Re: [Xen-devel] [PATCH 5/8] netback: multi-page ring support

[Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>]

On Fri, Feb 15, 2013 at 04:00:06PM +0000, Wei Liu wrote:

Please a bit more description. Say which XenBus feature this
is using.  And that probably means another patch to the Xen
tree to document this.


> Signed-off-by: Wei Liu <wei.liu2@citrix.com>
> ---
>  drivers/net/xen-netback/common.h    |   30 ++++++--
>  drivers/net/xen-netback/interface.c |   46 +++++++++--
>  drivers/net/xen-netback/netback.c   |   73 ++++++++----------
>  drivers/net/xen-netback/xenbus.c    |  143 +++++++++++++++++++++++++++++++++--
>  4 files changed, 229 insertions(+), 63 deletions(-)
> 
> diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
> index 35d8772..f541ba9 100644
> --- a/drivers/net/xen-netback/common.h
> +++ b/drivers/net/xen-netback/common.h
> @@ -45,6 +45,12 @@
>  #include <xen/grant_table.h>
>  #include <xen/xenbus.h>
>  
> +#define NETBK_MAX_RING_PAGE_ORDER XENBUS_MAX_RING_PAGE_ORDER
> +#define NETBK_MAX_RING_PAGES      (1U << NETBK_MAX_RING_PAGE_ORDER)
> +
> +#define NETBK_MAX_TX_RING_SIZE XEN_NETIF_TX_RING_SIZE(NETBK_MAX_RING_PAGES)
> +#define NETBK_MAX_RX_RING_SIZE XEN_NETIF_RX_RING_SIZE(NETBK_MAX_RING_PAGES)
> +
>  struct xen_netbk;
>  
>  struct xenvif {
> @@ -66,6 +72,8 @@ struct xenvif {
>  	/* The shared rings and indexes. */
>  	struct xen_netif_tx_back_ring tx;
>  	struct xen_netif_rx_back_ring rx;
> +	unsigned int nr_tx_handles;
> +	unsigned int nr_rx_handles;
>  
>  	/* Frontend feature information. */
>  	u8 can_sg:1;
> @@ -105,15 +113,19 @@ static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif)
>  	return to_xenbus_device(vif->dev->dev.parent);
>  }
>  
> -#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
> -#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
> +#define XEN_NETIF_TX_RING_SIZE(_nr_pages)		\
> +	__CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE * (_nr_pages))
> +#define XEN_NETIF_RX_RING_SIZE(_nr_pages)		\
> +	__CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE * (_nr_pages))
>  
>  struct xenvif *xenvif_alloc(struct device *parent,
>  			    domid_t domid,
>  			    unsigned int handle);
>  
> -int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
> -		   unsigned long rx_ring_ref, unsigned int evtchn);
> +int xenvif_connect(struct xenvif *vif,
> +		   unsigned long *tx_ring_ref, unsigned int tx_ring_order,
> +		   unsigned long *rx_ring_ref, unsigned int rx_ring_order,
> +		   unsigned int evtchn);
>  void xenvif_disconnect(struct xenvif *vif);
>  
>  void xenvif_get(struct xenvif *vif);
> @@ -129,10 +141,12 @@ int xen_netbk_rx_ring_full(struct xenvif *vif);
>  int xen_netbk_must_stop_queue(struct xenvif *vif);
>  
>  /* (Un)Map communication rings. */
> -void xen_netbk_unmap_frontend_rings(struct xenvif *vif);
> +void xen_netbk_unmap_frontend_rings(struct xenvif *vif, void *addr);
>  int xen_netbk_map_frontend_rings(struct xenvif *vif,
> -				 grant_ref_t tx_ring_ref,
> -				 grant_ref_t rx_ring_ref);
> +				 void **addr,
> +				 int domid,
> +				 int *ring_ref,
> +				 unsigned int ring_ref_count);
>  
>  /* (De)Register a xenvif with the netback backend. */
>  void xen_netbk_add_xenvif(struct xenvif *vif);
> @@ -158,4 +172,6 @@ void xenvif_carrier_off(struct xenvif *vif);
>  /* Returns number of ring slots required to send an skb to the frontend */
>  unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb);
>  
> +extern unsigned int MODPARM_netback_max_tx_ring_page_order;
> +extern unsigned int MODPARM_netback_max_rx_ring_page_order;
>  #endif /* __XEN_NETBACK__COMMON_H__ */
> diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
> index db638e1..fa4d46d 100644
> --- a/drivers/net/xen-netback/interface.c
> +++ b/drivers/net/xen-netback/interface.c
> @@ -305,10 +305,16 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
>  	return vif;
>  }
>  
> -int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
> -		   unsigned long rx_ring_ref, unsigned int evtchn)
> +int xenvif_connect(struct xenvif *vif,
> +		   unsigned long *tx_ring_ref, unsigned int tx_ring_ref_count,
> +		   unsigned long *rx_ring_ref, unsigned int rx_ring_ref_count,
> +		   unsigned int evtchn)
>  {
>  	int err = -ENOMEM;
> +	void *addr;
> +	struct xen_netif_tx_sring *txs;
> +	struct xen_netif_rx_sring *rxs;
> +	int tmp[NETBK_MAX_RING_PAGES], i;
>  
>  	/* Already connected through? */
>  	if (vif->irq)
> @@ -316,15 +322,36 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
>  
>  	__module_get(THIS_MODULE);
>  
> -	err = xen_netbk_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
> +	for (i = 0; i < tx_ring_ref_count; i++)
> +		tmp[i] = tx_ring_ref[i];
> +
> +	err = xen_netbk_map_frontend_rings(vif, &addr, vif->domid,
> +					   tmp, tx_ring_ref_count);
>  	if (err < 0)
>  		goto err;
>  
> +	txs = addr;
> +	BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE * tx_ring_ref_count);
> +	vif->nr_tx_handles = tx_ring_ref_count;
> +
> +	for (i = 0; i < rx_ring_ref_count; i++)
> +		tmp[i] = rx_ring_ref[i];
> +
> +	err = xen_netbk_map_frontend_rings(vif, &addr, vif->domid,
> +					   tmp, rx_ring_ref_count);
> +
> +	if (err < 0)
> +		goto err_tx_unmap;
> +
> +	rxs = addr;
> +	BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE * rx_ring_ref_count);
> +	vif->nr_rx_handles = rx_ring_ref_count;
> +
>  	err = bind_interdomain_evtchn_to_irqhandler(
>  		vif->domid, evtchn, xenvif_interrupt, 0,
>  		vif->dev->name, vif);
>  	if (err < 0)
> -		goto err_unmap;
> +		goto err_rx_unmap;
>  	vif->irq = err;
>  	disable_irq(vif->irq);
>  
> @@ -340,8 +367,12 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
>  	rtnl_unlock();
>  
>  	return 0;
> -err_unmap:
> -	xen_netbk_unmap_frontend_rings(vif);
> +err_rx_unmap:
> +	xen_netbk_unmap_frontend_rings(vif, (void *)vif->rx.sring);
> +	vif->nr_rx_handles = 0;
> +err_tx_unmap:
> +	xen_netbk_unmap_frontend_rings(vif, (void *)vif->tx.sring);
> +	vif->nr_tx_handles = 0;
>  err:
>  	module_put(THIS_MODULE);
>  	return err;
> @@ -382,7 +413,8 @@ void xenvif_disconnect(struct xenvif *vif)
>  
>  	unregister_netdev(vif->dev);
>  
> -	xen_netbk_unmap_frontend_rings(vif);
> +	xen_netbk_unmap_frontend_rings(vif, (void *)vif->tx.sring);
> +	xen_netbk_unmap_frontend_rings(vif, (void *)vif->rx.sring);
>  
>  	free_netdev(vif->dev);
>  
> diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
> index 98ccea9..644c760 100644
> --- a/drivers/net/xen-netback/netback.c
> +++ b/drivers/net/xen-netback/netback.c
> @@ -47,6 +47,19 @@
>  #include <asm/xen/hypercall.h>
>  #include <asm/xen/page.h>
>  
> +unsigned int MODPARM_netback_max_rx_ring_page_order = NETBK_MAX_RING_PAGE_ORDER;
> +module_param_named(netback_max_rx_ring_page_order,
> +		   MODPARM_netback_max_rx_ring_page_order, uint, 0);
> +MODULE_PARM_DESC(netback_max_rx_ring_page_order,
> +		 "Maximum supported receiver ring page order");
> +
> +unsigned int MODPARM_netback_max_tx_ring_page_order = NETBK_MAX_RING_PAGE_ORDER;
> +module_param_named(netback_max_tx_ring_page_order,
> +		   MODPARM_netback_max_tx_ring_page_order, uint, 0);
> +MODULE_PARM_DESC(netback_max_tx_ring_page_order,
> +		 "Maximum supported transmitter ring page order");
> +
> +

These should also show up in Documentation/ABI/sysfs/stable/xen* something

But more importantly.. why not make the TX=RX order and just have one
option?

>  struct pending_tx_info {
>  	struct xen_netif_tx_request req;
>  	struct xenvif *vif;
> @@ -59,7 +72,7 @@ struct netbk_rx_meta {
>  	int gso_size;
>  };
>  
> -#define MAX_PENDING_REQS 256
> +#define MAX_PENDING_REQS NETBK_MAX_TX_RING_SIZE
>  
>  /* Discriminate from any valid pending_idx value. */
>  #define INVALID_PENDING_IDX 0xFFFF
> @@ -111,8 +124,8 @@ struct xen_netbk {
>  	 * head/fragment page uses 2 copy operations because it
>  	 * straddles two buffers in the frontend.
>  	 */
> -	struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
> -	struct netbk_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
> +	struct gnttab_copy grant_copy_op[2*NETBK_MAX_RX_RING_SIZE];
> +	struct netbk_rx_meta meta[2*NETBK_MAX_RX_RING_SIZE];
>  };
>  
>  static struct xen_netbk *xen_netbk;
> @@ -262,7 +275,8 @@ int xen_netbk_rx_ring_full(struct xenvif *vif)
>  	RING_IDX needed = max_required_rx_slots(vif);
>  
>  	return ((vif->rx.sring->req_prod - peek) < needed) ||
> -	       ((vif->rx.rsp_prod_pvt + XEN_NETIF_RX_RING_SIZE - peek) < needed);
> +	       ((vif->rx.rsp_prod_pvt +
> +		 XEN_NETIF_RX_RING_SIZE(vif->nr_rx_handles) - peek) < needed);
>  }
>  
>  int xen_netbk_must_stop_queue(struct xenvif *vif)
> @@ -657,7 +671,8 @@ static void xen_netbk_rx_action(struct xen_netbk *netbk)
>  		__skb_queue_tail(&rxq, skb);
>  
>  		/* Filled the batch queue? */
> -		if (count + MAX_SKB_FRAGS >= XEN_NETIF_RX_RING_SIZE)
> +		if (count + MAX_SKB_FRAGS >=
> +		    XEN_NETIF_RX_RING_SIZE(vif->nr_rx_handles))
>  			break;
>  	}
>  
> @@ -1292,12 +1307,12 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
>  			continue;
>  
>  		if (vif->tx.sring->req_prod - vif->tx.req_cons >
> -		    XEN_NETIF_TX_RING_SIZE) {
> +		    XEN_NETIF_TX_RING_SIZE(vif->nr_tx_handles)) {
>  			netdev_err(vif->dev,
>  				   "Impossible number of requests. "
>  				   "req_prod %d, req_cons %d, size %ld\n",
>  				   vif->tx.sring->req_prod, vif->tx.req_cons,
> -				   XEN_NETIF_TX_RING_SIZE);
> +				   XEN_NETIF_TX_RING_SIZE(vif->nr_tx_handles));
>  			netbk_fatal_tx_err(vif);
>  			continue;
>  		}
> @@ -1644,48 +1659,22 @@ static int xen_netbk_kthread(void *data)
>  	return 0;
>  }
>  
> -void xen_netbk_unmap_frontend_rings(struct xenvif *vif)
> +void xen_netbk_unmap_frontend_rings(struct xenvif *vif, void *addr)
>  {
> -	if (vif->tx.sring)
> -		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
> -					vif->tx.sring);
> -	if (vif->rx.sring)
> -		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
> -					vif->rx.sring);
> +	if (addr)
> +		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif), addr);
>  }
>  
>  int xen_netbk_map_frontend_rings(struct xenvif *vif,
> -				 grant_ref_t tx_ring_ref,
> -				 grant_ref_t rx_ring_ref)
> +				 void **vaddr,
> +				 int domid,
> +				 int *ring_ref,
> +				 unsigned int ring_ref_count)
>  {
> -	void *addr;
> -	struct xen_netif_tx_sring *txs;
> -	struct xen_netif_rx_sring *rxs;
> -
> -	int err = -ENOMEM;
> -
> -	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
> -				     &tx_ring_ref, 1, &addr);
> -	if (err)
> -		goto err;
> -
> -	txs = (struct xen_netif_tx_sring *)addr;
> -	BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE);
> +	int err = 0;
>  
>  	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
> -				     &rx_ring_ref, 1, &addr);
> -	if (err)
> -		goto err;
> -
> -	rxs = (struct xen_netif_rx_sring *)addr;
> -	BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE);
> -
> -	vif->rx_req_cons_peek = 0;
> -
> -	return 0;
> -
> -err:
> -	xen_netbk_unmap_frontend_rings(vif);
> +				     ring_ref, ring_ref_count, vaddr);
>  	return err;
>  }
>  
> diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
> index 65d14f2..1791807 100644
> --- a/drivers/net/xen-netback/xenbus.c
> +++ b/drivers/net/xen-netback/xenbus.c
> @@ -114,6 +114,33 @@ static int netback_probe(struct xenbus_device *dev,
>  			goto abort_transaction;
>  		}
>  
> +		/* Multi-page ring support */
> +		if (MODPARM_netback_max_tx_ring_page_order >
> +		    NETBK_MAX_RING_PAGE_ORDER)
> +			MODPARM_netback_max_tx_ring_page_order =
> +				NETBK_MAX_RING_PAGE_ORDER;
> +		err = xenbus_printf(xbt, dev->nodename,
> +				    "max-tx-ring-page-order",
> +				    "%u",
> +				    MODPARM_netback_max_tx_ring_page_order);
> +		if (err) {
> +			message = "writing max-tx-ring-page-order";
> +			goto abort_transaction;
> +		}
> +
> +		if (MODPARM_netback_max_rx_ring_page_order >
> +		    NETBK_MAX_RING_PAGE_ORDER)
> +			MODPARM_netback_max_rx_ring_page_order =
> +				NETBK_MAX_RING_PAGE_ORDER;
> +		err = xenbus_printf(xbt, dev->nodename,
> +				    "max-rx-ring-page-order",
> +				    "%u",
> +				    MODPARM_netback_max_rx_ring_page_order);
> +		if (err) {
> +			message = "writing max-rx-ring-page-order";
> +			goto abort_transaction;
> +		}
> +
>  		err = xenbus_transaction_end(xbt, 0);
>  	} while (err == -EAGAIN);
>  
> @@ -392,22 +419,107 @@ static int connect_rings(struct backend_info *be)
>  {
>  	struct xenvif *vif = be->vif;
>  	struct xenbus_device *dev = be->dev;
> -	unsigned long tx_ring_ref, rx_ring_ref;
>  	unsigned int evtchn, rx_copy;
>  	int err;
>  	int val;
> +	unsigned long tx_ring_ref[NETBK_MAX_RING_PAGES];
> +	unsigned long rx_ring_ref[NETBK_MAX_RING_PAGES];
> +	unsigned int  tx_ring_order;
> +	unsigned int  rx_ring_order;
>  
>  	err = xenbus_gather(XBT_NIL, dev->otherend,
> -			    "tx-ring-ref", "%lu", &tx_ring_ref,
> -			    "rx-ring-ref", "%lu", &rx_ring_ref,
>  			    "event-channel", "%u", &evtchn, NULL);
>  	if (err) {
>  		xenbus_dev_fatal(dev, err,
> -				 "reading %s/ring-ref and event-channel",
> +				 "reading %s/event-channel",
>  				 dev->otherend);
>  		return err;
>  	}
>  
> +	err = xenbus_scanf(XBT_NIL, dev->otherend, "tx-ring-order", "%u",
> +			   &tx_ring_order);
> +	if (err < 0) {
> +		tx_ring_order = 0;
> +
> +		err = xenbus_scanf(XBT_NIL, dev->otherend, "tx-ring-ref", "%lu",
> +				   &tx_ring_ref[0]);
> +		if (err < 0) {
> +			xenbus_dev_fatal(dev, err, "reading %s/tx-ring-ref",
> +					 dev->otherend);
> +			return err;
> +		}
> +	} else {
> +		unsigned int i;
> +
> +		if (tx_ring_order > MODPARM_netback_max_tx_ring_page_order) {
> +			err = -EINVAL;
> +			xenbus_dev_fatal(dev, err,
> +					 "%s/tx-ring-page-order too big",
> +					 dev->otherend);
> +			return err;
> +		}
> +
> +		for (i = 0; i < (1U << tx_ring_order); i++) {
> +			char ring_ref_name[sizeof("tx-ring-ref") + 2];
> +
> +			snprintf(ring_ref_name, sizeof(ring_ref_name),
> +				 "tx-ring-ref%u", i);
> +
> +			err = xenbus_scanf(XBT_NIL, dev->otherend,
> +					   ring_ref_name, "%lu",
> +					   &tx_ring_ref[i]);
> +			if (err < 0) {
> +				xenbus_dev_fatal(dev, err,
> +						 "reading %s/%s",
> +						 dev->otherend,
> +						 ring_ref_name);
> +				return err;
> +			}
> +		}
> +	}
> +
> +	err = xenbus_scanf(XBT_NIL, dev->otherend, "rx-ring-order", "%u",
> +			   &rx_ring_order);
> +	if (err < 0) {
> +		rx_ring_order = 0;
> +
> +		err = xenbus_scanf(XBT_NIL, dev->otherend, "rx-ring-ref", "%lu",
> +				   &rx_ring_ref[0]);
> +		if (err < 0) {
> +			xenbus_dev_fatal(dev, err, "reading %s/rx-ring-ref",
> +					 dev->otherend);
> +			return err;
> +		}
> +	} else {
> +		unsigned int i;
> +
> +		if (rx_ring_order > MODPARM_netback_max_rx_ring_page_order) {
> +			err = -EINVAL;
> +			xenbus_dev_fatal(dev, err,
> +					 "%s/rx-ring-page-order too big",
> +					 dev->otherend);
> +			return err;
> +		}
> +
> +		for (i = 0; i < (1U << rx_ring_order); i++) {
> +			char ring_ref_name[sizeof("rx-ring-ref") + 2];
> +
> +			snprintf(ring_ref_name, sizeof(ring_ref_name),
> +				 "rx-ring-ref%u", i);
> +
> +			err = xenbus_scanf(XBT_NIL, dev->otherend,
> +					   ring_ref_name, "%lu",
> +					   &rx_ring_ref[i]);
> +			if (err < 0) {
> +				xenbus_dev_fatal(dev, err,
> +						 "reading %s/%s",
> +						 dev->otherend,
> +						 ring_ref_name);
> +				return err;
> +			}
> +		}
> +	}
> +
>  	err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
>  			   &rx_copy);
>  	if (err == -ENOENT) {
> @@ -454,11 +566,28 @@ static int connect_rings(struct backend_info *be)
>  	vif->csum = !val;
>  
>  	/* Map the shared frame, irq etc. */
> -	err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref, evtchn);
> +	err = xenvif_connect(vif, tx_ring_ref, (1U << tx_ring_order),
> +			     rx_ring_ref, (1U << rx_ring_order),
> +			     evtchn);
>  	if (err) {
> +		/* construct 1 2 3 / 4 5 6 */
> +		int i;
> +		char txs[3 * (1U << MODPARM_netback_max_tx_ring_page_order)];
> +		char rxs[3 * (1U << MODPARM_netback_max_rx_ring_page_order)];
> +
> +		txs[0] = rxs[0] = 0;
> +
> +		for (i = 0; i < (1U << tx_ring_order); i++)
> +			snprintf(txs+strlen(txs), sizeof(txs)-strlen(txs)-1,
> +				 " %lu", tx_ring_ref[i]);
> +
> +		for (i = 0; i < (1U << rx_ring_order); i++)
> +			snprintf(rxs+strlen(rxs), sizeof(rxs)-strlen(rxs)-1,
> +				 " %lu", rx_ring_ref[i]);
> +
>  		xenbus_dev_fatal(dev, err,
> -				 "mapping shared-frames %lu/%lu port %u",
> -				 tx_ring_ref, rx_ring_ref, evtchn);
> +				 "mapping shared-frames%s /%s port %u",
> +				 txs, rxs, evtchn);
>  		return err;
>  	}
>  	return 0;
> -- 
> 1.7.10.4
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> http://lists.xen.org/xen-devel
>