Commit cd2d5b52 authored by Ben Hutchings's avatar Ben Hutchings
Browse files

sfc: Add SR-IOV back-end support for SFC9000 family 



On the SFC9000 family, each port has 1024 Virtual Interfaces (VIs),
each with an RX queue, a TX queue, an event queue and a mailbox
register.  These may be assigned to up to 127 SR-IOV virtual functions
per port, with up to 64 VIs per VF.

We allocate an extra channel (IRQ and event queue only) to receive
requests from VF drivers.

There is a per-port limit of 4 concurrent RX queue flushes, and queue
flushes may be initiated by the MC in response to a Function Level
Reset (FLR) of a VF.  Therefore, when SR-IOV is in use, we submit all
flush requests via the MC.

The RSS indirection table is shared with VFs, so the number of RX
queues used in the PF is limited to the number of VIs per VF.

This is almost entirely the work of Steve Hodgson, formerly
shodgson@solarflare.com.

Signed-off-by: default avatarBen Hutchings <bhutchings@solarflare.com>
parent 28e47c49

drivers/net/ethernet/sfc/Kconfig

+8 −0
Original line number Diff line number Diff line
@@ -26,3 +26,11 @@ config SFC_MCDI_MON 
	----help---

	  This exposes the on-board firmware-managed sensors as a

	  hardware monitor device.

config SFC_SRIOV

	bool "Solarflare SFC9000-family SR-IOV support"

	depends on SFC && PCI_IOV

	default y

	---help---

	  This enables support for the SFC9000 I/O Virtualization

	  features, allowing accelerated network performance in

	  virtualized environments.

drivers/net/ethernet/sfc/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -4,5 +4,6 @@ sfc-y += efx.o nic.o falcon.o siena.o tx.o rx.o filter.o \ 
			   tenxpress.o txc43128_phy.o falcon_boards.o \

			   mcdi.o mcdi_phy.o mcdi_mon.o

sfc-$(CONFIG_SFC_MTD)	+= mtd.o

sfc-$(CONFIG_SFC_SRIOV)	+= siena_sriov.o



obj-$(CONFIG_SFC)	+= sfc.o

drivers/net/ethernet/sfc/efx.c

+55 −15
Original line number Diff line number Diff line
@@ -1175,9 +1175,9 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx) 
	unsigned int count;

	int cpu;



	if (rss_cpus)

		return rss_cpus;



	if (rss_cpus) {

		count = rss_cpus;

	} else {

		if (unlikely(!zalloc_cpumask_var(&thread_mask, GFP_KERNEL))) {

			netif_warn(efx, probe, efx->net_dev,

				   "RSS disabled due to allocation failure\n");
@@ -1194,6 +1194,21 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx) 
		}



		free_cpumask_var(thread_mask);

	}



	/* If RSS is requested for the PF *and* VFs then we can't write RSS

	 * table entries that are inaccessible to VFs

	 */

	if (efx_sriov_wanted(efx) && efx_vf_size(efx) > 1 &&

	    count > efx_vf_size(efx)) {

		netif_warn(efx, probe, efx->net_dev,

			   "Reducing number of RSS channels from %u to %u for "

			   "VF support. Increase vf-msix-limit to use more "

			   "channels on the PF.\n",

			   count, efx_vf_size(efx));

		count = efx_vf_size(efx);

	}



	return count;

}
@@ -1327,6 +1342,10 @@ static int efx_probe_interrupts(struct efx_nic *efx) 
		}

	}



	/* RSS might be usable on VFs even if it is disabled on the PF */

	efx->rss_spread = (efx->n_rx_channels > 1 ?

			   efx->n_rx_channels : efx_vf_size(efx));



	return 0;

}
@@ -1426,7 +1445,7 @@ static int efx_probe_nic(struct efx_nic *efx) 
		get_random_bytes(&efx->rx_hash_key, sizeof(efx->rx_hash_key));

	for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)

		efx->rx_indir_table[i] =

			ethtool_rxfh_indir_default(i, efx->n_rx_channels);

			ethtool_rxfh_indir_default(i, efx->rss_spread);



	efx_set_channels(efx);

	netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
@@ -1915,6 +1934,7 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data) 
	}



	memcpy(net_dev->dev_addr, new_addr, net_dev->addr_len);

	efx_sriov_mac_address_changed(efx);



	/* Reconfigure the MAC */

	mutex_lock(&efx->mac_lock);
@@ -1981,6 +2001,12 @@ static const struct net_device_ops efx_netdev_ops = { 
	.ndo_set_mac_address	= efx_set_mac_address,

	.ndo_set_rx_mode	= efx_set_rx_mode,

	.ndo_set_features	= efx_set_features,

#ifdef CONFIG_SFC_SRIOV

	.ndo_set_vf_mac		= efx_sriov_set_vf_mac,

	.ndo_set_vf_vlan	= efx_sriov_set_vf_vlan,

	.ndo_set_vf_spoofchk	= efx_sriov_set_vf_spoofchk,

	.ndo_get_vf_config	= efx_sriov_get_vf_config,

#endif

#ifdef CONFIG_NET_POLL_CONTROLLER

	.ndo_poll_controller = efx_netpoll,

#endif
@@ -2150,6 +2176,7 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok) 


	efx_start_interrupts(efx, false);

	efx_restore_filters(efx);

	efx_sriov_reset(efx);



	mutex_unlock(&efx->mac_lock);
@@ -2440,6 +2467,7 @@ static void efx_pci_remove(struct pci_dev *pci_dev) 
	rtnl_unlock();



	efx_stop_interrupts(efx, false);

	efx_sriov_fini(efx);

	efx_unregister_netdev(efx);



	efx_mtd_remove(efx);
@@ -2581,6 +2609,11 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, 
	if (rc)

		goto fail4;



	rc = efx_sriov_init(efx);

	if (rc)

		netif_err(efx, probe, efx->net_dev,

			  "SR-IOV can't be enabled rc %d\n", rc);



	netif_dbg(efx, probe, efx->net_dev, "initialisation successful\n");



	/* Try to create MTDs, but allow this to fail */
@@ -2732,6 +2765,10 @@ static int __init efx_init_module(void) 
	if (rc)

		goto err_notifier;



	rc = efx_init_sriov();

	if (rc)

		goto err_sriov;



	reset_workqueue = create_singlethread_workqueue("sfc_reset");

	if (!reset_workqueue) {

		rc = -ENOMEM;
@@ -2747,6 +2784,8 @@ static int __init efx_init_module(void) 
 err_pci:

	destroy_workqueue(reset_workqueue);

 err_reset:

	efx_fini_sriov();

 err_sriov:

	unregister_netdevice_notifier(&efx_netdev_notifier);

 err_notifier:

	return rc;
@@ -2758,6 +2797,7 @@ static void __exit efx_exit_module(void) 


	pci_unregister_driver(&efx_pci_driver);

	destroy_workqueue(reset_workqueue);

	efx_fini_sriov();

	unregister_netdevice_notifier(&efx_netdev_notifier);



}

drivers/net/ethernet/sfc/ethtool.c

+2 −1
Original line number Diff line number Diff line
@@ -1085,7 +1085,8 @@ static u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev) 
{

	struct efx_nic *efx = netdev_priv(net_dev);



	return (efx_nic_rev(efx) < EFX_REV_FALCON_B0 ?

	return ((efx_nic_rev(efx) < EFX_REV_FALCON_B0 ||

		 efx->n_rx_channels == 1) ?

		0 : ARRAY_SIZE(efx->rx_indir_table));

}

drivers/net/ethernet/sfc/mcdi.c

+34 −0
Original line number Diff line number Diff line
@@ -560,6 +560,9 @@ void efx_mcdi_process_event(struct efx_channel *channel, 
	case MCDI_EVENT_CODE_MAC_STATS_DMA:

		/* MAC stats are gather lazily.  We can ignore this. */

		break;

	case MCDI_EVENT_CODE_FLR:

		efx_sriov_flr(efx, MCDI_EVENT_FIELD(*event, FLR_VF));

		break;



	default:

		netif_err(efx, hw, efx->net_dev, "Unknown MCDI event 0x%x\n",
@@ -1154,6 +1157,37 @@ fail: 
	return rc;

}



int efx_mcdi_flush_rxqs(struct efx_nic *efx)

{

	struct efx_channel *channel;

	struct efx_rx_queue *rx_queue;

	__le32 *qid;

	int rc, count;



	qid = kmalloc(EFX_MAX_CHANNELS * sizeof(*qid), GFP_KERNEL);

	if (qid == NULL)

		return -ENOMEM;



	count = 0;

	efx_for_each_channel(channel, efx) {

		efx_for_each_channel_rx_queue(rx_queue, channel) {

			if (rx_queue->flush_pending) {

				rx_queue->flush_pending = false;

				atomic_dec(&efx->rxq_flush_pending);

				qid[count++] = cpu_to_le32(

					efx_rx_queue_index(rx_queue));

			}

		}

	}



	rc = efx_mcdi_rpc(efx, MC_CMD_FLUSH_RX_QUEUES, (u8 *)qid,

			  count * sizeof(*qid), NULL, 0, NULL);

	WARN_ON(rc > 0);



	kfree(qid);



	return rc;

}



int efx_mcdi_wol_filter_reset(struct efx_nic *efx)

{

CRA Git | Maintained and supported by SUSTech CRA and CCSE