From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
To: bpf@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Peter Zijlstra <peterz@infradead.org>,
Will Deacon <will@kernel.org>, Waiman Long <llong@redhat.com>,
Alexei Starovoitov <ast@kernel.org>,
Andrii Nakryiko <andrii@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Martin KaFai Lau <martin.lau@kernel.org>,
Eduard Zingerman <eddyz87@gmail.com>,
"Paul E. McKenney" <paulmck@kernel.org>,
Tejun Heo <tj@kernel.org>, Barret Rhoden <brho@google.com>,
Josh Don <joshdon@google.com>, Dohyun Kim <dohyunkim@google.com>,
linux-arm-kernel@lists.infradead.org, kkd@meta.com,
kernel-team@meta.com
Subject: [PATCH bpf-next v4 19/25] bpf: Convert hashtab.c to rqspinlock
Date: Sat, 15 Mar 2025 21:05:35 -0700 [thread overview]
Message-ID: <20250316040541.108729-20-memxor@gmail.com> (raw)
In-Reply-To: <20250316040541.108729-1-memxor@gmail.com>
Convert hashtab.c from raw_spinlock to rqspinlock, and drop the hashed
per-cpu counter crud from the code base which is no longer necessary.
Closes: https://lore.kernel.org/bpf/675302fd.050a0220.2477f.0004.GAE@google.com
Closes: https://lore.kernel.org/bpf/000000000000b3e63e061eed3f6b@google.com
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
kernel/bpf/hashtab.c | 102 ++++++++++++++-----------------------------
1 file changed, 32 insertions(+), 70 deletions(-)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 877298133fda..5a5adc66b8e2 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -16,6 +16,7 @@
#include "bpf_lru_list.h"
#include "map_in_map.h"
#include <linux/bpf_mem_alloc.h>
+#include <asm/rqspinlock.h>
#define HTAB_CREATE_FLAG_MASK \
(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
@@ -78,7 +79,7 @@
*/
struct bucket {
struct hlist_nulls_head head;
- raw_spinlock_t raw_lock;
+ rqspinlock_t raw_lock;
};
#define HASHTAB_MAP_LOCK_COUNT 8
@@ -104,8 +105,6 @@ struct bpf_htab {
u32 n_buckets; /* number of hash buckets */
u32 elem_size; /* size of each element in bytes */
u32 hashrnd;
- struct lock_class_key lockdep_key;
- int __percpu *map_locked[HASHTAB_MAP_LOCK_COUNT];
};
/* each htab element is struct htab_elem + key + value */
@@ -140,45 +139,26 @@ static void htab_init_buckets(struct bpf_htab *htab)
for (i = 0; i < htab->n_buckets; i++) {
INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
- raw_spin_lock_init(&htab->buckets[i].raw_lock);
- lockdep_set_class(&htab->buckets[i].raw_lock,
- &htab->lockdep_key);
+ raw_res_spin_lock_init(&htab->buckets[i].raw_lock);
cond_resched();
}
}
-static inline int htab_lock_bucket(const struct bpf_htab *htab,
- struct bucket *b, u32 hash,
- unsigned long *pflags)
+static inline int htab_lock_bucket(struct bucket *b, unsigned long *pflags)
{
unsigned long flags;
+ int ret;
- hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
-
- preempt_disable();
- local_irq_save(flags);
- if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
- __this_cpu_dec(*(htab->map_locked[hash]));
- local_irq_restore(flags);
- preempt_enable();
- return -EBUSY;
- }
-
- raw_spin_lock(&b->raw_lock);
+ ret = raw_res_spin_lock_irqsave(&b->raw_lock, flags);
+ if (ret)
+ return ret;
*pflags = flags;
-
return 0;
}
-static inline void htab_unlock_bucket(const struct bpf_htab *htab,
- struct bucket *b, u32 hash,
- unsigned long flags)
+static inline void htab_unlock_bucket(struct bucket *b, unsigned long flags)
{
- hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
- raw_spin_unlock(&b->raw_lock);
- __this_cpu_dec(*(htab->map_locked[hash]));
- local_irq_restore(flags);
- preempt_enable();
+ raw_res_spin_unlock_irqrestore(&b->raw_lock, flags);
}
static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
@@ -483,14 +463,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
struct bpf_htab *htab;
- int err, i;
+ int err;
htab = bpf_map_area_alloc(sizeof(*htab), NUMA_NO_NODE);
if (!htab)
return ERR_PTR(-ENOMEM);
- lockdep_register_key(&htab->lockdep_key);
-
bpf_map_init_from_attr(&htab->map, attr);
if (percpu_lru) {
@@ -536,15 +514,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
if (!htab->buckets)
goto free_elem_count;
- for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) {
- htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map,
- sizeof(int),
- sizeof(int),
- GFP_USER);
- if (!htab->map_locked[i])
- goto free_map_locked;
- }
-
if (htab->map.map_flags & BPF_F_ZERO_SEED)
htab->hashrnd = 0;
else
@@ -607,15 +576,12 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
free_map_locked:
if (htab->use_percpu_counter)
percpu_counter_destroy(&htab->pcount);
- for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
- free_percpu(htab->map_locked[i]);
bpf_map_area_free(htab->buckets);
bpf_mem_alloc_destroy(&htab->pcpu_ma);
bpf_mem_alloc_destroy(&htab->ma);
free_elem_count:
bpf_map_free_elem_count(&htab->map);
free_htab:
- lockdep_unregister_key(&htab->lockdep_key);
bpf_map_area_free(htab);
return ERR_PTR(err);
}
@@ -820,7 +786,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
b = __select_bucket(htab, tgt_l->hash);
head = &b->head;
- ret = htab_lock_bucket(htab, b, tgt_l->hash, &flags);
+ ret = htab_lock_bucket(b, &flags);
if (ret)
return false;
@@ -831,7 +797,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
break;
}
- htab_unlock_bucket(htab, b, tgt_l->hash, flags);
+ htab_unlock_bucket(b, flags);
if (l == tgt_l)
check_and_free_fields(htab, l);
@@ -1150,7 +1116,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
*/
}
- ret = htab_lock_bucket(htab, b, hash, &flags);
+ ret = htab_lock_bucket(b, &flags);
if (ret)
return ret;
@@ -1201,7 +1167,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
check_and_free_fields(htab, l_old);
}
}
- htab_unlock_bucket(htab, b, hash, flags);
+ htab_unlock_bucket(b, flags);
if (l_old) {
if (old_map_ptr)
map->ops->map_fd_put_ptr(map, old_map_ptr, true);
@@ -1210,7 +1176,7 @@ static long htab_map_update_elem(struct bpf_map *map, void *key, void *value,
}
return 0;
err:
- htab_unlock_bucket(htab, b, hash, flags);
+ htab_unlock_bucket(b, flags);
return ret;
}
@@ -1257,7 +1223,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value
copy_map_value(&htab->map,
l_new->key + round_up(map->key_size, 8), value);
- ret = htab_lock_bucket(htab, b, hash, &flags);
+ ret = htab_lock_bucket(b, &flags);
if (ret)
goto err_lock_bucket;
@@ -1278,7 +1244,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value
ret = 0;
err:
- htab_unlock_bucket(htab, b, hash, flags);
+ htab_unlock_bucket(b, flags);
err_lock_bucket:
if (ret)
@@ -1315,7 +1281,7 @@ static long __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
b = __select_bucket(htab, hash);
head = &b->head;
- ret = htab_lock_bucket(htab, b, hash, &flags);
+ ret = htab_lock_bucket(b, &flags);
if (ret)
return ret;
@@ -1340,7 +1306,7 @@ static long __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
}
ret = 0;
err:
- htab_unlock_bucket(htab, b, hash, flags);
+ htab_unlock_bucket(b, flags);
return ret;
}
@@ -1381,7 +1347,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
return -ENOMEM;
}
- ret = htab_lock_bucket(htab, b, hash, &flags);
+ ret = htab_lock_bucket(b, &flags);
if (ret)
goto err_lock_bucket;
@@ -1405,7 +1371,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
}
ret = 0;
err:
- htab_unlock_bucket(htab, b, hash, flags);
+ htab_unlock_bucket(b, flags);
err_lock_bucket:
if (l_new) {
bpf_map_dec_elem_count(&htab->map);
@@ -1447,7 +1413,7 @@ static long htab_map_delete_elem(struct bpf_map *map, void *key)
b = __select_bucket(htab, hash);
head = &b->head;
- ret = htab_lock_bucket(htab, b, hash, &flags);
+ ret = htab_lock_bucket(b, &flags);
if (ret)
return ret;
@@ -1457,7 +1423,7 @@ static long htab_map_delete_elem(struct bpf_map *map, void *key)
else
ret = -ENOENT;
- htab_unlock_bucket(htab, b, hash, flags);
+ htab_unlock_bucket(b, flags);
if (l)
free_htab_elem(htab, l);
@@ -1483,7 +1449,7 @@ static long htab_lru_map_delete_elem(struct bpf_map *map, void *key)
b = __select_bucket(htab, hash);
head = &b->head;
- ret = htab_lock_bucket(htab, b, hash, &flags);
+ ret = htab_lock_bucket(b, &flags);
if (ret)
return ret;
@@ -1494,7 +1460,7 @@ static long htab_lru_map_delete_elem(struct bpf_map *map, void *key)
else
ret = -ENOENT;
- htab_unlock_bucket(htab, b, hash, flags);
+ htab_unlock_bucket(b, flags);
if (l)
htab_lru_push_free(htab, l);
return ret;
@@ -1561,7 +1527,6 @@ static void htab_map_free_timers_and_wq(struct bpf_map *map)
static void htab_map_free(struct bpf_map *map)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
- int i;
/* bpf_free_used_maps() or close(map_fd) will trigger this map_free callback.
* bpf_free_used_maps() is called after bpf prog is no longer executing.
@@ -1586,9 +1551,6 @@ static void htab_map_free(struct bpf_map *map)
bpf_mem_alloc_destroy(&htab->ma);
if (htab->use_percpu_counter)
percpu_counter_destroy(&htab->pcount);
- for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
- free_percpu(htab->map_locked[i]);
- lockdep_unregister_key(&htab->lockdep_key);
bpf_map_area_free(htab);
}
@@ -1631,7 +1593,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
b = __select_bucket(htab, hash);
head = &b->head;
- ret = htab_lock_bucket(htab, b, hash, &bflags);
+ ret = htab_lock_bucket(b, &bflags);
if (ret)
return ret;
@@ -1668,7 +1630,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
hlist_nulls_del_rcu(&l->hash_node);
out_unlock:
- htab_unlock_bucket(htab, b, hash, bflags);
+ htab_unlock_bucket(b, bflags);
if (l) {
if (is_lru_map)
@@ -1790,7 +1752,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
head = &b->head;
/* do not grab the lock unless need it (bucket_cnt > 0). */
if (locked) {
- ret = htab_lock_bucket(htab, b, batch, &flags);
+ ret = htab_lock_bucket(b, &flags);
if (ret) {
rcu_read_unlock();
bpf_enable_instrumentation();
@@ -1813,7 +1775,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
/* Note that since bucket_cnt > 0 here, it is implicit
* that the locked was grabbed, so release it.
*/
- htab_unlock_bucket(htab, b, batch, flags);
+ htab_unlock_bucket(b, flags);
rcu_read_unlock();
bpf_enable_instrumentation();
goto after_loop;
@@ -1824,7 +1786,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
/* Note that since bucket_cnt > 0 here, it is implicit
* that the locked was grabbed, so release it.
*/
- htab_unlock_bucket(htab, b, batch, flags);
+ htab_unlock_bucket(b, flags);
rcu_read_unlock();
bpf_enable_instrumentation();
kvfree(keys);
@@ -1887,7 +1849,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
dst_val += value_size;
}
- htab_unlock_bucket(htab, b, batch, flags);
+ htab_unlock_bucket(b, flags);
locked = false;
while (node_to_free) {
--
2.47.1
next prev parent reply other threads:[~2025-03-16 4:39 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-16 4:05 [PATCH bpf-next v4 00/25] Resilient Queued Spin Lock Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 01/25] locking: Move MCS struct definition to public header Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 02/25] locking: Move common qspinlock helpers to a private header Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 03/25] locking: Allow obtaining result of arch_mcs_spin_lock_contended Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 04/25] locking: Copy out qspinlock.c to kernel/bpf/rqspinlock.c Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 05/25] rqspinlock: Add rqspinlock.h header Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 06/25] rqspinlock: Drop PV and virtualization support Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 07/25] rqspinlock: Add support for timeouts Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 08/25] rqspinlock: Hardcode cond_acquire loops for arm64 Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 09/25] rqspinlock: Protect pending bit owners from stalls Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 10/25] rqspinlock: Protect waiters in queue " Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 11/25] rqspinlock: Protect waiters in trylock fallback " Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 12/25] rqspinlock: Add deadlock detection and recovery Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 13/25] rqspinlock: Add a test-and-set fallback Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 14/25] rqspinlock: Add basic support for CONFIG_PARAVIRT Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 15/25] rqspinlock: Add helper to print a splat on timeout or deadlock Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 16/25] rqspinlock: Add macros for rqspinlock usage Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 17/25] rqspinlock: Add entry to Makefile, MAINTAINERS Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 18/25] rqspinlock: Add locktorture support Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` Kumar Kartikeya Dwivedi [this message]
2025-03-16 4:05 ` [PATCH bpf-next v4 20/25] bpf: Convert percpu_freelist.c to rqspinlock Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 21/25] bpf: Convert lpm_trie.c " Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 22/25] bpf: Introduce rqspinlock kfuncs Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 23/25] bpf: Implement verifier support for rqspinlock Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 24/25] bpf: Maintain FIFO property for rqspinlock unlock Kumar Kartikeya Dwivedi
2025-03-16 4:05 ` [PATCH bpf-next v4 25/25] selftests/bpf: Add tests for rqspinlock Kumar Kartikeya Dwivedi
2025-03-18 20:32 ` [PATCH bpf-next v4 00/25] Resilient Queued Spin Lock Alexei Starovoitov
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=20250316040541.108729-20-memxor@gmail.com \
--to=memxor@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=brho@google.com \
--cc=daniel@iogearbox.net \
--cc=dohyunkim@google.com \
--cc=eddyz87@gmail.com \
--cc=joshdon@google.com \
--cc=kernel-team@meta.com \
--cc=kkd@meta.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=llong@redhat.com \
--cc=martin.lau@kernel.org \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=tj@kernel.org \
--cc=torvalds@linux-foundation.org \
--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;
as well as URLs for NNTP newsgroup(s).