[net-next PATCH] be2net: Adding PCI SRIOV support

[net-next PATCH] be2net: Adding PCI SRIOV support

[Sarveshwar Bandi]

- Patch adds support to enable PCI SRIOV in the driver and changes to handle initialization of PCI virtual functions.
- Function handler to change mac addresses for VF from its corresponding PF.

Signed-off-by: Sarveshwar Bandi <sarveshwarb@serverengines.com>
---
 drivers/net/benet/be.h      |    9 ++
 drivers/net/benet/be_cmds.c |    4 +
 drivers/net/benet/be_cmds.h |    2 
 drivers/net/benet/be_hw.h   |    3 +
 drivers/net/benet/be_main.c |  222 ++++++++++++++++++++++++++++++++++---------
 5 files changed, 191 insertions(+), 49 deletions(-)

diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h
index 8f07525..20842c5 100644
--- a/drivers/net/benet/be.h
+++ b/drivers/net/benet/be.h
@@ -83,6 +83,8 @@ #define RX_FRAGS_REFILL_WM	(RX_Q_LEN - M
 
 #define FW_VER_LEN		32
 
+#define BE_MAX_VF		32
+
 struct be_dma_mem {
 	void *va;
 	dma_addr_t dma;
@@ -280,8 +282,15 @@ struct be_adapter {
 	u8 port_type;
 	u8 transceiver;
 	u8 generation;		/* BladeEngine ASIC generation */
+
+	bool sriov_enabled;
+	u32 vf_if_handle[BE_MAX_VF];
+	u32 vf_pmac_id[BE_MAX_VF];
+	u8 base_eq_id;
 };
 
+#define be_physfn(adapter) (!adapter->pdev->is_virtfn)
+
 /* BladeEngine Generation numbers */
 #define BE_GEN2 2
 #define BE_GEN3 3
diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c
index 50e6259..9f53d9e 100644
--- a/drivers/net/benet/be_cmds.c
+++ b/drivers/net/benet/be_cmds.c
@@ -843,7 +843,8 @@ int be_cmd_q_destroy(struct be_adapter *
  * Uses mbox
  */
 int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags, u32 en_flags,
-		u8 *mac, bool pmac_invalid, u32 *if_handle, u32 *pmac_id)
+		u8 *mac, bool pmac_invalid, u32 *if_handle, u32 *pmac_id,
+		u32 domain)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_if_create *req;
@@ -860,6 +861,7 @@ int be_cmd_if_create(struct be_adapter *
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 		OPCODE_COMMON_NTWK_INTERFACE_CREATE, sizeof(*req));
 
+	req->hdr.domain = domain;
 	req->capability_flags = cpu_to_le32(cap_flags);
 	req->enable_flags = cpu_to_le32(en_flags);
 	req->pmac_invalid = pmac_invalid;
diff --git a/drivers/net/benet/be_cmds.h b/drivers/net/benet/be_cmds.h
index cce61f9..763dc19 100644
--- a/drivers/net/benet/be_cmds.h
+++ b/drivers/net/benet/be_cmds.h
@@ -878,7 +878,7 @@ extern int be_cmd_pmac_add(struct be_ada
 extern int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id);
 extern int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags,
 			u32 en_flags, u8 *mac, bool pmac_invalid,
-			u32 *if_handle, u32 *pmac_id);
+			u32 *if_handle, u32 *pmac_id, u32 domain);
 extern int be_cmd_if_destroy(struct be_adapter *adapter, u32 if_handle);
 extern int be_cmd_eq_create(struct be_adapter *adapter,
 			struct be_queue_info *eq, int eq_delay);
diff --git a/drivers/net/benet/be_hw.h b/drivers/net/benet/be_hw.h
index 2d4a4b8..063026d 100644
--- a/drivers/net/benet/be_hw.h
+++ b/drivers/net/benet/be_hw.h
@@ -99,6 +99,9 @@ #define DB_MCCQ_RING_ID_MASK		0x7FF	/* b
 /* Number of entries posted */
 #define DB_MCCQ_NUM_POSTED_SHIFT	(16)	/* bits 16 - 29 */
 
+/********** SRIOV VF PCICFG OFFSET ********/
+#define SRIOV_VF_PCICFG_OFFSET		(4096)
+
 /* Flashrom related descriptors */
 #define IMAGE_TYPE_FIRMWARE		160
 #define IMAGE_TYPE_BOOTCODE		224
diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c
index 50ea056..881c87d 100644
--- a/drivers/net/benet/be_main.c
+++ b/drivers/net/benet/be_main.c
@@ -26,8 +26,11 @@ MODULE_AUTHOR("ServerEngines Corporation
 MODULE_LICENSE("GPL");
 
 static unsigned int rx_frag_size = 2048;
+static unsigned int num_vfs;
 module_param(rx_frag_size, uint, S_IRUGO);
+module_param(num_vfs, uint, S_IRUGO);
 MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");
+MODULE_PARM_DESC(num_vfs, "Number of PCI VFs to initialize");
 
 static DEFINE_PCI_DEVICE_TABLE(be_dev_ids) = {
 	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID1) },
@@ -138,12 +141,19 @@ static int be_mac_addr_set(struct net_de
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+	/* MAC addr configuration will be done in hardware for VFs
+	 * by their corresponding PFs. Just copy to netdev addr here
+	 */
+	if (!be_physfn(adapter))
+		goto netdev_addr;
+
 	status = be_cmd_pmac_del(adapter, adapter->if_handle, adapter->pmac_id);
 	if (status)
 		return status;
 
 	status = be_cmd_pmac_add(adapter, (u8 *)addr->sa_data,
 			adapter->if_handle, &adapter->pmac_id);
+netdev_addr:
 	if (!status)
 		memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
 
@@ -576,6 +586,9 @@ static void be_vlan_add_vid(struct net_d
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
+	if (!be_physfn(adapter))
+		return;
+
 	adapter->vlan_tag[vid] = 1;
 	adapter->vlans_added++;
 	if (adapter->vlans_added <= (adapter->max_vlans + 1))
@@ -586,6 +599,9 @@ static void be_vlan_rem_vid(struct net_d
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
+	if (!be_physfn(adapter))
+		return;
+
 	adapter->vlan_tag[vid] = 0;
 	vlan_group_set_device(adapter->vlan_grp, vid, NULL);
 	adapter->vlans_added--;
@@ -623,6 +639,28 @@ done:
 	return;
 }
 
+static int be_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+	int status;
+
+	if (!adapter->sriov_enabled)
+		return -EPERM;
+
+	if (!is_valid_ether_addr(mac) || (vf >= num_vfs))
+		return -EINVAL;
+
+	status = be_cmd_pmac_del(adapter, adapter->vf_if_handle[vf],
+				adapter->vf_pmac_id[vf]);
+
+	status = be_cmd_pmac_add(adapter, mac, adapter->vf_if_handle[vf],
+				&adapter->vf_pmac_id[vf]);
+	if (!status)
+		dev_err(&adapter->pdev->dev, "MAC %pM set on VF %d Failed\n",
+				mac, vf);
+	return status;
+}
+
 static void be_rx_rate_update(struct be_adapter *adapter)
 {
 	struct be_drvr_stats *stats = drvr_stats(adapter);
@@ -1281,6 +1319,8 @@ static int be_tx_queues_create(struct be
 	/* Ask BE to create Tx Event queue */
 	if (be_cmd_eq_create(adapter, eq, adapter->tx_eq.cur_eqd))
 		goto tx_eq_free;
+	adapter->base_eq_id = adapter->tx_eq.q.id;
+
 	/* Alloc TX eth compl queue */
 	cq = &adapter->tx_obj.cq;
 	if (be_queue_alloc(adapter, cq, TX_CQ_LEN,
@@ -1408,7 +1448,7 @@ rx_eq_free:
 /* There are 8 evt ids per func. Retruns the evt id's bit number */
 static inline int be_evt_bit_get(struct be_adapter *adapter, u32 eq_id)
 {
-	return eq_id % 8;
+	return eq_id - adapter->base_eq_id;
 }
 
 static irqreturn_t be_intx(int irq, void *dev)
@@ -1586,6 +1626,28 @@ static void be_msix_enable(struct be_ada
 	return;
 }
 
+static void be_sriov_enable(struct be_adapter *adapter)
+{
+#ifdef CONFIG_PCI_IOV
+	int status;
+	if (be_physfn(adapter) && num_vfs) {
+		status = pci_enable_sriov(adapter->pdev, num_vfs);
+		adapter->sriov_enabled = status ? false : true;
+	}
+#endif
+	return;
+}
+
+static void be_sriov_disable(struct be_adapter *adapter)
+{
+#ifdef CONFIG_PCI_IOV
+	if (adapter->sriov_enabled) {
+		pci_disable_sriov(adapter->pdev);
+		adapter->sriov_enabled = false;
+	}
+#endif
+}
+
 static inline int be_msix_vec_get(struct be_adapter *adapter, u32 eq_id)
 {
 	return adapter->msix_entries[
@@ -1643,6 +1705,9 @@ static int be_irq_register(struct be_ada
 		status = be_msix_register(adapter);
 		if (status == 0)
 			goto done;
+		/* INTx is not supported for VF */
+		if (!be_physfn(adapter))
+			return status;
 	}
 
 	/* INTx */
@@ -1716,14 +1781,17 @@ static int be_open(struct net_device *ne
 		goto ret_sts;
 	be_link_status_update(adapter, link_up);
 
-	status = be_vid_config(adapter);
+	if (be_physfn(adapter))
+		status = be_vid_config(adapter);
 	if (status)
 		goto ret_sts;
 
-	status = be_cmd_set_flow_control(adapter,
-					adapter->tx_fc, adapter->rx_fc);
-	if (status)
-		goto ret_sts;
+	if (be_physfn(adapter)) {
+		status = be_cmd_set_flow_control(adapter,
+				adapter->tx_fc, adapter->rx_fc);
+		if (status)
+			goto ret_sts;
+	}
 
 	schedule_delayed_work(&adapter->work, msecs_to_jiffies(100));
 ret_sts:
@@ -1771,22 +1839,48 @@ static int be_setup_wol(struct be_adapte
 static int be_setup(struct be_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
-	u32 cap_flags, en_flags;
+	u32 cap_flags, en_flags, vf = 0;
 	int status;
+	u8 mac[ETH_ALEN];
+
+	cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST;
 
-	cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
-			BE_IF_FLAGS_MCAST_PROMISCUOUS |
-			BE_IF_FLAGS_PROMISCUOUS |
-			BE_IF_FLAGS_PASS_L3L4_ERRORS;
-	en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
-			BE_IF_FLAGS_PASS_L3L4_ERRORS;
+	if (be_physfn(adapter)) {
+		cap_flags |= BE_IF_FLAGS_MCAST_PROMISCUOUS |
+				BE_IF_FLAGS_PROMISCUOUS |
+				BE_IF_FLAGS_PASS_L3L4_ERRORS;
+		en_flags |= BE_IF_FLAGS_PASS_L3L4_ERRORS;
+	}
 
 	status = be_cmd_if_create(adapter, cap_flags, en_flags,
 			netdev->dev_addr, false/* pmac_invalid */,
-			&adapter->if_handle, &adapter->pmac_id);
+			&adapter->if_handle, &adapter->pmac_id, 0);
 	if (status != 0)
 		goto do_none;
 
+	if (be_physfn(adapter)) {
+		while (vf < num_vfs) {
+			cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED
+					| BE_IF_FLAGS_BROADCAST;
+			status = be_cmd_if_create(adapter, cap_flags, en_flags,
+					mac, true, &adapter->vf_if_handle[vf],
+					NULL, vf+1);
+			if (status) {
+				dev_err(&adapter->pdev->dev,
+				"Interface Create failed for VF %d\n", vf);
+				goto if_destroy;
+			}
+			vf++;
+		} while (vf < num_vfs);
+	} else if (!be_physfn(adapter)) {
+		status = be_cmd_mac_addr_query(adapter, mac,
+			MAC_ADDRESS_TYPE_NETWORK, false, adapter->if_handle);
+		if (!status) {
+			memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
+			memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
+		}
+	}
+
 	status = be_tx_queues_create(adapter);
 	if (status != 0)
 		goto if_destroy;
@@ -1808,6 +1902,9 @@ rx_qs_destroy:
 tx_qs_destroy:
 	be_tx_queues_destroy(adapter);
 if_destroy:
+	for (vf = 0; vf < num_vfs; vf++)
+		if (adapter->vf_if_handle[vf])
+			be_cmd_if_destroy(adapter, adapter->vf_if_handle[vf]);
 	be_cmd_if_destroy(adapter, adapter->if_handle);
 do_none:
 	return status;
@@ -2088,6 +2185,7 @@ static struct net_device_ops be_netdev_o
 	.ndo_vlan_rx_register	= be_vlan_register,
 	.ndo_vlan_rx_add_vid	= be_vlan_add_vid,
 	.ndo_vlan_rx_kill_vid	= be_vlan_rem_vid,
+	.ndo_set_vf_mac		= be_set_vf_mac
 };
 
 static void be_netdev_init(struct net_device *netdev)
@@ -2129,37 +2227,48 @@ static void be_unmap_pci_bars(struct be_
 		iounmap(adapter->csr);
 	if (adapter->db)
 		iounmap(adapter->db);
-	if (adapter->pcicfg)
+	if (adapter->pcicfg && be_physfn(adapter))
 		iounmap(adapter->pcicfg);
 }
 
 static int be_map_pci_bars(struct be_adapter *adapter)
 {
 	u8 __iomem *addr;
-	int pcicfg_reg;
+	int pcicfg_reg, db_reg;
 
-	addr = ioremap_nocache(pci_resource_start(adapter->pdev, 2),
-			pci_resource_len(adapter->pdev, 2));
-	if (addr == NULL)
-		return -ENOMEM;
-	adapter->csr = addr;
-
-	addr = ioremap_nocache(pci_resource_start(adapter->pdev, 4),
-			128 * 1024);
-	if (addr == NULL)
-		goto pci_map_err;
-	adapter->db = addr;
+	if (be_physfn(adapter)) {
+		addr = ioremap_nocache(pci_resource_start(adapter->pdev, 2),
+				pci_resource_len(adapter->pdev, 2));
+		if (addr == NULL)
+			return -ENOMEM;
+		adapter->csr = addr;
+	}
 
-	if (adapter->generation == BE_GEN2)
+	if (adapter->generation == BE_GEN2) {
 		pcicfg_reg = 1;
-	else
+		db_reg = 4;
+	} else {
 		pcicfg_reg = 0;
-
-	addr = ioremap_nocache(pci_resource_start(adapter->pdev, pcicfg_reg),
-			pci_resource_len(adapter->pdev, pcicfg_reg));
+		if (be_physfn(adapter))
+			db_reg = 4;
+		else
+			db_reg = 0;
+	}
+	addr = ioremap_nocache(pci_resource_start(adapter->pdev, db_reg),
+				pci_resource_len(adapter->pdev, db_reg));
 	if (addr == NULL)
 		goto pci_map_err;
-	adapter->pcicfg = addr;
+	adapter->db = addr;
+
+	if (be_physfn(adapter)) {
+		addr = ioremap_nocache(
+				pci_resource_start(adapter->pdev, pcicfg_reg),
+				pci_resource_len(adapter->pdev, pcicfg_reg));
+		if (addr == NULL)
+			goto pci_map_err;
+		adapter->pcicfg = addr;
+	} else
+		adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET;
 
 	return 0;
 pci_map_err:
@@ -2273,6 +2382,8 @@ static void __devexit be_remove(struct p
 
 	be_ctrl_cleanup(adapter);
 
+	be_sriov_disable(adapter);
+
 	be_msix_disable(adapter);
 
 	pci_set_drvdata(pdev, NULL);
@@ -2297,16 +2408,20 @@ static int be_get_config(struct be_adapt
 		return status;
 
 	memset(mac, 0, ETH_ALEN);
-	status = be_cmd_mac_addr_query(adapter, mac,
+
+	if (be_physfn(adapter)) {
+		status = be_cmd_mac_addr_query(adapter, mac,
 			MAC_ADDRESS_TYPE_NETWORK, true /*permanent */, 0);
-	if (status)
-		return status;
 
-	if (!is_valid_ether_addr(mac))
-		return -EADDRNOTAVAIL;
+		if (status)
+			return status;
 
-	memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
-	memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
+		if (!is_valid_ether_addr(mac))
+			return -EADDRNOTAVAIL;
+
+		memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
+		memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
+	}
 
 	if (adapter->cap & 0x400)
 		adapter->max_vlans = BE_NUM_VLANS_SUPPORTED/4;
@@ -2323,6 +2438,7 @@ static int __devinit be_probe(struct pci
 	struct be_adapter *adapter;
 	struct net_device *netdev;
 
+
 	status = pci_enable_device(pdev);
 	if (status)
 		goto do_none;
@@ -2371,24 +2487,28 @@ static int __devinit be_probe(struct pci
 		}
 	}
 
+	be_sriov_enable(adapter);
+
 	status = be_ctrl_init(adapter);
 	if (status)
 		goto free_netdev;
 
 	/* sync up with fw's ready state */
-	status = be_cmd_POST(adapter);
-	if (status)
-		goto ctrl_clean;
+	if (be_physfn(adapter)) {
+		status = be_cmd_POST(adapter);
+		if (status)
+			goto ctrl_clean;
+
+		status = be_cmd_reset_function(adapter);
+		if (status)
+			goto ctrl_clean;
+	}
 
 	/* tell fw we're ready to fire cmds */
 	status = be_cmd_fw_init(adapter);
 	if (status)
 		goto ctrl_clean;
 
-	status = be_cmd_reset_function(adapter);
-	if (status)
-		goto ctrl_clean;
-
 	status = be_stats_init(adapter);
 	if (status)
 		goto ctrl_clean;
@@ -2418,6 +2538,7 @@ ctrl_clean:
 	be_ctrl_cleanup(adapter);
 free_netdev:
 	be_msix_disable(adapter);
+	be_sriov_disable(adapter);
 	free_netdev(adapter->netdev);
 	pci_set_drvdata(pdev, NULL);
 rel_reg:
@@ -2614,6 +2735,13 @@ static int __init be_init_module(void)
 		rx_frag_size = 2048;
 	}
 
+	if (num_vfs > 32) {
+		printk(KERN_WARNING DRV_NAME
+			" : Module param num_vfs must not be greater than 32."
+			"Using 32\n");
+		num_vfs = 32;
+	}
+
 	return pci_register_driver(&be_driver);
 }
 module_init(be_init_module);
-- 
1.4.0

Re: [net-next PATCH] be2net: Adding PCI SRIOV support

[David Miller]

From: Sarveshwar Bandi <sarveshwarb@serverengines.com>
Date: Wed, 31 Mar 2010 18:26:12 +0530

> - Patch adds support to enable PCI SRIOV in the driver and changes to handle initialization of PCI virtual functions.
> - Function handler to change mac addresses for VF from its corresponding PF.
> 
> Signed-off-by: Sarveshwar Bandi <sarveshwarb@serverengines.com>

Applied, thanks.

Re: [net-next PATCH] be2net: Adding PCI SRIOV support

[Venugopal Busireddy]

David,
>> From: Sarveshwar Bandi <sarveshwarb@serverengines.com>
>> Date: Wed, 31 Mar 2010 18:26:12 +0530
>> - Patch adds support to enable PCI SRIOV in the driver and changes to
handle \
>>                initialization of PCI virtual functions.
>> - Function handler to change mac addresses for VF from its
corresponding PF.
>> 
>> Signed-off-by: Sarveshwar Bandi <sarveshwarb@serverengines.com>
>Applied, thanks.
 I checked the 2.6.34 kernel, and could not see this patch applied in
it. In which kernel would this patch be available? Also, if I were to
apply this patch, which kernel version would this patch require?
Thanks,
Venu

Re: [net-next PATCH] be2net: Adding PCI SRIOV support

[Ajit Khaparde]

On 26/05/10 12:55 -0500, Venugopal Busireddy wrote:
> 
> David,
> >> From: Sarveshwar Bandi <sarveshwarb@serverengines.com>
> >> Date: Wed, 31 Mar 2010 18:26:12 +0530
> >> - Patch adds support to enable PCI SRIOV in the driver and changes to
> handle \
> >>                initialization of PCI virtual functions.
> >> - Function handler to change mac addresses for VF from its
> corresponding PF.
> >> 
> >> Signed-off-by: Sarveshwar Bandi <sarveshwarb@serverengines.com>
> >Applied, thanks.
>  I checked the 2.6.34 kernel, and could not see this patch applied in
> it. In which kernel would this patch be available? Also, if I were to
> apply this patch, which kernel version would this patch require?
You wouldn't see these changes in 2.6.34
They were pushed to Linus tree post 2.6.34 release.
You can take the latest driver from Linus git repository.

-Ajit