aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/entry/common.c
blob: b0b1c3cf0e6e5ca2b05d4e810a849a8c4a9aa790 (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
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
// SPDX-License-Identifier: GPL-2.0-only
/*
 * common.c - C code for kernel entry and exit
 * Copyright (c) 2015 Andrew Lutomirski
 *
 * Based on asm and ptrace code by many authors.  The code here originated
 * in ptrace.c and signal.c.
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>
#include <linux/export.h>
#include <linux/context_tracking.h>
#include <linux/user-return-notifier.h>
#include <linux/nospec.h>
#include <linux/uprobes.h>
#include <linux/livepatch.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>

#ifdef CONFIG_XEN_PV
#include <xen/xen-ops.h>
#include <xen/events.h>
#endif

#include <asm/desc.h>
#include <asm/traps.h>
#include <asm/vdso.h>
#include <asm/cpufeature.h>
#include <asm/fpu/api.h>
#include <asm/nospec-branch.h>
#include <asm/io_bitmap.h>
#include <asm/syscall.h>
#include <asm/irq_stack.h>

#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>

#ifdef CONFIG_CONTEXT_TRACKING
/**
 * enter_from_user_mode - Establish state when coming from user mode
 *
 * Syscall 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 noinstr void enter_from_user_mode(void)
{
	enum ctx_state state = ct_state();

	lockdep_hardirqs_off(CALLER_ADDR0);
	user_exit_irqoff();

	instrumentation_begin();
	CT_WARN_ON(state != CONTEXT_USER);
	trace_hardirqs_off_prepare();
	instrumentation_end();
}
#else
static __always_inline void enter_from_user_mode(void)
{
	lockdep_hardirqs_off(CALLER_ADDR0);
	instrumentation_begin();
	trace_hardirqs_off_prepare();
	instrumentation_end();
}
#endif

/**
 * exit_to_user_mode - Fixup state when exiting to user mode
 *
 * Syscall 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) Clear CPU buffers if CPU is affected by MDS and the migitation is on.
 * 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();
	mds_user_clear_cpu_buffers();
	lockdep_hardirqs_on(CALLER_ADDR0);
}

static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
{
#ifdef CONFIG_X86_64
	if (arch == AUDIT_ARCH_X86_64) {
		audit_syscall_entry(regs->orig_ax, regs->di,
				    regs->si, regs->dx, regs->r10);
	} else
#endif
	{
		audit_syscall_entry(regs->orig_ax, regs->bx,
				    regs->cx, regs->dx, regs->si);
	}
}

/*
 * Returns the syscall nr to run (which should match regs->orig_ax) or -1
 * to skip the syscall.
 */
static long syscall_trace_enter(struct pt_regs *regs)
{
	u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;

	struct thread_info *ti = current_thread_info();
	unsigned long ret = 0;
	u32 work;

	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
		BUG_ON(regs != task_pt_regs(current));

	work = READ_ONCE(ti->flags);

	if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
		ret = tracehook_report_syscall_entry(regs);
		if (ret || (work & _TIF_SYSCALL_EMU))
			return -1L;
	}

#ifdef CONFIG_SECCOMP
	/*
	 * Do seccomp after ptrace, to catch any tracer changes.
	 */
	if (work & _TIF_SECCOMP) {
		struct seccomp_data sd;

		sd.arch = arch;
		sd.nr = regs->orig_ax;
		sd.instruction_pointer = regs->ip;
#ifdef CONFIG_X86_64
		if (arch == AUDIT_ARCH_X86_64) {
			sd.args[0] = regs->di;
			sd.args[1] = regs->si;
			sd.args[2] = regs->dx;
			sd.args[3] = regs->r10;
			sd.args[4] = regs->r8;
			sd.args[5] = regs->r9;
		} else
#endif
		{
			sd.args[0] = regs->bx;
			sd.args[1] = regs->cx;
			sd.args[2] = regs->dx;
			sd.args[3] = regs->si;
			sd.args[4] = regs->di;
			sd.args[5] = regs->bp;
		}

		ret = __secure_computing(&sd);
		if (ret == -1)
			return ret;
	}
#endif

	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
		trace_sys_enter(regs, regs->orig_ax);

	do_audit_syscall_entry(regs, arch);

	return ret ?: regs->orig_ax;
}

#define EXIT_TO_USERMODE_LOOP_FLAGS				\
	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)

static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
{
	/*
	 * In order to return to user mode, we need to have IRQs off with
	 * none of EXIT_TO_USERMODE_LOOP_FLAGS set.  Several of these flags
	 * can be set at any time on preemptible kernels if we have IRQs on,
	 * so we need to loop.  Disabling preemption wouldn't help: doing the
	 * work to clear some of the flags can sleep.
	 */
	while (true) {
		/* We have work to do. */
		local_irq_enable();

		if (cached_flags & _TIF_NEED_RESCHED)
			schedule();

		if (cached_flags & _TIF_UPROBE)
			uprobe_notify_resume(regs);

		if (cached_flags & _TIF_PATCH_PENDING)
			klp_update_patch_state(current);

		/* deal with pending signal delivery */
		if (cached_flags & _TIF_SIGPENDING)
			do_signal(regs);

		if (cached_flags & _TIF_NOTIFY_RESUME) {
			clear_thread_flag(TIF_NOTIFY_RESUME);
			tracehook_notify_resume(regs);
			rseq_handle_notify_resume(NULL, regs);
		}

		if (cached_flags & _TIF_USER_RETURN_NOTIFY)
			fire_user_return_notifiers();

		/* Disable IRQs and retry */
		local_irq_disable();

		cached_flags = READ_ONCE(current_thread_info()->flags);

		if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
			break;
	}
}

static void __prepare_exit_to_usermode(struct pt_regs *regs)
{
	struct thread_info *ti = current_thread_info();
	u32 cached_flags;

	addr_limit_user_check();

	lockdep_assert_irqs_disabled();
	lockdep_sys_exit();

	cached_flags = READ_ONCE(ti->flags);

	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
		exit_to_usermode_loop(regs, cached_flags);

	/* Reload ti->flags; we may have rescheduled above. */
	cached_flags = READ_ONCE(ti->flags);

	if (unlikely(cached_flags & _TIF_IO_BITMAP))
		tss_update_io_bitmap();

	fpregs_assert_state_consistent();
	if (unlikely(cached_flags & _TIF_NEED_FPU_LOAD))
		switch_fpu_return();

#ifdef CONFIG_COMPAT
	/*
	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
	 * returning to user mode.  We need to clear it *after* signal
	 * handling, because syscall restart has a fixup for compat
	 * syscalls.  The fixup is exercised by the ptrace_syscall_32
	 * selftest.
	 *
	 * We also need to clear TS_REGS_POKED_I386: the 32-bit tracer
	 * special case only applies after poking regs and before the
	 * very next return to user mode.
	 */
	ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
#endif
}

__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
{
	instrumentation_begin();
	__prepare_exit_to_usermode(regs);
	instrumentation_end();
	exit_to_user_mode();
}

#define SYSCALL_EXIT_WORK_FLAGS				\
	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |	\
	 _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)

static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags)
{
	bool step;

	audit_syscall_exit(regs);

	if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
		trace_sys_exit(regs, regs->ax);

	/*
	 * If TIF_SYSCALL_EMU is set, we only get here because of
	 * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
	 * We already reported this syscall instruction in
	 * syscall_trace_enter().
	 */
	step = unlikely(
		(cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
		== _TIF_SINGLESTEP);
	if (step || cached_flags & _TIF_SYSCALL_TRACE)
		tracehook_report_syscall_exit(regs, step);
}

static void __syscall_return_slowpath(struct pt_regs *regs)
{
	struct thread_info *ti = current_thread_info();
	u32 cached_flags = READ_ONCE(ti->flags);

	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);

	if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
	    WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax))
		local_irq_enable();

	rseq_syscall(regs);

	/*
	 * First do one-time work.  If these work items are enabled, we
	 * want to run them exactly once per syscall exit with IRQs on.
	 */
	if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
		syscall_slow_exit_work(regs, cached_flags);

	local_irq_disable();
	__prepare_exit_to_usermode(regs);
}

/*
 * Called with IRQs on and fully valid regs.  Returns with IRQs off in a
 * state such that we can immediately switch to user mode.
 */
__visible noinstr void syscall_return_slowpath(struct pt_regs *regs)
{
	instrumentation_begin();
	__syscall_return_slowpath(regs);
	instrumentation_end();
	exit_to_user_mode();
}

#ifdef CONFIG_X86_64
__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
{
	struct thread_info *ti;

	enter_from_user_mode();
	instrumentation_begin();

	local_irq_enable();
	ti = current_thread_info();
	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
		nr = syscall_trace_enter(regs);

	if (likely(nr < NR_syscalls)) {
		nr = array_index_nospec(nr, NR_syscalls);
		regs->ax = sys_call_table[nr](regs);
#ifdef CONFIG_X86_X32_ABI
	} else if (likely((nr & __X32_SYSCALL_BIT) &&
			  (nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) {
		nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT,
					X32_NR_syscalls);
		regs->ax = x32_sys_call_table[nr](regs);
#endif
	}
	__syscall_return_slowpath(regs);

	instrumentation_end();
	exit_to_user_mode();
}
#endif

#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
/*
 * Does a 32-bit syscall.  Called with IRQs on in CONTEXT_KERNEL.  Does
 * all entry and exit work and returns with IRQs off.  This function is
 * extremely hot in workloads that use it, and it's usually called from
 * do_fast_syscall_32, so forcibly inline it to improve performance.
 */
static void do_syscall_32_irqs_on(struct pt_regs *regs)
{
	struct thread_info *ti = current_thread_info();
	unsigned int nr = (unsigned int)regs->orig_ax;

#ifdef CONFIG_IA32_EMULATION
	ti->status |= TS_COMPAT;
#endif

	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) {
		/*
		 * Subtlety here: if ptrace pokes something larger than
		 * 2^32-1 into orig_ax, this truncates it.  This may or
		 * may not be necessary, but it matches the old asm
		 * behavior.
		 */
		nr = syscall_trace_enter(regs);
	}

	if (likely(nr < IA32_NR_syscalls)) {
		nr = array_index_nospec(nr, IA32_NR_syscalls);
		regs->ax = ia32_sys_call_table[nr](regs);
	}

	__syscall_return_slowpath(regs);
}

/* Handles int $0x80 */
__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
{
	enter_from_user_mode();
	instrumentation_begin();

	local_irq_enable();
	do_syscall_32_irqs_on(regs);

	instrumentation_end();
	exit_to_user_mode();
}

static bool __do_fast_syscall_32(struct pt_regs *regs)
{
	int res;

	/* Fetch EBP from where the vDSO stashed it. */
	if (IS_ENABLED(CONFIG_X86_64)) {
		/*
		 * Micro-optimization: the pointer we're following is
		 * explicitly 32 bits, so it can't be out of range.
		 */
		res = __get_user(*(u32 *)&regs->bp,
			 (u32 __user __force *)(unsigned long)(u32)regs->sp);
	} else {
		res = get_user(*(u32 *)&regs->bp,
		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
	}

	if (res) {
		/* User code screwed up. */
		regs->ax = -EFAULT;
		local_irq_disable();
		__prepare_exit_to_usermode(regs);
		return false;
	}

	/* Now this is just like a normal syscall. */
	do_syscall_32_irqs_on(regs);
	return true;
}

/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
__visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
{
	/*
	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
	 * convention.  Adjust regs so it looks like we entered using int80.
	 */
	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
					vdso_image_32.sym_int80_landing_pad;
	bool success;

	/*
	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
	 * Fix it up.
	 */
	regs->ip = landing_pad;

	enter_from_user_mode();
	instrumentation_begin();

	local_irq_enable();
	success = __do_fast_syscall_32(regs);

	instrumentation_end();
	exit_to_user_mode();

	/* If it failed, keep it simple: use IRET. */
	if (!success)
		return 0;

#ifdef CONFIG_X86_64
	/*
	 * Opportunistic SYSRETL: if possible, try to return using SYSRETL.
	 * SYSRETL is available on all 64-bit CPUs, so we don't need to
	 * bother with SYSEXIT.
	 *
	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
	 * because the ECX fixup above will ensure that this is essentially
	 * never the case.
	 */
	return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
		regs->ip == landing_pad &&
		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
#else
	/*
	 * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT.
	 *
	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
	 * because the ECX fixup above will ensure that this is essentially
	 * never the case.
	 *
	 * We don't allow syscalls at all from VM86 mode, but we still
	 * need to check VM, because we might be returning from sys_vm86.
	 */
	return static_cpu_has(X86_FEATURE_SEP) &&
		regs->cs == __USER_CS && regs->ss == __USER_DS &&
		regs->ip == landing_pad &&
		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
#endif
}
#endif

SYSCALL_DEFINE0(ni_syscall)
{
	return -ENOSYS;
}

/**
 * idtentry_enter_cond_rcu - Handle state tracking on idtentry with conditional
 *			     RCU handling
 * @regs:	Pointer to pt_regs of interrupted context
 *
 * Invokes:
 *  - lockdep irqflag state tracking as low level ASM entry disabled
 *    interrupts.
 *
 *  - Context tracking if the exception hit user mode.
 *
 *  - The hardirq tracer to keep the state consistent as low level ASM
 *    entry disabled interrupts.
 *
 * For kernel mode entries RCU handling is done conditional. If RCU is
 * watching then the only RCU requirement is to check whether the tick has
 * to be restarted. If RCU is not watching then rcu_irq_enter() has to be
 * invoked on entry and rcu_irq_exit() on exit.
 *
 * Avoiding the rcu_irq_enter/exit() calls is an optimization but also
 * solves the problem of kernel mode pagefaults which can schedule, which
 * is not possible after invoking rcu_irq_enter() without undoing it.
 *
 * For user mode entries enter_from_user_mode() must be invoked to
 * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
 * would not be possible.
 *
 * Returns: True if RCU has been adjusted on a kernel entry
 *	    False otherwise
 *
 * The return value must be fed into the rcu_exit argument of
 * idtentry_exit_cond_rcu().
 */
bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
{
	if (user_mode(regs)) {
		enter_from_user_mode();
		return false;
	}

	if (!__rcu_is_watching()) {
		/*
		 * If RCU is not watching then the same careful
		 * sequence vs. lockdep and tracing is required
		 * as in enter_from_user_mode().
		 *
		 * This only happens for IRQs that hit the idle
		 * loop, i.e. if idle is not using MWAIT.
		 */
		lockdep_hardirqs_off(CALLER_ADDR0);
		rcu_irq_enter();
		instrumentation_begin();
		trace_hardirqs_off_prepare();
		instrumentation_end();

		return true;
	}

	/*
	 * If RCU is watching then RCU only wants to check
	 * whether it needs to restart the tick in NOHZ
	 * mode.
	 */
	instrumentation_begin();
	rcu_irq_enter_check_tick();
	/* Use the combo lockdep/tracing function */
	trace_hardirqs_off();
	instrumentation_end();

	return false;
}

static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
{
	if (may_sched && !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();
	}
	/* Covers both tracing and lockdep */
	trace_hardirqs_on();
}

/**
 * idtentry_exit_cond_rcu - Handle return from exception with conditional RCU
 *			    handling
 * @regs:	Pointer to pt_regs (exception entry regs)
 * @rcu_exit:	Invoke rcu_irq_exit() if true
 *
 * Depending on the return target (kernel/user) this runs the necessary
 * preemption and work checks if possible and reguired and returns to
 * the caller with interrupts disabled and no further work pending.
 *
 * This is the last action before returning to the low level ASM code which
 * just needs to return to the appropriate context.
 *
 * Counterpart to idtentry_enter_cond_rcu(). The return value of the entry
 * function must be fed into the @rcu_exit argument.
 */
void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
{
	lockdep_assert_irqs_disabled();

	/* Check whether this returns to user mode */
	if (user_mode(regs)) {
		prepare_exit_to_usermode(regs);
	} else if (regs->flags & X86_EFLAGS_IF) {
		/*
		 * 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 (rcu_exit) {
			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();
		idtentry_exit_cond_resched(regs, IS_ENABLED(CONFIG_PREEMPTION));
		instrumentation_end();
	} else {
		/*
		 * IRQ flags state is correct already. Just tell RCU if it
		 * was not watching on entry.
		 */
		if (rcu_exit)
			rcu_irq_exit();
	}
}

/**
 * idtentry_enter_user - Handle state tracking on idtentry from user mode
 * @regs:	Pointer to pt_regs of interrupted context
 *
 * Invokes enter_from_user_mode() to establish the proper context for
 * NOHZ_FULL. Otherwise scheduling on exit would not be possible.
 */
void noinstr idtentry_enter_user(struct pt_regs *regs)
{
	enter_from_user_mode();
}

/**
 * idtentry_exit_user - Handle return from exception to user mode
 * @regs:	Pointer to pt_regs (exception entry regs)
 *
 * Runs the necessary preemption and work checks and returns to the caller
 * with interrupts disabled and no further work pending.
 *
 * This is the last action before returning to the low level ASM code which
 * just needs to return to the appropriate context.
 *
 * Counterpart to idtentry_enter_user().
 */
void noinstr idtentry_exit_user(struct pt_regs *regs)
{
	lockdep_assert_irqs_disabled();

	prepare_exit_to_usermode(regs);
}

#ifdef CONFIG_XEN_PV
#ifndef CONFIG_PREEMPTION
/*
 * Some hypercalls issued by the toolstack can take many 10s of
 * seconds. Allow tasks running hypercalls via the privcmd driver to
 * be voluntarily preempted even if full kernel preemption is
 * disabled.
 *
 * Such preemptible hypercalls are bracketed by
 * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
 * calls.
 */
DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);

/*
 * In case of scheduling the flag must be cleared and restored after
 * returning from schedule as the task might move to a different CPU.
 */
static __always_inline bool get_and_clear_inhcall(void)
{
	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);

	__this_cpu_write(xen_in_preemptible_hcall, false);
	return inhcall;
}

static __always_inline void restore_inhcall(bool inhcall)
{
	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
}
#else
static __always_inline bool get_and_clear_inhcall(void) { return false; }
static __always_inline void restore_inhcall(bool inhcall) { }
#endif

static void __xen_pv_evtchn_do_upcall(void)
{
	irq_enter_rcu();
	inc_irq_stat(irq_hv_callback_count);

	xen_hvm_evtchn_do_upcall();

	irq_exit_rcu();
}

__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
{
	struct pt_regs *old_regs;
	bool inhcall, rcu_exit;

	rcu_exit = idtentry_enter_cond_rcu(regs);
	old_regs = set_irq_regs(regs);

	instrumentation_begin();
	run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, NULL, regs);
	instrumentation_begin();

	set_irq_regs(old_regs);

	inhcall = get_and_clear_inhcall();
	if (inhcall && !WARN_ON_ONCE(rcu_exit)) {
		instrumentation_begin();
		idtentry_exit_cond_resched(regs, true);
		instrumentation_end();
		restore_inhcall(inhcall);
	} else {
		idtentry_exit_cond_rcu(regs, rcu_exit);
	}
}
#endif /* CONFIG_XEN_PV */

Privacy Policy