",
+	    .mode         = PPS_CAPTUREASSERT | PPS_OFFSETASSERT |
+			    PPS_ECHOASSERT |
+			    PPS_CANWAIT | PPS_TSFMT_TSPEC,
+	    .echo         = pps_ktimer_echo,
+	    .owner        = THIS_MODULE,
+    };
+
+and then calling the function pps_register_source() in your
+initialization routine as follows::
+
+    source = pps_register_source(&pps_ktimer_info,
+			PPS_CAPTUREASSERT | PPS_OFFSETASSERT);
+
+The pps_register_source() prototype is::
+
+  int pps_register_source(struct pps_source_info *info, int default_params)
+
+where "info" is a pointer to a structure that describes a particular
+PPS source, "default_params" tells the system what the initial default
+parameters for the device should be (it is obvious that these parameters
+must be a subset of ones defined in the struct
+pps_source_info which describe the capabilities of the driver).
+
+Once you have registered a new PPS source into the system you can
+signal an assert event (for example in the interrupt handler routine)
+just using::
+
+    pps_event(source, &ts, PPS_CAPTUREASSERT, ptr)
+
+where "ts" is the event's timestamp.
+
+The same function may also run the defined echo function
+(pps_ktimer_echo(), passing to it the "ptr" pointer) if the user
+asked for that... etc..
+
+Please see the file drivers/pps/clients/pps-ktimer.c for example code.
+
+
+SYSFS support
+-------------
+
+If the SYSFS filesystem is enabled in the kernel it provides a new class::
+
+   $ ls /sys/class/pps/
+   pps0/  pps1/  pps2/
+
+Every directory is the ID of a PPS sources defined in the system and
+inside you find several files::
+
+   $ ls -F /sys/class/pps/pps0/
+   assert     dev        mode       path       subsystem@
+   clear      echo       name       power/     uevent
+
+
+Inside each "assert" and "clear" file you can find the timestamp and a
+sequence number::
+
+   $ cat /sys/class/pps/pps0/assert
+   1170026870.983207967#8
+
+Where before the "#" is the timestamp in seconds; after it is the
+sequence number. Other files are:
+
+ * echo: reports if the PPS source has an echo function or not;
+
+ * mode: reports available PPS functioning modes;
+
+ * name: reports the PPS source's name;
+
+ * path: reports the PPS source's device path, that is the device the
+   PPS source is connected to (if it exists).
+
+
+Testing the PPS support
+-----------------------
+
+In order to test the PPS support even without specific hardware you can use
+the pps-ktimer driver (see the client subsection in the PPS configuration menu)
+and the userland tools available in your distribution's pps-tools package,
+http://linuxpps.org , or https://github.com/redlab-i/pps-tools.
+
+Once you have enabled the compilation of pps-ktimer just modprobe it (if
+not statically compiled)::
+
+   # modprobe pps-ktimer
+
+and the run ppstest as follow::
+
+   $ ./ppstest /dev/pps1
+   trying PPS source "/dev/pps1"
+   found PPS source "/dev/pps1"
+   ok, found 1 source(s), now start fetching data...
+   source 0 - assert 1186592699.388832443, sequence: 364 - clear  0.000000000, sequence: 0
+   source 0 - assert 1186592700.388931295, sequence: 365 - clear  0.000000000, sequence: 0
+   source 0 - assert 1186592701.389032765, sequence: 366 - clear  0.000000000, sequence: 0
+
+Please note that to compile userland programs, you need the file timepps.h.
+This is available in the pps-tools repository mentioned above.
+
+
+Generators
+----------
+
+Sometimes one needs to be able not only to catch PPS signals but to produce
+them also. For example, running a distributed simulation, which requires
+computers' clock to be synchronized very tightly.
+
+To do so the class pps-gen has been added. PPS generators can be
+registered in the kernel by defining a struct pps_gen_source_info as
+follows::
+
+    static const struct pps_gen_source_info pps_gen_dummy_info = {
+            .use_system_clock       = true,
+            .get_time               = pps_gen_dummy_get_time,
+            .enable                 = pps_gen_dummy_enable,
+    };
+
+Where the use_system_clock states if the generator uses the system
+clock to generate its pulses, or they are from a peripheral device
+clock. Method get_time() is used to query the time stored into the
+generator clock, while the method enable() is used to enable or
+disable the PPS pulse generation.
+
+Then calling the function pps_gen_register_source() in your
+initialization routine as follows creates a new generator in the
+system::
+
+    pps_gen = pps_gen_register_source(&pps_gen_dummy_info);
+
+Generators SYSFS support
+------------------------
+
+If the SYSFS filesystem is enabled in the kernel it provides a new class::
+
+    $ ls /sys/class/pps-gen/
+    pps-gen0/  pps-gen1/  pps-gen2/
+
+Every directory is the ID of a PPS generator defined in the system and
+inside of it you find several files::
+
+    $ ls -F /sys/class/pps-gen/pps-gen0/
+    dev  enable  name  power/  subsystem@  system  time  uevent
+
+To enable the PPS signal generation you can use the command below::
+
+    $ echo 1 > /sys/class/pps-gen/pps-gen0/enable
+
+Parallel port generator
+------------------------
+
+One way to do this is to invent some complicated hardware solutions but it
+may be neither necessary nor affordable. The cheap way is to load a PPS
+generator on one of the computers (master) and PPS clients on others
+(slaves), and use very simple cables to deliver signals using parallel
+ports, for example.
+
+Parallel port cable pinout::
+
+	pin	name	master      slave
+	1	STROBE	  *------     *
+	2	D0	  *     |     *
+	3	D1	  *     |     *
+	4	D2	  *     |     *
+	5	D3	  *     |     *
+	6	D4	  *     |     *
+	7	D5	  *     |     *
+	8	D6	  *     |     *
+	9	D7	  *     |     *
+	10	ACK	  *     ------*
+	11	BUSY	  *           *
+	12	PE	  *           *
+	13	SEL	  *           *
+	14	AUTOFD	  *           *
+	15	ERROR	  *           *
+	16	INIT	  *           *
+	17	SELIN	  *           *
+	18-25	GND	  *-----------*
+
+Please note that parallel port interrupt occurs only on high->low transition,
+so it is used for PPS assert edge. PPS clear edge can be determined only
+using polling in the interrupt handler which actually can be done way more
+precisely because interrupt handling delays can be quite big and random. So
+current parport PPS generator implementation (pps_gen_parport module) is
+geared towards using the clear edge for time synchronization.
+
+Clear edge polling is done with disabled interrupts so it's better to select
+delay between assert and clear edge as small as possible to reduce system
+latencies. But if it is too small slave won't be able to capture clear edge
+transition. The default of 30us should be good enough in most situations.
+The delay can be selected using 'delay' pps_gen_parport module parameter.
+
+
+Intel Timed I/O PPS signal generator
+------------------------------------
+
+Intel Timed I/O is a high precision device, present on 2019 and newer Intel
+CPUs, that can generate PPS signals.
+
+Timed I/O and system time are both driven by same hardware clock. The signal
+is generated with a precision of ~20 nanoseconds. The generated PPS signal
+is used to synchronize an external device with system clock. For example,
+it can be used to share your clock with a device that receives PPS signal,
+generated by Timed I/O device. There are dedicated Timed I/O pins to deliver
+the PPS signal to an external device.
+
+Usage of Intel Timed I/O as PPS generator:
+
+Start generating PPS signal::
+
+        $echo 1 > /sys/class/pps-gen/pps-genx/enable
+
+Stop generating PPS signal::
+
+        $echo 0 > /sys/class/pps-gen/pps-genx/enable