linux-kernel - [PATCH bpf-next v1 19/22] bpf: Convert lpm

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250107140004.2732830-20-memxor@gmail.com>
Date: Tue,  7 Jan 2025 06:00:01 -0800
From: Kumar Kartikeya Dwivedi <memxor@...il.com>
To: bpf@...r.kernel.org,
	linux-kernel@...r.kernel.org
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Waiman Long <llong@...hat.com>,
	Alexei Starovoitov <ast@...nel.org>,
	Andrii Nakryiko <andrii@...nel.org>,
	Daniel Borkmann <daniel@...earbox.net>,
	Martin KaFai Lau <martin.lau@...nel.org>,
	Eduard Zingerman <eddyz87@...il.com>,
	"Paul E. McKenney" <paulmck@...nel.org>,
	Tejun Heo <tj@...nel.org>,
	Barret Rhoden <brho@...gle.com>,
	Josh Don <joshdon@...gle.com>,
	Dohyun Kim <dohyunkim@...gle.com>,
	kernel-team@...a.com
Subject: [PATCH bpf-next v1 19/22] bpf: Convert lpm_trie.c to rqspinlock

Convert all LPM trie usage of raw_spinlock to rqspinlock.

Note that rcu_dereference_protected in trie_delete_elem is switched over
to plain rcu_dereference, the RCU read lock should be held from BPF
program side or eBPF syscall path, and the trie->lock is just acquired
before the dereference. It is not clear the reason the protected variant
was used from the commit history, but the above reasoning makes sense so
switch over.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@...il.com>
---
 kernel/bpf/lpm_trie.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index f8bc1e096182..a92d1eeafb33 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -15,6 +15,7 @@
 #include <net/ipv6.h>
 #include <uapi/linux/btf.h>
 #include <linux/btf_ids.h>
+#include <asm/rqspinlock.h>
 #include <linux/bpf_mem_alloc.h>
 
 /* Intermediate node */
@@ -36,7 +37,7 @@ struct lpm_trie {
 	size_t				n_entries;
 	size_t				max_prefixlen;
 	size_t				data_size;
-	raw_spinlock_t			lock;
+	rqspinlock_t			lock;
 };
 
 /* This trie implements a longest prefix match algorithm that can be used to
@@ -349,7 +350,9 @@ static long trie_update_elem(struct bpf_map *map,
 	if (!new_node)
 		return -ENOMEM;
 
-	raw_spin_lock_irqsave(&trie->lock, irq_flags);
+	ret = raw_res_spin_lock_irqsave(&trie->lock, irq_flags);
+	if (ret)
+		goto out_free;
 
 	new_node->prefixlen = key->prefixlen;
 	RCU_INIT_POINTER(new_node->child[0], NULL);
@@ -363,8 +366,7 @@ static long trie_update_elem(struct bpf_map *map,
 	 */
 	slot = &trie->root;
 
-	while ((node = rcu_dereference_protected(*slot,
-					lockdep_is_held(&trie->lock)))) {
+	while ((node = rcu_dereference(*slot))) {
 		matchlen = longest_prefix_match(trie, node, key);
 
 		if (node->prefixlen != matchlen ||
@@ -450,8 +452,8 @@ static long trie_update_elem(struct bpf_map *map,
 	rcu_assign_pointer(*slot, im_node);
 
 out:
-	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
-
+	raw_res_spin_unlock_irqrestore(&trie->lock, irq_flags);
+out_free:
 	migrate_disable();
 	if (ret)
 		bpf_mem_cache_free(&trie->ma, new_node);
@@ -477,7 +479,9 @@ static long trie_delete_elem(struct bpf_map *map, void *_key)
 	if (key->prefixlen > trie->max_prefixlen)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&trie->lock, irq_flags);
+	ret = raw_res_spin_lock_irqsave(&trie->lock, irq_flags);
+	if (ret)
+		return ret;
 
 	/* Walk the tree looking for an exact key/length match and keeping
 	 * track of the path we traverse.  We will need to know the node
@@ -488,8 +492,7 @@ static long trie_delete_elem(struct bpf_map *map, void *_key)
 	trim = &trie->root;
 	trim2 = trim;
 	parent = NULL;
-	while ((node = rcu_dereference_protected(
-		       *trim, lockdep_is_held(&trie->lock)))) {
+	while ((node = rcu_dereference(*trim))) {
 		matchlen = longest_prefix_match(trie, node, key);
 
 		if (node->prefixlen != matchlen ||
@@ -553,7 +556,7 @@ static long trie_delete_elem(struct bpf_map *map, void *_key)
 	free_node = node;
 
 out:
-	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
+	raw_res_spin_unlock_irqrestore(&trie->lock, irq_flags);
 
 	migrate_disable();
 	bpf_mem_cache_free_rcu(&trie->ma, free_parent);
@@ -604,7 +607,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 			  offsetof(struct bpf_lpm_trie_key_u8, data);
 	trie->max_prefixlen = trie->data_size * 8;
 
-	raw_spin_lock_init(&trie->lock);
+	raw_res_spin_lock_init(&trie->lock);
 
 	/* Allocate intermediate and leaf nodes from the same allocator */
 	leaf_size = sizeof(struct lpm_trie_node) + trie->data_size +
-- 
2.43.5