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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-10-12

The main changes are:

1) The BPF verifier improvements to track register allocation pattern, from Alexei and Yonghong.

2) libbpf relocation support for different size load/store, from Andrii.

3) bpf_redirect_peer() helper and support for inner map array with different max_entries, from Daniel.

4) BPF support for per-cpu variables, form Hao.

5) sockmap improvements, from John.
====================

Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

Documentation/bpf/bpf_devel_QA.rst

@@ -60,13 +60,13 @@ Q: Where can I find patches currently under discussion for BPF subsystem?
 A: All patches that are Cc'ed to netdev are queued for review under netdev
 patchwork project:
 
-  http://patchwork.ozlabs.org/project/netdev/list/
+  https://patchwork.kernel.org/project/netdevbpf/list/
 
 Those patches which target BPF, are assigned to a 'bpf' delegate for
 further processing from BPF maintainers. The current queue with
 patches under review can be found at:
 
-  https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147
+  https://patchwork.kernel.org/project/netdevbpf/list/?delegate=121173
 
 Once the patches have been reviewed by the BPF community as a whole
 and approved by the BPF maintainers, their status in patchwork will be

MAINTAINERS

@@ -3263,7 +3263,7 @@ M:	Daniel Borkmann <[email protected]>
 R:	Martin KaFai Lau <[email protected]>
 R:	Song Liu <[email protected]>
 R:	Yonghong Song <[email protected]>
-R:	Andrii Nakryiko <[email protected]>
+R:	Andrii Nakryiko <[email protected]>
 R:	John Fastabend <[email protected]>
 R:	KP Singh <[email protected]>
 L:	[email protected]

drivers/net/veth.c

@@ -420,6 +420,14 @@ static int veth_select_rxq(struct net_device *dev)
 	return smp_processor_id() % dev->real_num_rx_queues;
 }
 
+static struct net_device *veth_peer_dev(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	/* Callers must be under RCU read side. */
+	return rcu_dereference(priv->peer);
+}
+
 static int veth_xdp_xmit(struct net_device *dev, int n,
 			 struct xdp_frame **frames,
 			 u32 flags, bool ndo_xmit)
@@ -1224,6 +1232,7 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
 	.ndo_bpf		= veth_xdp,
 	.ndo_xdp_xmit		= veth_ndo_xdp_xmit,
+	.ndo_get_peer_dev	= veth_peer_dev,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \

include/linux/bpf.h

@@ -82,7 +82,7 @@ struct bpf_map_ops {
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
 				int fd);
 	void (*map_fd_put_ptr)(void *ptr);
-	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
+	int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
@@ -293,6 +293,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
 	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
+	ARG_PTR_TO_PERCPU_BTF_ID,	/* pointer to in-kernel percpu type */
 	__BPF_ARG_TYPE_MAX,
 };
 
@@ -307,6 +308,8 @@ enum bpf_return_type {
 	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
 	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
 	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
+	RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
+	RET_PTR_TO_MEM_OR_BTF_ID,	/* returns a pointer to a valid memory or a btf_id */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -405,6 +408,7 @@ enum bpf_reg_type {
 	PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */
 	PTR_TO_RDWR_BUF,	 /* reg points to a read/write buffer */
 	PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
+	PTR_TO_PERCPU_BTF_ID,	 /* reg points to a percpu kernel variable */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -1828,6 +1832,8 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
+extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
+extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);

include/linux/bpf_verifier.h

@@ -308,6 +308,13 @@ struct bpf_insn_aux_data {
 			u32 map_index;		/* index into used_maps[] */
 			u32 map_off;		/* offset from value base address */
 		};
+		struct {
+			enum bpf_reg_type reg_type;	/* type of pseudo_btf_id */
+			union {
+				u32 btf_id;	/* btf_id for struct typed var */
+				u32 mem_size;	/* mem_size for non-struct typed var */
+			};
+		} btf_var;
 	};
 	u64 map_key_state; /* constant (32 bit) key tracking for maps */
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */

include/linux/btf.h

@@ -110,6 +110,11 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type,
 	     i < btf_type_vlen(struct_type);			\
 	     i++, member++)
 
+#define for_each_vsi(i, datasec_type, member)			\
+	for (i = 0, member = btf_type_var_secinfo(datasec_type);	\
+	     i < btf_type_vlen(datasec_type);			\
+	     i++, member++)
+
 static inline bool btf_type_is_ptr(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
@@ -145,6 +150,21 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
 }
 
+static inline bool btf_type_is_var(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
+}
+
+/* union is only a special case of struct:
+ * all its offsetof(member) == 0
+ */
+static inline bool btf_type_is_struct(const struct btf_type *t)
+{
+	u8 kind = BTF_INFO_KIND(t->info);
+
+	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
 static inline u16 btf_type_vlen(const struct btf_type *t)
 {
 	return BTF_INFO_VLEN(t->info);
@@ -179,6 +199,12 @@ static inline const struct btf_member *btf_type_member(const struct btf_type *t)
 	return (const struct btf_member *)(t + 1);
 }
 
+static inline const struct btf_var_secinfo *btf_type_var_secinfo(
+		const struct btf_type *t)
+{
+	return (const struct btf_var_secinfo *)(t + 1);
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);

include/linux/netdevice.h

@@ -1276,6 +1276,9 @@ struct netdev_net_notifier {
  * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
  *			 int cmd);
  *	Add, change, delete or get information on an IPv4 tunnel.
+ * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
+ *	If a device is paired with a peer device, return the peer instance.
+ *	The caller must be under RCU read context.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1483,6 +1486,7 @@ struct net_device_ops {
 	struct devlink_port *	(*ndo_get_devlink_port)(struct net_device *dev);
 	int			(*ndo_tunnel_ctl)(struct net_device *dev,
 						  struct ip_tunnel_parm *p, int cmd);
+	struct net_device *	(*ndo_get_peer_dev)(struct net_device *dev);
 };
 
 /**

include/linux/skmsg.h

@@ -308,6 +308,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node);
 int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock);
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock);
 void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock);
+void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock);
+void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock);
 
 int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
 			 struct sk_msg *msg);

include/net/tcp.h

@@ -2228,34 +2228,6 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 #endif /* CONFIG_NET_SOCK_MSG */
 
 #ifdef CONFIG_CGROUP_BPF
-/* Copy the listen sk's HDR_OPT_CB flags to its child.
- *
- * During 3-Way-HandShake, the synack is usually sent from
- * the listen sk with the HDR_OPT_CB flags set so that
- * bpf-prog will be called to write the BPF hdr option.
- *
- * In fastopen, the child sk is used to send synack instead
- * of the listen sk.  Thus, inheriting the HDR_OPT_CB flags
- * from the listen sk gives the bpf-prog a chance to write
- * BPF hdr option in the synack pkt during fastopen.
- *
- * Both fastopen and non-fastopen child will inherit the
- * HDR_OPT_CB flags to keep the bpf-prog having a consistent
- * behavior when deciding to clear this cb flags (or not)
- * during the PASSIVE_ESTABLISHED_CB.
- *
- * In the future, other cb flags could be inherited here also.
- */
-static inline void bpf_skops_init_child(const struct sock *sk,
-					struct sock *child)
-{
-	tcp_sk(child)->bpf_sock_ops_cb_flags =
-		tcp_sk(sk)->bpf_sock_ops_cb_flags &
-		(BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG |
-		 BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG |
-		 BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG);
-}
-
 static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
 				      struct sk_buff *skb,
 				      unsigned int end_offset)
@@ -2264,11 +2236,6 @@ static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
 	skops->skb_data_end = skb->data + end_offset;
 }
 #else
-static inline void bpf_skops_init_child(const struct sock *sk,
-					struct sock *child)
-{
-}
-
 static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
 				      struct sk_buff *skb,
 				      unsigned int end_offset)

include/uapi/linux/bpf.h

@@ -356,18 +356,36 @@ enum bpf_link_type {
 #define BPF_F_SLEEPABLE		(1U << 4)
 
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
- * two extensions:
- *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd              map fd
- * insn[1].imm:      0                   offset into value
- * insn[0].off:      0                   0
- * insn[1].off:      0                   0
- * ldimm64 rewrite:  address of map      address of map[0]+offset
- * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ * the following extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
+ * insn[0].imm:      map fd
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map
+ * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd
+ * insn[1].imm:      offset into value
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map[0]+offset
+ * verifier type:    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_VALUE	2
+/* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
+ * insn[0].imm:      kernel btd id of VAR
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of the kernel variable
+ * verifier type:    PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ *                   is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID	3
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
@@ -417,6 +435,9 @@ enum {
 
 /* Share perf_event among processes */
 	BPF_F_PRESERVE_ELEMS	= (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+	BPF_F_INNER_MAP		= (1U << 12),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1680,7 +1701,7 @@ union bpf_attr {
  * 		  **TCP_CONGESTION**, **TCP_BPF_IW**,
  * 		  **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
  * 		  **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**.
+ *		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
  * 	Return
@@ -2235,7 +2256,7 @@ union bpf_attr {
  *	Description
  *		This helper is used in programs implementing policies at the
  *		skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
- *		if the verdeict eBPF program returns **SK_PASS**), redirect it
+ *		if the verdict eBPF program returns **SK_PASS**), redirect it
  *		to the socket referenced by *map* (of type
  *		**BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
  *		egress interfaces can be used for redirection. The
@@ -3661,10 +3682,59 @@ union bpf_attr {
  * 		Redirect the packet to another net device of index *ifindex*
  * 		and fill in L2 addresses from neighboring subsystem. This helper
  * 		is somewhat similar to **bpf_redirect**\ (), except that it
- * 		fills in e.g. MAC addresses based on the L3 information from
- * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		populates L2 addresses as well, meaning, internally, the helper
+ * 		performs a FIB lookup based on the skb's networking header to
+ * 		get the address of the next hop and then relies on the neighbor
+ * 		lookup for the L2 address of the nexthop.
+ *
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types, and enabled
+ * 		for IPv4 and IPv6 protocols.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ *     Description
+ *             Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *             pointer to the percpu kernel variable on *cpu*. A ksym is an
+ *             extern variable decorated with '__ksym'. For ksym, there is a
+ *             global var (either static or global) defined of the same name
+ *             in the kernel. The ksym is percpu if the global var is percpu.
+ *             The returned pointer points to the global percpu var on *cpu*.
+ *
+ *             bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ *             kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ *             happens if *cpu* is larger than nr_cpu_ids. The caller of
+ *             bpf_per_cpu_ptr() must check the returned value.
+ *     Return
+ *             A pointer pointing to the kernel percpu variable on *cpu*, or
+ *             NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ *	Description
+ *		Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *		pointer to the percpu kernel variable on this cpu. See the
+ *		description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ *		bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ *		the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ *		never return NULL.
+ *	Return
+ *		A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*.
+ * 		This helper is somewhat similar to **bpf_redirect**\ (), except
+ * 		that the redirection happens to the *ifindex*' peer device and
+ * 		the netns switch takes place from ingress to ingress without
+ * 		going through the CPU's backlog queue.
+ *
  * 		The *flags* argument is reserved and must be 0. The helper is
- * 		currently only supported for tc BPF program types.
+ * 		currently only supported for tc BPF program types at the ingress
+ * 		hook and for veth device types. The peer device must reside in a
+ * 		different network namespace.
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
@@ -3823,6 +3893,9 @@ union bpf_attr {
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
+	FN(bpf_per_cpu_ptr),            \
+	FN(bpf_this_cpu_ptr),		\
+	FN(redirect_peer),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper