Merge tag 'net-7.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull  networking fixes from Jakub Kicinski:
 "Including fixes from Netfilter.

  Steady stream of fixes. Last two weeks feel comparable to the two
  weeks before the merge window. Lots of AI-aided bug discovery. A newer
  big source is Sashiko/Gemini (Roman Gushchin's system), which points
  out issues in existing code during patch review (maybe 25% of fixes
  here likely originating from Sashiko). Nice thing is these are often
  fixed by the respective maintainers, not drive-bys.

  Current release - new code bugs:

   - kconfig: MDIO_PIC64HPSC should depend on ARCH_MICROCHIP

  Previous releases - regressions:

   - add async ndo_set_rx_mode and switch drivers which we promised to
     be called under the per-netdev mutex to it

   - dsa: remove duplicate netdev_lock_ops() for conduit ethtool ops

   - hv_sock: report EOF instead of -EIO for FIN

   - vsock/virtio: fix MSG_PEEK calculation on bytes to copy

  Previous releases - always broken:

   - ipv6: fix possible UAF in icmpv6_rcv()

   - icmp: validate reply type before using icmp_pointers

   - af_unix: drop all SCM attributes for SOCKMAP

   - netfilter: fix a number of bugs in the osf (OS fingerprinting)

   - eth: intel: fix timestamp interrupt configuration for E825C

  Misc:

   - bunch of data-race annotations"

* tag 'net-7.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (148 commits)
  rxrpc: Fix error handling in rxgk_extract_token()
  rxrpc: Fix re-decryption of RESPONSE packets
  rxrpc: Fix rxrpc_input_call_event() to only unshare DATA packets
  rxrpc: Fix missing validation of ticket length in non-XDR key preparsing
  rxgk: Fix potential integer overflow in length check
  rxrpc: Fix conn-level packet handling to unshare RESPONSE packets
  rxrpc: Fix potential UAF after skb_unshare() failure
  rxrpc: Fix rxkad crypto unalignment handling
  rxrpc: Fix memory leaks in rxkad_verify_response()
  net: rds: fix MR cleanup on copy error
  m68k: mvme147: Make me the maintainer
  net: txgbe: fix firmware version check
  selftests/bpf: check epoll readiness during reuseport migration
  tcp: call sk_data_ready() after listener migration
  vhost_net: fix sleeping with preempt-disabled in vhost_net_busy_poll()
  ipv6: Cap TLV scan in ip6_tnl_parse_tlv_enc_lim
  tipc: fix double-free in tipc_buf_append()
  llc: Return -EINPROGRESS from llc_ui_connect()
  ipv4: icmp: validate reply type before using icmp_pointers
  selftests/net: packetdrill: cover RFC 5961 5.2 challenge ACK on both edges
  ...

10 files changed, 87 insertions, 20 deletions

diff --git a/include/linux/fsl/ntmp.h b/include/linux/fsl/ntmp.h
index 916dc4fe7de3..83a449b4d6ec 100644
--- a/include/linux/fsl/ntmp.h
+++ b/include/linux/fsl/ntmp.h
@@ -31,6 +31,12 @@ struct netc_tbl_vers {
 	u8 rsst_ver;
 };
 
+struct netc_swcbd {
+	void *buf;
+	dma_addr_t dma;
+	size_t size;
+};
+
 struct netc_cbdr {
 	struct device *dev;
 	struct netc_cbdr_regs regs;
@@ -44,9 +50,10 @@ struct netc_cbdr {
 	void *addr_base_align;
 	dma_addr_t dma_base;
 	dma_addr_t dma_base_align;
+	struct netc_swcbd *swcbd;
 
 	/* Serialize the order of command BD ring */
-	spinlock_t ring_lock;
+	struct mutex ring_lock;
 };
 
 struct ntmp_user {
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index e6272f9c5e42..20cc16ea4e5a 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -147,11 +147,13 @@ extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
  *	@priority: skb priority
  *	@vlan_qos: vlan priority: (skb->priority << 13) & 0xE000
  *	@next: pointer to next struct
+ *	@rcu: used for deferred freeing of mapping nodes
  */
 struct vlan_priority_tci_mapping {
 	u32					priority;
 	u16					vlan_qos;
-	struct vlan_priority_tci_mapping	*next;
+	struct vlan_priority_tci_mapping __rcu	*next;
+	struct rcu_head			rcu;
 };
 
 struct proc_dir_entry;
@@ -177,7 +179,7 @@ struct vlan_dev_priv {
 	unsigned int				nr_ingress_mappings;
 	u32					ingress_priority_map[8];
 	unsigned int				nr_egress_mappings;
-	struct vlan_priority_tci_mapping	*egress_priority_map[16];
+	struct vlan_priority_tci_mapping __rcu	*egress_priority_map[16];
 
 	__be16					vlan_proto;
 	u16					vlan_id;
@@ -209,19 +211,24 @@ static inline u16
 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
 {
 	struct vlan_priority_tci_mapping *mp;
+	u16 vlan_qos = 0;
 
-	smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */
+	rcu_read_lock();
 
-	mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)];
+	mp = rcu_dereference(vlan_dev_priv(dev)->egress_priority_map[skprio & 0xF]);
 	while (mp) {
 		if (mp->priority == skprio) {
-			return mp->vlan_qos; /* This should already be shifted
-					      * to mask correctly with the
-					      * VLAN's TCI */
+			vlan_qos = READ_ONCE(mp->vlan_qos);
+			break;
 		}
-		mp = mp->next;
+		mp = rcu_dereference(mp->next);
 	}
-	return 0;
+	rcu_read_unlock();
+
+	/* This should already be shifted to mask correctly with
+	 * the VLAN's TCI.
+	 */
+	return vlan_qos;
 }
 
 extern bool vlan_do_receive(struct sk_buff **skb);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7969fcdd5ac4..97b435da5771 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1119,6 +1119,16 @@ struct netdev_net_notifier {
  *	This function is called device changes address list filtering.
  *	If driver handles unicast address filtering, it should set
  *	IFF_UNICAST_FLT in its priv_flags.
+ *	Cannot sleep, called with netif_addr_lock_bh held.
+ *	Deprecated in favor of ndo_set_rx_mode_async.
+ *
+ * void (*ndo_set_rx_mode_async)(struct net_device *dev,
+ *				 struct netdev_hw_addr_list *uc,
+ *				 struct netdev_hw_addr_list *mc);
+ *	Async version of ndo_set_rx_mode which runs in process context
+ *	with rtnl_lock and netdev_lock_ops(dev) held. The uc/mc parameters
+ *	are snapshots of the address lists - iterate with
+ *	netdev_hw_addr_list_for_each(ha, uc).
  *
  * int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
  *	This function  is called when the Media Access Control address
@@ -1439,6 +1449,10 @@ struct net_device_ops {
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
+	void			(*ndo_set_rx_mode_async)(
+					struct net_device *dev,
+					struct netdev_hw_addr_list *uc,
+					struct netdev_hw_addr_list *mc);
 	int			(*ndo_set_mac_address)(struct net_device *dev,
 						       void *addr);
 	int			(*ndo_validate_addr)(struct net_device *dev);
@@ -1903,6 +1917,9 @@ enum netdev_reg_state {
  *				has been enabled due to the need to listen to
  *				additional unicast addresses in a device that
  *				does not implement ndo_set_rx_mode()
+ *	@rx_mode_node:		List entry for rx_mode work processing
+ *	@rx_mode_tracker:	Refcount tracker for rx_mode work
+ *	@rx_mode_addr_cache:	Recycled snapshot entries for rx_mode work
  *	@uc:			unicast mac addresses
  *	@mc:			multicast mac addresses
  *	@dev_addrs:		list of device hw addresses
@@ -2294,6 +2311,9 @@ struct net_device {
 	unsigned int		promiscuity;
 	unsigned int		allmulti;
 	bool			uc_promisc;
+	struct list_head	rx_mode_node;
+	netdevice_tracker	rx_mode_tracker;
+	struct netdev_hw_addr_list	rx_mode_addr_cache;
 #ifdef CONFIG_LOCKDEP
 	unsigned char		nested_level;
 #endif
@@ -5004,6 +5024,14 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
 			  int (*unsync)(struct net_device *,
 					const unsigned char *));
 void __hw_addr_init(struct netdev_hw_addr_list *list);
+void __hw_addr_flush(struct netdev_hw_addr_list *list);
+int __hw_addr_list_snapshot(struct netdev_hw_addr_list *snap,
+			    const struct netdev_hw_addr_list *list,
+			    int addr_len, struct netdev_hw_addr_list *cache);
+void __hw_addr_list_reconcile(struct netdev_hw_addr_list *real_list,
+			      struct netdev_hw_addr_list *work,
+			      struct netdev_hw_addr_list *ref, int addr_len,
+			      struct netdev_hw_addr_list *cache);
 
 /* Functions used for device addresses handling */
 void dev_addr_mod(struct net_device *dev, unsigned int offset,
diff --git a/include/linux/ppp_defs.h b/include/linux/ppp_defs.h
index b7e57fdbd413..b1d1f46d7d3b 100644
--- a/include/linux/ppp_defs.h
+++ b/include/linux/ppp_defs.h
@@ -8,6 +8,7 @@
 #define _PPP_DEFS_H_
 
 #include <linux/crc-ccitt.h>
+#include <linux/skbuff.h>
 #include <uapi/linux/ppp_defs.h>
 
 #define PPP_FCS(fcs, c) crc_ccitt_byte(fcs, c)
@@ -25,4 +26,19 @@ static inline bool ppp_proto_is_valid(u16 proto)
 	return !!((proto & 0x0101) == 0x0001);
 }
 
+/**
+ * ppp_skb_is_compressed_proto - checks if PPP protocol in a skb is compressed
+ * @skb: skb to check
+ *
+ * Check if the PPP protocol field is compressed (the least significant
+ * bit of the most significant octet is 1). skb->data must point to the PPP
+ * protocol header.
+ *
+ * Return: Whether the PPP protocol field is compressed.
+ */
+static inline bool ppp_skb_is_compressed_proto(const struct sk_buff *skb)
+{
+	return unlikely(skb->data[0] & 0x01);
+}
+
 #endif /* _PPP_DEFS_H_ */
diff --git a/include/net/mctp.h b/include/net/mctp.h
index e1e0a69afdce..d8bf9074110d 100644
--- a/include/net/mctp.h
+++ b/include/net/mctp.h
@@ -26,6 +26,9 @@ struct mctp_hdr {
 #define MCTP_VER_MIN	1
 #define MCTP_VER_MAX	1
 
+/* Definitions for ver field */
+#define MCTP_HDR_VER_MASK	GENMASK(3, 0)
+
 /* Definitions for flags_seq_tag field */
 #define MCTP_HDR_FLAG_SOM	BIT(7)
 #define MCTP_HDR_FLAG_EOM	BIT(6)
diff --git a/include/net/pie.h b/include/net/pie.h
index 01cbc66825a4..1f3db0c35514 100644
--- a/include/net/pie.h
+++ b/include/net/pie.h
@@ -104,7 +104,7 @@ static inline void pie_vars_init(struct pie_vars *vars)
 	vars->dq_tstamp = DTIME_INVALID;
 	vars->accu_prob = 0;
 	vars->dq_count = DQCOUNT_INVALID;
-	vars->avg_dq_rate = 0;
+	WRITE_ONCE(vars->avg_dq_rate, 0);
 }
 
 static inline struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index dfa52ceefd23..ecbadcb3a744 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1513,7 +1513,7 @@ static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp)
 static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val)
 {
 	WARN_ON_ONCE((int)val <= 0);
-	tp->snd_cwnd = val;
+	WRITE_ONCE(tp->snd_cwnd, val);
 }
 
 static inline bool tcp_in_slow_start(const struct tcp_sock *tp)
@@ -2208,10 +2208,14 @@ static inline void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new
 	const u32 now = tcp_jiffies32;
 	enum tcp_chrono old = tp->chrono_type;
 
+	/* Following WRITE_ONCE()s pair with READ_ONCE()s in
+	 * tcp_get_info_chrono_stats().
+	 */
 	if (old > TCP_CHRONO_UNSPEC)
-		tp->chrono_stat[old - 1] += now - tp->chrono_start;
-	tp->chrono_start = now;
-	tp->chrono_type = new;
+		WRITE_ONCE(tp->chrono_stat[old - 1],
+			   tp->chrono_stat[old - 1] + now - tp->chrono_start);
+	WRITE_ONCE(tp->chrono_start, now);
+	WRITE_ONCE(tp->chrono_type, new);
 }
 
 static inline void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type)
diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h
index e9a933641636..865d5c5a7718 100644
--- a/include/net/tcp_ecn.h
+++ b/include/net/tcp_ecn.h
@@ -181,7 +181,7 @@ static inline void tcp_accecn_third_ack(struct sock *sk,
 		    tcp_accecn_validate_syn_feedback(sk, ace, sent_ect)) {
 			if ((tcp_accecn_extract_syn_ect(ace) == INET_ECN_CE) &&
 			    !tp->delivered_ce)
-				tp->delivered_ce++;
+				WRITE_ONCE(tp->delivered_ce, 1);
 		}
 		break;
 	}
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index fdd9ad474ce3..dbc2c5598e35 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -10,6 +10,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/tracepoint.h>
+#include <net/busy_poll.h>
 
 TRACE_EVENT(net_dev_start_xmit,
 
@@ -208,7 +209,8 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template,
 	TP_fast_assign(
 		__assign_str(name);
 #ifdef CONFIG_NET_RX_BUSY_POLL
-		__entry->napi_id = skb->napi_id;
+		__entry->napi_id = napi_id_valid(skb->napi_id) ?
+				   skb->napi_id : 0;
 #else
 		__entry->napi_id = 0;
 #endif
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 578b8038b211..573f2df3a2c9 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -37,6 +37,7 @@
 	EM(rxkad_abort_1_short_encdata,		"rxkad1-short-encdata")	\
 	EM(rxkad_abort_1_short_header,		"rxkad1-short-hdr")	\
 	EM(rxkad_abort_2_short_check,		"rxkad2-short-check")	\
+	EM(rxkad_abort_2_crypto_unaligned,	"rxkad2-crypto-unaligned") \
 	EM(rxkad_abort_2_short_data,		"rxkad2-short-data")	\
 	EM(rxkad_abort_2_short_header,		"rxkad2-short-hdr")	\
 	EM(rxkad_abort_2_short_len,		"rxkad2-short-len")	\
@@ -161,8 +162,6 @@
 	E_(rxrpc_call_poke_timer_now,		"Timer-now")
 
 #define rxrpc_skb_traces \
-	EM(rxrpc_skb_eaten_by_unshare,		"ETN unshare  ") \
-	EM(rxrpc_skb_eaten_by_unshare_nomem,	"ETN unshar-nm") \
 	EM(rxrpc_skb_get_call_rx,		"GET call-rx  ") \
 	EM(rxrpc_skb_get_conn_secured,		"GET conn-secd") \
 	EM(rxrpc_skb_get_conn_work,		"GET conn-work") \
@@ -189,6 +188,7 @@
 	EM(rxrpc_skb_put_purge,			"PUT purge    ") \
 	EM(rxrpc_skb_put_purge_oob,		"PUT purge-oob") \
 	EM(rxrpc_skb_put_response,		"PUT response ") \
+	EM(rxrpc_skb_put_response_copy,		"PUT resp-cpy ") \
 	EM(rxrpc_skb_put_rotate,		"PUT rotate   ") \
 	EM(rxrpc_skb_put_unknown,		"PUT unknown  ") \
 	EM(rxrpc_skb_see_conn_work,		"SEE conn-work") \
@@ -197,6 +197,7 @@
 	EM(rxrpc_skb_see_recvmsg_oob,		"SEE recvm-oob") \
 	EM(rxrpc_skb_see_reject,		"SEE reject   ") \
 	EM(rxrpc_skb_see_rotate,		"SEE rotate   ") \
+	EM(rxrpc_skb_see_unshare_nomem,		"SEE unshar-nm") \
 	E_(rxrpc_skb_see_version,		"SEE version  ")
 
 #define rxrpc_local_traces \
@@ -284,7 +285,6 @@
 	EM(rxrpc_conn_put_unidle,		"PUT unidle  ") \
 	EM(rxrpc_conn_put_work,			"PUT work    ") \
 	EM(rxrpc_conn_queue_challenge,		"QUE chall   ") \
-	EM(rxrpc_conn_queue_retry_work,		"QUE retry-wk") \
 	EM(rxrpc_conn_queue_rx_work,		"QUE rx-work ") \
 	EM(rxrpc_conn_see_new_service_conn,	"SEE new-svc ") \
 	EM(rxrpc_conn_see_reap_service,		"SEE reap-svc") \