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 <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: Björn Töpel

include/net/xdp_sock.h

@@ -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;

include/uapi/linux/if_xdp.h

@@ -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;

net/xdp/xsk.c

@@ -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);

net/xdp/xsk_queue.c

@@ -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));

net/xdp/xsk_queue.h

@@ -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 */