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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 95 insertions, 10 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b92ef9f73e42..18f4cc2c6acd 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -63,6 +63,11 @@ struct bpf_map_ops {
 				     u64 imm, u32 *off);
 };
 
+struct bpf_map_memory {
+	u32 pages;
+	struct user_struct *user;
+};
+
 struct bpf_map {
 	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
@@ -83,7 +88,7 @@ struct bpf_map {
 	u32 btf_key_type_id;
 	u32 btf_value_type_id;
 	struct btf *btf;
-	u32 pages;
+	struct bpf_map_memory memory;
 	bool unpriv_array;
 	bool frozen; /* write-once */
 	/* 48 bytes hole */
@@ -91,8 +96,7 @@ struct bpf_map {
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
 	 */
-	struct user_struct *user ____cacheline_aligned;
-	atomic_t refcnt;
+	atomic_t refcnt ____cacheline_aligned;
 	atomic_t usercnt;
 	struct work_struct work;
 	char name[BPF_OBJ_NAME_LEN];
@@ -273,6 +277,7 @@ enum bpf_reg_type {
 	PTR_TO_TCP_SOCK,	 /* reg points to struct tcp_sock */
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
+	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -367,6 +372,7 @@ struct bpf_prog_aux {
 	u32 id;
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
+	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	struct bpf_prog **func;
 	void *jit_data; /* JIT specific data. arch dependent */
@@ -510,17 +516,18 @@ struct bpf_prog_array {
 };
 
 struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
-void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
-int bpf_prog_array_length(struct bpf_prog_array __rcu *progs);
-int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+void bpf_prog_array_free(struct bpf_prog_array *progs);
+int bpf_prog_array_length(struct bpf_prog_array *progs);
+bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
+int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
 				__u32 __user *prog_ids, u32 cnt);
 
-void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+void bpf_prog_array_delete_safe(struct bpf_prog_array *progs,
 				struct bpf_prog *old_prog);
-int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
+int bpf_prog_array_copy_info(struct bpf_prog_array *array,
 			     u32 *prog_ids, u32 request_cnt,
 			     u32 *prog_cnt);
-int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,
 			struct bpf_prog_array **new_array);
@@ -548,6 +555,56 @@ _out:							\
 		_ret;					\
 	 })
 
+/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs
+ * so BPF programs can request cwr for TCP packets.
+ *
+ * Current cgroup skb programs can only return 0 or 1 (0 to drop the
+ * packet. This macro changes the behavior so the low order bit
+ * indicates whether the packet should be dropped (0) or not (1)
+ * and the next bit is a congestion notification bit. This could be
+ * used by TCP to call tcp_enter_cwr()
+ *
+ * Hence, new allowed return values of CGROUP EGRESS BPF programs are:
+ *   0: drop packet
+ *   1: keep packet
+ *   2: drop packet and cn
+ *   3: keep packet and cn
+ *
+ * This macro then converts it to one of the NET_XMIT or an error
+ * code that is then interpreted as drop packet (and no cn):
+ *   0: NET_XMIT_SUCCESS  skb should be transmitted
+ *   1: NET_XMIT_DROP     skb should be dropped and cn
+ *   2: NET_XMIT_CN       skb should be transmitted and cn
+ *   3: -EPERM            skb should be dropped
+ */
+#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func)		\
+	({						\
+		struct bpf_prog_array_item *_item;	\
+		struct bpf_prog *_prog;			\
+		struct bpf_prog_array *_array;		\
+		u32 ret;				\
+		u32 _ret = 1;				\
+		u32 _cn = 0;				\
+		preempt_disable();			\
+		rcu_read_lock();			\
+		_array = rcu_dereference(array);	\
+		_item = &_array->items[0];		\
+		while ((_prog = READ_ONCE(_item->prog))) {		\
+			bpf_cgroup_storage_set(_item->cgroup_storage);	\
+			ret = func(_prog, ctx);		\
+			_ret &= (ret & 1);		\
+			_cn |= (ret & 2);		\
+			_item++;			\
+		}					\
+		rcu_read_unlock();			\
+		preempt_enable();			\
+		if (_ret)				\
+			_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);	\
+		else					\
+			_ret = (_cn ? NET_XMIT_DROP : -EPERM);		\
+		_ret;					\
+	})
+
 #define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
 	__BPF_PROG_RUN_ARRAY(array, ctx, func, false)
 
@@ -592,9 +649,12 @@ struct bpf_map *__bpf_map_get(struct fd f);
 struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
-int bpf_map_precharge_memlock(u32 pages);
 int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
 void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
+int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size);
+void bpf_map_charge_finish(struct bpf_map_memory *mem);
+void bpf_map_charge_move(struct bpf_map_memory *dst,
+			 struct bpf_map_memory *src);
 void *bpf_map_area_alloc(size_t size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
@@ -992,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto;
 extern const struct bpf_func_proto bpf_get_local_storage_proto;
 extern const struct bpf_func_proto bpf_strtol_proto;
 extern const struct bpf_func_proto bpf_strtoul_proto;
+extern const struct bpf_func_proto bpf_tcp_sock_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
@@ -1040,6 +1101,15 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
 				    struct bpf_insn *insn_buf,
 				    struct bpf_prog *prog,
 				    u32 *target_size);
+
+bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
+				  struct bpf_insn_access_aux *info);
+
+u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
+				    const struct bpf_insn *si,
+				    struct bpf_insn *insn_buf,
+				    struct bpf_prog *prog,
+				    u32 *target_size);
 #else
 static inline bool bpf_tcp_sock_is_valid_access(int off, int size,
 						enum bpf_access_type type,
@@ -1056,6 +1126,21 @@ static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
 {
 	return 0;
 }
+static inline bool bpf_xdp_sock_is_valid_access(int off, int size,
+						enum bpf_access_type type,
+						struct bpf_insn_access_aux *info)
+{
+	return false;
+}
+
+static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
+						  const struct bpf_insn *si,
+						  struct bpf_insn *insn_buf,
+						  struct bpf_prog *prog,
+						  u32 *target_size)
+{
+	return 0;
+}
 #endif /* CONFIG_INET */
 
 #endif /* _LINUX_BPF_H */