Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-10-31

We've added 13 non-merge commits during the last 16 day(s) which contain
a total of 16 files changed, 710 insertions(+), 668 deletions(-).

The main changes are:

1) Optimize and homogenize bpf_csum_diff helper for all archs and also
   add a batch of new BPF selftests for it, from Puranjay Mohan.

2) Rewrite and migrate the test_tcp_check_syncookie.sh BPF selftest
   into test_progs so that it can be run in BPF CI, from Alexis Lothoré.

3) Two BPF sockmap selftest fixes, from Zijian Zhang.

4) Small XDP synproxy BPF selftest cleanup to remove IP_DF check,
   from Vincent Li.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
  selftests/bpf: Add a selftest for bpf_csum_diff()
  selftests/bpf: Don't mask result of bpf_csum_diff() in test_verifier
  bpf: bpf_csum_diff: Optimize and homogenize for all archs
  net: checksum: Move from32to16() to generic header
  selftests/bpf: remove xdp_synproxy IP_DF check
  selftests/bpf: remove test_tcp_check_syncookie
  selftests/bpf: test MSS value returned with bpf_tcp_gen_syncookie
  selftests/bpf: add ipv4 and dual ipv4/ipv6 support in btf_skc_cls_ingress
  selftests/bpf: get rid of global vars in btf_skc_cls_ingress
  selftests/bpf: add missing ns cleanups in btf_skc_cls_ingress
  selftests/bpf: factorize conn and syncookies tests in a single runner
  selftests/bpf: Fix txmsg_redir of test_txmsg_pull in test_sockmap
  selftests/bpf: Fix msg_verify_data in test_sockmap

====================

Link: https://patch.msgid.link/20241031221543.108853-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 11 insertions, 28 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 9d2c57d17473..82f92ed0dc72 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1654,18 +1654,6 @@ void sk_reuseport_prog_free(struct bpf_prog *prog)
 		bpf_prog_destroy(prog);
 }
 
-struct bpf_scratchpad {
-	union {
-		__be32 diff[MAX_BPF_STACK / sizeof(__be32)];
-		u8     buff[MAX_BPF_STACK];
-	};
-	local_lock_t	bh_lock;
-};
-
-static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp) = {
-	.bh_lock	= INIT_LOCAL_LOCK(bh_lock),
-};
-
 static inline int __bpf_try_make_writable(struct sk_buff *skb,
 					  unsigned int write_len)
 {
@@ -2022,11 +2010,6 @@ static const struct bpf_func_proto bpf_l4_csum_replace_proto = {
 BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size,
 	   __be32 *, to, u32, to_size, __wsum, seed)
 {
-	struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
-	u32 diff_size = from_size + to_size;
-	int i, j = 0;
-	__wsum ret;
-
 	/* This is quite flexible, some examples:
 	 *
 	 * from_size == 0, to_size > 0,  seed := csum --> pushing data
@@ -2035,19 +2018,19 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size,
 	 *
 	 * Even for diffing, from_size and to_size don't need to be equal.
 	 */
-	if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) ||
-		     diff_size > sizeof(sp->diff)))
-		return -EINVAL;
 
-	local_lock_nested_bh(&bpf_sp.bh_lock);
-	for (i = 0; i < from_size / sizeof(__be32); i++, j++)
-		sp->diff[j] = ~from[i];
-	for (i = 0; i <   to_size / sizeof(__be32); i++, j++)
-		sp->diff[j] = to[i];
+	__wsum ret = seed;
 
-	ret = csum_partial(sp->diff, diff_size, seed);
-	local_unlock_nested_bh(&bpf_sp.bh_lock);
-	return ret;
+	if (from_size && to_size)
+		ret = csum_sub(csum_partial(to, to_size, ret),
+			       csum_partial(from, from_size, 0));
+	else if (to_size)
+		ret = csum_partial(to, to_size, ret);
+
+	else if (from_size)
+		ret = ~csum_partial(from, from_size, ~ret);
+
+	return csum_from32to16((__force unsigned int)ret);
 }
 
 static const struct bpf_func_proto bpf_csum_diff_proto = {