Commit | Line | Data |
---|---|---|
d27a4ddd JK |
1 | Title : Kernel Probes (Kprobes) |
2 | Authors : Jim Keniston <jkenisto@us.ibm.com> | |
b26486bf MH |
3 | : Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com> |
4 | : Masami Hiramatsu <mhiramat@redhat.com> | |
d27a4ddd JK |
5 | |
6 | CONTENTS | |
7 | ||
8 | 1. Concepts: Kprobes, Jprobes, Return Probes | |
9 | 2. Architectures Supported | |
10 | 3. Configuring Kprobes | |
11 | 4. API Reference | |
12 | 5. Kprobes Features and Limitations | |
13 | 6. Probe Overhead | |
14 | 7. TODO | |
15 | 8. Kprobes Example | |
16 | 9. Jprobes Example | |
17 | 10. Kretprobes Example | |
bf8f6e5b | 18 | Appendix A: The kprobes debugfs interface |
b26486bf | 19 | Appendix B: The kprobes sysctl interface |
d27a4ddd JK |
20 | |
21 | 1. Concepts: Kprobes, Jprobes, Return Probes | |
22 | ||
23 | Kprobes enables you to dynamically break into any kernel routine and | |
24 | collect debugging and performance information non-disruptively. You | |
25 | can trap at almost any kernel code address, specifying a handler | |
26 | routine to be invoked when the breakpoint is hit. | |
27 | ||
28 | There are currently three types of probes: kprobes, jprobes, and | |
29 | kretprobes (also called return probes). A kprobe can be inserted | |
30 | on virtually any instruction in the kernel. A jprobe is inserted at | |
31 | the entry to a kernel function, and provides convenient access to the | |
32 | function's arguments. A return probe fires when a specified function | |
33 | returns. | |
34 | ||
35 | In the typical case, Kprobes-based instrumentation is packaged as | |
36 | a kernel module. The module's init function installs ("registers") | |
37 | one or more probes, and the exit function unregisters them. A | |
38 | registration function such as register_kprobe() specifies where | |
39 | the probe is to be inserted and what handler is to be called when | |
40 | the probe is hit. | |
41 | ||
3b0cb4ca MH |
42 | There are also register_/unregister_*probes() functions for batch |
43 | registration/unregistration of a group of *probes. These functions | |
44 | can speed up unregistration process when you have to unregister | |
45 | a lot of probes at once. | |
46 | ||
b26486bf MH |
47 | The next four subsections explain how the different types of |
48 | probes work and how jump optimization works. They explain certain | |
49 | things that you'll need to know in order to make the best use of | |
50 | Kprobes -- e.g., the difference between a pre_handler and | |
51 | a post_handler, and how to use the maxactive and nmissed fields of | |
52 | a kretprobe. But if you're in a hurry to start using Kprobes, you | |
53 | can skip ahead to section 2. | |
d27a4ddd JK |
54 | |
55 | 1.1 How Does a Kprobe Work? | |
56 | ||
57 | When a kprobe is registered, Kprobes makes a copy of the probed | |
58 | instruction and replaces the first byte(s) of the probed instruction | |
59 | with a breakpoint instruction (e.g., int3 on i386 and x86_64). | |
60 | ||
61 | When a CPU hits the breakpoint instruction, a trap occurs, the CPU's | |
62 | registers are saved, and control passes to Kprobes via the | |
63 | notifier_call_chain mechanism. Kprobes executes the "pre_handler" | |
64 | associated with the kprobe, passing the handler the addresses of the | |
65 | kprobe struct and the saved registers. | |
66 | ||
67 | Next, Kprobes single-steps its copy of the probed instruction. | |
68 | (It would be simpler to single-step the actual instruction in place, | |
69 | but then Kprobes would have to temporarily remove the breakpoint | |
70 | instruction. This would open a small time window when another CPU | |
71 | could sail right past the probepoint.) | |
72 | ||
73 | After the instruction is single-stepped, Kprobes executes the | |
74 | "post_handler," if any, that is associated with the kprobe. | |
75 | Execution then continues with the instruction following the probepoint. | |
76 | ||
77 | 1.2 How Does a Jprobe Work? | |
78 | ||
79 | A jprobe is implemented using a kprobe that is placed on a function's | |
80 | entry point. It employs a simple mirroring principle to allow | |
81 | seamless access to the probed function's arguments. The jprobe | |
82 | handler routine should have the same signature (arg list and return | |
83 | type) as the function being probed, and must always end by calling | |
84 | the Kprobes function jprobe_return(). | |
85 | ||
86 | Here's how it works. When the probe is hit, Kprobes makes a copy of | |
87 | the saved registers and a generous portion of the stack (see below). | |
88 | Kprobes then points the saved instruction pointer at the jprobe's | |
89 | handler routine, and returns from the trap. As a result, control | |
90 | passes to the handler, which is presented with the same register and | |
91 | stack contents as the probed function. When it is done, the handler | |
92 | calls jprobe_return(), which traps again to restore the original stack | |
93 | contents and processor state and switch to the probed function. | |
94 | ||
95 | By convention, the callee owns its arguments, so gcc may produce code | |
96 | that unexpectedly modifies that portion of the stack. This is why | |
97 | Kprobes saves a copy of the stack and restores it after the jprobe | |
98 | handler has run. Up to MAX_STACK_SIZE bytes are copied -- e.g., | |
99 | 64 bytes on i386. | |
100 | ||
101 | Note that the probed function's args may be passed on the stack | |
b5606c2d HH |
102 | or in registers. The jprobe will work in either case, so long as the |
103 | handler's prototype matches that of the probed function. | |
d27a4ddd | 104 | |
f47cd9b5 AS |
105 | 1.3 Return Probes |
106 | ||
107 | 1.3.1 How Does a Return Probe Work? | |
d27a4ddd JK |
108 | |
109 | When you call register_kretprobe(), Kprobes establishes a kprobe at | |
110 | the entry to the function. When the probed function is called and this | |
111 | probe is hit, Kprobes saves a copy of the return address, and replaces | |
112 | the return address with the address of a "trampoline." The trampoline | |
113 | is an arbitrary piece of code -- typically just a nop instruction. | |
114 | At boot time, Kprobes registers a kprobe at the trampoline. | |
115 | ||
116 | When the probed function executes its return instruction, control | |
117 | passes to the trampoline and that probe is hit. Kprobes' trampoline | |
f47cd9b5 AS |
118 | handler calls the user-specified return handler associated with the |
119 | kretprobe, then sets the saved instruction pointer to the saved return | |
120 | address, and that's where execution resumes upon return from the trap. | |
d27a4ddd JK |
121 | |
122 | While the probed function is executing, its return address is | |
123 | stored in an object of type kretprobe_instance. Before calling | |
124 | register_kretprobe(), the user sets the maxactive field of the | |
125 | kretprobe struct to specify how many instances of the specified | |
126 | function can be probed simultaneously. register_kretprobe() | |
127 | pre-allocates the indicated number of kretprobe_instance objects. | |
128 | ||
129 | For example, if the function is non-recursive and is called with a | |
130 | spinlock held, maxactive = 1 should be enough. If the function is | |
131 | non-recursive and can never relinquish the CPU (e.g., via a semaphore | |
132 | or preemption), NR_CPUS should be enough. If maxactive <= 0, it is | |
133 | set to a default value. If CONFIG_PREEMPT is enabled, the default | |
134 | is max(10, 2*NR_CPUS). Otherwise, the default is NR_CPUS. | |
135 | ||
136 | It's not a disaster if you set maxactive too low; you'll just miss | |
137 | some probes. In the kretprobe struct, the nmissed field is set to | |
138 | zero when the return probe is registered, and is incremented every | |
139 | time the probed function is entered but there is no kretprobe_instance | |
140 | object available for establishing the return probe. | |
141 | ||
f47cd9b5 AS |
142 | 1.3.2 Kretprobe entry-handler |
143 | ||
144 | Kretprobes also provides an optional user-specified handler which runs | |
145 | on function entry. This handler is specified by setting the entry_handler | |
146 | field of the kretprobe struct. Whenever the kprobe placed by kretprobe at the | |
147 | function entry is hit, the user-defined entry_handler, if any, is invoked. | |
148 | If the entry_handler returns 0 (success) then a corresponding return handler | |
149 | is guaranteed to be called upon function return. If the entry_handler | |
150 | returns a non-zero error then Kprobes leaves the return address as is, and | |
151 | the kretprobe has no further effect for that particular function instance. | |
152 | ||
153 | Multiple entry and return handler invocations are matched using the unique | |
154 | kretprobe_instance object associated with them. Additionally, a user | |
155 | may also specify per return-instance private data to be part of each | |
156 | kretprobe_instance object. This is especially useful when sharing private | |
157 | data between corresponding user entry and return handlers. The size of each | |
158 | private data object can be specified at kretprobe registration time by | |
159 | setting the data_size field of the kretprobe struct. This data can be | |
160 | accessed through the data field of each kretprobe_instance object. | |
161 | ||
162 | In case probed function is entered but there is no kretprobe_instance | |
163 | object available, then in addition to incrementing the nmissed count, | |
164 | the user entry_handler invocation is also skipped. | |
165 | ||
b26486bf MH |
166 | 1.4 How Does Jump Optimization Work? |
167 | ||
5cc718b9 MH |
168 | If your kernel is built with CONFIG_OPTPROBES=y (currently this flag |
169 | is automatically set 'y' on x86/x86-64, non-preemptive kernel) and | |
b26486bf MH |
170 | the "debug.kprobes_optimization" kernel parameter is set to 1 (see |
171 | sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump | |
172 | instruction instead of a breakpoint instruction at each probepoint. | |
173 | ||
174 | 1.4.1 Init a Kprobe | |
175 | ||
176 | When a probe is registered, before attempting this optimization, | |
177 | Kprobes inserts an ordinary, breakpoint-based kprobe at the specified | |
178 | address. So, even if it's not possible to optimize this particular | |
179 | probepoint, there'll be a probe there. | |
180 | ||
181 | 1.4.2 Safety Check | |
182 | ||
183 | Before optimizing a probe, Kprobes performs the following safety checks: | |
184 | ||
185 | - Kprobes verifies that the region that will be replaced by the jump | |
186 | instruction (the "optimized region") lies entirely within one function. | |
187 | (A jump instruction is multiple bytes, and so may overlay multiple | |
188 | instructions.) | |
189 | ||
190 | - Kprobes analyzes the entire function and verifies that there is no | |
191 | jump 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 | |
201 | the instruction can be executed out of line. | |
202 | ||
203 | 1.4.3 Preparing Detour Buffer | |
204 | ||
205 | Next, Kprobes prepares a "detour" buffer, which contains the following | |
206 | instruction 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 | ||
213 | 1.4.4 Pre-optimization | |
214 | ||
215 | After preparing the detour buffer, Kprobes verifies that none of the | |
216 | following situations exist: | |
217 | - The probe has either a break_handler (i.e., it's a jprobe) or a | |
218 | post_handler. | |
219 | - Other instructions in the optimized region are probed. | |
220 | - The probe is disabled. | |
221 | In any of the above cases, Kprobes won't start optimizing the probe. | |
222 | Since these are temporary situations, Kprobes tries to start | |
223 | optimizing it again if the situation is changed. | |
224 | ||
225 | If the kprobe can be optimized, Kprobes enqueues the kprobe to an | |
226 | optimizing list, and kicks the kprobe-optimizer workqueue to optimize | |
227 | it. If the to-be-optimized probepoint is hit before being optimized, | |
228 | Kprobes returns control to the original instruction path by setting | |
229 | the CPU's instruction pointer to the copied code in the detour buffer | |
230 | -- thus at least avoiding the single-step. | |
231 | ||
232 | 1.4.5 Optimization | |
233 | ||
234 | The Kprobe-optimizer doesn't insert the jump instruction immediately; | |
235 | rather, it calls synchronize_sched() for safety first, because it's | |
236 | possible for a CPU to be interrupted in the middle of executing the | |
237 | optimized region(*). As you know, synchronize_sched() can ensure | |
238 | that all interruptions that were active when synchronize_sched() | |
239 | was called are done, but only if CONFIG_PREEMPT=n. So, this version | |
240 | of kprobe optimization supports only kernels with CONFIG_PREEMPT=n.(**) | |
241 | ||
242 | After that, the Kprobe-optimizer calls stop_machine() to replace | |
243 | the optimized region with a jump instruction to the detour buffer, | |
244 | using text_poke_smp(). | |
245 | ||
246 | 1.4.6 Unoptimization | |
247 | ||
248 | When an optimized kprobe is unregistered, disabled, or blocked by | |
249 | another kprobe, it will be unoptimized. If this happens before | |
250 | the optimization is complete, the kprobe is just dequeued from the | |
251 | optimized list. If the optimization has been done, the jump is | |
252 | replaced with the original code (except for an int3 breakpoint in | |
253 | the first byte) by using text_poke_smp(). | |
254 | ||
255 | (*)Please imagine that the 2nd instruction is interrupted and then | |
256 | the optimizer replaces the 2nd instruction with the jump *address* | |
257 | while the interrupt handler is running. When the interrupt | |
258 | returns to original address, there is no valid instruction, | |
259 | and it causes an unexpected result. | |
260 | ||
261 | (**)This optimization-safety checking may be replaced with the | |
262 | stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y | |
263 | kernel. | |
264 | ||
265 | NOTE for geeks: | |
266 | The jump optimization changes the kprobe's pre_handler behavior. | |
267 | Without optimization, the pre_handler can change the kernel's execution | |
268 | path by changing regs->ip and returning 1. However, when the probe | |
269 | is optimized, that modification is ignored. Thus, if you want to | |
270 | tweak the kernel's execution path, you need to suppress optimization, | |
271 | using one of the following techniques: | |
272 | - Specify an empty function for the kprobe's post_handler or break_handler. | |
273 | or | |
b26486bf MH |
274 | - Execute 'sysctl -w debug.kprobes_optimization=n' |
275 | ||
d27a4ddd JK |
276 | 2. Architectures Supported |
277 | ||
278 | Kprobes, jprobes, and return probes are implemented on the following | |
279 | architectures: | |
280 | ||
b26486bf MH |
281 | - i386 (Supports jump optimization) |
282 | - x86_64 (AMD-64, EM64T) (Supports jump optimization) | |
d27a4ddd | 283 | - ppc64 |
8861da31 | 284 | - ia64 (Does not support probes on instruction slot1.) |
d27a4ddd | 285 | - sparc64 (Return probes not yet implemented.) |
5de865b4 | 286 | - arm |
f8279621 | 287 | - ppc |
d27a4ddd JK |
288 | |
289 | 3. Configuring Kprobes | |
290 | ||
291 | When configuring the kernel using make menuconfig/xconfig/oldconfig, | |
8861da31 JK |
292 | ensure that CONFIG_KPROBES is set to "y". Under "Instrumentation |
293 | Support", look for "Kprobes". | |
294 | ||
295 | So that you can load and unload Kprobes-based instrumentation modules, | |
296 | make sure "Loadable module support" (CONFIG_MODULES) and "Module | |
297 | unloading" (CONFIG_MODULE_UNLOAD) are set to "y". | |
d27a4ddd | 298 | |
09b18203 AM |
299 | Also make sure that CONFIG_KALLSYMS and perhaps even CONFIG_KALLSYMS_ALL |
300 | are set to "y", since kallsyms_lookup_name() is used by the in-kernel | |
301 | kprobe address resolution code. | |
d27a4ddd JK |
302 | |
303 | If you need to insert a probe in the middle of a function, you may find | |
304 | it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO), | |
305 | so you can use "objdump -d -l vmlinux" to see the source-to-object | |
306 | code mapping. | |
307 | ||
308 | 4. API Reference | |
309 | ||
310 | The Kprobes API includes a "register" function and an "unregister" | |
3b0cb4ca MH |
311 | function for each type of probe. The API also includes "register_*probes" |
312 | and "unregister_*probes" functions for (un)registering arrays of probes. | |
313 | Here are terse, mini-man-page specifications for these functions and | |
314 | the associated probe handlers that you'll write. See the files in the | |
315 | samples/kprobes/ sub-directory for examples. | |
d27a4ddd JK |
316 | |
317 | 4.1 register_kprobe | |
318 | ||
319 | #include <linux/kprobes.h> | |
320 | int register_kprobe(struct kprobe *kp); | |
321 | ||
322 | Sets a breakpoint at the address kp->addr. When the breakpoint is | |
323 | hit, Kprobes calls kp->pre_handler. After the probed instruction | |
324 | is single-stepped, Kprobe calls kp->post_handler. If a fault | |
325 | occurs during execution of kp->pre_handler or kp->post_handler, | |
326 | or during single-stepping of the probed instruction, Kprobes calls | |
de5bd88d MH |
327 | kp->fault_handler. Any or all handlers can be NULL. If kp->flags |
328 | is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled, | |
329 | so, it's handlers aren't hit until calling enable_kprobe(kp). | |
d27a4ddd | 330 | |
09b18203 AM |
331 | NOTE: |
332 | 1. With the introduction of the "symbol_name" field to struct kprobe, | |
333 | the probepoint address resolution will now be taken care of by the kernel. | |
334 | The following will now work: | |
335 | ||
336 | kp.symbol_name = "symbol_name"; | |
337 | ||
338 | (64-bit powerpc intricacies such as function descriptors are handled | |
339 | transparently) | |
340 | ||
341 | 2. Use the "offset" field of struct kprobe if the offset into the symbol | |
342 | to install a probepoint is known. This field is used to calculate the | |
343 | probepoint. | |
344 | ||
345 | 3. Specify either the kprobe "symbol_name" OR the "addr". If both are | |
346 | specified, kprobe registration will fail with -EINVAL. | |
347 | ||
348 | 4. With CISC architectures (such as i386 and x86_64), the kprobes code | |
349 | does not validate if the kprobe.addr is at an instruction boundary. | |
350 | Use "offset" with caution. | |
351 | ||
d27a4ddd JK |
352 | register_kprobe() returns 0 on success, or a negative errno otherwise. |
353 | ||
354 | User's pre-handler (kp->pre_handler): | |
355 | #include <linux/kprobes.h> | |
356 | #include <linux/ptrace.h> | |
357 | int pre_handler(struct kprobe *p, struct pt_regs *regs); | |
358 | ||
359 | Called with p pointing to the kprobe associated with the breakpoint, | |
360 | and regs pointing to the struct containing the registers saved when | |
361 | the breakpoint was hit. Return 0 here unless you're a Kprobes geek. | |
362 | ||
363 | User's post-handler (kp->post_handler): | |
364 | #include <linux/kprobes.h> | |
365 | #include <linux/ptrace.h> | |
366 | void post_handler(struct kprobe *p, struct pt_regs *regs, | |
367 | unsigned long flags); | |
368 | ||
369 | p and regs are as described for the pre_handler. flags always seems | |
370 | to be zero. | |
371 | ||
372 | User's fault-handler (kp->fault_handler): | |
373 | #include <linux/kprobes.h> | |
374 | #include <linux/ptrace.h> | |
375 | int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr); | |
376 | ||
377 | p and regs are as described for the pre_handler. trapnr is the | |
378 | architecture-specific trap number associated with the fault (e.g., | |
379 | on i386, 13 for a general protection fault or 14 for a page fault). | |
380 | Returns 1 if it successfully handled the exception. | |
381 | ||
382 | 4.2 register_jprobe | |
383 | ||
384 | #include <linux/kprobes.h> | |
385 | int register_jprobe(struct jprobe *jp) | |
386 | ||
387 | Sets a breakpoint at the address jp->kp.addr, which must be the address | |
388 | of the first instruction of a function. When the breakpoint is hit, | |
389 | Kprobes runs the handler whose address is jp->entry. | |
390 | ||
391 | The handler should have the same arg list and return type as the probed | |
392 | function; and just before it returns, it must call jprobe_return(). | |
393 | (The handler never actually returns, since jprobe_return() returns | |
b5606c2d HH |
394 | control to Kprobes.) If the probed function is declared asmlinkage |
395 | or anything else that affects how args are passed, the handler's | |
396 | declaration must match. | |
d27a4ddd JK |
397 | |
398 | register_jprobe() returns 0 on success, or a negative errno otherwise. | |
399 | ||
400 | 4.3 register_kretprobe | |
401 | ||
402 | #include <linux/kprobes.h> | |
403 | int register_kretprobe(struct kretprobe *rp); | |
404 | ||
405 | Establishes a return probe for the function whose address is | |
406 | rp->kp.addr. When that function returns, Kprobes calls rp->handler. | |
407 | You must set rp->maxactive appropriately before you call | |
408 | register_kretprobe(); see "How Does a Return Probe Work?" for details. | |
409 | ||
410 | register_kretprobe() returns 0 on success, or a negative errno | |
411 | otherwise. | |
412 | ||
413 | User's return-probe handler (rp->handler): | |
414 | #include <linux/kprobes.h> | |
415 | #include <linux/ptrace.h> | |
416 | int kretprobe_handler(struct kretprobe_instance *ri, struct pt_regs *regs); | |
417 | ||
418 | regs is as described for kprobe.pre_handler. ri points to the | |
419 | kretprobe_instance object, of which the following fields may be | |
420 | of interest: | |
421 | - ret_addr: the return address | |
422 | - rp: points to the corresponding kretprobe object | |
423 | - task: points to the corresponding task struct | |
f47cd9b5 AS |
424 | - data: points to per return-instance private data; see "Kretprobe |
425 | entry-handler" for details. | |
09b18203 AM |
426 | |
427 | The regs_return_value(regs) macro provides a simple abstraction to | |
428 | extract the return value from the appropriate register as defined by | |
429 | the architecture's ABI. | |
430 | ||
d27a4ddd JK |
431 | The handler's return value is currently ignored. |
432 | ||
433 | 4.4 unregister_*probe | |
434 | ||
435 | #include <linux/kprobes.h> | |
436 | void unregister_kprobe(struct kprobe *kp); | |
437 | void unregister_jprobe(struct jprobe *jp); | |
438 | void unregister_kretprobe(struct kretprobe *rp); | |
439 | ||
440 | Removes the specified probe. The unregister function can be called | |
441 | at any time after the probe has been registered. | |
442 | ||
3b0cb4ca MH |
443 | NOTE: |
444 | If the functions find an incorrect probe (ex. an unregistered probe), | |
445 | they clear the addr field of the probe. | |
446 | ||
447 | 4.5 register_*probes | |
448 | ||
449 | #include <linux/kprobes.h> | |
450 | int register_kprobes(struct kprobe **kps, int num); | |
451 | int register_kretprobes(struct kretprobe **rps, int num); | |
452 | int register_jprobes(struct jprobe **jps, int num); | |
453 | ||
454 | Registers each of the num probes in the specified array. If any | |
455 | error occurs during registration, all probes in the array, up to | |
456 | the bad probe, are safely unregistered before the register_*probes | |
457 | function returns. | |
458 | - kps/rps/jps: an array of pointers to *probe data structures | |
459 | - num: the number of the array entries. | |
460 | ||
461 | NOTE: | |
462 | You have to allocate(or define) an array of pointers and set all | |
463 | of the array entries before using these functions. | |
464 | ||
465 | 4.6 unregister_*probes | |
466 | ||
467 | #include <linux/kprobes.h> | |
468 | void unregister_kprobes(struct kprobe **kps, int num); | |
469 | void unregister_kretprobes(struct kretprobe **rps, int num); | |
470 | void unregister_jprobes(struct jprobe **jps, int num); | |
471 | ||
472 | Removes each of the num probes in the specified array at once. | |
473 | ||
474 | NOTE: | |
475 | If the functions find some incorrect probes (ex. unregistered | |
476 | probes) in the specified array, they clear the addr field of those | |
477 | incorrect probes. However, other probes in the array are | |
478 | unregistered correctly. | |
479 | ||
8f9b1528 | 480 | 4.7 disable_*probe |
de5bd88d MH |
481 | |
482 | #include <linux/kprobes.h> | |
483 | int disable_kprobe(struct kprobe *kp); | |
8f9b1528 MH |
484 | int disable_kretprobe(struct kretprobe *rp); |
485 | int disable_jprobe(struct jprobe *jp); | |
de5bd88d | 486 | |
8f9b1528 MH |
487 | Temporarily disables the specified *probe. You can enable it again by using |
488 | enable_*probe(). You must specify the probe which has been registered. | |
de5bd88d | 489 | |
8f9b1528 | 490 | 4.8 enable_*probe |
de5bd88d MH |
491 | |
492 | #include <linux/kprobes.h> | |
493 | int enable_kprobe(struct kprobe *kp); | |
8f9b1528 MH |
494 | int enable_kretprobe(struct kretprobe *rp); |
495 | int enable_jprobe(struct jprobe *jp); | |
de5bd88d | 496 | |
8f9b1528 MH |
497 | Enables *probe which has been disabled by disable_*probe(). You must specify |
498 | the probe which has been registered. | |
de5bd88d | 499 | |
d27a4ddd JK |
500 | 5. Kprobes Features and Limitations |
501 | ||
8861da31 JK |
502 | Kprobes allows multiple probes at the same address. Currently, |
503 | however, there cannot be multiple jprobes on the same function at | |
b26486bf MH |
504 | the same time. Also, a probepoint for which there is a jprobe or |
505 | a post_handler cannot be optimized. So if you install a jprobe, | |
506 | or a kprobe with a post_handler, at an optimized probepoint, the | |
507 | probepoint will be unoptimized automatically. | |
d27a4ddd JK |
508 | |
509 | In general, you can install a probe anywhere in the kernel. | |
510 | In particular, you can probe interrupt handlers. Known exceptions | |
511 | are discussed in this section. | |
512 | ||
8861da31 JK |
513 | The register_*probe functions will return -EINVAL if you attempt |
514 | to install a probe in the code that implements Kprobes (mostly | |
515 | kernel/kprobes.c and arch/*/kernel/kprobes.c, but also functions such | |
516 | as do_page_fault and notifier_call_chain). | |
d27a4ddd JK |
517 | |
518 | If you install a probe in an inline-able function, Kprobes makes | |
519 | no attempt to chase down all inline instances of the function and | |
520 | install probes there. gcc may inline a function without being asked, | |
521 | so keep this in mind if you're not seeing the probe hits you expect. | |
522 | ||
523 | A probe handler can modify the environment of the probed function | |
524 | -- e.g., by modifying kernel data structures, or by modifying the | |
525 | contents of the pt_regs struct (which are restored to the registers | |
526 | upon return from the breakpoint). So Kprobes can be used, for example, | |
527 | to install a bug fix or to inject faults for testing. Kprobes, of | |
528 | course, has no way to distinguish the deliberately injected faults | |
529 | from the accidental ones. Don't drink and probe. | |
530 | ||
531 | Kprobes makes no attempt to prevent probe handlers from stepping on | |
532 | each other -- e.g., probing printk() and then calling printk() from a | |
8861da31 JK |
533 | probe handler. If a probe handler hits a probe, that second probe's |
534 | handlers won't be run in that instance, and the kprobe.nmissed member | |
535 | of the second probe will be incremented. | |
536 | ||
537 | As of Linux v2.6.15-rc1, multiple handlers (or multiple instances of | |
538 | the same handler) may run concurrently on different CPUs. | |
539 | ||
540 | Kprobes does not use mutexes or allocate memory except during | |
d27a4ddd JK |
541 | registration and unregistration. |
542 | ||
543 | Probe handlers are run with preemption disabled. Depending on the | |
544 | architecture, handlers may also run with interrupts disabled. In any | |
545 | case, your handler should not yield the CPU (e.g., by attempting to | |
546 | acquire a semaphore). | |
547 | ||
548 | Since a return probe is implemented by replacing the return | |
549 | address with the trampoline's address, stack backtraces and calls | |
550 | to __builtin_return_address() will typically yield the trampoline's | |
551 | address instead of the real return address for kretprobed functions. | |
552 | (As far as we can tell, __builtin_return_address() is used only | |
553 | for instrumentation and error reporting.) | |
554 | ||
8861da31 JK |
555 | If the number of times a function is called does not match the number |
556 | of times it returns, registering a return probe on that function may | |
bf8f6e5b AM |
557 | produce undesirable results. In such a case, a line: |
558 | kretprobe BUG!: Processing kretprobe d000000000041aa8 @ c00000000004f48c | |
559 | gets printed. With this information, one will be able to correlate the | |
560 | exact instance of the kretprobe that caused the problem. We have the | |
561 | do_exit() case covered. do_execve() and do_fork() are not an issue. | |
562 | We're unaware of other specific cases where this could be a problem. | |
8861da31 JK |
563 | |
564 | If, upon entry to or exit from a function, the CPU is running on | |
565 | a stack other than that of the current task, registering a return | |
566 | probe on that function may produce undesirable results. For this | |
567 | reason, Kprobes doesn't support return probes (or kprobes or jprobes) | |
568 | on the x86_64 version of __switch_to(); the registration functions | |
569 | return -EINVAL. | |
d27a4ddd | 570 | |
b26486bf MH |
571 | On x86/x86-64, since the Jump Optimization of Kprobes modifies |
572 | instructions widely, there are some limitations to optimization. To | |
573 | explain it, we introduce some terminology. Imagine a 3-instruction | |
574 | sequence consisting of a two 2-byte instructions and one 3-byte | |
575 | instruction. | |
576 | ||
577 | IA | |
578 | | | |
579 | [-2][-1][0][1][2][3][4][5][6][7] | |
580 | [ins1][ins2][ ins3 ] | |
581 | [<- DCR ->] | |
582 | [<- JTPR ->] | |
583 | ||
584 | ins1: 1st Instruction | |
585 | ins2: 2nd Instruction | |
586 | ins3: 3rd Instruction | |
587 | IA: Insertion Address | |
588 | JTPR: Jump Target Prohibition Region | |
589 | DCR: Detoured Code Region | |
590 | ||
591 | The instructions in DCR are copied to the out-of-line buffer | |
592 | of the kprobe, because the bytes in DCR are replaced by | |
593 | a 5-byte jump instruction. So there are several limitations. | |
594 | ||
595 | a) The instructions in DCR must be relocatable. | |
596 | b) The instructions in DCR must not include a call instruction. | |
597 | c) JTPR must not be targeted by any jump or call instruction. | |
598 | d) DCR must not straddle the border betweeen functions. | |
599 | ||
600 | Anyway, these limitations are checked by the in-kernel instruction | |
601 | decoder, so you don't need to worry about that. | |
602 | ||
d27a4ddd JK |
603 | 6. Probe Overhead |
604 | ||
605 | On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0 | |
606 | microseconds to process. Specifically, a benchmark that hits the same | |
607 | probepoint repeatedly, firing a simple handler each time, reports 1-2 | |
608 | million hits per second, depending on the architecture. A jprobe or | |
609 | return-probe hit typically takes 50-75% longer than a kprobe hit. | |
610 | When you have a return probe set on a function, adding a kprobe at | |
611 | the entry to that function adds essentially no overhead. | |
612 | ||
613 | Here are sample overhead figures (in usec) for different architectures. | |
614 | k = kprobe; j = jprobe; r = return probe; kr = kprobe + return probe | |
615 | on same function; jr = jprobe + return probe on same function | |
616 | ||
617 | i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips | |
618 | k = 0.57 usec; j = 1.00; r = 0.92; kr = 0.99; jr = 1.40 | |
619 | ||
620 | x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips | |
621 | k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07 | |
622 | ||
623 | ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU) | |
624 | k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99 | |
625 | ||
b26486bf MH |
626 | 6.1 Optimized Probe Overhead |
627 | ||
628 | Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to | |
629 | process. Here are sample overhead figures (in usec) for x86 architectures. | |
630 | k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe, | |
631 | r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe. | |
632 | ||
633 | i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips | |
634 | k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33 | |
635 | ||
636 | x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips | |
637 | k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30 | |
638 | ||
d27a4ddd JK |
639 | 7. TODO |
640 | ||
8861da31 JK |
641 | a. SystemTap (http://sourceware.org/systemtap): Provides a simplified |
642 | programming interface for probe-based instrumentation. Try it out. | |
643 | b. Kernel return probes for sparc64. | |
644 | c. Support for other architectures. | |
645 | d. User-space probes. | |
646 | e. Watchpoint probes (which fire on data references). | |
d27a4ddd JK |
647 | |
648 | 8. Kprobes Example | |
649 | ||
804defea | 650 | See samples/kprobes/kprobe_example.c |
d27a4ddd JK |
651 | |
652 | 9. Jprobes Example | |
653 | ||
804defea | 654 | See samples/kprobes/jprobe_example.c |
d27a4ddd JK |
655 | |
656 | 10. Kretprobes Example | |
657 | ||
804defea | 658 | See samples/kprobes/kretprobe_example.c |
d27a4ddd JK |
659 | |
660 | For additional information on Kprobes, refer to the following URLs: | |
661 | http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe | |
662 | http://www.redhat.com/magazine/005mar05/features/kprobes/ | |
09b18203 AM |
663 | http://www-users.cs.umn.edu/~boutcher/kprobes/ |
664 | http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115) | |
bf8f6e5b AM |
665 | |
666 | ||
667 | Appendix A: The kprobes debugfs interface | |
668 | ||
669 | With recent kernels (> 2.6.20) the list of registered kprobes is visible | |
156f5a78 | 670 | under the /sys/kernel/debug/kprobes/ directory (assuming debugfs is mounted at //sys/kernel/debug). |
bf8f6e5b | 671 | |
156f5a78 | 672 | /sys/kernel/debug/kprobes/list: Lists all registered probes on the system |
bf8f6e5b AM |
673 | |
674 | c015d71a k vfs_read+0x0 | |
675 | c011a316 j do_fork+0x0 | |
676 | c03dedc5 r tcp_v4_rcv+0x0 | |
677 | ||
678 | The first column provides the kernel address where the probe is inserted. | |
679 | The second column identifies the type of probe (k - kprobe, r - kretprobe | |
680 | and j - jprobe), while the third column specifies the symbol+offset of | |
681 | the probe. If the probed function belongs to a module, the module name | |
e8386a0c MH |
682 | is also specified. Following columns show probe status. If the probe is on |
683 | a virtual address that is no longer valid (module init sections, module | |
684 | virtual addresses that correspond to modules that've been unloaded), | |
de5bd88d | 685 | such probes are marked with [GONE]. If the probe is temporarily disabled, |
b26486bf MH |
686 | such probes are marked with [DISABLED]. If the probe is optimized, it is |
687 | marked with [OPTIMIZED]. | |
bf8f6e5b | 688 | |
156f5a78 | 689 | /sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly. |
bf8f6e5b | 690 | |
de5bd88d MH |
691 | Provides a knob to globally and forcibly turn registered kprobes ON or OFF. |
692 | By default, all kprobes are enabled. By echoing "0" to this file, all | |
693 | registered probes will be disarmed, till such time a "1" is echoed to this | |
694 | file. Note that this knob just disarms and arms all kprobes and doesn't | |
695 | change each probe's disabling state. This means that disabled kprobes (marked | |
696 | [DISABLED]) will be not enabled if you turn ON all kprobes by this knob. | |
b26486bf MH |
697 | |
698 | ||
699 | Appendix B: The kprobes sysctl interface | |
700 | ||
701 | /proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF. | |
702 | ||
703 | When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides | |
704 | a knob to globally and forcibly turn jump optimization (see section | |
705 | 1.4) ON or OFF. By default, jump optimization is allowed (ON). | |
706 | If you echo "0" to this file or set "debug.kprobes_optimization" to | |
707 | 0 via sysctl, all optimized probes will be unoptimized, and any new | |
708 | probes registered after that will not be optimized. Note that this | |
709 | knob *changes* the optimized state. This means that optimized probes | |
710 | (marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be | |
711 | removed). If the knob is turned on, they will be optimized again. | |
712 |