Merge tag 'net-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netstable

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Bluetooth, IPSec and Netfilter.

  Current release - fix to a fix:

   - netfilter: ipset: remove need to allocate memory on delete operations

  Current release - regressions:

   - macb: drop CONFIG_OF #if block, fix build

  Previous releases - always broken:

   - stream of fixes for SCTP continues

   - inet: frags: strip GSO state from fragments before reassembly

   - virtio-net: ensure that TCP packets don't overflow gso_segs

   - tcp-ao: fix use-after-free of current_key on reconnect to another
     peer

   - page_pool: remove zone/policy GFP flags when allocating XArray
     entries

   - Bluetooth: L2CAP: reject accept queue add unless BT_LISTEN

   - tls: device: fix out-of-bounds write in tls_append_frag()

   - eth: bnxt:
      - ring the doorbell when SW USO exits early, avoid packets stuck
        in Tx
      - gate TPH enablement behind BNXT_SUPPORTS_QUEUE_API check, avoid
        users of older NICs seeing non-actionable warning messages

   - eth: qede: fix NULL pointer dereference in TPA fragment processing"

* tag 'net-7.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (216 commits)
  inet: frags: strip GSO state from fragments before reassembly
  net/sched: sch_htb: limit htb_classify inner-class filter hops
  selftests/net: packetdrill: add tcp_urg_ptr_retransmit
  tcp: fix corruption of urgent data on multi-segment retransmit
  usb: atm: usbatm: fix invalid ci_range initialization
  net: fec: only stop PTP if it was initialized
  slip: remove slip_hangup() to fix use-after-free in slip_receive_buf()
  net: bridge: mcast: fix use-after-free of a master VLAN's multicast context
  net/sched: bound qdisc_pkt_len to prevent qdisc soft lockup
  net: dsa: mxl862xx: enable assisted learning on CPU port
  net: stmmac: restore NET_IP_ALIGN in the RX DMA offset
  net: stmmac: drop gso_enabled_types and rely on netdev features
  net: stmmac: selftests: Don't test flow control for small rx fifos
  net: stmmac: selftests: Account for the UC filter list for filtering tests
  net: stmmac: dwxgmac: Account for the primary MAC address for UC filtering
  net: stmmac: dwmac4: Account for the primary MAC address for UC filtering
  net: stmmac: dwmac1000: Account for the primary MAC address for UC filtering
  net: stmmac: selftests: Check multiple MMC counters
  selftests: net: Fix slow configurations in big_tcp_tunnels.sh
  selftests: net: Lower threshold with csum offload off in big_tcp_tunnels.sh
  ...

1 files changed, 35 insertions, 3 deletions

diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 5b957a831e7c..adf6dc8a95b4 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -21,6 +21,7 @@
 #include <net/ip.h>
 #include <net/inetpeer.h>
 #include <net/secure_seq.h>
+#include <linux/siphash.h>
 
 /*
  *  Theory of operations.
@@ -52,6 +53,34 @@
  */
 
 static struct kmem_cache *peer_cachep __ro_after_init;
+static siphash_aligned_key_t inetpeer_hash_key __read_mostly;
+
+static u64 inetpeer_addr_hash(const struct inetpeer_addr *a)
+{
+	net_get_random_once(&inetpeer_hash_key, sizeof(inetpeer_hash_key));
+
+	if (a->family == AF_INET)
+		return siphash_2u32((__force u32)a->a4.addr, a->a4.vif,
+				    &inetpeer_hash_key);
+
+	return siphash_4u32((__force u32)a->a6.s6_addr32[0],
+			    (__force u32)a->a6.s6_addr32[1],
+			    (__force u32)a->a6.s6_addr32[2],
+			    (__force u32)a->a6.s6_addr32[3],
+			    &inetpeer_hash_key);
+}
+
+static int inetpeer_entry_cmp(u64 dhash,
+			      const struct inetpeer_addr *daddr,
+			      const struct inet_peer *p)
+{
+	if (dhash < p->hash)
+		return -1;
+	if (dhash > p->hash)
+		return 1;
+
+	return inetpeer_addr_cmp(daddr, &p->daddr);
+}
 
 void inet_peer_base_init(struct inet_peer_base *bp)
 {
@@ -84,6 +113,7 @@ void __init inet_initpeers(void)
 
 /* Called with rcu_read_lock() or base->lock held */
 static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
+				u64 dhash,
 				struct inet_peer_base *base,
 				unsigned int seq,
 				struct inet_peer *gc_stack[],
@@ -105,7 +135,7 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr,
 			break;
 		parent = next;
 		p = rb_entry(parent, struct inet_peer, rb_node);
-		cmp = inetpeer_addr_cmp(daddr, &p->daddr);
+		cmp = inetpeer_entry_cmp(dhash, daddr, p);
 		if (cmp == 0) {
 			now = jiffies;
 			if (READ_ONCE(p->dtime) != now)
@@ -170,6 +200,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 			       const struct inetpeer_addr *daddr)
 {
 	struct inet_peer *p, *gc_stack[PEER_MAX_GC];
+	u64 dhash = inetpeer_addr_hash(daddr);
 	struct rb_node **pp, *parent;
 	unsigned int gc_cnt, seq;
 
@@ -177,7 +208,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 	 * Because of a concurrent writer, we might not find an existing entry.
 	 */
 	seq = read_seqbegin(&base->lock);
-	p = lookup(daddr, base, seq, NULL, &gc_cnt, &parent, &pp);
+	p = lookup(daddr, dhash, base, seq, NULL, &gc_cnt, &parent, &pp);
 
 	/* Make sure tree was not modified during our lookup. */
 	if (p && !read_seqretry(&base->lock, seq))
@@ -190,11 +221,12 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 	write_seqlock_bh(&base->lock);
 
 	gc_cnt = 0;
-	p = lookup(daddr, base, seq, gc_stack, &gc_cnt, &parent, &pp);
+	p = lookup(daddr, dhash, base, seq, gc_stack, &gc_cnt, &parent, &pp);
 	if (!p) {
 		p = kmem_cache_alloc(peer_cachep, GFP_ATOMIC);
 		if (p) {
 			p->daddr = *daddr;
+			p->hash = dhash;
 			p->dtime = (__u32)jiffies;
 			refcount_set(&p->refcnt, 1);
 			atomic_set(&p->rid, 0);