aboutsummaryrefslogtreecommitdiff
path: root/cpu-exec.c
blob: fa08c733daf10effc8929f81fed7c353ad817619 (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
/*
 *  emulator main execution loop
 *
 *  Copyright (c) 2003-2005 Fabrice Bellard
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */
#include "qemu/osdep.h"
#include "cpu.h"
#include "trace.h"
#include "disas/disas.h"
#include "exec/exec-all.h"
#include "tcg.h"
#include "qemu/atomic.h"
#include "sysemu/qtest.h"
#include "qemu/timer.h"
#include "exec/address-spaces.h"
#include "qemu/rcu.h"
#include "exec/tb-hash.h"
#include "exec/log.h"
#if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
#include "hw/i386/apic.h"
#endif
#include "sysemu/replay.h"

/* -icount align implementation. */

typedef struct SyncClocks {
    int64_t diff_clk;
    int64_t last_cpu_icount;
    int64_t realtime_clock;
} SyncClocks;

#if !defined(CONFIG_USER_ONLY)
/* Allow the guest to have a max 3ms advance.
 * The difference between the 2 clocks could therefore
 * oscillate around 0.
 */
#define VM_CLOCK_ADVANCE 3000000
#define THRESHOLD_REDUCE 1.5
#define MAX_DELAY_PRINT_RATE 2000000000LL
#define MAX_NB_PRINTS 100

static void align_clocks(SyncClocks *sc, const CPUState *cpu)
{
    int64_t cpu_icount;

    if (!icount_align_option) {
        return;
    }

    cpu_icount = cpu->icount_extra + cpu->icount_decr.u16.low;
    sc->diff_clk += cpu_icount_to_ns(sc->last_cpu_icount - cpu_icount);
    sc->last_cpu_icount = cpu_icount;

    if (sc->diff_clk > VM_CLOCK_ADVANCE) {
#ifndef _WIN32
        struct timespec sleep_delay, rem_delay;
        sleep_delay.tv_sec = sc->diff_clk / 1000000000LL;
        sleep_delay.tv_nsec = sc->diff_clk % 1000000000LL;
        if (nanosleep(&sleep_delay, &rem_delay) < 0) {
            sc->diff_clk = rem_delay.tv_sec * 1000000000LL + rem_delay.tv_nsec;
        } else {
            sc->diff_clk = 0;
        }
#else
        Sleep(sc->diff_clk / SCALE_MS);
        sc->diff_clk = 0;
#endif
    }
}

static void print_delay(const SyncClocks *sc)
{
    static float threshold_delay;
    static int64_t last_realtime_clock;
    static int nb_prints;

    if (icount_align_option &&
        sc->realtime_clock - last_realtime_clock >= MAX_DELAY_PRINT_RATE &&
        nb_prints < MAX_NB_PRINTS) {
        if ((-sc->diff_clk / (float)1000000000LL > threshold_delay) ||
            (-sc->diff_clk / (float)1000000000LL <
             (threshold_delay - THRESHOLD_REDUCE))) {
            threshold_delay = (-sc->diff_clk / 1000000000LL) + 1;
            printf("Warning: The guest is now late by %.1f to %.1f seconds\n",
                   threshold_delay - 1,
                   threshold_delay);
            nb_prints++;
            last_realtime_clock = sc->realtime_clock;
        }
    }
}

static void init_delay_params(SyncClocks *sc,
                              const CPUState *cpu)
{
    if (!icount_align_option) {
        return;
    }
    sc->realtime_clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
    sc->diff_clk = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - sc->realtime_clock;
    sc->last_cpu_icount = cpu->icount_extra + cpu->icount_decr.u16.low;
    if (sc->diff_clk < max_delay) {
        max_delay = sc->diff_clk;
    }
    if (sc->diff_clk > max_advance) {
        max_advance = sc->diff_clk;
    }

    /* Print every 2s max if the guest is late. We limit the number
       of printed messages to NB_PRINT_MAX(currently 100) */
    print_delay(sc);
}
#else
static void align_clocks(SyncClocks *sc, const CPUState *cpu)
{
}

static void init_delay_params(SyncClocks *sc, const CPUState *cpu)
{
}
#endif /* CONFIG USER ONLY */

/* Execute a TB, and fix up the CPU state afterwards if necessary */
static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
{
    CPUArchState *env = cpu->env_ptr;
    uintptr_t ret;
    TranslationBlock *last_tb;
    int tb_exit;
    uint8_t *tb_ptr = itb->tc_ptr;

    qemu_log_mask_and_addr(CPU_LOG_EXEC, itb->pc,
                           "Trace %p [%d: " TARGET_FMT_lx "] %s\n",
                           itb->tc_ptr, cpu->cpu_index, itb->pc,
                           lookup_symbol(itb->pc));

#if defined(DEBUG_DISAS)
    if (qemu_loglevel_mask(CPU_LOG_TB_CPU)
        && qemu_log_in_addr_range(itb->pc)) {
        qemu_log_lock();
#if defined(TARGET_I386)
        log_cpu_state(cpu, CPU_DUMP_CCOP);
#else
        log_cpu_state(cpu, 0);
#endif
        qemu_log_unlock();
    }
#endif /* DEBUG_DISAS */

    cpu->can_do_io = !use_icount;
    ret = tcg_qemu_tb_exec(env, tb_ptr);
    cpu->can_do_io = 1;
    last_tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
    tb_exit = ret & TB_EXIT_MASK;
    trace_exec_tb_exit(last_tb, tb_exit);

    if (tb_exit > TB_EXIT_IDX1) {
        /* We didn't start executing this TB (eg because the instruction
         * counter hit zero); we must restore the guest PC to the address
         * of the start of the TB.
         */
        CPUClass *cc = CPU_GET_CLASS(cpu);
        qemu_log_mask_and_addr(CPU_LOG_EXEC, last_tb->pc,
                               "Stopped execution of TB chain before %p ["
                               TARGET_FMT_lx "] %s\n",
                               last_tb->tc_ptr, last_tb->pc,
                               lookup_symbol(last_tb->pc));
        if (cc->synchronize_from_tb) {
            cc->synchronize_from_tb(cpu, last_tb);
        } else {
            assert(cc->set_pc);
            cc->set_pc(cpu, last_tb->pc);
        }
    }
    if (tb_exit == TB_EXIT_REQUESTED) {
        /* We were asked to stop executing TBs (probably a pending
         * interrupt. We've now stopped, so clear the flag.
         */
        atomic_set(&cpu->tcg_exit_req, 0);
    }
    return ret;
}

#ifndef CONFIG_USER_ONLY
/* Execute the code without caching the generated code. An interpreter
   could be used if available. */
static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
                             TranslationBlock *orig_tb, bool ignore_icount)
{
    TranslationBlock *tb;

    /* Should never happen.
       We only end up here when an existing TB is too long.  */
    if (max_cycles > CF_COUNT_MASK)
        max_cycles = CF_COUNT_MASK;

    tb_lock();
    tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
                     max_cycles | CF_NOCACHE
                         | (ignore_icount ? CF_IGNORE_ICOUNT : 0));
    tb->orig_tb = orig_tb;
    tb_unlock();

    /* execute the generated code */
    trace_exec_tb_nocache(tb, tb->pc);
    cpu_tb_exec(cpu, tb);

    tb_lock();
    tb_phys_invalidate(tb, -1);
    tb_free(tb);
    tb_unlock();
}
#endif

static void cpu_exec_step(CPUState *cpu)
{
    CPUArchState *env = (CPUArchState *)cpu->env_ptr;
    TranslationBlock *tb;
    target_ulong cs_base, pc;
    uint32_t flags;

    cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
    tb = tb_gen_code(cpu, pc, cs_base, flags,
                     1 | CF_NOCACHE | CF_IGNORE_ICOUNT);
    tb->orig_tb = NULL;
    /* execute the generated code */
    trace_exec_tb_nocache(tb, pc);
    cpu_tb_exec(cpu, tb);
    tb_phys_invalidate(tb, -1);
    tb_free(tb);
}

void cpu_exec_step_atomic(CPUState *cpu)
{
    start_exclusive();

    /* Since we got here, we know that parallel_cpus must be true.  */
    parallel_cpus = false;
    cpu_exec_step(cpu);
    parallel_cpus = true;

    end_exclusive();
}

struct tb_desc {
    target_ulong pc;
    target_ulong cs_base;
    CPUArchState *env;
    tb_page_addr_t phys_page1;
    uint32_t flags;
};

static bool tb_cmp(const void *p, const void *d)
{
    const TranslationBlock *tb = p;
    const struct tb_desc *desc = d;

    if (tb->pc == desc->pc &&
        tb->page_addr[0] == desc->phys_page1 &&
        tb->cs_base == desc->cs_base &&
        tb->flags == desc->flags &&
        !atomic_read(&tb->invalid)) {
        /* check next page if needed */
        if (tb->page_addr[1] == -1) {
            return true;
        } else {
            tb_page_addr_t phys_page2;
            target_ulong virt_page2;

            virt_page2 = (desc->pc & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE;
            phys_page2 = get_page_addr_code(desc->env, virt_page2);
            if (tb->page_addr[1] == phys_page2) {
                return true;
            }
        }
    }
    return false;
}

static TranslationBlock *tb_htable_lookup(CPUState *cpu,
                                          target_ulong pc,
                                          target_ulong cs_base,
                                          uint32_t flags)
{
    tb_page_addr_t phys_pc;
    struct tb_desc desc;
    uint32_t h;

    desc.env = (CPUArchState *)cpu->env_ptr;
    desc.cs_base = cs_base;
    desc.flags = flags;
    desc.pc = pc;
    phys_pc = get_page_addr_code(desc.env, pc);
    desc.phys_page1 = phys_pc & TARGET_PAGE_MASK;
    h = tb_hash_func(phys_pc, pc, flags);
    return qht_lookup(&tcg_ctx.tb_ctx.htable, tb_cmp, &desc, h);
}

static inline TranslationBlock *tb_find(CPUState *cpu,
                                        TranslationBlock *last_tb,
                                        int tb_exit)
{
    CPUArchState *env = (CPUArchState *)cpu->env_ptr;
    TranslationBlock *tb;
    target_ulong cs_base, pc;
    uint32_t flags;
    bool have_tb_lock = false;

    /* we record a subset of the CPU state. It will
       always be the same before a given translated block
       is executed. */
    cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
    tb = atomic_rcu_read(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)]);
    if (unlikely(!tb || tb->pc != pc || tb->cs_base != cs_base ||
                 tb->flags != flags)) {
        tb = tb_htable_lookup(cpu, pc, cs_base, flags);
        if (!tb) {

            /* mmap_lock is needed by tb_gen_code, and mmap_lock must be
             * taken outside tb_lock. As system emulation is currently
             * single threaded the locks are NOPs.
             */
            mmap_lock();
            tb_lock();
            have_tb_lock = true;

            /* There's a chance that our desired tb has been translated while
             * taking the locks so we check again inside the lock.
             */
            tb = tb_htable_lookup(cpu, pc, cs_base, flags);
            if (!tb) {
                /* if no translated code available, then translate it now */
                tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
            }

            mmap_unlock();
        }

        /* We add the TB in the virtual pc hash table for the fast lookup */
        atomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb);
    }
#ifndef CONFIG_USER_ONLY
    /* We don't take care of direct jumps when address mapping changes in
     * system emulation. So it's not safe to make a direct jump to a TB
     * spanning two pages because the mapping for the second page can change.
     */
    if (tb->page_addr[1] != -1) {
        last_tb = NULL;
    }
#endif
    /* See if we can patch the calling TB. */
    if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) {
        if (!have_tb_lock) {
            tb_lock();
            have_tb_lock = true;
        }
        if (!tb->invalid) {
            tb_add_jump(last_tb, tb_exit, tb);
        }
    }
    if (have_tb_lock) {
        tb_unlock();
    }
    return tb;
}

static inline bool cpu_handle_halt(CPUState *cpu)
{
    if (cpu->halted) {
#if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
        if ((cpu->interrupt_request & CPU_INTERRUPT_POLL)
            && replay_interrupt()) {
            X86CPU *x86_cpu = X86_CPU(cpu);
            apic_poll_irq(x86_cpu->apic_state);
            cpu_reset_interrupt(cpu, CPU_INTERRUPT_POLL);
        }
#endif
        if (!cpu_has_work(cpu)) {
            current_cpu = NULL;
            return true;
        }

        cpu->halted = 0;
    }

    return false;
}

static inline void cpu_handle_debug_exception(CPUState *cpu)
{
    CPUClass *cc = CPU_GET_CLASS(cpu);
    CPUWatchpoint *wp;

    if (!cpu->watchpoint_hit) {
        QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
            wp->flags &= ~BP_WATCHPOINT_HIT;
        }
    }

    cc->debug_excp_handler(cpu);
}

static inline bool cpu_handle_exception(CPUState *cpu, int *ret)
{
    if (cpu->exception_index >= 0) {
        if (cpu->exception_index >= EXCP_INTERRUPT) {
            /* exit request from the cpu execution loop */
            *ret = cpu->exception_index;
            if (*ret == EXCP_DEBUG) {
                cpu_handle_debug_exception(cpu);
            }
            cpu->exception_index = -1;
            return true;
        } else {
#if defined(CONFIG_USER_ONLY)
            /* if user mode only, we simulate a fake exception
               which will be handled outside the cpu execution
               loop */
#if defined(TARGET_I386)
            CPUClass *cc = CPU_GET_CLASS(cpu);
            cc->do_interrupt(cpu);
#endif
            *ret = cpu->exception_index;
            cpu->exception_index = -1;
            return true;
#else
            if (replay_exception()) {
                CPUClass *cc = CPU_GET_CLASS(cpu);
                cc->do_interrupt(cpu);
                cpu->exception_index = -1;
            } else if (!replay_has_interrupt()) {
                /* give a chance to iothread in replay mode */
                *ret = EXCP_INTERRUPT;
                return true;
            }
#endif
        }
#ifndef CONFIG_USER_ONLY
    } else if (replay_has_exception()
               && cpu->icount_decr.u16.low + cpu->icount_extra == 0) {
        /* try to cause an exception pending in the log */
        cpu_exec_nocache(cpu, 1, tb_find(cpu, NULL, 0), true);
        *ret = -1;
        return true;
#endif
    }

    return false;
}

static inline void cpu_handle_interrupt(CPUState *cpu,
                                        TranslationBlock **last_tb)
{
    CPUClass *cc = CPU_GET_CLASS(cpu);
    int interrupt_request = cpu->interrupt_request;

    if (unlikely(interrupt_request)) {
        if (unlikely(cpu->singlestep_enabled & SSTEP_NOIRQ)) {
            /* Mask out external interrupts for this step. */
            interrupt_request &= ~CPU_INTERRUPT_SSTEP_MASK;
        }
        if (interrupt_request & CPU_INTERRUPT_DEBUG) {
            cpu->interrupt_request &= ~CPU_INTERRUPT_DEBUG;
            cpu->exception_index = EXCP_DEBUG;
            cpu_loop_exit(cpu);
        }
        if (replay_mode == REPLAY_MODE_PLAY && !replay_has_interrupt()) {
            /* Do nothing */
        } else if (interrupt_request & CPU_INTERRUPT_HALT) {
            replay_interrupt();
            cpu->interrupt_request &= ~CPU_INTERRUPT_HALT;
            cpu->halted = 1;
            cpu->exception_index = EXCP_HLT;
            cpu_loop_exit(cpu);
        }
#if defined(TARGET_I386)
        else if (interrupt_request & CPU_INTERRUPT_INIT) {
            X86CPU *x86_cpu = X86_CPU(cpu);
            CPUArchState *env = &x86_cpu->env;
            replay_interrupt();
            cpu_svm_check_intercept_param(env, SVM_EXIT_INIT, 0);
            do_cpu_init(x86_cpu);
            cpu->exception_index = EXCP_HALTED;
            cpu_loop_exit(cpu);
        }
#else
        else if (interrupt_request & CPU_INTERRUPT_RESET) {
            replay_interrupt();
            cpu_reset(cpu);
            cpu_loop_exit(cpu);
        }
#endif
        /* The target hook has 3 exit conditions:
           False when the interrupt isn't processed,
           True when it is, and we should restart on a new TB,
           and via longjmp via cpu_loop_exit.  */
        else {
            if (cc->cpu_exec_interrupt(cpu, interrupt_request)) {
                replay_interrupt();
                *last_tb = NULL;
            }
            /* The target hook may have updated the 'cpu->interrupt_request';
             * reload the 'interrupt_request' value */
            interrupt_request = cpu->interrupt_request;
        }
        if (interrupt_request & CPU_INTERRUPT_EXITTB) {
            cpu->interrupt_request &= ~CPU_INTERRUPT_EXITTB;
            /* ensure that no TB jump will be modified as
               the program flow was changed */
            *last_tb = NULL;
        }
    }
    if (unlikely(atomic_read(&cpu->exit_request) || replay_has_interrupt())) {
        atomic_set(&cpu->exit_request, 0);
        cpu->exception_index = EXCP_INTERRUPT;
        cpu_loop_exit(cpu);
    }
}

static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
                                    TranslationBlock **last_tb, int *tb_exit,
                                    SyncClocks *sc)
{
    uintptr_t ret;

    if (unlikely(atomic_read(&cpu->exit_request))) {
        return;
    }

    trace_exec_tb(tb, tb->pc);
    ret = cpu_tb_exec(cpu, tb);
    *last_tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
    *tb_exit = ret & TB_EXIT_MASK;
    switch (*tb_exit) {
    case TB_EXIT_REQUESTED:
        /* Something asked us to stop executing
         * chained TBs; just continue round the main
         * loop. Whatever requested the exit will also
         * have set something else (eg exit_request or
         * interrupt_request) which we will handle
         * next time around the loop.  But we need to
         * ensure the tcg_exit_req read in generated code
         * comes before the next read of cpu->exit_request
         * or cpu->interrupt_request.
         */
        smp_rmb();
        *last_tb = NULL;
        break;
    case TB_EXIT_ICOUNT_EXPIRED:
    {
        /* Instruction counter expired.  */
#ifdef CONFIG_USER_ONLY
        abort();
#else
        int insns_left = cpu->icount_decr.u32;
        if (cpu->icount_extra && insns_left >= 0) {
            /* Refill decrementer and continue execution.  */
            cpu->icount_extra += insns_left;
            insns_left = MIN(0xffff, cpu->icount_extra);
            cpu->icount_extra -= insns_left;
            cpu->icount_decr.u16.low = insns_left;
        } else {
            if (insns_left > 0) {
                /* Execute remaining instructions.  */
                cpu_exec_nocache(cpu, insns_left, *last_tb, false);
                align_clocks(sc, cpu);
            }
            cpu->exception_index = EXCP_INTERRUPT;
            *last_tb = NULL;
            cpu_loop_exit(cpu);
        }
        break;
#endif
    }
    default:
        break;
    }
}

/* main execution loop */

int cpu_exec(CPUState *cpu)
{
    CPUClass *cc = CPU_GET_CLASS(cpu);
    int ret;
    SyncClocks sc;

    /* replay_interrupt may need current_cpu */
    current_cpu = cpu;

    if (cpu_handle_halt(cpu)) {
        return EXCP_HALTED;
    }

    atomic_mb_set(&tcg_current_cpu, cpu);
    rcu_read_lock();

    if (unlikely(atomic_mb_read(&exit_request))) {
        cpu->exit_request = 1;
    }

    cc->cpu_exec_enter(cpu);

    /* Calculate difference between guest clock and host clock.
     * This delay includes the delay of the last cycle, so
     * what we have to do is sleep until it is 0. As for the
     * advance/delay we gain here, we try to fix it next time.
     */
    init_delay_params(&sc, cpu);

    for(;;) {
        /* prepare setjmp context for exception handling */
        if (sigsetjmp(cpu->jmp_env, 0) == 0) {
            TranslationBlock *tb, *last_tb = NULL;
            int tb_exit = 0;

            /* if an exception is pending, we execute it here */
            if (cpu_handle_exception(cpu, &ret)) {
                break;
            }

            for(;;) {
                cpu_handle_interrupt(cpu, &last_tb);
                tb = tb_find(cpu, last_tb, tb_exit);
                cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit, &sc);
                /* Try to align the host and virtual clocks
                   if the guest is in advance */
                align_clocks(&sc, cpu);
            } /* for(;;) */
        } else {
#if defined(__clang__) || !QEMU_GNUC_PREREQ(4, 6)
            /* Some compilers wrongly smash all local variables after
             * siglongjmp. There were bug reports for gcc 4.5.0 and clang.
             * Reload essential local variables here for those compilers.
             * Newer versions of gcc would complain about this code (-Wclobbered). */
            cpu = current_cpu;
            cc = CPU_GET_CLASS(cpu);
#else /* buggy compiler */
            /* Assert that the compiler does not smash local variables. */
            g_assert(cpu == current_cpu);
            g_assert(cc == CPU_GET_CLASS(cpu));
#endif /* buggy compiler */
            cpu->can_do_io = 1;
            tb_lock_reset();
        }
    } /* for(;;) */

    cc->cpu_exec_exit(cpu);
    rcu_read_unlock();

    /* fail safe : never use current_cpu outside cpu_exec() */
    current_cpu = NULL;

    /* Does not need atomic_mb_set because a spurious wakeup is okay.  */
    atomic_set(&tcg_current_cpu, NULL);
    return ret;
}