0722db015c
This patch adds an ftrace plugin to detect and profile memory access over kernel variables. It uses HW Breakpoint interfaces to 'watch memory addresses. Signed-off-by: K.Prasad <prasad@linux.vnet.ibm.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
520 lines
15 KiB
Text
520 lines
15 KiB
Text
#
|
|
# 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
|
|
|
|
config HAVE_FUNCTION_TRACER
|
|
bool
|
|
|
|
config HAVE_FUNCTION_GRAPH_TRACER
|
|
bool
|
|
|
|
config HAVE_FUNCTION_TRACE_MCOUNT_TEST
|
|
bool
|
|
help
|
|
This gets selected when the arch tests the function_trace_stop
|
|
variable at the mcount call site. Otherwise, this variable
|
|
is tested by the called function.
|
|
|
|
config HAVE_DYNAMIC_FTRACE
|
|
bool
|
|
|
|
config HAVE_FTRACE_MCOUNT_RECORD
|
|
bool
|
|
|
|
config HAVE_HW_BRANCH_TRACER
|
|
bool
|
|
|
|
config HAVE_FTRACE_SYSCALLS
|
|
bool
|
|
|
|
config TRACER_MAX_TRACE
|
|
bool
|
|
|
|
config RING_BUFFER
|
|
bool
|
|
|
|
config FTRACE_NMI_ENTER
|
|
bool
|
|
depends on HAVE_FTRACE_NMI_ENTER
|
|
default y
|
|
|
|
config EVENT_TRACING
|
|
select CONTEXT_SWITCH_TRACER
|
|
bool
|
|
|
|
config CONTEXT_SWITCH_TRACER
|
|
select MARKERS
|
|
bool
|
|
|
|
config TRACING
|
|
bool
|
|
select DEBUG_FS
|
|
select RING_BUFFER
|
|
select STACKTRACE if STACKTRACE_SUPPORT
|
|
select TRACEPOINTS
|
|
select NOP_TRACER
|
|
select BINARY_PRINTF
|
|
select EVENT_TRACING
|
|
|
|
#
|
|
# Minimum requirements an architecture has to meet for us to
|
|
# be able to offer generic tracing facilities:
|
|
#
|
|
config TRACING_SUPPORT
|
|
bool
|
|
# PPC32 has no irqflags tracing support, but it can use most of the
|
|
# tracers anyway, they were tested to build and work. Note that new
|
|
# exceptions to this list aren't welcomed, better implement the
|
|
# irqflags tracing for your architecture.
|
|
depends on TRACE_IRQFLAGS_SUPPORT || PPC32
|
|
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 FRAME_POINTER
|
|
select KALLSYMS
|
|
select TRACING
|
|
select CONTEXT_SWITCH_TRACER
|
|
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 to 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
|
|
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 IRQSOFF_TRACER
|
|
bool "Interrupts-off Latency Tracer"
|
|
default n
|
|
depends on TRACE_IRQFLAGS_SUPPORT
|
|
depends on GENERIC_TIME
|
|
select TRACE_IRQFLAGS
|
|
select TRACING
|
|
select TRACER_MAX_TRACE
|
|
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 > /debugfs/tracing/tracing_max_latency
|
|
|
|
(Note that kernel size and overhead increases 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 GENERIC_TIME
|
|
depends on PREEMPT
|
|
select TRACING
|
|
select TRACER_MAX_TRACE
|
|
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 > /debugfs/tracing/tracing_max_latency
|
|
|
|
(Note that kernel size and overhead increases with this option
|
|
enabled. This option and the irqs-off timing option can be
|
|
used together or separately.)
|
|
|
|
config SYSPROF_TRACER
|
|
bool "Sysprof Tracer"
|
|
depends on X86
|
|
select TRACING
|
|
select CONTEXT_SWITCH_TRACER
|
|
help
|
|
This tracer provides the trace needed by the 'Sysprof' userspace
|
|
tool.
|
|
|
|
config SCHED_TRACER
|
|
bool "Scheduling Latency Tracer"
|
|
select TRACING
|
|
select CONTEXT_SWITCH_TRACER
|
|
select TRACER_MAX_TRACE
|
|
help
|
|
This tracer tracks the latency of the highest priority task
|
|
to be scheduled in, starting from the point it has woken up.
|
|
|
|
config ENABLE_CONTEXT_SWITCH_TRACER
|
|
bool "Trace process context switches"
|
|
select TRACING
|
|
select CONTEXT_SWITCH_TRACER
|
|
help
|
|
This tracer gets called from the context switch and records
|
|
all switching of tasks.
|
|
|
|
config ENABLE_EVENT_TRACING
|
|
bool "Trace various events in the kernel"
|
|
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.
|
|
|
|
Note, all tracers enable event tracing. This option is
|
|
only a convenience to enable event tracing when no other
|
|
tracers are selected.
|
|
|
|
config FTRACE_SYSCALLS
|
|
bool "Trace syscalls"
|
|
depends on HAVE_FTRACE_SYSCALLS
|
|
select TRACING
|
|
select KALLSYMS
|
|
help
|
|
Basic tracer to catch the syscall entry and exit events.
|
|
|
|
config BOOT_TRACER
|
|
bool "Trace boot initcalls"
|
|
select TRACING
|
|
select CONTEXT_SWITCH_TRACER
|
|
help
|
|
This tracer helps developers to optimize boot times: it records
|
|
the timings of the initcalls and traces key events and the identity
|
|
of tasks that can cause boot delays, such as context-switches.
|
|
|
|
Its aim is to be parsed by the /scripts/bootgraph.pl tool to
|
|
produce pretty graphics about boot inefficiencies, giving a visual
|
|
representation of the delays during initcalls - but the raw
|
|
/debug/tracing/trace text output is readable too.
|
|
|
|
You must pass in ftrace=initcall to the kernel command line
|
|
to enable this on bootup.
|
|
|
|
config TRACE_BRANCH_PROFILING
|
|
bool
|
|
select TRACING
|
|
|
|
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 as well.
|
|
|
|
Either of the above profilers add 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 the the likely and unlikely macros
|
|
in the kernel. It will display the results in:
|
|
|
|
/debugfs/tracing/profile_annotated_branch
|
|
|
|
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"
|
|
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:
|
|
|
|
/debugfs/tracing/profile_branch
|
|
|
|
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
|
|
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 POWER_TRACER
|
|
bool "Trace power consumption behavior"
|
|
depends on X86
|
|
select TRACING
|
|
help
|
|
This tracer helps developers to analyze and optimize the kernels
|
|
power management decisions, specifically the C-state and P-state
|
|
behavior.
|
|
|
|
config KSYM_TRACER
|
|
bool "Trace read and write access on kernel memory locations"
|
|
depends on HAVE_HW_BREAKPOINT
|
|
select TRACING
|
|
help
|
|
This tracer helps find read and write operations on any given kernel
|
|
symbol i.e. /proc/kallsyms.
|
|
|
|
config PROFILE_KSYM_TRACER
|
|
bool "Profile all kernel memory accesses on 'watched' variables"
|
|
depends on KSYM_TRACER
|
|
help
|
|
This tracer profiles kernel accesses on variables watched through the
|
|
ksym tracer ftrace plugin. Depending upon the hardware, all read
|
|
and write operations on kernel variables can be monitored for
|
|
accesses.
|
|
|
|
The results will be displayed in:
|
|
/debugfs/tracing/profile_ksym
|
|
|
|
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 debugfs/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 HW_BRANCH_TRACER
|
|
depends on HAVE_HW_BRANCH_TRACER
|
|
bool "Trace hw branches"
|
|
select TRACING
|
|
help
|
|
This tracer records all branches on the system in a circular
|
|
buffer giving access to the last N branches for each cpu.
|
|
|
|
config KMEMTRACE
|
|
bool "Trace SLAB allocations"
|
|
select TRACING
|
|
help
|
|
kmemtrace provides tracing for slab allocator functions, such as
|
|
kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
|
|
data is then fed to the userspace application in order to analyse
|
|
allocation hotspots, internal fragmentation and so on, making it
|
|
possible to see how well an allocator performs, as well as debug
|
|
and profile kernel code.
|
|
|
|
This requires an userspace application to use. See
|
|
Documentation/trace/kmemtrace.txt for more information.
|
|
|
|
Saying Y will make the kernel somewhat larger and slower. However,
|
|
if you disable kmemtrace at run-time or boot-time, the performance
|
|
impact is minimal (depending on the arch the kernel is built for).
|
|
|
|
If unsure, say N.
|
|
|
|
config WORKQUEUE_TRACER
|
|
bool "Trace workqueues"
|
|
select TRACING
|
|
help
|
|
The workqueue tracer provides some statistical informations
|
|
about each cpu workqueue thread such as the number of the
|
|
works inserted and executed since their creation. It can help
|
|
to evaluate the amount of work each of them have to perform.
|
|
For example it can help a developer to decide whether he should
|
|
choose a per cpu workqueue instead of a singlethreaded one.
|
|
|
|
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 TRACING
|
|
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 DYNAMIC_FTRACE
|
|
bool "enable/disable ftrace tracepoints dynamically"
|
|
depends on FUNCTION_TRACER
|
|
depends on HAVE_DYNAMIC_FTRACE
|
|
default y
|
|
help
|
|
This option will modify all the calls to ftrace dynamically
|
|
(will patch them out of the binary image and replaces them
|
|
with a No-Op instruction) as they are called. A table is
|
|
created to dynamically enable them again.
|
|
|
|
This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise
|
|
has native performance as long as no tracing is active.
|
|
|
|
The changes to the code are done by a kernel thread that
|
|
wakes up once a second and checks to see if any ftrace calls
|
|
were made. If so, it runs stop_machine (stops all CPUS)
|
|
and modifies the code to jump over the call to ftrace.
|
|
|
|
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 file in the trace_stats
|
|
directory called functions, that show the list of functions that
|
|
have been hit and their counters.
|
|
|
|
If in doubt, say N
|
|
|
|
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 TRACING
|
|
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 MMIOTRACE
|
|
bool "Memory mapped IO tracing"
|
|
depends on HAVE_MMIOTRACE_SUPPORT && PCI
|
|
select TRACING
|
|
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.txt.
|
|
If you are not helping to develop drivers, 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 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 bench mark it.
|
|
It creates its own ring buffer such that it will not interfer 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
|
|
|
|
endif # FTRACE
|
|
|
|
endif # TRACING_SUPPORT
|
|
|