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
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
|
/*
* Host code generation
*
* Copyright (c) 2003 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 2.1 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 "trace.h"
#include "disas/disas.h"
#include "exec/exec-all.h"
#include "tcg/tcg.h"
#if defined(CONFIG_USER_ONLY)
#include "qemu.h"
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
#include <sys/param.h>
#if __FreeBSD_version >= 700104
#define HAVE_KINFO_GETVMMAP
#define sigqueue sigqueue_freebsd /* avoid redefinition */
#include <sys/proc.h>
#include <machine/profile.h>
#define _KERNEL
#include <sys/user.h>
#undef _KERNEL
#undef sigqueue
#include <libutil.h>
#endif
#endif
#else
#include "exec/ram_addr.h"
#endif
#include "exec/cputlb.h"
#include "exec/translate-all.h"
#include "exec/translator.h"
#include "exec/tb-flush.h"
#include "qemu/bitmap.h"
#include "qemu/qemu-print.h"
#include "qemu/main-loop.h"
#include "qemu/cacheinfo.h"
#include "qemu/timer.h"
#include "exec/log.h"
#include "sysemu/cpus.h"
#include "sysemu/cpu-timers.h"
#include "sysemu/tcg.h"
#include "qapi/error.h"
#include "hw/core/tcg-cpu-ops.h"
#include "tb-jmp-cache.h"
#include "tb-hash.h"
#include "tb-context.h"
#include "internal-common.h"
#include "internal-target.h"
#include "perf.h"
#include "tcg/insn-start-words.h"
TBContext tb_ctx;
/*
* Encode VAL as a signed leb128 sequence at P.
* Return P incremented past the encoded value.
*/
static uint8_t *encode_sleb128(uint8_t *p, int64_t val)
{
int more, byte;
do {
byte = val & 0x7f;
val >>= 7;
more = !((val == 0 && (byte & 0x40) == 0)
|| (val == -1 && (byte & 0x40) != 0));
if (more) {
byte |= 0x80;
}
*p++ = byte;
} while (more);
return p;
}
/*
* Decode a signed leb128 sequence at *PP; increment *PP past the
* decoded value. Return the decoded value.
*/
static int64_t decode_sleb128(const uint8_t **pp)
{
const uint8_t *p = *pp;
int64_t val = 0;
int byte, shift = 0;
do {
byte = *p++;
val |= (int64_t)(byte & 0x7f) << shift;
shift += 7;
} while (byte & 0x80);
if (shift < TARGET_LONG_BITS && (byte & 0x40)) {
val |= -(int64_t)1 << shift;
}
*pp = p;
return val;
}
/* Encode the data collected about the instructions while compiling TB.
Place the data at BLOCK, and return the number of bytes consumed.
The logical table consists of TARGET_INSN_START_WORDS target_ulong's,
which come from the target's insn_start data, followed by a uintptr_t
which comes from the host pc of the end of the code implementing the insn.
Each line of the table is encoded as sleb128 deltas from the previous
line. The seed for the first line is { tb->pc, 0..., tb->tc.ptr }.
That is, the first column is seeded with the guest pc, the last column
with the host pc, and the middle columns with zeros. */
static int encode_search(TranslationBlock *tb, uint8_t *block)
{
uint8_t *highwater = tcg_ctx->code_gen_highwater;
uint64_t *insn_data = tcg_ctx->gen_insn_data;
uint16_t *insn_end_off = tcg_ctx->gen_insn_end_off;
uint8_t *p = block;
int i, j, n;
for (i = 0, n = tb->icount; i < n; ++i) {
uint64_t prev, curr;
for (j = 0; j < TARGET_INSN_START_WORDS; ++j) {
if (i == 0) {
prev = (!(tb_cflags(tb) & CF_PCREL) && j == 0 ? tb->pc : 0);
} else {
prev = insn_data[(i - 1) * TARGET_INSN_START_WORDS + j];
}
curr = insn_data[i * TARGET_INSN_START_WORDS + j];
p = encode_sleb128(p, curr - prev);
}
prev = (i == 0 ? 0 : insn_end_off[i - 1]);
curr = insn_end_off[i];
p = encode_sleb128(p, curr - prev);
/* Test for (pending) buffer overflow. The assumption is that any
one row beginning below the high water mark cannot overrun
the buffer completely. Thus we can test for overflow after
encoding a row without having to check during encoding. */
if (unlikely(p > highwater)) {
return -1;
}
}
return p - block;
}
static int cpu_unwind_data_from_tb(TranslationBlock *tb, uintptr_t host_pc,
uint64_t *data)
{
uintptr_t iter_pc = (uintptr_t)tb->tc.ptr;
const uint8_t *p = tb->tc.ptr + tb->tc.size;
int i, j, num_insns = tb->icount;
host_pc -= GETPC_ADJ;
if (host_pc < iter_pc) {
return -1;
}
memset(data, 0, sizeof(uint64_t) * TARGET_INSN_START_WORDS);
if (!(tb_cflags(tb) & CF_PCREL)) {
data[0] = tb->pc;
}
/*
* Reconstruct the stored insn data while looking for the point
* at which the end of the insn exceeds host_pc.
*/
for (i = 0; i < num_insns; ++i) {
for (j = 0; j < TARGET_INSN_START_WORDS; ++j) {
data[j] += decode_sleb128(&p);
}
iter_pc += decode_sleb128(&p);
if (iter_pc > host_pc) {
return num_insns - i;
}
}
return -1;
}
/*
* The cpu state corresponding to 'host_pc' is restored in
* preparation for exiting the TB.
*/
void cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
uintptr_t host_pc)
{
uint64_t data[TARGET_INSN_START_WORDS];
int insns_left = cpu_unwind_data_from_tb(tb, host_pc, data);
if (insns_left < 0) {
return;
}
if (tb_cflags(tb) & CF_USE_ICOUNT) {
assert(icount_enabled());
/*
* Reset the cycle counter to the start of the block and
* shift if to the number of actually executed instructions.
*/
cpu->neg.icount_decr.u16.low += insns_left;
}
cpu->cc->tcg_ops->restore_state_to_opc(cpu, tb, data);
}
bool cpu_restore_state(CPUState *cpu, uintptr_t host_pc)
{
/*
* The host_pc has to be in the rx region of the code buffer.
* If it is not we will not be able to resolve it here.
* The two cases where host_pc will not be correct are:
*
* - fault during translation (instruction fetch)
* - fault from helper (not using GETPC() macro)
*
* Either way we need return early as we can't resolve it here.
*/
if (in_code_gen_buffer((const void *)(host_pc - tcg_splitwx_diff))) {
TranslationBlock *tb = tcg_tb_lookup(host_pc);
if (tb) {
cpu_restore_state_from_tb(cpu, tb, host_pc);
return true;
}
}
return false;
}
bool cpu_unwind_state_data(CPUState *cpu, uintptr_t host_pc, uint64_t *data)
{
if (in_code_gen_buffer((const void *)(host_pc - tcg_splitwx_diff))) {
TranslationBlock *tb = tcg_tb_lookup(host_pc);
if (tb) {
return cpu_unwind_data_from_tb(tb, host_pc, data) >= 0;
}
}
return false;
}
void page_init(void)
{
page_size_init();
page_table_config_init();
}
/*
* Isolate the portion of code gen which can setjmp/longjmp.
* Return the size of the generated code, or negative on error.
*/
static int setjmp_gen_code(CPUArchState *env, TranslationBlock *tb,
vaddr pc, void *host_pc,
int *max_insns, int64_t *ti)
{
int ret = sigsetjmp(tcg_ctx->jmp_trans, 0);
if (unlikely(ret != 0)) {
return ret;
}
tcg_func_start(tcg_ctx);
tcg_ctx->cpu = env_cpu(env);
gen_intermediate_code(env_cpu(env), tb, max_insns, pc, host_pc);
assert(tb->size != 0);
tcg_ctx->cpu = NULL;
*max_insns = tb->icount;
return tcg_gen_code(tcg_ctx, tb, pc);
}
/* Called with mmap_lock held for user mode emulation. */
TranslationBlock *tb_gen_code(CPUState *cpu,
vaddr pc, uint64_t cs_base,
uint32_t flags, int cflags)
{
CPUArchState *env = cpu_env(cpu);
TranslationBlock *tb, *existing_tb;
tb_page_addr_t phys_pc, phys_p2;
tcg_insn_unit *gen_code_buf;
int gen_code_size, search_size, max_insns;
int64_t ti;
void *host_pc;
assert_memory_lock();
qemu_thread_jit_write();
phys_pc = get_page_addr_code_hostp(env, pc, &host_pc);
if (phys_pc == -1) {
/* Generate a one-shot TB with 1 insn in it */
cflags = (cflags & ~CF_COUNT_MASK) | CF_LAST_IO | 1;
}
max_insns = cflags & CF_COUNT_MASK;
if (max_insns == 0) {
max_insns = TCG_MAX_INSNS;
}
QEMU_BUILD_BUG_ON(CF_COUNT_MASK + 1 != TCG_MAX_INSNS);
buffer_overflow:
assert_no_pages_locked();
tb = tcg_tb_alloc(tcg_ctx);
if (unlikely(!tb)) {
/* flush must be done */
tb_flush(cpu);
mmap_unlock();
/* Make the execution loop process the flush as soon as possible. */
cpu->exception_index = EXCP_INTERRUPT;
cpu_loop_exit(cpu);
}
gen_code_buf = tcg_ctx->code_gen_ptr;
tb->tc.ptr = tcg_splitwx_to_rx(gen_code_buf);
if (!(cflags & CF_PCREL)) {
tb->pc = pc;
}
tb->cs_base = cs_base;
tb->flags = flags;
tb->cflags = cflags;
tb_set_page_addr0(tb, phys_pc);
tb_set_page_addr1(tb, -1);
if (phys_pc != -1) {
tb_lock_page0(phys_pc);
}
tcg_ctx->gen_tb = tb;
tcg_ctx->addr_type = TARGET_LONG_BITS == 32 ? TCG_TYPE_I32 : TCG_TYPE_I64;
#ifdef CONFIG_SOFTMMU
tcg_ctx->page_bits = TARGET_PAGE_BITS;
tcg_ctx->page_mask = TARGET_PAGE_MASK;
tcg_ctx->tlb_dyn_max_bits = CPU_TLB_DYN_MAX_BITS;
#endif
tcg_ctx->insn_start_words = TARGET_INSN_START_WORDS;
#ifdef TCG_GUEST_DEFAULT_MO
tcg_ctx->guest_mo = TCG_GUEST_DEFAULT_MO;
#else
tcg_ctx->guest_mo = TCG_MO_ALL;
#endif
restart_translate:
trace_translate_block(tb, pc, tb->tc.ptr);
gen_code_size = setjmp_gen_code(env, tb, pc, host_pc, &max_insns, &ti);
if (unlikely(gen_code_size < 0)) {
switch (gen_code_size) {
case -1:
/*
* Overflow of code_gen_buffer, or the current slice of it.
*
* TODO: We don't need to re-do gen_intermediate_code, nor
* should we re-do the tcg optimization currently hidden
* inside tcg_gen_code. All that should be required is to
* flush the TBs, allocate a new TB, re-initialize it per
* above, and re-do the actual code generation.
*/
qemu_log_mask(CPU_LOG_TB_OP | CPU_LOG_TB_OP_OPT,
"Restarting code generation for "
"code_gen_buffer overflow\n");
tb_unlock_pages(tb);
tcg_ctx->gen_tb = NULL;
goto buffer_overflow;
case -2:
/*
* The code generated for the TranslationBlock is too large.
* The maximum size allowed by the unwind info is 64k.
* There may be stricter constraints from relocations
* in the tcg backend.
*
* Try again with half as many insns as we attempted this time.
* If a single insn overflows, there's a bug somewhere...
*/
assert(max_insns > 1);
max_insns /= 2;
qemu_log_mask(CPU_LOG_TB_OP | CPU_LOG_TB_OP_OPT,
"Restarting code generation with "
"smaller translation block (max %d insns)\n",
max_insns);
/*
* The half-sized TB may not cross pages.
* TODO: Fix all targets that cross pages except with
* the first insn, at which point this can't be reached.
*/
phys_p2 = tb_page_addr1(tb);
if (unlikely(phys_p2 != -1)) {
tb_unlock_page1(phys_pc, phys_p2);
tb_set_page_addr1(tb, -1);
}
goto restart_translate;
case -3:
/*
* We had a page lock ordering problem. In order to avoid
* deadlock we had to drop the lock on page0, which means
* that everything we translated so far is compromised.
* Restart with locks held on both pages.
*/
qemu_log_mask(CPU_LOG_TB_OP | CPU_LOG_TB_OP_OPT,
"Restarting code generation with re-locked pages");
goto restart_translate;
default:
g_assert_not_reached();
}
}
tcg_ctx->gen_tb = NULL;
search_size = encode_search(tb, (void *)gen_code_buf + gen_code_size);
if (unlikely(search_size < 0)) {
tb_unlock_pages(tb);
goto buffer_overflow;
}
tb->tc.size = gen_code_size;
/*
* For CF_PCREL, attribute all executions of the generated code
* to its first mapping.
*/
perf_report_code(pc, tb, tcg_splitwx_to_rx(gen_code_buf));
if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM) &&
qemu_log_in_addr_range(pc)) {
FILE *logfile = qemu_log_trylock();
if (logfile) {
int code_size, data_size;
const tcg_target_ulong *rx_data_gen_ptr;
size_t chunk_start;
int insn = 0;
if (tcg_ctx->data_gen_ptr) {
rx_data_gen_ptr = tcg_splitwx_to_rx(tcg_ctx->data_gen_ptr);
code_size = (const void *)rx_data_gen_ptr - tb->tc.ptr;
data_size = gen_code_size - code_size;
} else {
rx_data_gen_ptr = 0;
code_size = gen_code_size;
data_size = 0;
}
/* Dump header and the first instruction */
fprintf(logfile, "OUT: [size=%d]\n", gen_code_size);
fprintf(logfile,
" -- guest addr 0x%016" PRIx64 " + tb prologue\n",
tcg_ctx->gen_insn_data[insn * TARGET_INSN_START_WORDS]);
chunk_start = tcg_ctx->gen_insn_end_off[insn];
disas(logfile, tb->tc.ptr, chunk_start);
/*
* Dump each instruction chunk, wrapping up empty chunks into
* the next instruction. The whole array is offset so the
* first entry is the beginning of the 2nd instruction.
*/
while (insn < tb->icount) {
size_t chunk_end = tcg_ctx->gen_insn_end_off[insn];
if (chunk_end > chunk_start) {
fprintf(logfile, " -- guest addr 0x%016" PRIx64 "\n",
tcg_ctx->gen_insn_data[insn * TARGET_INSN_START_WORDS]);
disas(logfile, tb->tc.ptr + chunk_start,
chunk_end - chunk_start);
chunk_start = chunk_end;
}
insn++;
}
if (chunk_start < code_size) {
fprintf(logfile, " -- tb slow paths + alignment\n");
disas(logfile, tb->tc.ptr + chunk_start,
code_size - chunk_start);
}
/* Finally dump any data we may have after the block */
if (data_size) {
int i;
fprintf(logfile, " data: [size=%d]\n", data_size);
for (i = 0; i < data_size / sizeof(tcg_target_ulong); i++) {
if (sizeof(tcg_target_ulong) == 8) {
fprintf(logfile,
"0x%08" PRIxPTR ": .quad 0x%016" TCG_PRIlx "\n",
(uintptr_t)&rx_data_gen_ptr[i], rx_data_gen_ptr[i]);
} else if (sizeof(tcg_target_ulong) == 4) {
fprintf(logfile,
"0x%08" PRIxPTR ": .long 0x%08" TCG_PRIlx "\n",
(uintptr_t)&rx_data_gen_ptr[i], rx_data_gen_ptr[i]);
} else {
qemu_build_not_reached();
}
}
}
fprintf(logfile, "\n");
qemu_log_unlock(logfile);
}
}
qatomic_set(&tcg_ctx->code_gen_ptr, (void *)
ROUND_UP((uintptr_t)gen_code_buf + gen_code_size + search_size,
CODE_GEN_ALIGN));
/* init jump list */
qemu_spin_init(&tb->jmp_lock);
tb->jmp_list_head = (uintptr_t)NULL;
tb->jmp_list_next[0] = (uintptr_t)NULL;
tb->jmp_list_next[1] = (uintptr_t)NULL;
tb->jmp_dest[0] = (uintptr_t)NULL;
tb->jmp_dest[1] = (uintptr_t)NULL;
/* init original jump addresses which have been set during tcg_gen_code() */
if (tb->jmp_reset_offset[0] != TB_JMP_OFFSET_INVALID) {
tb_reset_jump(tb, 0);
}
if (tb->jmp_reset_offset[1] != TB_JMP_OFFSET_INVALID) {
tb_reset_jump(tb, 1);
}
/*
* If the TB is not associated with a physical RAM page then it must be
* a temporary one-insn TB, and we have nothing left to do. Return early
* before attempting to link to other TBs or add to the lookup table.
*/
if (tb_page_addr0(tb) == -1) {
assert_no_pages_locked();
return tb;
}
/*
* Insert TB into the corresponding region tree before publishing it
* through QHT. Otherwise rewinding happened in the TB might fail to
* lookup itself using host PC.
*/
tcg_tb_insert(tb);
/*
* No explicit memory barrier is required -- tb_link_page() makes the
* TB visible in a consistent state.
*/
existing_tb = tb_link_page(tb);
assert_no_pages_locked();
/* if the TB already exists, discard what we just translated */
if (unlikely(existing_tb != tb)) {
uintptr_t orig_aligned = (uintptr_t)gen_code_buf;
orig_aligned -= ROUND_UP(sizeof(*tb), qemu_icache_linesize);
qatomic_set(&tcg_ctx->code_gen_ptr, (void *)orig_aligned);
tcg_tb_remove(tb);
return existing_tb;
}
return tb;
}
/* user-mode: call with mmap_lock held */
void tb_check_watchpoint(CPUState *cpu, uintptr_t retaddr)
{
TranslationBlock *tb;
assert_memory_lock();
tb = tcg_tb_lookup(retaddr);
if (tb) {
/* We can use retranslation to find the PC. */
cpu_restore_state_from_tb(cpu, tb, retaddr);
tb_phys_invalidate(tb, -1);
} else {
/* The exception probably happened in a helper. The CPU state should
have been saved before calling it. Fetch the PC from there. */
CPUArchState *env = cpu_env(cpu);
vaddr pc;
uint64_t cs_base;
tb_page_addr_t addr;
uint32_t flags;
cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
addr = get_page_addr_code(env, pc);
if (addr != -1) {
tb_invalidate_phys_range(addr, addr);
}
}
}
#ifndef CONFIG_USER_ONLY
/*
* In deterministic execution mode, instructions doing device I/Os
* must be at the end of the TB.
*
* Called by softmmu_template.h, with iothread mutex not held.
*/
void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
{
TranslationBlock *tb;
CPUClass *cc;
uint32_t n;
tb = tcg_tb_lookup(retaddr);
if (!tb) {
cpu_abort(cpu, "cpu_io_recompile: could not find TB for pc=%p",
(void *)retaddr);
}
cpu_restore_state_from_tb(cpu, tb, retaddr);
/*
* Some guests must re-execute the branch when re-executing a delay
* slot instruction. When this is the case, adjust icount and N
* to account for the re-execution of the branch.
*/
n = 1;
cc = CPU_GET_CLASS(cpu);
if (cc->tcg_ops->io_recompile_replay_branch &&
cc->tcg_ops->io_recompile_replay_branch(cpu, tb)) {
cpu->neg.icount_decr.u16.low++;
n = 2;
}
/*
* Exit the loop and potentially generate a new TB executing the
* just the I/O insns. We also limit instrumentation to memory
* operations only (which execute after completion) so we don't
* double instrument the instruction.
*/
cpu->cflags_next_tb = curr_cflags(cpu) | CF_MEMI_ONLY | CF_LAST_IO | n;
if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
vaddr pc = log_pc(cpu, tb);
if (qemu_log_in_addr_range(pc)) {
qemu_log("cpu_io_recompile: rewound execution of TB to %016"
VADDR_PRIx "\n", pc);
}
}
cpu_loop_exit_noexc(cpu);
}
static void print_qht_statistics(struct qht_stats hst, GString *buf)
{
uint32_t hgram_opts;
size_t hgram_bins;
char *hgram;
if (!hst.head_buckets) {
return;
}
g_string_append_printf(buf, "TB hash buckets %zu/%zu "
"(%0.2f%% head buckets used)\n",
hst.used_head_buckets, hst.head_buckets,
(double)hst.used_head_buckets /
hst.head_buckets * 100);
hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
hgram_opts |= QDIST_PR_100X | QDIST_PR_PERCENT;
if (qdist_xmax(&hst.occupancy) - qdist_xmin(&hst.occupancy) == 1) {
hgram_opts |= QDIST_PR_NODECIMAL;
}
hgram = qdist_pr(&hst.occupancy, 10, hgram_opts);
g_string_append_printf(buf, "TB hash occupancy %0.2f%% avg chain occ. "
"Histogram: %s\n",
qdist_avg(&hst.occupancy) * 100, hgram);
g_free(hgram);
hgram_opts = QDIST_PR_BORDER | QDIST_PR_LABELS;
hgram_bins = qdist_xmax(&hst.chain) - qdist_xmin(&hst.chain);
if (hgram_bins > 10) {
hgram_bins = 10;
} else {
hgram_bins = 0;
hgram_opts |= QDIST_PR_NODECIMAL | QDIST_PR_NOBINRANGE;
}
hgram = qdist_pr(&hst.chain, hgram_bins, hgram_opts);
g_string_append_printf(buf, "TB hash avg chain %0.3f buckets. "
"Histogram: %s\n",
qdist_avg(&hst.chain), hgram);
g_free(hgram);
}
struct tb_tree_stats {
size_t nb_tbs;
size_t host_size;
size_t target_size;
size_t max_target_size;
size_t direct_jmp_count;
size_t direct_jmp2_count;
size_t cross_page;
};
static gboolean tb_tree_stats_iter(gpointer key, gpointer value, gpointer data)
{
const TranslationBlock *tb = value;
struct tb_tree_stats *tst = data;
tst->nb_tbs++;
tst->host_size += tb->tc.size;
tst->target_size += tb->size;
if (tb->size > tst->max_target_size) {
tst->max_target_size = tb->size;
}
if (tb_page_addr1(tb) != -1) {
tst->cross_page++;
}
if (tb->jmp_reset_offset[0] != TB_JMP_OFFSET_INVALID) {
tst->direct_jmp_count++;
if (tb->jmp_reset_offset[1] != TB_JMP_OFFSET_INVALID) {
tst->direct_jmp2_count++;
}
}
return false;
}
void dump_exec_info(GString *buf)
{
struct tb_tree_stats tst = {};
struct qht_stats hst;
size_t nb_tbs, flush_full, flush_part, flush_elide;
tcg_tb_foreach(tb_tree_stats_iter, &tst);
nb_tbs = tst.nb_tbs;
/* XXX: avoid using doubles ? */
g_string_append_printf(buf, "Translation buffer state:\n");
/*
* Report total code size including the padding and TB structs;
* otherwise users might think "-accel tcg,tb-size" is not honoured.
* For avg host size we use the precise numbers from tb_tree_stats though.
*/
g_string_append_printf(buf, "gen code size %zu/%zu\n",
tcg_code_size(), tcg_code_capacity());
g_string_append_printf(buf, "TB count %zu\n", nb_tbs);
g_string_append_printf(buf, "TB avg target size %zu max=%zu bytes\n",
nb_tbs ? tst.target_size / nb_tbs : 0,
tst.max_target_size);
g_string_append_printf(buf, "TB avg host size %zu bytes "
"(expansion ratio: %0.1f)\n",
nb_tbs ? tst.host_size / nb_tbs : 0,
tst.target_size ?
(double)tst.host_size / tst.target_size : 0);
g_string_append_printf(buf, "cross page TB count %zu (%zu%%)\n",
tst.cross_page,
nb_tbs ? (tst.cross_page * 100) / nb_tbs : 0);
g_string_append_printf(buf, "direct jump count %zu (%zu%%) "
"(2 jumps=%zu %zu%%)\n",
tst.direct_jmp_count,
nb_tbs ? (tst.direct_jmp_count * 100) / nb_tbs : 0,
tst.direct_jmp2_count,
nb_tbs ? (tst.direct_jmp2_count * 100) / nb_tbs : 0);
qht_statistics_init(&tb_ctx.htable, &hst);
print_qht_statistics(hst, buf);
qht_statistics_destroy(&hst);
g_string_append_printf(buf, "\nStatistics:\n");
g_string_append_printf(buf, "TB flush count %u\n",
qatomic_read(&tb_ctx.tb_flush_count));
g_string_append_printf(buf, "TB invalidate count %u\n",
qatomic_read(&tb_ctx.tb_phys_invalidate_count));
tlb_flush_counts(&flush_full, &flush_part, &flush_elide);
g_string_append_printf(buf, "TLB full flushes %zu\n", flush_full);
g_string_append_printf(buf, "TLB partial flushes %zu\n", flush_part);
g_string_append_printf(buf, "TLB elided flushes %zu\n", flush_elide);
tcg_dump_info(buf);
}
#else /* CONFIG_USER_ONLY */
void cpu_interrupt(CPUState *cpu, int mask)
{
g_assert(qemu_mutex_iothread_locked());
cpu->interrupt_request |= mask;
qatomic_set(&cpu->neg.icount_decr.u16.high, -1);
}
#endif /* CONFIG_USER_ONLY */
/*
* Called by generic code at e.g. cpu reset after cpu creation,
* therefore we must be prepared to allocate the jump cache.
*/
void tcg_flush_jmp_cache(CPUState *cpu)
{
CPUJumpCache *jc = cpu->tb_jmp_cache;
/* During early initialization, the cache may not yet be allocated. */
if (unlikely(jc == NULL)) {
return;
}
for (int i = 0; i < TB_JMP_CACHE_SIZE; i++) {
qatomic_set(&jc->array[i].tb, NULL);
}
}
/* This is a wrapper for common code that can not use CONFIG_SOFTMMU */
void tcg_flush_softmmu_tlb(CPUState *cs)
{
#ifdef CONFIG_SOFTMMU
tlb_flush(cs);
#endif
}
|