linux.git/kernel/trace/trace.c, branch v6.0.6

tracing: Do not free snapshot if tracer is on cmdline

2022-10-21T10:37:53+00:00

commit a541a9559bb0a8ecc434de01d3e4826c32e8bb53 upstream.

The ftrace_boot_snapshot and alloc_snapshot cmdline options allocate the
snapshot buffer at boot up for use later. The ftrace_boot_snapshot in
particular requires the snapshot to be allocated because it will take a
snapshot at the end of boot up allowing to see the traces that happened
during boot so that it's not lost when user space takes over.

When a tracer is registered (started) there's a path that checks if it
requires the snapshot buffer or not, and if it does not and it was
allocated it will do a synchronization and free the snapshot buffer.

This is only required if the previous tracer was using it for "max
latency" snapshots, as it needs to make sure all max snapshots are
complete before freeing. But this is only needed if the previous tracer
was using the snapshot buffer for latency (like irqoff tracer and
friends). But it does not make sense to free it, if the previous tracer
was not using it, and the snapshot was allocated by the cmdline
parameters. This basically takes away the point of allocating it in the
first place!

Note, the allocated snapshot worked fine for just trace events, but fails
when a tracer is enabled on the cmdline.

Further investigation, this goes back even further and it does not require
a tracer on the cmdline to fail. Simply enable snapshots and then enable a
tracer, and it will remove the snapshot.

Link: https://lkml.kernel.org/r/20221005113757.041df7fe@gandalf.local.home

Cc: Masami Hiramatsu 
Cc: Andrew Morton 
Cc: stable@vger.kernel.org
Fixes: 45ad21ca5530 ("tracing: Have trace_array keep track if snapshot buffer is allocated")
Reported-by: Ross Zwisler 
Tested-by: Ross Zwisler 
Signed-off-by: Steven Rostedt (Google) 
Signed-off-by: Greg Kroah-Hartman

tracing: Add ioctl() to force ring buffer waiters to wake up

2022-10-21T10:37:53+00:00

commit 01b2a52171735c6eea80ee2f355f32bea6c41418 upstream.

If a process is waiting on the ring buffer for data, there currently isn't
a clean way to force it to wake up. Add an ioctl call that will force any
tasks that are waiting on the trace_pipe_raw file to wake up.

Link: https://lkml.kernel.org/r/20220929095029.117f913f@gandalf.local.home

Cc: stable@vger.kernel.org
Cc: Ingo Molnar 
Cc: Andrew Morton 
Fixes: e30f53aad2202 ("tracing: Do not busy wait in buffer splice")
Signed-off-by: Steven Rostedt (Google) 
Signed-off-by: Greg Kroah-Hartman

tracing: Wake up waiters when tracing is disabled

2022-10-21T10:37:53+00:00

commit 2b0fd9a59b7990c161fa1cb7b79edb22847c87c2 upstream.

When tracing is disabled, there's no reason that waiters should stay
waiting, wake them up, otherwise tasks get stuck when they should be
flushing the buffers.

Cc: stable@vger.kernel.org
Fixes: e30f53aad2202 ("tracing: Do not busy wait in buffer splice")
Signed-off-by: Steven Rostedt (Google) 
Signed-off-by: Greg Kroah-Hartman

tracing: Wake up ring buffer waiters on closing of the file

2022-10-21T10:37:52+00:00

commit f3ddb74ad0790030c9592229fb14d8c451f4e9a8 upstream.

When the file that represents the ring buffer is closed, there may be
waiters waiting on more input from the ring buffer. Call
ring_buffer_wake_waiters() to wake up any waiters when the file is
closed.

Link: https://lkml.kernel.org/r/20220927231825.182416969@goodmis.org

Cc: stable@vger.kernel.org
Cc: Ingo Molnar 
Cc: Andrew Morton 
Fixes: e30f53aad2202 ("tracing: Do not busy wait in buffer splice")
Signed-off-by: Steven Rostedt (Google) 
Signed-off-by: Greg Kroah-Hartman

tracing: Disable interrupt or preemption before acquiring arch_spinlock_t

2022-10-21T10:37:52+00:00

commit c0a581d7126c0bbc96163276f585fd7b4e4d8d0e upstream.

It was found that some tracing functions in kernel/trace/trace.c acquire
an arch_spinlock_t with preemption and irqs enabled. An example is the
tracing_saved_cmdlines_size_read() function which intermittently causes
a "BUG: using smp_processor_id() in preemptible" warning when the LTP
read_all_proc test is run.

That can be problematic in case preemption happens after acquiring the
lock. Add the necessary preemption or interrupt disabling code in the
appropriate places before acquiring an arch_spinlock_t.

The convention here is to disable preemption for trace_cmdline_lock and
interupt for max_lock.

Link: https://lkml.kernel.org/r/20220922145622.1744826-1-longman@redhat.com

Cc: Peter Zijlstra 
Cc: Ingo Molnar 
Cc: Will Deacon 
Cc: Boqun Feng 
Cc: stable@vger.kernel.org
Fixes: a35873a0993b ("tracing: Add conditional snapshot")
Fixes: 939c7a4f04fc ("tracing: Introduce saved_cmdlines_size file")
Suggested-by: Steven Rostedt 
Signed-off-by: Waiman Long 
Signed-off-by: Steven Rostedt (Google) 
Signed-off-by: Greg Kroah-Hartman

Merge tag 'trace-v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

2022-08-05T16:41:12+00:00

Pull tracing updates from Steven Rostedt:

 - Runtime verification infrastructure

   This is the biggest change here. It introduces the runtime
   verification that is necessary for running Linux on safety critical
   systems.

   It allows for deterministic automata models to be inserted into the
   kernel that will attach to tracepoints, where the information on
   these tracepoints will move the model from state to state.

   If a state is encountered that does not belong to the model, it will
   then activate a given reactor, that could just inform the user or
   even panic the kernel (for which safety critical systems will detect
   and can recover from).

 - Two monitor models are also added: Wakeup In Preemptive (WIP - not to
   be confused with "work in progress"), and Wakeup While Not Running
   (WWNR).

 - Added __vstring() helper to the TRACE_EVENT() macro to replace
   several vsnprintf() usages that were all doing it wrong.

 - eprobes now can have their event autogenerated when the event name is
   left off.

 - The rest is various cleanups and fixes.

* tag 'trace-v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (50 commits)
  rv: Unlock on error path in rv_unregister_reactor()
  tracing: Use alignof__(struct {type b;}) instead of offsetof()
  tracing/eprobe: Show syntax error logs in error_log file
  scripts/tracing: Fix typo 'the the' in comment
  tracepoints: It is CONFIG_TRACEPOINTS not CONFIG_TRACEPOINT
  tracing: Use free_trace_buffer() in allocate_trace_buffers()
  tracing: Use a struct alignof to determine trace event field alignment
  rv/reactor: Add the panic reactor
  rv/reactor: Add the printk reactor
  rv/monitor: Add the wwnr monitor
  rv/monitor: Add the wip monitor
  rv/monitor: Add the wip monitor skeleton created by dot2k
  Documentation/rv: Add deterministic automata instrumentation documentation
  Documentation/rv: Add deterministic automata monitor synthesis documentation
  tools/rv: Add dot2k
  Documentation/rv: Add deterministic automaton documentation
  tools/rv: Add dot2c
  Documentation/rv: Add a basic documentation
  rv/include: Add instrumentation helper functions
  rv/include: Add deterministic automata monitor definition via C macros
  ...

Merge tag 'rcu.2022.07.26a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

2022-08-03T02:12:45+00:00

Pull RCU updates from Paul McKenney:

 - Documentation updates

 - Miscellaneous fixes

 - Callback-offload updates, perhaps most notably a new
   RCU_NOCB_CPU_DEFAULT_ALL Kconfig option that causes all CPUs to be
   offloaded at boot time, regardless of kernel boot parameters.

   This is useful to battery-powered systems such as ChromeOS and
   Android. In addition, a new RCU_NOCB_CPU_CB_BOOST kernel boot
   parameter prevents offloaded callbacks from interfering with
   real-time workloads and with energy-efficiency mechanisms

 - Polled grace-period updates, perhaps most notably making these APIs
   account for both normal and expedited grace periods

 - Tasks RCU updates, perhaps most notably reducing the CPU overhead of
   RCU tasks trace grace periods by more than a factor of two on a
   system with 15,000 tasks.

   The reduction is expected to increase with the number of tasks, so it
   seems reasonable to hypothesize that a system with 150,000 tasks
   might see a 20-fold reduction in CPU overhead

 - Torture-test updates

 - Updates that merge RCU's dyntick-idle tracking into context tracking,
   thus reducing the overhead of transitioning to kernel mode from
   either idle or nohz_full userspace execution for kernels that track
   context independently of RCU.

   This is expected to be helpful primarily for kernels built with
   CONFIG_NO_HZ_FULL=y

* tag 'rcu.2022.07.26a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (98 commits)
  rcu: Add irqs-disabled indicator to expedited RCU CPU stall warnings
  rcu: Diagnose extended sync_rcu_do_polled_gp() loops
  rcu: Put panic_on_rcu_stall() after expedited RCU CPU stall warnings
  rcutorture: Test polled expedited grace-period primitives
  rcu: Add polled expedited grace-period primitives
  rcutorture: Verify that polled GP API sees synchronous grace periods
  rcu: Make Tiny RCU grace periods visible to polled APIs
  rcu: Make polled grace-period API account for expedited grace periods
  rcu: Switch polled grace-period APIs to ->gp_seq_polled
  rcu/nocb: Avoid polling when my_rdp->nocb_head_rdp list is empty
  rcu/nocb: Add option to opt rcuo kthreads out of RT priority
  rcu: Add nocb_cb_kthread check to rcu_is_callbacks_kthread()
  rcu/nocb: Add an option to offload all CPUs on boot
  rcu/nocb: Fix NOCB kthreads spawn failure with rcu_nocb_rdp_deoffload() direct call
  rcu/nocb: Invert rcu_state.barrier_mutex VS hotplug lock locking order
  rcu/nocb: Add/del rdp to iterate from rcuog itself
  rcu/tree: Add comment to describe GP-done condition in fqs loop
  rcu: Initialize first_gp_fqs at declaration in rcu_gp_fqs()
  rcu/kvfree: Remove useless monitor_todo flag
  rcu: Cleanup RCU urgency state for offline CPU
  ...

tracing: Use free_trace_buffer() in allocate_trace_buffers()

2022-08-02T19:13:19+00:00

In allocate_trace_buffers(), if allocating tr->max_buffer
fails, we can directly call free_trace_buffer to free
tr->array_buffer.

Link: https://lkml.kernel.org/r/65f0702d-07f6-08de-2a07-4c50af56a67b@huawei.com

Signed-off-by: Zhiqiang Liu 
Signed-off-by: Steven Rostedt (Google)

rv: Add Runtime Verification (RV) interface

2022-07-30T18:01:28+00:00

RV is a lightweight (yet rigorous) method that complements classical
exhaustive verification techniques (such as model checking and
theorem proving) with a more practical approach to complex systems.

RV works by analyzing the trace of the system's actual execution,
comparing it against a formal specification of the system behavior.
RV can give precise information on the runtime behavior of the
monitored system while enabling the reaction for unexpected
events, avoiding, for example, the propagation of a failure on
safety-critical systems.

The development of this interface roots in the development of the
paper:

De Oliveira, Daniel Bristot; Cucinotta, Tommaso; De Oliveira, Romulo
Silva. Efficient formal verification for the Linux kernel. In:
International Conference on Software Engineering and Formal Methods.
Springer, Cham, 2019. p. 315-332.

And:

De Oliveira, Daniel Bristot. Automata-based formal analysis
and verification of the real-time Linux kernel. PhD Thesis, 2020.

The RV interface resembles the tracing/ interface on purpose. The current
path for the RV interface is /sys/kernel/tracing/rv/.

It presents these files:

 "available_monitors"
   - List the available monitors, one per line.

   For example:
     # cat available_monitors
     wip
     wwnr

 "enabled_monitors"
   - Lists the enabled monitors, one per line;
   - Writing to it enables a given monitor;
   - Writing a monitor name with a '!' prefix disables it;
   - Truncating the file disables all enabled monitors.

   For example:
     # cat enabled_monitors
     # echo wip > enabled_monitors
     # echo wwnr >> enabled_monitors
     # cat enabled_monitors
     wip
     wwnr
     # echo '!wip' >> enabled_monitors
     # cat enabled_monitors
     wwnr
     # echo > enabled_monitors
     # cat enabled_monitors
     #

   Note that more than one monitor can be enabled concurrently.

 "monitoring_on"
   - It is an on/off general switcher for monitoring. Note
   that it does not disable enabled monitors or detach events,
   but stop the per-entity monitors of monitoring the events
   received from the system. It resembles the "tracing_on" switcher.

 "monitors/"
   Each monitor will have its one directory inside "monitors/". There
   the monitor specific files will be presented.
   The "monitors/" directory resembles the "events" directory on
   tracefs.

   For example:
     # cd monitors/wip/
     # ls
     desc  enable
     # cat desc
     wakeup in preemptive per-cpu testing monitor.
     # cat enable
     0

For further information, see the comments in the header of
kernel/trace/rv/rv.c from this patch.

Link: https://lkml.kernel.org/r/a4bfe038f50cb047bfb343ad0e12b0e646ab308b.1659052063.git.bristot@kernel.org

Cc: Wim Van Sebroeck 
Cc: Guenter Roeck 
Cc: Jonathan Corbet 
Cc: Ingo Molnar 
Cc: Thomas Gleixner 
Cc: Peter Zijlstra 
Cc: Will Deacon 
Cc: Catalin Marinas 
Cc: Marco Elver 
Cc: Dmitry Vyukov 
Cc: "Paul E. McKenney" 
Cc: Shuah Khan 
Cc: Gabriele Paoloni 
Cc: Juri Lelli 
Cc: Clark Williams 
Cc: Tao Zhou 
Cc: Randy Dunlap 
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-trace-devel@vger.kernel.org
Signed-off-by: Daniel Bristot de Oliveira 
Signed-off-by: Steven Rostedt (Google)

tracing: Auto generate event name when creating a group of events

2022-07-24T23:11:17+00:00

Currently when creating a specific group of trace events,
take kprobe event as example, the user must use the following format:
p:GRP/EVENT [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS],
which means user must enter EVENT name, one example is:

  echo 'p:usb_gadget/config_usb_cfg_link config_usb_cfg_link $arg1' >> kprobe_events

It is not simple if there are too many entries because the event name is
the same as symbol name.

This change allows user to specify no EVENT name, format changed as:

   p:GRP/ [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]

It will generate event name automatically and one example is:

  echo 'p:usb_gadget/ config_usb_cfg_link $arg1' >> kprobe_events.

Link: https://lore.kernel.org/all/1656296348-16111-4-git-send-email-quic_linyyuan@quicinc.com/

Acked-by: Masami Hiramatsu (Google) 
Reviewed-by: Tom Zanussi 
Signed-off-by: Linyu Yuan 
Signed-off-by: Steven Rostedt (Google)