Merge tag 'net-5.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.13-rc4, including fixes from bpf, netfilter,
  can and wireless trees. Notably including fixes for the recently
  announced "FragAttacks" WiFi vulnerabilities. Rather large batch,
  touching some core parts of the stack, too, but nothing hair-raising.

  Current release - regressions:

   - tipc: make node link identity publish thread safe

   - dsa: felix: re-enable TAS guard band mode

   - stmmac: correct clocks enabled in stmmac_vlan_rx_kill_vid()

   - stmmac: fix system hang if change mac address after interface
     ifdown

  Current release - new code bugs:

   - mptcp: avoid OOB access in setsockopt()

   - bpf: Fix nested bpf_bprintf_prepare with more per-cpu buffers

   - ethtool: stats: fix a copy-paste error - init correct array size

  Previous releases - regressions:

   - sched: fix packet stuck problem for lockless qdisc

   - net: really orphan skbs tied to closing sk

   - mlx4: fix EEPROM dump support

   - bpf: fix alu32 const subreg bound tracking on bitwise operations

   - bpf: fix mask direction swap upon off reg sign change

   - bpf, offload: reorder offload callback 'prepare' in verifier

   - stmmac: Fix MAC WoL not working if PHY does not support WoL

   - packetmmap: fix only tx timestamp on request

   - tipc: skb_linearize the head skb when reassembling msgs

  Previous releases - always broken:

   - mac80211: address recent "FragAttacks" vulnerabilities

   - mac80211: do not accept/forward invalid EAPOL frames

   - mptcp: avoid potential error message floods

   - bpf, ringbuf: deny reserve of buffers larger than ringbuf to
     prevent out of buffer writes

   - bpf: forbid trampoline attach for functions with variable arguments

   - bpf: add deny list of functions to prevent inf recursion of tracing
     programs

   - tls splice: check SPLICE_F_NONBLOCK instead of MSG_DONTWAIT

   - can: isotp: prevent race between isotp_bind() and
     isotp_setsockopt()

   - netfilter: nft_set_pipapo_avx2: Add irq_fpu_usable() check,
     fallback to non-AVX2 version

  Misc:

   - bpf: add kconfig knob for disabling unpriv bpf by default"

* tag 'net-5.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (172 commits)
  net: phy: Document phydev::dev_flags bits allocation
  mptcp: validate 'id' when stopping the ADD_ADDR retransmit timer
  mptcp: avoid error message on infinite mapping
  mptcp: drop unconditional pr_warn on bad opt
  mptcp: avoid OOB access in setsockopt()
  nfp: update maintainer and mailing list addresses
  net: mvpp2: add buffer header handling in RX
  bnx2x: Fix missing error code in bnx2x_iov_init_one()
  net: zero-initialize tc skb extension on allocation
  net: hns: Fix kernel-doc
  sctp: fix the proc_handler for sysctl encap_port
  sctp: add the missing setting for asoc encap_port
  bpf, selftests: Adjust few selftest result_unpriv outcomes
  bpf: No need to simulate speculative domain for immediates
  bpf: Fix mask direction swap upon off reg sign change
  bpf: Wrap aux data inside bpf_sanitize_info container
  bpf: Fix BPF_LSM kconfig symbol dependency
  selftests/bpf: Add test for l3 use of bpf_redirect_peer
  bpftool: Add sock_release help info for cgroup attach/prog load command
  net: dsa: microchip: enable phy errata workaround on 9567
  ...

10 files changed, 97 insertions, 33 deletions

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f8e8d7e90616..020a8f7fdbdd 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -703,6 +703,27 @@ struct mlx5_hv_vhca;
 #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity))
 #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))
 
+enum {
+	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
+	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
+};
+
+enum {
+	MR_CACHE_LAST_STD_ENTRY = 20,
+	MLX5_IMR_MTT_CACHE_ENTRY,
+	MLX5_IMR_KSM_CACHE_ENTRY,
+	MAX_MR_CACHE_ENTRIES
+};
+
+struct mlx5_profile {
+	u64	mask;
+	u8	log_max_qp;
+	struct {
+		int	size;
+		int	limit;
+	} mr_cache[MAX_MR_CACHE_ENTRIES];
+};
+
 struct mlx5_core_dev {
 	struct device *device;
 	enum mlx5_coredev_type coredev_type;
@@ -731,7 +752,7 @@ struct mlx5_core_dev {
 	struct mutex		intf_state_mutex;
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
-	struct mlx5_profile	*profile;
+	struct mlx5_profile	profile;
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
 	struct mlx5_dm          *dm;
@@ -1083,18 +1104,6 @@ static inline u8 mlx5_mkey_variant(u32 mkey)
 	return mkey & 0xff;
 }
 
-enum {
-	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
-	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
-};
-
-enum {
-	MR_CACHE_LAST_STD_ENTRY = 20,
-	MLX5_IMR_MTT_CACHE_ENTRY,
-	MLX5_IMR_KSM_CACHE_ENTRY,
-	MAX_MR_CACHE_ENTRIES
-};
-
 /* Async-atomic event notifier used by mlx5 core to forward FW
  * evetns recived from event queue to mlx5 consumers.
  * Optimise event queue dipatching.
@@ -1148,15 +1157,6 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev,
 			    struct ib_device *device,
 			    struct rdma_netdev_alloc_params *params);
 
-struct mlx5_profile {
-	u64	mask;
-	u8	log_max_qp;
-	struct {
-		int	size;
-		int	limit;
-	} mr_cache[MAX_MR_CACHE_ENTRIES];
-};
-
 enum {
 	MLX5_PCI_DEV_IS_VF		= 1 << 0,
 };
diff --git a/include/linux/mlx5/mpfs.h b/include/linux/mlx5/mpfs.h
new file mode 100644
index 000000000000..bf700c8d5516
--- /dev/null
+++ b/include/linux/mlx5/mpfs.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+ * Copyright (c) 2021 Mellanox Technologies Ltd.
+ */
+
+#ifndef _MLX5_MPFS_
+#define _MLX5_MPFS_
+
+struct mlx5_core_dev;
+
+#ifdef CONFIG_MLX5_MPFS
+int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac);
+int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac);
+#else /* #ifndef CONFIG_MLX5_MPFS */
+static inline int  mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
+static inline int  mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; }
+#endif
+
+#endif
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 60d2b26026a2..852743f07e3e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -496,6 +496,11 @@ struct macsec_ops;
  * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY
  * @state: State of the PHY for management purposes
  * @dev_flags: Device-specific flags used by the PHY driver.
+ *		Bits [15:0] are free to use by the PHY driver to communicate
+ *			    driver specific behavior.
+ *		Bits [23:16] are currently reserved for future use.
+ *		Bits [31:24] are reserved for defining generic
+ *			     PHY driver behavior.
  * @irq: IRQ number of the PHY's interrupt (-1 if none)
  * @phy_timer: The timer for handling the state machine
  * @phylink: Pointer to phylink instance for this PHY
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5224f885a99a..58c2cd417e89 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5760,7 +5760,7 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr);
  */
 int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 				  const u8 *addr, enum nl80211_iftype iftype,
-				  u8 data_offset);
+				  u8 data_offset, bool is_amsdu);
 
 /**
  * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3
@@ -5772,7 +5772,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
 					 enum nl80211_iftype iftype)
 {
-	return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0);
+	return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0, false);
 }
 
 /**
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 51d8eb99764d..48ef7460ff30 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -157,7 +157,6 @@ enum nf_flow_flags {
 	NF_FLOW_HW,
 	NF_FLOW_HW_DYING,
 	NF_FLOW_HW_DEAD,
-	NF_FLOW_HW_REFRESH,
 	NF_FLOW_HW_PENDING,
 };
 
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index bd76e8e082c0..1df0f8074c9d 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -298,6 +298,7 @@ int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len,
 		      struct sk_buff **resp);
 
 struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev);
+void nci_hci_deallocate(struct nci_dev *ndev);
 int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event,
 		       const u8 *param, size_t param_len);
 int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate,
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 255e4f4b521f..ec7823921bd2 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -709,6 +709,17 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common,
 		cls_common->extack = extack;
 }
 
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb)
+{
+	struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+
+	if (tc_skb_ext)
+		memset(tc_skb_ext, 0, sizeof(*tc_skb_ext));
+	return tc_skb_ext;
+}
+#endif
+
 enum tc_matchall_command {
 	TC_CLSMATCHALL_REPLACE,
 	TC_CLSMATCHALL_DESTROY,
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index f5c1bee0cd6a..6d7b12cba015 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -128,12 +128,7 @@ void __qdisc_run(struct Qdisc *q);
 static inline void qdisc_run(struct Qdisc *q)
 {
 	if (qdisc_run_begin(q)) {
-		/* NOLOCK qdisc must check 'state' under the qdisc seqlock
-		 * to avoid racing with dev_qdisc_reset()
-		 */
-		if (!(q->flags & TCQ_F_NOLOCK) ||
-		    likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
-			__qdisc_run(q);
+		__qdisc_run(q);
 		qdisc_run_end(q);
 	}
 }
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f7a6e14491fb..1e625519ae96 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -36,6 +36,7 @@ struct qdisc_rate_table {
 enum qdisc_state_t {
 	__QDISC_STATE_SCHED,
 	__QDISC_STATE_DEACTIVATED,
+	__QDISC_STATE_MISSED,
 };
 
 struct qdisc_size_table {
@@ -159,8 +160,33 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK) {
+		if (spin_trylock(&qdisc->seqlock))
+			goto nolock_empty;
+
+		/* If the MISSED flag is set, it means other thread has
+		 * set the MISSED flag before second spin_trylock(), so
+		 * we can return false here to avoid multi cpus doing
+		 * the set_bit() and second spin_trylock() concurrently.
+		 */
+		if (test_bit(__QDISC_STATE_MISSED, &qdisc->state))
+			return false;
+
+		/* Set the MISSED flag before the second spin_trylock(),
+		 * if the second spin_trylock() return false, it means
+		 * other cpu holding the lock will do dequeuing for us
+		 * or it will see the MISSED flag set after releasing
+		 * lock and reschedule the net_tx_action() to do the
+		 * dequeuing.
+		 */
+		set_bit(__QDISC_STATE_MISSED, &qdisc->state);
+
+		/* Retry again in case other CPU may not see the new flag
+		 * after it releases the lock at the end of qdisc_run_end().
+		 */
 		if (!spin_trylock(&qdisc->seqlock))
 			return false;
+
+nolock_empty:
 		WRITE_ONCE(qdisc->empty, false);
 	} else if (qdisc_is_running(qdisc)) {
 		return false;
@@ -176,8 +202,15 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
 	write_seqcount_end(&qdisc->running);
-	if (qdisc->flags & TCQ_F_NOLOCK)
+	if (qdisc->flags & TCQ_F_NOLOCK) {
 		spin_unlock(&qdisc->seqlock);
+
+		if (unlikely(test_bit(__QDISC_STATE_MISSED,
+				      &qdisc->state))) {
+			clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+			__netif_schedule(qdisc);
+		}
+	}
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
diff --git a/include/net/sock.h b/include/net/sock.h
index 42bc5e1a627f..0e962d8bc73b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2231,13 +2231,15 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk)
+static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk)
 {
 	if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) {
 		skb_orphan(skb);
 		skb->destructor = sock_efree;
 		skb->sk = sk;
+		return true;
 	}
+	return false;
 }
 
 void sk_reset_timer(struct sock *sk, struct timer_list *timer,