xsk: add Rx queue setup and mmap support

Another setsockopt (XDP_RX_QUEUE) is added to let the process allocate
a queue, where the kernel can pass completed Rx frames from the kernel
to user process.

The mmapping of the queue is done using the XDP_PGOFF_RX_QUEUE offset.

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit is contained in:
Björn Töpel 2018-05-02 13:01:25 +02:00 committed by Alexei Starovoitov
parent 423f38329d
commit b9b6b68e8a
5 changed files with 62 additions and 12 deletions

View File

@ -18,11 +18,15 @@
#include <linux/mutex.h>
#include <net/sock.h>
struct net_device;
struct xsk_queue;
struct xdp_umem;
struct xdp_sock {
/* struct sock must be the first member of struct xdp_sock */
struct sock sk;
struct xsk_queue *rx;
struct net_device *dev;
struct xdp_umem *umem;
/* Protects multiple processes in the control path */
struct mutex mutex;

View File

@ -22,6 +22,7 @@
#include <linux/types.h>
/* XDP socket options */
#define XDP_RX_RING 1
#define XDP_UMEM_REG 3
#define XDP_UMEM_FILL_RING 4
@ -33,13 +34,28 @@ struct xdp_umem_reg {
};
/* Pgoff for mmaping the rings */
#define XDP_PGOFF_RX_RING 0
#define XDP_UMEM_PGOFF_FILL_RING 0x100000000
struct xdp_desc {
__u32 idx;
__u32 len;
__u16 offset;
__u8 flags;
__u8 padding[5];
};
struct xdp_ring {
__u32 producer __attribute__((aligned(64)));
__u32 consumer __attribute__((aligned(64)));
};
/* Used for the RX and TX queues for packets */
struct xdp_rxtx_ring {
struct xdp_ring ptrs;
struct xdp_desc desc[0] __attribute__((aligned(64)));
};
/* Used for the fill and completion queues for buffers */
struct xdp_umem_ring {
struct xdp_ring ptrs;

View File

@ -31,6 +31,7 @@
#include <linux/net.h>
#include <linux/netdevice.h>
#include <net/xdp_sock.h>
#include <net/xdp.h>
#include "xsk_queue.h"
#include "xdp_umem.h"
@ -40,14 +41,15 @@ static struct xdp_sock *xdp_sk(struct sock *sk)
return (struct xdp_sock *)sk;
}
static int xsk_init_queue(u32 entries, struct xsk_queue **queue)
static int xsk_init_queue(u32 entries, struct xsk_queue **queue,
bool umem_queue)
{
struct xsk_queue *q;
if (entries == 0 || *queue || !is_power_of_2(entries))
return -EINVAL;
q = xskq_create(entries);
q = xskq_create(entries, umem_queue);
if (!q)
return -ENOMEM;
@ -89,6 +91,22 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
return -ENOPROTOOPT;
switch (optname) {
case XDP_RX_RING:
{
struct xsk_queue **q;
int entries;
if (optlen < sizeof(entries))
return -EINVAL;
if (copy_from_user(&entries, optval, sizeof(entries)))
return -EFAULT;
mutex_lock(&xs->mutex);
q = &xs->rx;
err = xsk_init_queue(entries, q, false);
mutex_unlock(&xs->mutex);
return err;
}
case XDP_UMEM_REG:
{
struct xdp_umem_reg mr;
@ -130,7 +148,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
mutex_lock(&xs->mutex);
q = &xs->umem->fq;
err = xsk_init_queue(entries, q);
err = xsk_init_queue(entries, q, true);
mutex_unlock(&xs->mutex);
return err;
}
@ -151,13 +169,17 @@ static int xsk_mmap(struct file *file, struct socket *sock,
unsigned long pfn;
struct page *qpg;
if (!xs->umem)
return -EINVAL;
if (offset == XDP_PGOFF_RX_RING) {
q = xs->rx;
} else {
if (!xs->umem)
return -EINVAL;
if (offset == XDP_UMEM_PGOFF_FILL_RING)
q = xs->umem->fq;
else
return -EINVAL;
if (offset == XDP_UMEM_PGOFF_FILL_RING)
q = xs->umem->fq;
else
return -EINVAL;
}
if (!q)
return -EINVAL;
@ -205,6 +227,7 @@ static void xsk_destruct(struct sock *sk)
if (!sock_flag(sk, SOCK_DEAD))
return;
xskq_destroy(xs->rx);
xdp_put_umem(xs->umem);
sk_refcnt_debug_dec(sk);

View File

@ -21,7 +21,13 @@ static u32 xskq_umem_get_ring_size(struct xsk_queue *q)
return sizeof(struct xdp_umem_ring) + q->nentries * sizeof(u32);
}
struct xsk_queue *xskq_create(u32 nentries)
static u32 xskq_rxtx_get_ring_size(struct xsk_queue *q)
{
return (sizeof(struct xdp_ring) +
q->nentries * sizeof(struct xdp_desc));
}
struct xsk_queue *xskq_create(u32 nentries, bool umem_queue)
{
struct xsk_queue *q;
gfp_t gfp_flags;
@ -36,7 +42,8 @@ struct xsk_queue *xskq_create(u32 nentries)
gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN |
__GFP_COMP | __GFP_NORETRY;
size = xskq_umem_get_ring_size(q);
size = umem_queue ? xskq_umem_get_ring_size(q) :
xskq_rxtx_get_ring_size(q);
q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags,
get_order(size));

View File

@ -32,7 +32,7 @@ struct xsk_queue {
u64 invalid_descs;
};
struct xsk_queue *xskq_create(u32 nentries);
struct xsk_queue *xskq_create(u32 nentries, bool umem_queue);
void xskq_destroy(struct xsk_queue *q);
#endif /* _LINUX_XSK_QUEUE_H */