Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-07-19

We've added 45 non-merge commits during the last 3 day(s) which contain
a total of 71 files changed, 7808 insertions(+), 592 deletions(-).

The main changes are:

1) multi-buffer support in AF_XDP, from Maciej Fijalkowski,
   Magnus Karlsson, Tirthendu Sarkar.

2) BPF link support for tc BPF programs, from Daniel Borkmann.

3) Enable bpf_map_sum_elem_count kfunc for all program types,
   from Anton Protopopov.

4) Add 'owner' field to bpf_rb_node to fix races in shared ownership,
   Dave Marchevsky.

5) Prevent potential skb_header_pointer() misuse, from Alexei Starovoitov.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (45 commits)
  bpf, net: Introduce skb_pointer_if_linear().
  bpf: sync tools/ uapi header with
  selftests/bpf: Add mprog API tests for BPF tcx links
  selftests/bpf: Add mprog API tests for BPF tcx opts
  bpftool: Extend net dump with tcx progs
  libbpf: Add helper macro to clear opts structs
  libbpf: Add link-based API for tcx
  libbpf: Add opts-based attach/detach/query API for tcx
  bpf: Add fd-based tcx multi-prog infra with link support
  bpf: Add generic attach/detach/query API for multi-progs
  selftests/xsk: reset NIC settings to default after running test suite
  selftests/xsk: add test for too many frags
  selftests/xsk: add metadata copy test for multi-buff
  selftests/xsk: add invalid descriptor test for multi-buffer
  selftests/xsk: add unaligned mode test for multi-buffer
  selftests/xsk: add basic multi-buffer test
  selftests/xsk: transmit and receive multi-buffer packets
  xsk: add multi-buffer documentation
  i40e: xsk: add TX multi-buffer support
  ice: xsk: Tx multi-buffer support
  ...
====================

Link: https://lore.kernel.org/r/20230719175424.75717-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/uapi/linux/bpf.h

@@ -1036,6 +1036,8 @@ enum bpf_attach_type {
 	BPF_LSM_CGROUP,
 	BPF_STRUCT_OPS,
 	BPF_NETFILTER,
+	BPF_TCX_INGRESS,
+	BPF_TCX_EGRESS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1053,7 +1055,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_KPROBE_MULTI = 8,
 	BPF_LINK_TYPE_STRUCT_OPS = 9,
 	BPF_LINK_TYPE_NETFILTER = 10,
-
+	BPF_LINK_TYPE_TCX = 11,
 	MAX_BPF_LINK_TYPE,
 };
 
@@ -1113,7 +1115,12 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 #define BPF_F_ALLOW_MULTI	(1U << 1)
+/* Generic attachment flags. */
 #define BPF_F_REPLACE		(1U << 2)
+#define BPF_F_BEFORE		(1U << 3)
+#define BPF_F_AFTER		(1U << 4)
+#define BPF_F_ID		(1U << 5)
+#define BPF_F_LINK		BPF_F_LINK /* 1 << 13 */
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel
@@ -1444,14 +1451,19 @@ union bpf_attr {
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
-		__u32		target_fd;	/* container object to attach to */
-		__u32		attach_bpf_fd;	/* eBPF program to attach */
+		union {
+			__u32	target_fd;	/* target object to attach to or ... */
+			__u32	target_ifindex;	/* target ifindex */
+		};
+		__u32		attach_bpf_fd;
 		__u32		attach_type;
 		__u32		attach_flags;
-		__u32		replace_bpf_fd;	/* previously attached eBPF
-						 * program to replace if
-						 * BPF_F_REPLACE is used
-						 */
+		__u32		replace_bpf_fd;
+		union {
+			__u32	relative_fd;
+			__u32	relative_id;
+		};
+		__u64		expected_revision;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
@@ -1497,16 +1509,26 @@ union bpf_attr {
 	} info;
 
 	struct { /* anonymous struct used by BPF_PROG_QUERY command */
-		__u32		target_fd;	/* container object to query */
+		union {
+			__u32	target_fd;	/* target object to query or ... */
+			__u32	target_ifindex;	/* target ifindex */
+		};
 		__u32		attach_type;
 		__u32		query_flags;
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
-		__u32		prog_cnt;
+		union {
+			__u32	prog_cnt;
+			__u32	count;
+		};
+		__u32		:32;
 		/* output: per-program attach_flags.
 		 * not allowed to be set during effective query.
 		 */
 		__aligned_u64	prog_attach_flags;
+		__aligned_u64	link_ids;
+		__aligned_u64	link_attach_flags;
+		__u64		revision;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
@@ -1549,13 +1571,13 @@ union bpf_attr {
 			__u32		map_fd;		/* struct_ops to attach */
 		};
 		union {
-			__u32		target_fd;	/* object to attach to */
-			__u32		target_ifindex; /* target ifindex */
+			__u32	target_fd;	/* target object to attach to or ... */
+			__u32	target_ifindex; /* target ifindex */
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 		union {
-			__u32		target_btf_id;	/* btf_id of target to attach to */
+			__u32	target_btf_id;	/* btf_id of target to attach to */
 			struct {
 				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
 				__u32		iter_info_len;	/* iter_info length */
@@ -1589,6 +1611,13 @@ union bpf_attr {
 				__s32		priority;
 				__u32		flags;
 			} netfilter;
+			struct {
+				union {
+					__u32	relative_fd;
+					__u32	relative_id;
+				};
+				__u64		expected_revision;
+			} tcx;
 		};
 	} link_create;
 
@@ -6197,6 +6226,19 @@ struct bpf_sock_tuple {
 	};
 };
 
+/* (Simplified) user return codes for tcx prog type.
+ * A valid tcx program must return one of these defined values. All other
+ * return codes are reserved for future use. Must remain compatible with
+ * their TC_ACT_* counter-parts. For compatibility in behavior, unknown
+ * return codes are mapped to TCX_NEXT.
+ */
+enum tcx_action_base {
+	TCX_NEXT	= -1,
+	TCX_PASS	= 0,
+	TCX_DROP	= 2,
+	TCX_REDIRECT	= 7,
+};
+
 struct bpf_xdp_sock {
 	__u32 queue_id;
 };
@@ -6479,6 +6521,10 @@ struct bpf_link_info {
 				} event; /* BPF_PERF_EVENT_EVENT */
 			};
 		} perf_event;
+		struct {
+			__u32 ifindex;
+			__u32 attach_type;
+		} tcx;
 	};
 } __attribute__((aligned(8)));
 
@@ -7052,6 +7098,7 @@ struct bpf_list_head {
 struct bpf_list_node {
 	__u64 :64;
 	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
@@ -7063,6 +7110,7 @@ struct bpf_rb_node {
 	__u64 :64;
 	__u64 :64;
 	__u64 :64;
+	__u64 :64;
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {

include/uapi/linux/if_xdp.h

@@ -25,6 +25,12 @@
  * application.
  */
 #define XDP_USE_NEED_WAKEUP (1 << 3)
+/* By setting this option, userspace application indicates that it can
+ * handle multiple descriptors per packet thus enabling AF_XDP to split
+ * multi-buffer XDP frames into multiple Rx descriptors. Without this set
+ * such frames will be dropped.
+ */
+#define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
 #define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
@@ -108,4 +114,11 @@ struct xdp_desc {
 
 /* UMEM descriptor is __u64 */
 
+/* Flag indicating that the packet continues with the buffer pointed out by the
+ * next frame in the ring. The end of the packet is signalled by setting this
+ * bit to zero. For single buffer packets, every descriptor has 'options' set
+ * to 0 and this maintains backward compatibility.
+ */
+#define XDP_PKT_CONTD (1 << 0)
+
 #endif /* _LINUX_IF_XDP_H */

include/uapi/linux/netdev.h

@@ -41,6 +41,7 @@ enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
+	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)