Merge tag 'net-5.15-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from WiFi (mac80211), and BPF.

  Current release - regressions:

   - skb_expand_head: adjust skb->truesize to fix socket memory
     accounting

   - mptcp: fix corrupt receiver key in MPC + data + checksum

  Previous releases - regressions:

   - multicast: calculate csum of looped-back and forwarded packets

   - cgroup: fix memory leak caused by missing cgroup_bpf_offline

   - cfg80211: fix management registrations locking, prevent list
     corruption

   - cfg80211: correct false positive in bridge/4addr mode check

   - tcp_bpf: fix race in the tcp_bpf_send_verdict resulting in reusing
     previous verdict

  Previous releases - always broken:

   - sctp: enhancements for the verification tag, prevent attackers from
     killing SCTP sessions

   - tipc: fix size validations for the MSG_CRYPTO type

   - mac80211: mesh: fix HE operation element length check, prevent out
     of bound access

   - tls: fix sign of socket errors, prevent positive error codes being
     reported from read()/write()

   - cfg80211: scan: extend RCU protection in
     cfg80211_add_nontrans_list()

   - implement ->sock_is_readable() for UDP and AF_UNIX, fix poll() for
     sockets in a BPF sockmap

   - bpf: fix potential race in tail call compatibility check resulting
     in two operations which would make the map incompatible succeeding

   - bpf: prevent increasing bpf_jit_limit above max

   - bpf: fix error usage of map_fd and fdget() in generic batch update

   - phy: ethtool: lock the phy for consistency of results

   - prevent infinite while loop in skb_tx_hash() when Tx races with
     driver reconfiguring the queue <> traffic class mapping

   - usbnet: fixes for bad HW conjured by syzbot

   - xen: stop tx queues during live migration, prevent UAF

   - net-sysfs: initialize uid and gid before calling
     net_ns_get_ownership

   - mlxsw: prevent Rx stalls under memory pressure"

* tag 'net-5.15-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (67 commits)
  Revert "net: hns3: fix pause config problem after autoneg disabled"
  mptcp: fix corrupt receiver key in MPC + data + checksum
  riscv, bpf: Fix potential NULL dereference
  octeontx2-af: Fix possible null pointer dereference.
  octeontx2-af: Display all enabled PF VF rsrc_alloc entries.
  octeontx2-af: Check whether ipolicers exists
  net: ethernet: microchip: lan743x: Fix skb allocation failure
  net/tls: Fix flipped sign in async_wait.err assignment
  net/tls: Fix flipped sign in tls_err_abort() calls
  net/smc: Correct spelling mistake to TCPF_SYN_RECV
  net/smc: Fix smc_link->llc_testlink_time overflow
  nfp: bpf: relax prog rejection for mtu check through max_pkt_offset
  vmxnet3: do not stop tx queues after netif_device_detach()
  r8169: Add device 10ec:8162 to driver r8169
  ptp: Document the PTP_CLK_MAGIC ioctl number
  usbnet: fix error return code in usbnet_probe()
  net: hns3: adjust string spaces of some parameters of tx bd info in debugfs
  net: hns3: expand buffer len for some debugfs command
  net: hns3: add more string spaces for dumping packets number of queue info in debugfs
  net: hns3: fix data endian problem of some functions of debugfs
  ...

6 files changed, 60 insertions, 17 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 7ee9fecd3aff..eb3a366bf212 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3163,6 +3163,12 @@ static u16 skb_tx_hash(const struct net_device *dev,
 
 		qoffset = sb_dev->tc_to_txq[tc].offset;
 		qcount = sb_dev->tc_to_txq[tc].count;
+		if (unlikely(!qcount)) {
+			net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n",
+					     sb_dev->name, qoffset, tc);
+			qoffset = 0;
+			qcount = dev->real_num_tx_queues;
+		}
 	}
 
 	if (skb_rx_queue_recorded(skb)) {
@@ -3906,7 +3912,8 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
 	skb_reset_mac_header(skb);
 	__skb_pull(skb, skb_network_offset(skb));
 	skb->pkt_type = PACKET_LOOPBACK;
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	if (skb->ip_summed == CHECKSUM_NONE)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	WARN_ON(!skb_dst(skb));
 	skb_dst_force(skb);
 	netif_rx_ni(skb);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f6197774048b..b2e49eb7001d 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1973,9 +1973,9 @@ int netdev_register_kobject(struct net_device *ndev)
 int netdev_change_owner(struct net_device *ndev, const struct net *net_old,
 			const struct net *net_new)
 {
+	kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID;
+	kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID;
 	struct device *dev = &ndev->dev;
-	kuid_t old_uid, new_uid;
-	kgid_t old_gid, new_gid;
 	int error;
 
 	net_ns_get_ownership(net_old, &old_uid, &old_gid);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2170bea2c7de..fe9358437380 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -80,6 +80,7 @@
 #include <linux/indirect_call_wrapper.h>
 
 #include "datagram.h"
+#include "sock_destructor.h"
 
 struct kmem_cache *skbuff_head_cache __ro_after_init;
 static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
@@ -1804,30 +1805,39 @@ EXPORT_SYMBOL(skb_realloc_headroom);
 struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom)
 {
 	int delta = headroom - skb_headroom(skb);
+	int osize = skb_end_offset(skb);
+	struct sock *sk = skb->sk;
 
 	if (WARN_ONCE(delta <= 0,
 		      "%s is expecting an increase in the headroom", __func__))
 		return skb;
 
-	/* pskb_expand_head() might crash, if skb is shared */
-	if (skb_shared(skb)) {
+	delta = SKB_DATA_ALIGN(delta);
+	/* pskb_expand_head() might crash, if skb is shared. */
+	if (skb_shared(skb) || !is_skb_wmem(skb)) {
 		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
 
-		if (likely(nskb)) {
-			if (skb->sk)
-				skb_set_owner_w(nskb, skb->sk);
-			consume_skb(skb);
-		} else {
-			kfree_skb(skb);
-		}
+		if (unlikely(!nskb))
+			goto fail;
+
+		if (sk)
+			skb_set_owner_w(nskb, sk);
+		consume_skb(skb);
 		skb = nskb;
 	}
-	if (skb &&
-	    pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
-		kfree_skb(skb);
-		skb = NULL;
+	if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC))
+		goto fail;
+
+	if (sk && is_skb_wmem(skb)) {
+		delta = skb_end_offset(skb) - osize;
+		refcount_add(delta, &sk->sk_wmem_alloc);
+		skb->truesize += delta;
 	}
 	return skb;
+
+fail:
+	kfree_skb(skb);
+	return NULL;
 }
 EXPORT_SYMBOL(skb_expand_head);
 
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2d6249b28928..a86ef7e844f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -474,6 +474,20 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 }
 EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
 
+bool sk_msg_is_readable(struct sock *sk)
+{
+	struct sk_psock *psock;
+	bool empty = true;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (likely(psock))
+		empty = list_empty(&psock->ingress_msg);
+	rcu_read_unlock();
+	return !empty;
+}
+EXPORT_SYMBOL_GPL(sk_msg_is_readable);
+
 static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
 						  struct sk_buff *skb)
 {
diff --git a/net/core/sock_destructor.h b/net/core/sock_destructor.h
new file mode 100644
index 000000000000..2f396e6bfba5
--- /dev/null
+++ b/net/core/sock_destructor.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _NET_CORE_SOCK_DESTRUCTOR_H
+#define _NET_CORE_SOCK_DESTRUCTOR_H
+#include <net/tcp.h>
+
+static inline bool is_skb_wmem(const struct sk_buff *skb)
+{
+	return skb->destructor == sock_wfree ||
+	       skb->destructor == __sock_wfree ||
+	       (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree);
+}
+#endif
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index c8496c1142c9..5f88526ad61c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -419,7 +419,7 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0600,
 		.proc_handler	= proc_dolongvec_minmax_bpf_restricted,
 		.extra1		= &long_one,
-		.extra2		= &long_max,
+		.extra2		= &bpf_jit_limit_max,
 	},
 #endif
 	{