Replace the per-waiter exact-match scan with a shared Bloom filter built during the second drain pass: each observed non-wildcard address sets three bits, so a waiter whose address hashes to an unset bit can be completed without another slot walk.
A Bloom filter has no false negatives, so an address absent from the final drain scan cannot be held by an observed slot; false positives only delay completion to a later scan cycle. The filter uses a one-page bitmap with three multiply-shift hash functions. It lives in the hazptr_scan_state and is only touched by the scan kthread, so waiter state remains on the caller's stack and no dynamic allocation is needed. Suggested-by: Boqun Feng <[email protected]> Signed-off-by: Kunwu Chan <[email protected]> --- kernel/hazptr.c | 93 +++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 83 insertions(+), 10 deletions(-) diff --git a/kernel/hazptr.c b/kernel/hazptr.c index 9e274a691af5..900ba35de2cb 100644 --- a/kernel/hazptr.c +++ b/kernel/hazptr.c @@ -7,6 +7,7 @@ */ #include <linux/hazptr.h> +#include <linux/bitops.h> #include <linux/percpu.h> #include <linux/spinlock.h> #include <linux/mutex.h> @@ -16,6 +17,7 @@ #include <linux/kthread.h> #include <linux/swait.h> #include <linux/sched.h> +#include <linux/bitmap.h> /* * The current hazard pointer wildcard. Flips between 1UL and 2UL to guarantee @@ -213,6 +215,55 @@ void hazptr_scan_period(void *addr, void *scan_wildcard) } } +/* Number of hash functions for the Bloom filter. */ +#define HAZPTR_BLOOM_HASHES 3 + +/* Number of bits in the Bloom filter bitmap: one page. */ +#define HAZPTR_BLOOM_NBITS (PAGE_SIZE * 8) + +struct hazptr_bloom { + unsigned long map[PAGE_SIZE / sizeof(unsigned long)]; +}; + +/* + * Multiply @addr by a per-hash odd constant and use the high bits + * as the Bloom filter index. + */ +static unsigned long hazptr_bloom_hash(void *addr, unsigned int i) +{ + static const u64 mult[HAZPTR_BLOOM_HASHES] = { + 0x9E3779B97F4A7C15ULL, + 0xC2B2AE3D27D4EB4FULL, + 0x165667B19E3779F9ULL, + }; + u64 hash = (u64)(unsigned long)addr * mult[i]; + + return hash >> (64 - ilog2(HAZPTR_BLOOM_NBITS)); +} + +static void hazptr_bloom_reset(struct hazptr_bloom *bloom) +{ + bitmap_zero(bloom->map, HAZPTR_BLOOM_NBITS); +} + +static void hazptr_bloom_add(struct hazptr_bloom *bloom, void *addr) +{ + unsigned int i; + + for (i = 0; i < HAZPTR_BLOOM_HASHES; i++) + __set_bit(hazptr_bloom_hash(addr, i), bloom->map); +} + +static bool hazptr_bloom_contains(const struct hazptr_bloom *bloom, void *addr) +{ + unsigned int i; + + for (i = 0; i < HAZPTR_BLOOM_HASHES; i++) + if (!test_bit(hazptr_bloom_hash(addr, i), bloom->map)) + return false; + return true; +} + struct hazptr_waiter { struct list_head node; void *addr; @@ -226,17 +277,26 @@ struct hazptr_scan_state { struct mutex lock; struct list_head pending; struct list_head scanning; /* kthread only */ + struct hazptr_bloom bloom; /* kthread only */ }; static struct hazptr_scan_state hazptr_scan; /* - * Check per-CPU slots before overflow-list slots to match the - * acquisition ordering of promoted slots. + * Walk all slots and return true if @watch is present. If @bloom + * is non-NULL, record observed non-wildcard addresses in it. + * + * Per-CPU slots are examined before overflow-list slots on each CPU + * to preserve the acquisition ordering required by the promote path: + * synchronize must observe the per-CPU slot release before the + * overflow-list entry can be missed. */ -static bool hazptr_value_present(void *val) +static bool hazptr_scan_walk(void *watch, struct hazptr_bloom *bloom) { int cpu; + if (bloom) + hazptr_bloom_reset(bloom); + for_each_possible_cpu(cpu) { struct hazptr_percpu_slots *percpu_slots = per_cpu_ptr(&hazptr_percpu_slots, cpu); struct hazptr_overflow_list_flip *overflow_list_flip = per_cpu_ptr(&percpu_overflow_list_flip, cpu); @@ -244,10 +304,14 @@ static bool hazptr_value_present(void *val) for (idx = 0; idx < NR_HAZPTR_PERCPU_SLOTS; idx++) { struct hazptr_slot_item *item = &percpu_slots->items[idx]; + void *v; /* Pairs with smp_store_release in hazptr_release(). */ - if (smp_load_acquire(&item->slot.addr) == val) + v = smp_load_acquire(&item->slot.addr); + if (v == watch) return true; + if (bloom && v && !is_wildcard(v)) + hazptr_bloom_add(bloom, v); } for (int i = 0; i < 2; i++) { struct hazptr_overflow_list *list = &overflow_list_flip->array[i]; @@ -256,11 +320,16 @@ static bool hazptr_value_present(void *val) raw_spin_lock_irqsave(&list->lock, flags); hlist_for_each_entry(b, &list->head, overflow_node) { + void *v; + /* Pairs with smp_store_release in hazptr_release(). */ - if (smp_load_acquire(&b->slot.addr) == val) { + v = smp_load_acquire(&b->slot.addr); + if (v == watch) { raw_spin_unlock_irqrestore(&list->lock, flags); return true; } + if (bloom && v && !is_wildcard(v)) + hazptr_bloom_add(bloom, v); } raw_spin_unlock_irqrestore(&list->lock, flags); } @@ -276,7 +345,7 @@ static bool hazptr_value_present(void *val) */ static void hazptr_drain_wildcard(void *wc) { - while (hazptr_value_present(wc)) + while (hazptr_scan_walk(wc, NULL)) cond_resched(); } @@ -309,12 +378,16 @@ static void hazptr_scan_do_cycle(void) WRITE_ONCE(hazptr_wildcard, scan_wildcard); old_wildcard = flip_wildcard(scan_wildcard); - /* Pass 2: drain the old wildcard. */ - hazptr_drain_wildcard(old_wildcard); + /* + * Pass 2: drain the old wildcard while collecting observed + * addresses into the Bloom filter. + */ + while (hazptr_scan_walk(old_wildcard, &hazptr_scan.bloom)) + cond_resched(); - /* Complete waiters whose address is no longer held by any slot. */ + /* Complete waiters whose address is not in the filter. */ list_for_each_entry_safe(w, n, &hazptr_scan.scanning, node) { - if (!hazptr_value_present(w->addr)) + if (!hazptr_bloom_contains(&hazptr_scan.bloom, w->addr)) list_move(&w->node, &done); } -- 2.43.0
