public inbox for bpf@vger.kernel.org
 help / color / mirror / Atom feed
From: Mykyta Yatsenko <mykyta.yatsenko5@gmail.com>
To: bpf@vger.kernel.org, ast@kernel.org, andrii@kernel.org,
	 daniel@iogearbox.net, kafai@meta.com, kernel-team@meta.com,
	 eddyz87@gmail.com, memxor@gmail.com,
	herbert@gondor.apana.org.au
Cc: Mykyta Yatsenko <yatsenko@meta.com>
Subject: [PATCH RFC bpf-next v2 04/18] rhashtable: Add rhashtable_walk_enter_from()
Date: Wed, 08 Apr 2026 08:10:09 -0700	[thread overview]
Message-ID: <20260408-rhash-v2-4-3b3675da1f6e@meta.com> (raw)
In-Reply-To: <20260408-rhash-v2-0-3b3675da1f6e@meta.com>

From: Mykyta Yatsenko <yatsenko@meta.com>

BPF resizable hashmap needs efficient iteration resume for
get_next_key and seq_file iterators. rhashtable_walk_enter()
always starts from bucket 0, forcing linear skip of already-seen
elements.

Add rhashtable_walk_enter_from() that looks up the key's bucket
and positions the walker there, so walk_next returns the successor
directly. If a resize moved the key to the future table, the
walker is migrated to that table.

Refactor __rhashtable_lookup into __rhashtable_lookup_one to reuse
the single-table lookup in both the two-table search and the new
enter_from positioning.

Signed-off-by: Mykyta Yatsenko <yatsenko@meta.com>
---
 include/linux/rhashtable.h |  31 ++++++++++--
 lib/rhashtable.c           |  53 ++++++++++++++++++++
 lib/test_rhashtable.c      | 120 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 199 insertions(+), 5 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 133ccb39137a..2c7a343ac592 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -253,6 +253,11 @@ static inline void rhashtable_walk_start(struct rhashtable_iter *iter)
 	(void)rhashtable_walk_start_check(iter);
 }
 
+void rhashtable_walk_enter_from(struct rhashtable *ht,
+				struct rhashtable_iter *iter,
+				const void *key,
+				const struct rhashtable_params params);
+
 void *rhashtable_walk_next(struct rhashtable_iter *iter);
 void *rhashtable_walk_peek(struct rhashtable_iter *iter);
 void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases_shared(RCU);
@@ -613,8 +618,8 @@ static inline int rhashtable_compare(struct rhashtable_compare_arg *arg,
 }
 
 /* Internal function, do not use. */
-static __always_inline struct rhash_head *__rhashtable_lookup(
-	struct rhashtable *ht, const void *key,
+static __always_inline struct rhash_head *__rhashtable_lookup_one(
+	struct rhashtable *ht, struct bucket_table *tbl, const void *key,
 	const struct rhashtable_params params,
 	const enum rht_lookup_freq freq)
 	__must_hold_shared(RCU)
@@ -624,13 +629,10 @@ static __always_inline struct rhash_head *__rhashtable_lookup(
 		.key = key,
 	};
 	struct rhash_lock_head __rcu *const *bkt;
-	struct bucket_table *tbl;
 	struct rhash_head *he;
 	unsigned int hash;
 
 	BUILD_BUG_ON(!__builtin_constant_p(freq));
-	tbl = rht_dereference_rcu(ht->tbl, ht);
-restart:
 	hash = rht_key_hashfn(ht, tbl, key, params);
 	bkt = rht_bucket(tbl, hash);
 	do {
@@ -646,6 +648,25 @@ static __always_inline struct rhash_head *__rhashtable_lookup(
 		 */
 	} while (he != RHT_NULLS_MARKER(bkt));
 
+	return NULL;
+}
+
+/* Internal function, do not use. */
+static __always_inline struct rhash_head *__rhashtable_lookup(
+	struct rhashtable *ht, const void *key,
+	const struct rhashtable_params params,
+	const enum rht_lookup_freq freq)
+	__must_hold_shared(RCU)
+{
+	struct bucket_table *tbl;
+	struct rhash_head *he;
+
+	tbl = rht_dereference_rcu(ht->tbl, ht);
+restart:
+	he = __rhashtable_lookup_one(ht, tbl, key, params, freq);
+	if (he)
+		return he;
+
 	/* Ensure we see any new tables. */
 	smp_rmb();
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 6074ed5f66f3..2fc277207dcc 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -692,6 +692,59 @@ void rhashtable_walk_enter(struct rhashtable *ht, struct rhashtable_iter *iter)
 }
 EXPORT_SYMBOL_GPL(rhashtable_walk_enter);
 
+/**
+ * rhashtable_walk_enter_from - Initialise a walk starting at a key's bucket
+ * @ht:		Table to walk over
+ * @iter:	Hash table iterator
+ * @key:	Key whose bucket to start from
+ * @params:	Hash table parameters
+ *
+ * Like rhashtable_walk_enter(), but positions the iterator at the bucket
+ * containing @key. If a resize is in progress and @key has been migrated
+ * to the future table, the walker is moved to that table.
+ *
+ * Same constraints as rhashtable_walk_enter() apply.
+ */
+void rhashtable_walk_enter_from(struct rhashtable *ht,
+				struct rhashtable_iter *iter,
+				const void *key,
+				const struct rhashtable_params params)
+				__must_hold(RCU)
+{
+	struct bucket_table *tbl;
+	struct rhash_head *he;
+
+	rhashtable_walk_enter(ht, iter);
+
+	if (!key)
+		return;
+
+	tbl = rht_dereference_rcu(ht->tbl, ht);
+	he = __rhashtable_lookup_one(ht, tbl, key, params,
+				     RHT_LOOKUP_NORMAL);
+	if (!he) {
+		smp_rmb();
+		tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+		if (!tbl)
+			return;
+
+		he = __rhashtable_lookup_one(ht, tbl, key, params,
+					     RHT_LOOKUP_NORMAL);
+		if (!he)
+			return;
+
+		spin_lock(&ht->lock);
+		list_del(&iter->walker.list);
+		iter->walker.tbl = tbl;
+		list_add(&iter->walker.list, &tbl->walkers);
+		spin_unlock(&ht->lock);
+	}
+
+	iter->slot = rht_key_hashfn(ht, tbl, key, params);
+	iter->p = he;
+}
+EXPORT_SYMBOL_GPL(rhashtable_walk_enter_from);
+
 /**
  * rhashtable_walk_exit - Free an iterator
  * @iter:	Hash table Iterator
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 0b33559a910b..0084157a96b4 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -23,6 +23,7 @@
 #include <linux/random.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
+#include <linux/cleanup.h>
 
 #define MAX_ENTRIES	1000000
 #define TEST_INSERT_FAIL INT_MAX
@@ -679,6 +680,122 @@ static int threadfunc(void *data)
 	return err;
 }
 
+static int __init test_walk_enter_from(void)
+{
+	struct rhashtable ht;
+	struct test_obj objs[4];
+	struct rhashtable_iter iter;
+	struct test_obj *obj;
+	int err, i;
+
+	err = rhashtable_init(&ht, &test_rht_params);
+	if (err)
+		return err;
+
+	/* Insert 4 elements with keys 0, 2, 4, 6 */
+	for (i = 0; i < 4; i++) {
+		objs[i].value.id = i * 2;
+		objs[i].value.tid = 0;
+		err = rhashtable_insert_fast(&ht, &objs[i].node,
+					     test_rht_params);
+		if (err) {
+			pr_warn("walk_enter_from: insert %d failed: %d\n",
+				i, err);
+			goto out;
+		}
+	}
+
+	/*
+	 * Test 1: walk_enter_from positions at key, walk_next returns
+	 * the successor (not the key itself).
+	 */
+	for (i = 0; i < 4; i++) {
+		struct test_obj_val key = { .id = i * 2 };
+
+		scoped_guard(rcu) {
+			rhashtable_walk_enter_from(&ht, &iter, &key,
+						   test_rht_params);
+			rhashtable_walk_start(&iter);
+		}
+
+		obj = rhashtable_walk_next(&iter);
+		while (IS_ERR(obj) && PTR_ERR(obj) == -EAGAIN)
+			obj = rhashtable_walk_next(&iter);
+
+		/* Successor must not be the key itself */
+		if (obj && obj->value.id == i * 2) {
+			pr_warn("walk_enter_from: returned key %d instead of successor\n",
+				i * 2);
+			err = -EINVAL;
+			rhashtable_walk_stop(&iter);
+			rhashtable_walk_exit(&iter);
+			goto out;
+		}
+
+		rhashtable_walk_stop(&iter);
+		rhashtable_walk_exit(&iter);
+	}
+
+	/* Test 2: walk_enter_from with non-existent key starts from bucket */
+	{
+		struct test_obj_val key = { .id = 99 };
+
+		scoped_guard(rcu) {
+			rhashtable_walk_enter_from(&ht, &iter, &key,
+						   test_rht_params);
+			rhashtable_walk_start(&iter);
+		}
+
+		obj = rhashtable_walk_next(&iter);
+		while (IS_ERR(obj) && PTR_ERR(obj) == -EAGAIN)
+			obj = rhashtable_walk_next(&iter);
+
+		/* Should still return some element (iteration from bucket start) */
+		rhashtable_walk_stop(&iter);
+		rhashtable_walk_exit(&iter);
+	}
+
+	/* Test 3: verify walk_enter_from + walk_next can iterate remaining elements */
+	{
+		struct test_obj_val key = { .id = 0 };
+		int count = 0;
+
+		scoped_guard(rcu) {
+			rhashtable_walk_enter_from(&ht, &iter, &key,
+						   test_rht_params);
+			rhashtable_walk_start(&iter);
+		}
+
+		while ((obj = rhashtable_walk_next(&iter))) {
+			if (IS_ERR(obj)) {
+				if (PTR_ERR(obj) == -EAGAIN)
+					continue;
+				break;
+			}
+			count++;
+		}
+
+		rhashtable_walk_stop(&iter);
+		rhashtable_walk_exit(&iter);
+
+		/*
+		 * Should see at least some elements after key 0.
+		 * Exact count depends on hash distribution.
+		 */
+		if (count == 0) {
+			pr_warn("walk_enter_from: no elements found after key 0\n");
+			err = -EINVAL;
+			goto out;
+		}
+	}
+
+	pr_info("walk_enter_from: all tests passed\n");
+	err = 0;
+out:
+	rhashtable_destroy(&ht);
+	return err;
+}
+
 static int __init test_rht_init(void)
 {
 	unsigned int entries;
@@ -738,6 +855,9 @@ static int __init test_rht_init(void)
 
 	test_insert_duplicates_run();
 
+	pr_info("Testing walk_enter_from: %s\n",
+		test_walk_enter_from() == 0 ? "pass" : "FAIL");
+
 	if (!tcount)
 		return 0;
 

-- 
2.52.0


  parent reply	other threads:[~2026-04-08 15:10 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-08 15:10 [PATCH RFC bpf-next v2 00/18] bpf: Introduce resizable hash map Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 01/18] bpf: Register rhash map Mykyta Yatsenko
2026-04-10 22:31   ` Emil Tsalapatis
2026-04-13  8:10     ` Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 02/18] bpf: Add resizable hashtab skeleton Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 03/18] bpf: Implement lookup, delete, update for resizable hashtab Mykyta Yatsenko
2026-04-12 23:10   ` Alexei Starovoitov
2026-04-13 10:52     ` Mykyta Yatsenko
2026-04-13 16:24       ` Alexei Starovoitov
2026-04-13 16:27         ` Daniel Borkmann
2026-04-08 15:10 ` Mykyta Yatsenko [this message]
2026-04-12 23:13   ` [PATCH RFC bpf-next v2 04/18] rhashtable: Add rhashtable_walk_enter_from() Alexei Starovoitov
2026-04-13 12:22     ` Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 05/18] bpf: Implement get_next_key and free_internal_structs for resizable hashtab Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 06/18] bpf: Implement bpf_each_rhash_elem() using walk API Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 07/18] bpf: Implement batch ops for resizable hashtab Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 08/18] bpf: Implement iterator APIs " Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 09/18] bpf: Implement alloc and free " Mykyta Yatsenko
2026-04-12 23:15   ` Alexei Starovoitov
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 10/18] bpf: Allow timers, workqueues and task_work in " Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 11/18] libbpf: Support resizable hashtable Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 12/18] selftests/bpf: Add basic tests for resizable hash map Mykyta Yatsenko
2026-04-12 23:16   ` Alexei Starovoitov
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 13/18] selftests/bpf: Support resizable hashtab in test_maps Mykyta Yatsenko
2026-04-12 23:17   ` Alexei Starovoitov
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 14/18] selftests/bpf: Resizable hashtab BPF_F_LOCK tests Mykyta Yatsenko
2026-04-12 23:18   ` Alexei Starovoitov
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 15/18] selftests/bpf: Add stress tests for resizable hash get_next_key Mykyta Yatsenko
2026-04-12 23:19   ` Alexei Starovoitov
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 16/18] selftests/bpf: Add BPF iterator tests for resizable hash map Mykyta Yatsenko
2026-04-12 23:20   ` Alexei Starovoitov
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 17/18] bpftool: Add rhash map documentation Mykyta Yatsenko
2026-04-08 15:10 ` [PATCH RFC bpf-next v2 18/18] selftests/bpf: Add resizable hashmap to benchmarks Mykyta Yatsenko
2026-04-12 23:25   ` Alexei Starovoitov
2026-04-12 23:11 ` [PATCH RFC bpf-next v2 00/18] bpf: Introduce resizable hash map Alexei Starovoitov
2026-04-13  8:28   ` Mykyta Yatsenko

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=20260408-rhash-v2-4-3b3675da1f6e@meta.com \
    --to=mykyta.yatsenko5@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=eddyz87@gmail.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=kafai@meta.com \
    --cc=kernel-team@meta.com \
    --cc=memxor@gmail.com \
    --cc=yatsenko@meta.com \
    /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