Merge tag 'net-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking updates from Jakub Kicinski:
 "Including fixes from netfilter and bpf.

  Current release - regressions:

   - eth: stmmac: fix failure to probe without MAC interface specified

  Current release - new code bugs:

   - docs: netlink: fix missing classic_netlink doc reference

  Previous releases - regressions:

   - deal with integer overflows in kmalloc_reserve()

   - use sk_forward_alloc_get() in sk_get_meminfo()

   - bpf_sk_storage: fix the missing uncharge in sk_omem_alloc

   - fib: avoid warn splat in flow dissector after packet mangling

   - skb_segment: call zero copy functions before using skbuff frags

   - eth: sfc: check for zero length in EF10 RX prefix

  Previous releases - always broken:

   - af_unix: fix msg_controllen test in scm_pidfd_recv() for
     MSG_CMSG_COMPAT

   - xsk: fix xsk_build_skb() dereferencing possible ERR_PTR()

   - netfilter:
      - nft_exthdr: fix non-linear header modification
      - xt_u32, xt_sctp: validate user space input
      - nftables: exthdr: fix 4-byte stack OOB write
      - nfnetlink_osf: avoid OOB read
      - one more fix for the garbage collection work from last release

   - igmp: limit igmpv3_newpack() packet size to IP_MAX_MTU

   - bpf, sockmap: fix preempt_rt splat when using raw_spin_lock_t

   - handshake: fix null-deref in handshake_nl_done_doit()

   - ip: ignore dst hint for multipath routes to ensure packets are
     hashed across the nexthops

   - phy: micrel:
      - correct bit assignments for cable test errata
      - disable EEE according to the KSZ9477 errata

  Misc:

   - docs/bpf: document compile-once-run-everywhere (CO-RE) relocations

   - Revert "net: macsec: preserve ingress frame ordering", it appears
     to have been developed against an older kernel, problem doesn't
     exist upstream"

* tag 'net-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (95 commits)
  net: enetc: distinguish error from valid pointers in enetc_fixup_clear_rss_rfs()
  Revert "net: team: do not use dynamic lockdep key"
  net: hns3: remove GSO partial feature bit
  net: hns3: fix the port information display when sfp is absent
  net: hns3: fix invalid mutex between tc qdisc and dcb ets command issue
  net: hns3: fix debugfs concurrency issue between kfree buffer and read
  net: hns3: fix byte order conversion issue in hclge_dbg_fd_tcam_read()
  net: hns3: Support query tx timeout threshold by debugfs
  net: hns3: fix tx timeout issue
  net: phy: Provide Module 4 KSZ9477 errata (DS80000754C)
  netfilter: nf_tables: Unbreak audit log reset
  netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c
  netfilter: nft_set_rbtree: skip sync GC for new elements in this transaction
  netfilter: nf_tables: uapi: Describe NFTA_RULE_CHAIN_ID
  netfilter: nfnetlink_osf: avoid OOB read
  netfilter: nftables: exthdr: fix 4-byte stack OOB write
  selftests/bpf: Check bpf_sk_storage has uncharged sk_omem_alloc
  bpf: bpf_sk_storage: Fix the missing uncharge in sk_omem_alloc
  bpf: bpf_sk_storage: Fix invalid wait context lockdep report
  s390/bpf: Pass through tail call counter in trampolines
  ...

1 files changed, 34 insertions, 20 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 45707059082f..4eaf7ed0d1f4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -550,7 +550,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 			     bool *pfmemalloc)
 {
 	bool ret_pfmemalloc = false;
-	unsigned int obj_size;
+	size_t obj_size;
 	void *obj;
 
 	obj_size = SKB_HEAD_ALIGN(*size);
@@ -567,7 +567,13 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 		obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node);
 		goto out;
 	}
-	*size = obj_size = kmalloc_size_roundup(obj_size);
+
+	obj_size = kmalloc_size_roundup(obj_size);
+	/* The following cast might truncate high-order bits of obj_size, this
+	 * is harmless because kmalloc(obj_size >= 2^32) will fail anyway.
+	 */
+	*size = (unsigned int)obj_size;
+
 	/*
 	 * Try a regular allocation, when that fails and we're not entitled
 	 * to the reserves, fail.
@@ -4423,21 +4429,20 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	struct sk_buff *segs = NULL;
 	struct sk_buff *tail = NULL;
 	struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
-	skb_frag_t *frag = skb_shinfo(head_skb)->frags;
 	unsigned int mss = skb_shinfo(head_skb)->gso_size;
 	unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
-	struct sk_buff *frag_skb = head_skb;
 	unsigned int offset = doffset;
 	unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
 	unsigned int partial_segs = 0;
 	unsigned int headroom;
 	unsigned int len = head_skb->len;
+	struct sk_buff *frag_skb;
+	skb_frag_t *frag;
 	__be16 proto;
 	bool csum, sg;
-	int nfrags = skb_shinfo(head_skb)->nr_frags;
 	int err = -ENOMEM;
 	int i = 0;
-	int pos;
+	int nfrags, pos;
 
 	if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) &&
 	    mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) {
@@ -4514,6 +4519,13 @@ normal:
 	headroom = skb_headroom(head_skb);
 	pos = skb_headlen(head_skb);
 
+	if (skb_orphan_frags(head_skb, GFP_ATOMIC))
+		return ERR_PTR(-ENOMEM);
+
+	nfrags = skb_shinfo(head_skb)->nr_frags;
+	frag = skb_shinfo(head_skb)->frags;
+	frag_skb = head_skb;
+
 	do {
 		struct sk_buff *nskb;
 		skb_frag_t *nskb_frag;
@@ -4534,6 +4546,10 @@ normal:
 		    (skb_headlen(list_skb) == len || sg)) {
 			BUG_ON(skb_headlen(list_skb) > len);
 
+			nskb = skb_clone(list_skb, GFP_ATOMIC);
+			if (unlikely(!nskb))
+				goto err;
+
 			i = 0;
 			nfrags = skb_shinfo(list_skb)->nr_frags;
 			frag = skb_shinfo(list_skb)->frags;
@@ -4552,12 +4568,8 @@ normal:
 				frag++;
 			}
 
-			nskb = skb_clone(list_skb, GFP_ATOMIC);
 			list_skb = list_skb->next;
 
-			if (unlikely(!nskb))
-				goto err;
-
 			if (unlikely(pskb_trim(nskb, len))) {
 				kfree_skb(nskb);
 				goto err;
@@ -4633,12 +4645,16 @@ normal:
 		skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags &
 					   SKBFL_SHARED_FRAG;
 
-		if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
-		    skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+		if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
 			goto err;
 
 		while (pos < offset + len) {
 			if (i >= nfrags) {
+				if (skb_orphan_frags(list_skb, GFP_ATOMIC) ||
+				    skb_zerocopy_clone(nskb, list_skb,
+						       GFP_ATOMIC))
+					goto err;
+
 				i = 0;
 				nfrags = skb_shinfo(list_skb)->nr_frags;
 				frag = skb_shinfo(list_skb)->frags;
@@ -4652,10 +4668,6 @@ normal:
 					i--;
 					frag--;
 				}
-				if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
-				    skb_zerocopy_clone(nskb, frag_skb,
-						       GFP_ATOMIC))
-					goto err;
 
 				list_skb = list_skb->next;
 			}
@@ -5207,7 +5219,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 	serr->ee.ee_info = tstype;
 	serr->opt_stats = opt_stats;
 	serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
-	if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
+	if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
 		serr->ee.ee_data = skb_shinfo(skb)->tskey;
 		if (sk_is_tcp(sk))
 			serr->ee.ee_data -= atomic_read(&sk->sk_tskey);
@@ -5263,21 +5275,23 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 {
 	struct sk_buff *skb;
 	bool tsonly, opt_stats = false;
+	u32 tsflags;
 
 	if (!sk)
 		return;
 
-	if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
+	tsflags = READ_ONCE(sk->sk_tsflags);
+	if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
 	    skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
 		return;
 
-	tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
+	tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
 	if (!skb_may_tx_timestamp(sk, tsonly))
 		return;
 
 	if (tsonly) {
 #ifdef CONFIG_INET
-		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
+		if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
 		    sk_is_tcp(sk)) {
 			skb = tcp_get_timestamping_opt_stats(sk, orig_skb,
 							     ack_skb);