Linux preempt-rt

Check our new training course

Real-Time Linux with PREEMPT_RT

Check our new training course
with Creative Commons CC-BY-SA
lecture and lab materials

Bootlin logo

Elixir Cross Referencer

  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
/*
 *  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 "config.h"
#include "cpu.h"
#include "trace.h"
#include "disas/disas.h"
#include "tcg.h"
#include "qemu/atomic.h"
#include "sysemu/qtest.h"
#include "qemu/timer.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 -= (sleep_delay.tv_sec - rem_delay.tv_sec) * 1000000000LL;
            sc->diff_clk -= sleep_delay.tv_nsec - 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_REALTIME);
    sc->diff_clk = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) -
                   sc->realtime_clock +
                   cpu_get_clock_offset();
    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 */

void cpu_loop_exit(CPUState *cpu)
{
    cpu->current_tb = NULL;
    siglongjmp(cpu->jmp_env, 1);
}

/* exit the current TB from a signal handler. The host registers are
   restored in a state compatible with the CPU emulator
 */
#if defined(CONFIG_SOFTMMU)
void cpu_resume_from_signal(CPUState *cpu, void *puc)
{
    /* XXX: restore cpu registers saved in host registers */

    cpu->exception_index = -1;
    siglongjmp(cpu->jmp_env, 1);
}
#endif

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

#if defined(DEBUG_DISAS)
    if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) {
#if defined(TARGET_I386)
        log_cpu_state(cpu, CPU_DUMP_CCOP);
#elif defined(TARGET_M68K)
        /* ??? Should not modify env state for dumping.  */
        cpu_m68k_flush_flags(env, env->cc_op);
        env->cc_op = CC_OP_FLAGS;
        env->sr = (env->sr & 0xffe0) | env->cc_dest | (env->cc_x << 4);
        log_cpu_state(cpu, 0);
#else
        log_cpu_state(cpu, 0);
#endif
    }
#endif /* DEBUG_DISAS */

    next_tb = tcg_qemu_tb_exec(env, tb_ptr);
    trace_exec_tb_exit((void *) (next_tb & ~TB_EXIT_MASK),
                       next_tb & TB_EXIT_MASK);

    if ((next_tb & TB_EXIT_MASK) > 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);
        TranslationBlock *tb = (TranslationBlock *)(next_tb & ~TB_EXIT_MASK);
        if (cc->synchronize_from_tb) {
            cc->synchronize_from_tb(cpu, tb);
        } else {
            assert(cc->set_pc);
            cc->set_pc(cpu, tb->pc);
        }
    }
    if ((next_tb & TB_EXIT_MASK) == TB_EXIT_REQUESTED) {
        /* We were asked to stop executing TBs (probably a pending
         * interrupt. We've now stopped, so clear the flag.
         */
        cpu->tcg_exit_req = 0;
    }
    return next_tb;
}

/* Execute the code without caching the generated code. An interpreter
   could be used if available. */
static void cpu_exec_nocache(CPUArchState *env, int max_cycles,
                             TranslationBlock *orig_tb)
{
    CPUState *cpu = ENV_GET_CPU(env);
    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 = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
                     max_cycles);
    cpu->current_tb = tb;
    /* execute the generated code */
    trace_exec_tb_nocache(tb, tb->pc);
    cpu_tb_exec(cpu, tb->tc_ptr);
    cpu->current_tb = NULL;
    tb_phys_invalidate(tb, -1);
    tb_free(tb);
}

static TranslationBlock *tb_find_slow(CPUArchState *env,
                                      target_ulong pc,
                                      target_ulong cs_base,
                                      uint64_t flags)
{
    CPUState *cpu = ENV_GET_CPU(env);
    TranslationBlock *tb, **ptb1;
    unsigned int h;
    tb_page_addr_t phys_pc, phys_page1;
    target_ulong virt_page2;

    tcg_ctx.tb_ctx.tb_invalidated_flag = 0;

    /* find translated block using physical mappings */
    phys_pc = get_page_addr_code(env, pc);
    phys_page1 = phys_pc & TARGET_PAGE_MASK;
    h = tb_phys_hash_func(phys_pc);
    ptb1 = &tcg_ctx.tb_ctx.tb_phys_hash[h];
    for(;;) {
        tb = *ptb1;
        if (!tb)
            goto not_found;
        if (tb->pc == pc &&
            tb->page_addr[0] == phys_page1 &&
            tb->cs_base == cs_base &&
            tb->flags == flags) {
            /* check next page if needed */
            if (tb->page_addr[1] != -1) {
                tb_page_addr_t phys_page2;

                virt_page2 = (pc & TARGET_PAGE_MASK) +
                    TARGET_PAGE_SIZE;
                phys_page2 = get_page_addr_code(env, virt_page2);
                if (tb->page_addr[1] == phys_page2)
                    goto found;
            } else {
                goto found;
            }
        }
        ptb1 = &tb->phys_hash_next;
    }
 not_found:
   /* if no translated code available, then translate it now */
    tb = tb_gen_code(cpu, pc, cs_base, flags, 0);

 found:
    /* Move the last found TB to the head of the list */
    if (likely(*ptb1)) {
        *ptb1 = tb->phys_hash_next;
        tb->phys_hash_next = tcg_ctx.tb_ctx.tb_phys_hash[h];
        tcg_ctx.tb_ctx.tb_phys_hash[h] = tb;
    }
    /* we add the TB in the virtual pc hash table */
    cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)] = tb;
    return tb;
}

static inline TranslationBlock *tb_find_fast(CPUArchState *env)
{
    CPUState *cpu = ENV_GET_CPU(env);
    TranslationBlock *tb;
    target_ulong cs_base, pc;
    int flags;

    /* 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 = 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_find_slow(env, pc, cs_base, flags);
    }
    return tb;
}

static void cpu_handle_debug_exception(CPUArchState *env)
{
    CPUState *cpu = ENV_GET_CPU(env);
    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);
}

/* main execution loop */

volatile sig_atomic_t exit_request;

int cpu_exec(CPUArchState *env)
{
    CPUState *cpu = ENV_GET_CPU(env);
    CPUClass *cc = CPU_GET_CLASS(cpu);
#ifdef TARGET_I386
    X86CPU *x86_cpu = X86_CPU(cpu);
#endif
    int ret, interrupt_request;
    TranslationBlock *tb;
    uint8_t *tc_ptr;
    uintptr_t next_tb;
    SyncClocks sc;

    /* This must be volatile so it is not trashed by longjmp() */
    volatile bool have_tb_lock = false;

    if (cpu->halted) {
        if (!cpu_has_work(cpu)) {
            return EXCP_HALTED;
        }

        cpu->halted = 0;
    }

    current_cpu = cpu;

    /* As long as current_cpu is null, up to the assignment just above,
     * requests by other threads to exit the execution loop are expected to
     * be issued using the exit_request global. We must make sure that our
     * evaluation of the global value is performed past the current_cpu
     * value transition point, which requires a memory barrier as well as
     * an instruction scheduling constraint on modern architectures.  */
    smp_mb();

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

    cc->cpu_exec_enter(cpu);
    cpu->exception_index = -1;

    /* 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);

    /* prepare setjmp context for exception handling */
    for(;;) {
        if (sigsetjmp(cpu->jmp_env, 0) == 0) {
            /* if an exception is pending, we execute it here */
            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(env);
                    }
                    break;
                } 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)
                    cc->do_interrupt(cpu);
#endif
                    ret = cpu->exception_index;
                    break;
#else
                    cc->do_interrupt(cpu);
                    cpu->exception_index = -1;
#endif
                }
            }

            next_tb = 0; /* force lookup of first TB */
            for(;;) {
                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 (interrupt_request & CPU_INTERRUPT_HALT) {
                        cpu->interrupt_request &= ~CPU_INTERRUPT_HALT;
                        cpu->halted = 1;
                        cpu->exception_index = EXCP_HLT;
                        cpu_loop_exit(cpu);
                    }
#if defined(TARGET_I386)
                    if (interrupt_request & CPU_INTERRUPT_INIT) {
                        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
                    if (interrupt_request & CPU_INTERRUPT_RESET) {
                        cpu_reset(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.  */
                    if (cc->cpu_exec_interrupt(cpu, interrupt_request)) {
                        next_tb = 0;
                    }
                    /* Don't use the cached interrupt_request value,
                       do_interrupt may have updated the EXITTB flag. */
                    if (cpu->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 */
                        next_tb = 0;
                    }
                }
                if (unlikely(cpu->exit_request)) {
                    cpu->exit_request = 0;
                    cpu->exception_index = EXCP_INTERRUPT;
                    cpu_loop_exit(cpu);
                }
                spin_lock(&tcg_ctx.tb_ctx.tb_lock);
                have_tb_lock = true;
                tb = tb_find_fast(env);
                /* Note: we do it here to avoid a gcc bug on Mac OS X when
                   doing it in tb_find_slow */
                if (tcg_ctx.tb_ctx.tb_invalidated_flag) {
                    /* as some TB could have been invalidated because
                       of memory exceptions while generating the code, we
                       must recompute the hash index here */
                    next_tb = 0;
                    tcg_ctx.tb_ctx.tb_invalidated_flag = 0;
                }
                if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
                    qemu_log("Trace %p [" TARGET_FMT_lx "] %s\n",
                             tb->tc_ptr, tb->pc, lookup_symbol(tb->pc));
                }
                /* see if we can patch the calling TB. When the TB
                   spans two pages, we cannot safely do a direct
                   jump. */
                if (next_tb != 0 && tb->page_addr[1] == -1) {
                    tb_add_jump((TranslationBlock *)(next_tb & ~TB_EXIT_MASK),
                                next_tb & TB_EXIT_MASK, tb);
                }
                have_tb_lock = false;
                spin_unlock(&tcg_ctx.tb_ctx.tb_lock);

                /* cpu_interrupt might be called while translating the
                   TB, but before it is linked into a potentially
                   infinite loop and becomes env->current_tb. Avoid
                   starting execution if there is a pending interrupt. */
                cpu->current_tb = tb;
                barrier();
                if (likely(!cpu->exit_request)) {
                    trace_exec_tb(tb, tb->pc);
                    tc_ptr = tb->tc_ptr;
                    /* execute the generated code */
                    next_tb = cpu_tb_exec(cpu, tc_ptr);
                    switch (next_tb & TB_EXIT_MASK) {
                    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.
                         */
                        tb = (TranslationBlock *)(next_tb & ~TB_EXIT_MASK);
                        next_tb = 0;
                        break;
                    case TB_EXIT_ICOUNT_EXPIRED:
                    {
                        /* Instruction counter expired.  */
                        int insns_left;
                        tb = (TranslationBlock *)(next_tb & ~TB_EXIT_MASK);
                        insns_left = cpu->icount_decr.u32;
                        if (cpu->icount_extra && insns_left >= 0) {
                            /* Refill decrementer and continue execution.  */
                            cpu->icount_extra += insns_left;
                            if (cpu->icount_extra > 0xffff) {
                                insns_left = 0xffff;
                            } else {
                                insns_left = 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(env, insns_left, tb);
                                align_clocks(&sc, cpu);
                            }
                            cpu->exception_index = EXCP_INTERRUPT;
                            next_tb = 0;
                            cpu_loop_exit(cpu);
                        }
                        break;
                    }
                    default:
                        break;
                    }
                }
                cpu->current_tb = NULL;
                /* Try to align the host and virtual clocks
                   if the guest is in advance */
                align_clocks(&sc, cpu);
                /* reset soft MMU for next block (it can currently
                   only be set by a memory fault) */
            } /* for(;;) */
        } else {
            /* Reload env after longjmp - the compiler may have smashed all
             * local variables as longjmp is marked 'noreturn'. */
            cpu = current_cpu;
            env = cpu->env_ptr;
            cc = CPU_GET_CLASS(cpu);
#ifdef TARGET_I386
            x86_cpu = X86_CPU(cpu);
#endif
            if (have_tb_lock) {
                spin_unlock(&tcg_ctx.tb_ctx.tb_lock);
                have_tb_lock = false;
            }
        }
    } /* for(;;) */

    cc->cpu_exec_exit(cpu);

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