1# SPDX-License-Identifier: GPL-2.0-only 2# 3# Architectures that offer an FUNCTION_TRACER implementation should 4# select HAVE_FUNCTION_TRACER: 5# 6 7config USER_STACKTRACE_SUPPORT 8 bool 9 10config NOP_TRACER 11 bool 12 13config HAVE_FUNCTION_TRACER 14 bool 15 help 16 See Documentation/trace/ftrace-design.rst 17 18config HAVE_FUNCTION_GRAPH_TRACER 19 bool 20 help 21 See Documentation/trace/ftrace-design.rst 22 23config HAVE_DYNAMIC_FTRACE 24 bool 25 help 26 See Documentation/trace/ftrace-design.rst 27 28config HAVE_DYNAMIC_FTRACE_WITH_REGS 29 bool 30 31config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS 32 bool 33 34config HAVE_DYNAMIC_FTRACE_WITH_ARGS 35 bool 36 help 37 If this is set, then arguments and stack can be found from 38 the pt_regs passed into the function callback regs parameter 39 by default, even without setting the REGS flag in the ftrace_ops. 40 This allows for use of regs_get_kernel_argument() and 41 kernel_stack_pointer(). 42 43config HAVE_FTRACE_MCOUNT_RECORD 44 bool 45 help 46 See Documentation/trace/ftrace-design.rst 47 48config HAVE_SYSCALL_TRACEPOINTS 49 bool 50 help 51 See Documentation/trace/ftrace-design.rst 52 53config HAVE_FENTRY 54 bool 55 help 56 Arch supports the gcc options -pg with -mfentry 57 58config HAVE_NOP_MCOUNT 59 bool 60 help 61 Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount 62 63config HAVE_OBJTOOL_MCOUNT 64 bool 65 help 66 Arch supports objtool --mcount 67 68config HAVE_C_RECORDMCOUNT 69 bool 70 help 71 C version of recordmcount available? 72 73config TRACER_MAX_TRACE 74 bool 75 76config TRACE_CLOCK 77 bool 78 79config RING_BUFFER 80 bool 81 select TRACE_CLOCK 82 select IRQ_WORK 83 84config EVENT_TRACING 85 select CONTEXT_SWITCH_TRACER 86 select GLOB 87 bool 88 89config CONTEXT_SWITCH_TRACER 90 bool 91 92config RING_BUFFER_ALLOW_SWAP 93 bool 94 help 95 Allow the use of ring_buffer_swap_cpu. 96 Adds a very slight overhead to tracing when enabled. 97 98config PREEMPTIRQ_TRACEPOINTS 99 bool 100 depends on TRACE_PREEMPT_TOGGLE || TRACE_IRQFLAGS 101 select TRACING 102 default y 103 help 104 Create preempt/irq toggle tracepoints if needed, so that other parts 105 of the kernel can use them to generate or add hooks to them. 106 107# All tracer options should select GENERIC_TRACER. For those options that are 108# enabled by all tracers (context switch and event tracer) they select TRACING. 109# This allows those options to appear when no other tracer is selected. But the 110# options do not appear when something else selects it. We need the two options 111# GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the 112# hiding of the automatic options. 113 114config TRACING 115 bool 116 select RING_BUFFER 117 select STACKTRACE if STACKTRACE_SUPPORT 118 select TRACEPOINTS 119 select NOP_TRACER 120 select BINARY_PRINTF 121 select EVENT_TRACING 122 select TRACE_CLOCK 123 124config GENERIC_TRACER 125 bool 126 select TRACING 127 128# 129# Minimum requirements an architecture has to meet for us to 130# be able to offer generic tracing facilities: 131# 132config TRACING_SUPPORT 133 bool 134 depends on TRACE_IRQFLAGS_SUPPORT 135 depends on STACKTRACE_SUPPORT 136 default y 137 138if TRACING_SUPPORT 139 140menuconfig FTRACE 141 bool "Tracers" 142 default y if DEBUG_KERNEL 143 help 144 Enable the kernel tracing infrastructure. 145 146if FTRACE 147 148config BOOTTIME_TRACING 149 bool "Boot-time Tracing support" 150 depends on TRACING 151 select BOOT_CONFIG 152 help 153 Enable developer to setup ftrace subsystem via supplemental 154 kernel cmdline at boot time for debugging (tracing) driver 155 initialization and boot process. 156 157config FUNCTION_TRACER 158 bool "Kernel Function Tracer" 159 depends on HAVE_FUNCTION_TRACER 160 select KALLSYMS 161 select GENERIC_TRACER 162 select CONTEXT_SWITCH_TRACER 163 select GLOB 164 select TASKS_RCU if PREEMPTION 165 select TASKS_RUDE_RCU 166 help 167 Enable the kernel to trace every kernel function. This is done 168 by using a compiler feature to insert a small, 5-byte No-Operation 169 instruction at the beginning of every kernel function, which NOP 170 sequence is then dynamically patched into a tracer call when 171 tracing is enabled by the administrator. If it's runtime disabled 172 (the bootup default), then the overhead of the instructions is very 173 small and not measurable even in micro-benchmarks. 174 175config FUNCTION_GRAPH_TRACER 176 bool "Kernel Function Graph Tracer" 177 depends on HAVE_FUNCTION_GRAPH_TRACER 178 depends on FUNCTION_TRACER 179 depends on !X86_32 || !CC_OPTIMIZE_FOR_SIZE 180 default y 181 help 182 Enable the kernel to trace a function at both its return 183 and its entry. 184 Its first purpose is to trace the duration of functions and 185 draw a call graph for each thread with some information like 186 the return value. This is done by setting the current return 187 address on the current task structure into a stack of calls. 188 189config DYNAMIC_FTRACE 190 bool "enable/disable function tracing dynamically" 191 depends on FUNCTION_TRACER 192 depends on HAVE_DYNAMIC_FTRACE 193 default y 194 help 195 This option will modify all the calls to function tracing 196 dynamically (will patch them out of the binary image and 197 replace them with a No-Op instruction) on boot up. During 198 compile time, a table is made of all the locations that ftrace 199 can function trace, and this table is linked into the kernel 200 image. When this is enabled, functions can be individually 201 enabled, and the functions not enabled will not affect 202 performance of the system. 203 204 See the files in /sys/kernel/debug/tracing: 205 available_filter_functions 206 set_ftrace_filter 207 set_ftrace_notrace 208 209 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but 210 otherwise has native performance as long as no tracing is active. 211 212config DYNAMIC_FTRACE_WITH_REGS 213 def_bool y 214 depends on DYNAMIC_FTRACE 215 depends on HAVE_DYNAMIC_FTRACE_WITH_REGS 216 217config DYNAMIC_FTRACE_WITH_DIRECT_CALLS 218 def_bool y 219 depends on DYNAMIC_FTRACE_WITH_REGS 220 depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS 221 222config FUNCTION_PROFILER 223 bool "Kernel function profiler" 224 depends on FUNCTION_TRACER 225 default n 226 help 227 This option enables the kernel function profiler. A file is created 228 in debugfs called function_profile_enabled which defaults to zero. 229 When a 1 is echoed into this file profiling begins, and when a 230 zero is entered, profiling stops. A "functions" file is created in 231 the trace_stat directory; this file shows the list of functions that 232 have been hit and their counters. 233 234 If in doubt, say N. 235 236config STACK_TRACER 237 bool "Trace max stack" 238 depends on HAVE_FUNCTION_TRACER 239 select FUNCTION_TRACER 240 select STACKTRACE 241 select KALLSYMS 242 help 243 This special tracer records the maximum stack footprint of the 244 kernel and displays it in /sys/kernel/debug/tracing/stack_trace. 245 246 This tracer works by hooking into every function call that the 247 kernel executes, and keeping a maximum stack depth value and 248 stack-trace saved. If this is configured with DYNAMIC_FTRACE 249 then it will not have any overhead while the stack tracer 250 is disabled. 251 252 To enable the stack tracer on bootup, pass in 'stacktrace' 253 on the kernel command line. 254 255 The stack tracer can also be enabled or disabled via the 256 sysctl kernel.stack_tracer_enabled 257 258 Say N if unsure. 259 260config TRACE_PREEMPT_TOGGLE 261 bool 262 help 263 Enables hooks which will be called when preemption is first disabled, 264 and last enabled. 265 266config IRQSOFF_TRACER 267 bool "Interrupts-off Latency Tracer" 268 default n 269 depends on TRACE_IRQFLAGS_SUPPORT 270 select TRACE_IRQFLAGS 271 select GENERIC_TRACER 272 select TRACER_MAX_TRACE 273 select RING_BUFFER_ALLOW_SWAP 274 select TRACER_SNAPSHOT 275 select TRACER_SNAPSHOT_PER_CPU_SWAP 276 help 277 This option measures the time spent in irqs-off critical 278 sections, with microsecond accuracy. 279 280 The default measurement method is a maximum search, which is 281 disabled by default and can be runtime (re-)started 282 via: 283 284 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency 285 286 (Note that kernel size and overhead increase with this option 287 enabled. This option and the preempt-off timing option can be 288 used together or separately.) 289 290config PREEMPT_TRACER 291 bool "Preemption-off Latency Tracer" 292 default n 293 depends on PREEMPTION 294 select GENERIC_TRACER 295 select TRACER_MAX_TRACE 296 select RING_BUFFER_ALLOW_SWAP 297 select TRACER_SNAPSHOT 298 select TRACER_SNAPSHOT_PER_CPU_SWAP 299 select TRACE_PREEMPT_TOGGLE 300 help 301 This option measures the time spent in preemption-off critical 302 sections, with microsecond accuracy. 303 304 The default measurement method is a maximum search, which is 305 disabled by default and can be runtime (re-)started 306 via: 307 308 echo 0 > /sys/kernel/debug/tracing/tracing_max_latency 309 310 (Note that kernel size and overhead increase with this option 311 enabled. This option and the irqs-off timing option can be 312 used together or separately.) 313 314config SCHED_TRACER 315 bool "Scheduling Latency Tracer" 316 select GENERIC_TRACER 317 select CONTEXT_SWITCH_TRACER 318 select TRACER_MAX_TRACE 319 select TRACER_SNAPSHOT 320 help 321 This tracer tracks the latency of the highest priority task 322 to be scheduled in, starting from the point it has woken up. 323 324config HWLAT_TRACER 325 bool "Tracer to detect hardware latencies (like SMIs)" 326 select GENERIC_TRACER 327 help 328 This tracer, when enabled will create one or more kernel threads, 329 depending on what the cpumask file is set to, which each thread 330 spinning in a loop looking for interruptions caused by 331 something other than the kernel. For example, if a 332 System Management Interrupt (SMI) takes a noticeable amount of 333 time, this tracer will detect it. This is useful for testing 334 if a system is reliable for Real Time tasks. 335 336 Some files are created in the tracing directory when this 337 is enabled: 338 339 hwlat_detector/width - time in usecs for how long to spin for 340 hwlat_detector/window - time in usecs between the start of each 341 iteration 342 343 A kernel thread is created that will spin with interrupts disabled 344 for "width" microseconds in every "window" cycle. It will not spin 345 for "window - width" microseconds, where the system can 346 continue to operate. 347 348 The output will appear in the trace and trace_pipe files. 349 350 When the tracer is not running, it has no affect on the system, 351 but when it is running, it can cause the system to be 352 periodically non responsive. Do not run this tracer on a 353 production system. 354 355 To enable this tracer, echo in "hwlat" into the current_tracer 356 file. Every time a latency is greater than tracing_thresh, it will 357 be recorded into the ring buffer. 358 359config MMIOTRACE 360 bool "Memory mapped IO tracing" 361 depends on HAVE_MMIOTRACE_SUPPORT && PCI 362 select GENERIC_TRACER 363 help 364 Mmiotrace traces Memory Mapped I/O access and is meant for 365 debugging and reverse engineering. It is called from the ioremap 366 implementation and works via page faults. Tracing is disabled by 367 default and can be enabled at run-time. 368 369 See Documentation/trace/mmiotrace.rst. 370 If you are not helping to develop drivers, say N. 371 372config ENABLE_DEFAULT_TRACERS 373 bool "Trace process context switches and events" 374 depends on !GENERIC_TRACER 375 select TRACING 376 help 377 This tracer hooks to various trace points in the kernel, 378 allowing the user to pick and choose which trace point they 379 want to trace. It also includes the sched_switch tracer plugin. 380 381config FTRACE_SYSCALLS 382 bool "Trace syscalls" 383 depends on HAVE_SYSCALL_TRACEPOINTS 384 select GENERIC_TRACER 385 select KALLSYMS 386 help 387 Basic tracer to catch the syscall entry and exit events. 388 389config TRACER_SNAPSHOT 390 bool "Create a snapshot trace buffer" 391 select TRACER_MAX_TRACE 392 help 393 Allow tracing users to take snapshot of the current buffer using the 394 ftrace interface, e.g.: 395 396 echo 1 > /sys/kernel/debug/tracing/snapshot 397 cat snapshot 398 399config TRACER_SNAPSHOT_PER_CPU_SWAP 400 bool "Allow snapshot to swap per CPU" 401 depends on TRACER_SNAPSHOT 402 select RING_BUFFER_ALLOW_SWAP 403 help 404 Allow doing a snapshot of a single CPU buffer instead of a 405 full swap (all buffers). If this is set, then the following is 406 allowed: 407 408 echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot 409 410 After which, only the tracing buffer for CPU 2 was swapped with 411 the main tracing buffer, and the other CPU buffers remain the same. 412 413 When this is enabled, this adds a little more overhead to the 414 trace recording, as it needs to add some checks to synchronize 415 recording with swaps. But this does not affect the performance 416 of the overall system. This is enabled by default when the preempt 417 or irq latency tracers are enabled, as those need to swap as well 418 and already adds the overhead (plus a lot more). 419 420config TRACE_BRANCH_PROFILING 421 bool 422 select GENERIC_TRACER 423 424choice 425 prompt "Branch Profiling" 426 default BRANCH_PROFILE_NONE 427 help 428 The branch profiling is a software profiler. It will add hooks 429 into the C conditionals to test which path a branch takes. 430 431 The likely/unlikely profiler only looks at the conditions that 432 are annotated with a likely or unlikely macro. 433 434 The "all branch" profiler will profile every if-statement in the 435 kernel. This profiler will also enable the likely/unlikely 436 profiler. 437 438 Either of the above profilers adds a bit of overhead to the system. 439 If unsure, choose "No branch profiling". 440 441config BRANCH_PROFILE_NONE 442 bool "No branch profiling" 443 help 444 No branch profiling. Branch profiling adds a bit of overhead. 445 Only enable it if you want to analyse the branching behavior. 446 Otherwise keep it disabled. 447 448config PROFILE_ANNOTATED_BRANCHES 449 bool "Trace likely/unlikely profiler" 450 select TRACE_BRANCH_PROFILING 451 help 452 This tracer profiles all likely and unlikely macros 453 in the kernel. It will display the results in: 454 455 /sys/kernel/debug/tracing/trace_stat/branch_annotated 456 457 Note: this will add a significant overhead; only turn this 458 on if you need to profile the system's use of these macros. 459 460config PROFILE_ALL_BRANCHES 461 bool "Profile all if conditionals" if !FORTIFY_SOURCE 462 select TRACE_BRANCH_PROFILING 463 help 464 This tracer profiles all branch conditions. Every if () 465 taken in the kernel is recorded whether it hit or miss. 466 The results will be displayed in: 467 468 /sys/kernel/debug/tracing/trace_stat/branch_all 469 470 This option also enables the likely/unlikely profiler. 471 472 This configuration, when enabled, will impose a great overhead 473 on the system. This should only be enabled when the system 474 is to be analyzed in much detail. 475endchoice 476 477config TRACING_BRANCHES 478 bool 479 help 480 Selected by tracers that will trace the likely and unlikely 481 conditions. This prevents the tracers themselves from being 482 profiled. Profiling the tracing infrastructure can only happen 483 when the likelys and unlikelys are not being traced. 484 485config BRANCH_TRACER 486 bool "Trace likely/unlikely instances" 487 depends on TRACE_BRANCH_PROFILING 488 select TRACING_BRANCHES 489 help 490 This traces the events of likely and unlikely condition 491 calls in the kernel. The difference between this and the 492 "Trace likely/unlikely profiler" is that this is not a 493 histogram of the callers, but actually places the calling 494 events into a running trace buffer to see when and where the 495 events happened, as well as their results. 496 497 Say N if unsure. 498 499config BLK_DEV_IO_TRACE 500 bool "Support for tracing block IO actions" 501 depends on SYSFS 502 depends on BLOCK 503 select RELAY 504 select DEBUG_FS 505 select TRACEPOINTS 506 select GENERIC_TRACER 507 select STACKTRACE 508 help 509 Say Y here if you want to be able to trace the block layer actions 510 on a given queue. Tracing allows you to see any traffic happening 511 on a block device queue. For more information (and the userspace 512 support tools needed), fetch the blktrace tools from: 513 514 git://git.kernel.dk/blktrace.git 515 516 Tracing also is possible using the ftrace interface, e.g.: 517 518 echo 1 > /sys/block/sda/sda1/trace/enable 519 echo blk > /sys/kernel/debug/tracing/current_tracer 520 cat /sys/kernel/debug/tracing/trace_pipe 521 522 If unsure, say N. 523 524config KPROBE_EVENTS 525 depends on KPROBES 526 depends on HAVE_REGS_AND_STACK_ACCESS_API 527 bool "Enable kprobes-based dynamic events" 528 select TRACING 529 select PROBE_EVENTS 530 select DYNAMIC_EVENTS 531 default y 532 help 533 This allows the user to add tracing events (similar to tracepoints) 534 on the fly via the ftrace interface. See 535 Documentation/trace/kprobetrace.rst for more details. 536 537 Those events can be inserted wherever kprobes can probe, and record 538 various register and memory values. 539 540 This option is also required by perf-probe subcommand of perf tools. 541 If you want to use perf tools, this option is strongly recommended. 542 543config KPROBE_EVENTS_ON_NOTRACE 544 bool "Do NOT protect notrace function from kprobe events" 545 depends on KPROBE_EVENTS 546 depends on DYNAMIC_FTRACE 547 default n 548 help 549 This is only for the developers who want to debug ftrace itself 550 using kprobe events. 551 552 If kprobes can use ftrace instead of breakpoint, ftrace related 553 functions are protected from kprobe-events to prevent an infinite 554 recursion or any unexpected execution path which leads to a kernel 555 crash. 556 557 This option disables such protection and allows you to put kprobe 558 events on ftrace functions for debugging ftrace by itself. 559 Note that this might let you shoot yourself in the foot. 560 561 If unsure, say N. 562 563config UPROBE_EVENTS 564 bool "Enable uprobes-based dynamic events" 565 depends on ARCH_SUPPORTS_UPROBES 566 depends on MMU 567 depends on PERF_EVENTS 568 select UPROBES 569 select PROBE_EVENTS 570 select DYNAMIC_EVENTS 571 select TRACING 572 default y 573 help 574 This allows the user to add tracing events on top of userspace 575 dynamic events (similar to tracepoints) on the fly via the trace 576 events interface. Those events can be inserted wherever uprobes 577 can probe, and record various registers. 578 This option is required if you plan to use perf-probe subcommand 579 of perf tools on user space applications. 580 581config BPF_EVENTS 582 depends on BPF_SYSCALL 583 depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS 584 bool 585 default y 586 help 587 This allows the user to attach BPF programs to kprobe, uprobe, and 588 tracepoint events. 589 590config DYNAMIC_EVENTS 591 def_bool n 592 593config PROBE_EVENTS 594 def_bool n 595 596config BPF_KPROBE_OVERRIDE 597 bool "Enable BPF programs to override a kprobed function" 598 depends on BPF_EVENTS 599 depends on FUNCTION_ERROR_INJECTION 600 default n 601 help 602 Allows BPF to override the execution of a probed function and 603 set a different return value. This is used for error injection. 604 605config FTRACE_MCOUNT_RECORD 606 def_bool y 607 depends on DYNAMIC_FTRACE 608 depends on HAVE_FTRACE_MCOUNT_RECORD 609 610config FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY 611 bool 612 depends on FTRACE_MCOUNT_RECORD 613 614config FTRACE_MCOUNT_USE_CC 615 def_bool y 616 depends on $(cc-option,-mrecord-mcount) 617 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY 618 depends on FTRACE_MCOUNT_RECORD 619 620config FTRACE_MCOUNT_USE_OBJTOOL 621 def_bool y 622 depends on HAVE_OBJTOOL_MCOUNT 623 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY 624 depends on !FTRACE_MCOUNT_USE_CC 625 depends on FTRACE_MCOUNT_RECORD 626 627config FTRACE_MCOUNT_USE_RECORDMCOUNT 628 def_bool y 629 depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY 630 depends on !FTRACE_MCOUNT_USE_CC 631 depends on !FTRACE_MCOUNT_USE_OBJTOOL 632 depends on FTRACE_MCOUNT_RECORD 633 634config TRACING_MAP 635 bool 636 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG 637 help 638 tracing_map is a special-purpose lock-free map for tracing, 639 separated out as a stand-alone facility in order to allow it 640 to be shared between multiple tracers. It isn't meant to be 641 generally used outside of that context, and is normally 642 selected by tracers that use it. 643 644config SYNTH_EVENTS 645 bool "Synthetic trace events" 646 select TRACING 647 select DYNAMIC_EVENTS 648 default n 649 help 650 Synthetic events are user-defined trace events that can be 651 used to combine data from other trace events or in fact any 652 data source. Synthetic events can be generated indirectly 653 via the trace() action of histogram triggers or directly 654 by way of an in-kernel API. 655 656 See Documentation/trace/events.rst or 657 Documentation/trace/histogram.rst for details and examples. 658 659 If in doubt, say N. 660 661config HIST_TRIGGERS 662 bool "Histogram triggers" 663 depends on ARCH_HAVE_NMI_SAFE_CMPXCHG 664 select TRACING_MAP 665 select TRACING 666 select DYNAMIC_EVENTS 667 select SYNTH_EVENTS 668 default n 669 help 670 Hist triggers allow one or more arbitrary trace event fields 671 to be aggregated into hash tables and dumped to stdout by 672 reading a debugfs/tracefs file. They're useful for 673 gathering quick and dirty (though precise) summaries of 674 event activity as an initial guide for further investigation 675 using more advanced tools. 676 677 Inter-event tracing of quantities such as latencies is also 678 supported using hist triggers under this option. 679 680 See Documentation/trace/histogram.rst. 681 If in doubt, say N. 682 683config TRACE_EVENT_INJECT 684 bool "Trace event injection" 685 depends on TRACING 686 help 687 Allow user-space to inject a specific trace event into the ring 688 buffer. This is mainly used for testing purpose. 689 690 If unsure, say N. 691 692config TRACEPOINT_BENCHMARK 693 bool "Add tracepoint that benchmarks tracepoints" 694 help 695 This option creates the tracepoint "benchmark:benchmark_event". 696 When the tracepoint is enabled, it kicks off a kernel thread that 697 goes into an infinite loop (calling cond_resched() to let other tasks 698 run), and calls the tracepoint. Each iteration will record the time 699 it took to write to the tracepoint and the next iteration that 700 data will be passed to the tracepoint itself. That is, the tracepoint 701 will report the time it took to do the previous tracepoint. 702 The string written to the tracepoint is a static string of 128 bytes 703 to keep the time the same. The initial string is simply a write of 704 "START". The second string records the cold cache time of the first 705 write which is not added to the rest of the calculations. 706 707 As it is a tight loop, it benchmarks as hot cache. That's fine because 708 we care most about hot paths that are probably in cache already. 709 710 An example of the output: 711 712 START 713 first=3672 [COLD CACHED] 714 last=632 first=3672 max=632 min=632 avg=316 std=446 std^2=199712 715 last=278 first=3672 max=632 min=278 avg=303 std=316 std^2=100337 716 last=277 first=3672 max=632 min=277 avg=296 std=258 std^2=67064 717 last=273 first=3672 max=632 min=273 avg=292 std=224 std^2=50411 718 last=273 first=3672 max=632 min=273 avg=288 std=200 std^2=40389 719 last=281 first=3672 max=632 min=273 avg=287 std=183 std^2=33666 720 721 722config RING_BUFFER_BENCHMARK 723 tristate "Ring buffer benchmark stress tester" 724 depends on RING_BUFFER 725 help 726 This option creates a test to stress the ring buffer and benchmark it. 727 It creates its own ring buffer such that it will not interfere with 728 any other users of the ring buffer (such as ftrace). It then creates 729 a producer and consumer that will run for 10 seconds and sleep for 730 10 seconds. Each interval it will print out the number of events 731 it recorded and give a rough estimate of how long each iteration took. 732 733 It does not disable interrupts or raise its priority, so it may be 734 affected by processes that are running. 735 736 If unsure, say N. 737 738config TRACE_EVAL_MAP_FILE 739 bool "Show eval mappings for trace events" 740 depends on TRACING 741 help 742 The "print fmt" of the trace events will show the enum/sizeof names 743 instead of their values. This can cause problems for user space tools 744 that use this string to parse the raw data as user space does not know 745 how to convert the string to its value. 746 747 To fix this, there's a special macro in the kernel that can be used 748 to convert an enum/sizeof into its value. If this macro is used, then 749 the print fmt strings will be converted to their values. 750 751 If something does not get converted properly, this option can be 752 used to show what enums/sizeof the kernel tried to convert. 753 754 This option is for debugging the conversions. A file is created 755 in the tracing directory called "eval_map" that will show the 756 names matched with their values and what trace event system they 757 belong too. 758 759 Normally, the mapping of the strings to values will be freed after 760 boot up or module load. With this option, they will not be freed, as 761 they are needed for the "eval_map" file. Enabling this option will 762 increase the memory footprint of the running kernel. 763 764 If unsure, say N. 765 766config FTRACE_RECORD_RECURSION 767 bool "Record functions that recurse in function tracing" 768 depends on FUNCTION_TRACER 769 help 770 All callbacks that attach to the function tracing have some sort 771 of protection against recursion. Even though the protection exists, 772 it adds overhead. This option will create a file in the tracefs 773 file system called "recursed_functions" that will list the functions 774 that triggered a recursion. 775 776 This will add more overhead to cases that have recursion. 777 778 If unsure, say N 779 780config FTRACE_RECORD_RECURSION_SIZE 781 int "Max number of recursed functions to record" 782 default 128 783 depends on FTRACE_RECORD_RECURSION 784 help 785 This defines the limit of number of functions that can be 786 listed in the "recursed_functions" file, that lists all 787 the functions that caused a recursion to happen. 788 This file can be reset, but the limit can not change in 789 size at runtime. 790 791config RING_BUFFER_RECORD_RECURSION 792 bool "Record functions that recurse in the ring buffer" 793 depends on FTRACE_RECORD_RECURSION 794 # default y, because it is coupled with FTRACE_RECORD_RECURSION 795 default y 796 help 797 The ring buffer has its own internal recursion. Although when 798 recursion happens it wont cause harm because of the protection, 799 but it does cause an unwanted overhead. Enabling this option will 800 place where recursion was detected into the ftrace "recursed_functions" 801 file. 802 803 This will add more overhead to cases that have recursion. 804 805config GCOV_PROFILE_FTRACE 806 bool "Enable GCOV profiling on ftrace subsystem" 807 depends on GCOV_KERNEL 808 help 809 Enable GCOV profiling on ftrace subsystem for checking 810 which functions/lines are tested. 811 812 If unsure, say N. 813 814 Note that on a kernel compiled with this config, ftrace will 815 run significantly slower. 816 817config FTRACE_SELFTEST 818 bool 819 820config FTRACE_STARTUP_TEST 821 bool "Perform a startup test on ftrace" 822 depends on GENERIC_TRACER 823 select FTRACE_SELFTEST 824 help 825 This option performs a series of startup tests on ftrace. On bootup 826 a series of tests are made to verify that the tracer is 827 functioning properly. It will do tests on all the configured 828 tracers of ftrace. 829 830config EVENT_TRACE_STARTUP_TEST 831 bool "Run selftest on trace events" 832 depends on FTRACE_STARTUP_TEST 833 default y 834 help 835 This option performs a test on all trace events in the system. 836 It basically just enables each event and runs some code that 837 will trigger events (not necessarily the event it enables) 838 This may take some time run as there are a lot of events. 839 840config EVENT_TRACE_TEST_SYSCALLS 841 bool "Run selftest on syscall events" 842 depends on EVENT_TRACE_STARTUP_TEST 843 help 844 This option will also enable testing every syscall event. 845 It only enables the event and disables it and runs various loads 846 with the event enabled. This adds a bit more time for kernel boot 847 up since it runs this on every system call defined. 848 849 TBD - enable a way to actually call the syscalls as we test their 850 events 851 852config RING_BUFFER_STARTUP_TEST 853 bool "Ring buffer startup self test" 854 depends on RING_BUFFER 855 help 856 Run a simple self test on the ring buffer on boot up. Late in the 857 kernel boot sequence, the test will start that kicks off 858 a thread per cpu. Each thread will write various size events 859 into the ring buffer. Another thread is created to send IPIs 860 to each of the threads, where the IPI handler will also write 861 to the ring buffer, to test/stress the nesting ability. 862 If any anomalies are discovered, a warning will be displayed 863 and all ring buffers will be disabled. 864 865 The test runs for 10 seconds. This will slow your boot time 866 by at least 10 more seconds. 867 868 At the end of the test, statics and more checks are done. 869 It will output the stats of each per cpu buffer. What 870 was written, the sizes, what was read, what was lost, and 871 other similar details. 872 873 If unsure, say N 874 875config RING_BUFFER_VALIDATE_TIME_DELTAS 876 bool "Verify ring buffer time stamp deltas" 877 depends on RING_BUFFER 878 help 879 This will audit the time stamps on the ring buffer sub 880 buffer to make sure that all the time deltas for the 881 events on a sub buffer matches the current time stamp. 882 This audit is performed for every event that is not 883 interrupted, or interrupting another event. A check 884 is also made when traversing sub buffers to make sure 885 that all the deltas on the previous sub buffer do not 886 add up to be greater than the current time stamp. 887 888 NOTE: This adds significant overhead to recording of events, 889 and should only be used to test the logic of the ring buffer. 890 Do not use it on production systems. 891 892 Only say Y if you understand what this does, and you 893 still want it enabled. Otherwise say N 894 895config MMIOTRACE_TEST 896 tristate "Test module for mmiotrace" 897 depends on MMIOTRACE && m 898 help 899 This is a dumb module for testing mmiotrace. It is very dangerous 900 as it will write garbage to IO memory starting at a given address. 901 However, it should be safe to use on e.g. unused portion of VRAM. 902 903 Say N, unless you absolutely know what you are doing. 904 905config PREEMPTIRQ_DELAY_TEST 906 tristate "Test module to create a preempt / IRQ disable delay thread to test latency tracers" 907 depends on m 908 help 909 Select this option to build a test module that can help test latency 910 tracers by executing a preempt or irq disable section with a user 911 configurable delay. The module busy waits for the duration of the 912 critical section. 913 914 For example, the following invocation generates a burst of three 915 irq-disabled critical sections for 500us: 916 modprobe preemptirq_delay_test test_mode=irq delay=500 burst_size=3 917 918 What's more, if you want to attach the test on the cpu which the latency 919 tracer is running on, specify cpu_affinity=cpu_num at the end of the 920 command. 921 922 If unsure, say N 923 924config SYNTH_EVENT_GEN_TEST 925 tristate "Test module for in-kernel synthetic event generation" 926 depends on SYNTH_EVENTS 927 help 928 This option creates a test module to check the base 929 functionality of in-kernel synthetic event definition and 930 generation. 931 932 To test, insert the module, and then check the trace buffer 933 for the generated sample events. 934 935 If unsure, say N. 936 937config KPROBE_EVENT_GEN_TEST 938 tristate "Test module for in-kernel kprobe event generation" 939 depends on KPROBE_EVENTS 940 help 941 This option creates a test module to check the base 942 functionality of in-kernel kprobe event definition. 943 944 To test, insert the module, and then check the trace buffer 945 for the generated kprobe events. 946 947 If unsure, say N. 948 949config HIST_TRIGGERS_DEBUG 950 bool "Hist trigger debug support" 951 depends on HIST_TRIGGERS 952 help 953 Add "hist_debug" file for each event, which when read will 954 dump out a bunch of internal details about the hist triggers 955 defined on that event. 956 957 The hist_debug file serves a couple of purposes: 958 959 - Helps developers verify that nothing is broken. 960 961 - Provides educational information to support the details 962 of the hist trigger internals as described by 963 Documentation/trace/histogram-design.rst. 964 965 The hist_debug output only covers the data structures 966 related to the histogram definitions themselves and doesn't 967 display the internals of map buckets or variable values of 968 running histograms. 969 970 If unsure, say N. 971 972endif # FTRACE 973 974endif # TRACING_SUPPORT 975 976