blob: cb12ae175aa2de80b3114434c20e64cac4857593 [file] [log] [blame]
Jim Kenistond27a4dd2005-08-04 12:53:35 -07001Title : Kernel Probes (Kprobes)
2Authors : Jim Keniston <jkenisto@us.ibm.com>
3 : Prasanna S Panchamukhi <prasanna@in.ibm.com>
4
5CONTENTS
6
71. Concepts: Kprobes, Jprobes, Return Probes
82. Architectures Supported
93. Configuring Kprobes
104. API Reference
115. Kprobes Features and Limitations
126. Probe Overhead
137. TODO
148. Kprobes Example
159. Jprobes Example
1610. Kretprobes Example
Ananth N Mavinakayanahallibf8f6e52007-05-08 00:34:16 -070017Appendix A: The kprobes debugfs interface
Jim Kenistond27a4dd2005-08-04 12:53:35 -070018
191. Concepts: Kprobes, Jprobes, Return Probes
20
21Kprobes enables you to dynamically break into any kernel routine and
22collect debugging and performance information non-disruptively. You
23can trap at almost any kernel code address, specifying a handler
24routine to be invoked when the breakpoint is hit.
25
26There are currently three types of probes: kprobes, jprobes, and
27kretprobes (also called return probes). A kprobe can be inserted
28on virtually any instruction in the kernel. A jprobe is inserted at
29the entry to a kernel function, and provides convenient access to the
30function's arguments. A return probe fires when a specified function
31returns.
32
33In the typical case, Kprobes-based instrumentation is packaged as
34a kernel module. The module's init function installs ("registers")
35one or more probes, and the exit function unregisters them. A
36registration function such as register_kprobe() specifies where
37the probe is to be inserted and what handler is to be called when
38the probe is hit.
39
40The next three subsections explain how the different types of
41probes work. They explain certain things that you'll need to
42know in order to make the best use of Kprobes -- e.g., the
43difference between a pre_handler and a post_handler, and how
44to use the maxactive and nmissed fields of a kretprobe. But
45if you're in a hurry to start using Kprobes, you can skip ahead
46to section 2.
47
481.1 How Does a Kprobe Work?
49
50When a kprobe is registered, Kprobes makes a copy of the probed
51instruction and replaces the first byte(s) of the probed instruction
52with a breakpoint instruction (e.g., int3 on i386 and x86_64).
53
54When a CPU hits the breakpoint instruction, a trap occurs, the CPU's
55registers are saved, and control passes to Kprobes via the
56notifier_call_chain mechanism. Kprobes executes the "pre_handler"
57associated with the kprobe, passing the handler the addresses of the
58kprobe struct and the saved registers.
59
60Next, Kprobes single-steps its copy of the probed instruction.
61(It would be simpler to single-step the actual instruction in place,
62but then Kprobes would have to temporarily remove the breakpoint
63instruction. This would open a small time window when another CPU
64could sail right past the probepoint.)
65
66After the instruction is single-stepped, Kprobes executes the
67"post_handler," if any, that is associated with the kprobe.
68Execution then continues with the instruction following the probepoint.
69
701.2 How Does a Jprobe Work?
71
72A jprobe is implemented using a kprobe that is placed on a function's
73entry point. It employs a simple mirroring principle to allow
74seamless access to the probed function's arguments. The jprobe
75handler routine should have the same signature (arg list and return
76type) as the function being probed, and must always end by calling
77the Kprobes function jprobe_return().
78
79Here's how it works. When the probe is hit, Kprobes makes a copy of
80the saved registers and a generous portion of the stack (see below).
81Kprobes then points the saved instruction pointer at the jprobe's
82handler routine, and returns from the trap. As a result, control
83passes to the handler, which is presented with the same register and
84stack contents as the probed function. When it is done, the handler
85calls jprobe_return(), which traps again to restore the original stack
86contents and processor state and switch to the probed function.
87
88By convention, the callee owns its arguments, so gcc may produce code
89that unexpectedly modifies that portion of the stack. This is why
90Kprobes saves a copy of the stack and restores it after the jprobe
91handler has run. Up to MAX_STACK_SIZE bytes are copied -- e.g.,
9264 bytes on i386.
93
94Note that the probed function's args may be passed on the stack
95or in registers (e.g., for x86_64 or for an i386 fastcall function).
96The jprobe will work in either case, so long as the handler's
97prototype matches that of the probed function.
98
991.3 How Does a Return Probe Work?
100
101When you call register_kretprobe(), Kprobes establishes a kprobe at
102the entry to the function. When the probed function is called and this
103probe is hit, Kprobes saves a copy of the return address, and replaces
104the return address with the address of a "trampoline." The trampoline
105is an arbitrary piece of code -- typically just a nop instruction.
106At boot time, Kprobes registers a kprobe at the trampoline.
107
108When the probed function executes its return instruction, control
109passes to the trampoline and that probe is hit. Kprobes' trampoline
110handler calls the user-specified handler associated with the kretprobe,
111then sets the saved instruction pointer to the saved return address,
112and that's where execution resumes upon return from the trap.
113
114While the probed function is executing, its return address is
115stored in an object of type kretprobe_instance. Before calling
116register_kretprobe(), the user sets the maxactive field of the
117kretprobe struct to specify how many instances of the specified
118function can be probed simultaneously. register_kretprobe()
119pre-allocates the indicated number of kretprobe_instance objects.
120
121For example, if the function is non-recursive and is called with a
122spinlock held, maxactive = 1 should be enough. If the function is
123non-recursive and can never relinquish the CPU (e.g., via a semaphore
124or preemption), NR_CPUS should be enough. If maxactive <= 0, it is
125set to a default value. If CONFIG_PREEMPT is enabled, the default
126is max(10, 2*NR_CPUS). Otherwise, the default is NR_CPUS.
127
128It's not a disaster if you set maxactive too low; you'll just miss
129some probes. In the kretprobe struct, the nmissed field is set to
130zero when the return probe is registered, and is incremented every
131time the probed function is entered but there is no kretprobe_instance
132object available for establishing the return probe.
133
1342. Architectures Supported
135
136Kprobes, jprobes, and return probes are implemented on the following
137architectures:
138
139- i386
Jim Keniston8861da32006-02-14 13:53:06 -0800140- x86_64 (AMD-64, EM64T)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700141- ppc64
Jim Keniston8861da32006-02-14 13:53:06 -0800142- ia64 (Does not support probes on instruction slot1.)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700143- sparc64 (Return probes not yet implemented.)
144
1453. Configuring Kprobes
146
147When configuring the kernel using make menuconfig/xconfig/oldconfig,
Jim Keniston8861da32006-02-14 13:53:06 -0800148ensure that CONFIG_KPROBES is set to "y". Under "Instrumentation
149Support", look for "Kprobes".
150
151So that you can load and unload Kprobes-based instrumentation modules,
152make sure "Loadable module support" (CONFIG_MODULES) and "Module
153unloading" (CONFIG_MODULE_UNLOAD) are set to "y".
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700154
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700155Also make sure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL
156are set to "y", since kallsyms_lookup_name() is used by the in-kernel
157kprobe address resolution code.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700158
159If you need to insert a probe in the middle of a function, you may find
160it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
161so you can use "objdump -d -l vmlinux" to see the source-to-object
162code mapping.
163
1644. API Reference
165
166The Kprobes API includes a "register" function and an "unregister"
167function for each type of probe. Here are terse, mini-man-page
168specifications for these functions and the associated probe handlers
169that you'll write. See the latter half of this document for examples.
170
1714.1 register_kprobe
172
173#include <linux/kprobes.h>
174int register_kprobe(struct kprobe *kp);
175
176Sets a breakpoint at the address kp->addr. When the breakpoint is
177hit, Kprobes calls kp->pre_handler. After the probed instruction
178is single-stepped, Kprobe calls kp->post_handler. If a fault
179occurs during execution of kp->pre_handler or kp->post_handler,
180or during single-stepping of the probed instruction, Kprobes calls
181kp->fault_handler. Any or all handlers can be NULL.
182
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700183NOTE:
1841. With the introduction of the "symbol_name" field to struct kprobe,
185the probepoint address resolution will now be taken care of by the kernel.
186The following will now work:
187
188 kp.symbol_name = "symbol_name";
189
190(64-bit powerpc intricacies such as function descriptors are handled
191transparently)
192
1932. Use the "offset" field of struct kprobe if the offset into the symbol
194to install a probepoint is known. This field is used to calculate the
195probepoint.
196
1973. Specify either the kprobe "symbol_name" OR the "addr". If both are
198specified, kprobe registration will fail with -EINVAL.
199
2004. With CISC architectures (such as i386 and x86_64), the kprobes code
201does not validate if the kprobe.addr is at an instruction boundary.
202Use "offset" with caution.
203
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700204register_kprobe() returns 0 on success, or a negative errno otherwise.
205
206User's pre-handler (kp->pre_handler):
207#include <linux/kprobes.h>
208#include <linux/ptrace.h>
209int pre_handler(struct kprobe *p, struct pt_regs *regs);
210
211Called with p pointing to the kprobe associated with the breakpoint,
212and regs pointing to the struct containing the registers saved when
213the breakpoint was hit. Return 0 here unless you're a Kprobes geek.
214
215User's post-handler (kp->post_handler):
216#include <linux/kprobes.h>
217#include <linux/ptrace.h>
218void post_handler(struct kprobe *p, struct pt_regs *regs,
219 unsigned long flags);
220
221p and regs are as described for the pre_handler. flags always seems
222to be zero.
223
224User's fault-handler (kp->fault_handler):
225#include <linux/kprobes.h>
226#include <linux/ptrace.h>
227int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr);
228
229p and regs are as described for the pre_handler. trapnr is the
230architecture-specific trap number associated with the fault (e.g.,
231on i386, 13 for a general protection fault or 14 for a page fault).
232Returns 1 if it successfully handled the exception.
233
2344.2 register_jprobe
235
236#include <linux/kprobes.h>
237int register_jprobe(struct jprobe *jp)
238
239Sets a breakpoint at the address jp->kp.addr, which must be the address
240of the first instruction of a function. When the breakpoint is hit,
241Kprobes runs the handler whose address is jp->entry.
242
243The handler should have the same arg list and return type as the probed
244function; and just before it returns, it must call jprobe_return().
245(The handler never actually returns, since jprobe_return() returns
246control to Kprobes.) If the probed function is declared asmlinkage,
247fastcall, or anything else that affects how args are passed, the
248handler's declaration must match.
249
250register_jprobe() returns 0 on success, or a negative errno otherwise.
251
2524.3 register_kretprobe
253
254#include <linux/kprobes.h>
255int register_kretprobe(struct kretprobe *rp);
256
257Establishes a return probe for the function whose address is
258rp->kp.addr. When that function returns, Kprobes calls rp->handler.
259You must set rp->maxactive appropriately before you call
260register_kretprobe(); see "How Does a Return Probe Work?" for details.
261
262register_kretprobe() returns 0 on success, or a negative errno
263otherwise.
264
265User's return-probe handler (rp->handler):
266#include <linux/kprobes.h>
267#include <linux/ptrace.h>
268int kretprobe_handler(struct kretprobe_instance *ri, struct pt_regs *regs);
269
270regs is as described for kprobe.pre_handler. ri points to the
271kretprobe_instance object, of which the following fields may be
272of interest:
273- ret_addr: the return address
274- rp: points to the corresponding kretprobe object
275- task: points to the corresponding task struct
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700276
277The regs_return_value(regs) macro provides a simple abstraction to
278extract the return value from the appropriate register as defined by
279the architecture's ABI.
280
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700281The handler's return value is currently ignored.
282
2834.4 unregister_*probe
284
285#include <linux/kprobes.h>
286void unregister_kprobe(struct kprobe *kp);
287void unregister_jprobe(struct jprobe *jp);
288void unregister_kretprobe(struct kretprobe *rp);
289
290Removes the specified probe. The unregister function can be called
291at any time after the probe has been registered.
292
2935. Kprobes Features and Limitations
294
Jim Keniston8861da32006-02-14 13:53:06 -0800295Kprobes allows multiple probes at the same address. Currently,
296however, there cannot be multiple jprobes on the same function at
297the same time.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700298
299In general, you can install a probe anywhere in the kernel.
300In particular, you can probe interrupt handlers. Known exceptions
301are discussed in this section.
302
Jim Keniston8861da32006-02-14 13:53:06 -0800303The register_*probe functions will return -EINVAL if you attempt
304to install a probe in the code that implements Kprobes (mostly
305kernel/kprobes.c and arch/*/kernel/kprobes.c, but also functions such
306as do_page_fault and notifier_call_chain).
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700307
308If you install a probe in an inline-able function, Kprobes makes
309no attempt to chase down all inline instances of the function and
310install probes there. gcc may inline a function without being asked,
311so keep this in mind if you're not seeing the probe hits you expect.
312
313A probe handler can modify the environment of the probed function
314-- e.g., by modifying kernel data structures, or by modifying the
315contents of the pt_regs struct (which are restored to the registers
316upon return from the breakpoint). So Kprobes can be used, for example,
317to install a bug fix or to inject faults for testing. Kprobes, of
318course, has no way to distinguish the deliberately injected faults
319from the accidental ones. Don't drink and probe.
320
321Kprobes makes no attempt to prevent probe handlers from stepping on
322each other -- e.g., probing printk() and then calling printk() from a
Jim Keniston8861da32006-02-14 13:53:06 -0800323probe handler. If a probe handler hits a probe, that second probe's
324handlers won't be run in that instance, and the kprobe.nmissed member
325of the second probe will be incremented.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700326
Jim Keniston8861da32006-02-14 13:53:06 -0800327As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of
328the same handler) may run concurrently on different CPUs.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700329
Jim Keniston8861da32006-02-14 13:53:06 -0800330Kprobes does not use mutexes or allocate memory except during
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700331registration and unregistration.
332
333Probe handlers are run with preemption disabled. Depending on the
334architecture, handlers may also run with interrupts disabled. In any
335case, your handler should not yield the CPU (e.g., by attempting to
336acquire a semaphore).
337
338Since a return probe is implemented by replacing the return
339address with the trampoline's address, stack backtraces and calls
340to __builtin_return_address() will typically yield the trampoline's
341address instead of the real return address for kretprobed functions.
342(As far as we can tell, __builtin_return_address() is used only
343for instrumentation and error reporting.)
344
Jim Keniston8861da32006-02-14 13:53:06 -0800345If the number of times a function is called does not match the number
346of times it returns, registering a return probe on that function may
Ananth N Mavinakayanahallibf8f6e52007-05-08 00:34:16 -0700347produce undesirable results. In such a case, a line:
348kretprobe BUG!: Processing kretprobe d000000000041aa8 @ c00000000004f48c
349gets printed. With this information, one will be able to correlate the
350exact instance of the kretprobe that caused the problem. We have the
351do_exit() case covered. do_execve() and do_fork() are not an issue.
352We're unaware of other specific cases where this could be a problem.
Jim Keniston8861da32006-02-14 13:53:06 -0800353
354If, upon entry to or exit from a function, the CPU is running on
355a stack other than that of the current task, registering a return
356probe on that function may produce undesirable results. For this
357reason, Kprobes doesn't support return probes (or kprobes or jprobes)
358on the x86_64 version of __switch_to(); the registration functions
359return -EINVAL.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700360
3616. Probe Overhead
362
363On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
364microseconds to process. Specifically, a benchmark that hits the same
365probepoint repeatedly, firing a simple handler each time, reports 1-2
366million hits per second, depending on the architecture. A jprobe or
367return-probe hit typically takes 50-75% longer than a kprobe hit.
368When you have a return probe set on a function, adding a kprobe at
369the entry to that function adds essentially no overhead.
370
371Here are sample overhead figures (in usec) for different architectures.
372k = kprobe; j = jprobe; r = return probe; kr = kprobe + return probe
373on same function; jr = jprobe + return probe on same function
374
375i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips
376k = 0.57 usec; j = 1.00; r = 0.92; kr = 0.99; jr = 1.40
377
378x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips
379k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
380
381ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
382k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
383
3847. TODO
385
Jim Keniston8861da32006-02-14 13:53:06 -0800386a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
387programming interface for probe-based instrumentation. Try it out.
388b. Kernel return probes for sparc64.
389c. Support for other architectures.
390d. User-space probes.
391e. Watchpoint probes (which fire on data references).
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700392
3938. Kprobes Example
394
395Here's a sample kernel module showing the use of kprobes to dump a
396stack trace and selected i386 registers when do_fork() is called.
397----- cut here -----
398/*kprobe_example.c*/
399#include <linux/kernel.h>
400#include <linux/module.h>
401#include <linux/kprobes.h>
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700402#include <linux/sched.h>
403
404/*For each probe you need to allocate a kprobe structure*/
405static struct kprobe kp;
406
407/*kprobe pre_handler: called just before the probed instruction is executed*/
408int handler_pre(struct kprobe *p, struct pt_regs *regs)
409{
410 printk("pre_handler: p->addr=0x%p, eip=%lx, eflags=0x%lx\n",
411 p->addr, regs->eip, regs->eflags);
412 dump_stack();
413 return 0;
414}
415
416/*kprobe post_handler: called after the probed instruction is executed*/
417void handler_post(struct kprobe *p, struct pt_regs *regs, unsigned long flags)
418{
419 printk("post_handler: p->addr=0x%p, eflags=0x%lx\n",
420 p->addr, regs->eflags);
421}
422
423/* fault_handler: this is called if an exception is generated for any
424 * instruction within the pre- or post-handler, or when Kprobes
425 * single-steps the probed instruction.
426 */
427int handler_fault(struct kprobe *p, struct pt_regs *regs, int trapnr)
428{
429 printk("fault_handler: p->addr=0x%p, trap #%dn",
430 p->addr, trapnr);
431 /* Return 0 because we don't handle the fault. */
432 return 0;
433}
434
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700435static int __init kprobe_init(void)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700436{
437 int ret;
438 kp.pre_handler = handler_pre;
439 kp.post_handler = handler_post;
440 kp.fault_handler = handler_fault;
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700441 kp.symbol_name = "do_fork";
442
Alexey Dobriyan565762f2006-11-16 01:19:28 -0800443 ret = register_kprobe(&kp);
444 if (ret < 0) {
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700445 printk("register_kprobe failed, returned %d\n", ret);
Alexey Dobriyan565762f2006-11-16 01:19:28 -0800446 return ret;
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700447 }
448 printk("kprobe registered\n");
449 return 0;
450}
451
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700452static void __exit kprobe_exit(void)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700453{
454 unregister_kprobe(&kp);
455 printk("kprobe unregistered\n");
456}
457
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700458module_init(kprobe_init)
459module_exit(kprobe_exit)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700460MODULE_LICENSE("GPL");
461----- cut here -----
462
463You can build the kernel module, kprobe-example.ko, using the following
464Makefile:
465----- cut here -----
466obj-m := kprobe-example.o
467KDIR := /lib/modules/$(shell uname -r)/build
468PWD := $(shell pwd)
469default:
470 $(MAKE) -C $(KDIR) SUBDIRS=$(PWD) modules
471clean:
472 rm -f *.mod.c *.ko *.o
473----- cut here -----
474
475$ make
476$ su -
477...
478# insmod kprobe-example.ko
479
480You will see the trace data in /var/log/messages and on the console
481whenever do_fork() is invoked to create a new process.
482
4839. Jprobes Example
484
485Here's a sample kernel module showing the use of jprobes to dump
486the arguments of do_fork().
487----- cut here -----
488/*jprobe-example.c */
489#include <linux/kernel.h>
490#include <linux/module.h>
491#include <linux/fs.h>
492#include <linux/uio.h>
493#include <linux/kprobes.h>
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700494
495/*
496 * Jumper probe for do_fork.
497 * Mirror principle enables access to arguments of the probed routine
498 * from the probe handler.
499 */
500
501/* Proxy routine having the same arguments as actual do_fork() routine */
502long jdo_fork(unsigned long clone_flags, unsigned long stack_start,
503 struct pt_regs *regs, unsigned long stack_size,
504 int __user * parent_tidptr, int __user * child_tidptr)
505{
506 printk("jprobe: clone_flags=0x%lx, stack_size=0x%lx, regs=0x%p\n",
507 clone_flags, stack_size, regs);
508 /* Always end with a call to jprobe_return(). */
509 jprobe_return();
510 /*NOTREACHED*/
511 return 0;
512}
513
514static struct jprobe my_jprobe = {
Michael Ellerman9e367d82007-07-19 01:48:10 -0700515 .entry = jdo_fork
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700516};
517
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700518static int __init jprobe_init(void)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700519{
520 int ret;
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700521 my_jprobe.kp.symbol_name = "do_fork";
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700522
523 if ((ret = register_jprobe(&my_jprobe)) <0) {
524 printk("register_jprobe failed, returned %d\n", ret);
525 return -1;
526 }
527 printk("Planted jprobe at %p, handler addr %p\n",
528 my_jprobe.kp.addr, my_jprobe.entry);
529 return 0;
530}
531
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700532static void __exit jprobe_exit(void)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700533{
534 unregister_jprobe(&my_jprobe);
535 printk("jprobe unregistered\n");
536}
537
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700538module_init(jprobe_init)
539module_exit(jprobe_exit)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700540MODULE_LICENSE("GPL");
541----- cut here -----
542
543Build and insert the kernel module as shown in the above kprobe
544example. You will see the trace data in /var/log/messages and on
545the console whenever do_fork() is invoked to create a new process.
546(Some messages may be suppressed if syslogd is configured to
547eliminate duplicate messages.)
548
54910. Kretprobes Example
550
551Here's a sample kernel module showing the use of return probes to
552report failed calls to sys_open().
553----- cut here -----
554/*kretprobe-example.c*/
555#include <linux/kernel.h>
556#include <linux/module.h>
557#include <linux/kprobes.h>
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700558
559static const char *probed_func = "sys_open";
560
561/* Return-probe handler: If the probed function fails, log the return value. */
562static int ret_handler(struct kretprobe_instance *ri, struct pt_regs *regs)
563{
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700564 int retval = regs_return_value(regs);
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700565 if (retval < 0) {
566 printk("%s returns %d\n", probed_func, retval);
567 }
568 return 0;
569}
570
571static struct kretprobe my_kretprobe = {
572 .handler = ret_handler,
573 /* Probe up to 20 instances concurrently. */
574 .maxactive = 20
575};
576
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700577static int __init kretprobe_init(void)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700578{
579 int ret;
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700580 my_kretprobe.kp.symbol_name = (char *)probed_func;
581
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700582 if ((ret = register_kretprobe(&my_kretprobe)) < 0) {
583 printk("register_kretprobe failed, returned %d\n", ret);
584 return -1;
585 }
586 printk("Planted return probe at %p\n", my_kretprobe.kp.addr);
587 return 0;
588}
589
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700590static void __exit kretprobe_exit(void)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700591{
592 unregister_kretprobe(&my_kretprobe);
593 printk("kretprobe unregistered\n");
594 /* nmissed > 0 suggests that maxactive was set too low. */
595 printk("Missed probing %d instances of %s\n",
596 my_kretprobe.nmissed, probed_func);
597}
598
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700599module_init(kretprobe_init)
600module_exit(kretprobe_exit)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700601MODULE_LICENSE("GPL");
602----- cut here -----
603
604Build and insert the kernel module as shown in the above kprobe
605example. You will see the trace data in /var/log/messages and on the
606console whenever sys_open() returns a negative value. (Some messages
607may be suppressed if syslogd is configured to eliminate duplicate
608messages.)
609
610For additional information on Kprobes, refer to the following URLs:
611http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe
612http://www.redhat.com/magazine/005mar05/features/kprobes/
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700613http://www-users.cs.umn.edu/~boutcher/kprobes/
614http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115)
Ananth N Mavinakayanahallibf8f6e52007-05-08 00:34:16 -0700615
616
617Appendix A: The kprobes debugfs interface
618
619With recent kernels (> 2.6.20) the list of registered kprobes is visible
620under the /debug/kprobes/ directory (assuming debugfs is mounted at /debug).
621
622/debug/kprobes/list: Lists all registered probes on the system
623
624c015d71a k vfs_read+0x0
625c011a316 j do_fork+0x0
626c03dedc5 r tcp_v4_rcv+0x0
627
628The first column provides the kernel address where the probe is inserted.
629The second column identifies the type of probe (k - kprobe, r - kretprobe
630and j - jprobe), while the third column specifies the symbol+offset of
631the probe. If the probed function belongs to a module, the module name
632is also specified.
633
634/debug/kprobes/enabled: Turn kprobes ON/OFF
635
636Provides a knob to globally turn registered kprobes ON or OFF. By default,
637all kprobes are enabled. By echoing "0" to this file, all registered probes
638will be disarmed, till such time a "1" is echoed to this file.