Merge tag 'net-6.0-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - tcp: fix cleanup and leaks in tcp_read_skb() (the new way BPF
     socket maps get data out of the TCP stack)

   - tls: rx: react to strparser initialization errors

   - netfilter: nf_tables: fix scheduling-while-atomic splat

   - net: fix suspicious RCU usage in bpf_sk_reuseport_detach()

  Current release - new code bugs:

   - mlxsw: ptp: fix a couple of races, static checker warnings and
     error handling

  Previous releases - regressions:

   - netfilter:
      - nf_tables: fix possible module reference underflow in error path
      - make conntrack helpers deal with BIG TCP (skbs > 64kB)
      - nfnetlink: re-enable conntrack expectation events

   - net: fix potential refcount leak in ndisc_router_discovery()

  Previous releases - always broken:

   - sched: cls_route: disallow handle of 0

   - neigh: fix possible local DoS due to net iface start/stop loop

   - rtnetlink: fix module refcount leak in rtnetlink_rcv_msg

   - sched: fix adding qlen to qcpu->backlog in gnet_stats_add_queue_cpu

   - virtio_net: fix endian-ness for RSS

   - dsa: mv88e6060: prevent crash on an unused port

   - fec: fix timer capture timing in `fec_ptp_enable_pps()`

   - ocelot: stats: fix races, integer wrapping and reading incorrect
     registers (the change of register definitions here accounts for
     bulk of the changed LoC in this PR)"

* tag 'net-6.0-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (77 commits)
  net: moxa: MAC address reading, generating, validity checking
  tcp: handle pure FIN case correctly
  tcp: refactor tcp_read_skb() a bit
  tcp: fix tcp_cleanup_rbuf() for tcp_read_skb()
  tcp: fix sock skb accounting in tcp_read_skb()
  igb: Add lock to avoid data race
  dt-bindings: Fix incorrect "the the" corrections
  net: genl: fix error path memory leak in policy dumping
  stmmac: intel: Add a missing clk_disable_unprepare() call in intel_eth_pci_remove()
  net: ethernet: mtk_eth_soc: fix possible NULL pointer dereference in mtk_xdp_run
  net/mlx5e: Allocate flow steering storage during uplink initialization
  net: mscc: ocelot: report ndo_get_stats64 from the wraparound-resistant ocelot->stats
  net: mscc: ocelot: keep ocelot_stat_layout by reg address, not offset
  net: mscc: ocelot: make struct ocelot_stat_layout array indexable
  net: mscc: ocelot: fix race between ndo_get_stats64 and ocelot_check_stats_work
  net: mscc: ocelot: turn stats_lock into a spinlock
  net: mscc: ocelot: fix address of SYS_COUNT_TX_AGING counter
  net: mscc: ocelot: fix incorrect ndo_get_stats64 packet counters
  net: dsa: felix: fix ethtool 256-511 and 512-1023 TX packet counters
  net: dsa: don't warn in dsa_port_set_state_now() when driver doesn't support it
  ...

4 files changed, 191 insertions, 16 deletions

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 9f0bab0589d9..3827a6b395fd 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -83,6 +83,7 @@ struct neigh_parms {
 	struct rcu_head rcu_head;
 
 	int	reachable_time;
+	int	qlen;
 	int	data[NEIGH_VAR_DATA_MAX];
 	DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX);
 };
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 0677cd3de034..c396a3862e80 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -95,7 +95,7 @@ struct nf_ip_net {
 
 struct netns_ct {
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-	bool ctnetlink_has_listener;
+	u8 ctnetlink_has_listener;
 	bool ecache_dwork_pending;
 #endif
 	u8			sysctl_log_invalid; /* Log invalid packets */
diff --git a/include/net/sock.h b/include/net/sock.h
index 05a1bbdf5805..d08cfe190a78 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -578,6 +578,31 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk)
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
 
 /**
+ * __locked_read_sk_user_data_with_flags - return the pointer
+ * only if argument flags all has been set in sk_user_data. Otherwise
+ * return NULL
+ *
+ * @sk: socket
+ * @flags: flag bits
+ *
+ * The caller must be holding sk->sk_callback_lock.
+ */
+static inline void *
+__locked_read_sk_user_data_with_flags(const struct sock *sk,
+				      uintptr_t flags)
+{
+	uintptr_t sk_user_data =
+		(uintptr_t)rcu_dereference_check(__sk_user_data(sk),
+						 lockdep_is_held(&sk->sk_callback_lock));
+
+	WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK);
+
+	if ((sk_user_data & flags) == flags)
+		return (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
+	return NULL;
+}
+
+/**
  * __rcu_dereference_sk_user_data_with_flags - return the pointer
  * only if argument flags all has been set in sk_user_data. Otherwise
  * return NULL
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index ac151ecc7f19..2edea901bbd5 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -105,11 +105,6 @@
 #define REG_RESERVED_ADDR		0xffffffff
 #define REG_RESERVED(reg)		REG(reg, REG_RESERVED_ADDR)
 
-#define for_each_stat(ocelot, stat)				\
-	for ((stat) = (ocelot)->stats_layout;			\
-	     ((stat)->name[0] != '\0');				\
-	     (stat)++)
-
 enum ocelot_target {
 	ANA = 1,
 	QS,
@@ -335,13 +330,38 @@ enum ocelot_reg {
 	SYS_COUNT_RX_64,
 	SYS_COUNT_RX_65_127,
 	SYS_COUNT_RX_128_255,
-	SYS_COUNT_RX_256_1023,
+	SYS_COUNT_RX_256_511,
+	SYS_COUNT_RX_512_1023,
 	SYS_COUNT_RX_1024_1526,
 	SYS_COUNT_RX_1527_MAX,
 	SYS_COUNT_RX_PAUSE,
 	SYS_COUNT_RX_CONTROL,
 	SYS_COUNT_RX_LONGS,
 	SYS_COUNT_RX_CLASSIFIED_DROPS,
+	SYS_COUNT_RX_RED_PRIO_0,
+	SYS_COUNT_RX_RED_PRIO_1,
+	SYS_COUNT_RX_RED_PRIO_2,
+	SYS_COUNT_RX_RED_PRIO_3,
+	SYS_COUNT_RX_RED_PRIO_4,
+	SYS_COUNT_RX_RED_PRIO_5,
+	SYS_COUNT_RX_RED_PRIO_6,
+	SYS_COUNT_RX_RED_PRIO_7,
+	SYS_COUNT_RX_YELLOW_PRIO_0,
+	SYS_COUNT_RX_YELLOW_PRIO_1,
+	SYS_COUNT_RX_YELLOW_PRIO_2,
+	SYS_COUNT_RX_YELLOW_PRIO_3,
+	SYS_COUNT_RX_YELLOW_PRIO_4,
+	SYS_COUNT_RX_YELLOW_PRIO_5,
+	SYS_COUNT_RX_YELLOW_PRIO_6,
+	SYS_COUNT_RX_YELLOW_PRIO_7,
+	SYS_COUNT_RX_GREEN_PRIO_0,
+	SYS_COUNT_RX_GREEN_PRIO_1,
+	SYS_COUNT_RX_GREEN_PRIO_2,
+	SYS_COUNT_RX_GREEN_PRIO_3,
+	SYS_COUNT_RX_GREEN_PRIO_4,
+	SYS_COUNT_RX_GREEN_PRIO_5,
+	SYS_COUNT_RX_GREEN_PRIO_6,
+	SYS_COUNT_RX_GREEN_PRIO_7,
 	SYS_COUNT_TX_OCTETS,
 	SYS_COUNT_TX_UNICAST,
 	SYS_COUNT_TX_MULTICAST,
@@ -351,11 +371,46 @@ enum ocelot_reg {
 	SYS_COUNT_TX_PAUSE,
 	SYS_COUNT_TX_64,
 	SYS_COUNT_TX_65_127,
-	SYS_COUNT_TX_128_511,
+	SYS_COUNT_TX_128_255,
+	SYS_COUNT_TX_256_511,
 	SYS_COUNT_TX_512_1023,
 	SYS_COUNT_TX_1024_1526,
 	SYS_COUNT_TX_1527_MAX,
+	SYS_COUNT_TX_YELLOW_PRIO_0,
+	SYS_COUNT_TX_YELLOW_PRIO_1,
+	SYS_COUNT_TX_YELLOW_PRIO_2,
+	SYS_COUNT_TX_YELLOW_PRIO_3,
+	SYS_COUNT_TX_YELLOW_PRIO_4,
+	SYS_COUNT_TX_YELLOW_PRIO_5,
+	SYS_COUNT_TX_YELLOW_PRIO_6,
+	SYS_COUNT_TX_YELLOW_PRIO_7,
+	SYS_COUNT_TX_GREEN_PRIO_0,
+	SYS_COUNT_TX_GREEN_PRIO_1,
+	SYS_COUNT_TX_GREEN_PRIO_2,
+	SYS_COUNT_TX_GREEN_PRIO_3,
+	SYS_COUNT_TX_GREEN_PRIO_4,
+	SYS_COUNT_TX_GREEN_PRIO_5,
+	SYS_COUNT_TX_GREEN_PRIO_6,
+	SYS_COUNT_TX_GREEN_PRIO_7,
 	SYS_COUNT_TX_AGING,
+	SYS_COUNT_DROP_LOCAL,
+	SYS_COUNT_DROP_TAIL,
+	SYS_COUNT_DROP_YELLOW_PRIO_0,
+	SYS_COUNT_DROP_YELLOW_PRIO_1,
+	SYS_COUNT_DROP_YELLOW_PRIO_2,
+	SYS_COUNT_DROP_YELLOW_PRIO_3,
+	SYS_COUNT_DROP_YELLOW_PRIO_4,
+	SYS_COUNT_DROP_YELLOW_PRIO_5,
+	SYS_COUNT_DROP_YELLOW_PRIO_6,
+	SYS_COUNT_DROP_YELLOW_PRIO_7,
+	SYS_COUNT_DROP_GREEN_PRIO_0,
+	SYS_COUNT_DROP_GREEN_PRIO_1,
+	SYS_COUNT_DROP_GREEN_PRIO_2,
+	SYS_COUNT_DROP_GREEN_PRIO_3,
+	SYS_COUNT_DROP_GREEN_PRIO_4,
+	SYS_COUNT_DROP_GREEN_PRIO_5,
+	SYS_COUNT_DROP_GREEN_PRIO_6,
+	SYS_COUNT_DROP_GREEN_PRIO_7,
 	SYS_RESET_CFG,
 	SYS_SR_ETYPE_CFG,
 	SYS_VLAN_ETYPE_CFG,
@@ -538,16 +593,111 @@ enum ocelot_ptp_pins {
 	TOD_ACC_PIN
 };
 
+enum ocelot_stat {
+	OCELOT_STAT_RX_OCTETS,
+	OCELOT_STAT_RX_UNICAST,
+	OCELOT_STAT_RX_MULTICAST,
+	OCELOT_STAT_RX_BROADCAST,
+	OCELOT_STAT_RX_SHORTS,
+	OCELOT_STAT_RX_FRAGMENTS,
+	OCELOT_STAT_RX_JABBERS,
+	OCELOT_STAT_RX_CRC_ALIGN_ERRS,
+	OCELOT_STAT_RX_SYM_ERRS,
+	OCELOT_STAT_RX_64,
+	OCELOT_STAT_RX_65_127,
+	OCELOT_STAT_RX_128_255,
+	OCELOT_STAT_RX_256_511,
+	OCELOT_STAT_RX_512_1023,
+	OCELOT_STAT_RX_1024_1526,
+	OCELOT_STAT_RX_1527_MAX,
+	OCELOT_STAT_RX_PAUSE,
+	OCELOT_STAT_RX_CONTROL,
+	OCELOT_STAT_RX_LONGS,
+	OCELOT_STAT_RX_CLASSIFIED_DROPS,
+	OCELOT_STAT_RX_RED_PRIO_0,
+	OCELOT_STAT_RX_RED_PRIO_1,
+	OCELOT_STAT_RX_RED_PRIO_2,
+	OCELOT_STAT_RX_RED_PRIO_3,
+	OCELOT_STAT_RX_RED_PRIO_4,
+	OCELOT_STAT_RX_RED_PRIO_5,
+	OCELOT_STAT_RX_RED_PRIO_6,
+	OCELOT_STAT_RX_RED_PRIO_7,
+	OCELOT_STAT_RX_YELLOW_PRIO_0,
+	OCELOT_STAT_RX_YELLOW_PRIO_1,
+	OCELOT_STAT_RX_YELLOW_PRIO_2,
+	OCELOT_STAT_RX_YELLOW_PRIO_3,
+	OCELOT_STAT_RX_YELLOW_PRIO_4,
+	OCELOT_STAT_RX_YELLOW_PRIO_5,
+	OCELOT_STAT_RX_YELLOW_PRIO_6,
+	OCELOT_STAT_RX_YELLOW_PRIO_7,
+	OCELOT_STAT_RX_GREEN_PRIO_0,
+	OCELOT_STAT_RX_GREEN_PRIO_1,
+	OCELOT_STAT_RX_GREEN_PRIO_2,
+	OCELOT_STAT_RX_GREEN_PRIO_3,
+	OCELOT_STAT_RX_GREEN_PRIO_4,
+	OCELOT_STAT_RX_GREEN_PRIO_5,
+	OCELOT_STAT_RX_GREEN_PRIO_6,
+	OCELOT_STAT_RX_GREEN_PRIO_7,
+	OCELOT_STAT_TX_OCTETS,
+	OCELOT_STAT_TX_UNICAST,
+	OCELOT_STAT_TX_MULTICAST,
+	OCELOT_STAT_TX_BROADCAST,
+	OCELOT_STAT_TX_COLLISION,
+	OCELOT_STAT_TX_DROPS,
+	OCELOT_STAT_TX_PAUSE,
+	OCELOT_STAT_TX_64,
+	OCELOT_STAT_TX_65_127,
+	OCELOT_STAT_TX_128_255,
+	OCELOT_STAT_TX_256_511,
+	OCELOT_STAT_TX_512_1023,
+	OCELOT_STAT_TX_1024_1526,
+	OCELOT_STAT_TX_1527_MAX,
+	OCELOT_STAT_TX_YELLOW_PRIO_0,
+	OCELOT_STAT_TX_YELLOW_PRIO_1,
+	OCELOT_STAT_TX_YELLOW_PRIO_2,
+	OCELOT_STAT_TX_YELLOW_PRIO_3,
+	OCELOT_STAT_TX_YELLOW_PRIO_4,
+	OCELOT_STAT_TX_YELLOW_PRIO_5,
+	OCELOT_STAT_TX_YELLOW_PRIO_6,
+	OCELOT_STAT_TX_YELLOW_PRIO_7,
+	OCELOT_STAT_TX_GREEN_PRIO_0,
+	OCELOT_STAT_TX_GREEN_PRIO_1,
+	OCELOT_STAT_TX_GREEN_PRIO_2,
+	OCELOT_STAT_TX_GREEN_PRIO_3,
+	OCELOT_STAT_TX_GREEN_PRIO_4,
+	OCELOT_STAT_TX_GREEN_PRIO_5,
+	OCELOT_STAT_TX_GREEN_PRIO_6,
+	OCELOT_STAT_TX_GREEN_PRIO_7,
+	OCELOT_STAT_TX_AGED,
+	OCELOT_STAT_DROP_LOCAL,
+	OCELOT_STAT_DROP_TAIL,
+	OCELOT_STAT_DROP_YELLOW_PRIO_0,
+	OCELOT_STAT_DROP_YELLOW_PRIO_1,
+	OCELOT_STAT_DROP_YELLOW_PRIO_2,
+	OCELOT_STAT_DROP_YELLOW_PRIO_3,
+	OCELOT_STAT_DROP_YELLOW_PRIO_4,
+	OCELOT_STAT_DROP_YELLOW_PRIO_5,
+	OCELOT_STAT_DROP_YELLOW_PRIO_6,
+	OCELOT_STAT_DROP_YELLOW_PRIO_7,
+	OCELOT_STAT_DROP_GREEN_PRIO_0,
+	OCELOT_STAT_DROP_GREEN_PRIO_1,
+	OCELOT_STAT_DROP_GREEN_PRIO_2,
+	OCELOT_STAT_DROP_GREEN_PRIO_3,
+	OCELOT_STAT_DROP_GREEN_PRIO_4,
+	OCELOT_STAT_DROP_GREEN_PRIO_5,
+	OCELOT_STAT_DROP_GREEN_PRIO_6,
+	OCELOT_STAT_DROP_GREEN_PRIO_7,
+	OCELOT_NUM_STATS,
+};
+
 struct ocelot_stat_layout {
-	u32 offset;
+	u32 reg;
 	char name[ETH_GSTRING_LEN];
 };
 
-#define OCELOT_STAT_END { .name = "" }
-
 struct ocelot_stats_region {
 	struct list_head node;
-	u32 offset;
+	u32 base;
 	int count;
 	u32 *buf;
 };
@@ -707,7 +857,6 @@ struct ocelot {
 	const u32 *const		*map;
 	const struct ocelot_stat_layout	*stats_layout;
 	struct list_head		stats_regions;
-	unsigned int			num_stats;
 
 	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
 	int				packet_buffer_size;
@@ -750,7 +899,7 @@ struct ocelot {
 	struct ocelot_psfp_list		psfp;
 
 	/* Workqueue to check statistics for overflow with its lock */
-	struct mutex			stats_lock;
+	spinlock_t			stats_lock;
 	u64				*stats;
 	struct delayed_work		stats_work;
 	struct workqueue_struct		*stats_queue;
@@ -786,8 +935,8 @@ struct ocelot_policer {
 	u32 burst; /* bytes */
 };
 
-#define ocelot_bulk_read_rix(ocelot, reg, ri, buf, count) \
-	__ocelot_bulk_read_ix(ocelot, reg, reg##_RSZ * (ri), buf, count)
+#define ocelot_bulk_read(ocelot, reg, buf, count) \
+	__ocelot_bulk_read_ix(ocelot, reg, 0, buf, count)
 
 #define ocelot_read_ix(ocelot, reg, gi, ri) \
 	__ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))