xsk: remove explicit ring structure from uapi

In this commit we remove the explicit ring structure from the the
uapi. It is tricky for an uapi to depend on a certain L1 cache line
size, since it can differ for variants of the same architecture. Now,
we let the user application determine the offsets of the producer,
consumer and descriptors by asking the socket via getsockopt.

A typical flow would be (Rx ring):

  struct xdp_mmap_offsets off;
  struct xdp_desc *ring;
  u32 *prod, *cons;
  void *map;
  ...

  getsockopt(fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);

  map = mmap(NULL, off.rx.desc +
		   NUM_DESCS * sizeof(struct xdp_desc),
		   PROT_READ | PROT_WRITE,
		   MAP_SHARED | MAP_POPULATE, sfd,
		   XDP_PGOFF_RX_RING);
  prod = map + off.rx.producer;
  cons = map + off.rx.consumer;
  ring = map + off.rx.desc;

Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

3 files changed, 68 insertions, 22 deletions

diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index c46609a00168..4737cfe222f5 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -23,13 +23,27 @@ struct sockaddr_xdp {
 	__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_RX_RING			1
-#define XDP_TX_RING			2
-#define XDP_UMEM_REG			3
-#define XDP_UMEM_FILL_RING		4
-#define XDP_UMEM_COMPLETION_RING	5
-#define XDP_STATISTICS			6
+#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 */
@@ -50,6 +64,7 @@ struct xdp_statistics {
 #define XDP_UMEM_PGOFF_FILL_RING	0x100000000
 #define XDP_UMEM_PGOFF_COMPLETION_RING	0x180000000
 
+/* Rx/Tx descriptor */
 struct xdp_desc {
 	__u32 idx;
 	__u32 len;
@@ -58,21 +73,6 @@ struct xdp_desc {
 	__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;
-	__u32 desc[0] __attribute__((aligned(64)));
-};
+/* UMEM descriptor is __u32 */
 
 #endif /* _LINUX_IF_XDP_H */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 29707354cf78..378dd9287da5 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -489,6 +489,35 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
 
 		return 0;
 	}
+	case XDP_MMAP_OFFSETS:
+	{
+		struct xdp_mmap_offsets off;
+
+		if (len < sizeof(off))
+			return -EINVAL;
+
+		off.rx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer);
+		off.rx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer);
+		off.rx.desc	= offsetof(struct xdp_rxtx_ring, desc);
+		off.tx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer);
+		off.tx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer);
+		off.tx.desc	= offsetof(struct xdp_rxtx_ring, desc);
+
+		off.fr.producer = offsetof(struct xdp_umem_ring, ptrs.producer);
+		off.fr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer);
+		off.fr.desc	= offsetof(struct xdp_umem_ring, desc);
+		off.cr.producer = offsetof(struct xdp_umem_ring, ptrs.producer);
+		off.cr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer);
+		off.cr.desc	= offsetof(struct xdp_umem_ring, desc);
+
+		len = sizeof(off);
+		if (copy_to_user(optval, &off, len))
+			return -EFAULT;
+		if (put_user(len, optlen))
+			return -EFAULT;
+
+		return 0;
+	}
 	default:
 		break;
 	}
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 62e43be407d8..cb8e5be35110 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -13,6 +13,23 @@
 
 #define RX_BATCH_SIZE 16
 
+struct xdp_ring {
+	u32 producer ____cacheline_aligned_in_smp;
+	u32 consumer ____cacheline_aligned_in_smp;
+};
+
+/* Used for the RX and TX queues for packets */
+struct xdp_rxtx_ring {
+	struct xdp_ring ptrs;
+	struct xdp_desc desc[0] ____cacheline_aligned_in_smp;
+};
+
+/* Used for the fill and completion queues for buffers */
+struct xdp_umem_ring {
+	struct xdp_ring ptrs;
+	u32 desc[0] ____cacheline_aligned_in_smp;
+};
+
 struct xsk_queue {
 	struct xdp_umem_props umem_props;
 	u32 ring_mask;