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
|
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/context_tracking.h>
#include <linux/entry-common.h>
#include <linux/err.h>
#include <linux/compat.h>
#include <linux/rseq.h>
#include <linux/sched/debug.h> /* for show_regs */
#include <asm/kup.h>
#include <asm/cputime.h>
#include <asm/hw_irq.h>
#include <asm/interrupt.h>
#include <asm/kprobes.h>
#include <asm/paca.h>
#include <asm/ptrace.h>
#include <asm/reg.h>
#include <asm/signal.h>
#include <asm/switch_to.h>
#include <asm/syscall.h>
#include <asm/time.h>
#include <asm/tm.h>
#include <asm/unistd.h>
#if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32)
unsigned long global_dbcr0[NR_CPUS];
#endif
#ifdef CONFIG_PPC_BOOK3S_64
DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
static inline bool exit_must_hard_disable(void)
{
return static_branch_unlikely(&interrupt_exit_not_reentrant);
}
#else
static inline bool exit_must_hard_disable(void)
{
return true;
}
#endif
/*
* local irqs must be disabled. Returns false if the caller must re-enable
* them, check for new work, and try again.
*
* This should be called with local irqs disabled, but if they were previously
* enabled when the interrupt handler returns (indicating a process-context /
* synchronous interrupt) then irqs_enabled should be true.
*
* restartable is true then EE/RI can be left on because interrupts are handled
* with a restart sequence.
*/
static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable)
{
bool must_hard_disable = (exit_must_hard_disable() || !restartable);
/* This must be done with RI=1 because tracing may touch vmaps */
trace_hardirqs_on();
if (must_hard_disable)
__hard_EE_RI_disable();
#ifdef CONFIG_PPC64
/* This pattern matches prep_irq_for_idle */
if (unlikely(lazy_irq_pending_nocheck())) {
if (must_hard_disable) {
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
__hard_RI_enable();
}
trace_hardirqs_off();
return false;
}
#endif
return true;
}
/*
* This should be called after a syscall returns, with r3 the return value
* from the syscall. If this function returns non-zero, the system call
* exit assembly should additionally load all GPR registers and CTR and XER
* from the interrupt frame.
*
* The function graph tracer can not trace the return side of this function,
* because RI=0 and soft mask state is "unreconciled", so it is marked notrace.
*/
notrace unsigned long syscall_exit_prepare(unsigned long r3,
struct pt_regs *regs,
long scv)
{
unsigned long ti_flags;
bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv;
kuap_assert_locked();
regs->result = r3;
regs->exit_flags = 0;
ti_flags = read_thread_flags();
if (unlikely(r3 >= (unsigned long)-MAX_ERRNO) && is_not_scv) {
if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) {
r3 = -r3;
regs->ccr |= 0x10000000; /* Set SO bit in CR */
}
}
if (unlikely(ti_flags & _TIF_PERSYSCALL_MASK)) {
if (ti_flags & _TIF_RESTOREALL)
regs->exit_flags = _TIF_RESTOREALL;
else
regs->gpr[3] = r3;
clear_bits(_TIF_PERSYSCALL_MASK, ¤t_thread_info()->flags);
} else {
regs->gpr[3] = r3;
}
if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
regs->exit_flags |= _TIF_RESTOREALL;
}
syscall_exit_to_user_mode(regs);
again:
user_enter_irqoff();
if (!prep_irq_for_enabled_exit(true)) {
user_exit_irqoff();
local_irq_enable();
local_irq_disable();
goto again;
}
/* Restore user access locks last */
kuap_user_restore(regs);
#ifdef CONFIG_PPC64
regs->exit_result = regs->exit_flags;
#endif
return regs->exit_flags;
}
#ifdef CONFIG_PPC64
notrace unsigned long syscall_exit_restart(unsigned long r3, struct pt_regs *regs)
{
/*
* This is called when detecting a soft-pending interrupt as well as
* an alternate-return interrupt. So we can't just have the alternate
* return path clear SRR1[MSR] and set PACA_IRQ_HARD_DIS (unless
* the soft-pending case were to fix things up as well). RI might be
* disabled, in which case it gets re-enabled by __hard_irq_disable().
*/
__hard_irq_disable();
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
#ifdef CONFIG_PPC_BOOK3S_64
set_kuap(AMR_KUAP_BLOCKED);
#endif
again:
user_enter_irqoff();
if (!prep_irq_for_enabled_exit(true)) {
user_exit_irqoff();
local_irq_enable();
local_irq_disable();
goto again;
}
kuap_user_restore(regs);
regs->exit_result |= regs->exit_flags;
return regs->exit_result;
}
#endif
notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs)
{
unsigned long ret;
BUG_ON(regs_is_unrecoverable(regs));
BUG_ON(regs_irqs_disabled(regs));
/*
* We don't need to restore AMR on the way back to userspace for KUAP.
* AMR can only have been unlocked if we interrupted the kernel.
*/
kuap_assert_locked();
local_irq_disable();
regs->exit_flags = 0;
again:
check_return_regs_valid(regs);
user_enter_irqoff();
if (!prep_irq_for_enabled_exit(true)) {
user_exit_irqoff();
local_irq_enable();
local_irq_disable();
goto again;
}
/* Restore user access locks last */
kuap_user_restore(regs);
ret = regs->exit_flags;
#ifdef CONFIG_PPC64
regs->exit_result = ret;
#endif
return ret;
}
void preempt_schedule_irq(void);
notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
{
unsigned long ret = 0;
unsigned long kuap;
bool stack_store = read_thread_flags() & _TIF_EMULATE_STACK_STORE;
if (regs_is_unrecoverable(regs))
unrecoverable_exception(regs);
/*
* CT_WARN_ON comes here via program_check_exception, so avoid
* recursion.
*
* Skip the assertion on PMIs on 64e to work around a problem caused
* by NMI PMIs incorrectly taking this interrupt return path, it's
* possible for this to hit after interrupt exit to user switches
* context to user. See also the comment in the performance monitor
* handler in exceptions-64e.S
*/
if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
TRAP(regs) != INTERRUPT_PROGRAM &&
TRAP(regs) != INTERRUPT_PERFMON)
CT_WARN_ON(ct_state() == CT_STATE_USER);
kuap = kuap_get_and_assert_locked();
local_irq_disable();
if (!regs_irqs_disabled(regs)) {
/* Returning to a kernel context with local irqs enabled. */
WARN_ON_ONCE(!(regs->msr & MSR_EE));
again:
check_return_regs_valid(regs);
/*
* Stack store exit can't be restarted because the interrupt
* stack frame might have been clobbered.
*/
if (!prep_irq_for_enabled_exit(unlikely(stack_store))) {
/*
* Replay pending soft-masked interrupts now. Don't
* just local_irq_enabe(); local_irq_disable(); because
* if we are returning from an asynchronous interrupt
* here, another one might hit after irqs are enabled,
* and it would exit via this same path allowing
* another to fire, and so on unbounded.
*/
hard_irq_disable();
replay_soft_interrupts();
/* Took an interrupt, may have more exit work to do. */
goto again;
}
#ifdef CONFIG_PPC64
/*
* An interrupt may clear MSR[EE] and set this concurrently,
* but it will be marked pending and the exit will be retried.
* This leaves a racy window where MSR[EE]=0 and HARD_DIS is
* clear, until interrupt_exit_kernel_restart() calls
* hard_irq_disable(), which will set HARD_DIS again.
*/
local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
} else {
check_return_regs_valid(regs);
if (unlikely(stack_store))
__hard_EE_RI_disable();
#else
} else {
__hard_EE_RI_disable();
#endif /* CONFIG_PPC64 */
}
if (unlikely(stack_store)) {
clear_bits(_TIF_EMULATE_STACK_STORE, ¤t_thread_info()->flags);
ret = 1;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
local_paca->tm_scratch = regs->msr;
#endif
/*
* 64s does not want to mfspr(SPRN_AMR) here, because this comes after
* mtmsr, which would cause Read-After-Write stalls. Hence, take the
* AMR value from the check above.
*/
kuap_kernel_restore(regs, kuap);
return ret;
}
#ifdef CONFIG_PPC64
notrace unsigned long interrupt_exit_user_restart(struct pt_regs *regs)
{
__hard_irq_disable();
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
#ifdef CONFIG_PPC_BOOK3S_64
set_kuap(AMR_KUAP_BLOCKED);
#endif
trace_hardirqs_off();
account_cpu_user_entry();
BUG_ON(!user_mode(regs));
regs->exit_result |= interrupt_exit_user_prepare(regs);
return regs->exit_result;
}
/*
* No real need to return a value here because the stack store case does not
* get restarted.
*/
notrace unsigned long interrupt_exit_kernel_restart(struct pt_regs *regs)
{
__hard_irq_disable();
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
#ifdef CONFIG_PPC_BOOK3S_64
set_kuap(AMR_KUAP_BLOCKED);
#endif
if (regs->softe == IRQS_ENABLED)
trace_hardirqs_off();
BUG_ON(user_mode(regs));
return interrupt_exit_kernel_prepare(regs);
}
#endif
|