Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "Several fixes here. Basically split down the line between newly
  introduced regressions and long existing problems:

   1) Double free in tipc_enable_bearer(), from Cong Wang.

   2) Many fixes to nf_conncount, from Florian Westphal.

   3) op->get_regs_len() can throw an error, check it, from Yunsheng
      Lin.

   4) Need to use GFP_ATOMIC in *_add_hash_mac_address() of fsl/fman
      driver, from Scott Wood.

   5) Inifnite loop in fib_empty_table(), from Yue Haibing.

   6) Use after free in ax25_fillin_cb(), from Cong Wang.

   7) Fix socket locking in nr_find_socket(), also from Cong Wang.

   8) Fix WoL wakeup enable in r8169, from Heiner Kallweit.

   9) On 32-bit sock->sk_stamp is not thread-safe, from Deepa Dinamani.

  10) Fix ptr_ring wrap during queue swap, from Cong Wang.

  11) Missing shutdown callback in hinic driver, from Xue Chaojing.

  12) Need to return NULL on error from ip6_neigh_lookup(), from Stefano
      Brivio.

  13) BPF out of bounds speculation fixes from Daniel Borkmann"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (57 commits)
  ipv6: Consider sk_bound_dev_if when binding a socket to an address
  ipv6: Fix dump of specific table with strict checking
  bpf: add various test cases to selftests
  bpf: prevent out of bounds speculation on pointer arithmetic
  bpf: fix check_map_access smin_value test when pointer contains offset
  bpf: restrict unknown scalars of mixed signed bounds for unprivileged
  bpf: restrict stack pointer arithmetic for unprivileged
  bpf: restrict map value pointer arithmetic for unprivileged
  bpf: enable access to ax register also from verifier rewrite
  bpf: move tmp variable into ax register in interpreter
  bpf: move {prev_,}insn_idx into verifier env
  isdn: fix kernel-infoleak in capi_unlocked_ioctl
  ipv6: route: Fix return value of ip6_neigh_lookup() on neigh_create() error
  net/hamradio/6pack: use mod_timer() to rearm timers
  net-next/hinic:add shutdown callback
  net: hns3: call hns3_nic_net_open() while doing HNAE3_UP_CLIENT
  ip: validate header length on virtual device xmit
  tap: call skb_probe_transport_header after setting skb->dev
  ptr_ring: wrap back ->producer in __ptr_ring_swap_queue()
  net: rds: remove unnecessary NULL check
  ...

8 files changed, 84 insertions, 32 deletions

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index c233efc106c6..27b74947cd2b 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -148,6 +148,7 @@ struct bpf_verifier_state {
 	/* call stack tracking */
 	struct bpf_func_state *frame[MAX_CALL_FRAMES];
 	u32 curframe;
+	bool speculative;
 };
 
 #define bpf_get_spilled_reg(slot, frame)				\
@@ -167,15 +168,24 @@ struct bpf_verifier_state_list {
 	struct bpf_verifier_state_list *next;
 };
 
+/* Possible states for alu_state member. */
+#define BPF_ALU_SANITIZE_SRC		1U
+#define BPF_ALU_SANITIZE_DST		2U
+#define BPF_ALU_NEG_VALUE		(1U << 2)
+#define BPF_ALU_SANITIZE		(BPF_ALU_SANITIZE_SRC | \
+					 BPF_ALU_SANITIZE_DST)
+
 struct bpf_insn_aux_data {
 	union {
 		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
 		unsigned long map_state;	/* pointer/poison value for maps */
 		s32 call_imm;			/* saved imm field of call insn */
+		u32 alu_limit;			/* limit for add/sub register with pointer */
 	};
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
 	int sanitize_stack_off; /* stack slot to be cleared */
 	bool seen; /* this insn was processed by the verifier */
+	u8 alu_state; /* used in combination with alu_limit */
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
@@ -212,6 +222,8 @@ struct bpf_subprog_info {
  * one verifier_env per bpf_check() call
  */
 struct bpf_verifier_env {
+	u32 insn_idx;
+	u32 prev_insn_idx;
 	struct bpf_prog *prog;		/* eBPF program being verified */
 	const struct bpf_verifier_ops *ops;
 	struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 8c8544b375eb..ad106d845b22 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -53,14 +53,10 @@ struct sock_reuseport;
 #define BPF_REG_D	BPF_REG_8	/* data, callee-saved */
 #define BPF_REG_H	BPF_REG_9	/* hlen, callee-saved */
 
-/* Kernel hidden auxiliary/helper register for hardening step.
- * Only used by eBPF JITs. It's nothing more than a temporary
- * register that JITs use internally, only that here it's part
- * of eBPF instructions that have been rewritten for blinding
- * constants. See JIT pre-step in bpf_jit_blind_constants().
- */
+/* Kernel hidden auxiliary/helper register. */
 #define BPF_REG_AX		MAX_BPF_REG
-#define MAX_BPF_JIT_REG		(MAX_BPF_REG + 1)
+#define MAX_BPF_EXT_REG		(MAX_BPF_REG + 1)
+#define MAX_BPF_JIT_REG		MAX_BPF_EXT_REG
 
 /* unused opcode to mark special call to bpf_tail_call() helper */
 #define BPF_TAIL_CALL	0xf0
diff --git a/include/linux/phy.h b/include/linux/phy.h
index da039f211c22..3b051f761450 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1,6 +1,6 @@
 /*
  * Framework and drivers for configuring and reading different PHYs
- * Based on code in sungem_phy.c and gianfar_phy.c
+ * Based on code in sungem_phy.c and (long-removed) gianfar_phy.c
  *
  * Author: Andy Fleming
  *
@@ -110,9 +110,9 @@ typedef enum {
  * @speeds: buffer to store supported speeds in.
  * @size: size of speeds buffer.
  *
- * Description: Returns the number of supported speeds, and
- * fills the speeds * buffer with the supported speeds. If speeds buffer is
- * too small to contain * all currently supported speeds, will return as
+ * Description: Returns the number of supported speeds, and fills
+ * the speeds buffer with the supported speeds. If speeds buffer is
+ * too small to contain all currently supported speeds, will return as
  * many speeds as can fit.
  */
 unsigned int phy_supported_speeds(struct phy_device *phy,
@@ -120,7 +120,10 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
 				      unsigned int size);
 
 /**
- * It maps 'enum phy_interface_t' found in include/linux/phy.h
+ * phy_modes - map phy_interface_t enum to device tree binding of phy-mode
+ * @interface: enum phy_interface_t value
+ *
+ * Description: maps 'enum phy_interface_t' defined in this file
  * into the device tree binding of 'phy-mode', so that Ethernet
  * device driver can get phy interface from device tree.
  */
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index 1fdefadf150a..e8e118d70fd7 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -110,6 +110,7 @@ struct phy_ops {
 /**
  * struct phy_attrs - represents phy attributes
  * @bus_width: Data path width implemented by PHY
+ * @mode: PHY mode
  */
 struct phy_attrs {
 	u32			bus_width;
@@ -121,7 +122,6 @@ struct phy_attrs {
  * @dev: phy device
  * @id: id of the phy device
  * @ops: function pointers for performing phy operations
- * @init_data: list of PHY consumers (non-dt only)
  * @mutex: mutex to protect phy_ops
  * @init_count: used to protect when the PHY is used by multiple consumers
  * @power_count: used to protect when the PHY is used by multiple consumers
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 6894976b54e3..186cd8e970c7 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -573,6 +573,8 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 		else if (destroy)
 			destroy(ptr);
 
+	if (producer >= size)
+		producer = 0;
 	__ptr_ring_set_size(r, size);
 	r->producer = producer;
 	r->consumer_head = 0;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index cbcf35ce1b14..34f019650941 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -308,6 +308,26 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap);
 
+static inline bool pskb_inet_may_pull(struct sk_buff *skb)
+{
+	int nhlen;
+
+	switch (skb->protocol) {
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		nhlen = sizeof(struct ipv6hdr);
+		break;
+#endif
+	case htons(ETH_P_IP):
+		nhlen = sizeof(struct iphdr);
+		break;
+	default:
+		nhlen = 0;
+	}
+
+	return pskb_network_may_pull(skb, nhlen);
+}
+
 static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
 {
 	const struct ip_tunnel_encap_ops *ops;
diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index 4b2b2baf8ab4..f32fc8289473 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -5,17 +5,10 @@
 
 struct nf_conncount_data;
 
-enum nf_conncount_list_add {
-	NF_CONNCOUNT_ADDED, 	/* list add was ok */
-	NF_CONNCOUNT_ERR,	/* -ENOMEM, must drop skb */
-	NF_CONNCOUNT_SKIP,	/* list is already reclaimed by gc */
-};
-
 struct nf_conncount_list {
 	spinlock_t list_lock;
 	struct list_head head;	/* connections with the same filtering key */
 	unsigned int count;	/* length of list */
-	bool dead;
 };
 
 struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
@@ -29,18 +22,12 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone);
 
-void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
-			 const struct nf_conntrack_tuple *tuple,
-			 const struct nf_conntrack_zone *zone,
-			 bool *addit);
+int nf_conncount_add(struct net *net, struct nf_conncount_list *list,
+		     const struct nf_conntrack_tuple *tuple,
+		     const struct nf_conntrack_zone *zone);
 
 void nf_conncount_list_init(struct nf_conncount_list *list);
 
-enum nf_conncount_list_add
-nf_conncount_add(struct nf_conncount_list *list,
-		 const struct nf_conntrack_tuple *tuple,
-		 const struct nf_conntrack_zone *zone);
-
 bool nf_conncount_gc_list(struct net *net,
 			  struct nf_conncount_list *list);
 
diff --git a/include/net/sock.h b/include/net/sock.h
index a6235c286ef9..2b229f7be8eb 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -298,6 +298,7 @@ struct sock_common {
   *	@sk_filter: socket filtering instructions
   *	@sk_timer: sock cleanup timer
   *	@sk_stamp: time stamp of last packet received
+  *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING socket options
   *	@sk_tskey: counter to disambiguate concurrent tstamp requests
   *	@sk_zckey: counter to order MSG_ZEROCOPY notifications
@@ -474,6 +475,9 @@ struct sock {
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
 	ktime_t			sk_stamp;
+#if BITS_PER_LONG==32
+	seqlock_t		sk_stamp_seq;
+#endif
 	u16			sk_tsflags;
 	u8			sk_shutdown;
 	u32			sk_tskey;
@@ -2297,6 +2301,34 @@ static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
 	atomic_add(segs, &sk->sk_drops);
 }
 
+static inline ktime_t sock_read_timestamp(struct sock *sk)
+{
+#if BITS_PER_LONG==32
+	unsigned int seq;
+	ktime_t kt;
+
+	do {
+		seq = read_seqbegin(&sk->sk_stamp_seq);
+		kt = sk->sk_stamp;
+	} while (read_seqretry(&sk->sk_stamp_seq, seq));
+
+	return kt;
+#else
+	return sk->sk_stamp;
+#endif
+}
+
+static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
+{
+#if BITS_PER_LONG==32
+	write_seqlock(&sk->sk_stamp_seq);
+	sk->sk_stamp = kt;
+	write_sequnlock(&sk->sk_stamp_seq);
+#else
+	sk->sk_stamp = kt;
+#endif
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2321,7 +2353,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 	     (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
 		__sock_recv_timestamp(msg, sk, skb);
 	else
-		sk->sk_stamp = kt;
+		sock_write_timestamp(sk, kt);
 
 	if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid)
 		__sock_recv_wifi_status(msg, sk, skb);
@@ -2342,9 +2374,9 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_recv_ts_and_drops(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
-		sk->sk_stamp = skb->tstamp;
+		sock_write_timestamp(sk, skb->tstamp);
 	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
-		sk->sk_stamp = 0;
+		sock_write_timestamp(sk, 0);
 }
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);