blob: a79633d702bff23230bb0d76cb68565e078b4fb2 [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 Mavinakayanahallibf8f6e5b2007-05-08 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
Masami Hiramatsu3b0cb4c2008-04-28 02:14:30 -070040There are also register_/unregister_*probes() functions for batch
41registration/unregistration of a group of *probes. These functions
42can speed up unregistration process when you have to unregister
43a lot of probes at once.
44
Jim Kenistond27a4dd2005-08-04 12:53:35 -070045The next three subsections explain how the different types of
46probes work. They explain certain things that you'll need to
47know in order to make the best use of Kprobes -- e.g., the
48difference between a pre_handler and a post_handler, and how
49to use the maxactive and nmissed fields of a kretprobe. But
50if you're in a hurry to start using Kprobes, you can skip ahead
51to section 2.
52
531.1 How Does a Kprobe Work?
54
55When a kprobe is registered, Kprobes makes a copy of the probed
56instruction and replaces the first byte(s) of the probed instruction
57with a breakpoint instruction (e.g., int3 on i386 and x86_64).
58
59When a CPU hits the breakpoint instruction, a trap occurs, the CPU's
60registers are saved, and control passes to Kprobes via the
61notifier_call_chain mechanism. Kprobes executes the "pre_handler"
62associated with the kprobe, passing the handler the addresses of the
63kprobe struct and the saved registers.
64
65Next, Kprobes single-steps its copy of the probed instruction.
66(It would be simpler to single-step the actual instruction in place,
67but then Kprobes would have to temporarily remove the breakpoint
68instruction. This would open a small time window when another CPU
69could sail right past the probepoint.)
70
71After the instruction is single-stepped, Kprobes executes the
72"post_handler," if any, that is associated with the kprobe.
73Execution then continues with the instruction following the probepoint.
74
751.2 How Does a Jprobe Work?
76
77A jprobe is implemented using a kprobe that is placed on a function's
78entry point. It employs a simple mirroring principle to allow
79seamless access to the probed function's arguments. The jprobe
80handler routine should have the same signature (arg list and return
81type) as the function being probed, and must always end by calling
82the Kprobes function jprobe_return().
83
84Here's how it works. When the probe is hit, Kprobes makes a copy of
85the saved registers and a generous portion of the stack (see below).
86Kprobes then points the saved instruction pointer at the jprobe's
87handler routine, and returns from the trap. As a result, control
88passes to the handler, which is presented with the same register and
89stack contents as the probed function. When it is done, the handler
90calls jprobe_return(), which traps again to restore the original stack
91contents and processor state and switch to the probed function.
92
93By convention, the callee owns its arguments, so gcc may produce code
94that unexpectedly modifies that portion of the stack. This is why
95Kprobes saves a copy of the stack and restores it after the jprobe
96handler has run. Up to MAX_STACK_SIZE bytes are copied -- e.g.,
9764 bytes on i386.
98
99Note that the probed function's args may be passed on the stack
Harvey Harrisonb5606c22008-02-13 15:03:16 -0800100or in registers. The jprobe will work in either case, so long as the
101handler's prototype matches that of the probed function.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700102
Abhishek Sagarf47cd9b2008-02-06 01:38:22 -08001031.3 Return Probes
104
1051.3.1 How Does a Return Probe Work?
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700106
107When you call register_kretprobe(), Kprobes establishes a kprobe at
108the entry to the function. When the probed function is called and this
109probe is hit, Kprobes saves a copy of the return address, and replaces
110the return address with the address of a "trampoline." The trampoline
111is an arbitrary piece of code -- typically just a nop instruction.
112At boot time, Kprobes registers a kprobe at the trampoline.
113
114When the probed function executes its return instruction, control
115passes to the trampoline and that probe is hit. Kprobes' trampoline
Abhishek Sagarf47cd9b2008-02-06 01:38:22 -0800116handler calls the user-specified return handler associated with the
117kretprobe, then sets the saved instruction pointer to the saved return
118address, and that's where execution resumes upon return from the trap.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700119
120While the probed function is executing, its return address is
121stored in an object of type kretprobe_instance. Before calling
122register_kretprobe(), the user sets the maxactive field of the
123kretprobe struct to specify how many instances of the specified
124function can be probed simultaneously. register_kretprobe()
125pre-allocates the indicated number of kretprobe_instance objects.
126
127For example, if the function is non-recursive and is called with a
128spinlock held, maxactive = 1 should be enough. If the function is
129non-recursive and can never relinquish the CPU (e.g., via a semaphore
130or preemption), NR_CPUS should be enough. If maxactive <= 0, it is
131set to a default value. If CONFIG_PREEMPT is enabled, the default
132is max(10, 2*NR_CPUS). Otherwise, the default is NR_CPUS.
133
134It's not a disaster if you set maxactive too low; you'll just miss
135some probes. In the kretprobe struct, the nmissed field is set to
136zero when the return probe is registered, and is incremented every
137time the probed function is entered but there is no kretprobe_instance
138object available for establishing the return probe.
139
Abhishek Sagarf47cd9b2008-02-06 01:38:22 -08001401.3.2 Kretprobe entry-handler
141
142Kretprobes also provides an optional user-specified handler which runs
143on function entry. This handler is specified by setting the entry_handler
144field of the kretprobe struct. Whenever the kprobe placed by kretprobe at the
145function entry is hit, the user-defined entry_handler, if any, is invoked.
146If the entry_handler returns 0 (success) then a corresponding return handler
147is guaranteed to be called upon function return. If the entry_handler
148returns a non-zero error then Kprobes leaves the return address as is, and
149the kretprobe has no further effect for that particular function instance.
150
151Multiple entry and return handler invocations are matched using the unique
152kretprobe_instance object associated with them. Additionally, a user
153may also specify per return-instance private data to be part of each
154kretprobe_instance object. This is especially useful when sharing private
155data between corresponding user entry and return handlers. The size of each
156private data object can be specified at kretprobe registration time by
157setting the data_size field of the kretprobe struct. This data can be
158accessed through the data field of each kretprobe_instance object.
159
160In case probed function is entered but there is no kretprobe_instance
161object available, then in addition to incrementing the nmissed count,
162the user entry_handler invocation is also skipped.
163
Jim Kenistond27a4dd2005-08-04 12:53:35 -07001642. Architectures Supported
165
166Kprobes, jprobes, and return probes are implemented on the following
167architectures:
168
169- i386
Jim Keniston8861da32006-02-14 13:53:06 -0800170- x86_64 (AMD-64, EM64T)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700171- ppc64
Jim Keniston8861da32006-02-14 13:53:06 -0800172- ia64 (Does not support probes on instruction slot1.)
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700173- sparc64 (Return probes not yet implemented.)
Nicolas Pitre5de865b2007-12-03 17:15:52 -0500174- arm
Kumar Galaf8279622008-06-26 02:01:37 -0500175- ppc
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700176
1773. Configuring Kprobes
178
179When configuring the kernel using make menuconfig/xconfig/oldconfig,
Jim Keniston8861da32006-02-14 13:53:06 -0800180ensure that CONFIG_KPROBES is set to "y". Under "Instrumentation
181Support", look for "Kprobes".
182
183So that you can load and unload Kprobes-based instrumentation modules,
184make sure "Loadable module support" (CONFIG_MODULES) and "Module
185unloading" (CONFIG_MODULE_UNLOAD) are set to "y".
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700186
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700187Also make sure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL
188are set to "y", since kallsyms_lookup_name() is used by the in-kernel
189kprobe address resolution code.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700190
191If you need to insert a probe in the middle of a function, you may find
192it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
193so you can use "objdump -d -l vmlinux" to see the source-to-object
194code mapping.
195
1964. API Reference
197
198The Kprobes API includes a "register" function and an "unregister"
Masami Hiramatsu3b0cb4c2008-04-28 02:14:30 -0700199function for each type of probe. The API also includes "register_*probes"
200and "unregister_*probes" functions for (un)registering arrays of probes.
201Here are terse, mini-man-page specifications for these functions and
202the associated probe handlers that you'll write. See the files in the
203samples/kprobes/ sub-directory for examples.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700204
2054.1 register_kprobe
206
207#include <linux/kprobes.h>
208int register_kprobe(struct kprobe *kp);
209
210Sets a breakpoint at the address kp->addr. When the breakpoint is
211hit, Kprobes calls kp->pre_handler. After the probed instruction
212is single-stepped, Kprobe calls kp->post_handler. If a fault
213occurs during execution of kp->pre_handler or kp->post_handler,
214or during single-stepping of the probed instruction, Kprobes calls
215kp->fault_handler. Any or all handlers can be NULL.
216
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700217NOTE:
2181. With the introduction of the "symbol_name" field to struct kprobe,
219the probepoint address resolution will now be taken care of by the kernel.
220The following will now work:
221
222 kp.symbol_name = "symbol_name";
223
224(64-bit powerpc intricacies such as function descriptors are handled
225transparently)
226
2272. Use the "offset" field of struct kprobe if the offset into the symbol
228to install a probepoint is known. This field is used to calculate the
229probepoint.
230
2313. Specify either the kprobe "symbol_name" OR the "addr". If both are
232specified, kprobe registration will fail with -EINVAL.
233
2344. With CISC architectures (such as i386 and x86_64), the kprobes code
235does not validate if the kprobe.addr is at an instruction boundary.
236Use "offset" with caution.
237
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700238register_kprobe() returns 0 on success, or a negative errno otherwise.
239
240User's pre-handler (kp->pre_handler):
241#include <linux/kprobes.h>
242#include <linux/ptrace.h>
243int pre_handler(struct kprobe *p, struct pt_regs *regs);
244
245Called with p pointing to the kprobe associated with the breakpoint,
246and regs pointing to the struct containing the registers saved when
247the breakpoint was hit. Return 0 here unless you're a Kprobes geek.
248
249User's post-handler (kp->post_handler):
250#include <linux/kprobes.h>
251#include <linux/ptrace.h>
252void post_handler(struct kprobe *p, struct pt_regs *regs,
253 unsigned long flags);
254
255p and regs are as described for the pre_handler. flags always seems
256to be zero.
257
258User's fault-handler (kp->fault_handler):
259#include <linux/kprobes.h>
260#include <linux/ptrace.h>
261int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr);
262
263p and regs are as described for the pre_handler. trapnr is the
264architecture-specific trap number associated with the fault (e.g.,
265on i386, 13 for a general protection fault or 14 for a page fault).
266Returns 1 if it successfully handled the exception.
267
2684.2 register_jprobe
269
270#include <linux/kprobes.h>
271int register_jprobe(struct jprobe *jp)
272
273Sets a breakpoint at the address jp->kp.addr, which must be the address
274of the first instruction of a function. When the breakpoint is hit,
275Kprobes runs the handler whose address is jp->entry.
276
277The handler should have the same arg list and return type as the probed
278function; and just before it returns, it must call jprobe_return().
279(The handler never actually returns, since jprobe_return() returns
Harvey Harrisonb5606c22008-02-13 15:03:16 -0800280control to Kprobes.) If the probed function is declared asmlinkage
281or anything else that affects how args are passed, the handler's
282declaration must match.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700283
284register_jprobe() returns 0 on success, or a negative errno otherwise.
285
2864.3 register_kretprobe
287
288#include <linux/kprobes.h>
289int register_kretprobe(struct kretprobe *rp);
290
291Establishes a return probe for the function whose address is
292rp->kp.addr. When that function returns, Kprobes calls rp->handler.
293You must set rp->maxactive appropriately before you call
294register_kretprobe(); see "How Does a Return Probe Work?" for details.
295
296register_kretprobe() returns 0 on success, or a negative errno
297otherwise.
298
299User's return-probe handler (rp->handler):
300#include <linux/kprobes.h>
301#include <linux/ptrace.h>
302int kretprobe_handler(struct kretprobe_instance *ri, struct pt_regs *regs);
303
304regs is as described for kprobe.pre_handler. ri points to the
305kretprobe_instance object, of which the following fields may be
306of interest:
307- ret_addr: the return address
308- rp: points to the corresponding kretprobe object
309- task: points to the corresponding task struct
Abhishek Sagarf47cd9b2008-02-06 01:38:22 -0800310- data: points to per return-instance private data; see "Kretprobe
311 entry-handler" for details.
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700312
313The regs_return_value(regs) macro provides a simple abstraction to
314extract the return value from the appropriate register as defined by
315the architecture's ABI.
316
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700317The handler's return value is currently ignored.
318
3194.4 unregister_*probe
320
321#include <linux/kprobes.h>
322void unregister_kprobe(struct kprobe *kp);
323void unregister_jprobe(struct jprobe *jp);
324void unregister_kretprobe(struct kretprobe *rp);
325
326Removes the specified probe. The unregister function can be called
327at any time after the probe has been registered.
328
Masami Hiramatsu3b0cb4c2008-04-28 02:14:30 -0700329NOTE:
330If the functions find an incorrect probe (ex. an unregistered probe),
331they clear the addr field of the probe.
332
3334.5 register_*probes
334
335#include <linux/kprobes.h>
336int register_kprobes(struct kprobe **kps, int num);
337int register_kretprobes(struct kretprobe **rps, int num);
338int register_jprobes(struct jprobe **jps, int num);
339
340Registers each of the num probes in the specified array. If any
341error occurs during registration, all probes in the array, up to
342the bad probe, are safely unregistered before the register_*probes
343function returns.
344- kps/rps/jps: an array of pointers to *probe data structures
345- num: the number of the array entries.
346
347NOTE:
348You have to allocate(or define) an array of pointers and set all
349of the array entries before using these functions.
350
3514.6 unregister_*probes
352
353#include <linux/kprobes.h>
354void unregister_kprobes(struct kprobe **kps, int num);
355void unregister_kretprobes(struct kretprobe **rps, int num);
356void unregister_jprobes(struct jprobe **jps, int num);
357
358Removes each of the num probes in the specified array at once.
359
360NOTE:
361If the functions find some incorrect probes (ex. unregistered
362probes) in the specified array, they clear the addr field of those
363incorrect probes. However, other probes in the array are
364unregistered correctly.
365
Jim Kenistond27a4dd2005-08-04 12:53:35 -07003665. Kprobes Features and Limitations
367
Jim Keniston8861da32006-02-14 13:53:06 -0800368Kprobes allows multiple probes at the same address. Currently,
369however, there cannot be multiple jprobes on the same function at
370the same time.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700371
372In general, you can install a probe anywhere in the kernel.
373In particular, you can probe interrupt handlers. Known exceptions
374are discussed in this section.
375
Jim Keniston8861da32006-02-14 13:53:06 -0800376The register_*probe functions will return -EINVAL if you attempt
377to install a probe in the code that implements Kprobes (mostly
378kernel/kprobes.c and arch/*/kernel/kprobes.c, but also functions such
379as do_page_fault and notifier_call_chain).
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700380
381If you install a probe in an inline-able function, Kprobes makes
382no attempt to chase down all inline instances of the function and
383install probes there. gcc may inline a function without being asked,
384so keep this in mind if you're not seeing the probe hits you expect.
385
386A probe handler can modify the environment of the probed function
387-- e.g., by modifying kernel data structures, or by modifying the
388contents of the pt_regs struct (which are restored to the registers
389upon return from the breakpoint). So Kprobes can be used, for example,
390to install a bug fix or to inject faults for testing. Kprobes, of
391course, has no way to distinguish the deliberately injected faults
392from the accidental ones. Don't drink and probe.
393
394Kprobes makes no attempt to prevent probe handlers from stepping on
395each other -- e.g., probing printk() and then calling printk() from a
Jim Keniston8861da32006-02-14 13:53:06 -0800396probe handler. If a probe handler hits a probe, that second probe's
397handlers won't be run in that instance, and the kprobe.nmissed member
398of the second probe will be incremented.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700399
Jim Keniston8861da32006-02-14 13:53:06 -0800400As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of
401the same handler) may run concurrently on different CPUs.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700402
Jim Keniston8861da32006-02-14 13:53:06 -0800403Kprobes does not use mutexes or allocate memory except during
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700404registration and unregistration.
405
406Probe handlers are run with preemption disabled. Depending on the
407architecture, handlers may also run with interrupts disabled. In any
408case, your handler should not yield the CPU (e.g., by attempting to
409acquire a semaphore).
410
411Since a return probe is implemented by replacing the return
412address with the trampoline's address, stack backtraces and calls
413to __builtin_return_address() will typically yield the trampoline's
414address instead of the real return address for kretprobed functions.
415(As far as we can tell, __builtin_return_address() is used only
416for instrumentation and error reporting.)
417
Jim Keniston8861da32006-02-14 13:53:06 -0800418If the number of times a function is called does not match the number
419of times it returns, registering a return probe on that function may
Ananth N Mavinakayanahallibf8f6e5b2007-05-08 00:34:16 -0700420produce undesirable results. In such a case, a line:
421kretprobe BUG!: Processing kretprobe d000000000041aa8 @ c00000000004f48c
422gets printed. With this information, one will be able to correlate the
423exact instance of the kretprobe that caused the problem. We have the
424do_exit() case covered. do_execve() and do_fork() are not an issue.
425We're unaware of other specific cases where this could be a problem.
Jim Keniston8861da32006-02-14 13:53:06 -0800426
427If, upon entry to or exit from a function, the CPU is running on
428a stack other than that of the current task, registering a return
429probe on that function may produce undesirable results. For this
430reason, Kprobes doesn't support return probes (or kprobes or jprobes)
431on the x86_64 version of __switch_to(); the registration functions
432return -EINVAL.
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700433
4346. Probe Overhead
435
436On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
437microseconds to process. Specifically, a benchmark that hits the same
438probepoint repeatedly, firing a simple handler each time, reports 1-2
439million hits per second, depending on the architecture. A jprobe or
440return-probe hit typically takes 50-75% longer than a kprobe hit.
441When you have a return probe set on a function, adding a kprobe at
442the entry to that function adds essentially no overhead.
443
444Here are sample overhead figures (in usec) for different architectures.
445k = kprobe; j = jprobe; r = return probe; kr = kprobe + return probe
446on same function; jr = jprobe + return probe on same function
447
448i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips
449k = 0.57 usec; j = 1.00; r = 0.92; kr = 0.99; jr = 1.40
450
451x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips
452k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
453
454ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
455k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
456
4577. TODO
458
Jim Keniston8861da32006-02-14 13:53:06 -0800459a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
460programming interface for probe-based instrumentation. Try it out.
461b. Kernel return probes for sparc64.
462c. Support for other architectures.
463d. User-space probes.
464e. Watchpoint probes (which fire on data references).
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700465
4668. Kprobes Example
467
Ananth N Mavinakayanahalli804defe2008-03-04 14:28:38 -0800468See samples/kprobes/kprobe_example.c
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700469
4709. Jprobes Example
471
Ananth N Mavinakayanahalli804defe2008-03-04 14:28:38 -0800472See samples/kprobes/jprobe_example.c
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700473
47410. Kretprobes Example
475
Ananth N Mavinakayanahalli804defe2008-03-04 14:28:38 -0800476See samples/kprobes/kretprobe_example.c
Jim Kenistond27a4dd2005-08-04 12:53:35 -0700477
478For additional information on Kprobes, refer to the following URLs:
479http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe
480http://www.redhat.com/magazine/005mar05/features/kprobes/
Ananth N Mavinakayanahalli09b18202006-10-02 02:17:32 -0700481http://www-users.cs.umn.edu/~boutcher/kprobes/
482http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115)
Ananth N Mavinakayanahallibf8f6e5b2007-05-08 00:34:16 -0700483
484
485Appendix A: The kprobes debugfs interface
486
487With recent kernels (> 2.6.20) the list of registered kprobes is visible
488under the /debug/kprobes/ directory (assuming debugfs is mounted at /debug).
489
490/debug/kprobes/list: Lists all registered probes on the system
491
492c015d71a k vfs_read+0x0
493c011a316 j do_fork+0x0
494c03dedc5 r tcp_v4_rcv+0x0
495
496The first column provides the kernel address where the probe is inserted.
497The second column identifies the type of probe (k - kprobe, r - kretprobe
498and j - jprobe), while the third column specifies the symbol+offset of
499the probe. If the probed function belongs to a module, the module name
500is also specified.
501
502/debug/kprobes/enabled: Turn kprobes ON/OFF
503
504Provides a knob to globally turn registered kprobes ON or OFF. By default,
505all kprobes are enabled. By echoing "0" to this file, all registered probes
506will be disarmed, till such time a "1" is echoed to this file.