1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
|
// SPDX-License-Identifier: GPL-2.0
#include <linux/context_tracking.h>
#include <linux/entry-common.h>
#include <linux/livepatch.h>
#include <linux/audit.h>
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
/**
* enter_from_user_mode - Establish state when coming from user mode
*
* Syscall/interrupt entry disables interrupts, but user mode is traced as
* interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
*
* 1) Tell lockdep that interrupts are disabled
* 2) Invoke context tracking if enabled to reactivate RCU
* 3) Trace interrupts off state
*/
static __always_inline void enter_from_user_mode(struct pt_regs *regs)
{
arch_check_user_regs(regs);
lockdep_hardirqs_off(CALLER_ADDR0);
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit_irqoff();
instrumentation_begin();
trace_hardirqs_off_finish();
instrumentation_end();
}
static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
{
if (unlikely(audit_context())) {
unsigned long args[6];
syscall_get_arguments(current, regs, args);
audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
}
}
static long syscall_trace_enter(struct pt_regs *regs, long syscall,
unsigned long ti_work)
{
long ret = 0;
/* Handle ptrace */
if (ti_work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
ret = arch_syscall_enter_tracehook(regs);
if (ret || (ti_work & _TIF_SYSCALL_EMU))
return -1L;
}
/* Do seccomp after ptrace, to catch any tracer changes. */
if (ti_work & _TIF_SECCOMP) {
ret = __secure_computing(NULL);
if (ret == -1L)
return ret;
}
/* Either of the above might have changed the syscall number */
syscall = syscall_get_nr(current, regs);
if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
trace_sys_enter(regs, syscall);
syscall_enter_audit(regs, syscall);
return ret ? : syscall;
}
static __always_inline long
__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
{
unsigned long ti_work;
ti_work = READ_ONCE(current_thread_info()->flags);
if (ti_work & SYSCALL_ENTER_WORK)
syscall = syscall_trace_enter(regs, syscall, ti_work);
return syscall;
}
long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
{
return __syscall_enter_from_user_work(regs, syscall);
}
noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
{
long ret;
enter_from_user_mode(regs);
instrumentation_begin();
local_irq_enable();
ret = __syscall_enter_from_user_work(regs, syscall);
instrumentation_end();
return ret;
}
noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
{
enter_from_user_mode(regs);
instrumentation_begin();
local_irq_enable();
instrumentation_end();
}
/**
* exit_to_user_mode - Fixup state when exiting to user mode
*
* Syscall/interupt exit enables interrupts, but the kernel state is
* interrupts disabled when this is invoked. Also tell RCU about it.
*
* 1) Trace interrupts on state
* 2) Invoke context tracking if enabled to adjust RCU state
* 3) Invoke architecture specific last minute exit code, e.g. speculation
* mitigations, etc.
* 4) Tell lockdep that interrupts are enabled
*/
static __always_inline void exit_to_user_mode(void)
{
instrumentation_begin();
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare(CALLER_ADDR0);
instrumentation_end();
user_enter_irqoff();
arch_exit_to_user_mode();
lockdep_hardirqs_on(CALLER_ADDR0);
}
/* Workaround to allow gradual conversion of architecture code */
void __weak arch_do_signal(struct pt_regs *regs) { }
static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
unsigned long ti_work)
{
/*
* Before returning to user space ensure that all pending work
* items have been completed.
*/
while (ti_work & EXIT_TO_USER_MODE_WORK) {
local_irq_enable_exit_to_user(ti_work);
if (ti_work & _TIF_NEED_RESCHED)
schedule();
if (ti_work & _TIF_UPROBE)
uprobe_notify_resume(regs);
if (ti_work & _TIF_PATCH_PENDING)
klp_update_patch_state(current);
if (ti_work & _TIF_SIGPENDING)
arch_do_signal(regs);
if (ti_work & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
rseq_handle_notify_resume(NULL, regs);
}
/* Architecture specific TIF work */
arch_exit_to_user_mode_work(regs, ti_work);
/*
* Disable interrupts and reevaluate the work flags as they
* might have changed while interrupts and preemption was
* enabled above.
*/
local_irq_disable_exit_to_user();
ti_work = READ_ONCE(current_thread_info()->flags);
}
/* Return the latest work state for arch_exit_to_user_mode() */
return ti_work;
}
static void exit_to_user_mode_prepare(struct pt_regs *regs)
{
unsigned long ti_work = READ_ONCE(current_thread_info()->flags);
lockdep_assert_irqs_disabled();
if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
ti_work = exit_to_user_mode_loop(regs, ti_work);
arch_exit_to_user_mode_prepare(regs, ti_work);
/* Ensure that the address limit is intact and no locks are held */
addr_limit_user_check();
lockdep_assert_irqs_disabled();
lockdep_sys_exit();
}
#ifndef _TIF_SINGLESTEP
static inline bool report_single_step(unsigned long ti_work)
{
return false;
}
#else
/*
* If TIF_SYSCALL_EMU is set, then the only reason to report is when
* TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall
* instruction has been already reported in syscall_enter_from_user_mode().
*/
#define SYSEMU_STEP (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
static inline bool report_single_step(unsigned long ti_work)
{
return (ti_work & SYSEMU_STEP) == _TIF_SINGLESTEP;
}
#endif
static void syscall_exit_work(struct pt_regs *regs, unsigned long ti_work)
{
bool step;
audit_syscall_exit(regs);
if (ti_work & _TIF_SYSCALL_TRACEPOINT)
trace_sys_exit(regs, syscall_get_return_value(current, regs));
step = report_single_step(ti_work);
if (step || ti_work & _TIF_SYSCALL_TRACE)
arch_syscall_exit_tracehook(regs, step);
}
/*
* Syscall specific exit to user mode preparation. Runs with interrupts
* enabled.
*/
static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
{
u32 cached_flags = READ_ONCE(current_thread_info()->flags);
unsigned long nr = syscall_get_nr(current, regs);
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
local_irq_enable();
}
rseq_syscall(regs);
/*
* Do one-time syscall specific work. If these work items are
* enabled, we want to run them exactly once per syscall exit with
* interrupts enabled.
*/
if (unlikely(cached_flags & SYSCALL_EXIT_WORK))
syscall_exit_work(regs, cached_flags);
}
__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
{
instrumentation_begin();
syscall_exit_to_user_mode_prepare(regs);
local_irq_disable_exit_to_user();
exit_to_user_mode_prepare(regs);
instrumentation_end();
exit_to_user_mode();
}
noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
{
enter_from_user_mode(regs);
}
noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
{
instrumentation_begin();
exit_to_user_mode_prepare(regs);
instrumentation_end();
exit_to_user_mode();
}
noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
{
irqentry_state_t ret = {
.exit_rcu = false,
};
if (user_mode(regs)) {
irqentry_enter_from_user_mode(regs);
return ret;
}
/*
* If this entry hit the idle task invoke rcu_irq_enter() whether
* RCU is watching or not.
*
* Interupts can nest when the first interrupt invokes softirq
* processing on return which enables interrupts.
*
* Scheduler ticks in the idle task can mark quiescent state and
* terminate a grace period, if and only if the timer interrupt is
* not nested into another interrupt.
*
* Checking for rcu_is_watching() here would prevent the nesting
* interrupt to invoke rcu_irq_enter(). If that nested interrupt is
* the tick then rcu_flavor_sched_clock_irq() would wrongfully
* assume that it is the first interupt and eventually claim
* quiescient state and end grace periods prematurely.
*
* Unconditionally invoke rcu_irq_enter() so RCU state stays
* consistent.
*
* TINY_RCU does not support EQS, so let the compiler eliminate
* this part when enabled.
*/
if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
/*
* If RCU is not watching then the same careful
* sequence vs. lockdep and tracing is required
* as in irq_enter_from_user_mode().
*/
lockdep_hardirqs_off(CALLER_ADDR0);
rcu_irq_enter();
instrumentation_begin();
trace_hardirqs_off_finish();
instrumentation_end();
ret.exit_rcu = true;
return ret;
}
/*
* If RCU is watching then RCU only wants to check whether it needs
* to restart the tick in NOHZ mode. rcu_irq_enter_check_tick()
* already contains a warning when RCU is not watching, so no point
* in having another one here.
*/
instrumentation_begin();
rcu_irq_enter_check_tick();
/* Use the combo lockdep/tracing function */
trace_hardirqs_off();
instrumentation_end();
return ret;
}
void irqentry_exit_cond_resched(void)
{
if (!preempt_count()) {
/* Sanity check RCU and thread stack */
rcu_irq_exit_check_preempt();
if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
WARN_ON_ONCE(!on_thread_stack());
if (need_resched())
preempt_schedule_irq();
}
}
noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
{
lockdep_assert_irqs_disabled();
/* Check whether this returns to user mode */
if (user_mode(regs)) {
irqentry_exit_to_user_mode(regs);
} else if (!regs_irqs_disabled(regs)) {
/*
* If RCU was not watching on entry this needs to be done
* carefully and needs the same ordering of lockdep/tracing
* and RCU as the return to user mode path.
*/
if (state.exit_rcu) {
instrumentation_begin();
/* Tell the tracer that IRET will enable interrupts */
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare(CALLER_ADDR0);
instrumentation_end();
rcu_irq_exit();
lockdep_hardirqs_on(CALLER_ADDR0);
return;
}
instrumentation_begin();
if (IS_ENABLED(CONFIG_PREEMPTION))
irqentry_exit_cond_resched();
/* Covers both tracing and lockdep */
trace_hardirqs_on();
instrumentation_end();
} else {
/*
* IRQ flags state is correct already. Just tell RCU if it
* was not watching on entry.
*/
if (state.exit_rcu)
rcu_irq_exit();
}
}
|