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

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 162 insertions, 12 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f1af7d63d678..c397934f91dd 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/rbtree_latch.h>
 #include <linux/numa.h>
+#include <linux/wait.h>
 
 struct perf_event;
 struct bpf_prog;
@@ -56,6 +57,10 @@ struct bpf_map {
 	struct work_struct work;
 	atomic_t usercnt;
 	struct bpf_map *inner_map_meta;
+	char name[BPF_OBJ_NAME_LEN];
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 };
 
 /* function argument constraints */
@@ -137,6 +142,7 @@ enum bpf_reg_type {
 	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
 	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
 	PTR_TO_STACK,		 /* reg == frame_pointer + offset */
+	PTR_TO_PACKET_META,	 /* skb->data - meta_len */
 	PTR_TO_PACKET,		 /* reg points to skb->data */
 	PTR_TO_PACKET_END,	 /* skb->data + headlen */
 };
@@ -155,6 +161,11 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
 	aux->ctx_field_size = size;
 }
 
+struct bpf_prog_ops {
+	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
+			union bpf_attr __user *uattr);
+};
+
 struct bpf_verifier_ops {
 	/* return eBPF function prototype for verification */
 	const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
@@ -170,8 +181,16 @@ struct bpf_verifier_ops {
 				  const struct bpf_insn *src,
 				  struct bpf_insn *dst,
 				  struct bpf_prog *prog, u32 *target_size);
-	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
-			union bpf_attr __user *uattr);
+};
+
+struct bpf_dev_offload {
+	struct bpf_prog		*prog;
+	struct net_device	*netdev;
+	void			*dev_priv;
+	struct list_head	offloads;
+	bool			dev_state;
+	bool			verifier_running;
+	wait_queue_head_t	verifier_done;
 };
 
 struct bpf_prog_aux {
@@ -182,10 +201,16 @@ struct bpf_prog_aux {
 	u32 id;
 	struct latch_tree_node ksym_tnode;
 	struct list_head ksym_lnode;
-	const struct bpf_verifier_ops *ops;
+	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
 	struct bpf_prog *prog;
 	struct user_struct *user;
+	u64 load_time; /* ns since boottime */
+	char name[BPF_OBJ_NAME_LEN];
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
+	struct bpf_dev_offload *offload;
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;
@@ -218,9 +243,6 @@ struct bpf_event_entry {
 	struct rcu_head rcu;
 };
 
-u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
-u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
-
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 int bpf_prog_calc_tag(struct bpf_prog *fp);
 
@@ -237,19 +259,84 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr);
 
+/* an array of programs to be executed under rcu_lock.
+ *
+ * Typical usage:
+ * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN);
+ *
+ * the structure returned by bpf_prog_array_alloc() should be populated
+ * with program pointers and the last pointer must be NULL.
+ * The user has to keep refcnt on the program and make sure the program
+ * is removed from the array before bpf_prog_put().
+ * The 'struct bpf_prog_array *' should only be replaced with xchg()
+ * since other cpus are walking the array of pointers in parallel.
+ */
+struct bpf_prog_array {
+	struct rcu_head rcu;
+	struct bpf_prog *progs[0];
+};
+
+struct bpf_prog_array __rcu *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,
+				__u32 __user *prog_ids, u32 cnt);
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+				struct bpf_prog *old_prog);
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+			struct bpf_prog *exclude_prog,
+			struct bpf_prog *include_prog,
+			struct bpf_prog_array **new_array);
+
+#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null)	\
+	({						\
+		struct bpf_prog **_prog, *__prog;	\
+		struct bpf_prog_array *_array;		\
+		u32 _ret = 1;				\
+		rcu_read_lock();			\
+		_array = rcu_dereference(array);	\
+		if (unlikely(check_non_null && !_array))\
+			goto _out;			\
+		_prog = _array->progs;			\
+		while ((__prog = READ_ONCE(*_prog))) {	\
+			_ret &= func(__prog, ctx);	\
+			_prog++;			\
+		}					\
+_out:							\
+		rcu_read_unlock();			\
+		_ret;					\
+	 })
+
+#define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, false)
+
+#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func)	\
+	__BPF_PROG_RUN_ARRAY(array, ctx, func, true)
+
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 
-#define BPF_PROG_TYPE(_id, _ops) \
-	extern const struct bpf_verifier_ops _ops;
+extern const struct file_operations bpf_map_fops;
+extern const struct file_operations bpf_prog_fops;
+
+#define BPF_PROG_TYPE(_id, _name) \
+	extern const struct bpf_prog_ops _name ## _prog_ops; \
+	extern const struct bpf_verifier_ops _name ## _verifier_ops;
 #define BPF_MAP_TYPE(_id, _ops) \
 	extern const struct bpf_map_ops _ops;
 #include <linux/bpf_types.h>
 #undef BPF_PROG_TYPE
 #undef BPF_MAP_TYPE
 
+extern const struct bpf_prog_ops bpf_offload_prog_ops;
+extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
+extern const struct bpf_verifier_ops xdp_analyzer_ops;
+
 struct bpf_prog *bpf_prog_get(u32 ufd);
 struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type);
+struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
+				       struct net_device *netdev);
 struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i);
 void bpf_prog_sub(struct bpf_prog *prog, int i);
 struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog);
@@ -269,11 +356,11 @@ void bpf_map_area_free(void *base);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
-int bpf_map_new_fd(struct bpf_map *map);
+int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
 
 int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
-int bpf_obj_get_user(const char __user *pathname);
+int bpf_obj_get_user(const char __user *pathname, int flags);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
@@ -292,6 +379,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 				void *key, void *value, u64 map_flags);
 int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
 
+int bpf_get_file_flag(int flags);
+
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
  * forced to use 'long' read/writes to try to atomically copy long counters.
  * Best-effort only.  No barriers here, since it _will_ race with concurrent
@@ -316,6 +405,13 @@ struct net_device  *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
 void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
 void __dev_map_flush(struct bpf_map *map);
 
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
+void __cpu_map_flush(struct bpf_map *map);
+struct xdp_buff;
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+		    struct net_device *dev_rx);
+
 /* Return map's numa specified by userspace */
 static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
 {
@@ -323,7 +419,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
 		attr->numa_node : NUMA_NO_NODE;
 }
 
-#else
+#else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
 	return ERR_PTR(-EOPNOTSUPP);
@@ -334,6 +430,14 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
+
+static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd,
+						     enum bpf_prog_type type,
+						     struct net_device *netdev)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog,
 							  int i)
 {
@@ -368,7 +472,7 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
 {
 }
 
-static inline int bpf_obj_get_user(const char __user *pathname)
+static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 {
 	return -EOPNOTSUPP;
 }
@@ -386,8 +490,54 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index)
 static inline void __dev_map_flush(struct bpf_map *map)
 {
 }
+
+static inline
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	return NULL;
+}
+
+static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index)
+{
+}
+
+static inline void __cpu_map_flush(struct bpf_map *map)
+{
+}
+
+struct xdp_buff;
+static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
+				  struct xdp_buff *xdp,
+				  struct net_device *dev_rx)
+{
+	return 0;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
+int bpf_prog_offload_compile(struct bpf_prog *prog);
+void bpf_prog_offload_destroy(struct bpf_prog *prog);
+u32 bpf_prog_offload_ifindex(struct bpf_prog *prog);
+
+#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
+int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
+
+static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
+{
+	return aux->offload;
+}
+#else
+static inline int bpf_prog_offload_init(struct bpf_prog *prog,
+					union bpf_attr *attr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
+{
+	return false;
+}
+#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
+
 #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL)
 struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
 int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);