Merge tag 'trace-v5.6-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

.. SPDX-License-Identifier: GPL-2.0

.. _bootconfig:

==================

Boot Configuration

==================

:Author: Masami Hiramatsu <mhiramat@kernel.org>

Overview

========

The boot configuration expands the current kernel command line to support

additional key-value data when booting the kernel in an efficient way.

This allows administrators to pass a structured-Key config file.

Config File Syntax

==================

The boot config syntax is a simple structured key-value. Each key consists

of dot-connected-words, and key and value are connected by ``=``. The value

has to be terminated by semi-colon (``;``) or newline (``\n``).

For array value, array entries are separated by comma (``,``). ::

KEY[.WORD[...]] = VALUE[, VALUE2[...]][;]

Unlike the kernel command line syntax, spaces are OK around the comma and ``=``.

Each key word must contain only alphabets, numbers, dash (``-``) or underscore

(``_``). And each value only contains printable characters or spaces except

for delimiters such as semi-colon (``;``), new-line (``\n``), comma (``,``),

hash (``#``) and closing brace (``}``).

If you want to use those delimiters in a value, you can use either double-

quotes (``"VALUE"``) or single-quotes (``'VALUE'``) to quote it. Note that

you can not escape these quotes.

There can be a key which doesn't have value or has an empty value. Those keys

are used for checking if the key exists or not (like a boolean).

Key-Value Syntax

----------------

The boot config file syntax allows user to merge partially same word keys

by brace. For example::

 foo.bar.baz = value1

 foo.bar.qux.quux = value2

These can be written also in::

 foo.bar {

    baz = value1

    qux.quux = value2

 }

Or more shorter, written as following::

 foo.bar { baz = value1; qux.quux = value2 }

In both styles, same key words are automatically merged when parsing it

at boot time. So you can append similar trees or key-values.

Comments

--------

The config syntax accepts shell-script style comments. The comments starting

with hash ("#") until newline ("\n") will be ignored.

::

 # comment line

 foo = value # value is set to foo.

 bar = 1, # 1st element

       2, # 2nd element

       3  # 3rd element

This is parsed as below::

 foo = value

 bar = 1, 2, 3

Note that you can not put a comment between value and delimiter(``,`` or

``;``). This means following config has a syntax error ::

 key = 1 # comment

       ,2

/proc/bootconfig

================

/proc/bootconfig is a user-space interface of the boot config.

Unlike /proc/cmdline, this file shows the key-value style list.

Each key-value pair is shown in each line with following style::

 KEY[.WORDS...] = "[VALUE]"[,"VALUE2"...]

Boot Kernel With a Boot Config

==============================

Since the boot configuration file is loaded with initrd, it will be added

to the end of the initrd (initramfs) image file. The Linux kernel decodes

the last part of the initrd image in memory to get the boot configuration

data.

Because of this "piggyback" method, there is no need to change or

update the boot loader and the kernel image itself.

To do this operation, Linux kernel provides "bootconfig" command under

tools/bootconfig, which allows admin to apply or delete the config file

to/from initrd image. You can build it by the following command::

 # make -C tools/bootconfig

To add your boot config file to initrd image, run bootconfig as below

(Old data is removed automatically if exists)::

 # tools/bootconfig/bootconfig -a your-config /boot/initrd.img-X.Y.Z

To remove the config from the image, you can use -d option as below::

 # tools/bootconfig/bootconfig -d /boot/initrd.img-X.Y.Z

Then add "bootconfig" on the normal kernel command line to tell the

kernel to look for the bootconfig at the end of the initrd file.

Config File Limitation

======================

Currently the maximum config size size is 32KB and the total key-words (not

key-value entries) must be under 1024 nodes.

Note: this is not the number of entries but nodes, an entry must consume

more than 2 nodes (a key-word and a value). So theoretically, it will be

up to 512 key-value pairs. If keys contains 3 words in average, it can

contain 256 key-value pairs. In most cases, the number of config items

will be under 100 entries and smaller than 8KB, so it would be enough.

If the node number exceeds 1024, parser returns an error even if the file

size is smaller than 32KB.

Anyway, since bootconfig command verifies it when appending a boot config

to initrd image, user can notice it before boot.

Bootconfig APIs

===============

User can query or loop on key-value pairs, also it is possible to find

a root (prefix) key node and find key-values under that node.

If you have a key string, you can query the value directly with the key

using xbc_find_value(). If you want to know what keys exist in the boot

config, you can use xbc_for_each_key_value() to iterate key-value pairs.

Note that you need to use xbc_array_for_each_value() for accessing

each array's value, e.g.::

 vnode = NULL;

 xbc_find_value("key.word", &vnode);

 if (vnode && xbc_node_is_array(vnode))

    xbc_array_for_each_value(vnode, value) {

      printk("%s ", value);

    }

If you want to focus on keys which have a prefix string, you can use

xbc_find_node() to find a node by the prefix string, and iterate

keys under the prefix node with xbc_node_for_each_key_value().

But the most typical usage is to get the named value under prefix

or get the named array under prefix as below::

 root = xbc_find_node("key.prefix");

 value = xbc_node_find_value(root, "option", &vnode);

 ...

 xbc_node_for_each_array_value(root, "array-option", value, anode) {

    ...

 }

This accesses a value of "key.prefix.option" and an array of

"key.prefix.array-option".

Locking is not needed, since after initialization, the config becomes

read-only. All data and keys must be copied if you need to modify it.

Functions and structures

========================

.. kernel-doc:: include/linux/bootconfig.h

.. kernel-doc:: lib/bootconfig.c

   binderfs

   binfmt-misc

   blockdev/index

   bootconfig

   braille-console

   btmrvl

   cgroup-v1/index

			no delay (0).

			Format: integer

	bootconfig	[KNL]

			Extended command line options can be added to an initrd

			and this will cause the kernel to look for it.

			See Documentation/admin-guide/bootconfig.rst

	bert_disable	[ACPI]

			Disable BERT OS support on buggy BIOSes.

.. SPDX-License-Identifier: GPL-2.0

=================

Boot-time tracing

=================

:Author: Masami Hiramatsu <mhiramat@kernel.org>

Overview

========

Boot-time tracing allows users to trace boot-time process including

device initialization with full features of ftrace including per-event

filter and actions, histograms, kprobe-events and synthetic-events,

and trace instances.

Since kernel command line is not enough to control these complex features,

this uses bootconfig file to describe tracing feature programming.

Options in the Boot Config

==========================

Here is the list of available options list for boot time tracing in

boot config file [1]_. All options are under "ftrace." or "kernel."

prefix. See kernel parameters for the options which starts

with "kernel." prefix [2]_.

.. [1] See :ref:`Documentation/admin-guide/bootconfig.rst <bootconfig>`

.. [2] See :ref:`Documentation/admin-guide/kernel-parameters.rst <kernelparameters>`

Ftrace Global Options

---------------------

Ftrace global options have "kernel." prefix in boot config, which means

these options are passed as a part of kernel legacy command line.

kernel.tp_printk

   Output trace-event data on printk buffer too.

kernel.dump_on_oops [= MODE]

   Dump ftrace on Oops. If MODE = 1 or omitted, dump trace buffer

   on all CPUs. If MODE = 2, dump a buffer on a CPU which kicks Oops.

kernel.traceoff_on_warning

   Stop tracing if WARN_ON() occurs.

kernel.fgraph_max_depth = MAX_DEPTH

   Set MAX_DEPTH to maximum depth of fgraph tracer.

kernel.fgraph_filters = FILTER[, FILTER2...]

   Add fgraph tracing function filters.

kernel.fgraph_notraces = FILTER[, FILTER2...]

   Add fgraph non-tracing function filters.

Ftrace Per-instance Options

---------------------------

These options can be used for each instance including global ftrace node.

ftrace.[instance.INSTANCE.]options = OPT1[, OPT2[...]]

   Enable given ftrace options.

ftrace.[instance.INSTANCE.]trace_clock = CLOCK

   Set given CLOCK to ftrace's trace_clock.

ftrace.[instance.INSTANCE.]buffer_size = SIZE

   Configure ftrace buffer size to SIZE. You can use "KB" or "MB"

   for that SIZE.

ftrace.[instance.INSTANCE.]alloc_snapshot

   Allocate snapshot buffer.

ftrace.[instance.INSTANCE.]cpumask = CPUMASK

   Set CPUMASK as trace cpu-mask.

ftrace.[instance.INSTANCE.]events = EVENT[, EVENT2[...]]

   Enable given events on boot. You can use a wild card in EVENT.

ftrace.[instance.INSTANCE.]tracer = TRACER

   Set TRACER to current tracer on boot. (e.g. function)

ftrace.[instance.INSTANCE.]ftrace.filters

   This will take an array of tracing function filter rules.

ftrace.[instance.INSTANCE.]ftrace.notraces

   This will take an array of NON-tracing function filter rules.

Ftrace Per-Event Options

------------------------

These options are setting per-event options.

ftrace.[instance.INSTANCE.]event.GROUP.EVENT.enable

   Enable GROUP:EVENT tracing.

ftrace.[instance.INSTANCE.]event.GROUP.EVENT.filter = FILTER

   Set FILTER rule to the GROUP:EVENT.

ftrace.[instance.INSTANCE.]event.GROUP.EVENT.actions = ACTION[, ACTION2[...]]

   Set ACTIONs to the GROUP:EVENT.

ftrace.[instance.INSTANCE.]event.kprobes.EVENT.probes = PROBE[, PROBE2[...]]

   Defines new kprobe event based on PROBEs. It is able to define

   multiple probes on one event, but those must have same type of

   arguments. This option is available only for the event which

   group name is "kprobes".

ftrace.[instance.INSTANCE.]event.synthetic.EVENT.fields = FIELD[, FIELD2[...]]

   Defines new synthetic event with FIELDs. Each field should be

   "type varname".

Note that kprobe and synthetic event definitions can be written under

instance node, but those are also visible from other instances. So please

take care for event name conflict.

Examples

========

For example, to add filter and actions for each event, define kprobe

events, and synthetic events with histogram, write a boot config like

below::

  ftrace.event {

        task.task_newtask {

                filter = "pid < 128"

                enable

        }

        kprobes.vfs_read {

                probes = "vfs_read $arg1 $arg2"

                filter = "common_pid < 200"

                enable

        }

        synthetic.initcall_latency {

                fields = "unsigned long func", "u64 lat"

                actions = "hist:keys=func.sym,lat:vals=lat:sort=lat"

        }

        initcall.initcall_start {

                actions = "hist:keys=func:ts0=common_timestamp.usecs"

        }

        initcall.initcall_finish {

                actions = "hist:keys=func:lat=common_timestamp.usecs-$ts0:onmatch(initcall.initcall_start).initcall_latency(func,$lat)"

        }

  }

Also, boot-time tracing supports "instance" node, which allows us to run

several tracers for different purpose at once. For example, one tracer

is for tracing functions starting with "user\_", and others tracing

"kernel\_" functions, you can write boot config as below::

  ftrace.instance {

        foo {

                tracer = "function"

                ftrace.filters = "user_*"

        }

        bar {

                tracer = "function"

                ftrace.filters = "kernel_*"

        }

  }

The instance node also accepts event nodes so that each instance

can customize its event tracing.

This boot-time tracing also supports ftrace kernel parameters via boot

config.

For example, following kernel parameters::

 trace_options=sym-addr trace_event=initcall:* tp_printk trace_buf_size=1M ftrace=function ftrace_filter="vfs*"

This can be written in boot config like below::

  kernel {

        trace_options = sym-addr

        trace_event = "initcall:*"

        tp_printk

        trace_buf_size = 1M

        ftrace = function

        ftrace_filter = "vfs*"

  }

Note that parameters start with "kernel" prefix instead of "ftrace".