summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/interrupt.c
blob: eca293794a1e831a7c657a75696fa9b53d95c990 (plain)
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
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
// SPDX-License-Identifier: GPL-2.0-or-later

#include <linux/context_tracking.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;
}

static notrace void booke_load_dbcr0(void)
{
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
	unsigned long dbcr0 = current->thread.debug.dbcr0;

	if (likely(!(dbcr0 & DBCR0_IDM)))
		return;

	/*
	 * Check to see if the dbcr0 register is set up to debug.
	 * Use the internal debug mode bit to do this.
	 */
	mtmsr(mfmsr() & ~MSR_DE);
	if (IS_ENABLED(CONFIG_PPC32)) {
		isync();
		global_dbcr0[smp_processor_id()] = mfspr(SPRN_DBCR0);
	}
	mtspr(SPRN_DBCR0, dbcr0);
	mtspr(SPRN_DBSR, -1);
#endif
}

static notrace void check_return_regs_valid(struct pt_regs *regs)
{
#ifdef CONFIG_PPC_BOOK3S_64
	unsigned long trap, srr0, srr1;
	static bool warned;
	u8 *validp;
	char *h;

	if (trap_is_scv(regs))
		return;

	trap = TRAP(regs);
	// EE in HV mode sets HSRRs like 0xea0
	if (cpu_has_feature(CPU_FTR_HVMODE) && trap == INTERRUPT_EXTERNAL)
		trap = 0xea0;

	switch (trap) {
	case 0x980:
	case INTERRUPT_H_DATA_STORAGE:
	case 0xe20:
	case 0xe40:
	case INTERRUPT_HMI:
	case 0xe80:
	case 0xea0:
	case INTERRUPT_H_FAC_UNAVAIL:
	case 0x1200:
	case 0x1500:
	case 0x1600:
	case 0x1800:
		validp = &local_paca->hsrr_valid;
		if (!READ_ONCE(*validp))
			return;

		srr0 = mfspr(SPRN_HSRR0);
		srr1 = mfspr(SPRN_HSRR1);
		h = "H";

		break;
	default:
		validp = &local_paca->srr_valid;
		if (!READ_ONCE(*validp))
			return;

		srr0 = mfspr(SPRN_SRR0);
		srr1 = mfspr(SPRN_SRR1);
		h = "";
		break;
	}

	if (srr0 == regs->nip && srr1 == regs->msr)
		return;

	/*
	 * A NMI / soft-NMI interrupt may have come in after we found
	 * srr_valid and before the SRRs are loaded. The interrupt then
	 * comes in and clobbers SRRs and clears srr_valid. Then we load
	 * the SRRs here and test them above and find they don't match.
	 *
	 * Test validity again after that, to catch such false positives.
	 *
	 * This test in general will have some window for false negatives
	 * and may not catch and fix all such cases if an NMI comes in
	 * later and clobbers SRRs without clearing srr_valid, but hopefully
	 * such things will get caught most of the time, statistically
	 * enough to be able to get a warning out.
	 */
	if (!READ_ONCE(*validp))
		return;

	if (!data_race(warned)) {
		data_race(warned = true);
		printk("%sSRR0 was: %lx should be: %lx\n", h, srr0, regs->nip);
		printk("%sSRR1 was: %lx should be: %lx\n", h, srr1, regs->msr);
		show_regs(regs);
	}

	WRITE_ONCE(*validp, 0); /* fixup */
#endif
}

static notrace unsigned long
interrupt_exit_user_prepare_main(unsigned long ret, struct pt_regs *regs)
{
	unsigned long ti_flags;

again:
	ti_flags = read_thread_flags();
	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
		local_irq_enable();
		if (ti_flags & _TIF_NEED_RESCHED) {
			schedule();
		} else {
			/*
			 * SIGPENDING must restore signal handler function
			 * argument GPRs, and some non-volatiles (e.g., r1).
			 * Restore all for now. This could be made lighter.
			 */
			if (ti_flags & _TIF_SIGPENDING)
				ret |= _TIF_RESTOREALL;
			do_notify_resume(regs, ti_flags);
		}
		local_irq_disable();
		ti_flags = read_thread_flags();
	}

	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && IS_ENABLED(CONFIG_PPC_FPU)) {
		if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
				unlikely((ti_flags & _TIF_RESTORE_TM))) {
			restore_tm_state(regs);
		} else {
			unsigned long mathflags = MSR_FP;

			if (cpu_has_feature(CPU_FTR_VSX))
				mathflags |= MSR_VEC | MSR_VSX;
			else if (cpu_has_feature(CPU_FTR_ALTIVEC))
				mathflags |= MSR_VEC;

			/*
			 * If userspace MSR has all available FP bits set,
			 * then they are live and no need to restore. If not,
			 * it means the regs were given up and restore_math
			 * may decide to restore them (to avoid taking an FP
			 * fault).
			 */
			if ((regs->msr & mathflags) != mathflags)
				restore_math(regs);
		}
	}

	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;
	}

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
	local_paca->tm_scratch = regs->msr;
#endif

	booke_load_dbcr0();

	account_cpu_user_exit();

	/* Restore user access locks last */
	kuap_user_restore(regs);

	return ret;
}

/*
 * 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;
	unsigned long ret = 0;
	bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv;

	CT_WARN_ON(ct_state() == CONTEXT_USER);

	kuap_assert_locked();

	regs->result = r3;

	/* Check whether the syscall is issued inside a restartable sequence */
	rseq_syscall(regs);

	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)
			ret = _TIF_RESTOREALL;
		else
			regs->gpr[3] = r3;
		clear_bits(_TIF_PERSYSCALL_MASK, &current_thread_info()->flags);
	} else {
		regs->gpr[3] = r3;
	}

	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
		do_syscall_trace_leave(regs);
		ret |= _TIF_RESTOREALL;
	}

	local_irq_disable();
	ret = interrupt_exit_user_prepare_main(ret, regs);

#ifdef CONFIG_PPC64
	regs->exit_result = ret;
#endif

	return ret;
}

#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

	trace_hardirqs_off();
	user_exit_irqoff();
	account_cpu_user_entry();

	BUG_ON(!user_mode(regs));

	regs->exit_result = interrupt_exit_user_prepare_main(regs->exit_result, regs);

	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(arch_irq_disabled_regs(regs));
	CT_WARN_ON(ct_state() == CONTEXT_USER);

	/*
	 * 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();

	ret = interrupt_exit_user_prepare_main(0, regs);

#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() == CONTEXT_USER);

	kuap = kuap_get_and_assert_locked();

	local_irq_disable();

	if (!arch_irq_disabled_regs(regs)) {
		/* Returning to a kernel context with local irqs enabled. */
		WARN_ON_ONCE(!(regs->msr & MSR_EE));
again:
		if (IS_ENABLED(CONFIG_PREEMPT)) {
			/* Return to preemptible kernel context */
			if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) {
				if (preempt_count() == 0)
					preempt_schedule_irq();
			}
		}

		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();
#endif /* CONFIG_PPC64 */
	}

	if (unlikely(stack_store)) {
		clear_bits(_TIF_EMULATE_STACK_STORE, &current_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();
	user_exit_irqoff();
	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