Commit 7361f9c3 authored by Magnus Karlsson's avatar Magnus Karlsson Committed by Daniel Borkmann
Browse files

xsk: Move fill and completion rings to buffer pool 



Move the fill and completion rings from the umem to the buffer
pool. This so that we in a later commit can share the umem
between multiple HW queue ids. In this case, we need one fill and
completion ring per queue id. As the buffer pool is per queue id
and napi id this is a natural place for it and one umem
struture can be shared between these buffer pools.

Signed-off-by: default avatarMagnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Acked-by: default avatarBjörn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-5-git-send-email-magnus.karlsson@intel.com
parent 1c1efc2a

include/net/xdp_sock.h

+2 −2
Original line number Diff line number Diff line
@@ -18,8 +18,6 @@ struct xsk_queue; 
struct xdp_buff;



struct xdp_umem {

	struct xsk_queue *fq;

	struct xsk_queue *cq;

	u64 size;

	u32 headroom;

	u32 chunk_size;
@@ -77,6 +75,8 @@ struct xdp_sock { 
	struct list_head map_list;

	/* Protects map_list */

	spinlock_t map_list_lock;

	struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */

	struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */

};



#ifdef CONFIG_XDP_SOCKETS

include/net/xsk_buff_pool.h

+1 −1
Original line number Diff line number Diff line
@@ -30,6 +30,7 @@ struct xdp_buff_xsk { 


struct xsk_buff_pool {

	struct xsk_queue *fq;

	struct xsk_queue *cq;

	struct list_head free_list;

	dma_addr_t *dma_pages;

	struct xdp_buff_xsk *heads;
@@ -57,7 +58,6 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, 
						struct xdp_umem *umem);

int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,

		  u16 queue_id, u16 flags);

void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq);

void xp_destroy(struct xsk_buff_pool *pool);

void xp_release(struct xdp_buff_xsk *xskb);

void xp_get_pool(struct xsk_buff_pool *pool);

net/xdp/xdp_umem.c

+0 −15
Original line number Diff line number Diff line
@@ -85,16 +85,6 @@ static void xdp_umem_release(struct xdp_umem *umem) 


	ida_simple_remove(&umem_ida, umem->id);



	if (umem->fq) {

		xskq_destroy(umem->fq);

		umem->fq = NULL;

	}



	if (umem->cq) {

		xskq_destroy(umem->cq);

		umem->cq = NULL;

	}



	xdp_umem_unpin_pages(umem);



	xdp_umem_unaccount_pages(umem);
@@ -278,8 +268,3 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) 


	return umem;

}
 


bool xdp_umem_validate_queues(struct xdp_umem *umem)

{

	return umem->fq && umem->cq;

}

net/xdp/xsk.c

+27 −21
Original line number Diff line number Diff line
@@ -36,7 +36,7 @@ static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); 
bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)

{

	return READ_ONCE(xs->rx) &&  READ_ONCE(xs->umem) &&

		READ_ONCE(xs->umem->fq);

		(xs->pool->fq || READ_ONCE(xs->fq_tmp));

}



void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
@@ -46,7 +46,7 @@ void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) 
	if (umem->need_wakeup & XDP_WAKEUP_RX)

		return;



	umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP;

	pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP;

	umem->need_wakeup |= XDP_WAKEUP_RX;

}

EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
@@ -76,7 +76,7 @@ void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) 
	if (!(umem->need_wakeup & XDP_WAKEUP_RX))

		return;



	umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;

	pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;

	umem->need_wakeup &= ~XDP_WAKEUP_RX;

}

EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
@@ -254,7 +254,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, 
static void xsk_flush(struct xdp_sock *xs)

{

	xskq_prod_submit(xs->rx);

	__xskq_cons_release(xs->umem->fq);

	__xskq_cons_release(xs->pool->fq);

	sock_def_readable(&xs->sk);

}
@@ -297,7 +297,7 @@ void __xsk_map_flush(void) 


void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)

{

	xskq_prod_submit_n(pool->umem->cq, nb_entries);

	xskq_prod_submit_n(pool->cq, nb_entries);

}

EXPORT_SYMBOL(xsk_tx_completed);
@@ -331,7 +331,7 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) 
		 * if there is space in it. This avoids having to implement

		 * any buffering in the Tx path.

		 */

		if (xskq_prod_reserve_addr(umem->cq, desc->addr))

		if (xskq_prod_reserve_addr(pool->cq, desc->addr))

			goto out;



		xskq_cons_release(xs->tx);
@@ -369,7 +369,7 @@ static void xsk_destruct_skb(struct sk_buff *skb) 
	unsigned long flags;



	spin_lock_irqsave(&xs->tx_completion_lock, flags);

	xskq_prod_submit_addr(xs->umem->cq, addr);

	xskq_prod_submit_addr(xs->pool->cq, addr);

	spin_unlock_irqrestore(&xs->tx_completion_lock, flags);



	sock_wfree(skb);
@@ -413,7 +413,7 @@ static int xsk_generic_xmit(struct sock *sk) 
		 * if there is space in it. This avoids having to implement

		 * any buffering in the Tx path.

		 */

		if (unlikely(err) || xskq_prod_reserve(xs->umem->cq)) {

		if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {

			kfree_skb(skb);

			goto out;

		}
@@ -606,6 +606,8 @@ static int xsk_release(struct socket *sock) 


	xskq_destroy(xs->rx);

	xskq_destroy(xs->tx);

	xskq_destroy(xs->fq_tmp);

	xskq_destroy(xs->cq_tmp);



	sock_orphan(sk);

	sock->sk = NULL;
@@ -633,6 +635,11 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd) 
	return sock;

}



static bool xsk_validate_queues(struct xdp_sock *xs)

{

	return xs->fq_tmp && xs->cq_tmp;

}



static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)

{

	struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
@@ -689,6 +696,12 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) 
			goto out_unlock;

		}



		if (xs->fq_tmp || xs->cq_tmp) {

			/* Do not allow setting your own fq or cq. */

			err = -EINVAL;

			goto out_unlock;

		}



		sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd);

		if (IS_ERR(sock)) {

			err = PTR_ERR(sock);
@@ -713,7 +726,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) 
		xdp_get_umem(umem_xs->umem);

		WRITE_ONCE(xs->umem, umem_xs->umem);

		sockfd_put(sock);

	} else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {

	} else if (!xs->umem || !xsk_validate_queues(xs)) {

		err = -EINVAL;

		goto out_unlock;

	} else {
@@ -849,11 +862,9 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, 
			return -EINVAL;

		}



		q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq :

			&xs->umem->cq;

		q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp :

			&xs->cq_tmp;

		err = xsk_init_queue(entries, q, true);

		if (optname == XDP_UMEM_FILL_RING)

			xp_set_fq(xs->pool, *q);

		mutex_unlock(&xs->mutex);

		return err;

	}
@@ -920,7 +931,7 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname, 
		if (extra_stats) {

			stats.rx_ring_full = xs->rx_queue_full;

			stats.rx_fill_ring_empty_descs =

				xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;

				xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0;

			stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx);

		} else {

			stats.rx_dropped += xs->rx_queue_full;
@@ -1022,7 +1033,6 @@ static int xsk_mmap(struct file *file, struct socket *sock, 
	unsigned long size = vma->vm_end - vma->vm_start;

	struct xdp_sock *xs = xdp_sk(sock->sk);

	struct xsk_queue *q = NULL;

	struct xdp_umem *umem;

	unsigned long pfn;

	struct page *qpg;
@@ -1034,16 +1044,12 @@ static int xsk_mmap(struct file *file, struct socket *sock, 
	} else if (offset == XDP_PGOFF_TX_RING) {

		q = READ_ONCE(xs->tx);

	} else {

		umem = READ_ONCE(xs->umem);

		if (!umem)

			return -EINVAL;



		/* Matches the smp_wmb() in XDP_UMEM_REG */

		smp_rmb();

		if (offset == XDP_UMEM_PGOFF_FILL_RING)

			q = READ_ONCE(umem->fq);

			q = READ_ONCE(xs->fq_tmp);

		else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)

			q = READ_ONCE(umem->cq);

			q = READ_ONCE(xs->cq_tmp);

	}



	if (!q)

net/xdp/xsk_buff_pool.c

+15 −5
Original line number Diff line number Diff line
@@ -65,6 +65,11 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, 
	INIT_LIST_HEAD(&pool->free_list);

	refcount_set(&pool->users, 1);



	pool->fq = xs->fq_tmp;

	pool->cq = xs->cq_tmp;

	xs->fq_tmp = NULL;

	xs->cq_tmp = NULL;



	for (i = 0; i < pool->free_heads_cnt; i++) {

		xskb = &pool->heads[i];

		xskb->pool = pool;
@@ -81,11 +86,6 @@ out: 
	return NULL;

}



void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq)

{

	pool->fq = fq;

}



void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)

{

	u32 i;
@@ -189,6 +189,16 @@ static void xp_release_deferred(struct work_struct *work) 
	xp_clear_dev(pool);

	rtnl_unlock();



	if (pool->fq) {

		xskq_destroy(pool->fq);

		pool->fq = NULL;

	}



	if (pool->cq) {

		xskq_destroy(pool->cq);

		pool->cq = NULL;

	}



	xdp_put_umem(pool->umem);

	xp_destroy(pool);

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE