Initial commit: Linux kernel 4.19 for Unplugged OS

kernel/trace/Kconfig

@@ -0,0 +1,825 @@
+#
+# Architectures that offer an FUNCTION_TRACER implementation should
+#  select HAVE_FUNCTION_TRACER:
+#
+
+config USER_STACKTRACE_SUPPORT
+	bool
+
+config NOP_TRACER
+	bool
+
+config HAVE_FTRACE_NMI_ENTER
+	bool
+	help
+	  See Documentation/trace/ftrace-design.rst
+
+config HAVE_FUNCTION_TRACER
+	bool
+	help
+	  See Documentation/trace/ftrace-design.rst
+
+config HAVE_FUNCTION_GRAPH_TRACER
+	bool
+	help
+	  See Documentation/trace/ftrace-design.rst
+
+config HAVE_DYNAMIC_FTRACE
+	bool
+	help
+	  See Documentation/trace/ftrace-design.rst
+
+config HAVE_DYNAMIC_FTRACE_WITH_REGS
+	bool
+
+config HAVE_FTRACE_MCOUNT_RECORD
+	bool
+	help
+	  See Documentation/trace/ftrace-design.rst
+
+config HAVE_SYSCALL_TRACEPOINTS
+	bool
+	help
+	  See Documentation/trace/ftrace-design.rst
+
+config HAVE_FENTRY
+	bool
+	help
+	  Arch supports the gcc options -pg with -mfentry
+
+config HAVE_NOP_MCOUNT
+	bool
+	help
+	  Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
+
+config HAVE_C_RECORDMCOUNT
+	bool
+	help
+	  C version of recordmcount available?
+
+config TRACER_MAX_TRACE
+	bool
+
+config TRACE_CLOCK
+	bool
+
+config RING_BUFFER
+	bool
+	select TRACE_CLOCK
+	select IRQ_WORK
+
+config FTRACE_NMI_ENTER
+       bool
+       depends on HAVE_FTRACE_NMI_ENTER
+       default y
+
+config EVENT_TRACING
+	select CONTEXT_SWITCH_TRACER
+        select GLOB
+	bool
+
+config CONTEXT_SWITCH_TRACER
+	bool
+
+config RING_BUFFER_ALLOW_SWAP
+	bool
+	help
+	 Allow the use of ring_buffer_swap_cpu.
+	 Adds a very slight overhead to tracing when enabled.
+
+config PREEMPTIRQ_TRACEPOINTS
+	bool
+	depends on TRACE_PREEMPT_TOGGLE || TRACE_IRQFLAGS
+	select TRACING
+	default y
+	help
+	  Create preempt/irq toggle tracepoints if needed, so that other parts
+	  of the kernel can use them to generate or add hooks to them.
+
+# All tracer options should select GENERIC_TRACER. For those options that are
+# enabled by all tracers (context switch and event tracer) they select TRACING.
+# This allows those options to appear when no other tracer is selected. But the
+# options do not appear when something else selects it. We need the two options
+# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
+# hiding of the automatic options.
+
+config TRACING
+	bool
+	select RING_BUFFER
+	select STACKTRACE if STACKTRACE_SUPPORT
+	select TRACEPOINTS
+	select NOP_TRACER
+	select BINARY_PRINTF
+	select EVENT_TRACING
+	select TRACE_CLOCK
+
+config GENERIC_TRACER
+	bool
+	select TRACING
+
+#
+# Minimum requirements an architecture has to meet for us to
+# be able to offer generic tracing facilities:
+#
+config TRACING_SUPPORT
+	bool
+	depends on TRACE_IRQFLAGS_SUPPORT
+	depends on STACKTRACE_SUPPORT
+	default y
+
+if TRACING_SUPPORT
+
+menuconfig FTRACE
+	bool "Tracers"
+	default y if DEBUG_KERNEL
+	help
+	  Enable the kernel tracing infrastructure.
+
+if FTRACE
+
+config FUNCTION_TRACER
+	bool "Kernel Function Tracer"
+	depends on HAVE_FUNCTION_TRACER
+	select KALLSYMS
+	select GENERIC_TRACER
+	select CONTEXT_SWITCH_TRACER
+	select GLOB
+	select TASKS_RCU if PREEMPT
+	help
+	  Enable the kernel to trace every kernel function. This is done
+	  by using a compiler feature to insert a small, 5-byte No-Operation
+	  instruction at the beginning of every kernel function, which NOP
+	  sequence is then dynamically patched into a tracer call when
+	  tracing is enabled by the administrator. If it's runtime disabled
+	  (the bootup default), then the overhead of the instructions is very
+	  small and not measurable even in micro-benchmarks.
+
+config FUNCTION_GRAPH_TRACER
+	bool "Kernel Function Graph Tracer"
+	depends on HAVE_FUNCTION_GRAPH_TRACER
+	depends on FUNCTION_TRACER
+	depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE
+	default y
+	help
+	  Enable the kernel to trace a function at both its return
+	  and its entry.
+	  Its first purpose is to trace the duration of functions and
+	  draw a call graph for each thread with some information like
+	  the return value. This is done by setting the current return
+	  address on the current task structure into a stack of calls.
+
+config TRACE_PREEMPT_TOGGLE
+	bool
+	help
+	  Enables hooks which will be called when preemption is first disabled,
+	  and last enabled.
+
+config PREEMPTIRQ_EVENTS
+	bool "Enable trace events for preempt and irq disable/enable"
+	select TRACE_IRQFLAGS
+	select TRACE_PREEMPT_TOGGLE if PREEMPT
+	select GENERIC_TRACER
+	default n
+	help
+	  Enable tracing of disable and enable events for preemption and irqs.
+
+config IRQSOFF_TRACER
+	bool "Interrupts-off Latency Tracer"
+	default n
+	depends on TRACE_IRQFLAGS_SUPPORT
+	depends on !ARCH_USES_GETTIMEOFFSET
+	select TRACE_IRQFLAGS
+	select GENERIC_TRACER
+	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
+	select TRACER_SNAPSHOT
+	select TRACER_SNAPSHOT_PER_CPU_SWAP
+	help
+	  This option measures the time spent in irqs-off critical
+	  sections, with microsecond accuracy.
+
+	  The default measurement method is a maximum search, which is
+	  disabled by default and can be runtime (re-)started
+	  via:
+
+	      echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
+
+	  (Note that kernel size and overhead increase with this option
+	  enabled. This option and the preempt-off timing option can be
+	  used together or separately.)
+
+config PREEMPT_TRACER
+	bool "Preemption-off Latency Tracer"
+	default n
+	depends on !ARCH_USES_GETTIMEOFFSET
+	depends on PREEMPT
+	select GENERIC_TRACER
+	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
+	select TRACER_SNAPSHOT
+	select TRACER_SNAPSHOT_PER_CPU_SWAP
+	select TRACE_PREEMPT_TOGGLE
+	help
+	  This option measures the time spent in preemption-off critical
+	  sections, with microsecond accuracy.
+
+	  The default measurement method is a maximum search, which is
+	  disabled by default and can be runtime (re-)started
+	  via:
+
+	      echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
+
+	  (Note that kernel size and overhead increase with this option
+	  enabled. This option and the irqs-off timing option can be
+	  used together or separately.)
+
+config SCHED_TRACER
+	bool "Scheduling Latency Tracer"
+	select GENERIC_TRACER
+	select CONTEXT_SWITCH_TRACER
+	select TRACER_MAX_TRACE
+	select TRACER_SNAPSHOT
+	help
+	  This tracer tracks the latency of the highest priority task
+	  to be scheduled in, starting from the point it has woken up.
+
+config HWLAT_TRACER
+	bool "Tracer to detect hardware latencies (like SMIs)"
+	select GENERIC_TRACER
+	help
+	 This tracer, when enabled will create one or more kernel threads,
+	 depending on what the cpumask file is set to, which each thread
+	 spinning in a loop looking for interruptions caused by
+	 something other than the kernel. For example, if a
+	 System Management Interrupt (SMI) takes a noticeable amount of
+	 time, this tracer will detect it. This is useful for testing
+	 if a system is reliable for Real Time tasks.
+
+	 Some files are created in the tracing directory when this
+	 is enabled:
+
+	   hwlat_detector/width   - time in usecs for how long to spin for
+	   hwlat_detector/window  - time in usecs between the start of each
+				     iteration
+
+	 A kernel thread is created that will spin with interrupts disabled
+	 for "width" microseconds in every "window" cycle. It will not spin
+	 for "window - width" microseconds, where the system can
+	 continue to operate.
+
+	 The output will appear in the trace and trace_pipe files.
+
+	 When the tracer is not running, it has no affect on the system,
+	 but when it is running, it can cause the system to be
+	 periodically non responsive. Do not run this tracer on a
+	 production system.
+
+	 To enable this tracer, echo in "hwlat" into the current_tracer
+	 file. Every time a latency is greater than tracing_thresh, it will
+	 be recorded into the ring buffer.
+
+config ENABLE_DEFAULT_TRACERS
+	bool "Trace process context switches and events"
+	depends on !GENERIC_TRACER
+	select TRACING
+	help
+	  This tracer hooks to various trace points in the kernel,
+	  allowing the user to pick and choose which trace point they
+	  want to trace. It also includes the sched_switch tracer plugin.
+
+config FTRACE_SYSCALLS
+	bool "Trace syscalls"
+	depends on HAVE_SYSCALL_TRACEPOINTS
+	select GENERIC_TRACER
+	select KALLSYMS
+	help
+	  Basic tracer to catch the syscall entry and exit events.
+
+config TRACER_SNAPSHOT
+	bool "Create a snapshot trace buffer"
+	select TRACER_MAX_TRACE
+	help
+	  Allow tracing users to take snapshot of the current buffer using the
+	  ftrace interface, e.g.:
+
+	      echo 1 > /sys/kernel/debug/tracing/snapshot
+	      cat snapshot
+
+config TRACER_SNAPSHOT_PER_CPU_SWAP
+        bool "Allow snapshot to swap per CPU"
+	depends on TRACER_SNAPSHOT
+	select RING_BUFFER_ALLOW_SWAP
+	help
+	  Allow doing a snapshot of a single CPU buffer instead of a
+	  full swap (all buffers). If this is set, then the following is
+	  allowed:
+
+	      echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot
+
+	  After which, only the tracing buffer for CPU 2 was swapped with
+	  the main tracing buffer, and the other CPU buffers remain the same.
+
+	  When this is enabled, this adds a little more overhead to the
+	  trace recording, as it needs to add some checks to synchronize
+	  recording with swaps. But this does not affect the performance
+	  of the overall system. This is enabled by default when the preempt
+	  or irq latency tracers are enabled, as those need to swap as well
+	  and already adds the overhead (plus a lot more).
+
+config TRACE_BRANCH_PROFILING
+	bool
+	select GENERIC_TRACER
+
+choice
+	prompt "Branch Profiling"
+	default BRANCH_PROFILE_NONE
+	help
+	 The branch profiling is a software profiler. It will add hooks
+	 into the C conditionals to test which path a branch takes.
+
+	 The likely/unlikely profiler only looks at the conditions that
+	 are annotated with a likely or unlikely macro.
+
+	 The "all branch" profiler will profile every if-statement in the
+	 kernel. This profiler will also enable the likely/unlikely
+	 profiler.
+
+	 Either of the above profilers adds a bit of overhead to the system.
+	 If unsure, choose "No branch profiling".
+
+config BRANCH_PROFILE_NONE
+	bool "No branch profiling"
+	help
+	  No branch profiling. Branch profiling adds a bit of overhead.
+	  Only enable it if you want to analyse the branching behavior.
+	  Otherwise keep it disabled.
+
+config PROFILE_ANNOTATED_BRANCHES
+	bool "Trace likely/unlikely profiler"
+	select TRACE_BRANCH_PROFILING
+	help
+	  This tracer profiles all likely and unlikely macros
+	  in the kernel. It will display the results in:
+
+	  /sys/kernel/debug/tracing/trace_stat/branch_annotated
+
+	  Note: this will add a significant overhead; only turn this
+	  on if you need to profile the system's use of these macros.
+
+config PROFILE_ALL_BRANCHES
+	bool "Profile all if conditionals" if !FORTIFY_SOURCE
+	select TRACE_BRANCH_PROFILING
+	help
+	  This tracer profiles all branch conditions. Every if ()
+	  taken in the kernel is recorded whether it hit or miss.
+	  The results will be displayed in:
+
+	  /sys/kernel/debug/tracing/trace_stat/branch_all
+
+	  This option also enables the likely/unlikely profiler.
+
+	  This configuration, when enabled, will impose a great overhead
+	  on the system. This should only be enabled when the system
+	  is to be analyzed in much detail.
+endchoice
+
+config TRACING_BRANCHES
+	bool
+	help
+	  Selected by tracers that will trace the likely and unlikely
+	  conditions. This prevents the tracers themselves from being
+	  profiled. Profiling the tracing infrastructure can only happen
+	  when the likelys and unlikelys are not being traced.
+
+config BRANCH_TRACER
+	bool "Trace likely/unlikely instances"
+	depends on TRACE_BRANCH_PROFILING
+	select TRACING_BRANCHES
+	help
+	  This traces the events of likely and unlikely condition
+	  calls in the kernel.  The difference between this and the
+	  "Trace likely/unlikely profiler" is that this is not a
+	  histogram of the callers, but actually places the calling
+	  events into a running trace buffer to see when and where the
+	  events happened, as well as their results.
+
+	  Say N if unsure.
+
+config STACK_TRACER
+	bool "Trace max stack"
+	depends on HAVE_FUNCTION_TRACER
+	select FUNCTION_TRACER
+	select STACKTRACE
+	select KALLSYMS
+	help
+	  This special tracer records the maximum stack footprint of the
+	  kernel and displays it in /sys/kernel/debug/tracing/stack_trace.
+
+	  This tracer works by hooking into every function call that the
+	  kernel executes, and keeping a maximum stack depth value and
+	  stack-trace saved.  If this is configured with DYNAMIC_FTRACE
+	  then it will not have any overhead while the stack tracer
+	  is disabled.
+
+	  To enable the stack tracer on bootup, pass in 'stacktrace'
+	  on the kernel command line.
+
+	  The stack tracer can also be enabled or disabled via the
+	  sysctl kernel.stack_tracer_enabled
+
+	  Say N if unsure.
+
+config BLK_DEV_IO_TRACE
+	bool "Support for tracing block IO actions"
+	depends on SYSFS
+	depends on BLOCK
+	select RELAY
+	select DEBUG_FS
+	select TRACEPOINTS
+	select GENERIC_TRACER
+	select STACKTRACE
+	help
+	  Say Y here if you want to be able to trace the block layer actions
+	  on a given queue. Tracing allows you to see any traffic happening
+	  on a block device queue. For more information (and the userspace
+	  support tools needed), fetch the blktrace tools from:
+
+	  git://git.kernel.dk/blktrace.git
+
+	  Tracing also is possible using the ftrace interface, e.g.:
+
+	    echo 1 > /sys/block/sda/sda1/trace/enable
+	    echo blk > /sys/kernel/debug/tracing/current_tracer
+	    cat /sys/kernel/debug/tracing/trace_pipe
+
+	  If unsure, say N.
+
+config KPROBE_EVENTS
+	depends on KPROBES
+	depends on HAVE_REGS_AND_STACK_ACCESS_API
+	bool "Enable kprobes-based dynamic events"
+	select TRACING
+	select PROBE_EVENTS
+	default y
+	help
+	  This allows the user to add tracing events (similar to tracepoints)
+	  on the fly via the ftrace interface. See
+	  Documentation/trace/kprobetrace.rst for more details.
+
+	  Those events can be inserted wherever kprobes can probe, and record
+	  various register and memory values.
+
+	  This option is also required by perf-probe subcommand of perf tools.
+	  If you want to use perf tools, this option is strongly recommended.
+
+config KPROBE_EVENTS_ON_NOTRACE
+	bool "Do NOT protect notrace function from kprobe events"
+	depends on KPROBE_EVENTS
+	depends on DYNAMIC_FTRACE
+	default n
+	help
+	  This is only for the developers who want to debug ftrace itself
+	  using kprobe events.
+
+	  If kprobes can use ftrace instead of breakpoint, ftrace related
+	  functions are protected from kprobe-events to prevent an infinit
+	  recursion or any unexpected execution path which leads to a kernel
+	  crash.
+
+	  This option disables such protection and allows you to put kprobe
+	  events on ftrace functions for debugging ftrace by itself.
+	  Note that this might let you shoot yourself in the foot.
+
+	  If unsure, say N.
+
+config UPROBE_EVENTS
+	bool "Enable uprobes-based dynamic events"
+	depends on ARCH_SUPPORTS_UPROBES
+	depends on MMU
+	depends on PERF_EVENTS
+	select UPROBES
+	select PROBE_EVENTS
+	select TRACING
+	default y
+	help
+	  This allows the user to add tracing events on top of userspace
+	  dynamic events (similar to tracepoints) on the fly via the trace
+	  events interface. Those events can be inserted wherever uprobes
+	  can probe, and record various registers.
+	  This option is required if you plan to use perf-probe subcommand
+	  of perf tools on user space applications.
+
+config BPF_EVENTS
+	depends on BPF_SYSCALL
+	depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
+	bool
+	default y
+	help
+	  This allows the user to attach BPF programs to kprobe events.
+
+config PROBE_EVENTS
+	def_bool n
+
+config DYNAMIC_FTRACE
+	bool "enable/disable function tracing dynamically"
+	depends on FUNCTION_TRACER
+	depends on HAVE_DYNAMIC_FTRACE
+	default y
+	help
+	  This option will modify all the calls to function tracing
+	  dynamically (will patch them out of the binary image and
+	  replace them with a No-Op instruction) on boot up. During
+	  compile time, a table is made of all the locations that ftrace
+	  can function trace, and this table is linked into the kernel
+	  image. When this is enabled, functions can be individually
+	  enabled, and the functions not enabled will not affect
+	  performance of the system.
+
+	  See the files in /sys/kernel/debug/tracing:
+	    available_filter_functions
+	    set_ftrace_filter
+	    set_ftrace_notrace
+
+	  This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
+	  otherwise has native performance as long as no tracing is active.
+
+config DYNAMIC_FTRACE_WITH_REGS
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on HAVE_DYNAMIC_FTRACE_WITH_REGS
+
+config FUNCTION_PROFILER
+	bool "Kernel function profiler"
+	depends on FUNCTION_TRACER
+	default n
+	help
+	  This option enables the kernel function profiler. A file is created
+	  in debugfs called function_profile_enabled which defaults to zero.
+	  When a 1 is echoed into this file profiling begins, and when a
+	  zero is entered, profiling stops. A "functions" file is created in
+	  the trace_stat directory; this file shows the list of functions that
+	  have been hit and their counters.
+
+	  If in doubt, say N.
+
+config BPF_KPROBE_OVERRIDE
+	bool "Enable BPF programs to override a kprobed function"
+	depends on BPF_EVENTS
+	depends on FUNCTION_ERROR_INJECTION
+	default n
+	help
+	 Allows BPF to override the execution of a probed function and
+	 set a different return value.  This is used for error injection.
+
+config FTRACE_MCOUNT_RECORD
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on HAVE_FTRACE_MCOUNT_RECORD
+
+config FTRACE_SELFTEST
+	bool
+
+config FTRACE_STARTUP_TEST
+	bool "Perform a startup test on ftrace"
+	depends on GENERIC_TRACER
+	select FTRACE_SELFTEST
+	help
+	  This option performs a series of startup tests on ftrace. On bootup
+	  a series of tests are made to verify that the tracer is
+	  functioning properly. It will do tests on all the configured
+	  tracers of ftrace.
+
+config EVENT_TRACE_TEST_SYSCALLS
+	bool "Run selftest on syscall events"
+	depends on FTRACE_STARTUP_TEST
+	help
+	 This option will also enable testing every syscall event.
+	 It only enables the event and disables it and runs various loads
+	 with the event enabled. This adds a bit more time for kernel boot
+	 up since it runs this on every system call defined.
+
+	 TBD - enable a way to actually call the syscalls as we test their
+	       events
+
+config MMIOTRACE
+	bool "Memory mapped IO tracing"
+	depends on HAVE_MMIOTRACE_SUPPORT && PCI
+	select GENERIC_TRACER
+	help
+	  Mmiotrace traces Memory Mapped I/O access and is meant for
+	  debugging and reverse engineering. It is called from the ioremap
+	  implementation and works via page faults. Tracing is disabled by
+	  default and can be enabled at run-time.
+
+	  See Documentation/trace/mmiotrace.rst.
+	  If you are not helping to develop drivers, say N.
+
+config TRACING_MAP
+	bool
+	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
+	help
+	  tracing_map is a special-purpose lock-free map for tracing,
+	  separated out as a stand-alone facility in order to allow it
+	  to be shared between multiple tracers.  It isn't meant to be
+	  generally used outside of that context, and is normally
+	  selected by tracers that use it.
+
+config HIST_TRIGGERS
+	bool "Histogram triggers"
+	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select TRACING_MAP
+	select TRACING
+	default n
+	help
+	  Hist triggers allow one or more arbitrary trace event fields
+	  to be aggregated into hash tables and dumped to stdout by
+	  reading a debugfs/tracefs file.  They're useful for
+	  gathering quick and dirty (though precise) summaries of
+	  event activity as an initial guide for further investigation
+	  using more advanced tools.
+
+	  Inter-event tracing of quantities such as latencies is also
+	  supported using hist triggers under this option.
+
+	  See Documentation/trace/histogram.rst.
+	  If in doubt, say N.
+
+config MMIOTRACE_TEST
+	tristate "Test module for mmiotrace"
+	depends on MMIOTRACE && m
+	help
+	  This is a dumb module for testing mmiotrace. It is very dangerous
+	  as it will write garbage to IO memory starting at a given address.
+	  However, it should be safe to use on e.g. unused portion of VRAM.
+
+	  Say N, unless you absolutely know what you are doing.
+
+config TRACEPOINT_BENCHMARK
+        bool "Add tracepoint that benchmarks tracepoints"
+	help
+	 This option creates the tracepoint "benchmark:benchmark_event".
+	 When the tracepoint is enabled, it kicks off a kernel thread that
+	 goes into an infinite loop (calling cond_sched() to let other tasks
+	 run), and calls the tracepoint. Each iteration will record the time
+	 it took to write to the tracepoint and the next iteration that
+	 data will be passed to the tracepoint itself. That is, the tracepoint
+	 will report the time it took to do the previous tracepoint.
+	 The string written to the tracepoint is a static string of 128 bytes
+	 to keep the time the same. The initial string is simply a write of
+	 "START". The second string records the cold cache time of the first
+	 write which is not added to the rest of the calculations.
+
+	 As it is a tight loop, it benchmarks as hot cache. That's fine because
+	 we care most about hot paths that are probably in cache already.
+
+	 An example of the output:
+
+	      START
+	      first=3672 [COLD CACHED]
+	      last=632 first=3672 max=632 min=632 avg=316 std=446 std^2=199712
+	      last=278 first=3672 max=632 min=278 avg=303 std=316 std^2=100337
+	      last=277 first=3672 max=632 min=277 avg=296 std=258 std^2=67064
+	      last=273 first=3672 max=632 min=273 avg=292 std=224 std^2=50411
+	      last=273 first=3672 max=632 min=273 avg=288 std=200 std^2=40389
+	      last=281 first=3672 max=632 min=273 avg=287 std=183 std^2=33666
+
+
+config RING_BUFFER_BENCHMARK
+	tristate "Ring buffer benchmark stress tester"
+	depends on RING_BUFFER
+	help
+	  This option creates a test to stress the ring buffer and benchmark it.
+	  It creates its own ring buffer such that it will not interfere with
+	  any other users of the ring buffer (such as ftrace). It then creates
+	  a producer and consumer that will run for 10 seconds and sleep for
+	  10 seconds. Each interval it will print out the number of events
+	  it recorded and give a rough estimate of how long each iteration took.
+
+	  It does not disable interrupts or raise its priority, so it may be
+	  affected by processes that are running.
+
+	  If unsure, say N.
+
+config RING_BUFFER_STARTUP_TEST
+       bool "Ring buffer startup self test"
+       depends on RING_BUFFER
+       help
+         Run a simple self test on the ring buffer on boot up. Late in the
+	 kernel boot sequence, the test will start that kicks off
+	 a thread per cpu. Each thread will write various size events
+	 into the ring buffer. Another thread is created to send IPIs
+	 to each of the threads, where the IPI handler will also write
+	 to the ring buffer, to test/stress the nesting ability.
+	 If any anomalies are discovered, a warning will be displayed
+	 and all ring buffers will be disabled.
+
+	 The test runs for 10 seconds. This will slow your boot time
+	 by at least 10 more seconds.
+
+	 At the end of the test, statics and more checks are done.
+	 It will output the stats of each per cpu buffer. What
+	 was written, the sizes, what was read, what was lost, and
+	 other similar details.
+
+	 If unsure, say N
+
+config PREEMPTIRQ_DELAY_TEST
+	tristate "Preempt / IRQ disable delay thread to test latency tracers"
+	depends on m
+	help
+	  Select this option to build a test module that can help test latency
+	  tracers by executing a preempt or irq disable section with a user
+	  configurable delay. The module busy waits for the duration of the
+	  critical section.
+
+	  For example, the following invocation forces a one-time irq-disabled
+	  critical section for 500us:
+	  modprobe preemptirq_delay_test test_mode=irq delay=500000
+
+	  If unsure, say N
+
+config TRACE_EVAL_MAP_FILE
+       bool "Show eval mappings for trace events"
+       depends on TRACING
+       help
+	The "print fmt" of the trace events will show the enum/sizeof names
+	instead	of their values. This can cause problems for user space tools
+	that use this string to parse the raw data as user space does not know
+	how to convert the string to its value.
+
+	To fix this, there's a special macro in the kernel that can be used
+	to convert an enum/sizeof into its value. If this macro is used, then
+	the print fmt strings will be converted to their values.
+
+	If something does not get converted properly, this option can be
+	used to show what enums/sizeof the kernel tried to convert.
+
+	This option is for debugging the conversions. A file is created
+	in the tracing directory called "eval_map" that will show the
+	names matched with their values and what trace event system they
+	belong too.
+
+	Normally, the mapping of the strings to values will be freed after
+	boot up or module load. With this option, they will not be freed, as
+	they are needed for the "eval_map" file. Enabling this option will
+	increase the memory footprint of the running kernel.
+
+	If unsure, say N
+
+config TRACING_EVENTS_GPIO
+	bool "Trace gpio events"
+	depends on GPIOLIB
+	default y
+	help
+	  Enable tracing events for gpio subsystem
+
+config GCOV_PROFILE_FTRACE
+	bool "Enable GCOV profiling on ftrace subsystem"
+	depends on GCOV_KERNEL
+	help
+	  Enable GCOV profiling on ftrace subsystem for checking
+	  which functions/lines are tested.
+
+	  If unsure, say N.
+
+	  Note that on a kernel compiled with this config, ftrace will
+	  run significantly slower.
+
+config MMSTAT_TRACER
+	tristate "Trace memory status periodically"
+	default m
+	help
+	  Periodic tracing of memory status.
+
+	  Mmstat tracer will track memory usage periodically according to
+	  indicated timer interval, which includes meminfo, buddy system,
+	  hardware memory(if possible) and process memory.
+
+endif # FTRACE
+
+endif # TRACING_SUPPORT
+
+if TRACING
+# MTK enhancements
+config MTK_FTRACER
+	bool "MTK Ftracer"
+	select CONTEXT_SWITCH_TRACER
+	help
+	  Mediatek ftrace enhancements to linux kernel, include boot trace
+	  and debug information. print enabled events list on trace log,
+	  developers can better analyze the problem
+
+	  If unsure, say N
+
+config MTK_FTRACE_DEFAULT_ENABLE
+	bool "enable events by default"
+	depends on MTK_FTRACER
+	help
+	  Enable ftrace at bootup e.g., enlarge ring_buffer size and enable
+	  configured events at bootup. With ftrace enabled and trace collected
+	  at exceptions, developers can better analyze the problem
+
+	  If unsure, say N
+
+endif # TRACING
+

kernel/trace/Makefile

@@ -0,0 +1,90 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Do not instrument the tracer itself:
+
+ifdef CONFIG_FUNCTION_TRACER
+ORIG_CFLAGS := $(KBUILD_CFLAGS)
+KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
+
+ifdef CONFIG_FTRACE_SELFTEST
+# selftest needs instrumentation
+CFLAGS_trace_selftest_dynamic.o = $(CC_FLAGS_FTRACE)
+obj-y += trace_selftest_dynamic.o
+endif
+endif
+
+ifdef CONFIG_FTRACE_STARTUP_TEST
+CFLAGS_trace_kprobe_selftest.o = $(CC_FLAGS_FTRACE)
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe_selftest.o
+endif
+
+# If unlikely tracing is enabled, do not trace these files
+ifdef CONFIG_TRACING_BRANCHES
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+endif
+
+# for GCOV coverage profiling
+ifdef CONFIG_GCOV_PROFILE_FTRACE
+GCOV_PROFILE := y
+endif
+
+CFLAGS_trace_benchmark.o := -I$(src)
+CFLAGS_trace_events_filter.o := -I$(src)
+
+obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o
+
+obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
+obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
+obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
+
+obj-$(CONFIG_TRACING) += trace.o
+obj-$(CONFIG_TRACING) += trace_output.o
+obj-$(CONFIG_TRACING) += trace_seq.o
+obj-$(CONFIG_TRACING) += trace_stat.o
+obj-$(CONFIG_TRACING) += trace_printk.o
+obj-$(CONFIG_TRACING_MAP) += tracing_map.o
+obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o
+obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
+obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
+obj-$(CONFIG_PREEMPTIRQ_TRACEPOINTS) += trace_preemptirq.o
+obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
+obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
+obj-$(CONFIG_TRACE_IRQFLAGS) += trace_irqsoff.o
+obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_HWLAT_TRACER) += trace_hwlat.o
+obj-$(CONFIG_NOP_TRACER) += trace_nop.o
+obj-$(CONFIG_STACK_TRACER) += trace_stack.o
+obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
+obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
+ifeq ($(CONFIG_BLOCK),y)
+obj-$(CONFIG_EVENT_TRACING) += blktrace.o
+endif
+obj-$(CONFIG_EVENT_TRACING) += trace_events.o
+obj-$(CONFIG_EVENT_TRACING) += trace_export.o
+obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
+ifeq ($(CONFIG_PERF_EVENTS),y)
+obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
+endif
+obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
+obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
+obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
+obj-$(CONFIG_TRACEPOINTS) += power-traces.o
+ifeq ($(CONFIG_PM),y)
+obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
+endif
+ifeq ($(CONFIG_TRACING),y)
+obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
+endif
+obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
+
+obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
+obj-$(CONFIG_MMSTAT_TRACER) += trace_mmstat.o
+
+libftrace-y := ftrace.o
+
+obj-$(CONFIG_TRACING) += mtk_trace.o

kernel/trace/mtk_ftrace.h

@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2015 MediaTek Inc.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mtk_ftrace
+
+#if !defined(_TRACE_MTK_FTRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MTK_FTRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(tracing_on,
+
+	TP_PROTO(int on, unsigned long ip),
+
+	TP_ARGS(on, ip),
+
+	TP_STRUCT__entry(
+		__field(int, on)
+		__field(unsigned long, ip)
+	),
+
+	TP_fast_assign(
+		__entry->on = on;
+		__entry->ip = ip;
+	),
+
+	TP_printk("ftrace is %s caller=%ps",
+		__entry->on ? "enabled" : "disabled",
+		(void *)__entry->ip)
+);
+
+#endif /* _TRACE_MTK_FTRACE_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE mtk_ftrace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
+/* MTK function define from here */
+#include <linux/string.h>
+#include <linux/seq_file.h>
+
+#ifdef CONFIG_MTK_FTRACER
+struct trace_buffer;
+void print_enabled_events(struct trace_buffer *buf, struct seq_file *m);
+void update_buf_size(unsigned long size);
+bool boot_ftrace_check(unsigned long trace_en);
+#if IS_BUILTIN(CONFIG_MTPROF)
+extern bool mt_boot_finish(void);
+#endif
+#endif/* CONFIG_TRACING && CONFIG_MTK_FTRACER */

kernel/trace/mtk_trace.c

@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2015 MediaTek Inc.
+ */
+
+#include <linux/ring_buffer.h>
+#include <linux/trace_events.h>
+#define CREATE_TRACE_POINTS
+#include "mtk_ftrace.h"
+#include "trace.h"
+
+
+#ifdef CONFIG_MTK_FTRACER
+static unsigned long buf_size = 25165824UL;
+static bool boot_trace;
+static __init int boot_trace_cmdline(char *str)
+{
+	boot_trace = true;
+	update_buf_size(buf_size);
+	return 0;
+}
+__setup("androidboot.boot_trace", boot_trace_cmdline);
+
+/* If boot tracing is on.Ignore tracing off command.*/
+bool boot_ftrace_check(unsigned long trace_en)
+{
+	bool boot_complete = false;
+
+	if (boot_trace != true || trace_en)
+		return false;
+
+#if IS_BUILTIN(CONFIG_MTPROF)
+	boot_complete = mt_boot_finish();
+#endif
+	if (!boot_complete) {
+		pr_info("Capturing boot ftrace,Ignore tracing off.\n");
+		return true;
+	}
+	return false;
+}
+
+#include <linux/rtc.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/sched/stat.h>
+
+
+void print_enabled_events(struct trace_buffer *buf, struct seq_file *m)
+{
+	struct trace_event_call *call;
+	struct trace_event_file *file;
+	struct trace_array *tr;
+
+	unsigned long usec_rem;
+	unsigned long long t;
+	struct rtc_time tm_utc, tm;
+	struct timeval tv = { 0 };
+
+	if (buf->tr)
+		tr = buf->tr;
+	else
+		return;
+
+	if (tr->name != NULL)
+		seq_printf(m, "# instance: %s, enabled events:", tr->name);
+	else
+		seq_puts(m, "# enabled events:");
+
+	list_for_each_entry(file, &tr->events, list) {
+		call = file->event_call;
+		if (file->flags & EVENT_FILE_FL_ENABLED)
+			seq_printf(m, " %s:%s", call->class->system,
+				   trace_event_name(call));
+	}
+
+	seq_puts(m, "\n");
+
+	t = sched_clock();
+	do_gettimeofday(&tv);
+	t = ns2usecs(t);
+	usec_rem = do_div(t, USEC_PER_SEC);
+	rtc_time_to_tm(tv.tv_sec, &tm_utc);
+	rtc_time_to_tm(tv.tv_sec - sys_tz.tz_minuteswest * 60, &tm);
+
+	seq_printf(m, "# kernel time now: %5llu.%06lu\n",
+		   t, usec_rem);
+	seq_printf(m, "# UTC time:\t%d-%02d-%02d %02d:%02d:%02d.%03u\n",
+			tm_utc.tm_year + 1900, tm_utc.tm_mon + 1,
+			tm_utc.tm_mday, tm_utc.tm_hour,
+			tm_utc.tm_min, tm_utc.tm_sec,
+			(unsigned int)tv.tv_usec);
+	seq_printf(m, "# android time:\t%d-%02d-%02d %02d:%02d:%02d.%03u\n",
+			tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+			tm.tm_hour, tm.tm_min, tm.tm_sec,
+			(unsigned int)tv.tv_usec);
+}
+
+/* ftrace's switch function for MTK solution */
+static void ftrace_events_enable(int enable)
+{
+	if (enable) {
+		trace_set_clr_event(NULL, "sched_switch", 1);
+		trace_set_clr_event(NULL, "sched_wakeup", 1);
+		trace_set_clr_event(NULL, "sched_wakeup_new", 1);
+		trace_set_clr_event(NULL, "sched_stat_iowait", 1);
+#ifdef CONFIG_SMP
+		trace_set_clr_event(NULL, "sched_migrate_task", 1);
+#endif
+		trace_set_clr_event(NULL, "workqueue_execute_start", 1);
+		trace_set_clr_event(NULL, "workqueue_execute_end", 1);
+		trace_set_clr_event(NULL, "cpu_frequency", 1);
+
+		trace_set_clr_event(NULL, "block_bio_frontmerge", 1);
+		trace_set_clr_event(NULL, "block_bio_backmerge", 1);
+		trace_set_clr_event(NULL, "block_rq_issue", 1);
+		trace_set_clr_event(NULL, "block_rq_insert", 1);
+		trace_set_clr_event(NULL, "block_rq_complete", 1);
+		trace_set_clr_event(NULL, "block_rq_requeue", 1);
+		trace_set_clr_event(NULL, "tracing_on", 1);
+
+		if (boot_trace) {
+			trace_set_clr_event("android_fs", NULL, 1);
+			trace_set_clr_event(NULL, "sched_blocked_reason", 1);
+			/*trace_set_clr_event(NULL, "sched_waking", 1);*/
+		} else {
+			trace_set_clr_event("ipi", NULL, 1);
+			trace_set_clr_event(NULL, "softirq_entry", 1);
+			trace_set_clr_event(NULL, "softirq_exit", 1);
+			trace_set_clr_event(NULL, "softirq_raise", 1);
+			trace_set_clr_event(NULL, "irq_handler_entry", 1);
+			trace_set_clr_event(NULL, "irq_handler_exit", 1);
+#ifdef CONFIG_MTK_SCHED_MONITOR
+			trace_set_clr_event(NULL, "sched_mon_msg", 1);
+#endif
+#ifdef CONFIG_LOCKDEP
+			trace_set_clr_event(NULL, "lock_dbg", 1);
+			trace_set_clr_event(NULL, "lock_monitor", 1);
+#endif
+#ifdef CONFIG_RCU_TRACE
+			trace_set_clr_event(NULL, "rcu_batch_start", 1);
+			trace_set_clr_event(NULL, "rcu_batch_end", 1);
+			trace_set_clr_event(NULL, "rcu_kfree_callback", 1);
+			trace_set_clr_event(NULL, "rcu_callback", 1);
+#endif
+		}
+
+		tracing_on();
+	} else {
+		tracing_off();
+		trace_set_clr_event(NULL, NULL, 0);
+	}
+}
+
+#ifdef CONFIG_MTK_PERF_TRACKER
+extern int perf_tracker_enable(int on);
+#endif
+static __init int boot_ftrace(void)
+{
+	struct trace_array *tr;
+	int ret;
+
+	if (boot_trace) {
+		tr = top_trace_array();
+		if (!tr) {
+			pr_info("[ftrace]Error: Tracer list is empty.\n");
+			return 0;
+		}
+
+#ifdef CONFIG_MTK_PERF_TRACKER
+		perf_tracker_enable(1);
+#endif
+		ret = tracing_update_buffers();
+		if (ret != 0)
+			pr_debug("unable to expand buffer, ret=%d\n", ret);
+#ifdef CONFIG_SCHEDSTATS
+		force_schedstat_enabled();
+#endif
+
+		ftrace_events_enable(1);
+		set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 0);
+		pr_debug("[ftrace]boot-time profiling...\n");
+	}
+	return 0;
+}
+core_initcall(boot_ftrace);
+
+#ifdef CONFIG_MTK_FTRACE_DEFAULT_ENABLE
+static __init int enable_ftrace(void)
+{
+	int ret;
+
+	if (!boot_trace) {
+		/* enable ftrace facilities */
+		ftrace_events_enable(1);
+
+		/*
+		 * only update buffer eariler
+		 * if we want to collect boot-time ftrace
+		 * to avoid the boot time impacted by
+		 * early-expanded ring buffer
+		 */
+		ret = tracing_update_buffers();
+		if (ret != 0)
+			pr_debug("fail to update buffer, ret=%d\n",
+				 ret);
+		else
+			pr_debug("[ftrace]ftrace ready...\n");
+	}
+	return 0;
+}
+late_initcall(enable_ftrace);
+#endif
+#endif
+

kernel/trace/power-traces.c

@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Arjan van de Ven <arjan@linux.intel.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_frequency);
+EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(clock_set_rate);

kernel/trace/preemptirq_delay_test.c

@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Preempt / IRQ disable delay thread to test latency tracers
+ *
+ * Copyright (C) 2018 Joel Fernandes (Google) <joel@joelfernandes.org>
+ */
+
+#include <linux/trace_clock.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/string.h>
+
+static ulong delay = 100;
+static char test_mode[10] = "irq";
+
+module_param_named(delay, delay, ulong, S_IRUGO);
+module_param_string(test_mode, test_mode, 10, S_IRUGO);
+MODULE_PARM_DESC(delay, "Period in microseconds (100 uS default)");
+MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt or irq (default irq)");
+
+static void busy_wait(ulong time)
+{
+	u64 start, end;
+	start = trace_clock_local();
+	do {
+		end = trace_clock_local();
+		if (kthread_should_stop())
+			break;
+	} while ((end - start) < (time * 1000));
+}
+
+static int preemptirq_delay_run(void *data)
+{
+	unsigned long flags;
+
+	if (!strcmp(test_mode, "irq")) {
+		local_irq_save(flags);
+		busy_wait(delay);
+		local_irq_restore(flags);
+	} else if (!strcmp(test_mode, "preempt")) {
+		preempt_disable();
+		busy_wait(delay);
+		preempt_enable();
+	}
+
+	return 0;
+}
+
+static int __init preemptirq_delay_init(void)
+{
+	char task_name[50];
+	struct task_struct *test_task;
+
+	snprintf(task_name, sizeof(task_name), "%s_test", test_mode);
+
+	test_task = kthread_run(preemptirq_delay_run, NULL, task_name);
+	return PTR_ERR_OR_ZERO(test_task);
+}
+
+static void __exit preemptirq_delay_exit(void)
+{
+	return;
+}
+
+module_init(preemptirq_delay_init)
+module_exit(preemptirq_delay_exit)
+MODULE_LICENSE("GPL v2");

kernel/trace/ring_buffer_benchmark.c

@@ -0,0 +1,499 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ring buffer tester and benchmark
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
+#include <linux/module.h>
+#include <linux/ktime.h>
+#include <asm/local.h>
+
+struct rb_page {
+	u64		ts;
+	local_t		commit;
+	char		data[4080];
+};
+
+/* run time and sleep time in seconds */
+#define RUN_TIME	10ULL
+#define SLEEP_TIME	10
+
+/* number of events for writer to wake up the reader */
+static int wakeup_interval = 100;
+
+static int reader_finish;
+static DECLARE_COMPLETION(read_start);
+static DECLARE_COMPLETION(read_done);
+
+static struct ring_buffer *buffer;
+static struct task_struct *producer;
+static struct task_struct *consumer;
+static unsigned long read;
+
+static unsigned int disable_reader;
+module_param(disable_reader, uint, 0644);
+MODULE_PARM_DESC(disable_reader, "only run producer");
+
+static unsigned int write_iteration = 50;
+module_param(write_iteration, uint, 0644);
+MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
+
+static int producer_nice = MAX_NICE;
+static int consumer_nice = MAX_NICE;
+
+static int producer_fifo = -1;
+static int consumer_fifo = -1;
+
+module_param(producer_nice, int, 0644);
+MODULE_PARM_DESC(producer_nice, "nice prio for producer");
+
+module_param(consumer_nice, int, 0644);
+MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
+
+module_param(producer_fifo, int, 0644);
+MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+
+module_param(consumer_fifo, int, 0644);
+MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+
+static int read_events;
+
+static int test_error;
+
+#define TEST_ERROR()				\
+	do {					\
+		if (!test_error) {		\
+			test_error = 1;		\
+			WARN_ON(1);		\
+		}				\
+	} while (0)
+
+enum event_status {
+	EVENT_FOUND,
+	EVENT_DROPPED,
+};
+
+static bool break_test(void)
+{
+	return test_error || kthread_should_stop();
+}
+
+static enum event_status read_event(int cpu)
+{
+	struct ring_buffer_event *event;
+	int *entry;
+	u64 ts;
+
+	event = ring_buffer_consume(buffer, cpu, &ts, NULL);
+	if (!event)
+		return EVENT_DROPPED;
+
+	entry = ring_buffer_event_data(event);
+	if (*entry != cpu) {
+		TEST_ERROR();
+		return EVENT_DROPPED;
+	}
+
+	read++;
+	return EVENT_FOUND;
+}
+
+static enum event_status read_page(int cpu)
+{
+	struct ring_buffer_event *event;
+	struct rb_page *rpage;
+	unsigned long commit;
+	void *bpage;
+	int *entry;
+	int ret;
+	int inc;
+	int i;
+
+	bpage = ring_buffer_alloc_read_page(buffer, cpu);
+	if (IS_ERR(bpage))
+		return EVENT_DROPPED;
+
+	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+	if (ret >= 0) {
+		rpage = bpage;
+		/* The commit may have missed event flags set, clear them */
+		commit = local_read(&rpage->commit) & 0xfffff;
+		for (i = 0; i < commit && !test_error ; i += inc) {
+
+			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+				TEST_ERROR();
+				break;
+			}
+
+			inc = -1;
+			event = (void *)&rpage->data[i];
+			switch (event->type_len) {
+			case RINGBUF_TYPE_PADDING:
+				/* failed writes may be discarded events */
+				if (!event->time_delta)
+					TEST_ERROR();
+				inc = event->array[0] + 4;
+				break;
+			case RINGBUF_TYPE_TIME_EXTEND:
+				inc = 8;
+				break;
+			case 0:
+				entry = ring_buffer_event_data(event);
+				if (*entry != cpu) {
+					TEST_ERROR();
+					break;
+				}
+				read++;
+				if (!event->array[0]) {
+					TEST_ERROR();
+					break;
+				}
+				inc = event->array[0] + 4;
+				break;
+			default:
+				entry = ring_buffer_event_data(event);
+				if (*entry != cpu) {
+					TEST_ERROR();
+					break;
+				}
+				read++;
+				inc = ((event->type_len + 1) * 4);
+			}
+			if (test_error)
+				break;
+
+			if (inc <= 0) {
+				TEST_ERROR();
+				break;
+			}
+		}
+	}
+	ring_buffer_free_read_page(buffer, cpu, bpage);
+
+	if (ret < 0)
+		return EVENT_DROPPED;
+	return EVENT_FOUND;
+}
+
+static void ring_buffer_consumer(void)
+{
+	/* toggle between reading pages and events */
+	read_events ^= 1;
+
+	read = 0;
+	/*
+	 * Continue running until the producer specifically asks to stop
+	 * and is ready for the completion.
+	 */
+	while (!READ_ONCE(reader_finish)) {
+		int found = 1;
+
+		while (found && !test_error) {
+			int cpu;
+
+			found = 0;
+			for_each_online_cpu(cpu) {
+				enum event_status stat;
+
+				if (read_events)
+					stat = read_event(cpu);
+				else
+					stat = read_page(cpu);
+
+				if (test_error)
+					break;
+
+				if (stat == EVENT_FOUND)
+					found = 1;
+
+			}
+		}
+
+		/* Wait till the producer wakes us up when there is more data
+		 * available or when the producer wants us to finish reading.
+		 */
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (reader_finish)
+			break;
+
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+	reader_finish = 0;
+	complete(&read_done);
+}
+
+static void ring_buffer_producer(void)
+{
+	ktime_t start_time, end_time, timeout;
+	unsigned long long time;
+	unsigned long long entries;
+	unsigned long long overruns;
+	unsigned long missed = 0;
+	unsigned long hit = 0;
+	unsigned long avg;
+	int cnt = 0;
+
+	/*
+	 * Hammer the buffer for 10 secs (this may
+	 * make the system stall)
+	 */
+	trace_printk("Starting ring buffer hammer\n");
+	start_time = ktime_get();
+	timeout = ktime_add_ns(start_time, RUN_TIME * NSEC_PER_SEC);
+	do {
+		struct ring_buffer_event *event;
+		int *entry;
+		int i;
+
+		for (i = 0; i < write_iteration; i++) {
+			event = ring_buffer_lock_reserve(buffer, 10);
+			if (!event) {
+				missed++;
+			} else {
+				hit++;
+				entry = ring_buffer_event_data(event);
+				*entry = smp_processor_id();
+				ring_buffer_unlock_commit(buffer, event);
+			}
+		}
+		end_time = ktime_get();
+
+		cnt++;
+		if (consumer && !(cnt % wakeup_interval))
+			wake_up_process(consumer);
+
+#ifndef CONFIG_PREEMPT
+		/*
+		 * If we are a non preempt kernel, the 10 second run will
+		 * stop everything while it runs. Instead, we will call
+		 * cond_resched and also add any time that was lost by a
+		 * rescedule.
+		 *
+		 * Do a cond resched at the same frequency we would wake up
+		 * the reader.
+		 */
+		if (cnt % wakeup_interval)
+			cond_resched();
+#endif
+	} while (ktime_before(end_time, timeout) && !break_test());
+	trace_printk("End ring buffer hammer\n");
+
+	if (consumer) {
+		/* Init both completions here to avoid races */
+		init_completion(&read_start);
+		init_completion(&read_done);
+		/* the completions must be visible before the finish var */
+		smp_wmb();
+		reader_finish = 1;
+		wake_up_process(consumer);
+		wait_for_completion(&read_done);
+	}
+
+	time = ktime_us_delta(end_time, start_time);
+
+	entries = ring_buffer_entries(buffer);
+	overruns = ring_buffer_overruns(buffer);
+
+	if (test_error)
+		trace_printk("ERROR!\n");
+
+	if (!disable_reader) {
+		if (consumer_fifo < 0)
+			trace_printk("Running Consumer at nice: %d\n",
+				     consumer_nice);
+		else
+			trace_printk("Running Consumer at SCHED_FIFO %d\n",
+				     consumer_fifo);
+	}
+	if (producer_fifo < 0)
+		trace_printk("Running Producer at nice: %d\n",
+			     producer_nice);
+	else
+		trace_printk("Running Producer at SCHED_FIFO %d\n",
+			     producer_fifo);
+
+	/* Let the user know that the test is running at low priority */
+	if (producer_fifo < 0 && consumer_fifo < 0 &&
+	    producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
+		trace_printk("WARNING!!! This test is running at lowest priority.\n");
+
+	trace_printk("Time:     %lld (usecs)\n", time);
+	trace_printk("Overruns: %lld\n", overruns);
+	if (disable_reader)
+		trace_printk("Read:     (reader disabled)\n");
+	else
+		trace_printk("Read:     %ld  (by %s)\n", read,
+			read_events ? "events" : "pages");
+	trace_printk("Entries:  %lld\n", entries);
+	trace_printk("Total:    %lld\n", entries + overruns + read);
+	trace_printk("Missed:   %ld\n", missed);
+	trace_printk("Hit:      %ld\n", hit);
+
+	/* Convert time from usecs to millisecs */
+	do_div(time, USEC_PER_MSEC);
+	if (time)
+		hit /= (long)time;
+	else
+		trace_printk("TIME IS ZERO??\n");
+
+	trace_printk("Entries per millisec: %ld\n", hit);
+
+	if (hit) {
+		/* Calculate the average time in nanosecs */
+		avg = NSEC_PER_MSEC / hit;
+		trace_printk("%ld ns per entry\n", avg);
+	}
+
+	if (missed) {
+		if (time)
+			missed /= (long)time;
+
+		trace_printk("Total iterations per millisec: %ld\n",
+			     hit + missed);
+
+		/* it is possible that hit + missed will overflow and be zero */
+		if (!(hit + missed)) {
+			trace_printk("hit + missed overflowed and totalled zero!\n");
+			hit--; /* make it non zero */
+		}
+
+		/* Caculate the average time in nanosecs */
+		avg = NSEC_PER_MSEC / (hit + missed);
+		trace_printk("%ld ns per entry\n", avg);
+	}
+}
+
+static void wait_to_die(void)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+static int ring_buffer_consumer_thread(void *arg)
+{
+	while (!break_test()) {
+		complete(&read_start);
+
+		ring_buffer_consumer();
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (break_test())
+			break;
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	if (!kthread_should_stop())
+		wait_to_die();
+
+	return 0;
+}
+
+static int ring_buffer_producer_thread(void *arg)
+{
+	while (!break_test()) {
+		ring_buffer_reset(buffer);
+
+		if (consumer) {
+			wake_up_process(consumer);
+			wait_for_completion(&read_start);
+		}
+
+		ring_buffer_producer();
+		if (break_test())
+			goto out_kill;
+
+		trace_printk("Sleeping for 10 secs\n");
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (break_test())
+			goto out_kill;
+		schedule_timeout(HZ * SLEEP_TIME);
+	}
+
+out_kill:
+	__set_current_state(TASK_RUNNING);
+	if (!kthread_should_stop())
+		wait_to_die();
+
+	return 0;
+}
+
+static int __init ring_buffer_benchmark_init(void)
+{
+	int ret;
+
+	/* make a one meg buffer in overwite mode */
+	buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
+	if (!buffer)
+		return -ENOMEM;
+
+	if (!disable_reader) {
+		consumer = kthread_create(ring_buffer_consumer_thread,
+					  NULL, "rb_consumer");
+		ret = PTR_ERR(consumer);
+		if (IS_ERR(consumer))
+			goto out_fail;
+	}
+
+	producer = kthread_run(ring_buffer_producer_thread,
+			       NULL, "rb_producer");
+	ret = PTR_ERR(producer);
+
+	if (IS_ERR(producer))
+		goto out_kill;
+
+	/*
+	 * Run them as low-prio background tasks by default:
+	 */
+	if (!disable_reader) {
+		if (consumer_fifo >= 0) {
+			struct sched_param param = {
+				.sched_priority = consumer_fifo
+			};
+			sched_setscheduler(consumer, SCHED_FIFO, &param);
+		} else
+			set_user_nice(consumer, consumer_nice);
+	}
+
+	if (producer_fifo >= 0) {
+		struct sched_param param = {
+			.sched_priority = producer_fifo
+		};
+		sched_setscheduler(producer, SCHED_FIFO, &param);
+	} else
+		set_user_nice(producer, producer_nice);
+
+	return 0;
+
+ out_kill:
+	if (consumer)
+		kthread_stop(consumer);
+
+ out_fail:
+	ring_buffer_free(buffer);
+	return ret;
+}
+
+static void __exit ring_buffer_benchmark_exit(void)
+{
+	kthread_stop(producer);
+	if (consumer)
+		kthread_stop(consumer);
+	ring_buffer_free(buffer);
+}
+
+module_init(ring_buffer_benchmark_init);
+module_exit(ring_buffer_benchmark_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("ring_buffer_benchmark");
+MODULE_LICENSE("GPL");

kernel/trace/rpm-traces.c

@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Ming Lei <ming.lei@canonical.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/usb.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/rpm.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_return_int);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_suspend);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_resume);

kernel/trace/trace_benchmark.c

@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/trace_clock.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace_benchmark.h"
+
+static struct task_struct *bm_event_thread;
+
+static char bm_str[BENCHMARK_EVENT_STRLEN] = "START";
+
+static u64 bm_total;
+static u64 bm_totalsq;
+static u64 bm_last;
+static u64 bm_max;
+static u64 bm_min;
+static u64 bm_first;
+static u64 bm_cnt;
+static u64 bm_stddev;
+static unsigned int bm_avg;
+static unsigned int bm_std;
+
+static bool ok_to_run;
+
+/*
+ * This gets called in a loop recording the time it took to write
+ * the tracepoint. What it writes is the time statistics of the last
+ * tracepoint write. As there is nothing to write the first time
+ * it simply writes "START". As the first write is cold cache and
+ * the rest is hot, we save off that time in bm_first and it is
+ * reported as "first", which is shown in the second write to the
+ * tracepoint. The "first" field is writen within the statics from
+ * then on but never changes.
+ */
+static void trace_do_benchmark(void)
+{
+	u64 start;
+	u64 stop;
+	u64 delta;
+	u64 stddev;
+	u64 seed;
+	u64 last_seed;
+	unsigned int avg;
+	unsigned int std = 0;
+
+	/* Only run if the tracepoint is actually active */
+	if (!trace_benchmark_event_enabled() || !tracing_is_on())
+		return;
+
+	local_irq_disable();
+	start = trace_clock_local();
+	trace_benchmark_event(bm_str);
+	stop = trace_clock_local();
+	local_irq_enable();
+
+	bm_cnt++;
+
+	delta = stop - start;
+
+	/*
+	 * The first read is cold cached, keep it separate from the
+	 * other calculations.
+	 */
+	if (bm_cnt == 1) {
+		bm_first = delta;
+		scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+			  "first=%llu [COLD CACHED]", bm_first);
+		return;
+	}
+
+	bm_last = delta;
+
+	if (delta > bm_max)
+		bm_max = delta;
+	if (!bm_min || delta < bm_min)
+		bm_min = delta;
+
+	/*
+	 * When bm_cnt is greater than UINT_MAX, it breaks the statistics
+	 * accounting. Freeze the statistics when that happens.
+	 * We should have enough data for the avg and stddev anyway.
+	 */
+	if (bm_cnt > UINT_MAX) {
+		scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+		    "last=%llu first=%llu max=%llu min=%llu ** avg=%u std=%d std^2=%lld",
+			  bm_last, bm_first, bm_max, bm_min, bm_avg, bm_std, bm_stddev);
+		return;
+	}
+
+	bm_total += delta;
+	bm_totalsq += delta * delta;
+
+
+	if (bm_cnt > 1) {
+		/*
+		 * Apply Welford's method to calculate standard deviation:
+		 * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
+		 */
+		stddev = (u64)bm_cnt * bm_totalsq - bm_total * bm_total;
+		do_div(stddev, (u32)bm_cnt);
+		do_div(stddev, (u32)bm_cnt - 1);
+	} else
+		stddev = 0;
+
+	delta = bm_total;
+	do_div(delta, bm_cnt);
+	avg = delta;
+
+	if (stddev > 0) {
+		int i = 0;
+		/*
+		 * stddev is the square of standard deviation but
+		 * we want the actualy number. Use the average
+		 * as our seed to find the std.
+		 *
+		 * The next try is:
+		 *  x = (x + N/x) / 2
+		 *
+		 * Where N is the squared number to find the square
+		 * root of.
+		 */
+		seed = avg;
+		do {
+			last_seed = seed;
+			seed = stddev;
+			if (!last_seed)
+				break;
+			do_div(seed, last_seed);
+			seed += last_seed;
+			do_div(seed, 2);
+		} while (i++ < 10 && last_seed != seed);
+
+		std = seed;
+	}
+
+	scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+		  "last=%llu first=%llu max=%llu min=%llu avg=%u std=%d std^2=%lld",
+		  bm_last, bm_first, bm_max, bm_min, avg, std, stddev);
+
+	bm_std = std;
+	bm_avg = avg;
+	bm_stddev = stddev;
+}
+
+static int benchmark_event_kthread(void *arg)
+{
+	/* sleep a bit to make sure the tracepoint gets activated */
+	msleep(100);
+
+	while (!kthread_should_stop()) {
+
+		trace_do_benchmark();
+
+		/*
+		 * We don't go to sleep, but let others run as well.
+		 * This is bascially a "yield()" to let any task that
+		 * wants to run, schedule in, but if the CPU is idle,
+		 * we'll keep burning cycles.
+		 *
+		 * Note the tasks_rcu_qs() version of cond_resched() will
+		 * notify synchronize_rcu_tasks() that this thread has
+		 * passed a quiescent state for rcu_tasks. Otherwise
+		 * this thread will never voluntarily schedule which would
+		 * block synchronize_rcu_tasks() indefinitely.
+		 */
+		cond_resched_tasks_rcu_qs();
+	}
+
+	return 0;
+}
+
+/*
+ * When the benchmark tracepoint is enabled, it calls this
+ * function and the thread that calls the tracepoint is created.
+ */
+int trace_benchmark_reg(void)
+{
+	if (!ok_to_run) {
+		pr_warning("trace benchmark cannot be started via kernel command line\n");
+		return -EBUSY;
+	}
+
+	bm_event_thread = kthread_run(benchmark_event_kthread,
+				      NULL, "event_benchmark");
+	if (IS_ERR(bm_event_thread)) {
+		pr_warning("trace benchmark failed to create kernel thread\n");
+		return PTR_ERR(bm_event_thread);
+	}
+
+	return 0;
+}
+
+/*
+ * When the benchmark tracepoint is disabled, it calls this
+ * function and the thread that calls the tracepoint is deleted
+ * and all the numbers are reset.
+ */
+void trace_benchmark_unreg(void)
+{
+	if (!bm_event_thread)
+		return;
+
+	kthread_stop(bm_event_thread);
+	bm_event_thread = NULL;
+
+	strcpy(bm_str, "START");
+	bm_total = 0;
+	bm_totalsq = 0;
+	bm_last = 0;
+	bm_max = 0;
+	bm_min = 0;
+	bm_cnt = 0;
+	/* These don't need to be reset but reset them anyway */
+	bm_first = 0;
+	bm_std = 0;
+	bm_avg = 0;
+	bm_stddev = 0;
+}
+
+static __init int ok_to_run_trace_benchmark(void)
+{
+	ok_to_run = true;
+
+	return 0;
+}
+
+early_initcall(ok_to_run_trace_benchmark);

kernel/trace/trace_benchmark.h

@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM benchmark
+
+#if !defined(_TRACE_BENCHMARK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BENCHMARK_H
+
+#include <linux/tracepoint.h>
+
+extern int trace_benchmark_reg(void);
+extern void trace_benchmark_unreg(void);
+
+#define BENCHMARK_EVENT_STRLEN		128
+
+TRACE_EVENT_FN(benchmark_event,
+
+	TP_PROTO(const char *str),
+
+	TP_ARGS(str),
+
+	TP_STRUCT__entry(
+		__array(	char,	str,	BENCHMARK_EVENT_STRLEN	)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->str, str, BENCHMARK_EVENT_STRLEN);
+	),
+
+	TP_printk("%s", __entry->str),
+
+	trace_benchmark_reg, trace_benchmark_unreg
+);
+
+#endif /* _TRACE_BENCHMARK_H */
+
+#undef TRACE_INCLUDE_FILE
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_benchmark
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

kernel/trace/trace_branch.c

@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * unlikely profiler
+ *
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/irqflags.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/hash.h>
+#include <linux/fs.h>
+#include <asm/local.h>
+
+#include "trace.h"
+#include "trace_stat.h"
+#include "trace_output.h"
+
+#ifdef CONFIG_BRANCH_TRACER
+
+static struct tracer branch_trace;
+static int branch_tracing_enabled __read_mostly;
+static DEFINE_MUTEX(branch_tracing_mutex);
+
+static struct trace_array *branch_tracer;
+
+static void
+probe_likely_condition(struct ftrace_likely_data *f, int val, int expect)
+{
+	struct trace_event_call *call = &event_branch;
+	struct trace_array *tr = branch_tracer;
+	struct trace_array_cpu *data;
+	struct ring_buffer_event *event;
+	struct trace_branch *entry;
+	struct ring_buffer *buffer;
+	unsigned long flags;
+	int pc;
+	const char *p;
+
+	if (current->trace_recursion & TRACE_BRANCH_BIT)
+		return;
+
+	/*
+	 * I would love to save just the ftrace_likely_data pointer, but
+	 * this code can also be used by modules. Ugly things can happen
+	 * if the module is unloaded, and then we go and read the
+	 * pointer.  This is slower, but much safer.
+	 */
+
+	if (unlikely(!tr))
+		return;
+
+	raw_local_irq_save(flags);
+	current->trace_recursion |= TRACE_BRANCH_BIT;
+	data = this_cpu_ptr(tr->trace_buffer.data);
+	if (atomic_read(&data->disabled))
+		goto out;
+
+	pc = preempt_count();
+	buffer = tr->trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		goto out;
+
+	entry	= ring_buffer_event_data(event);
+
+	/* Strip off the path, only save the file */
+	p = f->data.file + strlen(f->data.file);
+	while (p >= f->data.file && *p != '/')
+		p--;
+	p++;
+
+	strncpy(entry->func, f->data.func, TRACE_FUNC_SIZE);
+	strncpy(entry->file, p, TRACE_FILE_SIZE);
+	entry->func[TRACE_FUNC_SIZE] = 0;
+	entry->file[TRACE_FILE_SIZE] = 0;
+	entry->constant = f->constant;
+	entry->line = f->data.line;
+	entry->correct = val == expect;
+
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit_nostack(buffer, event);
+
+ out:
+	current->trace_recursion &= ~TRACE_BRANCH_BIT;
+	raw_local_irq_restore(flags);
+}
+
+static inline
+void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect)
+{
+	if (!branch_tracing_enabled)
+		return;
+
+	probe_likely_condition(f, val, expect);
+}
+
+int enable_branch_tracing(struct trace_array *tr)
+{
+	mutex_lock(&branch_tracing_mutex);
+	branch_tracer = tr;
+	/*
+	 * Must be seen before enabling. The reader is a condition
+	 * where we do not need a matching rmb()
+	 */
+	smp_wmb();
+	branch_tracing_enabled++;
+	mutex_unlock(&branch_tracing_mutex);
+
+	return 0;
+}
+
+void disable_branch_tracing(void)
+{
+	mutex_lock(&branch_tracing_mutex);
+
+	if (!branch_tracing_enabled)
+		goto out_unlock;
+
+	branch_tracing_enabled--;
+
+ out_unlock:
+	mutex_unlock(&branch_tracing_mutex);
+}
+
+static int branch_trace_init(struct trace_array *tr)
+{
+	return enable_branch_tracing(tr);
+}
+
+static void branch_trace_reset(struct trace_array *tr)
+{
+	disable_branch_tracing();
+}
+
+static enum print_line_t trace_branch_print(struct trace_iterator *iter,
+					    int flags, struct trace_event *event)
+{
+	struct trace_branch *field;
+
+	trace_assign_type(field, iter->ent);
+
+	trace_seq_printf(&iter->seq, "[%s] %s:%s:%d\n",
+			 field->correct ? "  ok  " : " MISS ",
+			 field->func,
+			 field->file,
+			 field->line);
+
+	return trace_handle_return(&iter->seq);
+}
+
+static void branch_print_header(struct seq_file *s)
+{
+	seq_puts(s, "#           TASK-PID    CPU#    TIMESTAMP  CORRECT"
+		    "  FUNC:FILE:LINE\n"
+		    "#              | |       |          |         |   "
+		    "    |\n");
+}
+
+static struct trace_event_functions trace_branch_funcs = {
+	.trace		= trace_branch_print,
+};
+
+static struct trace_event trace_branch_event = {
+	.type		= TRACE_BRANCH,
+	.funcs		= &trace_branch_funcs,
+};
+
+static struct tracer branch_trace __read_mostly =
+{
+	.name		= "branch",
+	.init		= branch_trace_init,
+	.reset		= branch_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest	= trace_selftest_startup_branch,
+#endif /* CONFIG_FTRACE_SELFTEST */
+	.print_header	= branch_print_header,
+};
+
+__init static int init_branch_tracer(void)
+{
+	int ret;
+
+	ret = register_trace_event(&trace_branch_event);
+	if (!ret) {
+		printk(KERN_WARNING "Warning: could not register "
+				    "branch events\n");
+		return 1;
+	}
+	return register_tracer(&branch_trace);
+}
+core_initcall(init_branch_tracer);
+
+#else
+static inline
+void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
+void ftrace_likely_update(struct ftrace_likely_data *f, int val,
+			  int expect, int is_constant)
+{
+	/* A constant is always correct */
+	if (is_constant) {
+		f->constant++;
+		val = expect;
+	}
+	/*
+	 * I would love to have a trace point here instead, but the
+	 * trace point code is so inundated with unlikely and likely
+	 * conditions that the recursive nightmare that exists is too
+	 * much to try to get working. At least for now.
+	 */
+	trace_likely_condition(f, val, expect);
+
+	/* FIXME: Make this atomic! */
+	if (val == expect)
+		f->data.correct++;
+	else
+		f->data.incorrect++;
+}
+EXPORT_SYMBOL(ftrace_likely_update);
+
+extern unsigned long __start_annotated_branch_profile[];
+extern unsigned long __stop_annotated_branch_profile[];
+
+static int annotated_branch_stat_headers(struct seq_file *m)
+{
+	seq_puts(m, " correct incorrect  % "
+		    "       Function                "
+		    "  File              Line\n"
+		    " ------- ---------  - "
+		    "       --------                "
+		    "  ----              ----\n");
+	return 0;
+}
+
+static inline long get_incorrect_percent(struct ftrace_branch_data *p)
+{
+	long percent;
+
+	if (p->correct) {
+		percent = p->incorrect * 100;
+		percent /= p->correct + p->incorrect;
+	} else
+		percent = p->incorrect ? 100 : -1;
+
+	return percent;
+}
+
+static const char *branch_stat_process_file(struct ftrace_branch_data *p)
+{
+	const char *f;
+
+	/* Only print the file, not the path */
+	f = p->file + strlen(p->file);
+	while (f >= p->file && *f != '/')
+		f--;
+	return ++f;
+}
+
+static void branch_stat_show(struct seq_file *m,
+			     struct ftrace_branch_data *p, const char *f)
+{
+	long percent;
+
+	/*
+	 * The miss is overlayed on correct, and hit on incorrect.
+	 */
+	percent = get_incorrect_percent(p);
+
+	if (percent < 0)
+		seq_puts(m, "  X ");
+	else
+		seq_printf(m, "%3ld ", percent);
+
+	seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line);
+}
+
+static int branch_stat_show_normal(struct seq_file *m,
+				   struct ftrace_branch_data *p, const char *f)
+{
+	seq_printf(m, "%8lu %8lu ",  p->correct, p->incorrect);
+	branch_stat_show(m, p, f);
+	return 0;
+}
+
+static int annotate_branch_stat_show(struct seq_file *m, void *v)
+{
+	struct ftrace_likely_data *p = v;
+	const char *f;
+	int l;
+
+	f = branch_stat_process_file(&p->data);
+
+	if (!p->constant)
+		return branch_stat_show_normal(m, &p->data, f);
+
+	l = snprintf(NULL, 0, "/%lu", p->constant);
+	l = l > 8 ? 0 : 8 - l;
+
+	seq_printf(m, "%8lu/%lu %*lu ",
+		   p->data.correct, p->constant, l, p->data.incorrect);
+	branch_stat_show(m, &p->data, f);
+	return 0;
+}
+
+static void *annotated_branch_stat_start(struct tracer_stat *trace)
+{
+	return __start_annotated_branch_profile;
+}
+
+static void *
+annotated_branch_stat_next(void *v, int idx)
+{
+	struct ftrace_likely_data *p = v;
+
+	++p;
+
+	if ((void *)p >= (void *)__stop_annotated_branch_profile)
+		return NULL;
+
+	return p;
+}
+
+static int annotated_branch_stat_cmp(void *p1, void *p2)
+{
+	struct ftrace_branch_data *a = p1;
+	struct ftrace_branch_data *b = p2;
+
+	long percent_a, percent_b;
+
+	percent_a = get_incorrect_percent(a);
+	percent_b = get_incorrect_percent(b);
+
+	if (percent_a < percent_b)
+		return -1;
+	if (percent_a > percent_b)
+		return 1;
+
+	if (a->incorrect < b->incorrect)
+		return -1;
+	if (a->incorrect > b->incorrect)
+		return 1;
+
+	/*
+	 * Since the above shows worse (incorrect) cases
+	 * first, we continue that by showing best (correct)
+	 * cases last.
+	 */
+	if (a->correct > b->correct)
+		return -1;
+	if (a->correct < b->correct)
+		return 1;
+
+	return 0;
+}
+
+static struct tracer_stat annotated_branch_stats = {
+	.name = "branch_annotated",
+	.stat_start = annotated_branch_stat_start,
+	.stat_next = annotated_branch_stat_next,
+	.stat_cmp = annotated_branch_stat_cmp,
+	.stat_headers = annotated_branch_stat_headers,
+	.stat_show = annotate_branch_stat_show
+};
+
+__init static int init_annotated_branch_stats(void)
+{
+	int ret;
+
+	ret = register_stat_tracer(&annotated_branch_stats);
+	if (!ret) {
+		printk(KERN_WARNING "Warning: could not register "
+				    "annotated branches stats\n");
+		return 1;
+	}
+	return 0;
+}
+fs_initcall(init_annotated_branch_stats);
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+
+extern unsigned long __start_branch_profile[];
+extern unsigned long __stop_branch_profile[];
+
+static int all_branch_stat_headers(struct seq_file *m)
+{
+	seq_puts(m, "   miss      hit    % "
+		    "       Function                "
+		    "  File              Line\n"
+		    " ------- ---------  - "
+		    "       --------                "
+		    "  ----              ----\n");
+	return 0;
+}
+
+static void *all_branch_stat_start(struct tracer_stat *trace)
+{
+	return __start_branch_profile;
+}
+
+static void *
+all_branch_stat_next(void *v, int idx)
+{
+	struct ftrace_branch_data *p = v;
+
+	++p;
+
+	if ((void *)p >= (void *)__stop_branch_profile)
+		return NULL;
+
+	return p;
+}
+
+static int all_branch_stat_show(struct seq_file *m, void *v)
+{
+	struct ftrace_branch_data *p = v;
+	const char *f;
+
+	f = branch_stat_process_file(p);
+	return branch_stat_show_normal(m, p, f);
+}
+
+static struct tracer_stat all_branch_stats = {
+	.name = "branch_all",
+	.stat_start = all_branch_stat_start,
+	.stat_next = all_branch_stat_next,
+	.stat_headers = all_branch_stat_headers,
+	.stat_show = all_branch_stat_show
+};
+
+__init static int all_annotated_branch_stats(void)
+{
+	int ret;
+
+	ret = register_stat_tracer(&all_branch_stats);
+	if (!ret) {
+		printk(KERN_WARNING "Warning: could not register "
+				    "all branches stats\n");
+		return 1;
+	}
+	return 0;
+}
+fs_initcall(all_annotated_branch_stats);
+#endif /* CONFIG_PROFILE_ALL_BRANCHES */

kernel/trace/trace_clock.c

@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tracing clocks
+ *
+ *  Copyright (C) 2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ * Implements 3 trace clock variants, with differing scalability/precision
+ * tradeoffs:
+ *
+ *  -   local: CPU-local trace clock
+ *  -  medium: scalable global clock with some jitter
+ *  -  global: globally monotonic, serialized clock
+ *
+ * Tracer plugins will chose a default from these clocks.
+ */
+#include <linux/spinlock.h>
+#include <linux/irqflags.h>
+#include <linux/hardirq.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/ktime.h>
+#include <linux/trace_clock.h>
+
+/*
+ * trace_clock_local(): the simplest and least coherent tracing clock.
+ *
+ * Useful for tracing that does not cross to other CPUs nor
+ * does it go through idle events.
+ */
+u64 notrace trace_clock_local(void)
+{
+	u64 clock;
+
+	/*
+	 * sched_clock() is an architecture implemented, fast, scalable,
+	 * lockless clock. It is not guaranteed to be coherent across
+	 * CPUs, nor across CPU idle events.
+	 */
+	preempt_disable_notrace();
+	clock = sched_clock();
+	preempt_enable_notrace();
+
+	return clock;
+}
+EXPORT_SYMBOL_GPL(trace_clock_local);
+
+/*
+ * trace_clock(): 'between' trace clock. Not completely serialized,
+ * but not completely incorrect when crossing CPUs either.
+ *
+ * This is based on cpu_clock(), which will allow at most ~1 jiffy of
+ * jitter between CPUs. So it's a pretty scalable clock, but there
+ * can be offsets in the trace data.
+ */
+u64 notrace trace_clock(void)
+{
+	return local_clock();
+}
+EXPORT_SYMBOL_GPL(trace_clock);
+
+/*
+ * trace_jiffy_clock(): Simply use jiffies as a clock counter.
+ * Note that this use of jiffies_64 is not completely safe on
+ * 32-bit systems. But the window is tiny, and the effect if
+ * we are affected is that we will have an obviously bogus
+ * timestamp on a trace event - i.e. not life threatening.
+ */
+u64 notrace trace_clock_jiffies(void)
+{
+	return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES);
+}
+EXPORT_SYMBOL_GPL(trace_clock_jiffies);
+
+/*
+ * trace_clock_global(): special globally coherent trace clock
+ *
+ * It has higher overhead than the other trace clocks but is still
+ * an order of magnitude faster than GTOD derived hardware clocks.
+ *
+ * Used by plugins that need globally coherent timestamps.
+ */
+
+/* keep prev_time and lock in the same cacheline. */
+static struct {
+	u64 prev_time;
+	arch_spinlock_t lock;
+} trace_clock_struct ____cacheline_aligned_in_smp =
+	{
+		.lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED,
+	};
+
+u64 notrace trace_clock_global(void)
+{
+	unsigned long flags;
+	int this_cpu;
+	u64 now, prev_time;
+
+	raw_local_irq_save(flags);
+
+	this_cpu = raw_smp_processor_id();
+
+	/*
+	 * The global clock "guarantees" that the events are ordered
+	 * between CPUs. But if two events on two different CPUS call
+	 * trace_clock_global at roughly the same time, it really does
+	 * not matter which one gets the earlier time. Just make sure
+	 * that the same CPU will always show a monotonic clock.
+	 *
+	 * Use a read memory barrier to get the latest written
+	 * time that was recorded.
+	 */
+	smp_rmb();
+	prev_time = READ_ONCE(trace_clock_struct.prev_time);
+	now = sched_clock_cpu(this_cpu);
+
+	/* Make sure that now is always greater than prev_time */
+	if ((s64)(now - prev_time) < 0)
+		now = prev_time + 1;
+
+	/*
+	 * If in an NMI context then dont risk lockups and simply return
+	 * the current time.
+	 */
+	if (unlikely(in_nmi()))
+		goto out;
+
+	/* Tracing can cause strange recursion, always use a try lock */
+	if (arch_spin_trylock(&trace_clock_struct.lock)) {
+		/* Reread prev_time in case it was already updated */
+		prev_time = READ_ONCE(trace_clock_struct.prev_time);
+		if ((s64)(now - prev_time) < 0)
+			now = prev_time + 1;
+
+		trace_clock_struct.prev_time = now;
+
+		/* The unlock acts as the wmb for the above rmb */
+		arch_spin_unlock(&trace_clock_struct.lock);
+	}
+ out:
+	raw_local_irq_restore(flags);
+
+	return now;
+}
+EXPORT_SYMBOL_GPL(trace_clock_global);
+
+static atomic64_t trace_counter;
+
+/*
+ * trace_clock_counter(): simply an atomic counter.
+ * Use the trace_counter "counter" for cases where you do not care
+ * about timings, but are interested in strict ordering.
+ */
+u64 notrace trace_clock_counter(void)
+{
+	return atomic64_add_return(1, &trace_counter);
+}

kernel/trace/trace_entries.h

@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file defines the trace event structures that go into the ring
+ * buffer directly. They are created via macros so that changes for them
+ * appear in the format file. Using macros will automate this process.
+ *
+ * The macro used to create a ftrace data structure is:
+ *
+ * FTRACE_ENTRY( name, struct_name, id, structure, print )
+ *
+ * @name: the name used the event name, as well as the name of
+ *   the directory that holds the format file.
+ *
+ * @struct_name: the name of the structure that is created.
+ *
+ * @id: The event identifier that is used to detect what event
+ *    this is from the ring buffer.
+ *
+ * @structure: the structure layout
+ *
+ *  - __field(	type,	item	)
+ *	  This is equivalent to declaring
+ *		type	item;
+ *	  in the structure.
+ *  - __array(	type,	item,	size	)
+ *	  This is equivalent to declaring
+ *		type	item[size];
+ *	  in the structure.
+ *
+ *   * for structures within structures, the format of the internal
+ *	structure is laid out. This allows the internal structure
+ *	to be deciphered for the format file. Although these macros
+ *	may become out of sync with the internal structure, they
+ *	will create a compile error if it happens. Since the
+ *	internel structures are just tracing helpers, this is not
+ *	an issue.
+ *
+ *	When an internal structure is used, it should use:
+ *
+ *	__field_struct(	type,	item	)
+ *
+ *	instead of __field. This will prevent it from being shown in
+ *	the output file. The fields in the structure should use.
+ *
+ *	__field_desc(	type,	container,	item		)
+ *	__array_desc(	type,	container,	item,	len	)
+ *
+ *	type, item and len are the same as __field and __array, but
+ *	container is added. This is the name of the item in
+ *	__field_struct that this is describing.
+ *
+ *
+ * @print: the print format shown to users in the format file.
+ */
+
+/*
+ * Function trace entry - function address and parent function address:
+ */
+FTRACE_ENTRY_REG(function, ftrace_entry,
+
+	TRACE_FN,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip		)
+		__field(	unsigned long,	parent_ip	)
+	),
+
+	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip),
+
+	FILTER_TRACE_FN,
+
+	perf_ftrace_event_register
+);
+
+/* Function call entry */
+FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
+
+	TRACE_GRAPH_ENT,
+
+	F_STRUCT(
+		__field_struct(	struct ftrace_graph_ent,	graph_ent	)
+		__field_desc(	unsigned long,	graph_ent,	func		)
+		__field_desc(	int,		graph_ent,	depth		)
+	),
+
+	F_printk("--> %lx (%d)", __entry->func, __entry->depth),
+
+	FILTER_OTHER
+);
+
+/* Function return entry */
+FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
+
+	TRACE_GRAPH_RET,
+
+	F_STRUCT(
+		__field_struct(	struct ftrace_graph_ret,	ret	)
+		__field_desc(	unsigned long,	ret,		func	)
+		__field_desc(	unsigned long long, ret,	calltime)
+		__field_desc(	unsigned long long, ret,	rettime	)
+		__field_desc(	unsigned long,	ret,		overrun	)
+		__field_desc(	int,		ret,		depth	)
+	),
+
+	F_printk("<-- %lx (%d) (start: %llx  end: %llx) over: %d",
+		 __entry->func, __entry->depth,
+		 __entry->calltime, __entry->rettime,
+		 __entry->depth),
+
+	FILTER_OTHER
+);
+
+/*
+ * Context switch trace entry - which task (and prio) we switched from/to:
+ *
+ * This is used for both wakeup and context switches. We only want
+ * to create one structure, but we need two outputs for it.
+ */
+#define FTRACE_CTX_FIELDS					\
+	__field(	unsigned int,	prev_pid	)	\
+	__field(	unsigned int,	next_pid	)	\
+	__field(	unsigned int,	next_cpu	)       \
+	__field(	unsigned char,	prev_prio	)	\
+	__field(	unsigned char,	prev_state	)	\
+	__field(	unsigned char,	next_prio	)	\
+	__field(	unsigned char,	next_state	)
+
+FTRACE_ENTRY(context_switch, ctx_switch_entry,
+
+	TRACE_CTX,
+
+	F_STRUCT(
+		FTRACE_CTX_FIELDS
+	),
+
+	F_printk("%u:%u:%u  ==> %u:%u:%u [%03u]",
+		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
+		 __entry->next_pid, __entry->next_prio, __entry->next_state,
+		 __entry->next_cpu),
+
+	FILTER_OTHER
+);
+
+/*
+ * FTRACE_ENTRY_DUP only creates the format file, it will not
+ *  create another structure.
+ */
+FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
+
+	TRACE_WAKE,
+
+	F_STRUCT(
+		FTRACE_CTX_FIELDS
+	),
+
+	F_printk("%u:%u:%u  ==+ %u:%u:%u [%03u]",
+		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
+		 __entry->next_pid, __entry->next_prio, __entry->next_state,
+		 __entry->next_cpu),
+
+	FILTER_OTHER
+);
+
+/*
+ * Stack-trace entry:
+ */
+
+#define FTRACE_STACK_ENTRIES	8
+
+#ifndef CONFIG_64BIT
+# define IP_FMT "%08lx"
+#else
+# define IP_FMT "%016lx"
+#endif
+
+FTRACE_ENTRY(kernel_stack, stack_entry,
+
+	TRACE_STACK,
+
+	F_STRUCT(
+		__field(	int,		size	)
+		__array(	unsigned long,	caller,	FTRACE_STACK_ENTRIES	)
+	),
+
+	F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+		 "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+		 "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n",
+		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
+		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
+		 __entry->caller[6], __entry->caller[7]),
+
+	FILTER_OTHER
+);
+
+FTRACE_ENTRY(user_stack, userstack_entry,
+
+	TRACE_USER_STACK,
+
+	F_STRUCT(
+		__field(	unsigned int,	tgid	)
+		__array(	unsigned long,	caller, FTRACE_STACK_ENTRIES	)
+	),
+
+	F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+		 "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+		 "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n",
+		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
+		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
+		 __entry->caller[6], __entry->caller[7]),
+
+	FILTER_OTHER
+);
+
+/*
+ * trace_printk entry:
+ */
+FTRACE_ENTRY(bprint, bprint_entry,
+
+	TRACE_BPRINT,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip	)
+		__field(	const char *,	fmt	)
+		__dynamic_array(	u32,	buf	)
+	),
+
+	F_printk("%ps: %s",
+		 (void *)__entry->ip, __entry->fmt),
+
+	FILTER_OTHER
+);
+
+FTRACE_ENTRY_REG(print, print_entry,
+
+	TRACE_PRINT,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip	)
+		__dynamic_array(	char,	buf	)
+	),
+
+	F_printk("%ps: %s",
+		 (void *)__entry->ip, __entry->buf),
+
+	FILTER_OTHER,
+
+	ftrace_event_register
+);
+
+FTRACE_ENTRY(raw_data, raw_data_entry,
+
+	TRACE_RAW_DATA,
+
+	F_STRUCT(
+		__field(	unsigned int,	id	)
+		__dynamic_array(	char,	buf	)
+	),
+
+	F_printk("id:%04x %08x",
+		 __entry->id, (int)__entry->buf[0]),
+
+	FILTER_OTHER
+);
+
+FTRACE_ENTRY(bputs, bputs_entry,
+
+	TRACE_BPUTS,
+
+	F_STRUCT(
+		__field(	unsigned long,	ip	)
+		__field(	const char *,	str	)
+	),
+
+	F_printk("%ps: %s",
+		 (void *)__entry->ip, __entry->str),
+
+	FILTER_OTHER
+);
+
+FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
+
+	TRACE_MMIO_RW,
+
+	F_STRUCT(
+		__field_struct(	struct mmiotrace_rw,	rw	)
+		__field_desc(	resource_size_t, rw,	phys	)
+		__field_desc(	unsigned long,	rw,	value	)
+		__field_desc(	unsigned long,	rw,	pc	)
+		__field_desc(	int, 		rw,	map_id	)
+		__field_desc(	unsigned char,	rw,	opcode	)
+		__field_desc(	unsigned char,	rw,	width	)
+	),
+
+	F_printk("%lx %lx %lx %d %x %x",
+		 (unsigned long)__entry->phys, __entry->value, __entry->pc,
+		 __entry->map_id, __entry->opcode, __entry->width),
+
+	FILTER_OTHER
+);
+
+FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
+
+	TRACE_MMIO_MAP,
+
+	F_STRUCT(
+		__field_struct(	struct mmiotrace_map,	map	)
+		__field_desc(	resource_size_t, map,	phys	)
+		__field_desc(	unsigned long,	map,	virt	)
+		__field_desc(	unsigned long,	map,	len	)
+		__field_desc(	int, 		map,	map_id	)
+		__field_desc(	unsigned char,	map,	opcode	)
+	),
+
+	F_printk("%lx %lx %lx %d %x",
+		 (unsigned long)__entry->phys, __entry->virt, __entry->len,
+		 __entry->map_id, __entry->opcode),
+
+	FILTER_OTHER
+);
+
+
+#define TRACE_FUNC_SIZE 30
+#define TRACE_FILE_SIZE 20
+
+FTRACE_ENTRY(branch, trace_branch,
+
+	TRACE_BRANCH,
+
+	F_STRUCT(
+		__field(	unsigned int,	line				)
+		__array(	char,		func,	TRACE_FUNC_SIZE+1	)
+		__array(	char,		file,	TRACE_FILE_SIZE+1	)
+		__field(	char,		correct				)
+		__field(	char,		constant			)
+	),
+
+	F_printk("%u:%s:%s (%u)%s",
+		 __entry->line,
+		 __entry->func, __entry->file, __entry->correct,
+		 __entry->constant ? " CONSTANT" : ""),
+
+	FILTER_OTHER
+);
+
+
+FTRACE_ENTRY(hwlat, hwlat_entry,
+
+	TRACE_HWLAT,
+
+	F_STRUCT(
+		__field(	u64,			duration	)
+		__field(	u64,			outer_duration	)
+		__field(	u64,			nmi_total_ts	)
+		__field_struct( struct timespec64,	timestamp	)
+		__field_desc(	s64,	timestamp,	tv_sec		)
+		__field_desc(	long,	timestamp,	tv_nsec		)
+		__field(	unsigned int,		nmi_count	)
+		__field(	unsigned int,		seqnum		)
+	),
+
+	F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n",
+		 __entry->seqnum,
+		 __entry->tv_sec,
+		 __entry->tv_nsec,
+		 __entry->duration,
+		 __entry->outer_duration,
+		 __entry->nmi_total_ts,
+		 __entry->nmi_count),
+
+	FILTER_OTHER
+);

kernel/trace/trace_event_perf.c

@@ -0,0 +1,521 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace event based perf event profiling/tracing
+ *
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra
+ * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kprobes.h>
+#include <linux/security.h>
+#include "trace.h"
+#include "trace_probe.h"
+
+static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];
+
+/*
+ * Force it to be aligned to unsigned long to avoid misaligned accesses
+ * suprises
+ */
+typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
+	perf_trace_t;
+
+/* Count the events in use (per event id, not per instance) */
+static int	total_ref_count;
+
+static int perf_trace_event_perm(struct trace_event_call *tp_event,
+				 struct perf_event *p_event)
+{
+	int ret;
+
+	if (tp_event->perf_perm) {
+		ret = tp_event->perf_perm(tp_event, p_event);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * We checked and allowed to create parent,
+	 * allow children without checking.
+	 */
+	if (p_event->parent)
+		return 0;
+
+	/*
+	 * It's ok to check current process (owner) permissions in here,
+	 * because code below is called only via perf_event_open syscall.
+	 */
+
+	/* The ftrace function trace is allowed only for root. */
+	if (ftrace_event_is_function(tp_event)) {
+		ret = perf_allow_tracepoint(&p_event->attr);
+		if (ret)
+			return ret;
+
+		if (!is_sampling_event(p_event))
+			return 0;
+
+		/*
+		 * We don't allow user space callchains for  function trace
+		 * event, due to issues with page faults while tracing page
+		 * fault handler and its overall trickiness nature.
+		 */
+		if (!p_event->attr.exclude_callchain_user)
+			return -EINVAL;
+
+		/*
+		 * Same reason to disable user stack dump as for user space
+		 * callchains above.
+		 */
+		if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER)
+			return -EINVAL;
+	}
+
+	/* No tracing, just counting, so no obvious leak */
+	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+		return 0;
+
+	/* Some events are ok to be traced by non-root users... */
+	if (p_event->attach_state == PERF_ATTACH_TASK) {
+		if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+			return 0;
+	}
+
+	/*
+	 * ...otherwise raw tracepoint data can be a severe data leak,
+	 * only allow root to have these.
+	 */
+	ret = perf_allow_tracepoint(&p_event->attr);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int perf_trace_event_reg(struct trace_event_call *tp_event,
+				struct perf_event *p_event)
+{
+	struct hlist_head __percpu *list;
+	int ret = -ENOMEM;
+	int cpu;
+
+	p_event->tp_event = tp_event;
+	if (tp_event->perf_refcount++ > 0)
+		return 0;
+
+	list = alloc_percpu(struct hlist_head);
+	if (!list)
+		goto fail;
+
+	for_each_possible_cpu(cpu)
+		INIT_HLIST_HEAD(per_cpu_ptr(list, cpu));
+
+	tp_event->perf_events = list;
+
+	if (!total_ref_count) {
+		char __percpu *buf;
+		int i;
+
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+			buf = (char __percpu *)alloc_percpu(perf_trace_t);
+			if (!buf)
+				goto fail;
+
+			perf_trace_buf[i] = buf;
+		}
+	}
+
+	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL);
+	if (ret)
+		goto fail;
+
+	total_ref_count++;
+	return 0;
+
+fail:
+	if (!total_ref_count) {
+		int i;
+
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+			free_percpu(perf_trace_buf[i]);
+			perf_trace_buf[i] = NULL;
+		}
+	}
+
+	if (!--tp_event->perf_refcount) {
+		free_percpu(tp_event->perf_events);
+		tp_event->perf_events = NULL;
+	}
+
+	return ret;
+}
+
+static void perf_trace_event_unreg(struct perf_event *p_event)
+{
+	struct trace_event_call *tp_event = p_event->tp_event;
+	int i;
+
+	if (--tp_event->perf_refcount > 0)
+		goto out;
+
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
+
+	/*
+	 * Ensure our callback won't be called anymore. The buffers
+	 * will be freed after that.
+	 */
+	tracepoint_synchronize_unregister();
+
+	free_percpu(tp_event->perf_events);
+	tp_event->perf_events = NULL;
+
+	if (!--total_ref_count) {
+		for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+			free_percpu(perf_trace_buf[i]);
+			perf_trace_buf[i] = NULL;
+		}
+	}
+out:
+	module_put(tp_event->mod);
+}
+
+static int perf_trace_event_open(struct perf_event *p_event)
+{
+	struct trace_event_call *tp_event = p_event->tp_event;
+	return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event);
+}
+
+static void perf_trace_event_close(struct perf_event *p_event)
+{
+	struct trace_event_call *tp_event = p_event->tp_event;
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event);
+}
+
+static int perf_trace_event_init(struct trace_event_call *tp_event,
+				 struct perf_event *p_event)
+{
+	int ret;
+
+	ret = perf_trace_event_perm(tp_event, p_event);
+	if (ret)
+		return ret;
+
+	ret = perf_trace_event_reg(tp_event, p_event);
+	if (ret)
+		return ret;
+
+	ret = perf_trace_event_open(p_event);
+	if (ret) {
+		perf_trace_event_unreg(p_event);
+		return ret;
+	}
+
+	return 0;
+}
+
+int perf_trace_init(struct perf_event *p_event)
+{
+	struct trace_event_call *tp_event;
+	u64 event_id = p_event->attr.config;
+	int ret = -EINVAL;
+
+	mutex_lock(&event_mutex);
+	list_for_each_entry(tp_event, &ftrace_events, list) {
+		if (tp_event->event.type == event_id &&
+		    tp_event->class && tp_event->class->reg &&
+		    try_module_get(tp_event->mod)) {
+			ret = perf_trace_event_init(tp_event, p_event);
+			if (ret)
+				module_put(tp_event->mod);
+			break;
+		}
+	}
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+void perf_trace_destroy(struct perf_event *p_event)
+{
+	mutex_lock(&event_mutex);
+	perf_trace_event_close(p_event);
+	perf_trace_event_unreg(p_event);
+	mutex_unlock(&event_mutex);
+}
+
+#ifdef CONFIG_KPROBE_EVENTS
+int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe)
+{
+	int ret;
+	char *func = NULL;
+	struct trace_event_call *tp_event;
+
+	if (p_event->attr.kprobe_func) {
+		func = kzalloc(KSYM_NAME_LEN, GFP_KERNEL);
+		if (!func)
+			return -ENOMEM;
+		ret = strncpy_from_user(
+			func, u64_to_user_ptr(p_event->attr.kprobe_func),
+			KSYM_NAME_LEN);
+		if (ret == KSYM_NAME_LEN)
+			ret = -E2BIG;
+		if (ret < 0)
+			goto out;
+
+		if (func[0] == '\0') {
+			kfree(func);
+			func = NULL;
+		}
+	}
+
+	tp_event = create_local_trace_kprobe(
+		func, (void *)(unsigned long)(p_event->attr.kprobe_addr),
+		p_event->attr.probe_offset, is_retprobe);
+	if (IS_ERR(tp_event)) {
+		ret = PTR_ERR(tp_event);
+		goto out;
+	}
+
+	mutex_lock(&event_mutex);
+	ret = perf_trace_event_init(tp_event, p_event);
+	if (ret)
+		destroy_local_trace_kprobe(tp_event);
+	mutex_unlock(&event_mutex);
+out:
+	kfree(func);
+	return ret;
+}
+
+void perf_kprobe_destroy(struct perf_event *p_event)
+{
+	mutex_lock(&event_mutex);
+	perf_trace_event_close(p_event);
+	perf_trace_event_unreg(p_event);
+	mutex_unlock(&event_mutex);
+
+	destroy_local_trace_kprobe(p_event->tp_event);
+}
+#endif /* CONFIG_KPROBE_EVENTS */
+
+#ifdef CONFIG_UPROBE_EVENTS
+int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe)
+{
+	int ret;
+	char *path = NULL;
+	struct trace_event_call *tp_event;
+
+	if (!p_event->attr.uprobe_path)
+		return -EINVAL;
+
+	path = strndup_user(u64_to_user_ptr(p_event->attr.uprobe_path),
+			    PATH_MAX);
+	if (IS_ERR(path)) {
+		ret = PTR_ERR(path);
+		return (ret == -EINVAL) ? -E2BIG : ret;
+	}
+	if (path[0] == '\0') {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	tp_event = create_local_trace_uprobe(
+		path, p_event->attr.probe_offset, is_retprobe);
+	if (IS_ERR(tp_event)) {
+		ret = PTR_ERR(tp_event);
+		goto out;
+	}
+
+	/*
+	 * local trace_uprobe need to hold event_mutex to call
+	 * uprobe_buffer_enable() and uprobe_buffer_disable().
+	 * event_mutex is not required for local trace_kprobes.
+	 */
+	mutex_lock(&event_mutex);
+	ret = perf_trace_event_init(tp_event, p_event);
+	if (ret)
+		destroy_local_trace_uprobe(tp_event);
+	mutex_unlock(&event_mutex);
+out:
+	kfree(path);
+	return ret;
+}
+
+void perf_uprobe_destroy(struct perf_event *p_event)
+{
+	mutex_lock(&event_mutex);
+	perf_trace_event_close(p_event);
+	perf_trace_event_unreg(p_event);
+	mutex_unlock(&event_mutex);
+	destroy_local_trace_uprobe(p_event->tp_event);
+}
+#endif /* CONFIG_UPROBE_EVENTS */
+
+int perf_trace_add(struct perf_event *p_event, int flags)
+{
+	struct trace_event_call *tp_event = p_event->tp_event;
+
+	if (!(flags & PERF_EF_START))
+		p_event->hw.state = PERF_HES_STOPPED;
+
+	/*
+	 * If TRACE_REG_PERF_ADD returns false; no custom action was performed
+	 * and we need to take the default action of enqueueing our event on
+	 * the right per-cpu hlist.
+	 */
+	if (!tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event)) {
+		struct hlist_head __percpu *pcpu_list;
+		struct hlist_head *list;
+
+		pcpu_list = tp_event->perf_events;
+		if (WARN_ON_ONCE(!pcpu_list))
+			return -EINVAL;
+
+		list = this_cpu_ptr(pcpu_list);
+		hlist_add_head_rcu(&p_event->hlist_entry, list);
+	}
+
+	return 0;
+}
+
+void perf_trace_del(struct perf_event *p_event, int flags)
+{
+	struct trace_event_call *tp_event = p_event->tp_event;
+
+	/*
+	 * If TRACE_REG_PERF_DEL returns false; no custom action was performed
+	 * and we need to take the default action of dequeueing our event from
+	 * the right per-cpu hlist.
+	 */
+	if (!tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event))
+		hlist_del_rcu(&p_event->hlist_entry);
+}
+
+void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp)
+{
+	char *raw_data;
+	int rctx;
+
+	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+		      "perf buffer not large enough"))
+		return NULL;
+
+	*rctxp = rctx = perf_swevent_get_recursion_context();
+	if (rctx < 0)
+		return NULL;
+
+	if (regs)
+		*regs = this_cpu_ptr(&__perf_regs[rctx]);
+	raw_data = this_cpu_ptr(perf_trace_buf[rctx]);
+
+	/* zero the dead bytes from align to not leak stack to user */
+	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
+	return raw_data;
+}
+EXPORT_SYMBOL_GPL(perf_trace_buf_alloc);
+NOKPROBE_SYMBOL(perf_trace_buf_alloc);
+
+void perf_trace_buf_update(void *record, u16 type)
+{
+	struct trace_entry *entry = record;
+	int pc = preempt_count();
+	unsigned long flags;
+
+	local_save_flags(flags);
+	tracing_generic_entry_update(entry, flags, pc);
+	entry->type = type;
+}
+NOKPROBE_SYMBOL(perf_trace_buf_update);
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void
+perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
+			  struct ftrace_ops *ops, struct pt_regs *pt_regs)
+{
+	struct ftrace_entry *entry;
+	struct perf_event *event;
+	struct hlist_head head;
+	struct pt_regs regs;
+	int rctx;
+
+	if ((unsigned long)ops->private != smp_processor_id())
+		return;
+
+	event = container_of(ops, struct perf_event, ftrace_ops);
+
+	/*
+	 * @event->hlist entry is NULL (per INIT_HLIST_NODE), and all
+	 * the perf code does is hlist_for_each_entry_rcu(), so we can
+	 * get away with simply setting the @head.first pointer in order
+	 * to create a singular list.
+	 */
+	head.first = &event->hlist_entry;
+
+#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
+		    sizeof(u64)) - sizeof(u32))
+
+	BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);
+
+	memset(&regs, 0, sizeof(regs));
+	perf_fetch_caller_regs(&regs);
+
+	entry = perf_trace_buf_alloc(ENTRY_SIZE, NULL, &rctx);
+	if (!entry)
+		return;
+
+	entry->ip = ip;
+	entry->parent_ip = parent_ip;
+	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN,
+			      1, &regs, &head, NULL);
+
+#undef ENTRY_SIZE
+}
+
+static int perf_ftrace_function_register(struct perf_event *event)
+{
+	struct ftrace_ops *ops = &event->ftrace_ops;
+
+	ops->flags   = FTRACE_OPS_FL_RCU;
+	ops->func    = perf_ftrace_function_call;
+	ops->private = (void *)(unsigned long)nr_cpu_ids;
+
+	return register_ftrace_function(ops);
+}
+
+static int perf_ftrace_function_unregister(struct perf_event *event)
+{
+	struct ftrace_ops *ops = &event->ftrace_ops;
+	int ret = unregister_ftrace_function(ops);
+	ftrace_free_filter(ops);
+	return ret;
+}
+
+int perf_ftrace_event_register(struct trace_event_call *call,
+			       enum trace_reg type, void *data)
+{
+	struct perf_event *event = data;
+
+	switch (type) {
+	case TRACE_REG_REGISTER:
+	case TRACE_REG_UNREGISTER:
+		break;
+	case TRACE_REG_PERF_REGISTER:
+	case TRACE_REG_PERF_UNREGISTER:
+		return 0;
+	case TRACE_REG_PERF_OPEN:
+		return perf_ftrace_function_register(data);
+	case TRACE_REG_PERF_CLOSE:
+		return perf_ftrace_function_unregister(data);
+	case TRACE_REG_PERF_ADD:
+		event->ftrace_ops.private = (void *)(unsigned long)smp_processor_id();
+		return 1;
+	case TRACE_REG_PERF_DEL:
+		event->ftrace_ops.private = (void *)(unsigned long)nr_cpu_ids;
+		return 1;
+	}
+
+	return -EINVAL;
+}
+#endif /* CONFIG_FUNCTION_TRACER */

kernel/trace/trace_events_filter_test.h

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM test
+
+#if !defined(_TRACE_TEST_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TEST_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(ftrace_test_filter,
+
+	TP_PROTO(int a, int b, int c, int d, int e, int f, int g, int h),
+
+	TP_ARGS(a, b, c, d, e, f, g, h),
+
+	TP_STRUCT__entry(
+		__field(int, a)
+		__field(int, b)
+		__field(int, c)
+		__field(int, d)
+		__field(int, e)
+		__field(int, f)
+		__field(int, g)
+		__field(int, h)
+	),
+
+	TP_fast_assign(
+		__entry->a = a;
+		__entry->b = b;
+		__entry->c = c;
+		__entry->d = d;
+		__entry->e = e;
+		__entry->f = f;
+		__entry->g = g;
+		__entry->h = h;
+	),
+
+	TP_printk("a %d, b %d, c %d, d %d, e %d, f %d, g %d, h %d",
+		  __entry->a, __entry->b, __entry->c, __entry->d,
+		  __entry->e, __entry->f, __entry->g, __entry->h)
+);
+
+#endif /* _TRACE_TEST_H || TRACE_HEADER_MULTI_READ */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_events_filter_test
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

kernel/trace/trace_export.c

@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace_export.c - export basic ftrace utilities to user space
+ *
+ * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/stringify.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include "trace_output.h"
+
+/* Stub function for events with triggers */
+static int ftrace_event_register(struct trace_event_call *call,
+				 enum trace_reg type, void *data)
+{
+	return 0;
+}
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM	ftrace
+
+/*
+ * The FTRACE_ENTRY_REG macro allows ftrace entry to define register
+ * function and thus become accesible via perf.
+ */
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
+			 filter, regfn) \
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
+
+/* not needed for this file */
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __field
+#define __field(type, item)				type item;
+
+#undef __field_desc
+#define __field_desc(type, container, item)		type item;
+
+#undef __array
+#define __array(type, item, size)			type item[size];
+
+#undef __array_desc
+#define __array_desc(type, container, item, size)	type item[size];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)			type item[];
+
+#undef F_STRUCT
+#define F_STRUCT(args...)				args
+
+#undef F_printk
+#define F_printk(fmt, args...) fmt, args
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+struct ____ftrace_##name {						\
+	tstruct								\
+};									\
+static void __always_unused ____ftrace_check_##name(void)		\
+{									\
+	struct ____ftrace_##name *__entry = NULL;			\
+									\
+	/* force compile-time check on F_printk() */			\
+	printk(print);							\
+}
+
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter)	\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
+
+#include "trace_entries.h"
+
+#undef __field
+#define __field(type, item)						\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item),			\
+				 is_signed_type(type), filter_type);	\
+	if (ret)							\
+		return ret;
+
+#undef __field_desc
+#define __field_desc(type, container, item)	\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field),		\
+					  container.item),		\
+				 sizeof(field.container.item),		\
+				 is_signed_type(type), filter_type);	\
+	if (ret)							\
+		return ret;
+
+#undef __array
+#define __array(type, item, len)					\
+	do {								\
+		char *type_str = #type"["__stringify(len)"]";		\
+		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
+		ret = trace_define_field(event_call, type_str, #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item),			\
+				 is_signed_type(type), filter_type);	\
+		if (ret)						\
+			return ret;					\
+	} while (0);
+
+#undef __array_desc
+#define __array_desc(type, container, item, len)			\
+	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field),		\
+					  container.item),		\
+				 sizeof(field.container.item),		\
+				 is_signed_type(type), filter_type);	\
+	if (ret)							\
+		return ret;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)					\
+	ret = trace_define_field(event_call, #type "[]", #item,  \
+				 offsetof(typeof(field), item),		\
+				 0, is_signed_type(type), filter_type);\
+	if (ret)							\
+		return ret;
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+static int __init							\
+ftrace_define_fields_##name(struct trace_event_call *event_call)	\
+{									\
+	struct struct_name field;					\
+	int ret;							\
+	int filter_type = filter;					\
+									\
+	tstruct;							\
+									\
+	return ret;							\
+}
+
+#include "trace_entries.h"
+
+#undef __entry
+#define __entry REC
+
+#undef __field
+#define __field(type, item)
+
+#undef __field_desc
+#define __field_desc(type, container, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __array_desc
+#define __array_desc(type, container, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)
+
+#undef F_printk
+#define F_printk(fmt, args...) __stringify(fmt) ", "  __stringify(args)
+
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
+			 regfn)						\
+									\
+struct trace_event_class __refdata event_class_ftrace_##call = {	\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.define_fields		= ftrace_define_fields_##call,		\
+	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
+	.reg			= regfn,				\
+};									\
+									\
+struct trace_event_call __used event_##call = {				\
+	.class			= &event_class_ftrace_##call,		\
+	{								\
+		.name			= #call,			\
+	},								\
+	.event.type		= etype,				\
+	.print_fmt		= print,				\
+	.flags			= TRACE_EVENT_FL_IGNORE_ENABLE,		\
+};									\
+struct trace_event_call __used						\
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter)	\
+	FTRACE_ENTRY_REG(call, struct_name, etype,			\
+			 PARAMS(tstruct), PARAMS(print), filter, NULL)
+
+bool ftrace_event_is_function(struct trace_event_call *call)
+{
+	return call == &event_function;
+}
+
+#include "trace_entries.h"

kernel/trace/trace_functions.c

@@ -0,0 +1,814 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ring buffer based function tracer
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * Based on code from the latency_tracer, that is:
+ *
+ *  Copyright (C) 2004-2006 Ingo Molnar
+ *  Copyright (C) 2004 Nadia Yvette Chambers
+ */
+#include <linux/ring_buffer.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+static void tracing_start_function_trace(struct trace_array *tr);
+static void tracing_stop_function_trace(struct trace_array *tr);
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip,
+		    struct ftrace_ops *op, struct pt_regs *pt_regs);
+static void
+function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
+			  struct ftrace_ops *op, struct pt_regs *pt_regs);
+static struct tracer_flags func_flags;
+
+/* Our option */
+enum {
+	TRACE_FUNC_OPT_STACK	= 0x1,
+};
+
+static int allocate_ftrace_ops(struct trace_array *tr)
+{
+	struct ftrace_ops *ops;
+
+	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+	if (!ops)
+		return -ENOMEM;
+
+	/* Currently only the non stack verision is supported */
+	ops->func = function_trace_call;
+	ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID;
+
+	tr->ops = ops;
+	ops->private = tr;
+	return 0;
+}
+
+
+int ftrace_create_function_files(struct trace_array *tr,
+				 struct dentry *parent)
+{
+	int ret;
+
+	/*
+	 * The top level array uses the "global_ops", and the files are
+	 * created on boot up.
+	 */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+		return 0;
+
+	ret = allocate_ftrace_ops(tr);
+	if (ret)
+		return ret;
+
+	ftrace_create_filter_files(tr->ops, parent);
+
+	return 0;
+}
+
+void ftrace_destroy_function_files(struct trace_array *tr)
+{
+	ftrace_destroy_filter_files(tr->ops);
+	kfree(tr->ops);
+	tr->ops = NULL;
+}
+
+static int function_trace_init(struct trace_array *tr)
+{
+	ftrace_func_t func;
+
+	/*
+	 * Instance trace_arrays get their ops allocated
+	 * at instance creation. Unless it failed
+	 * the allocation.
+	 */
+	if (!tr->ops)
+		return -ENOMEM;
+
+	/* Currently only the global instance can do stack tracing */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL &&
+	    func_flags.val & TRACE_FUNC_OPT_STACK)
+		func = function_stack_trace_call;
+	else
+		func = function_trace_call;
+
+	ftrace_init_array_ops(tr, func);
+
+	tr->trace_buffer.cpu = get_cpu();
+	put_cpu();
+
+	tracing_start_cmdline_record();
+	tracing_start_function_trace(tr);
+	return 0;
+}
+
+static void function_trace_reset(struct trace_array *tr)
+{
+	tracing_stop_function_trace(tr);
+	tracing_stop_cmdline_record();
+	ftrace_reset_array_ops(tr);
+}
+
+static void function_trace_start(struct trace_array *tr)
+{
+	tracing_reset_online_cpus(&tr->trace_buffer);
+}
+
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip,
+		    struct ftrace_ops *op, struct pt_regs *pt_regs)
+{
+	struct trace_array *tr = op->private;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	int bit;
+	int cpu;
+	int pc;
+
+	if (unlikely(!tr->function_enabled))
+		return;
+
+	pc = preempt_count();
+	preempt_disable_notrace();
+
+	bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+	if (bit < 0)
+		goto out;
+
+	cpu = smp_processor_id();
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+	if (!atomic_read(&data->disabled)) {
+		local_save_flags(flags);
+		trace_function(tr, ip, parent_ip, flags, pc);
+	}
+	trace_clear_recursion(bit);
+
+ out:
+	preempt_enable_notrace();
+}
+
+#ifdef CONFIG_UNWINDER_ORC
+/*
+ * Skip 2:
+ *
+ *   function_stack_trace_call()
+ *   ftrace_call()
+ */
+#define STACK_SKIP 2
+#else
+/*
+ * Skip 3:
+ *   __trace_stack()
+ *   function_stack_trace_call()
+ *   ftrace_call()
+ */
+#define STACK_SKIP 3
+#endif
+
+static void
+function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
+			  struct ftrace_ops *op, struct pt_regs *pt_regs)
+{
+	struct trace_array *tr = op->private;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	if (unlikely(!tr->function_enabled))
+		return;
+
+	/*
+	 * Need to use raw, since this must be called before the
+	 * recursive protection is performed.
+	 */
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+	disabled = atomic_inc_return(&data->disabled);
+
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		trace_function(tr, ip, parent_ip, flags, pc);
+		__trace_stack(tr, flags, STACK_SKIP, pc);
+	}
+
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
+}
+
+static struct tracer_opt func_opts[] = {
+#ifdef CONFIG_STACKTRACE
+	{ TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) },
+#endif
+	{ } /* Always set a last empty entry */
+};
+
+static struct tracer_flags func_flags = {
+	.val = 0, /* By default: all flags disabled */
+	.opts = func_opts
+};
+
+static void tracing_start_function_trace(struct trace_array *tr)
+{
+	tr->function_enabled = 0;
+	register_ftrace_function(tr->ops);
+	tr->function_enabled = 1;
+}
+
+static void tracing_stop_function_trace(struct trace_array *tr)
+{
+	tr->function_enabled = 0;
+	unregister_ftrace_function(tr->ops);
+}
+
+static struct tracer function_trace;
+
+static int
+func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
+{
+	switch (bit) {
+	case TRACE_FUNC_OPT_STACK:
+		/* do nothing if already set */
+		if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
+			break;
+
+		/* We can change this flag when not running. */
+		if (tr->current_trace != &function_trace)
+			break;
+
+		unregister_ftrace_function(tr->ops);
+
+		if (set) {
+			tr->ops->func = function_stack_trace_call;
+			register_ftrace_function(tr->ops);
+		} else {
+			tr->ops->func = function_trace_call;
+			register_ftrace_function(tr->ops);
+		}
+
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct tracer function_trace __tracer_data =
+{
+	.name		= "function",
+	.init		= function_trace_init,
+	.reset		= function_trace_reset,
+	.start		= function_trace_start,
+	.flags		= &func_flags,
+	.set_flag	= func_set_flag,
+	.allow_instances = true,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest	= trace_selftest_startup_function,
+#endif
+};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static void update_traceon_count(struct ftrace_probe_ops *ops,
+				 unsigned long ip,
+				 struct trace_array *tr, bool on,
+				 void *data)
+{
+	struct ftrace_func_mapper *mapper = data;
+	long *count;
+	long old_count;
+
+	/*
+	 * Tracing gets disabled (or enabled) once per count.
+	 * This function can be called at the same time on multiple CPUs.
+	 * It is fine if both disable (or enable) tracing, as disabling
+	 * (or enabling) the second time doesn't do anything as the
+	 * state of the tracer is already disabled (or enabled).
+	 * What needs to be synchronized in this case is that the count
+	 * only gets decremented once, even if the tracer is disabled
+	 * (or enabled) twice, as the second one is really a nop.
+	 *
+	 * The memory barriers guarantee that we only decrement the
+	 * counter once. First the count is read to a local variable
+	 * and a read barrier is used to make sure that it is loaded
+	 * before checking if the tracer is in the state we want.
+	 * If the tracer is not in the state we want, then the count
+	 * is guaranteed to be the old count.
+	 *
+	 * Next the tracer is set to the state we want (disabled or enabled)
+	 * then a write memory barrier is used to make sure that
+	 * the new state is visible before changing the counter by
+	 * one minus the old counter. This guarantees that another CPU
+	 * executing this code will see the new state before seeing
+	 * the new counter value, and would not do anything if the new
+	 * counter is seen.
+	 *
+	 * Note, there is no synchronization between this and a user
+	 * setting the tracing_on file. But we currently don't care
+	 * about that.
+	 */
+	count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+	old_count = *count;
+
+	if (old_count <= 0)
+		return;
+
+	/* Make sure we see count before checking tracing state */
+	smp_rmb();
+
+	if (on == !!tracer_tracing_is_on(tr))
+		return;
+
+	if (on)
+		tracer_tracing_on(tr);
+	else
+		tracer_tracing_off(tr);
+
+	/* Make sure tracing state is visible before updating count */
+	smp_wmb();
+
+	*count = old_count - 1;
+}
+
+static void
+ftrace_traceon_count(unsigned long ip, unsigned long parent_ip,
+		     struct trace_array *tr, struct ftrace_probe_ops *ops,
+		     void *data)
+{
+	update_traceon_count(ops, ip, tr, 1, data);
+}
+
+static void
+ftrace_traceoff_count(unsigned long ip, unsigned long parent_ip,
+		      struct trace_array *tr, struct ftrace_probe_ops *ops,
+		      void *data)
+{
+	update_traceon_count(ops, ip, tr, 0, data);
+}
+
+static void
+ftrace_traceon(unsigned long ip, unsigned long parent_ip,
+	       struct trace_array *tr, struct ftrace_probe_ops *ops,
+	       void *data)
+{
+	if (tracer_tracing_is_on(tr))
+		return;
+
+	tracer_tracing_on(tr);
+}
+
+static void
+ftrace_traceoff(unsigned long ip, unsigned long parent_ip,
+		struct trace_array *tr, struct ftrace_probe_ops *ops,
+		void *data)
+{
+	if (!tracer_tracing_is_on(tr))
+		return;
+
+	tracer_tracing_off(tr);
+}
+
+#ifdef CONFIG_UNWINDER_ORC
+/*
+ * Skip 3:
+ *
+ *   function_trace_probe_call()
+ *   ftrace_ops_assist_func()
+ *   ftrace_call()
+ */
+#define FTRACE_STACK_SKIP 3
+#else
+/*
+ * Skip 5:
+ *
+ *   __trace_stack()
+ *   ftrace_stacktrace()
+ *   function_trace_probe_call()
+ *   ftrace_ops_assist_func()
+ *   ftrace_call()
+ */
+#define FTRACE_STACK_SKIP 5
+#endif
+
+static __always_inline void trace_stack(struct trace_array *tr)
+{
+	unsigned long flags;
+	int pc;
+
+	local_save_flags(flags);
+	pc = preempt_count();
+
+	__trace_stack(tr, flags, FTRACE_STACK_SKIP, pc);
+}
+
+static void
+ftrace_stacktrace(unsigned long ip, unsigned long parent_ip,
+		  struct trace_array *tr, struct ftrace_probe_ops *ops,
+		  void *data)
+{
+	trace_stack(tr);
+}
+
+static void
+ftrace_stacktrace_count(unsigned long ip, unsigned long parent_ip,
+			struct trace_array *tr, struct ftrace_probe_ops *ops,
+			void *data)
+{
+	struct ftrace_func_mapper *mapper = data;
+	long *count;
+	long old_count;
+	long new_count;
+
+	if (!tracing_is_on())
+		return;
+
+	/* unlimited? */
+	if (!mapper) {
+		trace_stack(tr);
+		return;
+	}
+
+	count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+
+	/*
+	 * Stack traces should only execute the number of times the
+	 * user specified in the counter.
+	 */
+	do {
+		old_count = *count;
+
+		if (!old_count)
+			return;
+
+		new_count = old_count - 1;
+		new_count = cmpxchg(count, old_count, new_count);
+		if (new_count == old_count)
+			trace_stack(tr);
+
+		if (!tracing_is_on())
+			return;
+
+	} while (new_count != old_count);
+}
+
+static int update_count(struct ftrace_probe_ops *ops, unsigned long ip,
+			void *data)
+{
+	struct ftrace_func_mapper *mapper = data;
+	long *count = NULL;
+
+	if (mapper)
+		count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+
+	if (count) {
+		if (*count <= 0)
+			return 0;
+		(*count)--;
+	}
+
+	return 1;
+}
+
+static void
+ftrace_dump_probe(unsigned long ip, unsigned long parent_ip,
+		  struct trace_array *tr, struct ftrace_probe_ops *ops,
+		  void *data)
+{
+	if (update_count(ops, ip, data))
+		ftrace_dump(DUMP_ALL);
+}
+
+/* Only dump the current CPU buffer. */
+static void
+ftrace_cpudump_probe(unsigned long ip, unsigned long parent_ip,
+		     struct trace_array *tr, struct ftrace_probe_ops *ops,
+		     void *data)
+{
+	if (update_count(ops, ip, data))
+		ftrace_dump(DUMP_ORIG);
+}
+
+static int
+ftrace_probe_print(const char *name, struct seq_file *m,
+		   unsigned long ip, struct ftrace_probe_ops *ops,
+		   void *data)
+{
+	struct ftrace_func_mapper *mapper = data;
+	long *count = NULL;
+
+	seq_printf(m, "%ps:%s", (void *)ip, name);
+
+	if (mapper)
+		count = (long *)ftrace_func_mapper_find_ip(mapper, ip);
+
+	if (count)
+		seq_printf(m, ":count=%ld\n", *count);
+	else
+		seq_puts(m, ":unlimited\n");
+
+	return 0;
+}
+
+static int
+ftrace_traceon_print(struct seq_file *m, unsigned long ip,
+		     struct ftrace_probe_ops *ops,
+		     void *data)
+{
+	return ftrace_probe_print("traceon", m, ip, ops, data);
+}
+
+static int
+ftrace_traceoff_print(struct seq_file *m, unsigned long ip,
+			 struct ftrace_probe_ops *ops, void *data)
+{
+	return ftrace_probe_print("traceoff", m, ip, ops, data);
+}
+
+static int
+ftrace_stacktrace_print(struct seq_file *m, unsigned long ip,
+			struct ftrace_probe_ops *ops, void *data)
+{
+	return ftrace_probe_print("stacktrace", m, ip, ops, data);
+}
+
+static int
+ftrace_dump_print(struct seq_file *m, unsigned long ip,
+			struct ftrace_probe_ops *ops, void *data)
+{
+	return ftrace_probe_print("dump", m, ip, ops, data);
+}
+
+static int
+ftrace_cpudump_print(struct seq_file *m, unsigned long ip,
+			struct ftrace_probe_ops *ops, void *data)
+{
+	return ftrace_probe_print("cpudump", m, ip, ops, data);
+}
+
+
+static int
+ftrace_count_init(struct ftrace_probe_ops *ops, struct trace_array *tr,
+		  unsigned long ip, void *init_data, void **data)
+{
+	struct ftrace_func_mapper *mapper = *data;
+
+	if (!mapper) {
+		mapper = allocate_ftrace_func_mapper();
+		if (!mapper)
+			return -ENOMEM;
+		*data = mapper;
+	}
+
+	return ftrace_func_mapper_add_ip(mapper, ip, init_data);
+}
+
+static void
+ftrace_count_free(struct ftrace_probe_ops *ops, struct trace_array *tr,
+		  unsigned long ip, void *data)
+{
+	struct ftrace_func_mapper *mapper = data;
+
+	if (!ip) {
+		free_ftrace_func_mapper(mapper, NULL);
+		return;
+	}
+
+	ftrace_func_mapper_remove_ip(mapper, ip);
+}
+
+static struct ftrace_probe_ops traceon_count_probe_ops = {
+	.func			= ftrace_traceon_count,
+	.print			= ftrace_traceon_print,
+	.init			= ftrace_count_init,
+	.free			= ftrace_count_free,
+};
+
+static struct ftrace_probe_ops traceoff_count_probe_ops = {
+	.func			= ftrace_traceoff_count,
+	.print			= ftrace_traceoff_print,
+	.init			= ftrace_count_init,
+	.free			= ftrace_count_free,
+};
+
+static struct ftrace_probe_ops stacktrace_count_probe_ops = {
+	.func			= ftrace_stacktrace_count,
+	.print			= ftrace_stacktrace_print,
+	.init			= ftrace_count_init,
+	.free			= ftrace_count_free,
+};
+
+static struct ftrace_probe_ops dump_probe_ops = {
+	.func			= ftrace_dump_probe,
+	.print			= ftrace_dump_print,
+	.init			= ftrace_count_init,
+	.free			= ftrace_count_free,
+};
+
+static struct ftrace_probe_ops cpudump_probe_ops = {
+	.func			= ftrace_cpudump_probe,
+	.print			= ftrace_cpudump_print,
+};
+
+static struct ftrace_probe_ops traceon_probe_ops = {
+	.func			= ftrace_traceon,
+	.print			= ftrace_traceon_print,
+};
+
+static struct ftrace_probe_ops traceoff_probe_ops = {
+	.func			= ftrace_traceoff,
+	.print			= ftrace_traceoff_print,
+};
+
+static struct ftrace_probe_ops stacktrace_probe_ops = {
+	.func			= ftrace_stacktrace,
+	.print			= ftrace_stacktrace_print,
+};
+
+static int
+ftrace_trace_probe_callback(struct trace_array *tr,
+			    struct ftrace_probe_ops *ops,
+			    struct ftrace_hash *hash, char *glob,
+			    char *cmd, char *param, int enable)
+{
+	void *count = (void *)-1;
+	char *number;
+	int ret;
+
+	/* hash funcs only work with set_ftrace_filter */
+	if (!enable)
+		return -EINVAL;
+
+	if (glob[0] == '!')
+		return unregister_ftrace_function_probe_func(glob+1, tr, ops);
+
+	if (!param)
+		goto out_reg;
+
+	number = strsep(&param, ":");
+
+	if (!strlen(number))
+		goto out_reg;
+
+	/*
+	 * We use the callback data field (which is a pointer)
+	 * as our counter.
+	 */
+	ret = kstrtoul(number, 0, (unsigned long *)&count);
+	if (ret)
+		return ret;
+
+ out_reg:
+	ret = register_ftrace_function_probe(glob, tr, ops, count);
+
+	return ret < 0 ? ret : 0;
+}
+
+static int
+ftrace_trace_onoff_callback(struct trace_array *tr, struct ftrace_hash *hash,
+			    char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+
+	if (!tr)
+		return -ENODEV;
+
+	/* we register both traceon and traceoff to this callback */
+	if (strcmp(cmd, "traceon") == 0)
+		ops = param ? &traceon_count_probe_ops : &traceon_probe_ops;
+	else
+		ops = param ? &traceoff_count_probe_ops : &traceoff_probe_ops;
+
+	return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd,
+					   param, enable);
+}
+
+static int
+ftrace_stacktrace_callback(struct trace_array *tr, struct ftrace_hash *hash,
+			   char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+
+	if (!tr)
+		return -ENODEV;
+
+	ops = param ? &stacktrace_count_probe_ops : &stacktrace_probe_ops;
+
+	return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd,
+					   param, enable);
+}
+
+static int
+ftrace_dump_callback(struct trace_array *tr, struct ftrace_hash *hash,
+			   char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+
+	if (!tr)
+		return -ENODEV;
+
+	ops = &dump_probe_ops;
+
+	/* Only dump once. */
+	return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd,
+					   "1", enable);
+}
+
+static int
+ftrace_cpudump_callback(struct trace_array *tr, struct ftrace_hash *hash,
+			   char *glob, char *cmd, char *param, int enable)
+{
+	struct ftrace_probe_ops *ops;
+
+	if (!tr)
+		return -ENODEV;
+
+	ops = &cpudump_probe_ops;
+
+	/* Only dump once. */
+	return ftrace_trace_probe_callback(tr, ops, hash, glob, cmd,
+					   "1", enable);
+}
+
+static struct ftrace_func_command ftrace_traceon_cmd = {
+	.name			= "traceon",
+	.func			= ftrace_trace_onoff_callback,
+};
+
+static struct ftrace_func_command ftrace_traceoff_cmd = {
+	.name			= "traceoff",
+	.func			= ftrace_trace_onoff_callback,
+};
+
+static struct ftrace_func_command ftrace_stacktrace_cmd = {
+	.name			= "stacktrace",
+	.func			= ftrace_stacktrace_callback,
+};
+
+static struct ftrace_func_command ftrace_dump_cmd = {
+	.name			= "dump",
+	.func			= ftrace_dump_callback,
+};
+
+static struct ftrace_func_command ftrace_cpudump_cmd = {
+	.name			= "cpudump",
+	.func			= ftrace_cpudump_callback,
+};
+
+static int __init init_func_cmd_traceon(void)
+{
+	int ret;
+
+	ret = register_ftrace_command(&ftrace_traceoff_cmd);
+	if (ret)
+		return ret;
+
+	ret = register_ftrace_command(&ftrace_traceon_cmd);
+	if (ret)
+		goto out_free_traceoff;
+
+	ret = register_ftrace_command(&ftrace_stacktrace_cmd);
+	if (ret)
+		goto out_free_traceon;
+
+	ret = register_ftrace_command(&ftrace_dump_cmd);
+	if (ret)
+		goto out_free_stacktrace;
+
+	ret = register_ftrace_command(&ftrace_cpudump_cmd);
+	if (ret)
+		goto out_free_dump;
+
+	return 0;
+
+ out_free_dump:
+	unregister_ftrace_command(&ftrace_dump_cmd);
+ out_free_stacktrace:
+	unregister_ftrace_command(&ftrace_stacktrace_cmd);
+ out_free_traceon:
+	unregister_ftrace_command(&ftrace_traceon_cmd);
+ out_free_traceoff:
+	unregister_ftrace_command(&ftrace_traceoff_cmd);
+
+	return ret;
+}
+#else
+static inline int init_func_cmd_traceon(void)
+{
+	return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+__init int init_function_trace(void)
+{
+	init_func_cmd_traceon();
+	return register_tracer(&function_trace);
+}

kernel/trace/trace_hwlat.c

@@ -0,0 +1,637 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace_hwlatdetect.c - A simple Hardware Latency detector.
+ *
+ * Use this tracer to detect large system latencies induced by the behavior of
+ * certain underlying system hardware or firmware, independent of Linux itself.
+ * The code was developed originally to detect the presence of SMIs on Intel
+ * and AMD systems, although there is no dependency upon x86 herein.
+ *
+ * The classical example usage of this tracer is in detecting the presence of
+ * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a
+ * somewhat special form of hardware interrupt spawned from earlier CPU debug
+ * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge
+ * LPC (or other device) to generate a special interrupt under certain
+ * circumstances, for example, upon expiration of a special SMI timer device,
+ * due to certain external thermal readings, on certain I/O address accesses,
+ * and other situations. An SMI hits a special CPU pin, triggers a special
+ * SMI mode (complete with special memory map), and the OS is unaware.
+ *
+ * Although certain hardware-inducing latencies are necessary (for example,
+ * a modern system often requires an SMI handler for correct thermal control
+ * and remote management) they can wreak havoc upon any OS-level performance
+ * guarantees toward low-latency, especially when the OS is not even made
+ * aware of the presence of these interrupts. For this reason, we need a
+ * somewhat brute force mechanism to detect these interrupts. In this case,
+ * we do it by hogging all of the CPU(s) for configurable timer intervals,
+ * sampling the built-in CPU timer, looking for discontiguous readings.
+ *
+ * WARNING: This implementation necessarily introduces latencies. Therefore,
+ *          you should NEVER use this tracer while running in a production
+ *          environment requiring any kind of low-latency performance
+ *          guarantee(s).
+ *
+ * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. <jcm@redhat.com>
+ * Copyright (C) 2013-2016 Steven Rostedt, Red Hat, Inc. <srostedt@redhat.com>
+ *
+ * Includes useful feedback from Clark Williams <clark@redhat.com>
+ *
+ */
+#include <linux/kthread.h>
+#include <linux/tracefs.h>
+#include <linux/uaccess.h>
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+#include <linux/sched/clock.h>
+#include "trace.h"
+
+static struct trace_array	*hwlat_trace;
+
+#define U64STR_SIZE		22			/* 20 digits max */
+
+#define BANNER			"hwlat_detector: "
+#define DEFAULT_SAMPLE_WINDOW	1000000			/* 1s */
+#define DEFAULT_SAMPLE_WIDTH	500000			/* 0.5s */
+#define DEFAULT_LAT_THRESHOLD	10			/* 10us */
+
+/* sampling thread*/
+static struct task_struct *hwlat_kthread;
+
+static struct dentry *hwlat_sample_width;	/* sample width us */
+static struct dentry *hwlat_sample_window;	/* sample window us */
+
+/* Save the previous tracing_thresh value */
+static unsigned long save_tracing_thresh;
+
+/* NMI timestamp counters */
+static u64 nmi_ts_start;
+static u64 nmi_total_ts;
+static int nmi_count;
+static int nmi_cpu;
+
+/* Tells NMIs to call back to the hwlat tracer to record timestamps */
+bool trace_hwlat_callback_enabled;
+
+/* If the user changed threshold, remember it */
+static u64 last_tracing_thresh = DEFAULT_LAT_THRESHOLD * NSEC_PER_USEC;
+
+/* Individual latency samples are stored here when detected. */
+struct hwlat_sample {
+	u64			seqnum;		/* unique sequence */
+	u64			duration;	/* delta */
+	u64			outer_duration;	/* delta (outer loop) */
+	u64			nmi_total_ts;	/* Total time spent in NMIs */
+	struct timespec64	timestamp;	/* wall time */
+	int			nmi_count;	/* # NMIs during this sample */
+};
+
+/* keep the global state somewhere. */
+static struct hwlat_data {
+
+	struct mutex lock;		/* protect changes */
+
+	u64	count;			/* total since reset */
+
+	u64	sample_window;		/* total sampling window (on+off) */
+	u64	sample_width;		/* active sampling portion of window */
+
+} hwlat_data = {
+	.sample_window		= DEFAULT_SAMPLE_WINDOW,
+	.sample_width		= DEFAULT_SAMPLE_WIDTH,
+};
+
+static void trace_hwlat_sample(struct hwlat_sample *sample)
+{
+	struct trace_array *tr = hwlat_trace;
+	struct trace_event_call *call = &event_hwlat;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
+	struct ring_buffer_event *event;
+	struct hwlat_entry *entry;
+	unsigned long flags;
+	int pc;
+
+	pc = preempt_count();
+	local_save_flags(flags);
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_HWLAT, sizeof(*entry),
+					  flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->seqnum			= sample->seqnum;
+	entry->duration			= sample->duration;
+	entry->outer_duration		= sample->outer_duration;
+	entry->timestamp		= sample->timestamp;
+	entry->nmi_total_ts		= sample->nmi_total_ts;
+	entry->nmi_count		= sample->nmi_count;
+
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit_nostack(buffer, event);
+}
+
+/* Macros to encapsulate the time capturing infrastructure */
+#define time_type	u64
+#define time_get()	trace_clock_local()
+#define time_to_us(x)	div_u64(x, 1000)
+#define time_sub(a, b)	((a) - (b))
+#define init_time(a, b)	(a = b)
+#define time_u64(a)	a
+
+void trace_hwlat_callback(bool enter)
+{
+	if (smp_processor_id() != nmi_cpu)
+		return;
+
+	/*
+	 * Currently trace_clock_local() calls sched_clock() and the
+	 * generic version is not NMI safe.
+	 */
+	if (!IS_ENABLED(CONFIG_GENERIC_SCHED_CLOCK)) {
+		if (enter)
+			nmi_ts_start = time_get();
+		else
+			nmi_total_ts += time_get() - nmi_ts_start;
+	}
+
+	if (enter)
+		nmi_count++;
+}
+
+/**
+ * get_sample - sample the CPU TSC and look for likely hardware latencies
+ *
+ * Used to repeatedly capture the CPU TSC (or similar), looking for potential
+ * hardware-induced latency. Called with interrupts disabled and with
+ * hwlat_data.lock held.
+ */
+static int get_sample(void)
+{
+	struct trace_array *tr = hwlat_trace;
+	time_type start, t1, t2, last_t2;
+	s64 diff, total, last_total = 0;
+	u64 sample = 0;
+	u64 thresh = tracing_thresh;
+	u64 outer_sample = 0;
+	int ret = -1;
+
+	do_div(thresh, NSEC_PER_USEC); /* modifies interval value */
+
+	nmi_cpu = smp_processor_id();
+	nmi_total_ts = 0;
+	nmi_count = 0;
+	/* Make sure NMIs see this first */
+	barrier();
+
+	trace_hwlat_callback_enabled = true;
+
+	init_time(last_t2, 0);
+	start = time_get(); /* start timestamp */
+
+	do {
+
+		t1 = time_get();	/* we'll look for a discontinuity */
+		t2 = time_get();
+
+		if (time_u64(last_t2)) {
+			/* Check the delta from outer loop (t2 to next t1) */
+			diff = time_to_us(time_sub(t1, last_t2));
+			/* This shouldn't happen */
+			if (diff < 0) {
+				pr_err(BANNER "time running backwards\n");
+				goto out;
+			}
+			if (diff > outer_sample)
+				outer_sample = diff;
+		}
+		last_t2 = t2;
+
+		total = time_to_us(time_sub(t2, start)); /* sample width */
+
+		/* Check for possible overflows */
+		if (total < last_total) {
+			pr_err("Time total overflowed\n");
+			break;
+		}
+		last_total = total;
+
+		/* This checks the inner loop (t1 to t2) */
+		diff = time_to_us(time_sub(t2, t1));     /* current diff */
+
+		/* This shouldn't happen */
+		if (diff < 0) {
+			pr_err(BANNER "time running backwards\n");
+			goto out;
+		}
+
+		if (diff > sample)
+			sample = diff; /* only want highest value */
+
+	} while (total <= hwlat_data.sample_width);
+
+	barrier(); /* finish the above in the view for NMIs */
+	trace_hwlat_callback_enabled = false;
+	barrier(); /* Make sure nmi_total_ts is no longer updated */
+
+	ret = 0;
+
+	/* If we exceed the threshold value, we have found a hardware latency */
+	if (sample > thresh || outer_sample > thresh) {
+		struct hwlat_sample s;
+
+		ret = 1;
+
+		/* We read in microseconds */
+		if (nmi_total_ts)
+			do_div(nmi_total_ts, NSEC_PER_USEC);
+
+		hwlat_data.count++;
+		s.seqnum = hwlat_data.count;
+		s.duration = sample;
+		s.outer_duration = outer_sample;
+		ktime_get_real_ts64(&s.timestamp);
+		s.nmi_total_ts = nmi_total_ts;
+		s.nmi_count = nmi_count;
+		trace_hwlat_sample(&s);
+
+		/* Keep a running maximum ever recorded hardware latency */
+		if (sample > tr->max_latency)
+			tr->max_latency = sample;
+		if (outer_sample > tr->max_latency)
+			tr->max_latency = outer_sample;
+	}
+
+out:
+	return ret;
+}
+
+static struct cpumask save_cpumask;
+static bool disable_migrate;
+
+static void move_to_next_cpu(void)
+{
+	struct cpumask *current_mask = &save_cpumask;
+	struct trace_array *tr = hwlat_trace;
+	int next_cpu;
+
+	if (disable_migrate)
+		return;
+	/*
+	 * If for some reason the user modifies the CPU affinity
+	 * of this thread, than stop migrating for the duration
+	 * of the current test.
+	 */
+	if (!cpumask_equal(current_mask, &current->cpus_allowed))
+		goto disable;
+
+	get_online_cpus();
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
+	next_cpu = cpumask_next(smp_processor_id(), current_mask);
+	put_online_cpus();
+
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(current_mask);
+
+	if (next_cpu >= nr_cpu_ids) /* Shouldn't happen! */
+		goto disable;
+
+	cpumask_clear(current_mask);
+	cpumask_set_cpu(next_cpu, current_mask);
+
+	sched_setaffinity(0, current_mask);
+	return;
+
+ disable:
+	disable_migrate = true;
+}
+
+/*
+ * kthread_fn - The CPU time sampling/hardware latency detection kernel thread
+ *
+ * Used to periodically sample the CPU TSC via a call to get_sample. We
+ * disable interrupts, which does (intentionally) introduce latency since we
+ * need to ensure nothing else might be running (and thus preempting).
+ * Obviously this should never be used in production environments.
+ *
+ * Executes one loop interaction on each CPU in tracing_cpumask sysfs file.
+ */
+static int kthread_fn(void *data)
+{
+	u64 interval;
+
+	while (!kthread_should_stop()) {
+
+		move_to_next_cpu();
+
+		local_irq_disable();
+		get_sample();
+		local_irq_enable();
+
+		mutex_lock(&hwlat_data.lock);
+		interval = hwlat_data.sample_window - hwlat_data.sample_width;
+		mutex_unlock(&hwlat_data.lock);
+
+		do_div(interval, USEC_PER_MSEC); /* modifies interval value */
+
+		/* Always sleep for at least 1ms */
+		if (interval < 1)
+			interval = 1;
+
+		if (msleep_interruptible(interval))
+			break;
+	}
+
+	return 0;
+}
+
+/**
+ * start_kthread - Kick off the hardware latency sampling/detector kthread
+ *
+ * This starts the kernel thread that will sit and sample the CPU timestamp
+ * counter (TSC or similar) and look for potential hardware latencies.
+ */
+static int start_kthread(struct trace_array *tr)
+{
+	struct cpumask *current_mask = &save_cpumask;
+	struct task_struct *kthread;
+	int next_cpu;
+
+	if (hwlat_kthread)
+		return 0;
+
+	/* Just pick the first CPU on first iteration */
+	current_mask = &save_cpumask;
+	get_online_cpus();
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
+	put_online_cpus();
+	next_cpu = cpumask_first(current_mask);
+
+	kthread = kthread_create(kthread_fn, NULL, "hwlatd");
+	if (IS_ERR(kthread)) {
+		pr_err(BANNER "could not start sampling thread\n");
+		return -ENOMEM;
+	}
+
+	cpumask_clear(current_mask);
+	cpumask_set_cpu(next_cpu, current_mask);
+	sched_setaffinity(kthread->pid, current_mask);
+
+	hwlat_kthread = kthread;
+	wake_up_process(kthread);
+
+	return 0;
+}
+
+/**
+ * stop_kthread - Inform the hardware latency samping/detector kthread to stop
+ *
+ * This kicks the running hardware latency sampling/detector kernel thread and
+ * tells it to stop sampling now. Use this on unload and at system shutdown.
+ */
+static void stop_kthread(void)
+{
+	if (!hwlat_kthread)
+		return;
+	kthread_stop(hwlat_kthread);
+	hwlat_kthread = NULL;
+}
+
+/*
+ * hwlat_read - Wrapper read function for reading both window and width
+ * @filp: The active open file structure
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function provides a generic read implementation for the global state
+ * "hwlat_data" structure filesystem entries.
+ */
+static ssize_t hwlat_read(struct file *filp, char __user *ubuf,
+			  size_t cnt, loff_t *ppos)
+{
+	char buf[U64STR_SIZE];
+	u64 *entry = filp->private_data;
+	u64 val;
+	int len;
+
+	if (!entry)
+		return -EFAULT;
+
+	if (cnt > sizeof(buf))
+		cnt = sizeof(buf);
+
+	val = *entry;
+
+	len = snprintf(buf, sizeof(buf), "%llu\n", val);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
+}
+
+/**
+ * hwlat_width_write - Write function for "width" entry
+ * @filp: The active open file structure
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in @file
+ *
+ * This function provides a write implementation for the "width" interface
+ * to the hardware latency detector. It can be used to configure
+ * for how many us of the total window us we will actively sample for any
+ * hardware-induced latency periods. Obviously, it is not possible to
+ * sample constantly and have the system respond to a sample reader, or,
+ * worse, without having the system appear to have gone out to lunch. It
+ * is enforced that width is less that the total window size.
+ */
+static ssize_t
+hwlat_width_write(struct file *filp, const char __user *ubuf,
+		  size_t cnt, loff_t *ppos)
+{
+	u64 val;
+	int err;
+
+	err = kstrtoull_from_user(ubuf, cnt, 10, &val);
+	if (err)
+		return err;
+
+	mutex_lock(&hwlat_data.lock);
+	if (val < hwlat_data.sample_window)
+		hwlat_data.sample_width = val;
+	else
+		err = -EINVAL;
+	mutex_unlock(&hwlat_data.lock);
+
+	if (err)
+		return err;
+
+	return cnt;
+}
+
+/**
+ * hwlat_window_write - Write function for "window" entry
+ * @filp: The active open file structure
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in @file
+ *
+ * This function provides a write implementation for the "window" interface
+ * to the hardware latency detetector. The window is the total time
+ * in us that will be considered one sample period. Conceptually, windows
+ * occur back-to-back and contain a sample width period during which
+ * actual sampling occurs. Can be used to write a new total window size. It
+ * is enfoced that any value written must be greater than the sample width
+ * size, or an error results.
+ */
+static ssize_t
+hwlat_window_write(struct file *filp, const char __user *ubuf,
+		   size_t cnt, loff_t *ppos)
+{
+	u64 val;
+	int err;
+
+	err = kstrtoull_from_user(ubuf, cnt, 10, &val);
+	if (err)
+		return err;
+
+	mutex_lock(&hwlat_data.lock);
+	if (hwlat_data.sample_width < val)
+		hwlat_data.sample_window = val;
+	else
+		err = -EINVAL;
+	mutex_unlock(&hwlat_data.lock);
+
+	if (err)
+		return err;
+
+	return cnt;
+}
+
+static const struct file_operations width_fops = {
+	.open		= tracing_open_generic,
+	.read		= hwlat_read,
+	.write		= hwlat_width_write,
+};
+
+static const struct file_operations window_fops = {
+	.open		= tracing_open_generic,
+	.read		= hwlat_read,
+	.write		= hwlat_window_write,
+};
+
+/**
+ * init_tracefs - A function to initialize the tracefs interface files
+ *
+ * This function creates entries in tracefs for "hwlat_detector".
+ * It creates the hwlat_detector directory in the tracing directory,
+ * and within that directory is the count, width and window files to
+ * change and view those values.
+ */
+static int init_tracefs(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *top_dir;
+
+	d_tracer = tracing_init_dentry();
+	if (IS_ERR(d_tracer))
+		return -ENOMEM;
+
+	top_dir = tracefs_create_dir("hwlat_detector", d_tracer);
+	if (!top_dir)
+		return -ENOMEM;
+
+	hwlat_sample_window = tracefs_create_file("window", 0640,
+						  top_dir,
+						  &hwlat_data.sample_window,
+						  &window_fops);
+	if (!hwlat_sample_window)
+		goto err;
+
+	hwlat_sample_width = tracefs_create_file("width", 0644,
+						 top_dir,
+						 &hwlat_data.sample_width,
+						 &width_fops);
+	if (!hwlat_sample_width)
+		goto err;
+
+	return 0;
+
+ err:
+	tracefs_remove_recursive(top_dir);
+	return -ENOMEM;
+}
+
+static void hwlat_tracer_start(struct trace_array *tr)
+{
+	int err;
+
+	err = start_kthread(tr);
+	if (err)
+		pr_err(BANNER "Cannot start hwlat kthread\n");
+}
+
+static void hwlat_tracer_stop(struct trace_array *tr)
+{
+	stop_kthread();
+}
+
+static bool hwlat_busy;
+
+static int hwlat_tracer_init(struct trace_array *tr)
+{
+	/* Only allow one instance to enable this */
+	if (hwlat_busy)
+		return -EBUSY;
+
+	hwlat_trace = tr;
+
+	disable_migrate = false;
+	hwlat_data.count = 0;
+	tr->max_latency = 0;
+	save_tracing_thresh = tracing_thresh;
+
+	/* tracing_thresh is in nsecs, we speak in usecs */
+	if (!tracing_thresh)
+		tracing_thresh = last_tracing_thresh;
+
+	if (tracer_tracing_is_on(tr))
+		hwlat_tracer_start(tr);
+
+	hwlat_busy = true;
+
+	return 0;
+}
+
+static void hwlat_tracer_reset(struct trace_array *tr)
+{
+	stop_kthread();
+
+	/* the tracing threshold is static between runs */
+	last_tracing_thresh = tracing_thresh;
+
+	tracing_thresh = save_tracing_thresh;
+	hwlat_busy = false;
+}
+
+static struct tracer hwlat_tracer __read_mostly =
+{
+	.name		= "hwlat",
+	.init		= hwlat_tracer_init,
+	.reset		= hwlat_tracer_reset,
+	.start		= hwlat_tracer_start,
+	.stop		= hwlat_tracer_stop,
+	.allow_instances = true,
+};
+
+__init static int init_hwlat_tracer(void)
+{
+	int ret;
+
+	mutex_init(&hwlat_data.lock);
+
+	ret = register_tracer(&hwlat_tracer);
+	if (ret)
+		return ret;
+
+	init_tracefs();
+
+	return 0;
+}
+late_initcall(init_hwlat_tracer);

kernel/trace/trace_irqsoff.c

@@ -0,0 +1,760 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace irqs off critical timings
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * From code in the latency_tracer, that is:
+ *
+ *  Copyright (C) 2004-2006 Ingo Molnar
+ *  Copyright (C) 2004 Nadia Yvette Chambers
+ */
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+
+#include "trace.h"
+
+#include <trace/events/preemptirq.h>
+
+#if defined(CONFIG_IRQSOFF_TRACER) || defined(CONFIG_PREEMPT_TRACER)
+static struct trace_array		*irqsoff_trace __read_mostly;
+static int				tracer_enabled __read_mostly;
+
+static DEFINE_PER_CPU(int, tracing_cpu);
+
+static DEFINE_RAW_SPINLOCK(max_trace_lock);
+
+enum {
+	TRACER_IRQS_OFF		= (1 << 1),
+	TRACER_PREEMPT_OFF	= (1 << 2),
+};
+
+static int trace_type __read_mostly;
+
+static int save_flags;
+
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
+static int start_irqsoff_tracer(struct trace_array *tr, int graph);
+
+#ifdef CONFIG_PREEMPT_TRACER
+static inline int
+preempt_trace(int pc)
+{
+	return ((trace_type & TRACER_PREEMPT_OFF) && pc);
+}
+#else
+# define preempt_trace(pc) (0)
+#endif
+
+#ifdef CONFIG_IRQSOFF_TRACER
+static inline int
+irq_trace(void)
+{
+	return ((trace_type & TRACER_IRQS_OFF) &&
+		irqs_disabled());
+}
+#else
+# define irq_trace() (0)
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int irqsoff_display_graph(struct trace_array *tr, int set);
+# define is_graph(tr) ((tr)->trace_flags & TRACE_ITER_DISPLAY_GRAPH)
+#else
+static inline int irqsoff_display_graph(struct trace_array *tr, int set)
+{
+	return -EINVAL;
+}
+# define is_graph(tr) false
+#endif
+
+/*
+ * Sequence count - we record it when starting a measurement and
+ * skip the latency if the sequence has changed - some other section
+ * did a maximum and could disturb our measurement with serial console
+ * printouts, etc. Truly coinciding maximum latencies should be rare
+ * and what happens together happens separately as well, so this doesn't
+ * decrease the validity of the maximum found:
+ */
+static __cacheline_aligned_in_smp	unsigned long max_sequence;
+
+#ifdef CONFIG_FUNCTION_TRACER
+/*
+ * Prologue for the preempt and irqs off function tracers.
+ *
+ * Returns 1 if it is OK to continue, and data->disabled is
+ *            incremented.
+ *         0 if the trace is to be ignored, and data->disabled
+ *            is kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
+ */
+static int func_prolog_dec(struct trace_array *tr,
+			   struct trace_array_cpu **data,
+			   unsigned long *flags)
+{
+	long disabled;
+	int cpu;
+
+	/*
+	 * Does not matter if we preempt. We test the flags
+	 * afterward, to see if irqs are disabled or not.
+	 * If we preempt and get a false positive, the flags
+	 * test will fail.
+	 */
+	cpu = raw_smp_processor_id();
+	if (likely(!per_cpu(tracing_cpu, cpu)))
+		return 0;
+
+	local_save_flags(*flags);
+	/*
+	 * Slight chance to get a false positive on tracing_cpu,
+	 * although I'm starting to think there isn't a chance.
+	 * Leave this for now just to be paranoid.
+	 */
+	if (!irqs_disabled_flags(*flags) && !preempt_count())
+		return 0;
+
+	*data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+	disabled = atomic_inc_return(&(*data)->disabled);
+
+	if (likely(disabled == 1))
+		return 1;
+
+	atomic_dec(&(*data)->disabled);
+
+	return 0;
+}
+
+/*
+ * irqsoff uses its own tracer function to keep the overhead down:
+ */
+static void
+irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
+		    struct ftrace_ops *op, struct pt_regs *pt_regs)
+{
+	struct trace_array *tr = irqsoff_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+
+	if (!func_prolog_dec(tr, &data, &flags))
+		return;
+
+	trace_function(tr, ip, parent_ip, flags, preempt_count());
+
+	atomic_dec(&data->disabled);
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int irqsoff_display_graph(struct trace_array *tr, int set)
+{
+	int cpu;
+
+	if (!(is_graph(tr) ^ set))
+		return 0;
+
+	stop_irqsoff_tracer(irqsoff_trace, !set);
+
+	for_each_possible_cpu(cpu)
+		per_cpu(tracing_cpu, cpu) = 0;
+
+	tr->max_latency = 0;
+	tracing_reset_online_cpus(&irqsoff_trace->trace_buffer);
+
+	return start_irqsoff_tracer(irqsoff_trace, set);
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = irqsoff_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	int ret;
+	int pc;
+
+	if (ftrace_graph_ignore_func(trace))
+		return 0;
+	/*
+	 * Do not trace a function if it's filtered by set_graph_notrace.
+	 * Make the index of ret stack negative to indicate that it should
+	 * ignore further functions.  But it needs its own ret stack entry
+	 * to recover the original index in order to continue tracing after
+	 * returning from the function.
+	 */
+	if (ftrace_graph_notrace_addr(trace->func))
+		return 1;
+
+	if (!func_prolog_dec(tr, &data, &flags))
+		return 0;
+
+	pc = preempt_count();
+	ret = __trace_graph_entry(tr, trace, flags, pc);
+	atomic_dec(&data->disabled);
+
+	return ret;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct trace_array *tr = irqsoff_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	int pc;
+
+	ftrace_graph_addr_finish(trace);
+
+	if (!func_prolog_dec(tr, &data, &flags))
+		return;
+
+	pc = preempt_count();
+	__trace_graph_return(tr, trace, flags, pc);
+	atomic_dec(&data->disabled);
+}
+
+static void irqsoff_trace_open(struct trace_iterator *iter)
+{
+	if (is_graph(iter->tr))
+		graph_trace_open(iter);
+
+}
+
+static void irqsoff_trace_close(struct trace_iterator *iter)
+{
+	if (iter->private)
+		graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \
+			    TRACE_GRAPH_PRINT_PROC | \
+			    TRACE_GRAPH_PRINT_ABS_TIME | \
+			    TRACE_GRAPH_PRINT_DURATION)
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+	/*
+	 * In graph mode call the graph tracer output function,
+	 * otherwise go with the TRACE_FN event handler
+	 */
+	if (is_graph(iter->tr))
+		return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
+
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_print_header(struct seq_file *s)
+{
+	struct trace_array *tr = irqsoff_trace;
+
+	if (is_graph(tr))
+		print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+	else
+		trace_default_header(s);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+		 unsigned long ip, unsigned long parent_ip,
+		 unsigned long flags, int pc)
+{
+	if (is_graph(tr))
+		trace_graph_function(tr, ip, parent_ip, flags, pc);
+	else
+		trace_function(tr, ip, parent_ip, flags, pc);
+}
+
+#else
+#define __trace_function trace_function
+
+#ifdef CONFIG_FUNCTION_TRACER
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+	return -1;
+}
+#endif
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_trace_open(struct trace_iterator *iter) { }
+static void irqsoff_trace_close(struct trace_iterator *iter) { }
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
+static void irqsoff_print_header(struct seq_file *s)
+{
+	trace_default_header(s);
+}
+#else
+static void irqsoff_print_header(struct seq_file *s)
+{
+	trace_latency_header(s);
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+/*
+ * Should this new latency be reported/recorded?
+ */
+static bool report_latency(struct trace_array *tr, u64 delta)
+{
+	if (tracing_thresh) {
+		if (delta < tracing_thresh)
+			return false;
+	} else {
+		if (delta <= tr->max_latency)
+			return false;
+	}
+	return true;
+}
+
+static void
+check_critical_timing(struct trace_array *tr,
+		      struct trace_array_cpu *data,
+		      unsigned long parent_ip,
+		      int cpu)
+{
+	u64 T0, T1, delta;
+	unsigned long flags;
+	int pc;
+
+	T0 = data->preempt_timestamp;
+	T1 = ftrace_now(cpu);
+	delta = T1-T0;
+
+	local_save_flags(flags);
+
+	pc = preempt_count();
+
+	if (!report_latency(tr, delta))
+		goto out;
+
+	raw_spin_lock_irqsave(&max_trace_lock, flags);
+
+	/* check if we are still the max latency */
+	if (!report_latency(tr, delta))
+		goto out_unlock;
+
+	__trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+	/* Skip 5 functions to get to the irq/preempt enable function */
+	__trace_stack(tr, flags, 5, pc);
+
+	if (data->critical_sequence != max_sequence)
+		goto out_unlock;
+
+	data->critical_end = parent_ip;
+
+	if (likely(!is_tracing_stopped())) {
+		tr->max_latency = delta;
+		update_max_tr_single(tr, current, cpu);
+	}
+
+	max_sequence++;
+
+out_unlock:
+	raw_spin_unlock_irqrestore(&max_trace_lock, flags);
+
+out:
+	data->critical_sequence = max_sequence;
+	data->preempt_timestamp = ftrace_now(cpu);
+	__trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+}
+
+static inline void
+start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc)
+{
+	int cpu;
+	struct trace_array *tr = irqsoff_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+
+	if (!tracer_enabled || !tracing_is_enabled())
+		return;
+
+	cpu = raw_smp_processor_id();
+
+	if (per_cpu(tracing_cpu, cpu))
+		return;
+
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+
+	if (unlikely(!data) || atomic_read(&data->disabled))
+		return;
+
+	atomic_inc(&data->disabled);
+
+	data->critical_sequence = max_sequence;
+	data->preempt_timestamp = ftrace_now(cpu);
+	data->critical_start = parent_ip ? : ip;
+
+	local_save_flags(flags);
+
+	__trace_function(tr, ip, parent_ip, flags, pc);
+
+	per_cpu(tracing_cpu, cpu) = 1;
+
+	atomic_dec(&data->disabled);
+}
+
+static inline void
+stop_critical_timing(unsigned long ip, unsigned long parent_ip, int pc)
+{
+	int cpu;
+	struct trace_array *tr = irqsoff_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+
+	cpu = raw_smp_processor_id();
+	/* Always clear the tracing cpu on stopping the trace */
+	if (unlikely(per_cpu(tracing_cpu, cpu)))
+		per_cpu(tracing_cpu, cpu) = 0;
+	else
+		return;
+
+	if (!tracer_enabled || !tracing_is_enabled())
+		return;
+
+	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+
+	if (unlikely(!data) ||
+	    !data->critical_start || atomic_read(&data->disabled))
+		return;
+
+	atomic_inc(&data->disabled);
+
+	local_save_flags(flags);
+	__trace_function(tr, ip, parent_ip, flags, pc);
+	check_critical_timing(tr, data, parent_ip ? : ip, cpu);
+	data->critical_start = 0;
+	atomic_dec(&data->disabled);
+}
+
+/* start and stop critical timings used to for stoppage (in idle) */
+void start_critical_timings(void)
+{
+	int pc = preempt_count();
+
+	if (preempt_trace(pc) || irq_trace())
+		start_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc);
+}
+EXPORT_SYMBOL_GPL(start_critical_timings);
+
+void stop_critical_timings(void)
+{
+	int pc = preempt_count();
+
+	if (preempt_trace(pc) || irq_trace())
+		stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1, pc);
+}
+EXPORT_SYMBOL_GPL(stop_critical_timings);
+
+#ifdef CONFIG_FUNCTION_TRACER
+static bool function_enabled;
+
+static int register_irqsoff_function(struct trace_array *tr, int graph, int set)
+{
+	int ret;
+
+	/* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
+	if (function_enabled || (!set && !(tr->trace_flags & TRACE_ITER_FUNCTION)))
+		return 0;
+
+	if (graph)
+		ret = register_ftrace_graph(&irqsoff_graph_return,
+					    &irqsoff_graph_entry);
+	else
+		ret = register_ftrace_function(tr->ops);
+
+	if (!ret)
+		function_enabled = true;
+
+	return ret;
+}
+
+static void unregister_irqsoff_function(struct trace_array *tr, int graph)
+{
+	if (!function_enabled)
+		return;
+
+	if (graph)
+		unregister_ftrace_graph();
+	else
+		unregister_ftrace_function(tr->ops);
+
+	function_enabled = false;
+}
+
+static int irqsoff_function_set(struct trace_array *tr, u32 mask, int set)
+{
+	if (!(mask & TRACE_ITER_FUNCTION))
+		return 0;
+
+	if (set)
+		register_irqsoff_function(tr, is_graph(tr), 1);
+	else
+		unregister_irqsoff_function(tr, is_graph(tr));
+	return 1;
+}
+#else
+static int register_irqsoff_function(struct trace_array *tr, int graph, int set)
+{
+	return 0;
+}
+static void unregister_irqsoff_function(struct trace_array *tr, int graph) { }
+static inline int irqsoff_function_set(struct trace_array *tr, u32 mask, int set)
+{
+	return 0;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
+static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set)
+{
+	struct tracer *tracer = tr->current_trace;
+
+	if (irqsoff_function_set(tr, mask, set))
+		return 0;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (mask & TRACE_ITER_DISPLAY_GRAPH)
+		return irqsoff_display_graph(tr, set);
+#endif
+
+	return trace_keep_overwrite(tracer, mask, set);
+}
+
+static int start_irqsoff_tracer(struct trace_array *tr, int graph)
+{
+	int ret;
+
+	ret = register_irqsoff_function(tr, graph, 0);
+
+	if (!ret && tracing_is_enabled())
+		tracer_enabled = 1;
+	else
+		tracer_enabled = 0;
+
+	return ret;
+}
+
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
+{
+	tracer_enabled = 0;
+
+	unregister_irqsoff_function(tr, graph);
+}
+
+static bool irqsoff_busy;
+
+static int __irqsoff_tracer_init(struct trace_array *tr)
+{
+	if (irqsoff_busy)
+		return -EBUSY;
+
+	save_flags = tr->trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
+
+	tr->max_latency = 0;
+	irqsoff_trace = tr;
+	/* make sure that the tracer is visible */
+	smp_wmb();
+
+	ftrace_init_array_ops(tr, irqsoff_tracer_call);
+
+	/* Only toplevel instance supports graph tracing */
+	if (start_irqsoff_tracer(tr, (tr->flags & TRACE_ARRAY_FL_GLOBAL &&
+				      is_graph(tr))))
+		printk(KERN_ERR "failed to start irqsoff tracer\n");
+
+	irqsoff_busy = true;
+	return 0;
+}
+
+static void __irqsoff_tracer_reset(struct trace_array *tr)
+{
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
+	stop_irqsoff_tracer(tr, is_graph(tr));
+
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
+	ftrace_reset_array_ops(tr);
+
+	irqsoff_busy = false;
+}
+
+static void irqsoff_tracer_start(struct trace_array *tr)
+{
+	tracer_enabled = 1;
+}
+
+static void irqsoff_tracer_stop(struct trace_array *tr)
+{
+	tracer_enabled = 0;
+}
+
+#ifdef CONFIG_IRQSOFF_TRACER
+/*
+ * We are only interested in hardirq on/off events:
+ */
+void tracer_hardirqs_on(unsigned long a0, unsigned long a1)
+{
+	unsigned int pc = preempt_count();
+
+	if (!preempt_trace(pc) && irq_trace())
+		stop_critical_timing(a0, a1, pc);
+}
+
+void tracer_hardirqs_off(unsigned long a0, unsigned long a1)
+{
+	unsigned int pc = preempt_count();
+
+	if (!preempt_trace(pc) && irq_trace())
+		start_critical_timing(a0, a1, pc);
+}
+
+static int irqsoff_tracer_init(struct trace_array *tr)
+{
+	trace_type = TRACER_IRQS_OFF;
+
+	return __irqsoff_tracer_init(tr);
+}
+
+static void irqsoff_tracer_reset(struct trace_array *tr)
+{
+	__irqsoff_tracer_reset(tr);
+}
+
+static struct tracer irqsoff_tracer __read_mostly =
+{
+	.name		= "irqsoff",
+	.init		= irqsoff_tracer_init,
+	.reset		= irqsoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
+	.print_max	= true,
+	.print_header   = irqsoff_print_header,
+	.print_line     = irqsoff_print_line,
+	.flag_changed	= irqsoff_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_irqsoff,
+#endif
+	.open           = irqsoff_trace_open,
+	.close          = irqsoff_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+#endif /*  CONFIG_IRQSOFF_TRACER */
+
+#ifdef CONFIG_PREEMPT_TRACER
+void tracer_preempt_on(unsigned long a0, unsigned long a1)
+{
+	int pc = preempt_count();
+
+	if (preempt_trace(pc) && !irq_trace())
+		stop_critical_timing(a0, a1, pc);
+}
+
+void tracer_preempt_off(unsigned long a0, unsigned long a1)
+{
+	int pc = preempt_count();
+
+	if (preempt_trace(pc) && !irq_trace())
+		start_critical_timing(a0, a1, pc);
+}
+
+static int preemptoff_tracer_init(struct trace_array *tr)
+{
+	trace_type = TRACER_PREEMPT_OFF;
+
+	return __irqsoff_tracer_init(tr);
+}
+
+static void preemptoff_tracer_reset(struct trace_array *tr)
+{
+	__irqsoff_tracer_reset(tr);
+}
+
+static struct tracer preemptoff_tracer __read_mostly =
+{
+	.name		= "preemptoff",
+	.init		= preemptoff_tracer_init,
+	.reset		= preemptoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
+	.print_max	= true,
+	.print_header   = irqsoff_print_header,
+	.print_line     = irqsoff_print_line,
+	.flag_changed	= irqsoff_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_preemptoff,
+#endif
+	.open		= irqsoff_trace_open,
+	.close		= irqsoff_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+#endif /* CONFIG_PREEMPT_TRACER */
+
+#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER)
+
+static int preemptirqsoff_tracer_init(struct trace_array *tr)
+{
+	trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF;
+
+	return __irqsoff_tracer_init(tr);
+}
+
+static void preemptirqsoff_tracer_reset(struct trace_array *tr)
+{
+	__irqsoff_tracer_reset(tr);
+}
+
+static struct tracer preemptirqsoff_tracer __read_mostly =
+{
+	.name		= "preemptirqsoff",
+	.init		= preemptirqsoff_tracer_init,
+	.reset		= preemptirqsoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
+	.print_max	= true,
+	.print_header   = irqsoff_print_header,
+	.print_line     = irqsoff_print_line,
+	.flag_changed	= irqsoff_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_preemptirqsoff,
+#endif
+	.open		= irqsoff_trace_open,
+	.close		= irqsoff_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+#endif
+
+__init static int init_irqsoff_tracer(void)
+{
+#ifdef CONFIG_IRQSOFF_TRACER
+	register_tracer(&irqsoff_tracer);
+#endif
+#ifdef CONFIG_PREEMPT_TRACER
+	register_tracer(&preemptoff_tracer);
+#endif
+#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER)
+	register_tracer(&preemptirqsoff_tracer);
+#endif
+
+	return 0;
+}
+core_initcall(init_irqsoff_tracer);
+#endif /* IRQSOFF_TRACER || PREEMPTOFF_TRACER */

kernel/trace/trace_kdb.c

@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kdb helper for dumping the ftrace buffer
+ *
+ * Copyright (C) 2010 Jason Wessel <jason.wessel@windriver.com>
+ *
+ * ftrace_dump_buf based on ftrace_dump:
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ */
+#include <linux/init.h>
+#include <linux/kgdb.h>
+#include <linux/kdb.h>
+#include <linux/ftrace.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+static void ftrace_dump_buf(int skip_lines, long cpu_file)
+{
+	/* use static because iter can be a bit big for the stack */
+	static struct trace_iterator iter;
+	static struct ring_buffer_iter *buffer_iter[CONFIG_NR_CPUS];
+	struct trace_array *tr;
+	unsigned int old_userobj;
+	int cnt = 0, cpu;
+
+	trace_init_global_iter(&iter);
+	iter.buffer_iter = buffer_iter;
+	tr = iter.tr;
+
+	for_each_tracing_cpu(cpu) {
+		atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
+	}
+
+	old_userobj = tr->trace_flags;
+
+	/* don't look at user memory in panic mode */
+	tr->trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+
+	kdb_printf("Dumping ftrace buffer:\n");
+
+	trace_iterator_reset(&iter);
+	iter.iter_flags |= TRACE_FILE_LAT_FMT;
+
+	if (cpu_file == RING_BUFFER_ALL_CPUS) {
+		for_each_tracing_cpu(cpu) {
+			iter.buffer_iter[cpu] =
+			ring_buffer_read_prepare(iter.trace_buffer->buffer,
+						 cpu, GFP_ATOMIC);
+			ring_buffer_read_start(iter.buffer_iter[cpu]);
+			tracing_iter_reset(&iter, cpu);
+		}
+	} else {
+		iter.cpu_file = cpu_file;
+		iter.buffer_iter[cpu_file] =
+			ring_buffer_read_prepare(iter.trace_buffer->buffer,
+						 cpu_file, GFP_ATOMIC);
+		ring_buffer_read_start(iter.buffer_iter[cpu_file]);
+		tracing_iter_reset(&iter, cpu_file);
+	}
+
+	while (trace_find_next_entry_inc(&iter)) {
+		if (!cnt)
+			kdb_printf("---------------------------------\n");
+		cnt++;
+
+		if (!skip_lines) {
+			print_trace_line(&iter);
+			trace_printk_seq(&iter.seq);
+		} else {
+			skip_lines--;
+		}
+
+		if (KDB_FLAG(CMD_INTERRUPT))
+			goto out;
+	}
+
+	if (!cnt)
+		kdb_printf("   (ftrace buffer empty)\n");
+	else
+		kdb_printf("---------------------------------\n");
+
+out:
+	tr->trace_flags = old_userobj;
+
+	for_each_tracing_cpu(cpu) {
+		atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
+	}
+
+	for_each_tracing_cpu(cpu) {
+		if (iter.buffer_iter[cpu]) {
+			ring_buffer_read_finish(iter.buffer_iter[cpu]);
+			iter.buffer_iter[cpu] = NULL;
+		}
+	}
+}
+
+/*
+ * kdb_ftdump - Dump the ftrace log buffer
+ */
+static int kdb_ftdump(int argc, const char **argv)
+{
+	int skip_lines = 0;
+	long cpu_file;
+	char *cp;
+
+	if (argc > 2)
+		return KDB_ARGCOUNT;
+
+	if (argc) {
+		skip_lines = simple_strtol(argv[1], &cp, 0);
+		if (*cp)
+			skip_lines = 0;
+	}
+
+	if (argc == 2) {
+		cpu_file = simple_strtol(argv[2], &cp, 0);
+		if (*cp || cpu_file >= NR_CPUS || cpu_file < 0 ||
+		    !cpu_online(cpu_file))
+			return KDB_BADINT;
+	} else {
+		cpu_file = RING_BUFFER_ALL_CPUS;
+	}
+
+	kdb_trap_printk++;
+	ftrace_dump_buf(skip_lines, cpu_file);
+	kdb_trap_printk--;
+
+	return 0;
+}
+
+static __init int kdb_ftrace_register(void)
+{
+	kdb_register_flags("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
+			    "Dump ftrace log", 0, KDB_ENABLE_ALWAYS_SAFE);
+	return 0;
+}
+
+late_initcall(kdb_ftrace_register);

kernel/trace/trace_kprobe_selftest.c

@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Function used during the kprobe self test. This function is in a separate
+ * compile unit so it can be compile with CC_FLAGS_FTRACE to ensure that it
+ * can be probed by the selftests.
+ */
+int kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6)
+{
+	return a1 + a2 + a3 + a4 + a5 + a6;
+}

kernel/trace/trace_kprobe_selftest.h

@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Function used during the kprobe self test. This function is in a separate
+ * compile unit so it can be compile with CC_FLAGS_FTRACE to ensure that it
+ * can be probed by the selftests.
+ */
+int kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6);

kernel/trace/trace_mmiotrace.c

@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Memory mapped I/O tracing
+ *
+ * Copyright (C) 2008 Pekka Paalanen <pq@iki.fi>
+ */
+
+#define DEBUG 1
+
+#include <linux/kernel.h>
+#include <linux/mmiotrace.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+
+#include <linux/atomic.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+struct header_iter {
+	struct pci_dev *dev;
+};
+
+static struct trace_array *mmio_trace_array;
+static bool overrun_detected;
+static unsigned long prev_overruns;
+static atomic_t dropped_count;
+
+static void mmio_reset_data(struct trace_array *tr)
+{
+	overrun_detected = false;
+	prev_overruns = 0;
+
+	tracing_reset_online_cpus(&tr->trace_buffer);
+}
+
+static int mmio_trace_init(struct trace_array *tr)
+{
+	pr_debug("in %s\n", __func__);
+	mmio_trace_array = tr;
+
+	mmio_reset_data(tr);
+	enable_mmiotrace();
+	return 0;
+}
+
+static void mmio_trace_reset(struct trace_array *tr)
+{
+	pr_debug("in %s\n", __func__);
+
+	disable_mmiotrace();
+	mmio_reset_data(tr);
+	mmio_trace_array = NULL;
+}
+
+static void mmio_trace_start(struct trace_array *tr)
+{
+	pr_debug("in %s\n", __func__);
+	mmio_reset_data(tr);
+}
+
+static void mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
+{
+	int i;
+	resource_size_t start, end;
+	const struct pci_driver *drv = pci_dev_driver(dev);
+
+	trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
+			 dev->bus->number, dev->devfn,
+			 dev->vendor, dev->device, dev->irq);
+	for (i = 0; i < 7; i++) {
+		start = dev->resource[i].start;
+		trace_seq_printf(s, " %llx",
+			(unsigned long long)(start |
+			(dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
+	}
+	for (i = 0; i < 7; i++) {
+		start = dev->resource[i].start;
+		end = dev->resource[i].end;
+		trace_seq_printf(s, " %llx",
+			dev->resource[i].start < dev->resource[i].end ?
+			(unsigned long long)(end - start) + 1 : 0);
+	}
+	if (drv)
+		trace_seq_printf(s, " %s\n", drv->name);
+	else
+		trace_seq_puts(s, " \n");
+}
+
+static void destroy_header_iter(struct header_iter *hiter)
+{
+	if (!hiter)
+		return;
+	pci_dev_put(hiter->dev);
+	kfree(hiter);
+}
+
+static void mmio_pipe_open(struct trace_iterator *iter)
+{
+	struct header_iter *hiter;
+	struct trace_seq *s = &iter->seq;
+
+	trace_seq_puts(s, "VERSION 20070824\n");
+
+	hiter = kzalloc(sizeof(*hiter), GFP_KERNEL);
+	if (!hiter)
+		return;
+
+	hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, NULL);
+	iter->private = hiter;
+}
+
+/* XXX: This is not called when the pipe is closed! */
+static void mmio_close(struct trace_iterator *iter)
+{
+	struct header_iter *hiter = iter->private;
+	destroy_header_iter(hiter);
+	iter->private = NULL;
+}
+
+static unsigned long count_overruns(struct trace_iterator *iter)
+{
+	unsigned long cnt = atomic_xchg(&dropped_count, 0);
+	unsigned long over = ring_buffer_overruns(iter->trace_buffer->buffer);
+
+	if (over > prev_overruns)
+		cnt += over - prev_overruns;
+	prev_overruns = over;
+	return cnt;
+}
+
+static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp,
+				char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	ssize_t ret;
+	struct header_iter *hiter = iter->private;
+	struct trace_seq *s = &iter->seq;
+	unsigned long n;
+
+	n = count_overruns(iter);
+	if (n) {
+		/* XXX: This is later than where events were lost. */
+		trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n);
+		if (!overrun_detected)
+			pr_warn("mmiotrace has lost events\n");
+		overrun_detected = true;
+		goto print_out;
+	}
+
+	if (!hiter)
+		return 0;
+
+	mmio_print_pcidev(s, hiter->dev);
+	hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, hiter->dev);
+
+	if (!hiter->dev) {
+		destroy_header_iter(hiter);
+		iter->private = NULL;
+	}
+
+print_out:
+	ret = trace_seq_to_user(s, ubuf, cnt);
+	return (ret == -EBUSY) ? 0 : ret;
+}
+
+static enum print_line_t mmio_print_rw(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+	struct trace_mmiotrace_rw *field;
+	struct mmiotrace_rw *rw;
+	struct trace_seq *s	= &iter->seq;
+	unsigned long long t	= ns2usecs(iter->ts);
+	unsigned long usec_rem	= do_div(t, USEC_PER_SEC);
+	unsigned secs		= (unsigned long)t;
+
+	trace_assign_type(field, entry);
+	rw = &field->rw;
+
+	switch (rw->opcode) {
+	case MMIO_READ:
+		trace_seq_printf(s,
+			"R %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
+			rw->width, secs, usec_rem, rw->map_id,
+			(unsigned long long)rw->phys,
+			rw->value, rw->pc, 0);
+		break;
+	case MMIO_WRITE:
+		trace_seq_printf(s,
+			"W %d %u.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
+			rw->width, secs, usec_rem, rw->map_id,
+			(unsigned long long)rw->phys,
+			rw->value, rw->pc, 0);
+		break;
+	case MMIO_UNKNOWN_OP:
+		trace_seq_printf(s,
+			"UNKNOWN %u.%06lu %d 0x%llx %02lx,%02lx,"
+			"%02lx 0x%lx %d\n",
+			secs, usec_rem, rw->map_id,
+			(unsigned long long)rw->phys,
+			(rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff,
+			(rw->value >> 0) & 0xff, rw->pc, 0);
+		break;
+	default:
+		trace_seq_puts(s, "rw what?\n");
+		break;
+	}
+
+	return trace_handle_return(s);
+}
+
+static enum print_line_t mmio_print_map(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+	struct trace_mmiotrace_map *field;
+	struct mmiotrace_map *m;
+	struct trace_seq *s	= &iter->seq;
+	unsigned long long t	= ns2usecs(iter->ts);
+	unsigned long usec_rem	= do_div(t, USEC_PER_SEC);
+	unsigned secs		= (unsigned long)t;
+
+	trace_assign_type(field, entry);
+	m = &field->map;
+
+	switch (m->opcode) {
+	case MMIO_PROBE:
+		trace_seq_printf(s,
+			"MAP %u.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n",
+			secs, usec_rem, m->map_id,
+			(unsigned long long)m->phys, m->virt, m->len,
+			0UL, 0);
+		break;
+	case MMIO_UNPROBE:
+		trace_seq_printf(s,
+			"UNMAP %u.%06lu %d 0x%lx %d\n",
+			secs, usec_rem, m->map_id, 0UL, 0);
+		break;
+	default:
+		trace_seq_puts(s, "map what?\n");
+		break;
+	}
+
+	return trace_handle_return(s);
+}
+
+static enum print_line_t mmio_print_mark(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+	struct print_entry *print = (struct print_entry *)entry;
+	const char *msg		= print->buf;
+	struct trace_seq *s	= &iter->seq;
+	unsigned long long t	= ns2usecs(iter->ts);
+	unsigned long usec_rem	= do_div(t, USEC_PER_SEC);
+	unsigned secs		= (unsigned long)t;
+
+	/* The trailing newline must be in the message. */
+	trace_seq_printf(s, "MARK %u.%06lu %s", secs, usec_rem, msg);
+
+	return trace_handle_return(s);
+}
+
+static enum print_line_t mmio_print_line(struct trace_iterator *iter)
+{
+	switch (iter->ent->type) {
+	case TRACE_MMIO_RW:
+		return mmio_print_rw(iter);
+	case TRACE_MMIO_MAP:
+		return mmio_print_map(iter);
+	case TRACE_PRINT:
+		return mmio_print_mark(iter);
+	default:
+		return TRACE_TYPE_HANDLED; /* ignore unknown entries */
+	}
+}
+
+static struct tracer mmio_tracer __read_mostly =
+{
+	.name		= "mmiotrace",
+	.init		= mmio_trace_init,
+	.reset		= mmio_trace_reset,
+	.start		= mmio_trace_start,
+	.pipe_open	= mmio_pipe_open,
+	.close		= mmio_close,
+	.read		= mmio_read,
+	.print_line	= mmio_print_line,
+	.noboot		= true,
+};
+
+__init static int init_mmio_trace(void)
+{
+	return register_tracer(&mmio_tracer);
+}
+device_initcall(init_mmio_trace);
+
+static void __trace_mmiotrace_rw(struct trace_array *tr,
+				struct trace_array_cpu *data,
+				struct mmiotrace_rw *rw)
+{
+	struct trace_event_call *call = &event_mmiotrace_rw;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
+	struct ring_buffer_event *event;
+	struct trace_mmiotrace_rw *entry;
+	int pc = preempt_count();
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW,
+					  sizeof(*entry), 0, pc);
+	if (!event) {
+		atomic_inc(&dropped_count);
+		return;
+	}
+	entry	= ring_buffer_event_data(event);
+	entry->rw			= *rw;
+
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(tr, buffer, event, 0, pc);
+}
+
+void mmio_trace_rw(struct mmiotrace_rw *rw)
+{
+	struct trace_array *tr = mmio_trace_array;
+	struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id());
+	__trace_mmiotrace_rw(tr, data, rw);
+}
+
+static void __trace_mmiotrace_map(struct trace_array *tr,
+				struct trace_array_cpu *data,
+				struct mmiotrace_map *map)
+{
+	struct trace_event_call *call = &event_mmiotrace_map;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
+	struct ring_buffer_event *event;
+	struct trace_mmiotrace_map *entry;
+	int pc = preempt_count();
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP,
+					  sizeof(*entry), 0, pc);
+	if (!event) {
+		atomic_inc(&dropped_count);
+		return;
+	}
+	entry	= ring_buffer_event_data(event);
+	entry->map			= *map;
+
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(tr, buffer, event, 0, pc);
+}
+
+void mmio_trace_mapping(struct mmiotrace_map *map)
+{
+	struct trace_array *tr = mmio_trace_array;
+	struct trace_array_cpu *data;
+
+	preempt_disable();
+	data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id());
+	__trace_mmiotrace_map(tr, data, map);
+	preempt_enable();
+}
+
+int mmio_trace_printk(const char *fmt, va_list args)
+{
+	return trace_vprintk(0, fmt, args);
+}

kernel/trace/trace_mmstat.c

@@ -0,0 +1,501 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 MediaTek Inc.
+ * Author: Chinwen Chang <chinwen.chang@mediatek.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/debugfs.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/cred.h>
+#include <linux/mm.h>
+#include <linux/oom.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/vmstat.h>
+#include <linux/rcupdate.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/version.h>
+#include <linux/printk.h>
+#include <linux/init.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace_mmstat.h"
+
+#define P2K(x)	(((unsigned long)x) << (PAGE_SHIFT - 10))
+#define B2K(x)	(((unsigned long)x) >> (10))
+
+static struct delayed_work mmstat_work;
+static unsigned long timer_intval = HZ;
+
+const char * const meminfo_text[] = {
+	"memfr",	/* available memory */
+	"swpfr",
+	"cache",
+	"active",	/* (LRU) user pages */
+	"inactive",
+	"unevictable",
+	"shmem",	/* kernel memory */
+	"slab",
+	"kernel_stack",
+	"page_table",
+	"gpu",		/* HW memory */
+	"ion",
+	"zram",		/* misc */
+};
+
+const char * const vmstat_partial_text[] = {
+	"swpin",	/* vm events */
+	"swpout",
+	"majflt",
+	"refault",	/* vm stats */
+};
+
+const char * const proc_text[] = {
+	"pid",
+	"score_adj",
+	"rss",
+	"rswp",
+};
+
+#define NR_MEMINFO_ITEMS	ARRAY_SIZE(meminfo_text)
+#define NR_VMSTAT_PARTIAL_ITEMS	ARRAY_SIZE(vmstat_partial_text)
+#define NR_PROC_ITEMS		ARRAY_SIZE(proc_text)
+#define SWITCH_ON		UINT_MAX
+
+/* 4 switches */
+static unsigned int meminfo_switch = SWITCH_ON;
+static unsigned int vmstat_switch = SWITCH_ON;
+static unsigned int buddyinfo_switch = SWITCH_ON;
+static unsigned int proc_switch = SWITCH_ON;
+
+/* Sub controls for proc */
+static int min_adj = OOM_SCORE_ADJ_MIN;
+static int max_adj = OOM_SCORE_ADJ_MAX;
+static int limit_pid = -1;
+
+/* Refinement for analyses */
+#define TRACE_HUNGER_PERCENTAGE	(50)
+static unsigned long hungersize;
+
+const char *
+mmstat_trace_print_arrayset_seq(struct trace_seq *p,
+		const void *buf, int count, int sets)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	const char *prefix = "";
+	void *ptr = (void *)buf;
+	size_t buf_len = count * sizeof(unsigned long);
+	int entries = 0;
+
+	while (ptr < buf + buf_len) {
+		if (likely(*(long *)ptr >= 0))
+			trace_seq_printf(p, "%s%lu", prefix,
+					*(unsigned long *)ptr);
+		else
+			trace_seq_printf(p, "%s%ld", prefix,
+					*(long *)ptr);
+
+		prefix = ",";
+
+		if (++entries == count)
+			break;
+
+		if (entries % sets == 0)
+			prefix = "|";
+
+		ptr += sizeof(unsigned long);
+	}
+
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
+/* only consider the case of 1 node */
+static struct zone *mmstat_next_zone(struct zone *zone)
+{
+	pg_data_t *pgdat = zone->zone_pgdat;
+
+	if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
+		zone++;
+	else
+		zone = NULL;
+
+	return zone;
+}
+
+/*
+ * Record basic memory information
+ */
+static void mmstat_trace_meminfo(void)
+{
+	unsigned long meminfo[NR_MEMINFO_ITEMS] = {0};
+	size_t num_entries = 0;
+	unsigned int gpuuse = 0;
+	unsigned long ionuse = 0;
+
+	/* available memory */
+	meminfo[num_entries++] = P2K(global_zone_page_state(NR_FREE_PAGES));
+	meminfo[num_entries++] = P2K(atomic_long_read(&nr_swap_pages));
+	meminfo[num_entries++] = P2K(global_node_page_state(NR_FILE_PAGES));
+
+	/* user pages */
+	meminfo[num_entries++] = P2K(global_node_page_state(NR_ACTIVE_ANON) +
+			global_node_page_state(NR_ACTIVE_FILE));
+	meminfo[num_entries++] = P2K(global_node_page_state(NR_INACTIVE_ANON) +
+			global_node_page_state(NR_INACTIVE_FILE));
+	meminfo[num_entries++] = P2K(global_node_page_state(NR_UNEVICTABLE));
+
+	/* kernel memory usage */
+	meminfo[num_entries++] = P2K(global_node_page_state(NR_SHMEM));
+	meminfo[num_entries++] =
+		P2K(global_node_page_state(NR_SLAB_UNRECLAIMABLE) +
+				global_node_page_state(NR_SLAB_RECLAIMABLE));
+	meminfo[num_entries++] = global_zone_page_state(NR_KERNEL_STACK_KB);
+	meminfo[num_entries++] = P2K(global_zone_page_state(NR_PAGETABLE));
+
+#if IS_ENABLED(CONFIG_MTK_GPU_SUPPORT)
+	/* HW memory */
+	if (mtk_get_gpu_memory_usage(&gpuuse))
+		gpuuse = B2K(gpuuse);
+#endif
+	meminfo[num_entries++] = gpuuse;
+#if IS_ENABLED(CONFIG_MTK_ION)
+	ionuse = B2K((unsigned long)ion_mm_heap_total_memory());
+#endif
+	meminfo[num_entries++] = ionuse;
+
+	/* misc */
+#if IS_ENABLED(CONFIG_ZSMALLOC)
+	meminfo[num_entries++] = P2K(global_zone_page_state(NR_ZSPAGES));
+#else
+	meminfo[num_entries++] = 0;
+#endif
+
+	trace_mmstat_trace_meminfo((unsigned long *)meminfo, num_entries,
+			NR_MEMINFO_ITEMS);
+}
+
+/*
+ * Entry for recording vmstat - record partial VM status
+ */
+static void mmstat_trace_vmstat(void)
+{
+	int cpu;
+	unsigned long v[NR_VMSTAT_PARTIAL_ITEMS] = {0};
+	unsigned int nr_vm_events = NR_VMSTAT_PARTIAL_ITEMS - 1;
+	size_t num_entries = 0;
+
+	for_each_online_cpu(cpu) {
+		struct vm_event_state *this = &per_cpu(vm_event_states, cpu);
+
+		v[num_entries++ % nr_vm_events] +=
+			this->event[PSWPIN];
+		v[num_entries++ % nr_vm_events] +=
+			this->event[PSWPOUT];
+		v[num_entries++ % nr_vm_events] +=
+			this->event[PGMAJFAULT];
+	}
+
+	/* workingset_refsult */
+	v[NR_VMSTAT_PARTIAL_ITEMS - 1] =
+		global_node_page_state(WORKINGSET_REFAULT);
+
+	trace_mmstat_trace_vmstat((unsigned long *)v, NR_VMSTAT_PARTIAL_ITEMS,
+			NR_VMSTAT_PARTIAL_ITEMS);
+}
+
+/*
+ * Record buddy information
+ */
+static void mmstat_trace_buddyinfo(void)
+{
+	struct zone *zone;
+
+	/* imitate for_each_populated_zone */
+	for (zone = (NODE_DATA(0))->node_zones;
+	     zone; zone = mmstat_next_zone(zone)) {
+		if (populated_zone(zone)) {
+			unsigned long flags;
+			unsigned int order;
+			unsigned long buddyinfo[MAX_ORDER + 1] = {0};
+
+			buddyinfo[0] = zone_idx(zone);
+			spin_lock_irqsave(&zone->lock, flags);
+			for (order = 0; order < MAX_ORDER; ++order)
+				buddyinfo[order + 1] =
+					zone->free_area[order].nr_free;
+			spin_unlock_irqrestore(&zone->lock, flags);
+
+			trace_mmstat_trace_buddyinfo((unsigned long *)buddyinfo,
+					MAX_ORDER + 1, MAX_ORDER + 1);
+		}
+	}
+}
+
+static bool filter_out_process(struct task_struct *p, pid_t pid,
+		short oom_score_adj, unsigned long sz)
+{
+	/* if the size is too large, just show it */
+	if (sz >= hungersize)
+		return false;
+
+	/* by oom_score_adj */
+	if (oom_score_adj > max_adj || oom_score_adj < min_adj)
+		return true;
+
+	/* by pid */
+	if (limit_pid != -1 && pid != limit_pid)
+		return true;
+
+	/* by ppid, bypass process whose parent is init */
+	if (pid_alive(p)) {
+		if (task_pid_nr(rcu_dereference(p->real_parent)) == 1)
+			return true;
+	} else {
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Record process information
+ */
+static void mmstat_trace_procinfo(void)
+{
+#define PROC_SET_SIZE	NR_PROC_ITEMS
+#define PROC_ARRAY_SIZE	(PROC_SET_SIZE * 4)
+
+	struct task_struct *p;
+	long proc_array[PROC_ARRAY_SIZE] = {0};
+	size_t num_entries = 0;
+
+	rcu_read_lock();
+	for_each_process(p) {
+		pid_t pid;
+		short oom_score_adj;
+		unsigned long rss;
+		unsigned long rswap;
+
+		if (p->flags & PF_KTHREAD)
+			continue;
+
+		task_lock(p);
+		if (!p->mm || !p->signal) {
+			task_unlock(p);
+			continue;
+		}
+
+		pid = p->pid;
+		oom_score_adj = p->signal->oom_score_adj;
+		rss = get_mm_rss(p->mm);
+		rswap = get_mm_counter(p->mm, MM_SWAPENTS);
+		if (filter_out_process(p, pid, oom_score_adj, rss + rswap)) {
+			task_unlock(p);
+			continue;
+		}
+		task_unlock(p);
+
+		proc_array[num_entries++] = pid;
+		proc_array[num_entries++] = oom_score_adj;
+		proc_array[num_entries++] = P2K(rss);
+		proc_array[num_entries++] = P2K(rswap);
+
+		if (num_entries == PROC_ARRAY_SIZE) {
+			trace_mmstat_trace_proc((unsigned long *)proc_array,
+					num_entries, PROC_SET_SIZE);
+			num_entries = 0;
+		}
+	}
+	rcu_read_unlock();
+
+	/* remaining entries */
+	if (num_entries)
+		trace_mmstat_trace_proc((unsigned long *)proc_array,
+				num_entries, PROC_SET_SIZE);
+
+#undef PROC_ARRAY_SIZE
+#undef PROC_SET_SIZE
+}
+
+/*
+ * Main entry of recording information
+ */
+static void trace_mmstat_entry(void)
+{
+	/* basic memory information */
+	if (meminfo_switch)
+		mmstat_trace_meminfo();
+
+	/* vm status */
+	if (vmstat_switch)
+		mmstat_trace_vmstat();
+
+	/* buddy information */
+	if (buddyinfo_switch)
+		mmstat_trace_buddyinfo();
+
+	/* process information */
+	if (proc_switch)
+		mmstat_trace_procinfo();
+}
+
+module_param(min_adj, int, 0644);
+module_param(max_adj, int, 0644);
+module_param(limit_pid, int, 0644);
+
+static int do_switch_handler(const char *val, const struct kernel_param *kp)
+{
+	const int ret = param_set_uint(val, kp);
+
+	return ret;
+}
+
+static const struct kernel_param_ops param_ops_change_switch = {
+	.set = &do_switch_handler,
+	.get = &param_get_uint,
+	.free = NULL,
+};
+
+static int do_time_intval_handler(const char *val,
+		const struct kernel_param *kp)
+{
+	int ret;
+
+	ret = param_set_ulong(val, kp);
+	if (ret < 0)
+		return ret;
+
+	queue_delayed_work(system_unbound_wq, &mmstat_work, 0);
+
+	return 0;
+}
+
+static const struct kernel_param_ops param_ops_change_time_intval = {
+	.set = &do_time_intval_handler,
+	.get = &param_get_ulong,
+	.free = NULL,
+};
+
+module_param_cb(meminfo_switch, &param_ops_change_switch,
+		&meminfo_switch, 0644);
+module_param_cb(vmstat_switch, &param_ops_change_switch,
+		&vmstat_switch, 0644);
+module_param_cb(buddyinfo_switch, &param_ops_change_switch,
+		&buddyinfo_switch, 0644);
+module_param_cb(proc_switch, &param_ops_change_switch,
+		&proc_switch, 0644);
+
+param_check_ulong(timer_intval, &timer_intval);
+module_param_cb(timer_intval, &param_ops_change_time_intval,
+		&timer_intval, 0644);
+__MODULE_PARM_TYPE(timer_intval, "ulong");
+
+static void mmstat_work_handler(struct work_struct *work)
+{
+	trace_mmstat_entry();
+	queue_delayed_work(system_unbound_wq, &mmstat_work, timer_intval);
+}
+
+int mmstat_print_fmt(struct seq_file *m)
+{
+	int i;
+
+	/* basic memory information */
+	if (meminfo_switch) {
+		seq_puts(m, "mmstat_trace_meminfo: ");
+		seq_printf(m, "%s", meminfo_text[0]);
+		for (i = 1; i < NR_MEMINFO_ITEMS; i++)
+			seq_printf(m, ",%s", meminfo_text[i]);
+		seq_putc(m, '\n');
+	}
+
+	/* vm status */
+	if (vmstat_switch) {
+		seq_puts(m, "mmstat_trace_vmstat: ");
+		seq_printf(m, "%s", vmstat_partial_text[0]);
+		for (i = 1; i < NR_VMSTAT_PARTIAL_ITEMS; i++)
+			seq_printf(m, ",%s", vmstat_partial_text[i]);
+		seq_putc(m, '\n');
+	}
+
+	/* buddy information */
+	if (buddyinfo_switch) {
+		struct zone *zone;
+		int order;
+
+		/* imitate for_each_populated_zone */
+		for (zone = (NODE_DATA(0))->node_zones;
+		     zone; zone = mmstat_next_zone(zone)) {
+			if (populated_zone(zone)) {
+				seq_puts(m, "mmstat_trace_buddyinfo: ");
+				seq_printf(m, "%s", zone->name);
+				for (order = 0; order < MAX_ORDER; ++order)
+					seq_printf(m, ",%d", order);
+				seq_putc(m, '\n');
+			}
+		}
+	}
+
+	/* process information */
+	if (proc_switch) {
+		seq_puts(m, "mmstat_trace_proc: ");
+		seq_printf(m, "%s", proc_text[0]);
+		for (i = 1; i < NR_PROC_ITEMS; i++)
+			seq_printf(m, ",%s", proc_text[i]);
+		seq_putc(m, '\n');
+	}
+
+	return 0;
+}
+
+static int mmstat_fmt_proc_show(struct seq_file *m, void *v)
+{
+	return mmstat_print_fmt(m);
+}
+
+static int mmstat_fmt_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mmstat_fmt_proc_show, NULL);
+}
+
+static const struct file_operations mmstat_fmt_proc_fops = {
+	.open = mmstat_fmt_proc_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init trace_mmstat_init(void)
+{
+	hungersize = totalram_pages * TRACE_HUNGER_PERCENTAGE / 100;
+
+	debugfs_create_file("mmstat_fmt", 0444, NULL, NULL,
+			&mmstat_fmt_proc_fops);
+
+	INIT_DELAYED_WORK(&mmstat_work, mmstat_work_handler);
+	queue_delayed_work(system_unbound_wq, &mmstat_work, timer_intval);
+
+	return 0;
+}
+
+static void __exit trace_mmstat_exit(void)
+{
+	cancel_delayed_work_sync(&mmstat_work);
+}
+
+module_init(trace_mmstat_init);
+module_exit(trace_mmstat_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MediaTek mmstat tracer");
+MODULE_AUTHOR("MediaTek Inc.");

kernel/trace/trace_mmstat.h

@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 MediaTek Inc.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mmstat
+
+#if IS_ENABLED(CONFIG_MTK_GPU_SUPPORT)
+extern bool mtk_get_gpu_memory_usage(unsigned int *pMemUsage);
+#endif
+
+#if IS_ENABLED(CONFIG_MTK_ION)
+extern size_t ion_mm_heap_total_memory(void);
+#endif
+
+#if !defined(__TRACE_MMSTAT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __TRACE_MMSTAT_H
+
+#include <linux/tracepoint.h>
+#include <linux/trace_seq.h>
+
+const char *mmstat_trace_print_arrayset_seq(struct trace_seq*,
+		const void*, int, int);
+#define __print_mmstat_array(array, len, sets)				\
+	({								\
+		mmstat_trace_print_arrayset_seq(p, array, len, sets);	\
+	})
+
+/* num_entries should be a multiplie of set_size */
+DECLARE_EVENT_CLASS(mmstat_trace_arrayset,
+
+	TP_PROTO(unsigned long *arrayset, size_t num_entries, size_t set_size),
+
+	TP_ARGS(arrayset, num_entries, set_size),
+
+	TP_STRUCT__entry(
+		__dynamic_array(unsigned long, arrayset, num_entries)
+		__field(size_t, num_entries)
+		__field(size_t, set_size)
+	),
+
+	TP_fast_assign(
+		memcpy(__get_dynamic_array(arrayset), arrayset,
+			num_entries * sizeof(unsigned long));
+		__entry->num_entries = num_entries;
+		__entry->set_size = set_size;
+	),
+
+	TP_printk("%s", __print_mmstat_array(__get_dynamic_array(arrayset),
+			__entry->num_entries, __entry->set_size))
+);
+
+DEFINE_EVENT(mmstat_trace_arrayset, mmstat_trace_meminfo,
+
+	TP_PROTO(unsigned long *meminfo, size_t num_entries, size_t set_size),
+
+	TP_ARGS(meminfo, num_entries, set_size)
+);
+
+DEFINE_EVENT(mmstat_trace_arrayset, mmstat_trace_vmstat,
+
+	TP_PROTO(unsigned long *vmstat, size_t num_entries, size_t set_size),
+
+	TP_ARGS(vmstat, num_entries, set_size)
+);
+
+DEFINE_EVENT(mmstat_trace_arrayset, mmstat_trace_buddyinfo,
+
+	TP_PROTO(unsigned long *buddyinfo, size_t num_entries, size_t set_size),
+
+	TP_ARGS(buddyinfo, num_entries, set_size)
+);
+
+DEFINE_EVENT(mmstat_trace_arrayset, mmstat_trace_proc,
+
+	TP_PROTO(unsigned long *proc_array, size_t num_entries,
+		size_t set_size),
+
+	TP_ARGS(proc_array, num_entries, set_size)
+);
+#endif /* __TRACE_MMSTAT_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace_mmstat
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

kernel/trace/trace_nop.c

@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * nop tracer
+ *
+ * Copyright (C) 2008 Steven Noonan <steven@uplinklabs.net>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/ftrace.h>
+
+#include "trace.h"
+
+/* Our two options */
+enum {
+	TRACE_NOP_OPT_ACCEPT = 0x1,
+	TRACE_NOP_OPT_REFUSE = 0x2
+};
+
+/* Options for the tracer (see trace_options file) */
+static struct tracer_opt nop_opts[] = {
+	/* Option that will be accepted by set_flag callback */
+	{ TRACER_OPT(test_nop_accept, TRACE_NOP_OPT_ACCEPT) },
+	/* Option that will be refused by set_flag callback */
+	{ TRACER_OPT(test_nop_refuse, TRACE_NOP_OPT_REFUSE) },
+	{ } /* Always set a last empty entry */
+};
+
+static struct tracer_flags nop_flags = {
+	/* You can check your flags value here when you want. */
+	.val = 0, /* By default: all flags disabled */
+	.opts = nop_opts
+};
+
+static struct trace_array	*ctx_trace;
+
+static void start_nop_trace(struct trace_array *tr)
+{
+	/* Nothing to do! */
+}
+
+static void stop_nop_trace(struct trace_array *tr)
+{
+	/* Nothing to do! */
+}
+
+static int nop_trace_init(struct trace_array *tr)
+{
+	ctx_trace = tr;
+	start_nop_trace(tr);
+	return 0;
+}
+
+static void nop_trace_reset(struct trace_array *tr)
+{
+	stop_nop_trace(tr);
+}
+
+/* It only serves as a signal handler and a callback to
+ * accept or refuse the setting of a flag.
+ * If you don't implement it, then the flag setting will be
+ * automatically accepted.
+ */
+static int nop_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
+{
+	/*
+	 * Note that you don't need to update nop_flags.val yourself.
+	 * The tracing Api will do it automatically if you return 0
+	 */
+	if (bit == TRACE_NOP_OPT_ACCEPT) {
+		printk(KERN_DEBUG "nop_test_accept flag set to %d: we accept."
+			" Now cat trace_options to see the result\n",
+			set);
+		return 0;
+	}
+
+	if (bit == TRACE_NOP_OPT_REFUSE) {
+		printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse."
+			" Now cat trace_options to see the result\n",
+			set);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+
+struct tracer nop_trace __read_mostly =
+{
+	.name		= "nop",
+	.init		= nop_trace_init,
+	.reset		= nop_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest	= trace_selftest_startup_nop,
+#endif
+	.flags		= &nop_flags,
+	.set_flag	= nop_set_flag,
+	.allow_instances = true,
+};
+

kernel/trace/trace_output.h

@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __TRACE_EVENTS_H
+#define __TRACE_EVENTS_H
+
+#include <linux/trace_seq.h>
+#include "trace.h"
+
+extern enum print_line_t
+trace_print_bputs_msg_only(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_bprintk_msg_only(struct trace_iterator *iter);
+extern enum print_line_t
+trace_print_printk_msg_only(struct trace_iterator *iter);
+
+extern int
+seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
+		unsigned long sym_flags);
+
+extern int trace_print_context(struct trace_iterator *iter);
+extern int trace_print_lat_context(struct trace_iterator *iter);
+
+extern void trace_event_read_lock(void);
+extern void trace_event_read_unlock(void);
+extern struct trace_event *ftrace_find_event(int type);
+
+extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
+					 int flags, struct trace_event *event);
+extern int
+trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
+
+/* used by module unregistering */
+extern int __unregister_trace_event(struct trace_event *event);
+extern struct rw_semaphore trace_event_sem;
+
+#define SEQ_PUT_FIELD(s, x)				\
+	trace_seq_putmem(s, &(x), sizeof(x))
+
+#define SEQ_PUT_HEX_FIELD(s, x)				\
+	trace_seq_putmem_hex(s, &(x), sizeof(x))
+
+#endif
+

kernel/trace/trace_preemptirq.c

@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * preemptoff and irqoff tracepoints
+ *
+ * Copyright (C) Joel Fernandes (Google) <joel@joelfernandes.org>
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <mt-plat/mtk_sched_mon.h>
+#include "trace.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/preemptirq.h>
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+/* Per-cpu variable to prevent redundant calls when IRQs already off */
+static DEFINE_PER_CPU(int, tracing_irq_cpu);
+
+void trace_hardirqs_on(void)
+{
+	if (this_cpu_read(tracing_irq_cpu)) {
+		if (!in_nmi())
+			trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
+		trace_hardirqs_on_time();
+		this_cpu_write(tracing_irq_cpu, 0);
+	}
+
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+EXPORT_SYMBOL(trace_hardirqs_on);
+
+void trace_hardirqs_off(void)
+{
+#ifdef CONFIG_MTK_IRQ_OFF_TRACER
+	int trace_time = 0;
+#endif
+	if (!this_cpu_read(tracing_irq_cpu)) {
+		this_cpu_write(tracing_irq_cpu, 1);
+#ifdef CONFIG_MTK_IRQ_OFF_TRACER
+		trace_time = 1;
+#endif
+		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
+		if (!in_nmi())
+			trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+	}
+
+	lockdep_hardirqs_off(CALLER_ADDR0);
+#ifdef CONFIG_MTK_IRQ_OFF_TRACER
+	if (trace_time)
+		trace_hardirqs_off_time();
+#endif
+}
+EXPORT_SYMBOL(trace_hardirqs_off);
+
+__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
+{
+	if (this_cpu_read(tracing_irq_cpu)) {
+		if (!in_nmi())
+			trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr);
+		tracer_hardirqs_on(CALLER_ADDR0, caller_addr);
+		this_cpu_write(tracing_irq_cpu, 0);
+	}
+
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+EXPORT_SYMBOL(trace_hardirqs_on_caller);
+
+__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
+{
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	if (!this_cpu_read(tracing_irq_cpu)) {
+		this_cpu_write(tracing_irq_cpu, 1);
+		tracer_hardirqs_off(CALLER_ADDR0, caller_addr);
+		if (!in_nmi())
+			trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
+	}
+}
+EXPORT_SYMBOL(trace_hardirqs_off_caller);
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
+#ifdef CONFIG_TRACE_PREEMPT_TOGGLE
+
+void trace_preempt_on(unsigned long a0, unsigned long a1)
+{
+	if (!in_nmi())
+		trace_preempt_enable_rcuidle(a0, a1);
+	tracer_preempt_on(a0, a1);
+	trace_preempt_on_time();
+}
+
+void trace_preempt_off(unsigned long a0, unsigned long a1)
+{
+	trace_preempt_off_time();
+	if (!in_nmi())
+		trace_preempt_disable_rcuidle(a0, a1);
+	tracer_preempt_off(a0, a1);
+}
+#endif

kernel/trace/trace_printk.c

@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace binary printk
+ *
+ * Copyright (C) 2008 Lai Jiangshan <laijs@cn.fujitsu.com>
+ *
+ */
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+#include "trace.h"
+
+#ifdef CONFIG_MODULES
+
+/*
+ * modules trace_printk()'s formats are autosaved in struct trace_bprintk_fmt
+ * which are queued on trace_bprintk_fmt_list.
+ */
+static LIST_HEAD(trace_bprintk_fmt_list);
+
+/* serialize accesses to trace_bprintk_fmt_list */
+static DEFINE_MUTEX(btrace_mutex);
+
+struct trace_bprintk_fmt {
+	struct list_head list;
+	const char *fmt;
+};
+
+static inline struct trace_bprintk_fmt *lookup_format(const char *fmt)
+{
+	struct trace_bprintk_fmt *pos;
+
+	if (!fmt)
+		return ERR_PTR(-EINVAL);
+
+	list_for_each_entry(pos, &trace_bprintk_fmt_list, list) {
+		if (!strcmp(pos->fmt, fmt))
+			return pos;
+	}
+	return NULL;
+}
+
+static
+void hold_module_trace_bprintk_format(const char **start, const char **end)
+{
+	const char **iter;
+	char *fmt;
+
+	/* allocate the trace_printk per cpu buffers */
+	if (start != end)
+		trace_printk_init_buffers();
+
+	mutex_lock(&btrace_mutex);
+	for (iter = start; iter < end; iter++) {
+		struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);
+		if (tb_fmt) {
+			if (!IS_ERR(tb_fmt))
+				*iter = tb_fmt->fmt;
+			continue;
+		}
+
+		fmt = NULL;
+		tb_fmt = kmalloc(sizeof(*tb_fmt), GFP_KERNEL);
+		if (tb_fmt) {
+			fmt = kmalloc(strlen(*iter) + 1, GFP_KERNEL);
+			if (fmt) {
+				list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list);
+				strcpy(fmt, *iter);
+				tb_fmt->fmt = fmt;
+			} else
+				kfree(tb_fmt);
+		}
+		*iter = fmt;
+
+	}
+	mutex_unlock(&btrace_mutex);
+}
+
+static int module_trace_bprintk_format_notify(struct notifier_block *self,
+		unsigned long val, void *data)
+{
+	struct module *mod = data;
+	if (mod->num_trace_bprintk_fmt) {
+		const char **start = mod->trace_bprintk_fmt_start;
+		const char **end = start + mod->num_trace_bprintk_fmt;
+
+		if (val == MODULE_STATE_COMING)
+			hold_module_trace_bprintk_format(start, end);
+	}
+	return 0;
+}
+
+/*
+ * The debugfs/tracing/printk_formats file maps the addresses with
+ * the ASCII formats that are used in the bprintk events in the
+ * buffer. For userspace tools to be able to decode the events from
+ * the buffer, they need to be able to map the address with the format.
+ *
+ * The addresses of the bprintk formats are in their own section
+ * __trace_printk_fmt. But for modules we copy them into a link list.
+ * The code to print the formats and their addresses passes around the
+ * address of the fmt string. If the fmt address passed into the seq
+ * functions is within the kernel core __trace_printk_fmt section, then
+ * it simply uses the next pointer in the list.
+ *
+ * When the fmt pointer is outside the kernel core __trace_printk_fmt
+ * section, then we need to read the link list pointers. The trick is
+ * we pass the address of the string to the seq function just like
+ * we do for the kernel core formats. To get back the structure that
+ * holds the format, we simply use containerof() and then go to the
+ * next format in the list.
+ */
+static const char **
+find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos)
+{
+	struct trace_bprintk_fmt *mod_fmt;
+
+	if (list_empty(&trace_bprintk_fmt_list))
+		return NULL;
+
+	/*
+	 * v will point to the address of the fmt record from t_next
+	 * v will be NULL from t_start.
+	 * If this is the first pointer or called from start
+	 * then we need to walk the list.
+	 */
+	if (!v || start_index == *pos) {
+		struct trace_bprintk_fmt *p;
+
+		/* search the module list */
+		list_for_each_entry(p, &trace_bprintk_fmt_list, list) {
+			if (start_index == *pos)
+				return &p->fmt;
+			start_index++;
+		}
+		/* pos > index */
+		return NULL;
+	}
+
+	/*
+	 * v points to the address of the fmt field in the mod list
+	 * structure that holds the module print format.
+	 */
+	mod_fmt = container_of(v, typeof(*mod_fmt), fmt);
+	if (mod_fmt->list.next == &trace_bprintk_fmt_list)
+		return NULL;
+
+	mod_fmt = container_of(mod_fmt->list.next, typeof(*mod_fmt), list);
+
+	return &mod_fmt->fmt;
+}
+
+static void format_mod_start(void)
+{
+	mutex_lock(&btrace_mutex);
+}
+
+static void format_mod_stop(void)
+{
+	mutex_unlock(&btrace_mutex);
+}
+
+#else /* !CONFIG_MODULES */
+__init static int
+module_trace_bprintk_format_notify(struct notifier_block *self,
+		unsigned long val, void *data)
+{
+	return 0;
+}
+static inline const char **
+find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos)
+{
+	return NULL;
+}
+static inline void format_mod_start(void) { }
+static inline void format_mod_stop(void) { }
+#endif /* CONFIG_MODULES */
+
+static bool __read_mostly trace_printk_enabled = true;
+
+void trace_printk_control(bool enabled)
+{
+	trace_printk_enabled = enabled;
+}
+
+__initdata_or_module static
+struct notifier_block module_trace_bprintk_format_nb = {
+	.notifier_call = module_trace_bprintk_format_notify,
+};
+
+int __trace_bprintk(unsigned long ip, const char *fmt, ...)
+{
+	int ret;
+	va_list ap;
+
+	if (unlikely(!fmt))
+		return 0;
+
+	if (!trace_printk_enabled)
+		return 0;
+
+	va_start(ap, fmt);
+	ret = trace_vbprintk(ip, fmt, ap);
+	va_end(ap);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__trace_bprintk);
+
+int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap)
+{
+	if (unlikely(!fmt))
+		return 0;
+
+	if (!trace_printk_enabled)
+		return 0;
+
+	return trace_vbprintk(ip, fmt, ap);
+}
+EXPORT_SYMBOL_GPL(__ftrace_vbprintk);
+
+int __trace_printk(unsigned long ip, const char *fmt, ...)
+{
+	int ret;
+	va_list ap;
+
+	if (!trace_printk_enabled)
+		return 0;
+
+	va_start(ap, fmt);
+	ret = trace_vprintk(ip, fmt, ap);
+	va_end(ap);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__trace_printk);
+
+int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
+{
+	if (!trace_printk_enabled)
+		return 0;
+
+	return trace_vprintk(ip, fmt, ap);
+}
+EXPORT_SYMBOL_GPL(__ftrace_vprintk);
+
+static const char **find_next(void *v, loff_t *pos)
+{
+	const char **fmt = v;
+	int start_index;
+	int last_index;
+
+	start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt;
+
+	if (*pos < start_index)
+		return __start___trace_bprintk_fmt + *pos;
+
+	/*
+	 * The __tracepoint_str section is treated the same as the
+	 * __trace_printk_fmt section. The difference is that the
+	 * __trace_printk_fmt section should only be used by trace_printk()
+	 * in a debugging environment, as if anything exists in that section
+	 * the trace_prink() helper buffers are allocated, which would just
+	 * waste space in a production environment.
+	 *
+	 * The __tracepoint_str sections on the other hand are used by
+	 * tracepoints which need to map pointers to their strings to
+	 * the ASCII text for userspace.
+	 */
+	last_index = start_index;
+	start_index = __stop___tracepoint_str - __start___tracepoint_str;
+
+	if (*pos < last_index + start_index)
+		return __start___tracepoint_str + (*pos - last_index);
+
+	start_index += last_index;
+	return find_next_mod_format(start_index, v, fmt, pos);
+}
+
+static void *
+t_start(struct seq_file *m, loff_t *pos)
+{
+	format_mod_start();
+	return find_next(NULL, pos);
+}
+
+static void *t_next(struct seq_file *m, void * v, loff_t *pos)
+{
+	(*pos)++;
+	return find_next(v, pos);
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+	const char **fmt = v;
+	const char *str = *fmt;
+	int i;
+
+	if (!*fmt)
+		return 0;
+
+	seq_printf(m, "0x%pK : \"", *(void **)fmt);
+
+	/*
+	 * Tabs and new lines need to be converted.
+	 */
+	for (i = 0; str[i]; i++) {
+		switch (str[i]) {
+		case '\n':
+			seq_puts(m, "\\n");
+			break;
+		case '\t':
+			seq_puts(m, "\\t");
+			break;
+		case '\\':
+			seq_putc(m, '\\');
+			break;
+		case '"':
+			seq_puts(m, "\\\"");
+			break;
+		default:
+			seq_putc(m, str[i]);
+		}
+	}
+	seq_puts(m, "\"\n");
+
+	return 0;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+	format_mod_stop();
+}
+
+static const struct seq_operations show_format_seq_ops = {
+	.start = t_start,
+	.next = t_next,
+	.show = t_show,
+	.stop = t_stop,
+};
+
+static int
+ftrace_formats_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &show_format_seq_ops);
+}
+
+static const struct file_operations ftrace_formats_fops = {
+	.open = ftrace_formats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
+};
+
+static __init int init_trace_printk_function_export(void)
+{
+	struct dentry *d_tracer;
+
+	d_tracer = tracing_init_dentry();
+	if (IS_ERR(d_tracer))
+		return 0;
+
+	trace_create_file("printk_formats", 0444, d_tracer,
+				    NULL, &ftrace_formats_fops);
+
+	return 0;
+}
+
+fs_initcall(init_trace_printk_function_export);
+
+static __init int init_trace_printk(void)
+{
+	return register_module_notifier(&module_trace_bprintk_format_nb);
+}
+
+early_initcall(init_trace_printk);

kernel/trace/trace_probe.c

@@ -0,0 +1,672 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common code for probe-based Dynamic events.
+ *
+ * This code was copied from kernel/trace/trace_kprobe.c written by
+ * Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+ *
+ * Updates to make this generic:
+ * Copyright (C) IBM Corporation, 2010-2011
+ * Author:     Srikar Dronamraju
+ */
+#define pr_fmt(fmt)	"trace_probe: " fmt
+
+#include "trace_probe.h"
+
+const char *reserved_field_names[] = {
+	"common_type",
+	"common_flags",
+	"common_preempt_count",
+	"common_pid",
+	"common_tgid",
+	FIELD_STRING_IP,
+	FIELD_STRING_RETIP,
+	FIELD_STRING_FUNC,
+};
+
+/* Printing  in basic type function template */
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(tname, type, fmt)			\
+int PRINT_TYPE_FUNC_NAME(tname)(struct trace_seq *s, const char *name,	\
+				void *data, void *ent)			\
+{									\
+	trace_seq_printf(s, " %s=" fmt, name, *(type *)data);		\
+	return !trace_seq_has_overflowed(s);				\
+}									\
+const char PRINT_TYPE_FMT_NAME(tname)[] = fmt;				\
+NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(tname));
+
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8,  u8,  "%u")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, u16, "%u")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, u32, "%u")
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, u64, "%Lu")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8,  s8,  "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, s16, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, s32, "%d")
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, s64, "%Ld")
+DEFINE_BASIC_PRINT_TYPE_FUNC(x8,  u8,  "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(x16, u16, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(x32, u32, "0x%x")
+DEFINE_BASIC_PRINT_TYPE_FUNC(x64, u64, "0x%Lx")
+
+/* Print type function for string type */
+int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, const char *name,
+				 void *data, void *ent)
+{
+	int len = *(u32 *)data >> 16;
+
+	if (!len)
+		trace_seq_printf(s, " %s=(fault)", name);
+	else
+		trace_seq_printf(s, " %s=\"%s\"", name,
+				 (const char *)get_loc_data(data, ent));
+	return !trace_seq_has_overflowed(s);
+}
+NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(string));
+
+const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
+
+#define CHECK_FETCH_FUNCS(method, fn)			\
+	(((FETCH_FUNC_NAME(method, u8) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, u16) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, u32) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, u64) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, string) == fn) ||	\
+	  (FETCH_FUNC_NAME(method, string_size) == fn)) \
+	 && (fn != NULL))
+
+/* Data fetch function templates */
+#define DEFINE_FETCH_reg(type)						\
+void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, void *offset, void *dest)	\
+{									\
+	*(type *)dest = (type)regs_get_register(regs,			\
+				(unsigned int)((unsigned long)offset));	\
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(reg, type));
+DEFINE_BASIC_FETCH_FUNCS(reg)
+/* No string on the register */
+#define fetch_reg_string	NULL
+#define fetch_reg_string_size	NULL
+
+#define DEFINE_FETCH_retval(type)					\
+void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,		\
+				   void *dummy, void *dest)		\
+{									\
+	*(type *)dest = (type)regs_return_value(regs);			\
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(retval, type));
+DEFINE_BASIC_FETCH_FUNCS(retval)
+/* No string on the retval */
+#define fetch_retval_string		NULL
+#define fetch_retval_string_size	NULL
+
+/* Dereference memory access function */
+struct deref_fetch_param {
+	struct fetch_param	orig;
+	long			offset;
+	fetch_func_t		fetch;
+	fetch_func_t		fetch_size;
+};
+
+#define DEFINE_FETCH_deref(type)					\
+void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,			\
+				  void *data, void *dest)		\
+{									\
+	struct deref_fetch_param *dprm = data;				\
+	unsigned long addr;						\
+	call_fetch(&dprm->orig, regs, &addr);				\
+	if (addr) {							\
+		addr += dprm->offset;					\
+		dprm->fetch(regs, (void *)addr, dest);			\
+	} else								\
+		*(type *)dest = 0;					\
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, type));
+DEFINE_BASIC_FETCH_FUNCS(deref)
+DEFINE_FETCH_deref(string)
+
+void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs,
+					 void *data, void *dest)
+{
+	struct deref_fetch_param *dprm = data;
+	unsigned long addr;
+
+	call_fetch(&dprm->orig, regs, &addr);
+	if (addr && dprm->fetch_size) {
+		addr += dprm->offset;
+		dprm->fetch_size(regs, (void *)addr, dest);
+	} else
+		*(string_size *)dest = 0;
+}
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, string_size));
+
+static void update_deref_fetch_param(struct deref_fetch_param *data)
+{
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		update_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		update_symbol_cache(data->orig.data);
+}
+NOKPROBE_SYMBOL(update_deref_fetch_param);
+
+static void free_deref_fetch_param(struct deref_fetch_param *data)
+{
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		free_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		free_symbol_cache(data->orig.data);
+	kfree(data);
+}
+NOKPROBE_SYMBOL(free_deref_fetch_param);
+
+/* Bitfield fetch function */
+struct bitfield_fetch_param {
+	struct fetch_param	orig;
+	unsigned char		hi_shift;
+	unsigned char		low_shift;
+};
+
+#define DEFINE_FETCH_bitfield(type)					\
+void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,		\
+				     void *data, void *dest)		\
+{									\
+	struct bitfield_fetch_param *bprm = data;			\
+	type buf = 0;							\
+	call_fetch(&bprm->orig, regs, &buf);				\
+	if (buf) {							\
+		buf <<= bprm->hi_shift;					\
+		buf >>= bprm->low_shift;				\
+	}								\
+	*(type *)dest = buf;						\
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(bitfield, type));
+DEFINE_BASIC_FETCH_FUNCS(bitfield)
+#define fetch_bitfield_string		NULL
+#define fetch_bitfield_string_size	NULL
+
+static void
+update_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+	/*
+	 * Don't check the bitfield itself, because this must be the
+	 * last fetch function.
+	 */
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		update_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		update_symbol_cache(data->orig.data);
+}
+
+static void
+free_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+	/*
+	 * Don't check the bitfield itself, because this must be the
+	 * last fetch function.
+	 */
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		free_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		free_symbol_cache(data->orig.data);
+
+	kfree(data);
+}
+
+void FETCH_FUNC_NAME(comm, string)(struct pt_regs *regs,
+					  void *data, void *dest)
+{
+	int maxlen = get_rloc_len(*(u32 *)dest);
+	u8 *dst = get_rloc_data(dest);
+	long ret;
+
+	if (!maxlen)
+		return;
+
+	ret = strlcpy(dst, current->comm, maxlen);
+	*(u32 *)dest = make_data_rloc(ret, get_rloc_offs(*(u32 *)dest));
+}
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string));
+
+void FETCH_FUNC_NAME(comm, string_size)(struct pt_regs *regs,
+					       void *data, void *dest)
+{
+	*(u32 *)dest = strlen(current->comm) + 1;
+}
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(comm, string_size));
+
+static const struct fetch_type *find_fetch_type(const char *type,
+						const struct fetch_type *ftbl)
+{
+	int i;
+
+	if (!type)
+		type = DEFAULT_FETCH_TYPE_STR;
+
+	/* Special case: bitfield */
+	if (*type == 'b') {
+		unsigned long bs;
+
+		type = strchr(type, '/');
+		if (!type)
+			goto fail;
+
+		type++;
+		if (kstrtoul(type, 0, &bs))
+			goto fail;
+
+		switch (bs) {
+		case 8:
+			return find_fetch_type("u8", ftbl);
+		case 16:
+			return find_fetch_type("u16", ftbl);
+		case 32:
+			return find_fetch_type("u32", ftbl);
+		case 64:
+			return find_fetch_type("u64", ftbl);
+		default:
+			goto fail;
+		}
+	}
+
+	for (i = 0; ftbl[i].name; i++) {
+		if (strcmp(type, ftbl[i].name) == 0)
+			return &ftbl[i];
+	}
+
+fail:
+	return NULL;
+}
+
+/* Special function : only accept unsigned long */
+static void fetch_kernel_stack_address(struct pt_regs *regs, void *dummy, void *dest)
+{
+	*(unsigned long *)dest = kernel_stack_pointer(regs);
+}
+NOKPROBE_SYMBOL(fetch_kernel_stack_address);
+
+static void fetch_user_stack_address(struct pt_regs *regs, void *dummy, void *dest)
+{
+	*(unsigned long *)dest = user_stack_pointer(regs);
+}
+NOKPROBE_SYMBOL(fetch_user_stack_address);
+
+static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
+					    fetch_func_t orig_fn,
+					    const struct fetch_type *ftbl)
+{
+	int i;
+
+	if (type != &ftbl[FETCH_TYPE_STRING])
+		return NULL;	/* Only string type needs size function */
+
+	for (i = 0; i < FETCH_MTD_END; i++)
+		if (type->fetch[i] == orig_fn)
+			return ftbl[FETCH_TYPE_STRSIZE].fetch[i];
+
+	WARN_ON(1);	/* This should not happen */
+
+	return NULL;
+}
+
+/* Split symbol and offset. */
+int traceprobe_split_symbol_offset(char *symbol, long *offset)
+{
+	char *tmp;
+	int ret;
+
+	if (!offset)
+		return -EINVAL;
+
+	tmp = strpbrk(symbol, "+-");
+	if (tmp) {
+		ret = kstrtol(tmp, 0, offset);
+		if (ret)
+			return ret;
+		*tmp = '\0';
+	} else
+		*offset = 0;
+
+	return 0;
+}
+
+#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
+
+static int parse_probe_vars(char *arg, const struct fetch_type *t,
+			    struct fetch_param *f, bool is_return,
+			    bool is_kprobe)
+{
+	int ret = 0;
+	unsigned long param;
+
+	if (strcmp(arg, "retval") == 0) {
+		if (is_return)
+			f->fn = t->fetch[FETCH_MTD_retval];
+		else
+			ret = -EINVAL;
+	} else if (strncmp(arg, "stack", 5) == 0) {
+		if (arg[5] == '\0') {
+			if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR))
+				return -EINVAL;
+
+			if (is_kprobe)
+				f->fn = fetch_kernel_stack_address;
+			else
+				f->fn = fetch_user_stack_address;
+		} else if (isdigit(arg[5])) {
+			ret = kstrtoul(arg + 5, 10, &param);
+			if (ret || (is_kprobe && param > PARAM_MAX_STACK))
+				ret = -EINVAL;
+			else {
+				f->fn = t->fetch[FETCH_MTD_stack];
+				f->data = (void *)param;
+			}
+		} else
+			ret = -EINVAL;
+	} else if (strcmp(arg, "comm") == 0) {
+		if (strcmp(t->name, "string") != 0 &&
+		    strcmp(t->name, "string_size") != 0)
+			return -EINVAL;
+		f->fn = t->fetch[FETCH_MTD_comm];
+	} else
+		ret = -EINVAL;
+
+	return ret;
+}
+
+/* Recursive argument parser */
+static int parse_probe_arg(char *arg, const struct fetch_type *t,
+		     struct fetch_param *f, bool is_return, bool is_kprobe,
+		     const struct fetch_type *ftbl)
+{
+	unsigned long param;
+	long offset;
+	char *tmp;
+	int ret = 0;
+
+	switch (arg[0]) {
+	case '$':
+		ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe);
+		break;
+
+	case '%':	/* named register */
+		ret = regs_query_register_offset(arg + 1);
+		if (ret >= 0) {
+			f->fn = t->fetch[FETCH_MTD_reg];
+			f->data = (void *)(unsigned long)ret;
+			ret = 0;
+		}
+		break;
+
+	case '@':	/* memory, file-offset or symbol */
+		if (isdigit(arg[1])) {
+			ret = kstrtoul(arg + 1, 0, &param);
+			if (ret)
+				break;
+
+			f->fn = t->fetch[FETCH_MTD_memory];
+			f->data = (void *)param;
+		} else if (arg[1] == '+') {
+			/* kprobes don't support file offsets */
+			if (is_kprobe)
+				return -EINVAL;
+
+			ret = kstrtol(arg + 2, 0, &offset);
+			if (ret)
+				break;
+
+			f->fn = t->fetch[FETCH_MTD_file_offset];
+			f->data = (void *)offset;
+		} else {
+			/* uprobes don't support symbols */
+			if (!is_kprobe)
+				return -EINVAL;
+
+			ret = traceprobe_split_symbol_offset(arg + 1, &offset);
+			if (ret)
+				break;
+
+			f->data = alloc_symbol_cache(arg + 1, offset);
+			if (f->data)
+				f->fn = t->fetch[FETCH_MTD_symbol];
+		}
+		break;
+
+	case '+':	/* deref memory */
+		arg++;	/* Skip '+', because kstrtol() rejects it. */
+	case '-':
+		tmp = strchr(arg, '(');
+		if (!tmp)
+			break;
+
+		*tmp = '\0';
+		ret = kstrtol(arg, 0, &offset);
+
+		if (ret)
+			break;
+
+		arg = tmp + 1;
+		tmp = strrchr(arg, ')');
+
+		if (tmp) {
+			struct deref_fetch_param	*dprm;
+			const struct fetch_type		*t2;
+
+			t2 = find_fetch_type(NULL, ftbl);
+			*tmp = '\0';
+			dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL);
+
+			if (!dprm)
+				return -ENOMEM;
+
+			dprm->offset = offset;
+			dprm->fetch = t->fetch[FETCH_MTD_memory];
+			dprm->fetch_size = get_fetch_size_function(t,
+							dprm->fetch, ftbl);
+			ret = parse_probe_arg(arg, t2, &dprm->orig, is_return,
+							is_kprobe, ftbl);
+			if (ret)
+				kfree(dprm);
+			else {
+				f->fn = t->fetch[FETCH_MTD_deref];
+				f->data = (void *)dprm;
+			}
+		}
+		break;
+	}
+	if (!ret && !f->fn) {	/* Parsed, but do not find fetch method */
+		pr_info("%s type has no corresponding fetch method.\n", t->name);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+#define BYTES_TO_BITS(nb)	((BITS_PER_LONG * (nb)) / sizeof(long))
+
+/* Bitfield type needs to be parsed into a fetch function */
+static int __parse_bitfield_probe_arg(const char *bf,
+				      const struct fetch_type *t,
+				      struct fetch_param *f)
+{
+	struct bitfield_fetch_param *bprm;
+	unsigned long bw, bo;
+	char *tail;
+
+	if (*bf != 'b')
+		return 0;
+
+	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+	if (!bprm)
+		return -ENOMEM;
+
+	bprm->orig = *f;
+	f->fn = t->fetch[FETCH_MTD_bitfield];
+	f->data = (void *)bprm;
+	bw = simple_strtoul(bf + 1, &tail, 0);	/* Use simple one */
+
+	if (bw == 0 || *tail != '@')
+		return -EINVAL;
+
+	bf = tail + 1;
+	bo = simple_strtoul(bf, &tail, 0);
+
+	if (tail == bf || *tail != '/')
+		return -EINVAL;
+
+	bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo);
+	bprm->low_shift = bprm->hi_shift + bo;
+
+	return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0;
+}
+
+/* String length checking wrapper */
+int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
+		struct probe_arg *parg, bool is_return, bool is_kprobe,
+		const struct fetch_type *ftbl)
+{
+	const char *t;
+	int ret;
+
+	if (strlen(arg) > MAX_ARGSTR_LEN) {
+		pr_info("Argument is too long.: %s\n",  arg);
+		return -ENOSPC;
+	}
+	parg->comm = kstrdup(arg, GFP_KERNEL);
+	if (!parg->comm) {
+		pr_info("Failed to allocate memory for command '%s'.\n", arg);
+		return -ENOMEM;
+	}
+	t = strchr(parg->comm, ':');
+	if (t) {
+		arg[t - parg->comm] = '\0';
+		t++;
+	}
+	/*
+	 * The default type of $comm should be "string", and it can't be
+	 * dereferenced.
+	 */
+	if (!t && strcmp(arg, "$comm") == 0)
+		t = "string";
+	parg->type = find_fetch_type(t, ftbl);
+	if (!parg->type) {
+		pr_info("Unsupported type: %s\n", t);
+		return -EINVAL;
+	}
+	parg->offset = *size;
+	*size += parg->type->size;
+	ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return,
+			      is_kprobe, ftbl);
+
+	if (ret >= 0 && t != NULL)
+		ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
+
+	if (ret >= 0) {
+		parg->fetch_size.fn = get_fetch_size_function(parg->type,
+							      parg->fetch.fn,
+							      ftbl);
+		parg->fetch_size.data = parg->fetch.data;
+	}
+
+	return ret;
+}
+
+/* Return 1 if name is reserved or already used by another argument */
+int traceprobe_conflict_field_name(const char *name,
+			       struct probe_arg *args, int narg)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+		if (strcmp(reserved_field_names[i], name) == 0)
+			return 1;
+
+	for (i = 0; i < narg; i++)
+		if (strcmp(args[i].name, name) == 0)
+			return 1;
+
+	return 0;
+}
+
+void traceprobe_update_arg(struct probe_arg *arg)
+{
+	if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+		update_bitfield_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+		update_deref_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
+		update_symbol_cache(arg->fetch.data);
+}
+
+void traceprobe_free_probe_arg(struct probe_arg *arg)
+{
+	if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+		free_bitfield_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+		free_deref_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
+		free_symbol_cache(arg->fetch.data);
+
+	kfree(arg->name);
+	kfree(arg->comm);
+}
+
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len,
+			   bool is_return)
+{
+	int i;
+	int pos = 0;
+
+	const char *fmt, *arg;
+
+	if (!is_return) {
+		fmt = "(%lx)";
+		arg = "REC->" FIELD_STRING_IP;
+	} else {
+		fmt = "(%lx <- %lx)";
+		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+	}
+
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
+
+	for (i = 0; i < tp->nr_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+				tp->args[i].name, tp->args[i].type->fmt);
+	}
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+	for (i = 0; i < tp->nr_args; i++) {
+		if (strcmp(tp->args[i].type->name, "string") == 0)
+			pos += snprintf(buf + pos, LEN_OR_ZERO,
+					", __get_str(%s)",
+					tp->args[i].name);
+		else
+			pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+					tp->args[i].name);
+	}
+
+#undef LEN_OR_ZERO
+
+	/* return the length of print_fmt */
+	return pos;
+}
+
+int set_print_fmt(struct trace_probe *tp, bool is_return)
+{
+	int len;
+	char *print_fmt;
+
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_print_fmt(tp, NULL, 0, is_return);
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
+
+	/* Second: actually write the @print_fmt */
+	__set_print_fmt(tp, print_fmt, len + 1, is_return);
+	tp->call.print_fmt = print_fmt;
+
+	return 0;
+}

kernel/trace/trace_probe.h

@@ -0,0 +1,417 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common header file for probe-based Dynamic events.
+ *
+ * This code was copied from kernel/trace/trace_kprobe.h written by
+ * Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+ *
+ * Updates to make this generic:
+ * Copyright (C) IBM Corporation, 2010-2011
+ * Author:     Srikar Dronamraju
+ */
+
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/tracefs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/ptrace.h>
+#include <linux/perf_event.h>
+#include <linux/kprobes.h>
+#include <linux/stringify.h>
+#include <linux/limits.h>
+#include <linux/uaccess.h>
+#include <asm/bitsperlong.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+#define MAX_TRACE_ARGS		128
+#define MAX_ARGSTR_LEN		63
+#define MAX_STRING_SIZE		PATH_MAX
+
+/* Reserved field names */
+#define FIELD_STRING_IP		"__probe_ip"
+#define FIELD_STRING_RETIP	"__probe_ret_ip"
+#define FIELD_STRING_FUNC	"__probe_func"
+
+#undef DEFINE_FIELD
+#define DEFINE_FIELD(type, item, name, is_signed)			\
+	do {								\
+		ret = trace_define_field(event_call, #type, name,	\
+					 offsetof(typeof(field), item),	\
+					 sizeof(field.item), is_signed, \
+					 FILTER_OTHER);			\
+		if (ret)						\
+			return ret;					\
+	} while (0)
+
+
+/* Flags for trace_probe */
+#define TP_FLAG_TRACE		1
+#define TP_FLAG_PROFILE		2
+#define TP_FLAG_REGISTERED	4
+
+
+/* data_rloc: data relative location, compatible with u32 */
+#define make_data_rloc(len, roffs)	\
+	(((u32)(len) << 16) | ((u32)(roffs) & 0xffff))
+#define get_rloc_len(dl)		((u32)(dl) >> 16)
+#define get_rloc_offs(dl)		((u32)(dl) & 0xffff)
+
+/*
+ * Convert data_rloc to data_loc:
+ *  data_rloc stores the offset from data_rloc itself, but data_loc
+ *  stores the offset from event entry.
+ */
+#define convert_rloc_to_loc(dl, offs)	((u32)(dl) + (offs))
+
+static nokprobe_inline void *get_rloc_data(u32 *dl)
+{
+	return (u8 *)dl + get_rloc_offs(*dl);
+}
+
+/* For data_loc conversion */
+static nokprobe_inline void *get_loc_data(u32 *dl, void *ent)
+{
+	return (u8 *)ent + get_rloc_offs(*dl);
+}
+
+/* Data fetch function type */
+typedef	void (*fetch_func_t)(struct pt_regs *, void *, void *);
+/* Printing function type */
+typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *, void *);
+
+/* Fetch types */
+enum {
+	FETCH_MTD_reg = 0,
+	FETCH_MTD_stack,
+	FETCH_MTD_retval,
+	FETCH_MTD_comm,
+	FETCH_MTD_memory,
+	FETCH_MTD_symbol,
+	FETCH_MTD_deref,
+	FETCH_MTD_bitfield,
+	FETCH_MTD_file_offset,
+	FETCH_MTD_END,
+};
+
+/* Fetch type information table */
+struct fetch_type {
+	const char		*name;		/* Name of type */
+	size_t			size;		/* Byte size of type */
+	int			is_signed;	/* Signed flag */
+	print_type_func_t	print;		/* Print functions */
+	const char		*fmt;		/* Fromat string */
+	const char		*fmttype;	/* Name in format file */
+	/* Fetch functions */
+	fetch_func_t		fetch[FETCH_MTD_END];
+};
+
+struct fetch_param {
+	fetch_func_t		fn;
+	void 			*data;
+};
+
+/* For defining macros, define string/string_size types */
+typedef u32 string;
+typedef u32 string_size;
+
+#define PRINT_TYPE_FUNC_NAME(type)	print_type_##type
+#define PRINT_TYPE_FMT_NAME(type)	print_type_format_##type
+
+/* Printing  in basic type function template */
+#define DECLARE_BASIC_PRINT_TYPE_FUNC(type)				\
+int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name,	\
+				void *data, void *ent);			\
+extern const char PRINT_TYPE_FMT_NAME(type)[]
+
+DECLARE_BASIC_PRINT_TYPE_FUNC(u8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(u64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(s64);
+DECLARE_BASIC_PRINT_TYPE_FUNC(x8);
+DECLARE_BASIC_PRINT_TYPE_FUNC(x16);
+DECLARE_BASIC_PRINT_TYPE_FUNC(x32);
+DECLARE_BASIC_PRINT_TYPE_FUNC(x64);
+
+DECLARE_BASIC_PRINT_TYPE_FUNC(string);
+
+#define FETCH_FUNC_NAME(method, type)	fetch_##method##_##type
+
+/* Declare macro for basic types */
+#define DECLARE_FETCH_FUNC(method, type)				\
+extern void FETCH_FUNC_NAME(method, type)(struct pt_regs *regs, 	\
+					  void *data, void *dest)
+
+#define DECLARE_BASIC_FETCH_FUNCS(method) 	\
+DECLARE_FETCH_FUNC(method, u8);			\
+DECLARE_FETCH_FUNC(method, u16);		\
+DECLARE_FETCH_FUNC(method, u32);		\
+DECLARE_FETCH_FUNC(method, u64)
+
+DECLARE_BASIC_FETCH_FUNCS(reg);
+#define fetch_reg_string			NULL
+#define fetch_reg_string_size			NULL
+
+DECLARE_BASIC_FETCH_FUNCS(retval);
+#define fetch_retval_string			NULL
+#define fetch_retval_string_size		NULL
+
+DECLARE_BASIC_FETCH_FUNCS(symbol);
+DECLARE_FETCH_FUNC(symbol, string);
+DECLARE_FETCH_FUNC(symbol, string_size);
+
+DECLARE_BASIC_FETCH_FUNCS(deref);
+DECLARE_FETCH_FUNC(deref, string);
+DECLARE_FETCH_FUNC(deref, string_size);
+
+DECLARE_BASIC_FETCH_FUNCS(bitfield);
+#define fetch_bitfield_string			NULL
+#define fetch_bitfield_string_size		NULL
+
+/* comm only makes sense as a string */
+#define fetch_comm_u8		NULL
+#define fetch_comm_u16		NULL
+#define fetch_comm_u32		NULL
+#define fetch_comm_u64		NULL
+DECLARE_FETCH_FUNC(comm, string);
+DECLARE_FETCH_FUNC(comm, string_size);
+
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(method) \
+DEFINE_FETCH_##method(u8)		\
+DEFINE_FETCH_##method(u16)		\
+DEFINE_FETCH_##method(u32)		\
+DEFINE_FETCH_##method(u64)
+
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) x##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+#define ASSIGN_FETCH_FUNC(method, type)	\
+	[FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
+
+#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype)	\
+	{.name = _name,				\
+	 .size = _size,					\
+	 .is_signed = sign,				\
+	 .print = PRINT_TYPE_FUNC_NAME(ptype),		\
+	 .fmt = PRINT_TYPE_FMT_NAME(ptype),		\
+	 .fmttype = _fmttype,				\
+	 .fetch = {					\
+ASSIGN_FETCH_FUNC(reg, ftype),				\
+ASSIGN_FETCH_FUNC(stack, ftype),			\
+ASSIGN_FETCH_FUNC(retval, ftype),			\
+ASSIGN_FETCH_FUNC(comm, ftype),				\
+ASSIGN_FETCH_FUNC(memory, ftype),			\
+ASSIGN_FETCH_FUNC(symbol, ftype),			\
+ASSIGN_FETCH_FUNC(deref, ftype),			\
+ASSIGN_FETCH_FUNC(bitfield, ftype),			\
+ASSIGN_FETCH_FUNC(file_offset, ftype),			\
+	  }						\
+	}
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign)			\
+	__ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
+
+/* If ptype is an alias of atype, use this macro (show atype in format) */
+#define ASSIGN_FETCH_TYPE_ALIAS(ptype, atype, ftype, sign)		\
+	__ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #atype)
+
+#define ASSIGN_FETCH_TYPE_END {}
+
+#define FETCH_TYPE_STRING	0
+#define FETCH_TYPE_STRSIZE	1
+
+#ifdef CONFIG_KPROBE_EVENTS
+struct symbol_cache;
+unsigned long update_symbol_cache(struct symbol_cache *sc);
+void free_symbol_cache(struct symbol_cache *sc);
+struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
+bool trace_kprobe_on_func_entry(struct trace_event_call *call);
+bool trace_kprobe_error_injectable(struct trace_event_call *call);
+#else
+/* uprobes do not support symbol fetch methods */
+#define fetch_symbol_u8			NULL
+#define fetch_symbol_u16		NULL
+#define fetch_symbol_u32		NULL
+#define fetch_symbol_u64		NULL
+#define fetch_symbol_string		NULL
+#define fetch_symbol_string_size	NULL
+
+struct symbol_cache {
+};
+static inline unsigned long __used update_symbol_cache(struct symbol_cache *sc)
+{
+	return 0;
+}
+
+static inline void __used free_symbol_cache(struct symbol_cache *sc)
+{
+}
+
+static inline struct symbol_cache * __used
+alloc_symbol_cache(const char *sym, long offset)
+{
+	return NULL;
+}
+
+static inline bool trace_kprobe_on_func_entry(struct trace_event_call *call)
+{
+	return false;
+}
+
+static inline bool trace_kprobe_error_injectable(struct trace_event_call *call)
+{
+	return false;
+}
+#endif /* CONFIG_KPROBE_EVENTS */
+
+struct probe_arg {
+	struct fetch_param	fetch;
+	struct fetch_param	fetch_size;
+	unsigned int		offset;	/* Offset from argument entry */
+	const char		*name;	/* Name of this argument */
+	const char		*comm;	/* Command of this argument */
+	const struct fetch_type	*type;	/* Type of this argument */
+};
+
+struct trace_probe {
+	unsigned int			flags;	/* For TP_FLAG_* */
+	struct trace_event_class	class;
+	struct trace_event_call		call;
+	struct list_head 		files;
+	ssize_t				size;	/* trace entry size */
+	unsigned int			nr_args;
+	struct probe_arg		args[];
+};
+
+struct event_file_link {
+	struct trace_event_file		*file;
+	struct list_head		list;
+};
+
+static inline bool trace_probe_is_enabled(struct trace_probe *tp)
+{
+	return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+}
+
+static inline bool trace_probe_is_registered(struct trace_probe *tp)
+{
+	return !!(tp->flags & TP_FLAG_REGISTERED);
+}
+
+static nokprobe_inline void call_fetch(struct fetch_param *fprm,
+				 struct pt_regs *regs, void *dest)
+{
+	return fprm->fn(regs, fprm->data, dest);
+}
+
+/* Check the name is good for event/group/fields */
+static inline bool is_good_name(const char *name)
+{
+	if (!isalpha(*name) && *name != '_')
+		return false;
+	while (*++name != '\0') {
+		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+			return false;
+	}
+	return true;
+}
+
+static inline struct event_file_link *
+find_event_file_link(struct trace_probe *tp, struct trace_event_file *file)
+{
+	struct event_file_link *link;
+
+	list_for_each_entry(link, &tp->files, list)
+		if (link->file == file)
+			return link;
+
+	return NULL;
+}
+
+extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
+		   struct probe_arg *parg, bool is_return, bool is_kprobe,
+		   const struct fetch_type *ftbl);
+
+extern int traceprobe_conflict_field_name(const char *name,
+			       struct probe_arg *args, int narg);
+
+extern void traceprobe_update_arg(struct probe_arg *arg);
+extern void traceprobe_free_probe_arg(struct probe_arg *arg);
+
+extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
+
+/* Sum up total data length for dynamic arraies (strings) */
+static nokprobe_inline int
+__get_data_size(struct trace_probe *tp, struct pt_regs *regs)
+{
+	int i, ret = 0;
+	u32 len;
+
+	for (i = 0; i < tp->nr_args; i++)
+		if (unlikely(tp->args[i].fetch_size.fn)) {
+			call_fetch(&tp->args[i].fetch_size, regs, &len);
+			ret += len;
+		}
+
+	return ret;
+}
+
+/* Store the value of each argument */
+static nokprobe_inline void
+store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs,
+		 u8 *data, int maxlen)
+{
+	int i;
+	u32 end = tp->size;
+	u32 *dl;	/* Data (relative) location */
+
+	for (i = 0; i < tp->nr_args; i++) {
+		if (unlikely(tp->args[i].fetch_size.fn)) {
+			/*
+			 * First, we set the relative location and
+			 * maximum data length to *dl
+			 */
+			dl = (u32 *)(data + tp->args[i].offset);
+			*dl = make_data_rloc(maxlen, end - tp->args[i].offset);
+			/* Then try to fetch string or dynamic array data */
+			call_fetch(&tp->args[i].fetch, regs, dl);
+			/* Reduce maximum length */
+			end += get_rloc_len(*dl);
+			maxlen -= get_rloc_len(*dl);
+			/* Trick here, convert data_rloc to data_loc */
+			*dl = convert_rloc_to_loc(*dl,
+				 ent_size + tp->args[i].offset);
+		} else
+			/* Just fetching data normally */
+			call_fetch(&tp->args[i].fetch, regs,
+				   data + tp->args[i].offset);
+	}
+}
+
+extern int set_print_fmt(struct trace_probe *tp, bool is_return);
+
+#ifdef CONFIG_PERF_EVENTS
+extern struct trace_event_call *
+create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
+			  bool is_return);
+extern void destroy_local_trace_kprobe(struct trace_event_call *event_call);
+
+extern struct trace_event_call *
+create_local_trace_uprobe(char *name, unsigned long offs, bool is_return);
+extern void destroy_local_trace_uprobe(struct trace_event_call *event_call);
+#endif

kernel/trace/trace_sched_switch.c

@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace context switch
+ *
+ * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <trace/events/sched.h>
+
+#include "trace.h"
+
+#define RECORD_CMDLINE	1
+#define RECORD_TGID	2
+
+static int		sched_cmdline_ref;
+static int		sched_tgid_ref;
+static DEFINE_MUTEX(sched_register_mutex);
+
+static void
+probe_sched_switch(void *ignore, bool preempt,
+		   struct task_struct *prev, struct task_struct *next)
+{
+	int flags;
+
+	flags = (RECORD_TGID * !!sched_tgid_ref) +
+		(RECORD_CMDLINE * !!sched_cmdline_ref);
+
+	if (!flags)
+		return;
+	tracing_record_taskinfo_sched_switch(prev, next, flags);
+}
+
+static void
+probe_sched_wakeup(void *ignore, struct task_struct *wakee)
+{
+	int flags;
+
+	flags = (RECORD_TGID * !!sched_tgid_ref) +
+		(RECORD_CMDLINE * !!sched_cmdline_ref);
+
+	if (!flags)
+		return;
+	tracing_record_taskinfo(current, flags);
+}
+
+static int tracing_sched_register(void)
+{
+	int ret;
+
+	ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_wakeup\n");
+		return ret;
+	}
+
+	ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_wakeup_new\n");
+		goto fail_deprobe;
+	}
+
+	ret = register_trace_sched_switch(probe_sched_switch, NULL);
+	if (ret) {
+		pr_info("sched trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_switch\n");
+		goto fail_deprobe_wake_new;
+	}
+
+	return ret;
+fail_deprobe_wake_new:
+	unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
+fail_deprobe:
+	unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
+	return ret;
+}
+
+static void tracing_sched_unregister(void)
+{
+	unregister_trace_sched_switch(probe_sched_switch, NULL);
+	unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
+	unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
+}
+
+static void tracing_start_sched_switch(int ops)
+{
+	bool sched_register;
+
+	mutex_lock(&sched_register_mutex);
+	sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
+
+	switch (ops) {
+	case RECORD_CMDLINE:
+		sched_cmdline_ref++;
+		break;
+
+	case RECORD_TGID:
+		sched_tgid_ref++;
+		break;
+	}
+
+	if (sched_register && (sched_cmdline_ref || sched_tgid_ref))
+		tracing_sched_register();
+	mutex_unlock(&sched_register_mutex);
+}
+
+static void tracing_stop_sched_switch(int ops)
+{
+	mutex_lock(&sched_register_mutex);
+
+	switch (ops) {
+	case RECORD_CMDLINE:
+		sched_cmdline_ref--;
+		break;
+
+	case RECORD_TGID:
+		sched_tgid_ref--;
+		break;
+	}
+
+	if (!sched_cmdline_ref && !sched_tgid_ref)
+		tracing_sched_unregister();
+	mutex_unlock(&sched_register_mutex);
+}
+
+void tracing_start_cmdline_record(void)
+{
+	tracing_start_sched_switch(RECORD_CMDLINE);
+}
+
+void tracing_stop_cmdline_record(void)
+{
+	tracing_stop_sched_switch(RECORD_CMDLINE);
+}
+
+void tracing_start_tgid_record(void)
+{
+	tracing_start_sched_switch(RECORD_TGID);
+}
+
+void tracing_stop_tgid_record(void)
+{
+	tracing_stop_sched_switch(RECORD_TGID);
+}

kernel/trace/trace_sched_wakeup.c

@@ -0,0 +1,832 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace task wakeup timings
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ * Based on code from the latency_tracer, that is:
+ *
+ *  Copyright (C) 2004-2006 Ingo Molnar
+ *  Copyright (C) 2004 Nadia Yvette Chambers
+ */
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
+#include <trace/events/sched.h>
+#include "trace.h"
+
+static struct trace_array	*wakeup_trace;
+static int __read_mostly	tracer_enabled;
+
+static struct task_struct	*wakeup_task;
+static int			wakeup_cpu;
+static int			wakeup_current_cpu;
+static unsigned			wakeup_prio = -1;
+static int			wakeup_rt;
+static int			wakeup_dl;
+static int			tracing_dl = 0;
+
+static arch_spinlock_t wakeup_lock =
+	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+static void wakeup_reset(struct trace_array *tr);
+static void __wakeup_reset(struct trace_array *tr);
+
+static int save_flags;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int wakeup_display_graph(struct trace_array *tr, int set);
+# define is_graph(tr) ((tr)->trace_flags & TRACE_ITER_DISPLAY_GRAPH)
+#else
+static inline int wakeup_display_graph(struct trace_array *tr, int set)
+{
+	return 0;
+}
+# define is_graph(tr) false
+#endif
+
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
+static void wakeup_graph_return(struct ftrace_graph_ret *trace);
+
+static bool function_enabled;
+
+/*
+ * Prologue for the wakeup function tracers.
+ *
+ * Returns 1 if it is OK to continue, and preemption
+ *            is disabled and data->disabled is incremented.
+ *         0 if the trace is to be ignored, and preemption
+ *            is not disabled and data->disabled is
+ *            kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
+ */
+static int
+func_prolog_preempt_disable(struct trace_array *tr,
+			    struct trace_array_cpu **data,
+			    int *pc)
+{
+	long disabled;
+	int cpu;
+
+	if (likely(!wakeup_task))
+		return 0;
+
+	*pc = preempt_count();
+	preempt_disable_notrace();
+
+	cpu = raw_smp_processor_id();
+	if (cpu != wakeup_current_cpu)
+		goto out_enable;
+
+	*data = per_cpu_ptr(tr->trace_buffer.data, cpu);
+	disabled = atomic_inc_return(&(*data)->disabled);
+	if (unlikely(disabled != 1))
+		goto out;
+
+	return 1;
+
+out:
+	atomic_dec(&(*data)->disabled);
+
+out_enable:
+	preempt_enable_notrace();
+	return 0;
+}
+
+/*
+ * wakeup uses its own tracer function to keep the overhead down:
+ */
+static void
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
+		   struct ftrace_ops *op, struct pt_regs *pt_regs)
+{
+	struct trace_array *tr = wakeup_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	int pc;
+
+	if (!func_prolog_preempt_disable(tr, &data, &pc))
+		return;
+
+	local_irq_save(flags);
+	trace_function(tr, ip, parent_ip, flags, pc);
+	local_irq_restore(flags);
+
+	atomic_dec(&data->disabled);
+	preempt_enable_notrace();
+}
+
+static int register_wakeup_function(struct trace_array *tr, int graph, int set)
+{
+	int ret;
+
+	/* 'set' is set if TRACE_ITER_FUNCTION is about to be set */
+	if (function_enabled || (!set && !(tr->trace_flags & TRACE_ITER_FUNCTION)))
+		return 0;
+
+	if (graph)
+		ret = register_ftrace_graph(&wakeup_graph_return,
+					    &wakeup_graph_entry);
+	else
+		ret = register_ftrace_function(tr->ops);
+
+	if (!ret)
+		function_enabled = true;
+
+	return ret;
+}
+
+static void unregister_wakeup_function(struct trace_array *tr, int graph)
+{
+	if (!function_enabled)
+		return;
+
+	if (graph)
+		unregister_ftrace_graph();
+	else
+		unregister_ftrace_function(tr->ops);
+
+	function_enabled = false;
+}
+
+static int wakeup_function_set(struct trace_array *tr, u32 mask, int set)
+{
+	if (!(mask & TRACE_ITER_FUNCTION))
+		return 0;
+
+	if (set)
+		register_wakeup_function(tr, is_graph(tr), 1);
+	else
+		unregister_wakeup_function(tr, is_graph(tr));
+	return 1;
+}
+#else
+static int register_wakeup_function(struct trace_array *tr, int graph, int set)
+{
+	return 0;
+}
+static void unregister_wakeup_function(struct trace_array *tr, int graph) { }
+static int wakeup_function_set(struct trace_array *tr, u32 mask, int set)
+{
+	return 0;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
+static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set)
+{
+	struct tracer *tracer = tr->current_trace;
+
+	if (wakeup_function_set(tr, mask, set))
+		return 0;
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (mask & TRACE_ITER_DISPLAY_GRAPH)
+		return wakeup_display_graph(tr, set);
+#endif
+
+	return trace_keep_overwrite(tracer, mask, set);
+}
+
+static int start_func_tracer(struct trace_array *tr, int graph)
+{
+	int ret;
+
+	ret = register_wakeup_function(tr, graph, 0);
+
+	if (!ret && tracing_is_enabled())
+		tracer_enabled = 1;
+	else
+		tracer_enabled = 0;
+
+	return ret;
+}
+
+static void stop_func_tracer(struct trace_array *tr, int graph)
+{
+	tracer_enabled = 0;
+
+	unregister_wakeup_function(tr, graph);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int wakeup_display_graph(struct trace_array *tr, int set)
+{
+	if (!(is_graph(tr) ^ set))
+		return 0;
+
+	stop_func_tracer(tr, !set);
+
+	wakeup_reset(wakeup_trace);
+	tr->max_latency = 0;
+
+	return start_func_tracer(tr, set);
+}
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = wakeup_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	int pc, ret = 0;
+
+	if (ftrace_graph_ignore_func(trace))
+		return 0;
+	/*
+	 * Do not trace a function if it's filtered by set_graph_notrace.
+	 * Make the index of ret stack negative to indicate that it should
+	 * ignore further functions.  But it needs its own ret stack entry
+	 * to recover the original index in order to continue tracing after
+	 * returning from the function.
+	 */
+	if (ftrace_graph_notrace_addr(trace->func))
+		return 1;
+
+	if (!func_prolog_preempt_disable(tr, &data, &pc))
+		return 0;
+
+	local_save_flags(flags);
+	ret = __trace_graph_entry(tr, trace, flags, pc);
+	atomic_dec(&data->disabled);
+	preempt_enable_notrace();
+
+	return ret;
+}
+
+static void wakeup_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct trace_array *tr = wakeup_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	int pc;
+
+	ftrace_graph_addr_finish(trace);
+
+	if (!func_prolog_preempt_disable(tr, &data, &pc))
+		return;
+
+	local_save_flags(flags);
+	__trace_graph_return(tr, trace, flags, pc);
+	atomic_dec(&data->disabled);
+
+	preempt_enable_notrace();
+	return;
+}
+
+static void wakeup_trace_open(struct trace_iterator *iter)
+{
+	if (is_graph(iter->tr))
+		graph_trace_open(iter);
+}
+
+static void wakeup_trace_close(struct trace_iterator *iter)
+{
+	if (iter->private)
+		graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC | \
+			    TRACE_GRAPH_PRINT_ABS_TIME | \
+			    TRACE_GRAPH_PRINT_DURATION)
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+	/*
+	 * In graph mode call the graph tracer output function,
+	 * otherwise go with the TRACE_FN event handler
+	 */
+	if (is_graph(iter->tr))
+		return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
+
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_print_header(struct seq_file *s)
+{
+	if (is_graph(wakeup_trace))
+		print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+	else
+		trace_default_header(s);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+		 unsigned long ip, unsigned long parent_ip,
+		 unsigned long flags, int pc)
+{
+	if (is_graph(tr))
+		trace_graph_function(tr, ip, parent_ip, flags, pc);
+	else
+		trace_function(tr, ip, parent_ip, flags, pc);
+}
+#else
+#define __trace_function trace_function
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_trace_open(struct trace_iterator *iter) { }
+static void wakeup_trace_close(struct trace_iterator *iter) { }
+
+#ifdef CONFIG_FUNCTION_TRACER
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+	return -1;
+}
+static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
+static void wakeup_print_header(struct seq_file *s)
+{
+	trace_default_header(s);
+}
+#else
+static void wakeup_print_header(struct seq_file *s)
+{
+	trace_latency_header(s);
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+/*
+ * Should this new latency be reported/recorded?
+ */
+static bool report_latency(struct trace_array *tr, u64 delta)
+{
+	if (tracing_thresh) {
+		if (delta < tracing_thresh)
+			return false;
+	} else {
+		if (delta <= tr->max_latency)
+			return false;
+	}
+	return true;
+}
+
+static void
+probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu)
+{
+	if (task != wakeup_task)
+		return;
+
+	wakeup_current_cpu = cpu;
+}
+
+static void
+tracing_sched_switch_trace(struct trace_array *tr,
+			   struct task_struct *prev,
+			   struct task_struct *next,
+			   unsigned long flags, int pc)
+{
+	struct trace_event_call *call = &event_context_switch;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= prev->pid;
+	entry->prev_prio		= prev->prio;
+	entry->prev_state		= task_state_index(prev);
+	entry->next_pid			= next->pid;
+	entry->next_prio		= next->prio;
+	entry->next_state		= task_state_index(next);
+	entry->next_cpu	= task_cpu(next);
+
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(tr, buffer, event, flags, pc);
+}
+
+static void
+tracing_sched_wakeup_trace(struct trace_array *tr,
+			   struct task_struct *wakee,
+			   struct task_struct *curr,
+			   unsigned long flags, int pc)
+{
+	struct trace_event_call *call = &event_wakeup;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+	struct ring_buffer *buffer = tr->trace_buffer.buffer;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= curr->pid;
+	entry->prev_prio		= curr->prio;
+	entry->prev_state		= task_state_index(curr);
+	entry->next_pid			= wakee->pid;
+	entry->next_prio		= wakee->prio;
+	entry->next_state		= task_state_index(wakee);
+	entry->next_cpu			= task_cpu(wakee);
+
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(tr, buffer, event, flags, pc);
+}
+
+static void notrace
+probe_wakeup_sched_switch(void *ignore, bool preempt,
+			  struct task_struct *prev, struct task_struct *next)
+{
+	struct trace_array_cpu *data;
+	u64 T0, T1, delta;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	tracing_record_cmdline(prev);
+
+	if (unlikely(!tracer_enabled))
+		return;
+
+	/*
+	 * When we start a new trace, we set wakeup_task to NULL
+	 * and then set tracer_enabled = 1. We want to make sure
+	 * that another CPU does not see the tracer_enabled = 1
+	 * and the wakeup_task with an older task, that might
+	 * actually be the same as next.
+	 */
+	smp_rmb();
+
+	if (next != wakeup_task)
+		return;
+
+	pc = preempt_count();
+
+	/* disable local data, not wakeup_cpu data */
+	cpu = raw_smp_processor_id();
+	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
+	if (likely(disabled != 1))
+		goto out;
+
+	local_irq_save(flags);
+	arch_spin_lock(&wakeup_lock);
+
+	/* We could race with grabbing wakeup_lock */
+	if (unlikely(!tracer_enabled || next != wakeup_task))
+		goto out_unlock;
+
+	/* The task we are waiting for is waking up */
+	data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu);
+
+	__trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
+	tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
+
+	T0 = data->preempt_timestamp;
+	T1 = ftrace_now(cpu);
+	delta = T1-T0;
+
+	if (!report_latency(wakeup_trace, delta))
+		goto out_unlock;
+
+	if (likely(!is_tracing_stopped())) {
+		wakeup_trace->max_latency = delta;
+		update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
+	}
+
+out_unlock:
+	__wakeup_reset(wakeup_trace);
+	arch_spin_unlock(&wakeup_lock);
+	local_irq_restore(flags);
+out:
+	atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
+}
+
+static void __wakeup_reset(struct trace_array *tr)
+{
+	wakeup_cpu = -1;
+	wakeup_prio = -1;
+	tracing_dl = 0;
+
+	if (wakeup_task)
+		put_task_struct(wakeup_task);
+
+	wakeup_task = NULL;
+}
+
+static void wakeup_reset(struct trace_array *tr)
+{
+	unsigned long flags;
+
+	tracing_reset_online_cpus(&tr->trace_buffer);
+
+	local_irq_save(flags);
+	arch_spin_lock(&wakeup_lock);
+	__wakeup_reset(tr);
+	arch_spin_unlock(&wakeup_lock);
+	local_irq_restore(flags);
+}
+
+static void
+probe_wakeup(void *ignore, struct task_struct *p)
+{
+	struct trace_array_cpu *data;
+	int cpu = smp_processor_id();
+	unsigned long flags;
+	long disabled;
+	int pc;
+
+	if (likely(!tracer_enabled))
+		return;
+
+	tracing_record_cmdline(p);
+	tracing_record_cmdline(current);
+
+	/*
+	 * Semantic is like this:
+	 *  - wakeup tracer handles all tasks in the system, independently
+	 *    from their scheduling class;
+	 *  - wakeup_rt tracer handles tasks belonging to sched_dl and
+	 *    sched_rt class;
+	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
+	 */
+	if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
+	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
+		return;
+
+	pc = preempt_count();
+	disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
+	if (unlikely(disabled != 1))
+		goto out;
+
+	/* interrupts should be off from try_to_wake_up */
+	arch_spin_lock(&wakeup_lock);
+
+	/* check for races. */
+	if (!tracer_enabled || tracing_dl ||
+	    (!dl_task(p) && p->prio >= wakeup_prio))
+		goto out_locked;
+
+	/* reset the trace */
+	__wakeup_reset(wakeup_trace);
+
+	wakeup_cpu = task_cpu(p);
+	wakeup_current_cpu = wakeup_cpu;
+	wakeup_prio = p->prio;
+
+	/*
+	 * Once you start tracing a -deadline task, don't bother tracing
+	 * another task until the first one wakes up.
+	 */
+	if (dl_task(p))
+		tracing_dl = 1;
+	else
+		tracing_dl = 0;
+
+	wakeup_task = p;
+	get_task_struct(wakeup_task);
+
+	local_save_flags(flags);
+
+	data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu);
+	data->preempt_timestamp = ftrace_now(cpu);
+	tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc);
+
+	/*
+	 * We must be careful in using CALLER_ADDR2. But since wake_up
+	 * is not called by an assembly function  (where as schedule is)
+	 * it should be safe to use it here.
+	 */
+	__trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
+
+out_locked:
+	arch_spin_unlock(&wakeup_lock);
+out:
+	atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled);
+}
+
+static void start_wakeup_tracer(struct trace_array *tr)
+{
+	int ret;
+
+	ret = register_trace_sched_wakeup(probe_wakeup, NULL);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_wakeup\n");
+		return;
+	}
+
+	ret = register_trace_sched_wakeup_new(probe_wakeup, NULL);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_wakeup_new\n");
+		goto fail_deprobe;
+	}
+
+	ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+	if (ret) {
+		pr_info("sched trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_switch\n");
+		goto fail_deprobe_wake_new;
+	}
+
+	ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
+	if (ret) {
+		pr_info("wakeup trace: Couldn't activate tracepoint"
+			" probe to kernel_sched_migrate_task\n");
+		goto fail_deprobe_sched_switch;
+	}
+
+	wakeup_reset(tr);
+
+	/*
+	 * Don't let the tracer_enabled = 1 show up before
+	 * the wakeup_task is reset. This may be overkill since
+	 * wakeup_reset does a spin_unlock after setting the
+	 * wakeup_task to NULL, but I want to be safe.
+	 * This is a slow path anyway.
+	 */
+	smp_wmb();
+
+	if (start_func_tracer(tr, is_graph(tr)))
+		printk(KERN_ERR "failed to start wakeup tracer\n");
+
+	return;
+fail_deprobe_sched_switch:
+	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+fail_deprobe_wake_new:
+	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+fail_deprobe:
+	unregister_trace_sched_wakeup(probe_wakeup, NULL);
+}
+
+static void stop_wakeup_tracer(struct trace_array *tr)
+{
+	tracer_enabled = 0;
+	stop_func_tracer(tr, is_graph(tr));
+	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+	unregister_trace_sched_wakeup(probe_wakeup, NULL);
+	unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
+}
+
+static bool wakeup_busy;
+
+static int __wakeup_tracer_init(struct trace_array *tr)
+{
+	save_flags = tr->trace_flags;
+
+	/* non overwrite screws up the latency tracers */
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
+
+	tr->max_latency = 0;
+	wakeup_trace = tr;
+	ftrace_init_array_ops(tr, wakeup_tracer_call);
+	start_wakeup_tracer(tr);
+
+	wakeup_busy = true;
+	return 0;
+}
+
+static int wakeup_tracer_init(struct trace_array *tr)
+{
+	if (wakeup_busy)
+		return -EBUSY;
+
+	wakeup_dl = 0;
+	wakeup_rt = 0;
+	return __wakeup_tracer_init(tr);
+}
+
+static int wakeup_rt_tracer_init(struct trace_array *tr)
+{
+	if (wakeup_busy)
+		return -EBUSY;
+
+	wakeup_dl = 0;
+	wakeup_rt = 1;
+	return __wakeup_tracer_init(tr);
+}
+
+static int wakeup_dl_tracer_init(struct trace_array *tr)
+{
+	if (wakeup_busy)
+		return -EBUSY;
+
+	wakeup_dl = 1;
+	wakeup_rt = 0;
+	return __wakeup_tracer_init(tr);
+}
+
+static void wakeup_tracer_reset(struct trace_array *tr)
+{
+	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
+	int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE;
+
+	stop_wakeup_tracer(tr);
+	/* make sure we put back any tasks we are tracing */
+	wakeup_reset(tr);
+
+	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
+	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
+	ftrace_reset_array_ops(tr);
+	wakeup_busy = false;
+}
+
+static void wakeup_tracer_start(struct trace_array *tr)
+{
+	wakeup_reset(tr);
+	tracer_enabled = 1;
+}
+
+static void wakeup_tracer_stop(struct trace_array *tr)
+{
+	tracer_enabled = 0;
+}
+
+static struct tracer wakeup_tracer __read_mostly =
+{
+	.name		= "wakeup",
+	.init		= wakeup_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.print_max	= true,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flag_changed	= wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+
+static struct tracer wakeup_rt_tracer __read_mostly =
+{
+	.name		= "wakeup_rt",
+	.init		= wakeup_rt_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.print_max	= true,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flag_changed	= wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+
+static struct tracer wakeup_dl_tracer __read_mostly =
+{
+	.name		= "wakeup_dl",
+	.init		= wakeup_dl_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.print_max	= true,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flag_changed	= wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
+	.allow_instances = true,
+	.use_max_tr	= true,
+};
+
+__init static int init_wakeup_tracer(void)
+{
+	int ret;
+
+	ret = register_tracer(&wakeup_tracer);
+	if (ret)
+		return ret;
+
+	ret = register_tracer(&wakeup_rt_tracer);
+	if (ret)
+		return ret;
+
+	ret = register_tracer(&wakeup_dl_tracer);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+core_initcall(init_wakeup_tracer);

kernel/trace/trace_selftest_dynamic.c

@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include "trace.h"
+
+noinline __noclone int DYN_FTRACE_TEST_NAME(void)
+{
+	/* used to call mcount */
+	return 0;
+}
+
+noinline __noclone int DYN_FTRACE_TEST_NAME2(void)
+{
+	/* used to call mcount */
+	return 0;
+}

kernel/trace/trace_seq.c

@@ -0,0 +1,378 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace_seq.c
+ *
+ * Copyright (C) 2008-2014 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * The trace_seq is a handy tool that allows you to pass a descriptor around
+ * to a buffer that other functions can write to. It is similar to the
+ * seq_file functionality but has some differences.
+ *
+ * To use it, the trace_seq must be initialized with trace_seq_init().
+ * This will set up the counters within the descriptor. You can call
+ * trace_seq_init() more than once to reset the trace_seq to start
+ * from scratch.
+ * 
+ * The buffer size is currently PAGE_SIZE, although it may become dynamic
+ * in the future.
+ *
+ * A write to the buffer will either succed or fail. That is, unlike
+ * sprintf() there will not be a partial write (well it may write into
+ * the buffer but it wont update the pointers). This allows users to
+ * try to write something into the trace_seq buffer and if it fails
+ * they can flush it and try again.
+ *
+ */
+#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/trace_seq.h>
+
+/* How much buffer is left on the trace_seq? */
+#define TRACE_SEQ_BUF_LEFT(s) seq_buf_buffer_left(&(s)->seq)
+
+/* How much buffer is written? */
+#define TRACE_SEQ_BUF_USED(s) seq_buf_used(&(s)->seq)
+
+/*
+ * trace_seq should work with being initialized with 0s.
+ */
+static inline void __trace_seq_init(struct trace_seq *s)
+{
+	if (unlikely(!s->seq.size))
+		trace_seq_init(s);
+}
+
+/**
+ * trace_print_seq - move the contents of trace_seq into a seq_file
+ * @m: the seq_file descriptor that is the destination
+ * @s: the trace_seq descriptor that is the source.
+ *
+ * Returns 0 on success and non zero on error. If it succeeds to
+ * write to the seq_file it will reset the trace_seq, otherwise
+ * it does not modify the trace_seq to let the caller try again.
+ */
+int trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+	int ret;
+
+	__trace_seq_init(s);
+
+	ret = seq_buf_print_seq(m, &s->seq);
+
+	/*
+	 * Only reset this buffer if we successfully wrote to the
+	 * seq_file buffer. This lets the caller try again or
+	 * do something else with the contents.
+	 */
+	if (!ret)
+		trace_seq_init(s);
+
+	return ret;
+}
+
+/**
+ * trace_seq_printf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf() is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+void trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+	unsigned int save_len = s->seq.len;
+	va_list ap;
+
+	if (s->full)
+		return;
+
+	__trace_seq_init(s);
+
+	va_start(ap, fmt);
+	seq_buf_vprintf(&s->seq, fmt, ap);
+	va_end(ap);
+
+	/* If we can't write it all, don't bother writing anything */
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+	}
+}
+EXPORT_SYMBOL_GPL(trace_seq_printf);
+
+/**
+ * trace_seq_bitmask - write a bitmask array in its ASCII representation
+ * @s:		trace sequence descriptor
+ * @maskp:	points to an array of unsigned longs that represent a bitmask
+ * @nmaskbits:	The number of bits that are valid in @maskp
+ *
+ * Writes a ASCII representation of a bitmask string into @s.
+ */
+void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
+		      int nmaskbits)
+{
+	unsigned int save_len = s->seq.len;
+
+	if (s->full)
+		return;
+
+	__trace_seq_init(s);
+
+	seq_buf_printf(&s->seq, "%*pb", nmaskbits, maskp);
+
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+	}
+}
+EXPORT_SYMBOL_GPL(trace_seq_bitmask);
+
+/**
+ * trace_seq_vprintf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
+void trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+{
+	unsigned int save_len = s->seq.len;
+
+	if (s->full)
+		return;
+
+	__trace_seq_init(s);
+
+	seq_buf_vprintf(&s->seq, fmt, args);
+
+	/* If we can't write it all, don't bother writing anything */
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+	}
+}
+EXPORT_SYMBOL_GPL(trace_seq_vprintf);
+
+/**
+ * trace_seq_bprintf - Write the printf string from binary arguments
+ * @s: trace sequence descriptor
+ * @fmt: The format string for the @binary arguments
+ * @binary: The binary arguments for @fmt.
+ *
+ * When recording in a fast path, a printf may be recorded with just
+ * saving the format and the arguments as they were passed to the
+ * function, instead of wasting cycles converting the arguments into
+ * ASCII characters. Instead, the arguments are saved in a 32 bit
+ * word array that is defined by the format string constraints.
+ *
+ * This function will take the format and the binary array and finish
+ * the conversion into the ASCII string within the buffer.
+ */
+void trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+{
+	unsigned int save_len = s->seq.len;
+
+	if (s->full)
+		return;
+
+	__trace_seq_init(s);
+
+	seq_buf_bprintf(&s->seq, fmt, binary);
+
+	/* If we can't write it all, don't bother writing anything */
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+		return;
+	}
+}
+EXPORT_SYMBOL_GPL(trace_seq_bprintf);
+
+/**
+ * trace_seq_puts - trace sequence printing of simple string
+ * @s: trace sequence descriptor
+ * @str: simple string to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple string
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ */
+void trace_seq_puts(struct trace_seq *s, const char *str)
+{
+	unsigned int len = strlen(str);
+
+	if (s->full)
+		return;
+
+	__trace_seq_init(s);
+
+	if (len > TRACE_SEQ_BUF_LEFT(s)) {
+		s->full = 1;
+		return;
+	}
+
+	seq_buf_putmem(&s->seq, str, len);
+}
+EXPORT_SYMBOL_GPL(trace_seq_puts);
+
+/**
+ * trace_seq_putc - trace sequence printing of simple character
+ * @s: trace sequence descriptor
+ * @c: simple character to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple charater
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ */
+void trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+	if (s->full)
+		return;
+
+	__trace_seq_init(s);
+
+	if (TRACE_SEQ_BUF_LEFT(s) < 1) {
+		s->full = 1;
+		return;
+	}
+
+	seq_buf_putc(&s->seq, c);
+}
+EXPORT_SYMBOL_GPL(trace_seq_putc);
+
+/**
+ * trace_seq_putmem - write raw data into the trace_seq buffer
+ * @s: trace sequence descriptor
+ * @mem: The raw memory to copy into the buffer
+ * @len: The length of the raw memory to copy (in bytes)
+ *
+ * There may be cases where raw memory needs to be written into the
+ * buffer and a strcpy() would not work. Using this function allows
+ * for such cases.
+ */
+void trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len)
+{
+	if (s->full)
+		return;
+
+	__trace_seq_init(s);
+
+	if (len > TRACE_SEQ_BUF_LEFT(s)) {
+		s->full = 1;
+		return;
+	}
+
+	seq_buf_putmem(&s->seq, mem, len);
+}
+EXPORT_SYMBOL_GPL(trace_seq_putmem);
+
+/**
+ * trace_seq_putmem_hex - write raw memory into the buffer in ASCII hex
+ * @s: trace sequence descriptor
+ * @mem: The raw memory to write its hex ASCII representation of
+ * @len: The length of the raw memory to copy (in bytes)
+ *
+ * This is similar to trace_seq_putmem() except instead of just copying the
+ * raw memory into the buffer it writes its ASCII representation of it
+ * in hex characters.
+ */
+void trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+			 unsigned int len)
+{
+	unsigned int save_len = s->seq.len;
+
+	if (s->full)
+		return;
+
+	__trace_seq_init(s);
+
+	/* Each byte is represented by two chars */
+	if (len * 2 > TRACE_SEQ_BUF_LEFT(s)) {
+		s->full = 1;
+		return;
+	}
+
+	/* The added spaces can still cause an overflow */
+	seq_buf_putmem_hex(&s->seq, mem, len);
+
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+		return;
+	}
+}
+EXPORT_SYMBOL_GPL(trace_seq_putmem_hex);
+
+/**
+ * trace_seq_path - copy a path into the sequence buffer
+ * @s: trace sequence descriptor
+ * @path: path to write into the sequence buffer.
+ *
+ * Write a path name into the sequence buffer.
+ *
+ * Returns 1 if we successfully written all the contents to
+ *   the buffer.
+ * Returns 0 if we the length to write is bigger than the
+ *   reserved buffer space. In this case, nothing gets written.
+ */
+int trace_seq_path(struct trace_seq *s, const struct path *path)
+{
+	unsigned int save_len = s->seq.len;
+
+	if (s->full)
+		return 0;
+
+	__trace_seq_init(s);
+
+	if (TRACE_SEQ_BUF_LEFT(s) < 1) {
+		s->full = 1;
+		return 0;
+	}
+
+	seq_buf_path(&s->seq, path, "\n");
+
+	if (unlikely(seq_buf_has_overflowed(&s->seq))) {
+		s->seq.len = save_len;
+		s->full = 1;
+		return 0;
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(trace_seq_path);
+
+/**
+ * trace_seq_to_user - copy the squence buffer to user space
+ * @s: trace sequence descriptor
+ * @ubuf: The userspace memory location to copy to
+ * @cnt: The amount to copy
+ *
+ * Copies the sequence buffer into the userspace memory pointed to
+ * by @ubuf. It starts from the last read position (@s->readpos)
+ * and writes up to @cnt characters or till it reaches the end of
+ * the content in the buffer (@s->len), which ever comes first.
+ *
+ * On success, it returns a positive number of the number of bytes
+ * it copied.
+ *
+ * On failure it returns -EBUSY if all of the content in the
+ * sequence has been already read, which includes nothing in the
+ * sequenc (@s->len == @s->readpos).
+ *
+ * Returns -EFAULT if the copy to userspace fails.
+ */
+int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt)
+{
+	__trace_seq_init(s);
+	return seq_buf_to_user(&s->seq, ubuf, cnt);
+}
+EXPORT_SYMBOL_GPL(trace_seq_to_user);

kernel/trace/trace_stack.c

@@ -0,0 +1,493 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+#include <linux/init.h>
+
+#include <asm/setup.h>
+
+#include "trace.h"
+
+static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
+	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
+unsigned stack_trace_index[STACK_TRACE_ENTRIES];
+
+/*
+ * Reserve one entry for the passed in ip. This will allow
+ * us to remove most or all of the stack size overhead
+ * added by the stack tracer itself.
+ */
+struct stack_trace stack_trace_max = {
+	.max_entries		= STACK_TRACE_ENTRIES - 1,
+	.entries		= &stack_dump_trace[0],
+};
+
+unsigned long stack_trace_max_size;
+arch_spinlock_t stack_trace_max_lock =
+	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+DEFINE_PER_CPU(int, disable_stack_tracer);
+static DEFINE_MUTEX(stack_sysctl_mutex);
+
+int stack_tracer_enabled;
+static int last_stack_tracer_enabled;
+
+void stack_trace_print(void)
+{
+	long i;
+	int size;
+
+	pr_emerg("        Depth    Size   Location    (%d entries)\n"
+			   "        -----    ----   --------\n",
+			   stack_trace_max.nr_entries);
+
+	for (i = 0; i < stack_trace_max.nr_entries; i++) {
+		if (stack_dump_trace[i] == ULONG_MAX)
+			break;
+		if (i+1 == stack_trace_max.nr_entries ||
+				stack_dump_trace[i+1] == ULONG_MAX)
+			size = stack_trace_index[i];
+		else
+			size = stack_trace_index[i] - stack_trace_index[i+1];
+
+		pr_emerg("%3ld) %8d   %5d   %pS\n", i, stack_trace_index[i],
+				size, (void *)stack_dump_trace[i]);
+	}
+}
+
+/*
+ * When arch-specific code overrides this function, the following
+ * data should be filled up, assuming stack_trace_max_lock is held to
+ * prevent concurrent updates.
+ *     stack_trace_index[]
+ *     stack_trace_max
+ *     stack_trace_max_size
+ */
+void __weak
+check_stack(unsigned long ip, unsigned long *stack)
+{
+	unsigned long this_size, flags; unsigned long *p, *top, *start;
+	static int tracer_frame;
+	int frame_size = READ_ONCE(tracer_frame);
+	int i, x;
+
+	this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
+	this_size = THREAD_SIZE - this_size;
+	/* Remove the frame of the tracer */
+	this_size -= frame_size;
+
+	if (this_size <= stack_trace_max_size)
+		return;
+
+	/* we do not handle interrupt stacks yet */
+	if (!object_is_on_stack(stack))
+		return;
+
+	/* Can't do this from NMI context (can cause deadlocks) */
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+	arch_spin_lock(&stack_trace_max_lock);
+
+	/* In case another CPU set the tracer_frame on us */
+	if (unlikely(!frame_size))
+		this_size -= tracer_frame;
+
+	/* a race could have already updated it */
+	if (this_size <= stack_trace_max_size)
+		goto out;
+
+	stack_trace_max_size = this_size;
+
+	stack_trace_max.nr_entries = 0;
+	stack_trace_max.skip = 3;
+
+	save_stack_trace(&stack_trace_max);
+
+	/* Skip over the overhead of the stack tracer itself */
+	for (i = 0; i < stack_trace_max.nr_entries; i++) {
+		if (stack_dump_trace[i] == ip)
+			break;
+	}
+
+	/*
+	 * Some archs may not have the passed in ip in the dump.
+	 * If that happens, we need to show everything.
+	 */
+	if (i == stack_trace_max.nr_entries)
+		i = 0;
+
+	/*
+	 * Now find where in the stack these are.
+	 */
+	x = 0;
+	start = stack;
+	top = (unsigned long *)
+		(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
+
+	/*
+	 * Loop through all the entries. One of the entries may
+	 * for some reason be missed on the stack, so we may
+	 * have to account for them. If they are all there, this
+	 * loop will only happen once. This code only takes place
+	 * on a new max, so it is far from a fast path.
+	 */
+	while (i < stack_trace_max.nr_entries) {
+		int found = 0;
+
+		stack_trace_index[x] = this_size;
+		p = start;
+
+		for (; p < top && i < stack_trace_max.nr_entries; p++) {
+			if (stack_dump_trace[i] == ULONG_MAX)
+				break;
+			/*
+			 * The READ_ONCE_NOCHECK is used to let KASAN know that
+			 * this is not a stack-out-of-bounds error.
+			 */
+			if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) {
+				stack_dump_trace[x] = stack_dump_trace[i++];
+				this_size = stack_trace_index[x++] =
+					(top - p) * sizeof(unsigned long);
+				found = 1;
+				/* Start the search from here */
+				start = p + 1;
+				/*
+				 * We do not want to show the overhead
+				 * of the stack tracer stack in the
+				 * max stack. If we haven't figured
+				 * out what that is, then figure it out
+				 * now.
+				 */
+				if (unlikely(!tracer_frame)) {
+					tracer_frame = (p - stack) *
+						sizeof(unsigned long);
+					stack_trace_max_size -= tracer_frame;
+				}
+			}
+		}
+
+		if (!found)
+			i++;
+	}
+
+	stack_trace_max.nr_entries = x;
+	for (; x < i; x++)
+		stack_dump_trace[x] = ULONG_MAX;
+
+	if (task_stack_end_corrupted(current)) {
+		stack_trace_print();
+		BUG();
+	}
+
+ out:
+	arch_spin_unlock(&stack_trace_max_lock);
+	local_irq_restore(flags);
+}
+
+/* Some archs may not define MCOUNT_INSN_SIZE */
+#ifndef MCOUNT_INSN_SIZE
+# define MCOUNT_INSN_SIZE 0
+#endif
+
+static void
+stack_trace_call(unsigned long ip, unsigned long parent_ip,
+		 struct ftrace_ops *op, struct pt_regs *pt_regs)
+{
+	unsigned long stack;
+
+	preempt_disable_notrace();
+
+	/* no atomic needed, we only modify this variable by this cpu */
+	__this_cpu_inc(disable_stack_tracer);
+	if (__this_cpu_read(disable_stack_tracer) != 1)
+		goto out;
+
+	/* If rcu is not watching, then save stack trace can fail */
+	if (!rcu_is_watching())
+		goto out;
+
+	ip += MCOUNT_INSN_SIZE;
+
+	check_stack(ip, &stack);
+
+ out:
+	__this_cpu_dec(disable_stack_tracer);
+	/* prevent recursion in schedule */
+	preempt_enable_notrace();
+}
+
+static struct ftrace_ops trace_ops __read_mostly =
+{
+	.func = stack_trace_call,
+	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
+static ssize_t
+stack_max_size_read(struct file *filp, char __user *ubuf,
+		    size_t count, loff_t *ppos)
+{
+	unsigned long *ptr = filp->private_data;
+	char buf[64];
+	int r;
+
+	r = snprintf(buf, sizeof(buf), "%ld\n", *ptr);
+	if (r > sizeof(buf))
+		r = sizeof(buf);
+	return simple_read_from_buffer(ubuf, count, ppos, buf, r);
+}
+
+static ssize_t
+stack_max_size_write(struct file *filp, const char __user *ubuf,
+		     size_t count, loff_t *ppos)
+{
+	long *ptr = filp->private_data;
+	unsigned long val, flags;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, count, 10, &val);
+	if (ret)
+		return ret;
+
+	local_irq_save(flags);
+
+	/*
+	 * In case we trace inside arch_spin_lock() or after (NMI),
+	 * we will cause circular lock, so we also need to increase
+	 * the percpu disable_stack_tracer here.
+	 */
+	__this_cpu_inc(disable_stack_tracer);
+
+	arch_spin_lock(&stack_trace_max_lock);
+	*ptr = val;
+	arch_spin_unlock(&stack_trace_max_lock);
+
+	__this_cpu_dec(disable_stack_tracer);
+	local_irq_restore(flags);
+
+	return count;
+}
+
+static const struct file_operations stack_max_size_fops = {
+	.open		= tracing_open_generic,
+	.read		= stack_max_size_read,
+	.write		= stack_max_size_write,
+	.llseek		= default_llseek,
+};
+
+static void *
+__next(struct seq_file *m, loff_t *pos)
+{
+	long n = *pos - 1;
+
+	if (n > stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX)
+		return NULL;
+
+	m->private = (void *)n;
+	return &m->private;
+}
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return __next(m, pos);
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+	local_irq_disable();
+
+	__this_cpu_inc(disable_stack_tracer);
+
+	arch_spin_lock(&stack_trace_max_lock);
+
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
+	return __next(m, pos);
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+	arch_spin_unlock(&stack_trace_max_lock);
+
+	__this_cpu_dec(disable_stack_tracer);
+
+	local_irq_enable();
+}
+
+static void trace_lookup_stack(struct seq_file *m, long i)
+{
+	unsigned long addr = stack_dump_trace[i];
+
+	seq_printf(m, "%pS\n", (void *)addr);
+}
+
+static void print_disabled(struct seq_file *m)
+{
+	seq_puts(m, "#\n"
+		 "#  Stack tracer disabled\n"
+		 "#\n"
+		 "# To enable the stack tracer, either add 'stacktrace' to the\n"
+		 "# kernel command line\n"
+		 "# or 'echo 1 > /proc/sys/kernel/stack_tracer_enabled'\n"
+		 "#\n");
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+	long i;
+	int size;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_printf(m, "        Depth    Size   Location"
+			   "    (%d entries)\n"
+			   "        -----    ----   --------\n",
+			   stack_trace_max.nr_entries);
+
+		if (!stack_tracer_enabled && !stack_trace_max_size)
+			print_disabled(m);
+
+		return 0;
+	}
+
+	i = *(long *)v;
+
+	if (i >= stack_trace_max.nr_entries ||
+	    stack_dump_trace[i] == ULONG_MAX)
+		return 0;
+
+	if (i+1 == stack_trace_max.nr_entries ||
+	    stack_dump_trace[i+1] == ULONG_MAX)
+		size = stack_trace_index[i];
+	else
+		size = stack_trace_index[i] - stack_trace_index[i+1];
+
+	seq_printf(m, "%3ld) %8d   %5d   ", i, stack_trace_index[i], size);
+
+	trace_lookup_stack(m, i);
+
+	return 0;
+}
+
+static const struct seq_operations stack_trace_seq_ops = {
+	.start		= t_start,
+	.next		= t_next,
+	.stop		= t_stop,
+	.show		= t_show,
+};
+
+static int stack_trace_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &stack_trace_seq_ops);
+}
+
+static const struct file_operations stack_trace_fops = {
+	.open		= stack_trace_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+static int
+stack_trace_filter_open(struct inode *inode, struct file *file)
+{
+	struct ftrace_ops *ops = inode->i_private;
+
+	return ftrace_regex_open(ops, FTRACE_ITER_FILTER,
+				 inode, file);
+}
+
+static const struct file_operations stack_trace_filter_fops = {
+	.open = stack_trace_filter_open,
+	.read = seq_read,
+	.write = ftrace_filter_write,
+	.llseek = tracing_lseek,
+	.release = ftrace_regex_release,
+};
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+int
+stack_trace_sysctl(struct ctl_table *table, int write,
+		   void __user *buffer, size_t *lenp,
+		   loff_t *ppos)
+{
+	int ret;
+
+	mutex_lock(&stack_sysctl_mutex);
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (ret || !write ||
+	    (last_stack_tracer_enabled == !!stack_tracer_enabled))
+		goto out;
+
+	last_stack_tracer_enabled = !!stack_tracer_enabled;
+
+	if (stack_tracer_enabled)
+		register_ftrace_function(&trace_ops);
+	else
+		unregister_ftrace_function(&trace_ops);
+
+ out:
+	mutex_unlock(&stack_sysctl_mutex);
+	return ret;
+}
+
+static char stack_trace_filter_buf[COMMAND_LINE_SIZE+1] __initdata;
+
+static __init int enable_stacktrace(char *str)
+{
+	if (strncmp(str, "_filter=", 8) == 0)
+		strncpy(stack_trace_filter_buf, str+8, COMMAND_LINE_SIZE);
+
+	stack_tracer_enabled = 1;
+	last_stack_tracer_enabled = 1;
+	return 1;
+}
+__setup("stacktrace", enable_stacktrace);
+
+static __init int stack_trace_init(void)
+{
+	struct dentry *d_tracer;
+
+	d_tracer = tracing_init_dentry();
+	if (IS_ERR(d_tracer))
+		return 0;
+
+	trace_create_file("stack_max_size", 0644, d_tracer,
+			&stack_trace_max_size, &stack_max_size_fops);
+
+	trace_create_file("stack_trace", 0444, d_tracer,
+			NULL, &stack_trace_fops);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+	trace_create_file("stack_trace_filter", 0644, d_tracer,
+			  &trace_ops, &stack_trace_filter_fops);
+#endif
+
+	if (stack_trace_filter_buf[0])
+		ftrace_set_early_filter(&trace_ops, stack_trace_filter_buf, 1);
+
+	if (stack_tracer_enabled)
+		register_ftrace_function(&trace_ops);
+
+	return 0;
+}
+
+device_initcall(stack_trace_init);

kernel/trace/trace_stat.c

@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Infrastructure for statistic tracing (histogram output).
+ *
+ * Copyright (C) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ * Based on the code from trace_branch.c which is
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/rbtree.h>
+#include <linux/tracefs.h>
+#include "trace_stat.h"
+#include "trace.h"
+
+
+/*
+ * List of stat red-black nodes from a tracer
+ * We use a such tree to sort quickly the stat
+ * entries from the tracer.
+ */
+struct stat_node {
+	struct rb_node		node;
+	void			*stat;
+};
+
+/* A stat session is the stats output in one file */
+struct stat_session {
+	struct list_head	session_list;
+	struct tracer_stat	*ts;
+	struct rb_root		stat_root;
+	struct mutex		stat_mutex;
+	struct dentry		*file;
+};
+
+/* All of the sessions currently in use. Each stat file embed one session */
+static LIST_HEAD(all_stat_sessions);
+static DEFINE_MUTEX(all_stat_sessions_mutex);
+
+/* The root directory for all stat files */
+static struct dentry		*stat_dir;
+
+static void __reset_stat_session(struct stat_session *session)
+{
+	struct stat_node *snode, *n;
+
+	rbtree_postorder_for_each_entry_safe(snode, n, &session->stat_root, node) {
+		if (session->ts->stat_release)
+			session->ts->stat_release(snode->stat);
+		kfree(snode);
+	}
+
+	session->stat_root = RB_ROOT;
+}
+
+static void reset_stat_session(struct stat_session *session)
+{
+	mutex_lock(&session->stat_mutex);
+	__reset_stat_session(session);
+	mutex_unlock(&session->stat_mutex);
+}
+
+static void destroy_session(struct stat_session *session)
+{
+	tracefs_remove(session->file);
+	__reset_stat_session(session);
+	mutex_destroy(&session->stat_mutex);
+	kfree(session);
+}
+
+typedef int (*cmp_stat_t)(void *, void *);
+
+static int insert_stat(struct rb_root *root, void *stat, cmp_stat_t cmp)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct stat_node *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	data->stat = stat;
+
+	/*
+	 * Figure out where to put new node
+	 * This is a descendent sorting
+	 */
+	while (*new) {
+		struct stat_node *this;
+		int result;
+
+		this = container_of(*new, struct stat_node, node);
+		result = cmp(data->stat, this->stat);
+
+		parent = *new;
+		if (result >= 0)
+			new = &((*new)->rb_left);
+		else
+			new = &((*new)->rb_right);
+	}
+
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+	return 0;
+}
+
+/*
+ * For tracers that don't provide a stat_cmp callback.
+ * This one will force an insertion as right-most node
+ * in the rbtree.
+ */
+static int dummy_cmp(void *p1, void *p2)
+{
+	return -1;
+}
+
+/*
+ * Initialize the stat rbtree at each trace_stat file opening.
+ * All of these copies and sorting are required on all opening
+ * since the stats could have changed between two file sessions.
+ */
+static int stat_seq_init(struct stat_session *session)
+{
+	struct tracer_stat *ts = session->ts;
+	struct rb_root *root = &session->stat_root;
+	void *stat;
+	int ret = 0;
+	int i;
+
+	mutex_lock(&session->stat_mutex);
+	__reset_stat_session(session);
+
+	if (!ts->stat_cmp)
+		ts->stat_cmp = dummy_cmp;
+
+	stat = ts->stat_start(ts);
+	if (!stat)
+		goto exit;
+
+	ret = insert_stat(root, stat, ts->stat_cmp);
+	if (ret)
+		goto exit;
+
+	/*
+	 * Iterate over the tracer stat entries and store them in an rbtree.
+	 */
+	for (i = 1; ; i++) {
+		stat = ts->stat_next(stat, i);
+
+		/* End of insertion */
+		if (!stat)
+			break;
+
+		ret = insert_stat(root, stat, ts->stat_cmp);
+		if (ret)
+			goto exit_free_rbtree;
+	}
+
+exit:
+	mutex_unlock(&session->stat_mutex);
+	return ret;
+
+exit_free_rbtree:
+	__reset_stat_session(session);
+	mutex_unlock(&session->stat_mutex);
+	return ret;
+}
+
+
+static void *stat_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct stat_session *session = s->private;
+	struct rb_node *node;
+	int n = *pos;
+	int i;
+
+	/* Prevent from tracer switch or rbtree modification */
+	mutex_lock(&session->stat_mutex);
+
+	/* If we are in the beginning of the file, print the headers */
+	if (session->ts->stat_headers) {
+		if (n == 0)
+			return SEQ_START_TOKEN;
+		n--;
+	}
+
+	node = rb_first(&session->stat_root);
+	for (i = 0; node && i < n; i++)
+		node = rb_next(node);
+
+	return node;
+}
+
+static void *stat_seq_next(struct seq_file *s, void *p, loff_t *pos)
+{
+	struct stat_session *session = s->private;
+	struct rb_node *node = p;
+
+	(*pos)++;
+
+	if (p == SEQ_START_TOKEN)
+		return rb_first(&session->stat_root);
+
+	return rb_next(node);
+}
+
+static void stat_seq_stop(struct seq_file *s, void *p)
+{
+	struct stat_session *session = s->private;
+	mutex_unlock(&session->stat_mutex);
+}
+
+static int stat_seq_show(struct seq_file *s, void *v)
+{
+	struct stat_session *session = s->private;
+	struct stat_node *l = container_of(v, struct stat_node, node);
+
+	if (v == SEQ_START_TOKEN)
+		return session->ts->stat_headers(s);
+
+	return session->ts->stat_show(s, l->stat);
+}
+
+static const struct seq_operations trace_stat_seq_ops = {
+	.start		= stat_seq_start,
+	.next		= stat_seq_next,
+	.stop		= stat_seq_stop,
+	.show		= stat_seq_show
+};
+
+/* The session stat is refilled and resorted at each stat file opening */
+static int tracing_stat_open(struct inode *inode, struct file *file)
+{
+	int ret;
+	struct seq_file *m;
+	struct stat_session *session = inode->i_private;
+
+	ret = stat_seq_init(session);
+	if (ret)
+		return ret;
+
+	ret = seq_open(file, &trace_stat_seq_ops);
+	if (ret) {
+		reset_stat_session(session);
+		return ret;
+	}
+
+	m = file->private_data;
+	m->private = session;
+	return ret;
+}
+
+/*
+ * Avoid consuming memory with our now useless rbtree.
+ */
+static int tracing_stat_release(struct inode *i, struct file *f)
+{
+	struct stat_session *session = i->i_private;
+
+	reset_stat_session(session);
+
+	return seq_release(i, f);
+}
+
+static const struct file_operations tracing_stat_fops = {
+	.open		= tracing_stat_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= tracing_stat_release
+};
+
+static int tracing_stat_init(void)
+{
+	struct dentry *d_tracing;
+
+	d_tracing = tracing_init_dentry();
+	if (IS_ERR(d_tracing))
+		return -ENODEV;
+
+	stat_dir = tracefs_create_dir("trace_stat", d_tracing);
+	if (!stat_dir) {
+		pr_warn("Could not create tracefs 'trace_stat' entry\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static int init_stat_file(struct stat_session *session)
+{
+	int ret;
+
+	if (!stat_dir && (ret = tracing_stat_init()))
+		return ret;
+
+	session->file = tracefs_create_file(session->ts->name, 0644,
+					    stat_dir,
+					    session, &tracing_stat_fops);
+	if (!session->file)
+		return -ENOMEM;
+	return 0;
+}
+
+int register_stat_tracer(struct tracer_stat *trace)
+{
+	struct stat_session *session, *node;
+	int ret = -EINVAL;
+
+	if (!trace)
+		return -EINVAL;
+
+	if (!trace->stat_start || !trace->stat_next || !trace->stat_show)
+		return -EINVAL;
+
+	/* Already registered? */
+	mutex_lock(&all_stat_sessions_mutex);
+	list_for_each_entry(node, &all_stat_sessions, session_list) {
+		if (node->ts == trace)
+			goto out;
+	}
+
+	ret = -ENOMEM;
+	/* Init the session */
+	session = kzalloc(sizeof(*session), GFP_KERNEL);
+	if (!session)
+		goto out;
+
+	session->ts = trace;
+	INIT_LIST_HEAD(&session->session_list);
+	mutex_init(&session->stat_mutex);
+
+	ret = init_stat_file(session);
+	if (ret) {
+		destroy_session(session);
+		goto out;
+	}
+
+	ret = 0;
+	/* Register */
+	list_add_tail(&session->session_list, &all_stat_sessions);
+ out:
+	mutex_unlock(&all_stat_sessions_mutex);
+
+	return ret;
+}
+
+void unregister_stat_tracer(struct tracer_stat *trace)
+{
+	struct stat_session *node, *tmp;
+
+	mutex_lock(&all_stat_sessions_mutex);
+	list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) {
+		if (node->ts == trace) {
+			list_del(&node->session_list);
+			destroy_session(node);
+			break;
+		}
+	}
+	mutex_unlock(&all_stat_sessions_mutex);
+}

kernel/trace/trace_stat.h

@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __TRACE_STAT_H
+#define __TRACE_STAT_H
+
+#include <linux/seq_file.h>
+
+/*
+ * If you want to provide a stat file (one-shot statistics), fill
+ * an iterator with stat_start/stat_next and a stat_show callbacks.
+ * The others callbacks are optional.
+ */
+struct tracer_stat {
+	/* The name of your stat file */
+	const char		*name;
+	/* Iteration over statistic entries */
+	void			*(*stat_start)(struct tracer_stat *trace);
+	void			*(*stat_next)(void *prev, int idx);
+	/* Compare two entries for stats sorting */
+	int			(*stat_cmp)(void *p1, void *p2);
+	/* Print a stat entry */
+	int			(*stat_show)(struct seq_file *s, void *p);
+	/* Release an entry */
+	void			(*stat_release)(void *stat);
+	/* Print the headers of your stat entries */
+	int			(*stat_headers)(struct seq_file *s);
+};
+
+/*
+ * Destroy or create a stat file
+ */
+extern int register_stat_tracer(struct tracer_stat *trace);
+extern void unregister_stat_tracer(struct tracer_stat *trace);
+
+#endif /* __TRACE_STAT_H */

kernel/trace/trace_syscalls.c

@@ -0,0 +1,817 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <trace/syscall.h>
+#include <trace/events/syscalls.h>
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>	/* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */
+#include <linux/ftrace.h>
+#include <linux/perf_event.h>
+#include <asm/syscall.h>
+
+#include "trace_output.h"
+#include "trace.h"
+
+static DEFINE_MUTEX(syscall_trace_lock);
+
+static int syscall_enter_register(struct trace_event_call *event,
+				 enum trace_reg type, void *data);
+static int syscall_exit_register(struct trace_event_call *event,
+				 enum trace_reg type, void *data);
+
+static struct list_head *
+syscall_get_enter_fields(struct trace_event_call *call)
+{
+	struct syscall_metadata *entry = call->data;
+
+	return &entry->enter_fields;
+}
+
+extern struct syscall_metadata *__start_syscalls_metadata[];
+extern struct syscall_metadata *__stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
+{
+	/*
+	 * Only compare after the "sys" prefix. Archs that use
+	 * syscall wrappers may have syscalls symbols aliases prefixed
+	 * with ".SyS" or ".sys" instead of "sys", leading to an unwanted
+	 * mismatch.
+	 */
+	return !strcmp(sym + 3, name + 3);
+}
+#endif
+
+#ifdef ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+/*
+ * Some architectures that allow for 32bit applications
+ * to run on a 64bit kernel, do not map the syscalls for
+ * the 32bit tasks the same as they do for 64bit tasks.
+ *
+ *     *cough*x86*cough*
+ *
+ * In such a case, instead of reporting the wrong syscalls,
+ * simply ignore them.
+ *
+ * For an arch to ignore the compat syscalls it needs to
+ * define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS as well as
+ * define the function arch_trace_is_compat_syscall() to let
+ * the tracing system know that it should ignore it.
+ */
+static int
+trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	if (unlikely(arch_trace_is_compat_syscall(regs)))
+		return -1;
+
+	return syscall_get_nr(task, regs);
+}
+#else
+static inline int
+trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	return syscall_get_nr(task, regs);
+}
+#endif /* ARCH_TRACE_IGNORE_COMPAT_SYSCALLS */
+
+static __init struct syscall_metadata *
+find_syscall_meta(unsigned long syscall)
+{
+	struct syscall_metadata **start;
+	struct syscall_metadata **stop;
+	char str[KSYM_SYMBOL_LEN];
+
+
+	start = __start_syscalls_metadata;
+	stop = __stop_syscalls_metadata;
+	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+	if (arch_syscall_match_sym_name(str, "sys_ni_syscall"))
+		return NULL;
+
+	for ( ; start < stop; start++) {
+		if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name))
+			return *start;
+	}
+	return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+		return NULL;
+
+	return syscalls_metadata[nr];
+}
+
+const char *get_syscall_name(int syscall)
+{
+	struct syscall_metadata *entry;
+
+	entry = syscall_nr_to_meta(syscall);
+	if (!entry)
+		return NULL;
+
+	return entry->name;
+}
+
+static enum print_line_t
+print_syscall_enter(struct trace_iterator *iter, int flags,
+		    struct trace_event *event)
+{
+	struct trace_array *tr = iter->tr;
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *ent = iter->ent;
+	struct syscall_trace_enter *trace;
+	struct syscall_metadata *entry;
+	int i, syscall;
+
+	trace = (typeof(trace))ent;
+	syscall = trace->nr;
+	entry = syscall_nr_to_meta(syscall);
+
+	if (!entry)
+		goto end;
+
+	if (entry->enter_event->event.type != ent->type) {
+		WARN_ON_ONCE(1);
+		goto end;
+	}
+
+	trace_seq_printf(s, "%s(", entry->name);
+
+	for (i = 0; i < entry->nb_args; i++) {
+
+		if (trace_seq_has_overflowed(s))
+			goto end;
+
+		/* parameter types */
+		if (tr->trace_flags & TRACE_ITER_VERBOSE)
+			trace_seq_printf(s, "%s ", entry->types[i]);
+
+		/* parameter values */
+		trace_seq_printf(s, "%s: %lx%s", entry->args[i],
+				 trace->args[i],
+				 i == entry->nb_args - 1 ? "" : ", ");
+	}
+
+	trace_seq_putc(s, ')');
+end:
+	trace_seq_putc(s, '\n');
+
+	return trace_handle_return(s);
+}
+
+static enum print_line_t
+print_syscall_exit(struct trace_iterator *iter, int flags,
+		   struct trace_event *event)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *ent = iter->ent;
+	struct syscall_trace_exit *trace;
+	int syscall;
+	struct syscall_metadata *entry;
+
+	trace = (typeof(trace))ent;
+	syscall = trace->nr;
+	entry = syscall_nr_to_meta(syscall);
+
+	if (!entry) {
+		trace_seq_putc(s, '\n');
+		goto out;
+	}
+
+	if (entry->exit_event->event.type != ent->type) {
+		WARN_ON_ONCE(1);
+		return TRACE_TYPE_UNHANDLED;
+	}
+
+	trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
+				trace->ret);
+
+ out:
+	return trace_handle_return(s);
+}
+
+extern char *__bad_type_size(void);
+
+#define SYSCALL_FIELD(type, field, name)				\
+	sizeof(type) != sizeof(trace.field) ?				\
+		__bad_type_size() :					\
+		#type, #name, offsetof(typeof(trace), field),		\
+		sizeof(trace.field), is_signed_type(type)
+
+static int __init
+__set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
+{
+	int i;
+	int pos = 0;
+
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+	for (i = 0; i < entry->nb_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
+				entry->args[i], sizeof(unsigned long),
+				i == entry->nb_args - 1 ? "" : ", ");
+	}
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+	for (i = 0; i < entry->nb_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO,
+				", ((unsigned long)(REC->%s))", entry->args[i]);
+	}
+
+#undef LEN_OR_ZERO
+
+	/* return the length of print_fmt */
+	return pos;
+}
+
+static int __init set_syscall_print_fmt(struct trace_event_call *call)
+{
+	char *print_fmt;
+	int len;
+	struct syscall_metadata *entry = call->data;
+
+	if (entry->enter_event != call) {
+		call->print_fmt = "\"0x%lx\", REC->ret";
+		return 0;
+	}
+
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_enter_print_fmt(entry, NULL, 0);
+
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
+
+	/* Second: actually write the @print_fmt */
+	__set_enter_print_fmt(entry, print_fmt, len + 1);
+	call->print_fmt = print_fmt;
+
+	return 0;
+}
+
+static void __init free_syscall_print_fmt(struct trace_event_call *call)
+{
+	struct syscall_metadata *entry = call->data;
+
+	if (entry->enter_event == call)
+		kfree(call->print_fmt);
+}
+
+static int __init syscall_enter_define_fields(struct trace_event_call *call)
+{
+	struct syscall_trace_enter trace;
+	struct syscall_metadata *meta = call->data;
+	int ret;
+	int i;
+	int offset = offsetof(typeof(trace), args);
+
+	ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
+				 FILTER_OTHER);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < meta->nb_args; i++) {
+		ret = trace_define_field(call, meta->types[i],
+					 meta->args[i], offset,
+					 sizeof(unsigned long), 0,
+					 FILTER_OTHER);
+		offset += sizeof(unsigned long);
+	}
+
+	return ret;
+}
+
+static int __init syscall_exit_define_fields(struct trace_event_call *call)
+{
+	struct syscall_trace_exit trace;
+	int ret;
+
+	ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
+				 FILTER_OTHER);
+	if (ret)
+		return ret;
+
+	ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret),
+				 FILTER_OTHER);
+
+	return ret;
+}
+
+static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
+{
+	struct trace_array *tr = data;
+	struct trace_event_file *trace_file;
+	struct syscall_trace_enter *entry;
+	struct syscall_metadata *sys_data;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	unsigned long irq_flags;
+	int pc;
+	int syscall_nr;
+	int size;
+
+	syscall_nr = trace_get_syscall_nr(current, regs);
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
+		return;
+
+	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
+	trace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
+	if (!trace_file)
+		return;
+
+	if (trace_trigger_soft_disabled(trace_file))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
+
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
+	buffer = tr->trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer,
+			sys_data->enter_event->event.type, size, irq_flags, pc);
+	if (!event)
+		return;
+
+	entry = ring_buffer_event_data(event);
+	entry->nr = syscall_nr;
+	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
+
+	event_trigger_unlock_commit(trace_file, buffer, event, entry,
+				    irq_flags, pc);
+}
+
+static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
+{
+	struct trace_array *tr = data;
+	struct trace_event_file *trace_file;
+	struct syscall_trace_exit *entry;
+	struct syscall_metadata *sys_data;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	unsigned long irq_flags;
+	int pc;
+	int syscall_nr;
+
+	syscall_nr = trace_get_syscall_nr(current, regs);
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
+		return;
+
+	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
+	trace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
+	if (!trace_file)
+		return;
+
+	if (trace_trigger_soft_disabled(trace_file))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
+	buffer = tr->trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer,
+			sys_data->exit_event->event.type, sizeof(*entry),
+			irq_flags, pc);
+	if (!event)
+		return;
+
+	entry = ring_buffer_event_data(event);
+	entry->nr = syscall_nr;
+	entry->ret = syscall_get_return_value(current, regs);
+
+	event_trigger_unlock_commit(trace_file, buffer, event, entry,
+				    irq_flags, pc);
+}
+
+static int reg_event_syscall_enter(struct trace_event_file *file,
+				   struct trace_event_call *call)
+{
+	struct trace_array *tr = file->tr;
+	int ret = 0;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
+		return -ENOSYS;
+	mutex_lock(&syscall_trace_lock);
+	if (!tr->sys_refcount_enter)
+		ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
+	if (!ret) {
+		rcu_assign_pointer(tr->enter_syscall_files[num], file);
+		tr->sys_refcount_enter++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+static void unreg_event_syscall_enter(struct trace_event_file *file,
+				      struct trace_event_call *call)
+{
+	struct trace_array *tr = file->tr;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
+		return;
+	mutex_lock(&syscall_trace_lock);
+	tr->sys_refcount_enter--;
+	RCU_INIT_POINTER(tr->enter_syscall_files[num], NULL);
+	if (!tr->sys_refcount_enter)
+		unregister_trace_sys_enter(ftrace_syscall_enter, tr);
+	mutex_unlock(&syscall_trace_lock);
+}
+
+static int reg_event_syscall_exit(struct trace_event_file *file,
+				  struct trace_event_call *call)
+{
+	struct trace_array *tr = file->tr;
+	int ret = 0;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
+		return -ENOSYS;
+	mutex_lock(&syscall_trace_lock);
+	if (!tr->sys_refcount_exit)
+		ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
+	if (!ret) {
+		rcu_assign_pointer(tr->exit_syscall_files[num], file);
+		tr->sys_refcount_exit++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+static void unreg_event_syscall_exit(struct trace_event_file *file,
+				     struct trace_event_call *call)
+{
+	struct trace_array *tr = file->tr;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
+		return;
+	mutex_lock(&syscall_trace_lock);
+	tr->sys_refcount_exit--;
+	RCU_INIT_POINTER(tr->exit_syscall_files[num], NULL);
+	if (!tr->sys_refcount_exit)
+		unregister_trace_sys_exit(ftrace_syscall_exit, tr);
+	mutex_unlock(&syscall_trace_lock);
+}
+
+static int __init init_syscall_trace(struct trace_event_call *call)
+{
+	int id;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+	if (num < 0 || num >= NR_syscalls) {
+		pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
+				((struct syscall_metadata *)call->data)->name);
+		return -ENOSYS;
+	}
+
+	if (set_syscall_print_fmt(call) < 0)
+		return -ENOMEM;
+
+	id = trace_event_raw_init(call);
+
+	if (id < 0) {
+		free_syscall_print_fmt(call);
+		return id;
+	}
+
+	return id;
+}
+
+struct trace_event_functions enter_syscall_print_funcs = {
+	.trace		= print_syscall_enter,
+};
+
+struct trace_event_functions exit_syscall_print_funcs = {
+	.trace		= print_syscall_exit,
+};
+
+struct trace_event_class __refdata event_class_syscall_enter = {
+	.system		= "syscalls",
+	.reg		= syscall_enter_register,
+	.define_fields	= syscall_enter_define_fields,
+	.get_fields	= syscall_get_enter_fields,
+	.raw_init	= init_syscall_trace,
+};
+
+struct trace_event_class __refdata event_class_syscall_exit = {
+	.system		= "syscalls",
+	.reg		= syscall_exit_register,
+	.define_fields	= syscall_exit_define_fields,
+	.fields		= LIST_HEAD_INIT(event_class_syscall_exit.fields),
+	.raw_init	= init_syscall_trace,
+};
+
+unsigned long __init __weak arch_syscall_addr(int nr)
+{
+	return (unsigned long)sys_call_table[nr];
+}
+
+void __init init_ftrace_syscalls(void)
+{
+	struct syscall_metadata *meta;
+	unsigned long addr;
+	int i;
+
+	syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata),
+				    GFP_KERNEL);
+	if (!syscalls_metadata) {
+		WARN_ON(1);
+		return;
+	}
+
+	for (i = 0; i < NR_syscalls; i++) {
+		addr = arch_syscall_addr(i);
+		meta = find_syscall_meta(addr);
+		if (!meta)
+			continue;
+
+		meta->syscall_nr = i;
+		syscalls_metadata[i] = meta;
+	}
+}
+
+#ifdef CONFIG_PERF_EVENTS
+
+static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
+static int sys_perf_refcount_enter;
+static int sys_perf_refcount_exit;
+
+static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *regs,
+			       struct syscall_metadata *sys_data,
+			       struct syscall_trace_enter *rec)
+{
+	struct syscall_tp_t {
+		unsigned long long regs;
+		unsigned long syscall_nr;
+		unsigned long args[SYSCALL_DEFINE_MAXARGS];
+	} param;
+	int i;
+
+	*(struct pt_regs **)&param = regs;
+	param.syscall_nr = rec->nr;
+	for (i = 0; i < sys_data->nb_args; i++)
+		param.args[i] = rec->args[i];
+	return trace_call_bpf(call, &param);
+}
+
+static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
+{
+	struct syscall_metadata *sys_data;
+	struct syscall_trace_enter *rec;
+	struct hlist_head *head;
+	bool valid_prog_array;
+	int syscall_nr;
+	int rctx;
+	int size;
+
+	syscall_nr = trace_get_syscall_nr(current, regs);
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
+		return;
+	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	head = this_cpu_ptr(sys_data->enter_event->perf_events);
+	valid_prog_array = bpf_prog_array_valid(sys_data->enter_event);
+	if (!valid_prog_array && hlist_empty(head))
+		return;
+
+	/* get the size after alignment with the u32 buffer size field */
+	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
+	size = ALIGN(size + sizeof(u32), sizeof(u64));
+	size -= sizeof(u32);
+
+	rec = perf_trace_buf_alloc(size, NULL, &rctx);
+	if (!rec)
+		return;
+
+	rec->nr = syscall_nr;
+	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
+			       (unsigned long *)&rec->args);
+
+	if ((valid_prog_array &&
+	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
+	    hlist_empty(head)) {
+		perf_swevent_put_recursion_context(rctx);
+		return;
+	}
+
+	perf_trace_buf_submit(rec, size, rctx,
+			      sys_data->enter_event->event.type, 1, regs,
+			      head, NULL);
+}
+
+static int perf_sysenter_enable(struct trace_event_call *call)
+{
+	int ret = 0;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_perf_refcount_enter)
+		ret = register_trace_sys_enter(perf_syscall_enter, NULL);
+	if (ret) {
+		pr_info("event trace: Could not activate syscall entry trace point");
+	} else {
+		set_bit(num, enabled_perf_enter_syscalls);
+		sys_perf_refcount_enter++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+static void perf_sysenter_disable(struct trace_event_call *call)
+{
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+	mutex_lock(&syscall_trace_lock);
+	sys_perf_refcount_enter--;
+	clear_bit(num, enabled_perf_enter_syscalls);
+	if (!sys_perf_refcount_enter)
+		unregister_trace_sys_enter(perf_syscall_enter, NULL);
+	mutex_unlock(&syscall_trace_lock);
+}
+
+static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *regs,
+			      struct syscall_trace_exit *rec)
+{
+	struct syscall_tp_t {
+		unsigned long long regs;
+		unsigned long syscall_nr;
+		unsigned long ret;
+	} param;
+
+	*(struct pt_regs **)&param = regs;
+	param.syscall_nr = rec->nr;
+	param.ret = rec->ret;
+	return trace_call_bpf(call, &param);
+}
+
+static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
+{
+	struct syscall_metadata *sys_data;
+	struct syscall_trace_exit *rec;
+	struct hlist_head *head;
+	bool valid_prog_array;
+	int syscall_nr;
+	int rctx;
+	int size;
+
+	syscall_nr = trace_get_syscall_nr(current, regs);
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
+		return;
+	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
+		return;
+
+	sys_data = syscall_nr_to_meta(syscall_nr);
+	if (!sys_data)
+		return;
+
+	head = this_cpu_ptr(sys_data->exit_event->perf_events);
+	valid_prog_array = bpf_prog_array_valid(sys_data->exit_event);
+	if (!valid_prog_array && hlist_empty(head))
+		return;
+
+	/* We can probably do that at build time */
+	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
+	size -= sizeof(u32);
+
+	rec = perf_trace_buf_alloc(size, NULL, &rctx);
+	if (!rec)
+		return;
+
+	rec->nr = syscall_nr;
+	rec->ret = syscall_get_return_value(current, regs);
+
+	if ((valid_prog_array &&
+	     !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
+	    hlist_empty(head)) {
+		perf_swevent_put_recursion_context(rctx);
+		return;
+	}
+
+	perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
+			      1, regs, head, NULL);
+}
+
+static int perf_sysexit_enable(struct trace_event_call *call)
+{
+	int ret = 0;
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+	mutex_lock(&syscall_trace_lock);
+	if (!sys_perf_refcount_exit)
+		ret = register_trace_sys_exit(perf_syscall_exit, NULL);
+	if (ret) {
+		pr_info("event trace: Could not activate syscall exit trace point");
+	} else {
+		set_bit(num, enabled_perf_exit_syscalls);
+		sys_perf_refcount_exit++;
+	}
+	mutex_unlock(&syscall_trace_lock);
+	return ret;
+}
+
+static void perf_sysexit_disable(struct trace_event_call *call)
+{
+	int num;
+
+	num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+	mutex_lock(&syscall_trace_lock);
+	sys_perf_refcount_exit--;
+	clear_bit(num, enabled_perf_exit_syscalls);
+	if (!sys_perf_refcount_exit)
+		unregister_trace_sys_exit(perf_syscall_exit, NULL);
+	mutex_unlock(&syscall_trace_lock);
+}
+
+#endif /* CONFIG_PERF_EVENTS */
+
+static int syscall_enter_register(struct trace_event_call *event,
+				 enum trace_reg type, void *data)
+{
+	struct trace_event_file *file = data;
+
+	switch (type) {
+	case TRACE_REG_REGISTER:
+		return reg_event_syscall_enter(file, event);
+	case TRACE_REG_UNREGISTER:
+		unreg_event_syscall_enter(file, event);
+		return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+	case TRACE_REG_PERF_REGISTER:
+		return perf_sysenter_enable(event);
+	case TRACE_REG_PERF_UNREGISTER:
+		perf_sysenter_disable(event);
+		return 0;
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+		return 0;
+#endif
+	}
+	return 0;
+}
+
+static int syscall_exit_register(struct trace_event_call *event,
+				 enum trace_reg type, void *data)
+{
+	struct trace_event_file *file = data;
+
+	switch (type) {
+	case TRACE_REG_REGISTER:
+		return reg_event_syscall_exit(file, event);
+	case TRACE_REG_UNREGISTER:
+		unreg_event_syscall_exit(file, event);
+		return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+	case TRACE_REG_PERF_REGISTER:
+		return perf_sysexit_enable(event);
+	case TRACE_REG_PERF_UNREGISTER:
+		perf_sysexit_disable(event);
+		return 0;
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+		return 0;
+#endif
+	}
+	return 0;
+}

kernel/trace/tracing_map.h

@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __TRACING_MAP_H
+#define __TRACING_MAP_H
+
+#define TRACING_MAP_BITS_DEFAULT	11
+#define TRACING_MAP_BITS_MAX		17
+#define TRACING_MAP_BITS_MIN		7
+
+#define TRACING_MAP_KEYS_MAX		3
+#define TRACING_MAP_VALS_MAX		3
+#define TRACING_MAP_FIELDS_MAX		(TRACING_MAP_KEYS_MAX + \
+					 TRACING_MAP_VALS_MAX)
+#define TRACING_MAP_VARS_MAX		16
+#define TRACING_MAP_SORT_KEYS_MAX	2
+
+typedef int (*tracing_map_cmp_fn_t) (void *val_a, void *val_b);
+
+/*
+ * This is an overview of the tracing_map data structures and how they
+ * relate to the tracing_map API.  The details of the algorithms
+ * aren't discussed here - this is just a general overview of the data
+ * structures and how they interact with the API.
+ *
+ * The central data structure of the tracing_map is an initially
+ * zeroed array of struct tracing_map_entry (stored in the map field
+ * of struct tracing_map).  tracing_map_entry is a very simple data
+ * structure containing only two fields: a 32-bit unsigned 'key'
+ * variable and a pointer named 'val'.  This array of struct
+ * tracing_map_entry is essentially a hash table which will be
+ * modified by a single function, tracing_map_insert(), but which can
+ * be traversed and read by a user at any time (though the user does
+ * this indirectly via an array of tracing_map_sort_entry - see the
+ * explanation of that data structure in the discussion of the
+ * sorting-related data structures below).
+ *
+ * The central function of the tracing_map API is
+ * tracing_map_insert().  tracing_map_insert() hashes the
+ * arbitrarily-sized key passed into it into a 32-bit unsigned key.
+ * It then uses this key, truncated to the array size, as an index
+ * into the array of tracing_map_entries.  If the value of the 'key'
+ * field of the tracing_map_entry found at that location is 0, then
+ * that entry is considered to be free and can be claimed, by
+ * replacing the 0 in the 'key' field of the tracing_map_entry with
+ * the new 32-bit hashed key.  Once claimed, that tracing_map_entry's
+ * 'val' field is then used to store a unique element which will be
+ * forever associated with that 32-bit hashed key in the
+ * tracing_map_entry.
+ *
+ * That unique element now in the tracing_map_entry's 'val' field is
+ * an instance of tracing_map_elt, where 'elt' in the latter part of
+ * that variable name is short for 'element'.  The purpose of a
+ * tracing_map_elt is to hold values specific to the particular
+ * 32-bit hashed key it's assocated with.  Things such as the unique
+ * set of aggregated sums associated with the 32-bit hashed key, along
+ * with a copy of the full key associated with the entry, and which
+ * was used to produce the 32-bit hashed key.
+ *
+ * When tracing_map_create() is called to create the tracing map, the
+ * user specifies (indirectly via the map_bits param, the details are
+ * unimportant for this discussion) the maximum number of elements
+ * that the map can hold (stored in the max_elts field of struct
+ * tracing_map).  This is the maximum possible number of
+ * tracing_map_entries in the tracing_map_entry array which can be
+ * 'claimed' as described in the above discussion, and therefore is
+ * also the maximum number of tracing_map_elts that can be associated
+ * with the tracing_map_entry array in the tracing_map.  Because of
+ * the way the insertion algorithm works, the size of the allocated
+ * tracing_map_entry array is always twice the maximum number of
+ * elements (2 * max_elts).  This value is stored in the map_size
+ * field of struct tracing_map.
+ *
+ * Because tracing_map_insert() needs to work from any context,
+ * including from within the memory allocation functions themselves,
+ * both the tracing_map_entry array and a pool of max_elts
+ * tracing_map_elts are pre-allocated before any call is made to
+ * tracing_map_insert().
+ *
+ * The tracing_map_entry array is allocated as a single block by
+ * tracing_map_create().
+ *
+ * Because the tracing_map_elts are much larger objects and can't
+ * generally be allocated together as a single large array without
+ * failure, they're allocated individually, by tracing_map_init().
+ *
+ * The pool of tracing_map_elts are allocated by tracing_map_init()
+ * rather than by tracing_map_create() because at the time
+ * tracing_map_create() is called, there isn't enough information to
+ * create the tracing_map_elts.  Specifically,the user first needs to
+ * tell the tracing_map implementation how many fields the
+ * tracing_map_elts contain, and which types of fields they are (key
+ * or sum).  The user does this via the tracing_map_add_sum_field()
+ * and tracing_map_add_key_field() functions, following which the user
+ * calls tracing_map_init() to finish up the tracing map setup.  The
+ * array holding the pointers which make up the pre-allocated pool of
+ * tracing_map_elts is allocated as a single block and is stored in
+ * the elts field of struct tracing_map.
+ *
+ * There is also a set of structures used for sorting that might
+ * benefit from some minimal explanation.
+ *
+ * struct tracing_map_sort_key is used to drive the sort at any given
+ * time.  By 'any given time' we mean that a different
+ * tracing_map_sort_key will be used at different times depending on
+ * whether the sort currently being performed is a primary or a
+ * secondary sort.
+ *
+ * The sort key is very simple, consisting of the field index of the
+ * tracing_map_elt field to sort on (which the user saved when adding
+ * the field), and whether the sort should be done in an ascending or
+ * descending order.
+ *
+ * For the convenience of the sorting code, a tracing_map_sort_entry
+ * is created for each tracing_map_elt, again individually allocated
+ * to avoid failures that might be expected if allocated as a single
+ * large array of struct tracing_map_sort_entry.
+ * tracing_map_sort_entry instances are the objects expected by the
+ * various internal sorting functions, and are also what the user
+ * ultimately receives after calling tracing_map_sort_entries().
+ * Because it doesn't make sense for users to access an unordered and
+ * sparsely populated tracing_map directly, the
+ * tracing_map_sort_entries() function is provided so that users can
+ * retrieve a sorted list of all existing elements.  In addition to
+ * the associated tracing_map_elt 'elt' field contained within the
+ * tracing_map_sort_entry, which is the object of interest to the
+ * user, tracing_map_sort_entry objects contain a number of additional
+ * fields which are used for caching and internal purposes and can
+ * safely be ignored.
+*/
+
+struct tracing_map_field {
+	tracing_map_cmp_fn_t		cmp_fn;
+	union {
+		atomic64_t			sum;
+		unsigned int			offset;
+	};
+};
+
+struct tracing_map_elt {
+	struct tracing_map		*map;
+	struct tracing_map_field	*fields;
+	atomic64_t			*vars;
+	bool				*var_set;
+	void				*key;
+	void				*private_data;
+};
+
+struct tracing_map_entry {
+	u32				key;
+	struct tracing_map_elt		*val;
+};
+
+struct tracing_map_sort_key {
+	unsigned int			field_idx;
+	bool				descending;
+};
+
+struct tracing_map_sort_entry {
+	void				*key;
+	struct tracing_map_elt		*elt;
+	bool				elt_copied;
+	bool				dup;
+};
+
+struct tracing_map_array {
+	unsigned int entries_per_page;
+	unsigned int entry_size_shift;
+	unsigned int entry_shift;
+	unsigned int entry_mask;
+	unsigned int n_pages;
+	void **pages;
+};
+
+#define TRACING_MAP_ARRAY_ELT(array, idx)				\
+	(array->pages[idx >> array->entry_shift] +			\
+	 ((idx & array->entry_mask) << array->entry_size_shift))
+
+#define TRACING_MAP_ENTRY(array, idx)					\
+	((struct tracing_map_entry *)TRACING_MAP_ARRAY_ELT(array, idx))
+
+#define TRACING_MAP_ELT(array, idx)					\
+	((struct tracing_map_elt **)TRACING_MAP_ARRAY_ELT(array, idx))
+
+struct tracing_map {
+	unsigned int			key_size;
+	unsigned int			map_bits;
+	unsigned int			map_size;
+	unsigned int			max_elts;
+	atomic_t			next_elt;
+	struct tracing_map_array	*elts;
+	struct tracing_map_array	*map;
+	const struct tracing_map_ops	*ops;
+	void				*private_data;
+	struct tracing_map_field	fields[TRACING_MAP_FIELDS_MAX];
+	unsigned int			n_fields;
+	int				key_idx[TRACING_MAP_KEYS_MAX];
+	unsigned int			n_keys;
+	struct tracing_map_sort_key	sort_key;
+	unsigned int			n_vars;
+	atomic64_t			hits;
+	atomic64_t			drops;
+};
+
+/**
+ * struct tracing_map_ops - callbacks for tracing_map
+ *
+ * The methods in this structure define callback functions for various
+ * operations on a tracing_map or objects related to a tracing_map.
+ *
+ * For a detailed description of tracing_map_elt objects please see
+ * the overview of tracing_map data structures at the beginning of
+ * this file.
+ *
+ * All the methods below are optional.
+ *
+ * @elt_alloc: When a tracing_map_elt is allocated, this function, if
+ *	defined, will be called and gives clients the opportunity to
+ *	allocate additional data and attach it to the element
+ *	(tracing_map_elt->private_data is meant for that purpose).
+ *	Element allocation occurs before tracing begins, when the
+ *	tracing_map_init() call is made by client code.
+ *
+ * @elt_free: When a tracing_map_elt is freed, this function is called
+ *	and allows client-allocated per-element data to be freed.
+ *
+ * @elt_clear: This callback allows per-element client-defined data to
+ *	be cleared, if applicable.
+ *
+ * @elt_init: This callback allows per-element client-defined data to
+ *	be initialized when used i.e. when the element is actually
+ *	claimed by tracing_map_insert() in the context of the map
+ *	insertion.
+ */
+struct tracing_map_ops {
+	int			(*elt_alloc)(struct tracing_map_elt *elt);
+	void			(*elt_free)(struct tracing_map_elt *elt);
+	void			(*elt_clear)(struct tracing_map_elt *elt);
+	void			(*elt_init)(struct tracing_map_elt *elt);
+};
+
+extern struct tracing_map *
+tracing_map_create(unsigned int map_bits,
+		   unsigned int key_size,
+		   const struct tracing_map_ops *ops,
+		   void *private_data);
+extern int tracing_map_init(struct tracing_map *map);
+
+extern int tracing_map_add_sum_field(struct tracing_map *map);
+extern int tracing_map_add_var(struct tracing_map *map);
+extern int tracing_map_add_key_field(struct tracing_map *map,
+				     unsigned int offset,
+				     tracing_map_cmp_fn_t cmp_fn);
+
+extern void tracing_map_destroy(struct tracing_map *map);
+extern void tracing_map_clear(struct tracing_map *map);
+
+extern struct tracing_map_elt *
+tracing_map_insert(struct tracing_map *map, void *key);
+extern struct tracing_map_elt *
+tracing_map_lookup(struct tracing_map *map, void *key);
+
+extern tracing_map_cmp_fn_t tracing_map_cmp_num(int field_size,
+						int field_is_signed);
+extern int tracing_map_cmp_string(void *val_a, void *val_b);
+extern int tracing_map_cmp_none(void *val_a, void *val_b);
+
+extern void tracing_map_update_sum(struct tracing_map_elt *elt,
+				   unsigned int i, u64 n);
+extern void tracing_map_set_var(struct tracing_map_elt *elt,
+				unsigned int i, u64 n);
+extern bool tracing_map_var_set(struct tracing_map_elt *elt, unsigned int i);
+extern u64 tracing_map_read_sum(struct tracing_map_elt *elt, unsigned int i);
+extern u64 tracing_map_read_var(struct tracing_map_elt *elt, unsigned int i);
+extern u64 tracing_map_read_var_once(struct tracing_map_elt *elt, unsigned int i);
+
+extern void tracing_map_set_field_descr(struct tracing_map *map,
+					unsigned int i,
+					unsigned int key_offset,
+					tracing_map_cmp_fn_t cmp_fn);
+extern int
+tracing_map_sort_entries(struct tracing_map *map,
+			 struct tracing_map_sort_key *sort_keys,
+			 unsigned int n_sort_keys,
+			 struct tracing_map_sort_entry ***sort_entries);
+
+extern void
+tracing_map_destroy_sort_entries(struct tracing_map_sort_entry **entries,
+				 unsigned int n_entries);
+#endif /* __TRACING_MAP_H */