xsk: add support to allow unaligned chunk placement

Currently, addresses are chunk size aligned. This means, we are very
restricted in terms of where we can place chunk within the umem. For
example, if we have a chunk size of 2k, then our chunks can only be placed
at 0,2k,4k,6k,8k... and so on (ie. every 2k starting from 0).

This patch introduces the ability to use unaligned chunks. With these
changes, we are no longer bound to having to place chunks at a 2k (or
whatever your chunk size is) interval. Since we are no longer dealing with
aligned chunks, they can now cross page boundaries. Checks for page
contiguity have been added in order to keep track of which pages are
followed by a physically contiguous page.

Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 76 insertions, 18 deletions

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ee4428a892fa..187fd157fcff 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL(xsk_umem_has_addrs);
 
 u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
 {
-	return xskq_peek_addr(umem->fq, addr);
+	return xskq_peek_addr(umem->fq, addr, umem);
 }
 EXPORT_SYMBOL(xsk_umem_peek_addr);
 
@@ -115,21 +115,43 @@ bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
 }
 EXPORT_SYMBOL(xsk_umem_uses_need_wakeup);
 
+/* If a buffer crosses a page boundary, we need to do 2 memcpy's, one for
+ * each page. This is only required in copy mode.
+ */
+static void __xsk_rcv_memcpy(struct xdp_umem *umem, u64 addr, void *from_buf,
+			     u32 len, u32 metalen)
+{
+	void *to_buf = xdp_umem_get_data(umem, addr);
+
+	addr = xsk_umem_add_offset_to_addr(addr);
+	if (xskq_crosses_non_contig_pg(umem, addr, len + metalen)) {
+		void *next_pg_addr = umem->pages[(addr >> PAGE_SHIFT) + 1].addr;
+		u64 page_start = addr & ~(PAGE_SIZE - 1);
+		u64 first_len = PAGE_SIZE - (addr - page_start);
+
+		memcpy(to_buf, from_buf, first_len + metalen);
+		memcpy(next_pg_addr, from_buf + first_len, len - first_len);
+
+		return;
+	}
+
+	memcpy(to_buf, from_buf, len + metalen);
+}
+
 static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
-	void *to_buf, *from_buf;
+	u64 offset = xs->umem->headroom;
+	u64 addr, memcpy_addr;
+	void *from_buf;
 	u32 metalen;
-	u64 addr;
 	int err;
 
-	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
+	if (!xskq_peek_addr(xs->umem->fq, &addr, xs->umem) ||
 	    len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
 		xs->rx_dropped++;
 		return -ENOSPC;
 	}
 
-	addr += xs->umem->headroom;
-
 	if (unlikely(xdp_data_meta_unsupported(xdp))) {
 		from_buf = xdp->data;
 		metalen = 0;
@@ -138,9 +160,11 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		metalen = xdp->data - xdp->data_meta;
 	}
 
-	to_buf = xdp_umem_get_data(xs->umem, addr);
-	memcpy(to_buf, from_buf, len + metalen);
-	addr += metalen;
+	memcpy_addr = xsk_umem_adjust_offset(xs->umem, addr, offset);
+	__xsk_rcv_memcpy(xs->umem, memcpy_addr, from_buf, len, metalen);
+
+	offset += metalen;
+	addr = xsk_umem_adjust_offset(xs->umem, addr, offset);
 	err = xskq_produce_batch_desc(xs->rx, addr, len);
 	if (!err) {
 		xskq_discard_addr(xs->umem->fq);
@@ -185,6 +209,7 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
 	u32 metalen = xdp->data - xdp->data_meta;
 	u32 len = xdp->data_end - xdp->data;
+	u64 offset = xs->umem->headroom;
 	void *buffer;
 	u64 addr;
 	int err;
@@ -196,17 +221,17 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 		goto out_unlock;
 	}
 
-	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
+	if (!xskq_peek_addr(xs->umem->fq, &addr, xs->umem) ||
 	    len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
 		err = -ENOSPC;
 		goto out_drop;
 	}
 
-	addr += xs->umem->headroom;
-
+	addr = xsk_umem_adjust_offset(xs->umem, addr, offset);
 	buffer = xdp_umem_get_data(xs->umem, addr);
 	memcpy(buffer, xdp->data_meta, len + metalen);
-	addr += metalen;
+
+	addr = xsk_umem_adjust_offset(xs->umem, addr, metalen);
 	err = xskq_produce_batch_desc(xs->rx, addr, len);
 	if (err)
 		goto out_drop;
@@ -250,7 +275,7 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
-		if (!xskq_peek_desc(xs->tx, desc))
+		if (!xskq_peek_desc(xs->tx, desc, umem))
 			continue;
 
 		if (xskq_produce_addr_lazy(umem->cq, desc->addr))
@@ -304,7 +329,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 	if (xs->queue_id >= xs->dev->real_num_tx_queues)
 		goto out;
 
-	while (xskq_peek_desc(xs->tx, &desc)) {
+	while (xskq_peek_desc(xs->tx, &desc, xs->umem)) {
 		char *buffer;
 		u64 addr;
 		u32 len;
@@ -333,7 +358,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 		skb->dev = xs->dev;
 		skb->priority = sk->sk_priority;
 		skb->mark = sk->sk_mark;
-		skb_shinfo(skb)->destructor_arg = (void *)(long)addr;
+		skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
 		skb->destructor = xsk_destruct_skb;
 
 		err = dev_direct_xmit(skb, xs->queue_id);
@@ -526,6 +551,24 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd)
 	return sock;
 }
 
+/* Check if umem pages are contiguous.
+ * If zero-copy mode, use the DMA address to do the page contiguity check
+ * For all other modes we use addr (kernel virtual address)
+ * Store the result in the low bits of addr.
+ */
+static void xsk_check_page_contiguity(struct xdp_umem *umem, u32 flags)
+{
+	struct xdp_umem_page *pgs = umem->pages;
+	int i, is_contig;
+
+	for (i = 0; i < umem->npgs - 1; i++) {
+		is_contig = (flags & XDP_ZEROCOPY) ?
+			(pgs[i].dma + PAGE_SIZE == pgs[i + 1].dma) :
+			(pgs[i].addr + PAGE_SIZE == pgs[i + 1].addr);
+		pgs[i].addr += is_contig << XSK_NEXT_PG_CONTIG_SHIFT;
+	}
+}
+
 static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 {
 	struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
@@ -616,6 +659,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		err = xdp_umem_assign_dev(xs->umem, dev, qid, flags);
 		if (err)
 			goto out_unlock;
+
+		xsk_check_page_contiguity(xs->umem, flags);
 	}
 
 	xs->dev = dev;
@@ -636,6 +681,13 @@ out_release:
 	return err;
 }
 
+struct xdp_umem_reg_v1 {
+	__u64 addr; /* Start of packet data area */
+	__u64 len; /* Length of packet data area */
+	__u32 chunk_size;
+	__u32 headroom;
+};
+
 static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			  char __user *optval, unsigned int optlen)
 {
@@ -673,10 +725,16 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 	}
 	case XDP_UMEM_REG:
 	{
-		struct xdp_umem_reg mr;
+		size_t mr_size = sizeof(struct xdp_umem_reg);
+		struct xdp_umem_reg mr = {};
 		struct xdp_umem *umem;
 
-		if (copy_from_user(&mr, optval, sizeof(mr)))
+		if (optlen < sizeof(struct xdp_umem_reg_v1))
+			return -EINVAL;
+		else if (optlen < sizeof(mr))
+			mr_size = sizeof(struct xdp_umem_reg_v1);
+
+		if (copy_from_user(&mr, optval, mr_size))
 			return -EFAULT;
 
 		mutex_lock(&xs->mutex);