mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Kunwu Chan <kunwu.chan@gmail.com>
To: paulmck@kernel.org, corbet@lwn.net, mingo@redhat.com,
	frederic@kernel.org, neeraj.upadhyay@kernel.org,
	josh@joshtriplett.org, urezki@gmail.com, dave@stgolabs.net,
	lianux.mm@gmail.com
Cc: stern@rowland.harvard.edu, parri.andrea@gmail.com,
	will@kernel.org, peterz@infradead.org, boqun@kernel.org,
	npiggin@gmail.com, dhowells@redhat.com, j.alglave@ucl.ac.uk,
	luc.maranget@inria.fr, akiyks@gmail.com, dlustig@nvidia.com,
	joelagnelf@nvidia.com, skhan@linuxfoundation.org,
	rdunlap@infradead.org, longman@redhat.com, rostedt@goodmis.org,
	mathieu.desnoyers@efficios.com, jiangshanlai@gmail.com,
	qiang.zhang@linux.dev, kunwu.chan@gmail.com,
	brads@mainlining.org, linux-kernel@vger.kernel.org,
	linux-arch@vger.kernel.org, lkmm@lists.linux.dev,
	linux-doc@vger.kernel.org, rcu@vger.kernel.org,
	linux-kselftest@vger.kernel.org
Subject: [PATCH RFC v2 02/15] hazptr: use Bloom filter for shared scan waiters
Date: Sat,  3 Oct 2026 01:08:34 +0800	[thread overview]
Message-ID: <20261002170847.3653663-3-kunwu.chan@gmail.com> (raw)
In-Reply-To: <20261002170847.3653663-1-kunwu.chan@gmail.com>

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 <boqun@kernel.org>
Signed-off-by: Kunwu Chan <kunwu.chan@gmail.com>
---
 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


  parent reply	other threads:[~2026-10-02 17:09 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-02 17:08 [PATCH RFC v2 00/15] hazptr: batch synchronize operations through a shared scan Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 01/15] hazptr: add shared scan kthread Kunwu Chan
2026-10-02 17:08 ` Kunwu Chan [this message]
2026-10-02 17:08 ` [PATCH RFC v2 03/15] hazptr: scan all per-CPU slots before overflow lists Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 04/15] hazptr: add scoped_guard() support Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 05/15] hazptr: add debug option to force the acquire slow path Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 06/15] hazptr: elide redundant first drain pass Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 07/15] Documentation/litmus-tests: add hazptr wildcard-flip escape test Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 08/15] locking/lockdep: use hazptr to wait for dynamic key lookups Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 09/15] rcuscale: add hazptr scale type Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 10/15] hazptr: fix kernel-doc of hazptr_release() Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 11/15] Documentation/litmus-tests: add hazptr acquire-before-scan test Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 12/15] hazptrtorture: add slowpath and lockdep scenarios Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 13/15] hazptrtorture: add READERS4 and READERS0 torture configs Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 14/15] hazptrtorture: add 128- and 256-CPU configs Kunwu Chan
2026-10-02 17:08 ` [PATCH RFC v2 15/15] selftests/rcutorture: add hazptr torture test script Kunwu Chan
2026-10-02 17:12 ` [PATCH RFC v2 00/15] hazptr: batch synchronize operations through a shared scan Bradley Morgan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261002170847.3653663-3-kunwu.chan@gmail.com \
    --to=kunwu.chan@gmail.com \
    --cc=akiyks@gmail.com \
    --cc=boqun@kernel.org \
    --cc=brads@mainlining.org \
    --cc=corbet@lwn.net \
    --cc=dave@stgolabs.net \
    --cc=dhowells@redhat.com \
    --cc=dlustig@nvidia.com \
    --cc=frederic@kernel.org \
    --cc=j.alglave@ucl.ac.uk \
    --cc=jiangshanlai@gmail.com \
    --cc=joelagnelf@nvidia.com \
    --cc=josh@joshtriplett.org \
    --cc=lianux.mm@gmail.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=lkmm@lists.linux.dev \
    --cc=longman@redhat.com \
    --cc=luc.maranget@inria.fr \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mingo@redhat.com \
    --cc=neeraj.upadhyay@kernel.org \
    --cc=npiggin@gmail.com \
    --cc=parri.andrea@gmail.com \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=qiang.zhang@linux.dev \
    --cc=rcu@vger.kernel.org \
    --cc=rdunlap@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=skhan@linuxfoundation.org \
    --cc=stern@rowland.harvard.edu \
    --cc=urezki@gmail.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®