Merge branch 'be2net'

Sathya Perla says:

====================
be2net: patch set

v2 change: merged 2 lines into one in patch 4

Patch 1 refactors be_cmd_get_profile_config() routine to reduce
code duplication by using the be_cmd_notify_wait() routine, instead
of using a separate variant of the code for MBOX and MCCQ.

Patch 2 introduces the required FW-cmd code in the PF to query
RSS support on a VF. This is in preparation for patch 3.

Patch 3 adds support for the PF driver to re-configure the resource
distribution in FW based on the number of VFs enabled by the user. When
the user is not interested in enabling VFs, all resources of a port are
set-aside for the PF. If less than maximum number of VFs are enabled, then
each VF gets a better share of the resources and can now enable RSS (if
the interface supports it.)

Patch 4 is a minor fix to re-enable HW vlan filtering as soon as the number
of vlans programmed is within the HW limit.

Please consider applying to net-next tree. Thanks!
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 230 insertions, 155 deletions

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index c2f5d2d3b932..d3d871b28cad 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -411,6 +411,7 @@ struct be_resources {
 	u16 max_vlans;		/* Number of vlans supported */
 	u16 max_evt_qs;
 	u32 if_cap_flags;
+	u32 vf_if_cap_flags;	/* VF if capability flags */
 };
 
 struct rss_info {
@@ -500,6 +501,7 @@ struct be_adapter {
 	u32 flash_status;
 	struct completion et_cmd_compl;
 
+	struct be_resources pool_res;	/* resources available for the port */
 	struct be_resources res;	/* resources available for the func */
 	u16 num_vfs;			/* Number of VFs provisioned by PF */
 	u8 virtfn;
@@ -523,9 +525,8 @@ struct be_adapter {
 
 #define be_physfn(adapter)		(!adapter->virtfn)
 #define be_virtfn(adapter)		(adapter->virtfn)
-#define	sriov_enabled(adapter)		(adapter->num_vfs > 0)
-#define sriov_want(adapter)             (be_physfn(adapter) &&	\
-					 (num_vfs || pci_num_vf(adapter->pdev)))
+#define sriov_enabled(adapter)		(adapter->num_vfs > 0)
+
 #define for_all_vfs(adapter, vf_cfg, i)					\
 	for (i = 0, vf_cfg = &adapter->vf_cfg[i]; i < adapter->num_vfs;	\
 		i++, vf_cfg++)
@@ -536,7 +537,7 @@ struct be_adapter {
 #define be_max_vlans(adapter)		(adapter->res.max_vlans)
 #define be_max_uc(adapter)		(adapter->res.max_uc_mac)
 #define be_max_mc(adapter)		(adapter->res.max_mcast_mac)
-#define be_max_vfs(adapter)		(adapter->res.max_vfs)
+#define be_max_vfs(adapter)		(adapter->pool_res.max_vfs)
 #define be_max_rss(adapter)		(adapter->res.max_rss_qs)
 #define be_max_txqs(adapter)		(adapter->res.max_tx_qs)
 #define be_max_prio_txqs(adapter)	(adapter->res.max_prio_tx_qs)
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index f4ea3490f446..9904bbfd4e93 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -3313,15 +3313,28 @@ err:
 	return status;
 }
 
-static struct be_nic_res_desc *be_get_nic_desc(u8 *buf, u32 desc_count)
+/* Descriptor type */
+enum {
+	FUNC_DESC = 1,
+	VFT_DESC = 2
+};
+
+static struct be_nic_res_desc *be_get_nic_desc(u8 *buf, u32 desc_count,
+					       int desc_type)
 {
 	struct be_res_desc_hdr *hdr = (struct be_res_desc_hdr *)buf;
+	struct be_nic_res_desc *nic;
 	int i;
 
 	for (i = 0; i < desc_count; i++) {
 		if (hdr->desc_type == NIC_RESOURCE_DESC_TYPE_V0 ||
-		    hdr->desc_type == NIC_RESOURCE_DESC_TYPE_V1)
-			return (struct be_nic_res_desc *)hdr;
+		    hdr->desc_type == NIC_RESOURCE_DESC_TYPE_V1) {
+			nic = (struct be_nic_res_desc *)hdr;
+			if (desc_type == FUNC_DESC ||
+			    (desc_type == VFT_DESC &&
+			     nic->flags & (1 << VFT_SHIFT)))
+				return nic;
+		}
 
 		hdr->desc_len = hdr->desc_len ? : RESOURCE_DESC_SIZE_V0;
 		hdr = (void *)hdr + hdr->desc_len;
@@ -3329,6 +3342,16 @@ static struct be_nic_res_desc *be_get_nic_desc(u8 *buf, u32 desc_count)
 	return NULL;
 }
 
+static struct be_nic_res_desc *be_get_vft_desc(u8 *buf, u32 desc_count)
+{
+	return be_get_nic_desc(buf, desc_count, VFT_DESC);
+}
+
+static struct be_nic_res_desc *be_get_func_nic_desc(u8 *buf, u32 desc_count)
+{
+	return be_get_nic_desc(buf, desc_count, FUNC_DESC);
+}
+
 static struct be_pcie_res_desc *be_get_pcie_desc(u8 devfn, u8 *buf,
 						 u32 desc_count)
 {
@@ -3424,7 +3447,7 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 		u32 desc_count = le32_to_cpu(resp->desc_count);
 		struct be_nic_res_desc *desc;
 
-		desc = be_get_nic_desc(resp->func_param, desc_count);
+		desc = be_get_func_nic_desc(resp->func_param, desc_count);
 		if (!desc) {
 			status = -EINVAL;
 			goto err;
@@ -3440,76 +3463,17 @@ err:
 	return status;
 }
 
-/* Uses mbox */
-static int be_cmd_get_profile_config_mbox(struct be_adapter *adapter,
-					  u8 domain, struct be_dma_mem *cmd)
-{
-	struct be_mcc_wrb *wrb;
-	struct be_cmd_req_get_profile_config *req;
-	int status;
-
-	if (mutex_lock_interruptible(&adapter->mbox_lock))
-		return -1;
-	wrb = wrb_from_mbox(adapter);
-
-	req = cmd->va;
-	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			       OPCODE_COMMON_GET_PROFILE_CONFIG,
-			       cmd->size, wrb, cmd);
-
-	req->type = ACTIVE_PROFILE_TYPE;
-	req->hdr.domain = domain;
-	if (!lancer_chip(adapter))
-		req->hdr.version = 1;
-
-	status = be_mbox_notify_wait(adapter);
-
-	mutex_unlock(&adapter->mbox_lock);
-	return status;
-}
-
-/* Uses sync mcc */
-static int be_cmd_get_profile_config_mccq(struct be_adapter *adapter,
-					  u8 domain, struct be_dma_mem *cmd)
-{
-	struct be_mcc_wrb *wrb;
-	struct be_cmd_req_get_profile_config *req;
-	int status;
-
-	spin_lock_bh(&adapter->mcc_lock);
-
-	wrb = wrb_from_mccq(adapter);
-	if (!wrb) {
-		status = -EBUSY;
-		goto err;
-	}
-
-	req = cmd->va;
-	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			       OPCODE_COMMON_GET_PROFILE_CONFIG,
-			       cmd->size, wrb, cmd);
-
-	req->type = ACTIVE_PROFILE_TYPE;
-	req->hdr.domain = domain;
-	if (!lancer_chip(adapter))
-		req->hdr.version = 1;
-
-	status = be_mcc_notify_wait(adapter);
-
-err:
-	spin_unlock_bh(&adapter->mcc_lock);
-	return status;
-}
-
-/* Uses sync mcc, if MCCQ is already created otherwise mbox */
+/* Will use MBOX only if MCCQ has not been created */
 int be_cmd_get_profile_config(struct be_adapter *adapter,
 			      struct be_resources *res, u8 domain)
 {
 	struct be_cmd_resp_get_profile_config *resp;
+	struct be_cmd_req_get_profile_config *req;
+	struct be_nic_res_desc *vf_res;
 	struct be_pcie_res_desc *pcie;
 	struct be_port_res_desc *port;
 	struct be_nic_res_desc *nic;
-	struct be_queue_info *mccq = &adapter->mcc_obj.q;
+	struct be_mcc_wrb wrb = {0};
 	struct be_dma_mem cmd;
 	u32 desc_count;
 	int status;
@@ -3520,10 +3484,17 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 	if (!cmd.va)
 		return -ENOMEM;
 
-	if (!mccq->created)
-		status = be_cmd_get_profile_config_mbox(adapter, domain, &cmd);
-	else
-		status = be_cmd_get_profile_config_mccq(adapter, domain, &cmd);
+	req = cmd.va;
+	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+			       OPCODE_COMMON_GET_PROFILE_CONFIG,
+			       cmd.size, &wrb, &cmd);
+
+	req->hdr.domain = domain;
+	if (!lancer_chip(adapter))
+		req->hdr.version = 1;
+	req->type = ACTIVE_PROFILE_TYPE;
+
+	status = be_cmd_notify_wait(adapter, &wrb);
 	if (status)
 		goto err;
 
@@ -3539,48 +3510,52 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 	if (port)
 		adapter->mc_type = port->mc_type;
 
-	nic = be_get_nic_desc(resp->func_param, desc_count);
+	nic = be_get_func_nic_desc(resp->func_param, desc_count);
 	if (nic)
 		be_copy_nic_desc(res, nic);
 
+	vf_res = be_get_vft_desc(resp->func_param, desc_count);
+	if (vf_res)
+		res->vf_if_cap_flags = vf_res->cap_flags;
 err:
 	if (cmd.va)
 		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
 
-int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
-			      int size, u8 version, u8 domain)
+/* Will use MBOX only if MCCQ has not been created */
+static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
+				     int size, int count, u8 version, u8 domain)
 {
 	struct be_cmd_req_set_profile_config *req;
-	struct be_mcc_wrb *wrb;
+	struct be_mcc_wrb wrb = {0};
+	struct be_dma_mem cmd;
 	int status;
 
-	spin_lock_bh(&adapter->mcc_lock);
-
-	wrb = wrb_from_mccq(adapter);
-	if (!wrb) {
-		status = -EBUSY;
-		goto err;
-	}
+	memset(&cmd, 0, sizeof(struct be_dma_mem));
+	cmd.size = sizeof(struct be_cmd_req_set_profile_config);
+	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	if (!cmd.va)
+		return -ENOMEM;
 
-	req = embedded_payload(wrb);
+	req = cmd.va;
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			       OPCODE_COMMON_SET_PROFILE_CONFIG, sizeof(*req),
-			       wrb, NULL);
+			       OPCODE_COMMON_SET_PROFILE_CONFIG, cmd.size,
+			       &wrb, &cmd);
 	req->hdr.version = version;
 	req->hdr.domain = domain;
-	req->desc_count = cpu_to_le32(1);
+	req->desc_count = cpu_to_le32(count);
 	memcpy(req->desc, desc, size);
 
-	status = be_mcc_notify_wait(adapter);
-err:
-	spin_unlock_bh(&adapter->mcc_lock);
+	status = be_cmd_notify_wait(adapter, &wrb);
+
+	if (cmd.va)
+		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
 
 /* Mark all fields invalid */
-void be_reset_nic_desc(struct be_nic_res_desc *nic)
+static void be_reset_nic_desc(struct be_nic_res_desc *nic)
 {
 	memset(nic, 0, sizeof(*nic));
 	nic->unicast_mac_count = 0xFFFF;
@@ -3601,9 +3576,20 @@ void be_reset_nic_desc(struct be_nic_res_desc *nic)
 	nic->wol_param = 0x0F;
 	nic->tunnel_iface_count = 0xFFFF;
 	nic->direct_tenant_iface_count = 0xFFFF;
+	nic->bw_min = 0xFFFFFFFF;
 	nic->bw_max = 0xFFFFFFFF;
 }
 
+/* Mark all fields invalid */
+static void be_reset_pcie_desc(struct be_pcie_res_desc *pcie)
+{
+	memset(pcie, 0, sizeof(*pcie));
+	pcie->sriov_state = 0xFF;
+	pcie->pf_state = 0xFF;
+	pcie->pf_type = 0xFF;
+	pcie->num_vfs = 0xFFFF;
+}
+
 int be_cmd_config_qos(struct be_adapter *adapter, u32 max_rate, u16 link_speed,
 		      u8 domain)
 {
@@ -3634,7 +3620,63 @@ int be_cmd_config_qos(struct be_adapter *adapter, u32 max_rate, u16 link_speed,
 
 	return be_cmd_set_profile_config(adapter, &nic_desc,
 					 nic_desc.hdr.desc_len,
-					 version, domain);
+					 1, version, domain);
+}
+
+int be_cmd_set_sriov_config(struct be_adapter *adapter,
+			    struct be_resources res, u16 num_vfs)
+{
+	struct {
+		struct be_pcie_res_desc pcie;
+		struct be_nic_res_desc nic_vft;
+	} __packed desc;
+	u16 vf_q_count;
+
+	if (BEx_chip(adapter) || lancer_chip(adapter))
+		return 0;
+
+	/* PF PCIE descriptor */
+	be_reset_pcie_desc(&desc.pcie);
+	desc.pcie.hdr.desc_type = PCIE_RESOURCE_DESC_TYPE_V1;
+	desc.pcie.hdr.desc_len = RESOURCE_DESC_SIZE_V1;
+	desc.pcie.flags = (1 << IMM_SHIFT) | (1 << NOSV_SHIFT);
+	desc.pcie.pf_num = adapter->pdev->devfn;
+	desc.pcie.sriov_state = num_vfs ? 1 : 0;
+	desc.pcie.num_vfs = cpu_to_le16(num_vfs);
+
+	/* VF NIC Template descriptor */
+	be_reset_nic_desc(&desc.nic_vft);
+	desc.nic_vft.hdr.desc_type = NIC_RESOURCE_DESC_TYPE_V1;
+	desc.nic_vft.hdr.desc_len = RESOURCE_DESC_SIZE_V1;
+	desc.nic_vft.flags = (1 << VFT_SHIFT) | (1 << IMM_SHIFT) |
+				(1 << NOSV_SHIFT);
+	desc.nic_vft.pf_num = adapter->pdev->devfn;
+	desc.nic_vft.vf_num = 0;
+
+	if (num_vfs && res.vf_if_cap_flags & BE_IF_FLAGS_RSS) {
+		/* If number of VFs requested is 8 less than max supported,
+		 * assign 8 queue pairs to the PF and divide the remaining
+		 * resources evenly among the VFs
+		 */
+		if (num_vfs < (be_max_vfs(adapter) - 8))
+			vf_q_count = (res.max_rss_qs - 8) / num_vfs;
+		else
+			vf_q_count = res.max_rss_qs / num_vfs;
+
+		desc.nic_vft.rq_count = cpu_to_le16(vf_q_count);
+		desc.nic_vft.txq_count = cpu_to_le16(vf_q_count);
+		desc.nic_vft.rssq_count = cpu_to_le16(vf_q_count - 1);
+		desc.nic_vft.cq_count = cpu_to_le16(3 * vf_q_count);
+	} else {
+		desc.nic_vft.txq_count = cpu_to_le16(1);
+		desc.nic_vft.rq_count = cpu_to_le16(1);
+		desc.nic_vft.rssq_count = cpu_to_le16(0);
+		/* One CQ for each TX, RX and MCCQ */
+		desc.nic_vft.cq_count = cpu_to_le16(3);
+	}
+
+	return be_cmd_set_profile_config(adapter, &desc,
+					 2 * RESOURCE_DESC_SIZE_V1, 2, 1, 0);
 }
 
 int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
@@ -3686,7 +3728,7 @@ int be_cmd_set_vxlan_port(struct be_adapter *adapter, __be16 port)
 	}
 
 	return be_cmd_set_profile_config(adapter, &port_desc,
-					 RESOURCE_DESC_SIZE_V1, 1, 0);
+					 RESOURCE_DESC_SIZE_V1, 1, 1, 0);
 }
 
 int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 59b3c056f329..c0f7167049b7 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1835,6 +1835,7 @@ struct be_cmd_req_set_ext_fat_caps {
 #define PORT_RESOURCE_DESC_TYPE_V1		0x55
 #define MAX_RESOURCE_DESC			264
 
+#define VFT_SHIFT				3	/* VF template */
 #define IMM_SHIFT				6	/* Immediate */
 #define NOSV_SHIFT				7	/* No save */
 
@@ -1962,8 +1963,8 @@ struct be_cmd_req_set_profile_config {
 	struct be_cmd_req_hdr hdr;
 	u32 rsvd;
 	u32 desc_count;
-	u8 desc[RESOURCE_DESC_SIZE_V1];
-};
+	u8 desc[2 * RESOURCE_DESC_SIZE_V1];
+} __packed;
 
 struct be_cmd_resp_set_profile_config {
 	struct be_cmd_resp_hdr hdr;
@@ -2157,8 +2158,6 @@ int be_cmd_get_func_config(struct be_adapter *adapter,
 			   struct be_resources *res);
 int be_cmd_get_profile_config(struct be_adapter *adapter,
 			      struct be_resources *res, u8 domain);
-int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
-			      int size, u8 version, u8 domain);
 int be_cmd_get_active_profile(struct be_adapter *adapter, u16 *profile);
 int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 		     int vf_num);
@@ -2168,3 +2167,5 @@ int be_cmd_set_logical_link_config(struct be_adapter *adapter,
 					  int link_state, u8 domain);
 int be_cmd_set_vxlan_port(struct be_adapter *adapter, __be16 port);
 int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op);
+int be_cmd_set_sriov_config(struct be_adapter *adapter,
+			    struct be_resources res, u16 num_vfs);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 34a26e42f19d..6297e72b77e2 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1172,20 +1172,15 @@ static int be_vlan_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
 static int be_vlan_rem_vid(struct net_device *netdev, __be16 proto, u16 vid)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
-	int status = 0;
 
 	/* Packets with VID 0 are always received by Lancer by default */
 	if (lancer_chip(adapter) && vid == 0)
-		goto ret;
+		return 0;
 
 	clear_bit(vid, adapter->vids);
-	status = be_vid_config(adapter);
-	if (!status)
-		adapter->vlans_added--;
-	else
-		set_bit(vid, adapter->vids);
-ret:
-	return status;
+	adapter->vlans_added--;
+
+	return be_vid_config(adapter);
 }
 
 static void be_clear_promisc(struct be_adapter *adapter)
@@ -3098,6 +3093,13 @@ static int be_clear(struct be_adapter *adapter)
 	if (sriov_enabled(adapter))
 		be_vf_clear(adapter);
 
+	/* Re-configure FW to distribute resources evenly across max-supported
+	 * number of VFs, only when VFs are not already enabled.
+	 */
+	if (be_physfn(adapter) && !pci_vfs_assigned(adapter->pdev))
+		be_cmd_set_sriov_config(adapter, adapter->pool_res,
+					pci_sriov_get_totalvfs(adapter->pdev));
+
 #ifdef CONFIG_BE2NET_VXLAN
 	be_disable_vxlan_offloads(adapter);
 #endif
@@ -3170,19 +3172,6 @@ static int be_vf_setup(struct be_adapter *adapter)
 	u32 privileges;
 
 	old_vfs = pci_num_vf(adapter->pdev);
-	if (old_vfs) {
-		dev_info(dev, "%d VFs are already enabled\n", old_vfs);
-		if (old_vfs != num_vfs)
-			dev_warn(dev, "Ignoring num_vfs=%d setting\n", num_vfs);
-		adapter->num_vfs = old_vfs;
-	} else {
-		if (num_vfs > be_max_vfs(adapter))
-			dev_info(dev, "Device supports %d VFs and not %d\n",
-				 be_max_vfs(adapter), num_vfs);
-		adapter->num_vfs = min_t(u16, num_vfs, be_max_vfs(adapter));
-		if (!adapter->num_vfs)
-			return 0;
-	}
 
 	status = be_vf_setup_init(adapter);
 	if (status)
@@ -3194,17 +3183,15 @@ static int be_vf_setup(struct be_adapter *adapter)
 			if (status)
 				goto err;
 		}
-	} else {
-		status = be_vfs_if_create(adapter);
-		if (status)
-			goto err;
-	}
 
-	if (old_vfs) {
 		status = be_vfs_mac_query(adapter);
 		if (status)
 			goto err;
 	} else {
+		status = be_vfs_if_create(adapter);
+		if (status)
+			goto err;
+
 		status = be_vf_eth_addr_config(adapter);
 		if (status)
 			goto err;
@@ -3270,19 +3257,7 @@ static u8 be_convert_mc_type(u32 function_mode)
 static void BEx_get_resources(struct be_adapter *adapter,
 			      struct be_resources *res)
 {
-	struct pci_dev *pdev = adapter->pdev;
-	bool use_sriov = false;
-	int max_vfs = 0;
-
-	if (be_physfn(adapter) && BE3_chip(adapter)) {
-		be_cmd_get_profile_config(adapter, res, 0);
-		/* Some old versions of BE3 FW don't report max_vfs value */
-		if (res->max_vfs == 0) {
-			max_vfs = pci_sriov_get_totalvfs(pdev);
-			res->max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0;
-		}
-		use_sriov = res->max_vfs && sriov_want(adapter);
-	}
+	bool use_sriov = adapter->num_vfs ? 1 : 0;
 
 	if (be_physfn(adapter))
 		res->max_uc_mac = BE_UC_PMAC_COUNT;
@@ -3349,6 +3324,54 @@ static void be_setup_init(struct be_adapter *adapter)
 		adapter->cmd_privileges = MIN_PRIVILEGES;
 }
 
+static int be_get_sriov_config(struct be_adapter *adapter)
+{
+	struct device *dev = &adapter->pdev->dev;
+	struct be_resources res = {0};
+	int status, max_vfs, old_vfs;
+
+	status = be_cmd_get_profile_config(adapter, &res, 0);
+	if (status)
+		return status;
+
+	adapter->pool_res = res;
+
+	/* Some old versions of BE3 FW don't report max_vfs value */
+	if (BE3_chip(adapter) && !res.max_vfs) {
+		max_vfs = pci_sriov_get_totalvfs(adapter->pdev);
+		res.max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0;
+	}
+
+	adapter->pool_res.max_vfs = res.max_vfs;
+	pci_sriov_set_totalvfs(adapter->pdev, be_max_vfs(adapter));
+
+	if (!be_max_vfs(adapter)) {
+		if (num_vfs)
+			dev_warn(dev, "device doesn't support SRIOV\n");
+		adapter->num_vfs = 0;
+		return 0;
+	}
+
+	/* validate num_vfs module param */
+	old_vfs = pci_num_vf(adapter->pdev);
+	if (old_vfs) {
+		dev_info(dev, "%d VFs are already enabled\n", old_vfs);
+		if (old_vfs != num_vfs)
+			dev_warn(dev, "Ignoring num_vfs=%d setting\n", num_vfs);
+		adapter->num_vfs = old_vfs;
+	} else {
+		if (num_vfs > be_max_vfs(adapter)) {
+			dev_info(dev, "Resources unavailable to init %d VFs\n",
+				 num_vfs);
+			dev_info(dev, "Limiting to %d VFs\n",
+				 be_max_vfs(adapter));
+		}
+		adapter->num_vfs = min_t(u16, num_vfs, be_max_vfs(adapter));
+	}
+
+	return 0;
+}
+
 static int be_get_resources(struct be_adapter *adapter)
 {
 	struct device *dev = &adapter->pdev->dev;
@@ -3374,13 +3397,6 @@ static int be_get_resources(struct be_adapter *adapter)
 			res.max_evt_qs /= 2;
 		adapter->res = res;
 
-		if (be_physfn(adapter)) {
-			status = be_cmd_get_profile_config(adapter, &res, 0);
-			if (status)
-				return status;
-			adapter->res.max_vfs = res.max_vfs;
-		}
-
 		dev_info(dev, "Max: txqs %d, rxqs %d, rss %d, eqs %d, vfs %d\n",
 			 be_max_txqs(adapter), be_max_rxqs(adapter),
 			 be_max_rss(adapter), be_max_eqs(adapter),
@@ -3393,7 +3409,6 @@ static int be_get_resources(struct be_adapter *adapter)
 	return 0;
 }
 
-/* Routine to query per function resource limits */
 static int be_get_config(struct be_adapter *adapter)
 {
 	u16 profile_id;
@@ -3411,6 +3426,26 @@ static int be_get_config(struct be_adapter *adapter)
 		if (!status)
 			dev_info(&adapter->pdev->dev,
 				 "Using profile 0x%x\n", profile_id);
+
+		status = be_get_sriov_config(adapter);
+		if (status)
+			return status;
+
+		/* When the HW is in SRIOV capable configuration, the PF-pool
+		 * resources are equally distributed across the max-number of
+		 * VFs. The user may request only a subset of the max-vfs to be
+		 * enabled. Based on num_vfs, redistribute the resources across
+		 * num_vfs so that each VF will have access to more number of
+		 * resources. This facility is not available in BE3 FW.
+		 * Also, this is done by FW in Lancer chip.
+		 */
+		if (!pci_num_vf(adapter->pdev)) {
+			status = be_cmd_set_sriov_config(adapter,
+							 adapter->pool_res,
+							 adapter->num_vfs);
+			if (status)
+				return status;
+		}
 	}
 
 	status = be_get_resources(adapter);
@@ -3596,12 +3631,8 @@ static int be_setup(struct be_adapter *adapter)
 		be_cmd_set_logical_link_config(adapter,
 					       IFLA_VF_LINK_STATE_AUTO, 0);
 
-	if (sriov_want(adapter)) {
-		if (be_max_vfs(adapter))
-			be_vf_setup(adapter);
-		else
-			dev_warn(dev, "device doesn't support SRIOV\n");
-	}
+	if (adapter->num_vfs)
+		be_vf_setup(adapter);
 
 	status = be_cmd_get_phy_info(adapter);
 	if (!status && be_pause_supported(adapter))