790 lines · plain
1=======================2Kernel Probes (Kprobes)3=======================4 5:Author: Jim Keniston <jkenisto@us.ibm.com>6:Author: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>7:Author: Masami Hiramatsu <mhiramat@kernel.org>8 9.. CONTENTS10 11 1. Concepts: Kprobes, and Return Probes12 2. Architectures Supported13 3. Configuring Kprobes14 4. API Reference15 5. Kprobes Features and Limitations16 6. Probe Overhead17 7. TODO18 8. Kprobes Example19 9. Kretprobes Example20 10. Deprecated Features21 Appendix A: The kprobes debugfs interface22 Appendix B: The kprobes sysctl interface23 Appendix C: References24 25Concepts: Kprobes and Return Probes26=========================================27 28Kprobes enables you to dynamically break into any kernel routine and29collect debugging and performance information non-disruptively. You30can trap at almost any kernel code address [1]_, specifying a handler31routine to be invoked when the breakpoint is hit.32 33.. [1] some parts of the kernel code can not be trapped, see34 :ref:`kprobes_blacklist`)35 36There are currently two types of probes: kprobes, and kretprobes37(also called return probes). A kprobe can be inserted on virtually38any instruction in the kernel. A return probe fires when a specified39function returns.40 41In the typical case, Kprobes-based instrumentation is packaged as42a kernel module. The module's init function installs ("registers")43one or more probes, and the exit function unregisters them. A44registration function such as register_kprobe() specifies where45the probe is to be inserted and what handler is to be called when46the probe is hit.47 48There are also ``register_/unregister_*probes()`` functions for batch49registration/unregistration of a group of ``*probes``. These functions50can speed up unregistration process when you have to unregister51a lot of probes at once.52 53The next four subsections explain how the different types of54probes work and how jump optimization works. They explain certain55things that you'll need to know in order to make the best use of56Kprobes -- e.g., the difference between a pre_handler and57a post_handler, and how to use the maxactive and nmissed fields of58a kretprobe. But if you're in a hurry to start using Kprobes, you59can skip ahead to :ref:`kprobes_archs_supported`.60 61How Does a Kprobe Work?62-----------------------63 64When a kprobe is registered, Kprobes makes a copy of the probed65instruction and replaces the first byte(s) of the probed instruction66with a breakpoint instruction (e.g., int3 on i386 and x86_64).67 68When a CPU hits the breakpoint instruction, a trap occurs, the CPU's69registers are saved, and control passes to Kprobes via the70notifier_call_chain mechanism. Kprobes executes the "pre_handler"71associated with the kprobe, passing the handler the addresses of the72kprobe struct and the saved registers.73 74Next, Kprobes single-steps its copy of the probed instruction.75(It would be simpler to single-step the actual instruction in place,76but then Kprobes would have to temporarily remove the breakpoint77instruction. This would open a small time window when another CPU78could sail right past the probepoint.)79 80After the instruction is single-stepped, Kprobes executes the81"post_handler," if any, that is associated with the kprobe.82Execution then continues with the instruction following the probepoint.83 84Changing Execution Path85-----------------------86 87Since kprobes can probe into a running kernel code, it can change the88register set, including instruction pointer. This operation requires89maximum care, such as keeping the stack frame, recovering the execution90path etc. Since it operates on a running kernel and needs deep knowledge91of computer architecture and concurrent computing, you can easily shoot92your foot.93 94If you change the instruction pointer (and set up other related95registers) in pre_handler, you must return !0 so that kprobes stops96single stepping and just returns to the given address.97This also means post_handler should not be called anymore.98 99Note that this operation may be harder on some architectures which use100TOC (Table of Contents) for function call, since you have to setup a new101TOC for your function in your module, and recover the old one after102returning from it.103 104Return Probes105-------------106 107How Does a Return Probe Work?108^^^^^^^^^^^^^^^^^^^^^^^^^^^^^109 110When you call register_kretprobe(), Kprobes establishes a kprobe at111the entry to the function. When the probed function is called and this112probe is hit, Kprobes saves a copy of the return address, and replaces113the return address with the address of a "trampoline." The trampoline114is an arbitrary piece of code -- typically just a nop instruction.115At boot time, Kprobes registers a kprobe at the trampoline.116 117When the probed function executes its return instruction, control118passes to the trampoline and that probe is hit. Kprobes' trampoline119handler calls the user-specified return handler associated with the120kretprobe, then sets the saved instruction pointer to the saved return121address, and that's where execution resumes upon return from the trap.122 123While the probed function is executing, its return address is124stored in an object of type kretprobe_instance. Before calling125register_kretprobe(), the user sets the maxactive field of the126kretprobe struct to specify how many instances of the specified127function can be probed simultaneously. register_kretprobe()128pre-allocates the indicated number of kretprobe_instance objects.129 130For example, if the function is non-recursive and is called with a131spinlock held, maxactive = 1 should be enough. If the function is132non-recursive and can never relinquish the CPU (e.g., via a semaphore133or preemption), NR_CPUS should be enough. If maxactive <= 0, it is134set to a default value: max(10, 2*NR_CPUS).135 136It's not a disaster if you set maxactive too low; you'll just miss137some probes. In the kretprobe struct, the nmissed field is set to138zero when the return probe is registered, and is incremented every139time the probed function is entered but there is no kretprobe_instance140object available for establishing the return probe.141 142Kretprobe entry-handler143^^^^^^^^^^^^^^^^^^^^^^^144 145Kretprobes also provides an optional user-specified handler which runs146on function entry. This handler is specified by setting the entry_handler147field of the kretprobe struct. Whenever the kprobe placed by kretprobe at the148function entry is hit, the user-defined entry_handler, if any, is invoked.149If the entry_handler returns 0 (success) then a corresponding return handler150is guaranteed to be called upon function return. If the entry_handler151returns a non-zero error then Kprobes leaves the return address as is, and152the kretprobe has no further effect for that particular function instance.153 154Multiple entry and return handler invocations are matched using the unique155kretprobe_instance object associated with them. Additionally, a user156may also specify per return-instance private data to be part of each157kretprobe_instance object. This is especially useful when sharing private158data between corresponding user entry and return handlers. The size of each159private data object can be specified at kretprobe registration time by160setting the data_size field of the kretprobe struct. This data can be161accessed through the data field of each kretprobe_instance object.162 163In case probed function is entered but there is no kretprobe_instance164object available, then in addition to incrementing the nmissed count,165the user entry_handler invocation is also skipped.166 167.. _kprobes_jump_optimization:168 169How Does Jump Optimization Work?170--------------------------------171 172If your kernel is built with CONFIG_OPTPROBES=y (currently this flag173is automatically set 'y' on x86/x86-64, non-preemptive kernel) and174the "debug.kprobes_optimization" kernel parameter is set to 1 (see175sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump176instruction instead of a breakpoint instruction at each probepoint.177 178Init a Kprobe179^^^^^^^^^^^^^180 181When a probe is registered, before attempting this optimization,182Kprobes inserts an ordinary, breakpoint-based kprobe at the specified183address. So, even if it's not possible to optimize this particular184probepoint, there'll be a probe there.185 186Safety Check187^^^^^^^^^^^^188 189Before optimizing a probe, Kprobes performs the following safety checks:190 191- Kprobes verifies that the region that will be replaced by the jump192 instruction (the "optimized region") lies entirely within one function.193 (A jump instruction is multiple bytes, and so may overlay multiple194 instructions.)195 196- Kprobes analyzes the entire function and verifies that there is no197 jump into the optimized region. Specifically:198 199 - the function contains no indirect jump;200 - the function contains no instruction that causes an exception (since201 the fixup code triggered by the exception could jump back into the202 optimized region -- Kprobes checks the exception tables to verify this);203 - there is no near jump to the optimized region (other than to the first204 byte).205 206- For each instruction in the optimized region, Kprobes verifies that207 the instruction can be executed out of line.208 209Preparing Detour Buffer210^^^^^^^^^^^^^^^^^^^^^^^211 212Next, Kprobes prepares a "detour" buffer, which contains the following213instruction sequence:214 215- code to push the CPU's registers (emulating a breakpoint trap)216- a call to the trampoline code which calls user's probe handlers.217- code to restore registers218- the instructions from the optimized region219- a jump back to the original execution path.220 221Pre-optimization222^^^^^^^^^^^^^^^^223 224After preparing the detour buffer, Kprobes verifies that none of the225following situations exist:226 227- The probe has a post_handler.228- Other instructions in the optimized region are probed.229- The probe is disabled.230 231In any of the above cases, Kprobes won't start optimizing the probe.232Since these are temporary situations, Kprobes tries to start233optimizing it again if the situation is changed.234 235If the kprobe can be optimized, Kprobes enqueues the kprobe to an236optimizing list, and kicks the kprobe-optimizer workqueue to optimize237it. If the to-be-optimized probepoint is hit before being optimized,238Kprobes returns control to the original instruction path by setting239the CPU's instruction pointer to the copied code in the detour buffer240-- thus at least avoiding the single-step.241 242Optimization243^^^^^^^^^^^^244 245The Kprobe-optimizer doesn't insert the jump instruction immediately;246rather, it calls synchronize_rcu() for safety first, because it's247possible for a CPU to be interrupted in the middle of executing the248optimized region [3]_. As you know, synchronize_rcu() can ensure249that all interruptions that were active when synchronize_rcu()250was called are done, but only if CONFIG_PREEMPT=n. So, this version251of kprobe optimization supports only kernels with CONFIG_PREEMPT=n [4]_.252 253After that, the Kprobe-optimizer calls stop_machine() to replace254the optimized region with a jump instruction to the detour buffer,255using text_poke_smp().256 257Unoptimization258^^^^^^^^^^^^^^259 260When an optimized kprobe is unregistered, disabled, or blocked by261another kprobe, it will be unoptimized. If this happens before262the optimization is complete, the kprobe is just dequeued from the263optimized list. If the optimization has been done, the jump is264replaced with the original code (except for an int3 breakpoint in265the first byte) by using text_poke_smp().266 267.. [3] Please imagine that the 2nd instruction is interrupted and then268 the optimizer replaces the 2nd instruction with the jump *address*269 while the interrupt handler is running. When the interrupt270 returns to original address, there is no valid instruction,271 and it causes an unexpected result.272 273.. [4] This optimization-safety checking may be replaced with the274 stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y275 kernel.276 277NOTE for geeks:278The jump optimization changes the kprobe's pre_handler behavior.279Without optimization, the pre_handler can change the kernel's execution280path by changing regs->ip and returning 1. However, when the probe281is optimized, that modification is ignored. Thus, if you want to282tweak the kernel's execution path, you need to suppress optimization,283using one of the following techniques:284 285- Specify an empty function for the kprobe's post_handler.286 287or288 289- Execute 'sysctl -w debug.kprobes_optimization=n'290 291.. _kprobes_blacklist:292 293Blacklist294---------295 296Kprobes can probe most of the kernel except itself. This means297that there are some functions where kprobes cannot probe. Probing298(trapping) such functions can cause a recursive trap (e.g. double299fault) or the nested probe handler may never be called.300Kprobes manages such functions as a blacklist.301If you want to add a function into the blacklist, you just need302to (1) include linux/kprobes.h and (2) use NOKPROBE_SYMBOL() macro303to specify a blacklisted function.304Kprobes checks the given probe address against the blacklist and305rejects registering it, if the given address is in the blacklist.306 307.. _kprobes_archs_supported:308 309Architectures Supported310=======================311 312Kprobes and return probes are implemented on the following313architectures:314 315- i386 (Supports jump optimization)316- x86_64 (AMD-64, EM64T) (Supports jump optimization)317- ppc64318- sparc64 (Return probes not yet implemented.)319- arm320- ppc321- mips322- s390323- parisc324- loongarch325- riscv326 327Configuring Kprobes328===================329 330When configuring the kernel using make menuconfig/xconfig/oldconfig,331ensure that CONFIG_KPROBES is set to "y", look for "Kprobes" under332"General architecture-dependent options".333 334So that you can load and unload Kprobes-based instrumentation modules,335make sure "Loadable module support" (CONFIG_MODULES) and "Module336unloading" (CONFIG_MODULE_UNLOAD) are set to "y".337 338Also make sure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL339are set to "y", since kallsyms_lookup_name() is used by the in-kernel340kprobe address resolution code.341 342If you need to insert a probe in the middle of a function, you may find343it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),344so you can use "objdump -d -l vmlinux" to see the source-to-object345code mapping.346 347API Reference348=============349 350The Kprobes API includes a "register" function and an "unregister"351function for each type of probe. The API also includes "register_*probes"352and "unregister_*probes" functions for (un)registering arrays of probes.353Here are terse, mini-man-page specifications for these functions and354the associated probe handlers that you'll write. See the files in the355samples/kprobes/ sub-directory for examples.356 357register_kprobe358---------------359 360::361 362 #include <linux/kprobes.h>363 int register_kprobe(struct kprobe *kp);364 365Sets a breakpoint at the address kp->addr. When the breakpoint is hit, Kprobes366calls kp->pre_handler. After the probed instruction is single-stepped, Kprobe367calls kp->post_handler. Any or all handlers can be NULL. If kp->flags is set368KPROBE_FLAG_DISABLED, that kp will be registered but disabled, so, its handlers369aren't hit until calling enable_kprobe(kp).370 371.. note::372 373 1. With the introduction of the "symbol_name" field to struct kprobe,374 the probepoint address resolution will now be taken care of by the kernel.375 The following will now work::376 377 kp.symbol_name = "symbol_name";378 379 (64-bit powerpc intricacies such as function descriptors are handled380 transparently)381 382 2. Use the "offset" field of struct kprobe if the offset into the symbol383 to install a probepoint is known. This field is used to calculate the384 probepoint.385 386 3. Specify either the kprobe "symbol_name" OR the "addr". If both are387 specified, kprobe registration will fail with -EINVAL.388 389 4. With CISC architectures (such as i386 and x86_64), the kprobes code390 does not validate if the kprobe.addr is at an instruction boundary.391 Use "offset" with caution.392 393register_kprobe() returns 0 on success, or a negative errno otherwise.394 395User's pre-handler (kp->pre_handler)::396 397 #include <linux/kprobes.h>398 #include <linux/ptrace.h>399 int pre_handler(struct kprobe *p, struct pt_regs *regs);400 401Called with p pointing to the kprobe associated with the breakpoint,402and regs pointing to the struct containing the registers saved when403the breakpoint was hit. Return 0 here unless you're a Kprobes geek.404 405User's post-handler (kp->post_handler)::406 407 #include <linux/kprobes.h>408 #include <linux/ptrace.h>409 void post_handler(struct kprobe *p, struct pt_regs *regs,410 unsigned long flags);411 412p and regs are as described for the pre_handler. flags always seems413to be zero.414 415register_kretprobe416------------------417 418::419 420 #include <linux/kprobes.h>421 int register_kretprobe(struct kretprobe *rp);422 423Establishes a return probe for the function whose address is424rp->kp.addr. When that function returns, Kprobes calls rp->handler.425You must set rp->maxactive appropriately before you call426register_kretprobe(); see "How Does a Return Probe Work?" for details.427 428register_kretprobe() returns 0 on success, or a negative errno429otherwise.430 431User's return-probe handler (rp->handler)::432 433 #include <linux/kprobes.h>434 #include <linux/ptrace.h>435 int kretprobe_handler(struct kretprobe_instance *ri,436 struct pt_regs *regs);437 438regs is as described for kprobe.pre_handler. ri points to the439kretprobe_instance object, of which the following fields may be440of interest:441 442- ret_addr: the return address443- rp: points to the corresponding kretprobe object444- task: points to the corresponding task struct445- data: points to per return-instance private data; see "Kretprobe446 entry-handler" for details.447 448The regs_return_value(regs) macro provides a simple abstraction to449extract the return value from the appropriate register as defined by450the architecture's ABI.451 452The handler's return value is currently ignored.453 454unregister_*probe455------------------456 457::458 459 #include <linux/kprobes.h>460 void unregister_kprobe(struct kprobe *kp);461 void unregister_kretprobe(struct kretprobe *rp);462 463Removes the specified probe. The unregister function can be called464at any time after the probe has been registered.465 466.. note::467 468 If the functions find an incorrect probe (ex. an unregistered probe),469 they clear the addr field of the probe.470 471register_*probes472----------------473 474::475 476 #include <linux/kprobes.h>477 int register_kprobes(struct kprobe **kps, int num);478 int register_kretprobes(struct kretprobe **rps, int num);479 480Registers each of the num probes in the specified array. If any481error occurs during registration, all probes in the array, up to482the bad probe, are safely unregistered before the register_*probes483function returns.484 485- kps/rps: an array of pointers to ``*probe`` data structures486- num: the number of the array entries.487 488.. note::489 490 You have to allocate(or define) an array of pointers and set all491 of the array entries before using these functions.492 493unregister_*probes494------------------495 496::497 498 #include <linux/kprobes.h>499 void unregister_kprobes(struct kprobe **kps, int num);500 void unregister_kretprobes(struct kretprobe **rps, int num);501 502Removes each of the num probes in the specified array at once.503 504.. note::505 506 If the functions find some incorrect probes (ex. unregistered507 probes) in the specified array, they clear the addr field of those508 incorrect probes. However, other probes in the array are509 unregistered correctly.510 511disable_*probe512--------------513 514::515 516 #include <linux/kprobes.h>517 int disable_kprobe(struct kprobe *kp);518 int disable_kretprobe(struct kretprobe *rp);519 520Temporarily disables the specified ``*probe``. You can enable it again by using521enable_*probe(). You must specify the probe which has been registered.522 523enable_*probe524-------------525 526::527 528 #include <linux/kprobes.h>529 int enable_kprobe(struct kprobe *kp);530 int enable_kretprobe(struct kretprobe *rp);531 532Enables ``*probe`` which has been disabled by disable_*probe(). You must specify533the probe which has been registered.534 535Kprobes Features and Limitations536================================537 538Kprobes allows multiple probes at the same address. Also,539a probepoint for which there is a post_handler cannot be optimized.540So if you install a kprobe with a post_handler, at an optimized541probepoint, the probepoint will be unoptimized automatically.542 543In general, you can install a probe anywhere in the kernel.544In particular, you can probe interrupt handlers. Known exceptions545are discussed in this section.546 547The register_*probe functions will return -EINVAL if you attempt548to install a probe in the code that implements Kprobes (mostly549kernel/kprobes.c and ``arch/*/kernel/kprobes.c``, but also functions such550as do_page_fault and notifier_call_chain).551 552If you install a probe in an inline-able function, Kprobes makes553no attempt to chase down all inline instances of the function and554install probes there. gcc may inline a function without being asked,555so keep this in mind if you're not seeing the probe hits you expect.556 557A probe handler can modify the environment of the probed function558-- e.g., by modifying kernel data structures, or by modifying the559contents of the pt_regs struct (which are restored to the registers560upon return from the breakpoint). So Kprobes can be used, for example,561to install a bug fix or to inject faults for testing. Kprobes, of562course, has no way to distinguish the deliberately injected faults563from the accidental ones. Don't drink and probe.564 565Kprobes makes no attempt to prevent probe handlers from stepping on566each other -- e.g., probing printk() and then calling printk() from a567probe handler. If a probe handler hits a probe, that second probe's568handlers won't be run in that instance, and the kprobe.nmissed member569of the second probe will be incremented.570 571As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of572the same handler) may run concurrently on different CPUs.573 574Kprobes does not use mutexes or allocate memory except during575registration and unregistration.576 577Probe handlers are run with preemption disabled or interrupt disabled,578which depends on the architecture and optimization state. (e.g.,579kretprobe handlers and optimized kprobe handlers run without interrupt580disabled on x86/x86-64). In any case, your handler should not yield581the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O).582 583Since a return probe is implemented by replacing the return584address with the trampoline's address, stack backtraces and calls585to __builtin_return_address() will typically yield the trampoline's586address instead of the real return address for kretprobed functions.587(As far as we can tell, __builtin_return_address() is used only588for instrumentation and error reporting.)589 590If the number of times a function is called does not match the number591of times it returns, registering a return probe on that function may592produce undesirable results. In such a case, a line:593kretprobe BUG!: Processing kretprobe d000000000041aa8 @ c00000000004f48c594gets printed. With this information, one will be able to correlate the595exact instance of the kretprobe that caused the problem. We have the596do_exit() case covered. do_execve() and do_fork() are not an issue.597We're unaware of other specific cases where this could be a problem.598 599If, upon entry to or exit from a function, the CPU is running on600a stack other than that of the current task, registering a return601probe on that function may produce undesirable results. For this602reason, Kprobes doesn't support return probes (or kprobes)603on the x86_64 version of __switch_to(); the registration functions604return -EINVAL.605 606On x86/x86-64, since the Jump Optimization of Kprobes modifies607instructions widely, there are some limitations to optimization. To608explain it, we introduce some terminology. Imagine a 3-instruction609sequence consisting of a two 2-byte instructions and one 3-byte610instruction.611 612::613 614 IA615 |616 [-2][-1][0][1][2][3][4][5][6][7]617 [ins1][ins2][ ins3 ]618 [<- DCR ->]619 [<- JTPR ->]620 621 ins1: 1st Instruction622 ins2: 2nd Instruction623 ins3: 3rd Instruction624 IA: Insertion Address625 JTPR: Jump Target Prohibition Region626 DCR: Detoured Code Region627 628The instructions in DCR are copied to the out-of-line buffer629of the kprobe, because the bytes in DCR are replaced by630a 5-byte jump instruction. So there are several limitations.631 632a) The instructions in DCR must be relocatable.633b) The instructions in DCR must not include a call instruction.634c) JTPR must not be targeted by any jump or call instruction.635d) DCR must not straddle the border between functions.636 637Anyway, these limitations are checked by the in-kernel instruction638decoder, so you don't need to worry about that.639 640Probe Overhead641==============642 643On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0644microseconds to process. Specifically, a benchmark that hits the same645probepoint repeatedly, firing a simple handler each time, reports 1-2646million hits per second, depending on the architecture. A return-probe647hit typically takes 50-75% longer than a kprobe hit.648When you have a return probe set on a function, adding a kprobe at649the entry to that function adds essentially no overhead.650 651Here are sample overhead figures (in usec) for different architectures::652 653 k = kprobe; r = return probe; kr = kprobe + return probe654 on same function655 656 i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips657 k = 0.57 usec; r = 0.92; kr = 0.99658 659 x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips660 k = 0.49 usec; r = 0.80; kr = 0.82661 662 ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)663 k = 0.77 usec; r = 1.26; kr = 1.45664 665Optimized Probe Overhead666------------------------667 668Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to669process. Here are sample overhead figures (in usec) for x86 architectures::670 671 k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,672 r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.673 674 i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips675 k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33676 677 x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips678 k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30679 680TODO681====682 683a. SystemTap (http://sourceware.org/systemtap): Provides a simplified684 programming interface for probe-based instrumentation. Try it out.685b. Kernel return probes for sparc64.686c. Support for other architectures.687d. User-space probes.688e. Watchpoint probes (which fire on data references).689 690Kprobes Example691===============692 693See samples/kprobes/kprobe_example.c694 695Kretprobes Example696==================697 698See samples/kprobes/kretprobe_example.c699 700Deprecated Features701===================702 703Jprobes is now a deprecated feature. People who are depending on it should704migrate to other tracing features or use older kernels. Please consider to705migrate your tool to one of the following options:706 707- Use trace-event to trace target function with arguments.708 709 trace-event is a low-overhead (and almost no visible overhead if it710 is off) statically defined event interface. You can define new events711 and trace it via ftrace or any other tracing tools.712 713 See the following urls:714 715 - https://lwn.net/Articles/379903/716 - https://lwn.net/Articles/381064/717 - https://lwn.net/Articles/383362/718 719- Use ftrace dynamic events (kprobe event) with perf-probe.720 721 If you build your kernel with debug info (CONFIG_DEBUG_INFO=y), you can722 find which register/stack is assigned to which local variable or arguments723 by using perf-probe and set up new event to trace it.724 725 See following documents:726 727 - Documentation/trace/kprobetrace.rst728 - Documentation/trace/events.rst729 - tools/perf/Documentation/perf-probe.txt730 731 732The kprobes debugfs interface733=============================734 735 736With recent kernels (> 2.6.20) the list of registered kprobes is visible737under the /sys/kernel/debug/kprobes/ directory (assuming debugfs is mounted at //sys/kernel/debug).738 739/sys/kernel/debug/kprobes/list: Lists all registered probes on the system::740 741 c015d71a k vfs_read+0x0742 c03dedc5 r tcp_v4_rcv+0x0743 744The first column provides the kernel address where the probe is inserted.745The second column identifies the type of probe (k - kprobe and r - kretprobe)746while the third column specifies the symbol+offset of the probe.747If the probed function belongs to a module, the module name is also748specified. Following columns show probe status. If the probe is on749a virtual address that is no longer valid (module init sections, module750virtual addresses that correspond to modules that've been unloaded),751such probes are marked with [GONE]. If the probe is temporarily disabled,752such probes are marked with [DISABLED]. If the probe is optimized, it is753marked with [OPTIMIZED]. If the probe is ftrace-based, it is marked with754[FTRACE].755 756/sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.757 758Provides a knob to globally and forcibly turn registered kprobes ON or OFF.759By default, all kprobes are enabled. By echoing "0" to this file, all760registered probes will be disarmed, till such time a "1" is echoed to this761file. Note that this knob just disarms and arms all kprobes and doesn't762change each probe's disabling state. This means that disabled kprobes (marked763[DISABLED]) will be not enabled if you turn ON all kprobes by this knob.764 765 766The kprobes sysctl interface767============================768 769/proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.770 771When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides772a knob to globally and forcibly turn jump optimization (see section773:ref:`kprobes_jump_optimization`) ON or OFF. By default, jump optimization774is allowed (ON). If you echo "0" to this file or set775"debug.kprobes_optimization" to 0 via sysctl, all optimized probes will be776unoptimized, and any new probes registered after that will not be optimized.777 778Note that this knob *changes* the optimized state. This means that optimized779probes (marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be780removed). If the knob is turned on, they will be optimized again.781 782References783==========784 785For additional information on Kprobes, refer to the following URLs:786 787- https://lwn.net/Articles/132196/788- https://www.kernel.org/doc/ols/2006/ols2006v2-pages-109-124.pdf789 790