linux_dsm_epyc7002/tools/lib/bpf/xsk.h
Magnus Karlsson 1cad078842 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>
2019-02-25 23:21:42 +01:00

204 lines
4.8 KiB
C

/* 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 */