libbpf: add support for using AF_XDP sockets

This commit adds AF_XDP support to libbpf. The main reason for this is
to facilitate writing applications that use AF_XDP by offering
higher-level APIs that hide many of the details of the AF_XDP
uapi. This is in the same vein as libbpf facilitates XDP adoption by
offering easy-to-use higher level interfaces of XDP
functionality. Hopefully this will facilitate adoption of AF_XDP, make
applications using it simpler and smaller, and finally also make it
possible for applications to benefit from optimizations in the AF_XDP
user space access code. Previously, people just copied and pasted the
code from the sample application into their application, which is not
desirable.

The interface is composed of two parts:

* Low-level access interface to the four rings and the packet
* High-level control plane interface for creating and setting
  up umems and af_xdp sockets as well as a simple XDP program.
Tested-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

tools/include/uapi/linux/ethtool.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * ethtool.h: Defines for Linux ethtool.
+ *
+ * Copyright (C) 1998 David S. Miller (davem@redhat.com)
+ * Copyright 2001 Jeff Garzik <jgarzik@pobox.com>
+ * Portions Copyright 2001 Sun Microsystems (thockin@sun.com)
+ * Portions Copyright 2002 Intel (eli.kupermann@intel.com,
+ *                                christopher.leech@intel.com,
+ *                                scott.feldman@intel.com)
+ * Portions Copyright (C) Sun Microsystems 2008
+ */
+
+#ifndef _UAPI_LINUX_ETHTOOL_H
+#define _UAPI_LINUX_ETHTOOL_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#define ETHTOOL_GCHANNELS       0x0000003c /* Get no of channels */
+
+/**
+ * struct ethtool_channels - configuring number of network channel
+ * @cmd: ETHTOOL_{G,S}CHANNELS
+ * @max_rx: Read only. Maximum number of receive channel the driver support.
+ * @max_tx: Read only. Maximum number of transmit channel the driver support.
+ * @max_other: Read only. Maximum number of other channel the driver support.
+ * @max_combined: Read only. Maximum number of combined channel the driver
+ *	support. Set of queues RX, TX or other.
+ * @rx_count: Valid values are in the range 1 to the max_rx.
+ * @tx_count: Valid values are in the range 1 to the max_tx.
+ * @other_count: Valid values are in the range 1 to the max_other.
+ * @combined_count: Valid values are in the range 1 to the max_combined.
+ *
+ * This can be used to configure RX, TX and other channels.
+ */
+
+struct ethtool_channels {
+	__u32	cmd;
+	__u32	max_rx;
+	__u32	max_tx;
+	__u32	max_other;
+	__u32	max_combined;
+	__u32	rx_count;
+	__u32	tx_count;
+	__u32	other_count;
+	__u32	combined_count;
+};
+
+#endif /* _UAPI_LINUX_ETHTOOL_H */

tools/include/uapi/linux/if_xdp.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * if_xdp: XDP socket user-space interface
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * Author(s): Björn Töpel <bjorn.topel@intel.com>
+ *	      Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#ifndef _LINUX_IF_XDP_H
+#define _LINUX_IF_XDP_H
+
+#include <linux/types.h>
+
+/* Options for the sxdp_flags field */
+#define XDP_SHARED_UMEM	(1 << 0)
+#define XDP_COPY	(1 << 1) /* Force copy-mode */
+#define XDP_ZEROCOPY	(1 << 2) /* Force zero-copy mode */
+
+struct sockaddr_xdp {
+	__u16 sxdp_family;
+	__u16 sxdp_flags;
+	__u32 sxdp_ifindex;
+	__u32 sxdp_queue_id;
+	__u32 sxdp_shared_umem_fd;
+};
+
+struct xdp_ring_offset {
+	__u64 producer;
+	__u64 consumer;
+	__u64 desc;
+};
+
+struct xdp_mmap_offsets {
+	struct xdp_ring_offset rx;
+	struct xdp_ring_offset tx;
+	struct xdp_ring_offset fr; /* Fill */
+	struct xdp_ring_offset cr; /* Completion */
+};
+
+/* XDP socket options */
+#define XDP_MMAP_OFFSETS		1
+#define XDP_RX_RING			2
+#define XDP_TX_RING			3
+#define XDP_UMEM_REG			4
+#define XDP_UMEM_FILL_RING		5
+#define XDP_UMEM_COMPLETION_RING	6
+#define XDP_STATISTICS			7
+
+struct xdp_umem_reg {
+	__u64 addr; /* Start of packet data area */
+	__u64 len; /* Length of packet data area */
+	__u32 chunk_size;
+	__u32 headroom;
+};
+
+struct xdp_statistics {
+	__u64 rx_dropped; /* Dropped for reasons other than invalid desc */
+	__u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
+	__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+};
+
+/* Pgoff for mmaping the rings */
+#define XDP_PGOFF_RX_RING			  0
+#define XDP_PGOFF_TX_RING		 0x80000000
+#define XDP_UMEM_PGOFF_FILL_RING	0x100000000ULL
+#define XDP_UMEM_PGOFF_COMPLETION_RING	0x180000000ULL
+
+/* Rx/Tx descriptor */
+struct xdp_desc {
+	__u64 addr;
+	__u32 len;
+	__u32 options;
+};
+
+/* UMEM descriptor is __u64 */
+
+#endif /* _LINUX_IF_XDP_H */

tools/lib/bpf/Build

-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o bpf_prog_linfo.o libbpf_probes.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o

tools/lib/bpf/Makefile

@@ -164,6 +164,9 @@ $(BPF_IN): force elfdep bpfdep
 	@(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \
 	(diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true
+	@(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \
+	(diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \
+	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
 $(OUTPUT)libbpf.so: $(BPF_IN)
@@ -174,7 +177,7 @@ $(OUTPUT)libbpf.a: $(BPF_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
 $(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
-	$(QUIET_LINK)$(CXX) $^ -lelf -o $@
+	$(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@
 
 check: check_abi
 

tools/lib/bpf/README.rst

@@ -9,7 +9,7 @@ described here. It's recommended to follow these conventions whenever a
 new function or type is added to keep libbpf API clean and consistent.
 
 All types and functions provided by libbpf API should have one of the
-following prefixes: ``bpf_``, ``btf_``, ``libbpf_``.
+following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``.
 
 System call wrappers
 --------------------
@@ -62,6 +62,19 @@ Auxiliary functions and types that don't fit well in any of categories
 described above should have ``libbpf_`` prefix, e.g.
 ``libbpf_get_error`` or ``libbpf_prog_type_by_name``.
 
+AF_XDP functions
+-------------------
+
+AF_XDP functions should have an ``xsk_`` prefix, e.g.
+``xsk_umem__get_data`` or ``xsk_umem__create``. The interface consists
+of both low-level ring access functions and high-level configuration
+functions. These can be mixed and matched. Note that these functions
+are not reentrant for performance reasons.
+
+Please take a look at Documentation/networking/af_xdp.rst in the Linux
+kernel source tree on how to use XDP sockets and for some common
+mistakes in case you do not get any traffic up to user space.
+
 libbpf ABI
 ==========
 

tools/lib/bpf/libbpf.map

@@ -147,4 +147,10 @@ LIBBPF_0.0.2 {
 		btf_ext__new;
 		btf_ext__reloc_func_info;
 		btf_ext__reloc_line_info;
+		xsk_umem__create;
+		xsk_socket__create;
+		xsk_umem__delete;
+		xsk_socket__delete;
+		xsk_umem__fd;
+		xsk_socket__fd;
 } LIBBPF_0.0.1;

tools/lib/bpf/xsk.h

+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * AF_XDP user-space access library.
+ *
+ * Copyright(c) 2018 - 2019 Intel Corporation.
+ *
+ * Author(s): Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#ifndef __LIBBPF_XSK_H
+#define __LIBBPF_XSK_H
+
+#include <stdio.h>
+#include <stdint.h>
+#include <linux/if_xdp.h>
+
+#include "libbpf.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Do not access these members directly. Use the functions below. */
+#define DEFINE_XSK_RING(name) \
+struct name { \
+	__u32 cached_prod; \
+	__u32 cached_cons; \
+	__u32 mask; \
+	__u32 size; \
+	__u32 *producer; \
+	__u32 *consumer; \
+	void *ring; \
+}
+
+DEFINE_XSK_RING(xsk_ring_prod);
+DEFINE_XSK_RING(xsk_ring_cons);
+
+struct xsk_umem;
+struct xsk_socket;
+
+static inline __u64 *xsk_ring_prod__fill_addr(struct xsk_ring_prod *fill,
+					      __u32 idx)
+{
+	__u64 *addrs = (__u64 *)fill->ring;
+
+	return &addrs[idx & fill->mask];
+}
+
+static inline const __u64 *
+xsk_ring_cons__comp_addr(const struct xsk_ring_cons *comp, __u32 idx)
+{
+	const __u64 *addrs = (const __u64 *)comp->ring;
+
+	return &addrs[idx & comp->mask];
+}
+
+static inline struct xdp_desc *xsk_ring_prod__tx_desc(struct xsk_ring_prod *tx,
+						      __u32 idx)
+{
+	struct xdp_desc *descs = (struct xdp_desc *)tx->ring;
+
+	return &descs[idx & tx->mask];
+}
+
+static inline const struct xdp_desc *
+xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx)
+{
+	const struct xdp_desc *descs = (const struct xdp_desc *)rx->ring;
+
+	return &descs[idx & rx->mask];
+}
+
+static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
+{
+	__u32 free_entries = r->cached_cons - r->cached_prod;
+
+	if (free_entries >= nb)
+		return free_entries;
+
+	/* Refresh the local tail pointer.
+	 * cached_cons is r->size bigger than the real consumer pointer so
+	 * that this addition can be avoided in the more frequently
+	 * executed code that computs free_entries in the beginning of
+	 * this function. Without this optimization it whould have been
+	 * free_entries = r->cached_prod - r->cached_cons + r->size.
+	 */
+	r->cached_cons = *r->consumer + r->size;
+
+	return r->cached_cons - r->cached_prod;
+}
+
+static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
+{
+	__u32 entries = r->cached_prod - r->cached_cons;
+
+	if (entries == 0) {
+		r->cached_prod = *r->producer;
+		entries = r->cached_prod - r->cached_cons;
+	}
+
+	return (entries > nb) ? nb : entries;
+}
+
+static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod,
+					    size_t nb, __u32 *idx)
+{
+	if (unlikely(xsk_prod_nb_free(prod, nb) < nb))
+		return 0;
+
+	*idx = prod->cached_prod;
+	prod->cached_prod += nb;
+
+	return nb;
+}
+
+static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb)
+{
+	/* Make sure everything has been written to the ring before signalling
+	 * this to the kernel.
+	 */
+	smp_wmb();
+
+	*prod->producer += nb;
+}
+
+static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons,
+					 size_t nb, __u32 *idx)
+{
+	size_t entries = xsk_cons_nb_avail(cons, nb);
+
+	if (likely(entries > 0)) {
+		/* Make sure we do not speculatively read the data before
+		 * we have received the packet buffers from the ring.
+		 */
+		smp_rmb();
+
+		*idx = cons->cached_cons;
+		cons->cached_cons += entries;
+	}
+
+	return entries;
+}
+
+static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb)
+{
+	*cons->consumer += nb;
+}
+
+static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)
+{
+	return &((char *)umem_area)[addr];
+}
+
+LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem);
+LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
+
+#define XSK_RING_CONS__DEFAULT_NUM_DESCS      2048
+#define XSK_RING_PROD__DEFAULT_NUM_DESCS      2048
+#define XSK_UMEM__DEFAULT_FRAME_SHIFT    11 /* 2048 bytes */
+#define XSK_UMEM__DEFAULT_FRAME_SIZE     (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
+#define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0
+
+struct xsk_umem_config {
+	__u32 fill_size;
+	__u32 comp_size;
+	__u32 frame_size;
+	__u32 frame_headroom;
+};
+
+/* Flags for the libbpf_flags field. */
+#define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
+
+struct xsk_socket_config {
+	__u32 rx_size;
+	__u32 tx_size;
+	__u32 libbpf_flags;
+	__u32 xdp_flags;
+	__u16 bind_flags;
+};
+
+/* Set config to NULL to get the default configuration. */
+LIBBPF_API int xsk_umem__create(struct xsk_umem **umem,
+				void *umem_area, __u64 size,
+				struct xsk_ring_prod *fill,
+				struct xsk_ring_cons *comp,
+				const struct xsk_umem_config *config);
+LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk,
+				  const char *ifname, __u32 queue_id,
+				  struct xsk_umem *umem,
+				  struct xsk_ring_cons *rx,
+				  struct xsk_ring_prod *tx,
+				  const struct xsk_socket_config *config);
+
+/* Returns 0 for success and -EBUSY if the umem is still in use. */
+LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem);
+LIBBPF_API void xsk_socket__delete(struct xsk_socket *xsk);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* __LIBBPF_XSK_H */