summaryrefslogtreecommitdiff
path: root/util/qht.c
blob: aa51be3c52f891dc55990231ba959a9c585b5b77 (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
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
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
/*
 * qht.c - QEMU Hash Table, designed to scale for read-mostly workloads.
 *
 * Copyright (C) 2016, Emilio G. Cota <cota@braap.org>
 *
 * License: GNU GPL, version 2 or later.
 *   See the COPYING file in the top-level directory.
 *
 * Assumptions:
 * - NULL cannot be inserted/removed as a pointer value.
 * - Trying to insert an already-existing hash-pointer pair is OK. However,
 *   it is not OK to insert into the same hash table different hash-pointer
 *   pairs that have the same pointer value, but not the hashes.
 * - Lookups are performed under an RCU read-critical section; removals
 *   must wait for a grace period to elapse before freeing removed objects.
 *
 * Features:
 * - Reads (i.e. lookups and iterators) can be concurrent with other reads.
 *   Lookups that are concurrent with writes to the same bucket will retry
 *   via a seqlock; iterators acquire all bucket locks and therefore can be
 *   concurrent with lookups and are serialized wrt writers.
 * - Writes (i.e. insertions/removals) can be concurrent with writes to
 *   different buckets; writes to the same bucket are serialized through a lock.
 * - Optional auto-resizing: the hash table resizes up if the load surpasses
 *   a certain threshold. Resizing is done concurrently with readers; writes
 *   are serialized with the resize operation.
 *
 * The key structure is the bucket, which is cacheline-sized. Buckets
 * contain a few hash values and pointers; the u32 hash values are stored in
 * full so that resizing is fast. Having this structure instead of directly
 * chaining items has two advantages:
 * - Failed lookups fail fast, and touch a minimum number of cache lines.
 * - Resizing the hash table with concurrent lookups is easy.
 *
 * There are two types of buckets:
 * 1. "head" buckets are the ones allocated in the array of buckets in qht_map.
 * 2. all "non-head" buckets (i.e. all others) are members of a chain that
 *    starts from a head bucket.
 * Note that the seqlock and spinlock of a head bucket applies to all buckets
 * chained to it; these two fields are unused in non-head buckets.
 *
 * On removals, we move the last valid item in the chain to the position of the
 * just-removed entry. This makes lookups slightly faster, since the moment an
 * invalid entry is found, the (failed) lookup is over.
 *
 * Resizing is done by taking all bucket spinlocks (so that no other writers can
 * race with us) and then copying all entries into a new hash map. Then, the
 * ht->map pointer is set, and the old map is freed once no RCU readers can see
 * it anymore.
 *
 * Writers check for concurrent resizes by comparing ht->map before and after
 * acquiring their bucket lock. If they don't match, a resize has occured
 * while the bucket spinlock was being acquired.
 *
 * Related Work:
 * - Idea of cacheline-sized buckets with full hashes taken from:
 *   David, Guerraoui & Trigonakis, "Asynchronized Concurrency:
 *   The Secret to Scaling Concurrent Search Data Structures", ASPLOS'15.
 * - Why not RCU-based hash tables? They would allow us to get rid of the
 *   seqlock, but resizing would take forever since RCU read critical
 *   sections in QEMU take quite a long time.
 *   More info on relativistic hash tables:
 *   + Triplett, McKenney & Walpole, "Resizable, Scalable, Concurrent Hash
 *     Tables via Relativistic Programming", USENIX ATC'11.
 *   + Corbet, "Relativistic hash tables, part 1: Algorithms", @ lwn.net, 2014.
 *     https://lwn.net/Articles/612021/
 */
#include "qemu/osdep.h"
#include "qemu/qht.h"
#include "qemu/atomic.h"
#include "qemu/rcu.h"

//#define QHT_DEBUG

/*
 * We want to avoid false sharing of cache lines. Most systems have 64-byte
 * cache lines so we go with it for simplicity.
 *
 * Note that systems with smaller cache lines will be fine (the struct is
 * almost 64-bytes); systems with larger cache lines might suffer from
 * some false sharing.
 */
#define QHT_BUCKET_ALIGN 64

/* define these to keep sizeof(qht_bucket) within QHT_BUCKET_ALIGN */
#if HOST_LONG_BITS == 32
#define QHT_BUCKET_ENTRIES 6
#else /* 64-bit */
#define QHT_BUCKET_ENTRIES 4
#endif

enum qht_iter_type {
    QHT_ITER_VOID,    /* do nothing; use retvoid */
    QHT_ITER_RM,      /* remove element if retbool returns true */
};

struct qht_iter {
    union {
        qht_iter_func_t retvoid;
        qht_iter_bool_func_t retbool;
    } f;
    enum qht_iter_type type;
};

/*
 * Do _not_ use qemu_mutex_[try]lock directly! Use these macros, otherwise
 * the profiler (QSP) will deadlock.
 */
static inline void qht_lock(struct qht *ht)
{
    if (ht->mode & QHT_MODE_RAW_MUTEXES) {
        qemu_mutex_lock__raw(&ht->lock);
    } else {
        qemu_mutex_lock(&ht->lock);
    }
}

static inline int qht_trylock(struct qht *ht)
{
    if (ht->mode & QHT_MODE_RAW_MUTEXES) {
        return qemu_mutex_trylock__raw(&(ht)->lock);
    }
    return qemu_mutex_trylock(&(ht)->lock);
}

/* this inline is not really necessary, but it helps keep code consistent */
static inline void qht_unlock(struct qht *ht)
{
    qemu_mutex_unlock(&ht->lock);
}

/*
 * Note: reading partially-updated pointers in @pointers could lead to
 * segfaults. We thus access them with atomic_read/set; this guarantees
 * that the compiler makes all those accesses atomic. We also need the
 * volatile-like behavior in atomic_read, since otherwise the compiler
 * might refetch the pointer.
 * atomic_read's are of course not necessary when the bucket lock is held.
 *
 * If both ht->lock and b->lock are grabbed, ht->lock should always
 * be grabbed first.
 */
struct qht_bucket {
    QemuSpin lock;
    QemuSeqLock sequence;
    uint32_t hashes[QHT_BUCKET_ENTRIES];
    void *pointers[QHT_BUCKET_ENTRIES];
    struct qht_bucket *next;
} QEMU_ALIGNED(QHT_BUCKET_ALIGN);

QEMU_BUILD_BUG_ON(sizeof(struct qht_bucket) > QHT_BUCKET_ALIGN);

/**
 * struct qht_map - structure to track an array of buckets
 * @rcu: used by RCU. Keep it as the top field in the struct to help valgrind
 *       find the whole struct.
 * @buckets: array of head buckets. It is constant once the map is created.
 * @n_buckets: number of head buckets. It is constant once the map is created.
 * @n_added_buckets: number of added (i.e. "non-head") buckets
 * @n_added_buckets_threshold: threshold to trigger an upward resize once the
 *                             number of added buckets surpasses it.
 *
 * Buckets are tracked in what we call a "map", i.e. this structure.
 */
struct qht_map {
    struct rcu_head rcu;
    struct qht_bucket *buckets;
    size_t n_buckets;
    size_t n_added_buckets;
    size_t n_added_buckets_threshold;
};

/* trigger a resize when n_added_buckets > n_buckets / div */
#define QHT_NR_ADDED_BUCKETS_THRESHOLD_DIV 8

static void qht_do_resize_reset(struct qht *ht, struct qht_map *new,
                                bool reset);
static void qht_grow_maybe(struct qht *ht);

#ifdef QHT_DEBUG

#define qht_debug_assert(X) do { assert(X); } while (0)

static void qht_bucket_debug__locked(struct qht_bucket *b)
{
    bool seen_empty = false;
    bool corrupt = false;
    int i;

    do {
        for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
            if (b->pointers[i] == NULL) {
                seen_empty = true;
                continue;
            }
            if (seen_empty) {
                fprintf(stderr, "%s: b: %p, pos: %i, hash: 0x%x, p: %p\n",
                        __func__, b, i, b->hashes[i], b->pointers[i]);
                corrupt = true;
            }
        }
        b = b->next;
    } while (b);
    qht_debug_assert(!corrupt);
}

static void qht_map_debug__all_locked(struct qht_map *map)
{
    int i;

    for (i = 0; i < map->n_buckets; i++) {
        qht_bucket_debug__locked(&map->buckets[i]);
    }
}
#else

#define qht_debug_assert(X) do { (void)(X); } while (0)

static inline void qht_bucket_debug__locked(struct qht_bucket *b)
{ }

static inline void qht_map_debug__all_locked(struct qht_map *map)
{ }
#endif /* QHT_DEBUG */

static inline size_t qht_elems_to_buckets(size_t n_elems)
{
    return pow2ceil(n_elems / QHT_BUCKET_ENTRIES);
}

static inline void qht_head_init(struct qht_bucket *b)
{
    memset(b, 0, sizeof(*b));
    qemu_spin_init(&b->lock);
    seqlock_init(&b->sequence);
}

static inline
struct qht_bucket *qht_map_to_bucket(const struct qht_map *map, uint32_t hash)
{
    return &map->buckets[hash & (map->n_buckets - 1)];
}

/* acquire all bucket locks from a map */
static void qht_map_lock_buckets(struct qht_map *map)
{
    size_t i;

    for (i = 0; i < map->n_buckets; i++) {
        struct qht_bucket *b = &map->buckets[i];

        qemu_spin_lock(&b->lock);
    }
}

static void qht_map_unlock_buckets(struct qht_map *map)
{
    size_t i;

    for (i = 0; i < map->n_buckets; i++) {
        struct qht_bucket *b = &map->buckets[i];

        qemu_spin_unlock(&b->lock);
    }
}

/*
 * Call with at least a bucket lock held.
 * @map should be the value read before acquiring the lock (or locks).
 */
static inline bool qht_map_is_stale__locked(const struct qht *ht,
                                            const struct qht_map *map)
{
    return map != ht->map;
}

/*
 * Grab all bucket locks, and set @pmap after making sure the map isn't stale.
 *
 * Pairs with qht_map_unlock_buckets(), hence the pass-by-reference.
 *
 * Note: callers cannot have ht->lock held.
 */
static inline
void qht_map_lock_buckets__no_stale(struct qht *ht, struct qht_map **pmap)
{
    struct qht_map *map;

    map = atomic_rcu_read(&ht->map);
    qht_map_lock_buckets(map);
    if (likely(!qht_map_is_stale__locked(ht, map))) {
        *pmap = map;
        return;
    }
    qht_map_unlock_buckets(map);

    /* we raced with a resize; acquire ht->lock to see the updated ht->map */
    qht_lock(ht);
    map = ht->map;
    qht_map_lock_buckets(map);
    qht_unlock(ht);
    *pmap = map;
    return;
}

/*
 * Get a head bucket and lock it, making sure its parent map is not stale.
 * @pmap is filled with a pointer to the bucket's parent map.
 *
 * Unlock with qemu_spin_unlock(&b->lock).
 *
 * Note: callers cannot have ht->lock held.
 */
static inline
struct qht_bucket *qht_bucket_lock__no_stale(struct qht *ht, uint32_t hash,
                                             struct qht_map **pmap)
{
    struct qht_bucket *b;
    struct qht_map *map;

    map = atomic_rcu_read(&ht->map);
    b = qht_map_to_bucket(map, hash);

    qemu_spin_lock(&b->lock);
    if (likely(!qht_map_is_stale__locked(ht, map))) {
        *pmap = map;
        return b;
    }
    qemu_spin_unlock(&b->lock);

    /* we raced with a resize; acquire ht->lock to see the updated ht->map */
    qht_lock(ht);
    map = ht->map;
    b = qht_map_to_bucket(map, hash);
    qemu_spin_lock(&b->lock);
    qht_unlock(ht);
    *pmap = map;
    return b;
}

static inline bool qht_map_needs_resize(const struct qht_map *map)
{
    return atomic_read(&map->n_added_buckets) > map->n_added_buckets_threshold;
}

static inline void qht_chain_destroy(const struct qht_bucket *head)
{
    struct qht_bucket *curr = head->next;
    struct qht_bucket *prev;

    while (curr) {
        prev = curr;
        curr = curr->next;
        qemu_vfree(prev);
    }
}

/* pass only an orphan map */
static void qht_map_destroy(struct qht_map *map)
{
    size_t i;

    for (i = 0; i < map->n_buckets; i++) {
        qht_chain_destroy(&map->buckets[i]);
    }
    qemu_vfree(map->buckets);
    g_free(map);
}

static struct qht_map *qht_map_create(size_t n_buckets)
{
    struct qht_map *map;
    size_t i;

    map = g_malloc(sizeof(*map));
    map->n_buckets = n_buckets;

    map->n_added_buckets = 0;
    map->n_added_buckets_threshold = n_buckets /
        QHT_NR_ADDED_BUCKETS_THRESHOLD_DIV;

    /* let tiny hash tables to at least add one non-head bucket */
    if (unlikely(map->n_added_buckets_threshold == 0)) {
        map->n_added_buckets_threshold = 1;
    }

    map->buckets = qemu_memalign(QHT_BUCKET_ALIGN,
                                 sizeof(*map->buckets) * n_buckets);
    for (i = 0; i < n_buckets; i++) {
        qht_head_init(&map->buckets[i]);
    }
    return map;
}

void qht_init(struct qht *ht, qht_cmp_func_t cmp, size_t n_elems,
              unsigned int mode)
{
    struct qht_map *map;
    size_t n_buckets = qht_elems_to_buckets(n_elems);

    g_assert(cmp);
    ht->cmp = cmp;
    ht->mode = mode;
    qemu_mutex_init(&ht->lock);
    map = qht_map_create(n_buckets);
    atomic_rcu_set(&ht->map, map);
}

/* call only when there are no readers/writers left */
void qht_destroy(struct qht *ht)
{
    qht_map_destroy(ht->map);
    memset(ht, 0, sizeof(*ht));
}

static void qht_bucket_reset__locked(struct qht_bucket *head)
{
    struct qht_bucket *b = head;
    int i;

    seqlock_write_begin(&head->sequence);
    do {
        for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
            if (b->pointers[i] == NULL) {
                goto done;
            }
            atomic_set(&b->hashes[i], 0);
            atomic_set(&b->pointers[i], NULL);
        }
        b = b->next;
    } while (b);
 done:
    seqlock_write_end(&head->sequence);
}

/* call with all bucket locks held */
static void qht_map_reset__all_locked(struct qht_map *map)
{
    size_t i;

    for (i = 0; i < map->n_buckets; i++) {
        qht_bucket_reset__locked(&map->buckets[i]);
    }
    qht_map_debug__all_locked(map);
}

void qht_reset(struct qht *ht)
{
    struct qht_map *map;

    qht_map_lock_buckets__no_stale(ht, &map);
    qht_map_reset__all_locked(map);
    qht_map_unlock_buckets(map);
}

static inline void qht_do_resize(struct qht *ht, struct qht_map *new)
{
    qht_do_resize_reset(ht, new, false);
}

static inline void qht_do_resize_and_reset(struct qht *ht, struct qht_map *new)
{
    qht_do_resize_reset(ht, new, true);
}

bool qht_reset_size(struct qht *ht, size_t n_elems)
{
    struct qht_map *new = NULL;
    struct qht_map *map;
    size_t n_buckets;

    n_buckets = qht_elems_to_buckets(n_elems);

    qht_lock(ht);
    map = ht->map;
    if (n_buckets != map->n_buckets) {
        new = qht_map_create(n_buckets);
    }
    qht_do_resize_and_reset(ht, new);
    qht_unlock(ht);

    return !!new;
}

static inline
void *qht_do_lookup(const struct qht_bucket *head, qht_lookup_func_t func,
                    const void *userp, uint32_t hash)
{
    const struct qht_bucket *b = head;
    int i;

    do {
        for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
            if (atomic_read(&b->hashes[i]) == hash) {
                /* The pointer is dereferenced before seqlock_read_retry,
                 * so (unlike qht_insert__locked) we need to use
                 * atomic_rcu_read here.
                 */
                void *p = atomic_rcu_read(&b->pointers[i]);

                if (likely(p) && likely(func(p, userp))) {
                    return p;
                }
            }
        }
        b = atomic_rcu_read(&b->next);
    } while (b);

    return NULL;
}

static __attribute__((noinline))
void *qht_lookup__slowpath(const struct qht_bucket *b, qht_lookup_func_t func,
                           const void *userp, uint32_t hash)
{
    unsigned int version;
    void *ret;

    do {
        version = seqlock_read_begin(&b->sequence);
        ret = qht_do_lookup(b, func, userp, hash);
    } while (seqlock_read_retry(&b->sequence, version));
    return ret;
}

void *qht_lookup_custom(const struct qht *ht, const void *userp, uint32_t hash,
                        qht_lookup_func_t func)
{
    const struct qht_bucket *b;
    const struct qht_map *map;
    unsigned int version;
    void *ret;

    map = atomic_rcu_read(&ht->map);
    b = qht_map_to_bucket(map, hash);

    version = seqlock_read_begin(&b->sequence);
    ret = qht_do_lookup(b, func, userp, hash);
    if (likely(!seqlock_read_retry(&b->sequence, version))) {
        return ret;
    }
    /*
     * Removing the do/while from the fastpath gives a 4% perf. increase when
     * running a 100%-lookup microbenchmark.
     */
    return qht_lookup__slowpath(b, func, userp, hash);
}

void *qht_lookup(const struct qht *ht, const void *userp, uint32_t hash)
{
    return qht_lookup_custom(ht, userp, hash, ht->cmp);
}

/*
 * call with head->lock held
 * @ht is const since it is only used for ht->cmp()
 */
static void *qht_insert__locked(const struct qht *ht, struct qht_map *map,
                                struct qht_bucket *head, void *p, uint32_t hash,
                                bool *needs_resize)
{
    struct qht_bucket *b = head;
    struct qht_bucket *prev = NULL;
    struct qht_bucket *new = NULL;
    int i;

    do {
        for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
            if (b->pointers[i]) {
                if (unlikely(b->hashes[i] == hash &&
                             ht->cmp(b->pointers[i], p))) {
                    return b->pointers[i];
                }
            } else {
                goto found;
            }
        }
        prev = b;
        b = b->next;
    } while (b);

    b = qemu_memalign(QHT_BUCKET_ALIGN, sizeof(*b));
    memset(b, 0, sizeof(*b));
    new = b;
    i = 0;
    atomic_inc(&map->n_added_buckets);
    if (unlikely(qht_map_needs_resize(map)) && needs_resize) {
        *needs_resize = true;
    }

 found:
    /* found an empty key: acquire the seqlock and write */
    seqlock_write_begin(&head->sequence);
    if (new) {
        atomic_rcu_set(&prev->next, b);
    }
    /* smp_wmb() implicit in seqlock_write_begin.  */
    atomic_set(&b->hashes[i], hash);
    atomic_set(&b->pointers[i], p);
    seqlock_write_end(&head->sequence);
    return NULL;
}

static __attribute__((noinline)) void qht_grow_maybe(struct qht *ht)
{
    struct qht_map *map;

    /*
     * If the lock is taken it probably means there's an ongoing resize,
     * so bail out.
     */
    if (qht_trylock(ht)) {
        return;
    }
    map = ht->map;
    /* another thread might have just performed the resize we were after */
    if (qht_map_needs_resize(map)) {
        struct qht_map *new = qht_map_create(map->n_buckets * 2);

        qht_do_resize(ht, new);
    }
    qht_unlock(ht);
}

bool qht_insert(struct qht *ht, void *p, uint32_t hash, void **existing)
{
    struct qht_bucket *b;
    struct qht_map *map;
    bool needs_resize = false;
    void *prev;

    /* NULL pointers are not supported */
    qht_debug_assert(p);

    b = qht_bucket_lock__no_stale(ht, hash, &map);
    prev = qht_insert__locked(ht, map, b, p, hash, &needs_resize);
    qht_bucket_debug__locked(b);
    qemu_spin_unlock(&b->lock);

    if (unlikely(needs_resize) && ht->mode & QHT_MODE_AUTO_RESIZE) {
        qht_grow_maybe(ht);
    }
    if (likely(prev == NULL)) {
        return true;
    }
    if (existing) {
        *existing = prev;
    }
    return false;
}

static inline bool qht_entry_is_last(const struct qht_bucket *b, int pos)
{
    if (pos == QHT_BUCKET_ENTRIES - 1) {
        if (b->next == NULL) {
            return true;
        }
        return b->next->pointers[0] == NULL;
    }
    return b->pointers[pos + 1] == NULL;
}

static void
qht_entry_move(struct qht_bucket *to, int i, struct qht_bucket *from, int j)
{
    qht_debug_assert(!(to == from && i == j));
    qht_debug_assert(to->pointers[i]);
    qht_debug_assert(from->pointers[j]);

    atomic_set(&to->hashes[i], from->hashes[j]);
    atomic_set(&to->pointers[i], from->pointers[j]);

    atomic_set(&from->hashes[j], 0);
    atomic_set(&from->pointers[j], NULL);
}

/*
 * Find the last valid entry in @orig, and swap it with @orig[pos], which has
 * just been invalidated.
 */
static inline void qht_bucket_remove_entry(struct qht_bucket *orig, int pos)
{
    struct qht_bucket *b = orig;
    struct qht_bucket *prev = NULL;
    int i;

    if (qht_entry_is_last(orig, pos)) {
        orig->hashes[pos] = 0;
        atomic_set(&orig->pointers[pos], NULL);
        return;
    }
    do {
        for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
            if (b->pointers[i]) {
                continue;
            }
            if (i > 0) {
                return qht_entry_move(orig, pos, b, i - 1);
            }
            qht_debug_assert(prev);
            return qht_entry_move(orig, pos, prev, QHT_BUCKET_ENTRIES - 1);
        }
        prev = b;
        b = b->next;
    } while (b);
    /* no free entries other than orig[pos], so swap it with the last one */
    qht_entry_move(orig, pos, prev, QHT_BUCKET_ENTRIES - 1);
}

/* call with b->lock held */
static inline
bool qht_remove__locked(struct qht_bucket *head, const void *p, uint32_t hash)
{
    struct qht_bucket *b = head;
    int i;

    do {
        for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
            void *q = b->pointers[i];

            if (unlikely(q == NULL)) {
                return false;
            }
            if (q == p) {
                qht_debug_assert(b->hashes[i] == hash);
                seqlock_write_begin(&head->sequence);
                qht_bucket_remove_entry(b, i);
                seqlock_write_end(&head->sequence);
                return true;
            }
        }
        b = b->next;
    } while (b);
    return false;
}

bool qht_remove(struct qht *ht, const void *p, uint32_t hash)
{
    struct qht_bucket *b;
    struct qht_map *map;
    bool ret;

    /* NULL pointers are not supported */
    qht_debug_assert(p);

    b = qht_bucket_lock__no_stale(ht, hash, &map);
    ret = qht_remove__locked(b, p, hash);
    qht_bucket_debug__locked(b);
    qemu_spin_unlock(&b->lock);
    return ret;
}

static inline void qht_bucket_iter(struct qht_bucket *head,
                                   const struct qht_iter *iter, void *userp)
{
    struct qht_bucket *b = head;
    int i;

    do {
        for (i = 0; i < QHT_BUCKET_ENTRIES; i++) {
            if (b->pointers[i] == NULL) {
                return;
            }
            switch (iter->type) {
            case QHT_ITER_VOID:
                iter->f.retvoid(b->pointers[i], b->hashes[i], userp);
                break;
            case QHT_ITER_RM:
                if (iter->f.retbool(b->pointers[i], b->hashes[i], userp)) {
                    /* replace i with the last valid element in the bucket */
                    seqlock_write_begin(&head->sequence);
                    qht_bucket_remove_entry(b, i);
                    seqlock_write_end(&head->sequence);
                    qht_bucket_debug__locked(b);
                    /* reevaluate i, since it just got replaced */
                    i--;
                    continue;
                }
                break;
            default:
                g_assert_not_reached();
            }
        }
        b = b->next;
    } while (b);
}

/* call with all of the map's locks held */
static inline void qht_map_iter__all_locked(struct qht_map *map,
                                            const struct qht_iter *iter,
                                            void *userp)
{
    size_t i;

    for (i = 0; i < map->n_buckets; i++) {
        qht_bucket_iter(&map->buckets[i], iter, userp);
    }
}

static inline void
do_qht_iter(struct qht *ht, const struct qht_iter *iter, void *userp)
{
    struct qht_map *map;

    map = atomic_rcu_read(&ht->map);
    qht_map_lock_buckets(map);
    qht_map_iter__all_locked(map, iter, userp);
    qht_map_unlock_buckets(map);
}

void qht_iter(struct qht *ht, qht_iter_func_t func, void *userp)
{
    const struct qht_iter iter = {
        .f.retvoid = func,
        .type = QHT_ITER_VOID,
    };

    do_qht_iter(ht, &iter, userp);
}

void qht_iter_remove(struct qht *ht, qht_iter_bool_func_t func, void *userp)
{
    const struct qht_iter iter = {
        .f.retbool = func,
        .type = QHT_ITER_RM,
    };

    do_qht_iter(ht, &iter, userp);
}

struct qht_map_copy_data {
    struct qht *ht;
    struct qht_map *new;
};

static void qht_map_copy(void *p, uint32_t hash, void *userp)
{
    struct qht_map_copy_data *data = userp;
    struct qht *ht = data->ht;
    struct qht_map *new = data->new;
    struct qht_bucket *b = qht_map_to_bucket(new, hash);

    /* no need to acquire b->lock because no thread has seen this map yet */
    qht_insert__locked(ht, new, b, p, hash, NULL);
}

/*
 * Atomically perform a resize and/or reset.
 * Call with ht->lock held.
 */
static void qht_do_resize_reset(struct qht *ht, struct qht_map *new, bool reset)
{
    struct qht_map *old;
    const struct qht_iter iter = {
        .f.retvoid = qht_map_copy,
        .type = QHT_ITER_VOID,
    };
    struct qht_map_copy_data data;

    old = ht->map;
    qht_map_lock_buckets(old);

    if (reset) {
        qht_map_reset__all_locked(old);
    }

    if (new == NULL) {
        qht_map_unlock_buckets(old);
        return;
    }

    g_assert(new->n_buckets != old->n_buckets);
    data.ht = ht;
    data.new = new;
    qht_map_iter__all_locked(old, &iter, &data);
    qht_map_debug__all_locked(new);

    atomic_rcu_set(&ht->map, new);
    qht_map_unlock_buckets(old);
    call_rcu(old, qht_map_destroy, rcu);
}

bool qht_resize(struct qht *ht, size_t n_elems)
{
    size_t n_buckets = qht_elems_to_buckets(n_elems);
    size_t ret = false;

    qht_lock(ht);
    if (n_buckets != ht->map->n_buckets) {
        struct qht_map *new;

        new = qht_map_create(n_buckets);
        qht_do_resize(ht, new);
        ret = true;
    }
    qht_unlock(ht);

    return ret;
}

/* pass @stats to qht_statistics_destroy() when done */
void qht_statistics_init(const struct qht *ht, struct qht_stats *stats)
{
    const struct qht_map *map;
    int i;

    map = atomic_rcu_read(&ht->map);

    stats->used_head_buckets = 0;
    stats->entries = 0;
    qdist_init(&stats->chain);
    qdist_init(&stats->occupancy);
    /* bail out if the qht has not yet been initialized */
    if (unlikely(map == NULL)) {
        stats->head_buckets = 0;
        return;
    }
    stats->head_buckets = map->n_buckets;

    for (i = 0; i < map->n_buckets; i++) {
        const struct qht_bucket *head = &map->buckets[i];
        const struct qht_bucket *b;
        unsigned int version;
        size_t buckets;
        size_t entries;
        int j;

        do {
            version = seqlock_read_begin(&head->sequence);
            buckets = 0;
            entries = 0;
            b = head;
            do {
                for (j = 0; j < QHT_BUCKET_ENTRIES; j++) {
                    if (atomic_read(&b->pointers[j]) == NULL) {
                        break;
                    }
                    entries++;
                }
                buckets++;
                b = atomic_rcu_read(&b->next);
            } while (b);
        } while (seqlock_read_retry(&head->sequence, version));

        if (entries) {
            qdist_inc(&stats->chain, buckets);
            qdist_inc(&stats->occupancy,
                      (double)entries / QHT_BUCKET_ENTRIES / buckets);
            stats->used_head_buckets++;
            stats->entries += entries;
        } else {
            qdist_inc(&stats->occupancy, 0);
        }
    }
}

void qht_statistics_destroy(struct qht_stats *stats)
{
    qdist_destroy(&stats->occupancy);
    qdist_destroy(&stats->chain);
}