Root/Documentation/kprobes.txt

1Title : Kernel Probes (Kprobes)
2Authors : Jim Keniston <jkenisto@us.ibm.com>
3    : Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
4    : Masami Hiramatsu <mhiramat@redhat.com>
5
6CONTENTS
7
81. Concepts: Kprobes, Jprobes, Return Probes
92. Architectures Supported
103. Configuring Kprobes
114. API Reference
125. Kprobes Features and Limitations
136. Probe Overhead
147. TODO
158. Kprobes Example
169. Jprobes Example
1710. Kretprobes Example
18Appendix A: The kprobes debugfs interface
19Appendix B: The kprobes sysctl interface
20
211. Concepts: Kprobes, Jprobes, Return Probes
22
23Kprobes enables you to dynamically break into any kernel routine and
24collect debugging and performance information non-disruptively. You
25can trap at almost any kernel code address, specifying a handler
26routine to be invoked when the breakpoint is hit.
27
28There are currently three types of probes: kprobes, jprobes, and
29kretprobes (also called return probes). A kprobe can be inserted
30on virtually any instruction in the kernel. A jprobe is inserted at
31the entry to a kernel function, and provides convenient access to the
32function's arguments. A return probe fires when a specified function
33returns.
34
35In the typical case, Kprobes-based instrumentation is packaged as
36a kernel module. The module's init function installs ("registers")
37one or more probes, and the exit function unregisters them. A
38registration function such as register_kprobe() specifies where
39the probe is to be inserted and what handler is to be called when
40the probe is hit.
41
42There are also register_/unregister_*probes() functions for batch
43registration/unregistration of a group of *probes. These functions
44can speed up unregistration process when you have to unregister
45a lot of probes at once.
46
47The next four subsections explain how the different types of
48probes work and how jump optimization works. They explain certain
49things that you'll need to know in order to make the best use of
50Kprobes -- e.g., the difference between a pre_handler and
51a post_handler, and how to use the maxactive and nmissed fields of
52a kretprobe. But if you're in a hurry to start using Kprobes, you
53can skip ahead to section 2.
54
551.1 How Does a Kprobe Work?
56
57When a kprobe is registered, Kprobes makes a copy of the probed
58instruction and replaces the first byte(s) of the probed instruction
59with a breakpoint instruction (e.g., int3 on i386 and x86_64).
60
61When a CPU hits the breakpoint instruction, a trap occurs, the CPU's
62registers are saved, and control passes to Kprobes via the
63notifier_call_chain mechanism. Kprobes executes the "pre_handler"
64associated with the kprobe, passing the handler the addresses of the
65kprobe struct and the saved registers.
66
67Next, Kprobes single-steps its copy of the probed instruction.
68(It would be simpler to single-step the actual instruction in place,
69but then Kprobes would have to temporarily remove the breakpoint
70instruction. This would open a small time window when another CPU
71could sail right past the probepoint.)
72
73After the instruction is single-stepped, Kprobes executes the
74"post_handler," if any, that is associated with the kprobe.
75Execution then continues with the instruction following the probepoint.
76
771.2 How Does a Jprobe Work?
78
79A jprobe is implemented using a kprobe that is placed on a function's
80entry point. It employs a simple mirroring principle to allow
81seamless access to the probed function's arguments. The jprobe
82handler routine should have the same signature (arg list and return
83type) as the function being probed, and must always end by calling
84the Kprobes function jprobe_return().
85
86Here's how it works. When the probe is hit, Kprobes makes a copy of
87the saved registers and a generous portion of the stack (see below).
88Kprobes then points the saved instruction pointer at the jprobe's
89handler routine, and returns from the trap. As a result, control
90passes to the handler, which is presented with the same register and
91stack contents as the probed function. When it is done, the handler
92calls jprobe_return(), which traps again to restore the original stack
93contents and processor state and switch to the probed function.
94
95By convention, the callee owns its arguments, so gcc may produce code
96that unexpectedly modifies that portion of the stack. This is why
97Kprobes saves a copy of the stack and restores it after the jprobe
98handler has run. Up to MAX_STACK_SIZE bytes are copied -- e.g.,
9964 bytes on i386.
100
101Note that the probed function's args may be passed on the stack
102or in registers. The jprobe will work in either case, so long as the
103handler's prototype matches that of the probed function.
104
1051.3 Return Probes
106
1071.3.1 How Does a Return Probe Work?
108
109When you call register_kretprobe(), Kprobes establishes a kprobe at
110the entry to the function. When the probed function is called and this
111probe is hit, Kprobes saves a copy of the return address, and replaces
112the return address with the address of a "trampoline." The trampoline
113is an arbitrary piece of code -- typically just a nop instruction.
114At boot time, Kprobes registers a kprobe at the trampoline.
115
116When the probed function executes its return instruction, control
117passes to the trampoline and that probe is hit. Kprobes' trampoline
118handler calls the user-specified return handler associated with the
119kretprobe, then sets the saved instruction pointer to the saved return
120address, and that's where execution resumes upon return from the trap.
121
122While the probed function is executing, its return address is
123stored in an object of type kretprobe_instance. Before calling
124register_kretprobe(), the user sets the maxactive field of the
125kretprobe struct to specify how many instances of the specified
126function can be probed simultaneously. register_kretprobe()
127pre-allocates the indicated number of kretprobe_instance objects.
128
129For example, if the function is non-recursive and is called with a
130spinlock held, maxactive = 1 should be enough. If the function is
131non-recursive and can never relinquish the CPU (e.g., via a semaphore
132or preemption), NR_CPUS should be enough. If maxactive <= 0, it is
133set to a default value. If CONFIG_PREEMPT is enabled, the default
134is max(10, 2*NR_CPUS). Otherwise, the default is NR_CPUS.
135
136It's not a disaster if you set maxactive too low; you'll just miss
137some probes. In the kretprobe struct, the nmissed field is set to
138zero when the return probe is registered, and is incremented every
139time the probed function is entered but there is no kretprobe_instance
140object available for establishing the return probe.
141
1421.3.2 Kretprobe entry-handler
143
144Kretprobes also provides an optional user-specified handler which runs
145on function entry. This handler is specified by setting the entry_handler
146field of the kretprobe struct. Whenever the kprobe placed by kretprobe at the
147function entry is hit, the user-defined entry_handler, if any, is invoked.
148If the entry_handler returns 0 (success) then a corresponding return handler
149is guaranteed to be called upon function return. If the entry_handler
150returns a non-zero error then Kprobes leaves the return address as is, and
151the kretprobe has no further effect for that particular function instance.
152
153Multiple entry and return handler invocations are matched using the unique
154kretprobe_instance object associated with them. Additionally, a user
155may also specify per return-instance private data to be part of each
156kretprobe_instance object. This is especially useful when sharing private
157data between corresponding user entry and return handlers. The size of each
158private data object can be specified at kretprobe registration time by
159setting the data_size field of the kretprobe struct. This data can be
160accessed through the data field of each kretprobe_instance object.
161
162In case probed function is entered but there is no kretprobe_instance
163object available, then in addition to incrementing the nmissed count,
164the user entry_handler invocation is also skipped.
165
1661.4 How Does Jump Optimization Work?
167
168If you configured your kernel with CONFIG_OPTPROBES=y (currently
169this option is supported on x86/x86-64, non-preemptive kernel) and
170the "debug.kprobes_optimization" kernel parameter is set to 1 (see
171sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
172instruction instead of a breakpoint instruction at each probepoint.
173
1741.4.1 Init a Kprobe
175
176When a probe is registered, before attempting this optimization,
177Kprobes inserts an ordinary, breakpoint-based kprobe at the specified
178address. So, even if it's not possible to optimize this particular
179probepoint, there'll be a probe there.
180
1811.4.2 Safety Check
182
183Before optimizing a probe, Kprobes performs the following safety checks:
184
185- Kprobes verifies that the region that will be replaced by the jump
186instruction (the "optimized region") lies entirely within one function.
187(A jump instruction is multiple bytes, and so may overlay multiple
188instructions.)
189
190- Kprobes analyzes the entire function and verifies that there is no
191jump into the optimized region. Specifically:
192  - the function contains no indirect jump;
193  - the function contains no instruction that causes an exception (since
194  the fixup code triggered by the exception could jump back into the
195  optimized region -- Kprobes checks the exception tables to verify this);
196  and
197  - there is no near jump to the optimized region (other than to the first
198  byte).
199
200- For each instruction in the optimized region, Kprobes verifies that
201the instruction can be executed out of line.
202
2031.4.3 Preparing Detour Buffer
204
205Next, Kprobes prepares a "detour" buffer, which contains the following
206instruction sequence:
207- code to push the CPU's registers (emulating a breakpoint trap)
208- a call to the trampoline code which calls user's probe handlers.
209- code to restore registers
210- the instructions from the optimized region
211- a jump back to the original execution path.
212
2131.4.4 Pre-optimization
214
215After preparing the detour buffer, Kprobes verifies that none of the
216following situations exist:
217- The probe has either a break_handler (i.e., it's a jprobe) or a
218post_handler.
219- Other instructions in the optimized region are probed.
220- The probe is disabled.
221In any of the above cases, Kprobes won't start optimizing the probe.
222Since these are temporary situations, Kprobes tries to start
223optimizing it again if the situation is changed.
224
225If the kprobe can be optimized, Kprobes enqueues the kprobe to an
226optimizing list, and kicks the kprobe-optimizer workqueue to optimize
227it. If the to-be-optimized probepoint is hit before being optimized,
228Kprobes returns control to the original instruction path by setting
229the CPU's instruction pointer to the copied code in the detour buffer
230-- thus at least avoiding the single-step.
231
2321.4.5 Optimization
233
234The Kprobe-optimizer doesn't insert the jump instruction immediately;
235rather, it calls synchronize_sched() for safety first, because it's
236possible for a CPU to be interrupted in the middle of executing the
237optimized region(*). As you know, synchronize_sched() can ensure
238that all interruptions that were active when synchronize_sched()
239was called are done, but only if CONFIG_PREEMPT=n. So, this version
240of kprobe optimization supports only kernels with CONFIG_PREEMPT=n.(**)
241
242After that, the Kprobe-optimizer calls stop_machine() to replace
243the optimized region with a jump instruction to the detour buffer,
244using text_poke_smp().
245
2461.4.6 Unoptimization
247
248When an optimized kprobe is unregistered, disabled, or blocked by
249another kprobe, it will be unoptimized. If this happens before
250the optimization is complete, the kprobe is just dequeued from the
251optimized list. If the optimization has been done, the jump is
252replaced with the original code (except for an int3 breakpoint in
253the first byte) by using text_poke_smp().
254
255(*)Please imagine that the 2nd instruction is interrupted and then
256the optimizer replaces the 2nd instruction with the jump *address*
257while the interrupt handler is running. When the interrupt
258returns to original address, there is no valid instruction,
259and it causes an unexpected result.
260
261(**)This optimization-safety checking may be replaced with the
262stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
263kernel.
264
265NOTE for geeks:
266The jump optimization changes the kprobe's pre_handler behavior.
267Without optimization, the pre_handler can change the kernel's execution
268path by changing regs->ip and returning 1. However, when the probe
269is optimized, that modification is ignored. Thus, if you want to
270tweak the kernel's execution path, you need to suppress optimization,
271using one of the following techniques:
272- Specify an empty function for the kprobe's post_handler or break_handler.
273 or
274- Config CONFIG_OPTPROBES=n.
275 or
276- Execute 'sysctl -w debug.kprobes_optimization=n'
277
2782. Architectures Supported
279
280Kprobes, jprobes, and return probes are implemented on the following
281architectures:
282
283- i386 (Supports jump optimization)
284- x86_64 (AMD-64, EM64T) (Supports jump optimization)
285- ppc64
286- ia64 (Does not support probes on instruction slot1.)
287- sparc64 (Return probes not yet implemented.)
288- arm
289- ppc
290
2913. Configuring Kprobes
292
293When configuring the kernel using make menuconfig/xconfig/oldconfig,
294ensure that CONFIG_KPROBES is set to "y". Under "Instrumentation
295Support", look for "Kprobes".
296
297So that you can load and unload Kprobes-based instrumentation modules,
298make sure "Loadable module support" (CONFIG_MODULES) and "Module
299unloading" (CONFIG_MODULE_UNLOAD) are set to "y".
300
301Also make sure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL
302are set to "y", since kallsyms_lookup_name() is used by the in-kernel
303kprobe address resolution code.
304
305If you need to insert a probe in the middle of a function, you may find
306it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
307so you can use "objdump -d -l vmlinux" to see the source-to-object
308code mapping.
309
310If you want to reduce probing overhead, set "Kprobes jump optimization
311support" (CONFIG_OPTPROBES) to "y". You can find this option under the
312"Kprobes" line.
313
3144. API Reference
315
316The Kprobes API includes a "register" function and an "unregister"
317function for each type of probe. The API also includes "register_*probes"
318and "unregister_*probes" functions for (un)registering arrays of probes.
319Here are terse, mini-man-page specifications for these functions and
320the associated probe handlers that you'll write. See the files in the
321samples/kprobes/ sub-directory for examples.
322
3234.1 register_kprobe
324
325#include <linux/kprobes.h>
326int register_kprobe(struct kprobe *kp);
327
328Sets a breakpoint at the address kp->addr. When the breakpoint is
329hit, Kprobes calls kp->pre_handler. After the probed instruction
330is single-stepped, Kprobe calls kp->post_handler. If a fault
331occurs during execution of kp->pre_handler or kp->post_handler,
332or during single-stepping of the probed instruction, Kprobes calls
333kp->fault_handler. Any or all handlers can be NULL. If kp->flags
334is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled,
335so, it's handlers aren't hit until calling enable_kprobe(kp).
336
337NOTE:
3381. With the introduction of the "symbol_name" field to struct kprobe,
339the probepoint address resolution will now be taken care of by the kernel.
340The following will now work:
341
342    kp.symbol_name = "symbol_name";
343
344(64-bit powerpc intricacies such as function descriptors are handled
345transparently)
346
3472. Use the "offset" field of struct kprobe if the offset into the symbol
348to install a probepoint is known. This field is used to calculate the
349probepoint.
350
3513. Specify either the kprobe "symbol_name" OR the "addr". If both are
352specified, kprobe registration will fail with -EINVAL.
353
3544. With CISC architectures (such as i386 and x86_64), the kprobes code
355does not validate if the kprobe.addr is at an instruction boundary.
356Use "offset" with caution.
357
358register_kprobe() returns 0 on success, or a negative errno otherwise.
359
360User's pre-handler (kp->pre_handler):
361#include <linux/kprobes.h>
362#include <linux/ptrace.h>
363int pre_handler(struct kprobe *p, struct pt_regs *regs);
364
365Called with p pointing to the kprobe associated with the breakpoint,
366and regs pointing to the struct containing the registers saved when
367the breakpoint was hit. Return 0 here unless you're a Kprobes geek.
368
369User's post-handler (kp->post_handler):
370#include <linux/kprobes.h>
371#include <linux/ptrace.h>
372void post_handler(struct kprobe *p, struct pt_regs *regs,
373    unsigned long flags);
374
375p and regs are as described for the pre_handler. flags always seems
376to be zero.
377
378User's fault-handler (kp->fault_handler):
379#include <linux/kprobes.h>
380#include <linux/ptrace.h>
381int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr);
382
383p and regs are as described for the pre_handler. trapnr is the
384architecture-specific trap number associated with the fault (e.g.,
385on i386, 13 for a general protection fault or 14 for a page fault).
386Returns 1 if it successfully handled the exception.
387
3884.2 register_jprobe
389
390#include <linux/kprobes.h>
391int register_jprobe(struct jprobe *jp)
392
393Sets a breakpoint at the address jp->kp.addr, which must be the address
394of the first instruction of a function. When the breakpoint is hit,
395Kprobes runs the handler whose address is jp->entry.
396
397The handler should have the same arg list and return type as the probed
398function; and just before it returns, it must call jprobe_return().
399(The handler never actually returns, since jprobe_return() returns
400control to Kprobes.) If the probed function is declared asmlinkage
401or anything else that affects how args are passed, the handler's
402declaration must match.
403
404register_jprobe() returns 0 on success, or a negative errno otherwise.
405
4064.3 register_kretprobe
407
408#include <linux/kprobes.h>
409int register_kretprobe(struct kretprobe *rp);
410
411Establishes a return probe for the function whose address is
412rp->kp.addr. When that function returns, Kprobes calls rp->handler.
413You must set rp->maxactive appropriately before you call
414register_kretprobe(); see "How Does a Return Probe Work?" for details.
415
416register_kretprobe() returns 0 on success, or a negative errno
417otherwise.
418
419User's return-probe handler (rp->handler):
420#include <linux/kprobes.h>
421#include <linux/ptrace.h>
422int kretprobe_handler(struct kretprobe_instance *ri, struct pt_regs *regs);
423
424regs is as described for kprobe.pre_handler. ri points to the
425kretprobe_instance object, of which the following fields may be
426of interest:
427- ret_addr: the return address
428- rp: points to the corresponding kretprobe object
429- task: points to the corresponding task struct
430- data: points to per return-instance private data; see "Kretprobe
431    entry-handler" for details.
432
433The regs_return_value(regs) macro provides a simple abstraction to
434extract the return value from the appropriate register as defined by
435the architecture's ABI.
436
437The handler's return value is currently ignored.
438
4394.4 unregister_*probe
440
441#include <linux/kprobes.h>
442void unregister_kprobe(struct kprobe *kp);
443void unregister_jprobe(struct jprobe *jp);
444void unregister_kretprobe(struct kretprobe *rp);
445
446Removes the specified probe. The unregister function can be called
447at any time after the probe has been registered.
448
449NOTE:
450If the functions find an incorrect probe (ex. an unregistered probe),
451they clear the addr field of the probe.
452
4534.5 register_*probes
454
455#include <linux/kprobes.h>
456int register_kprobes(struct kprobe **kps, int num);
457int register_kretprobes(struct kretprobe **rps, int num);
458int register_jprobes(struct jprobe **jps, int num);
459
460Registers each of the num probes in the specified array. If any
461error occurs during registration, all probes in the array, up to
462the bad probe, are safely unregistered before the register_*probes
463function returns.
464- kps/rps/jps: an array of pointers to *probe data structures
465- num: the number of the array entries.
466
467NOTE:
468You have to allocate(or define) an array of pointers and set all
469of the array entries before using these functions.
470
4714.6 unregister_*probes
472
473#include <linux/kprobes.h>
474void unregister_kprobes(struct kprobe **kps, int num);
475void unregister_kretprobes(struct kretprobe **rps, int num);
476void unregister_jprobes(struct jprobe **jps, int num);
477
478Removes each of the num probes in the specified array at once.
479
480NOTE:
481If the functions find some incorrect probes (ex. unregistered
482probes) in the specified array, they clear the addr field of those
483incorrect probes. However, other probes in the array are
484unregistered correctly.
485
4864.7 disable_*probe
487
488#include <linux/kprobes.h>
489int disable_kprobe(struct kprobe *kp);
490int disable_kretprobe(struct kretprobe *rp);
491int disable_jprobe(struct jprobe *jp);
492
493Temporarily disables the specified *probe. You can enable it again by using
494enable_*probe(). You must specify the probe which has been registered.
495
4964.8 enable_*probe
497
498#include <linux/kprobes.h>
499int enable_kprobe(struct kprobe *kp);
500int enable_kretprobe(struct kretprobe *rp);
501int enable_jprobe(struct jprobe *jp);
502
503Enables *probe which has been disabled by disable_*probe(). You must specify
504the probe which has been registered.
505
5065. Kprobes Features and Limitations
507
508Kprobes allows multiple probes at the same address. Currently,
509however, there cannot be multiple jprobes on the same function at
510the same time. Also, a probepoint for which there is a jprobe or
511a post_handler cannot be optimized. So if you install a jprobe,
512or a kprobe with a post_handler, at an optimized probepoint, the
513probepoint will be unoptimized automatically.
514
515In general, you can install a probe anywhere in the kernel.
516In particular, you can probe interrupt handlers. Known exceptions
517are discussed in this section.
518
519The register_*probe functions will return -EINVAL if you attempt
520to install a probe in the code that implements Kprobes (mostly
521kernel/kprobes.c and arch/*/kernel/kprobes.c, but also functions such
522as do_page_fault and notifier_call_chain).
523
524If you install a probe in an inline-able function, Kprobes makes
525no attempt to chase down all inline instances of the function and
526install probes there. gcc may inline a function without being asked,
527so keep this in mind if you're not seeing the probe hits you expect.
528
529A probe handler can modify the environment of the probed function
530-- e.g., by modifying kernel data structures, or by modifying the
531contents of the pt_regs struct (which are restored to the registers
532upon return from the breakpoint). So Kprobes can be used, for example,
533to install a bug fix or to inject faults for testing. Kprobes, of
534course, has no way to distinguish the deliberately injected faults
535from the accidental ones. Don't drink and probe.
536
537Kprobes makes no attempt to prevent probe handlers from stepping on
538each other -- e.g., probing printk() and then calling printk() from a
539probe handler. If a probe handler hits a probe, that second probe's
540handlers won't be run in that instance, and the kprobe.nmissed member
541of the second probe will be incremented.
542
543As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of
544the same handler) may run concurrently on different CPUs.
545
546Kprobes does not use mutexes or allocate memory except during
547registration and unregistration.
548
549Probe handlers are run with preemption disabled. Depending on the
550architecture, handlers may also run with interrupts disabled. In any
551case, your handler should not yield the CPU (e.g., by attempting to
552acquire a semaphore).
553
554Since a return probe is implemented by replacing the return
555address with the trampoline's address, stack backtraces and calls
556to __builtin_return_address() will typically yield the trampoline's
557address instead of the real return address for kretprobed functions.
558(As far as we can tell, __builtin_return_address() is used only
559for instrumentation and error reporting.)
560
561If the number of times a function is called does not match the number
562of times it returns, registering a return probe on that function may
563produce undesirable results. In such a case, a line:
564kretprobe BUG!: Processing kretprobe d000000000041aa8 @ c00000000004f48c
565gets printed. With this information, one will be able to correlate the
566exact instance of the kretprobe that caused the problem. We have the
567do_exit() case covered. do_execve() and do_fork() are not an issue.
568We're unaware of other specific cases where this could be a problem.
569
570If, upon entry to or exit from a function, the CPU is running on
571a stack other than that of the current task, registering a return
572probe on that function may produce undesirable results. For this
573reason, Kprobes doesn't support return probes (or kprobes or jprobes)
574on the x86_64 version of __switch_to(); the registration functions
575return -EINVAL.
576
577On x86/x86-64, since the Jump Optimization of Kprobes modifies
578instructions widely, there are some limitations to optimization. To
579explain it, we introduce some terminology. Imagine a 3-instruction
580sequence consisting of a two 2-byte instructions and one 3-byte
581instruction.
582
583        IA
584         |
585[-2][-1][0][1][2][3][4][5][6][7]
586        [ins1][ins2][ ins3 ]
587    [<- DCR ->]
588       [<- JTPR ->]
589
590ins1: 1st Instruction
591ins2: 2nd Instruction
592ins3: 3rd Instruction
593IA: Insertion Address
594JTPR: Jump Target Prohibition Region
595DCR: Detoured Code Region
596
597The instructions in DCR are copied to the out-of-line buffer
598of the kprobe, because the bytes in DCR are replaced by
599a 5-byte jump instruction. So there are several limitations.
600
601a) The instructions in DCR must be relocatable.
602b) The instructions in DCR must not include a call instruction.
603c) JTPR must not be targeted by any jump or call instruction.
604d) DCR must not straddle the border betweeen functions.
605
606Anyway, these limitations are checked by the in-kernel instruction
607decoder, so you don't need to worry about that.
608
6096. Probe Overhead
610
611On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
612microseconds to process. Specifically, a benchmark that hits the same
613probepoint repeatedly, firing a simple handler each time, reports 1-2
614million hits per second, depending on the architecture. A jprobe or
615return-probe hit typically takes 50-75% longer than a kprobe hit.
616When you have a return probe set on a function, adding a kprobe at
617the entry to that function adds essentially no overhead.
618
619Here are sample overhead figures (in usec) for different architectures.
620k = kprobe; j = jprobe; r = return probe; kr = kprobe + return probe
621on same function; jr = jprobe + return probe on same function
622
623i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips
624k = 0.57 usec; j = 1.00; r = 0.92; kr = 0.99; jr = 1.40
625
626x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips
627k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
628
629ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
630k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
631
6326.1 Optimized Probe Overhead
633
634Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to
635process. Here are sample overhead figures (in usec) for x86 architectures.
636k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
637r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
638
639i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
640k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
641
642x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
643k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
644
6457. TODO
646
647a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
648programming interface for probe-based instrumentation. Try it out.
649b. Kernel return probes for sparc64.
650c. Support for other architectures.
651d. User-space probes.
652e. Watchpoint probes (which fire on data references).
653
6548. Kprobes Example
655
656See samples/kprobes/kprobe_example.c
657
6589. Jprobes Example
659
660See samples/kprobes/jprobe_example.c
661
66210. Kretprobes Example
663
664See samples/kprobes/kretprobe_example.c
665
666For additional information on Kprobes, refer to the following URLs:
667http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe
668http://www.redhat.com/magazine/005mar05/features/kprobes/
669http://www-users.cs.umn.edu/~boutcher/kprobes/
670http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115)
671
672
673Appendix A: The kprobes debugfs interface
674
675With recent kernels (> 2.6.20) the list of registered kprobes is visible
676under the /sys/kernel/debug/kprobes/ directory (assuming debugfs is mounted at //sys/kernel/debug).
677
678/sys/kernel/debug/kprobes/list: Lists all registered probes on the system
679
680c015d71a k vfs_read+0x0
681c011a316 j do_fork+0x0
682c03dedc5 r tcp_v4_rcv+0x0
683
684The first column provides the kernel address where the probe is inserted.
685The second column identifies the type of probe (k - kprobe, r - kretprobe
686and j - jprobe), while the third column specifies the symbol+offset of
687the probe. If the probed function belongs to a module, the module name
688is also specified. Following columns show probe status. If the probe is on
689a virtual address that is no longer valid (module init sections, module
690virtual addresses that correspond to modules that've been unloaded),
691such probes are marked with [GONE]. If the probe is temporarily disabled,
692such probes are marked with [DISABLED]. If the probe is optimized, it is
693marked with [OPTIMIZED].
694
695/sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
696
697Provides a knob to globally and forcibly turn registered kprobes ON or OFF.
698By default, all kprobes are enabled. By echoing "0" to this file, all
699registered probes will be disarmed, till such time a "1" is echoed to this
700file. Note that this knob just disarms and arms all kprobes and doesn't
701change each probe's disabling state. This means that disabled kprobes (marked
702[DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
703
704
705Appendix B: The kprobes sysctl interface
706
707/proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.
708
709When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides
710a knob to globally and forcibly turn jump optimization (see section
7111.4) ON or OFF. By default, jump optimization is allowed (ON).
712If you echo "0" to this file or set "debug.kprobes_optimization" to
7130 via sysctl, all optimized probes will be unoptimized, and any new
714probes registered after that will not be optimized. Note that this
715knob *changes* the optimized state. This means that optimized probes
716(marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
717removed). If the knob is turned on, they will be optimized again.
718
719

Archive Download this file



interactive