diff options
Diffstat (limited to 'kernel/trace/Kconfig')
| -rw-r--r-- | kernel/trace/Kconfig | 486 |
1 files changed, 383 insertions, 103 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 34e707e5ab8..d4409356f40 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -9,33 +9,94 @@ config USER_STACKTRACE_SUPPORT config NOP_TRACER bool +config HAVE_FTRACE_NMI_ENTER + bool + help + See Documentation/trace/ftrace-design.txt + config HAVE_FUNCTION_TRACER bool + help + See Documentation/trace/ftrace-design.txt config HAVE_FUNCTION_GRAPH_TRACER bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_FUNCTION_GRAPH_FP_TEST + bool + help + See Documentation/trace/ftrace-design.txt 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. + See Documentation/trace/ftrace-design.txt config HAVE_DYNAMIC_FTRACE bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_DYNAMIC_FTRACE_WITH_REGS + bool config HAVE_FTRACE_MCOUNT_RECORD bool + help + See Documentation/trace/ftrace-design.txt -config HAVE_HW_BRANCH_TRACER +config HAVE_SYSCALL_TRACEPOINTS bool + help + See Documentation/trace/ftrace-design.txt + +config HAVE_FENTRY + bool + help + Arch supports the gcc options -pg with -mfentry + +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 + 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. + +# 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 @@ -44,21 +105,48 @@ config TRACING select STACKTRACE if STACKTRACE_SUPPORT select TRACEPOINTS select NOP_TRACER + select BINARY_PRINTF + select EVENT_TRACING + select TRACE_CLOCK -menu "Tracers" +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 + # 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 - depends on DEBUG_KERNEL - select FRAME_POINTER select KALLSYMS - select TRACING + select GENERIC_TRACER 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 + 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 @@ -68,25 +156,28 @@ 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. - It's first purpose is to trace the duration of functions and - draw a call graph for each thread with some informations like - the return value. - This is done by setting the current return address on the current - task structure into a stack of calls. + 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 - depends on DEBUG_KERNEL + depends on !ARCH_USES_GETTIMEOFFSET select TRACE_IRQFLAGS - select TRACING + 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. @@ -95,110 +186,150 @@ config IRQSOFF_TRACER disabled by default and can be runtime (re-)started via: - echo 0 > /debugfs/tracing/tracing_max_latency + echo 0 > /sys/kernel/debug/tracing/tracing_max_latency - (Note that kernel size and overhead increases with this option + (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 GENERIC_TIME + depends on !ARCH_USES_GETTIMEOFFSET depends on PREEMPT - depends on DEBUG_KERNEL - select TRACING + 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 preemption off critical + 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 + echo 0 > /sys/kernel/debug/tracing/tracing_max_latency - (Note that kernel size and overhead increases with this option + (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 SYSPROF_TRACER - bool "Sysprof Tracer" - depends on X86 - select TRACING - help - This tracer provides the trace needed by the 'Sysprof' userspace - tool. - config SCHED_TRACER bool "Scheduling Latency Tracer" - depends on DEBUG_KERNEL - select TRACING + 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 CONTEXT_SWITCH_TRACER - bool "Trace process context switches" - depends on DEBUG_KERNEL +config ENABLE_DEFAULT_TRACERS + bool "Trace process context switches and events" + depends on !GENERIC_TRACER select TRACING - select MARKERS help - This tracer gets called from the context switch and records - all switching of tasks. + 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 BOOT_TRACER - bool "Trace boot initcalls" - depends on DEBUG_KERNEL - select TRACING - select CONTEXT_SWITCH_TRACER +config TRACER_SNAPSHOT + bool "Create a snapshot trace buffer" + select TRACER_MAX_TRACE 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. + Allow tracing users to take snapshot of the current buffer using the + ftrace interface, e.g.: - 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. + echo 1 > /sys/kernel/debug/tracing/snapshot + cat snapshot - ( Note that tracing self tests can't be enabled if this tracer is - selected, because the self-tests are an initcall as well and that - would invalidate the boot trace. ) +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" - depends on DEBUG_KERNEL - select TRACING + select TRACE_BRANCH_PROFILING help - This tracer profiles all the the likely and unlikely macros + This tracer profiles all likely and unlikely macros in the kernel. It will display the results in: - /debugfs/tracing/profile_annotated_branch + /sys/kernel/debug/tracing/trace_stat/branch_annotated - Note: this will add a significant overhead, only turn this + Note: this will add a significant overhead; only turn this on if you need to profile the system's use of these macros. - Say N if unsure. - config PROFILE_ALL_BRANCHES bool "Profile all if conditionals" - depends on TRACE_BRANCH_PROFILING + 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 + /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 - - Say N if unsure. + is to be analyzed in much detail. +endchoice config TRACING_BRANCHES bool @@ -222,27 +353,15 @@ config BRANCH_TRACER Say N if unsure. -config POWER_TRACER - bool "Trace power consumption behavior" - depends on DEBUG_KERNEL - 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 STACK_TRACER bool "Trace max stack" depends on HAVE_FUNCTION_TRACER - depends on DEBUG_KERNEL 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. + 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 @@ -258,33 +377,110 @@ config STACK_TRACER Say N if unsure. -config HW_BRANCH_TRACER - depends on HAVE_HW_BRANCH_TRACER - bool "Trace hw branches" +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_EVENT + 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.txt 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 UPROBE_EVENT + 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 n help - This tracer records all branches on the system in a circular - buffer giving access to the last N branches for each cpu. + 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 PROBE_EVENTS + def_bool n config DYNAMIC_FTRACE - bool "enable/disable ftrace tracepoints dynamically" + bool "enable/disable function tracing dynamically" depends on FUNCTION_TRACER depends on HAVE_DYNAMIC_FTRACE - depends on DEBUG_KERNEL 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 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 - This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise - has native performance as long as no tracing is active. +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_stats directory; this file shows the list of functions that + have been hit and their counters. - 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. + If in doubt, say N. config FTRACE_MCOUNT_RECORD def_bool y @@ -296,7 +492,7 @@ config FTRACE_SELFTEST config FTRACE_STARTUP_TEST bool "Perform a startup test on ftrace" - depends on TRACING && DEBUG_KERNEL && !BOOT_TRACER + depends on GENERIC_TRACER select FTRACE_SELFTEST help This option performs a series of startup tests on ftrace. On bootup @@ -304,17 +500,29 @@ config FTRACE_STARTUP_TEST 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 && DEBUG_KERNEL && PCI - select 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/tracers/mmiotrace.txt. + See Documentation/trace/mmiotrace.txt. If you are not helping to develop drivers, say N. config MMIOTRACE_TEST @@ -327,4 +535,76 @@ config MMIOTRACE_TEST Say N, unless you absolutely know what you are doing. -endmenu +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 + +endif # FTRACE + +endif # TRACING_SUPPORT + |