[PATCH 02/28] bnxt_en: Enable MSIX early in bnxt_init_one().

[PATCH 02/28] bnxt_en: Enable MSIX early in bnxt_init_one().

[Selvin Xavier]

From: Michael Chan <michael.chan@broadcom.com>

To better support the new RDMA driver, we need to move pci_enable_msix()
from bnxt_open() to bnxt_init_one().  This way, MSIX vectors are available
to the RDMA driver whether the network device is up or down.

Part of the existing bnxt_setup_int_mode() function is now refactored into
a new bnxt_init_int_mode().  bnxt_init_int_mode() is called during
bnxt_init_one() to enable MSIX.  The remaining logic in
bnxt_setup_int_mode() to map the IRQs to the completion rings is called
during bnxt_open().

Cc: David Miller <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 183 +++++++++++++++++++-----------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |   1 +
 2 files changed, 115 insertions(+), 69 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6cdfe3e..9178bf8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4743,6 +4743,80 @@ static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
 	return 0;
 }
 
+static void bnxt_setup_msix(struct bnxt *bp)
+{
+	const int len = sizeof(bp->irq_tbl[0].name);
+	struct net_device *dev = bp->dev;
+	int tcs, i;
+
+	tcs = netdev_get_num_tc(dev);
+	if (tcs > 1) {
+		bp->tx_nr_rings_per_tc = bp->tx_nr_rings / tcs;
+		if (bp->tx_nr_rings_per_tc == 0) {
+			netdev_reset_tc(dev);
+			bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+		} else {
+			int i, off, count;
+
+			bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tcs;
+			for (i = 0; i < tcs; i++) {
+				count = bp->tx_nr_rings_per_tc;
+				off = i * count;
+				netdev_set_tc_queue(dev, i, count, off);
+			}
+		}
+	}
+
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		char *attr;
+
+		if (bp->flags & BNXT_FLAG_SHARED_RINGS)
+			attr = "TxRx";
+		else if (i < bp->rx_nr_rings)
+			attr = "rx";
+		else
+			attr = "tx";
+
+		snprintf(bp->irq_tbl[i].name, len, "%s-%s-%d", dev->name, attr,
+			 i);
+		bp->irq_tbl[i].handler = bnxt_msix;
+	}
+}
+
+static void bnxt_setup_inta(struct bnxt *bp)
+{
+	const int len = sizeof(bp->irq_tbl[0].name);
+
+	if (netdev_get_num_tc(bp->dev))
+		netdev_reset_tc(bp->dev);
+
+	snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx",
+		 0);
+	bp->irq_tbl[0].handler = bnxt_inta;
+}
+
+static int bnxt_setup_int_mode(struct bnxt *bp)
+{
+	int rc;
+
+	if (bp->flags & BNXT_FLAG_USING_MSIX)
+		bnxt_setup_msix(bp);
+	else
+		bnxt_setup_inta(bp);
+
+	rc = bnxt_set_real_num_queues(bp);
+	return rc;
+}
+
+static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		return bp->pf.max_irqs;
+#if defined(CONFIG_BNXT_SRIOV)
+	return bp->vf.max_irqs;
+#endif
+}
+
 void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
 {
 	if (BNXT_PF(bp))
@@ -4753,16 +4827,12 @@ void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
 #endif
 }
 
-static int bnxt_setup_msix(struct bnxt *bp)
+static int bnxt_init_msix(struct bnxt *bp)
 {
-	struct msix_entry *msix_ent;
-	struct net_device *dev = bp->dev;
 	int i, total_vecs, rc = 0, min = 1;
-	const int len = sizeof(bp->irq_tbl[0].name);
-
-	bp->flags &= ~BNXT_FLAG_USING_MSIX;
-	total_vecs = bp->cp_nr_rings;
+	struct msix_entry *msix_ent;
 
+	total_vecs = bnxt_get_max_func_irqs(bp);
 	msix_ent = kcalloc(total_vecs, sizeof(struct msix_entry), GFP_KERNEL);
 	if (!msix_ent)
 		return -ENOMEM;
@@ -4783,8 +4853,10 @@ static int bnxt_setup_msix(struct bnxt *bp)
 
 	bp->irq_tbl = kcalloc(total_vecs, sizeof(struct bnxt_irq), GFP_KERNEL);
 	if (bp->irq_tbl) {
-		int tcs;
+		for (i = 0; i < total_vecs; i++)
+			bp->irq_tbl[i].vector = msix_ent[i].vector;
 
+		bp->total_irqs = total_vecs;
 		/* Trim rings based upon num of vectors allocated */
 		rc = bnxt_trim_rings(bp, &bp->rx_nr_rings, &bp->tx_nr_rings,
 				     total_vecs, min == 1);
@@ -4792,43 +4864,10 @@ static int bnxt_setup_msix(struct bnxt *bp)
 			goto msix_setup_exit;
 
 		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
-		tcs = netdev_get_num_tc(dev);
-		if (tcs > 1) {
-			bp->tx_nr_rings_per_tc = bp->tx_nr_rings / tcs;
-			if (bp->tx_nr_rings_per_tc == 0) {
-				netdev_reset_tc(dev);
-				bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
-			} else {
-				int i, off, count;
+		bp->cp_nr_rings = (min == 1) ?
+				  max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
+				  bp->tx_nr_rings + bp->rx_nr_rings;
 
-				bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tcs;
-				for (i = 0; i < tcs; i++) {
-					count = bp->tx_nr_rings_per_tc;
-					off = i * count;
-					netdev_set_tc_queue(dev, i, count, off);
-				}
-			}
-		}
-		bp->cp_nr_rings = total_vecs;
-
-		for (i = 0; i < bp->cp_nr_rings; i++) {
-			char *attr;
-
-			bp->irq_tbl[i].vector = msix_ent[i].vector;
-			if (bp->flags & BNXT_FLAG_SHARED_RINGS)
-				attr = "TxRx";
-			else if (i < bp->rx_nr_rings)
-				attr = "rx";
-			else
-				attr = "tx";
-
-			snprintf(bp->irq_tbl[i].name, len,
-				 "%s-%s-%d", dev->name, attr, i);
-			bp->irq_tbl[i].handler = bnxt_msix;
-		}
-		rc = bnxt_set_real_num_queues(bp);
-		if (rc)
-			goto msix_setup_exit;
 	} else {
 		rc = -ENOMEM;
 		goto msix_setup_exit;
@@ -4838,52 +4877,54 @@ static int bnxt_setup_msix(struct bnxt *bp)
 	return 0;
 
 msix_setup_exit:
-	netdev_err(bp->dev, "bnxt_setup_msix err: %x\n", rc);
+	netdev_err(bp->dev, "bnxt_init_msix err: %x\n", rc);
+	kfree(bp->irq_tbl);
+	bp->irq_tbl = NULL;
 	pci_disable_msix(bp->pdev);
 	kfree(msix_ent);
 	return rc;
 }
 
-static int bnxt_setup_inta(struct bnxt *bp)
+static int bnxt_init_inta(struct bnxt *bp)
 {
-	int rc;
-	const int len = sizeof(bp->irq_tbl[0].name);
-
-	if (netdev_get_num_tc(bp->dev))
-		netdev_reset_tc(bp->dev);
-
 	bp->irq_tbl = kcalloc(1, sizeof(struct bnxt_irq), GFP_KERNEL);
-	if (!bp->irq_tbl) {
-		rc = -ENOMEM;
-		return rc;
-	}
+	if (!bp->irq_tbl)
+		return -ENOMEM;
+
+	bp->total_irqs = 1;
 	bp->rx_nr_rings = 1;
 	bp->tx_nr_rings = 1;
 	bp->cp_nr_rings = 1;
 	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
 	bp->flags |= BNXT_FLAG_SHARED_RINGS;
 	bp->irq_tbl[0].vector = bp->pdev->irq;
-	snprintf(bp->irq_tbl[0].name, len,
-		 "%s-%s-%d", bp->dev->name, "TxRx", 0);
-	bp->irq_tbl[0].handler = bnxt_inta;
-	rc = bnxt_set_real_num_queues(bp);
-	return rc;
+	return 0;
 }
 
-static int bnxt_setup_int_mode(struct bnxt *bp)
+static int bnxt_init_int_mode(struct bnxt *bp)
 {
 	int rc = 0;
 
 	if (bp->flags & BNXT_FLAG_MSIX_CAP)
-		rc = bnxt_setup_msix(bp);
+		rc = bnxt_init_msix(bp);
 
 	if (!(bp->flags & BNXT_FLAG_USING_MSIX) && BNXT_PF(bp)) {
 		/* fallback to INTA */
-		rc = bnxt_setup_inta(bp);
+		rc = bnxt_init_inta(bp);
 	}
 	return rc;
 }
 
+static void bnxt_clear_int_mode(struct bnxt *bp)
+{
+	if (bp->flags & BNXT_FLAG_USING_MSIX)
+		pci_disable_msix(bp->pdev);
+
+	kfree(bp->irq_tbl);
+	bp->irq_tbl = NULL;
+	bp->flags &= ~BNXT_FLAG_USING_MSIX;
+}
+
 static void bnxt_free_irq(struct bnxt *bp)
 {
 	struct bnxt_irq *irq;
@@ -4902,10 +4943,6 @@ static void bnxt_free_irq(struct bnxt *bp)
 			free_irq(irq->vector, bp->bnapi[i]);
 		irq->requested = 0;
 	}
-	if (bp->flags & BNXT_FLAG_USING_MSIX)
-		pci_disable_msix(bp->pdev);
-	kfree(bp->irq_tbl);
-	bp->irq_tbl = NULL;
 }
 
 static int bnxt_request_irq(struct bnxt *bp)
@@ -6695,6 +6732,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	cancel_work_sync(&bp->sp_task);
 	bp->sp_event = 0;
 
+	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_dcb_free(bp);
@@ -6990,10 +7028,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err;
 
-	rc = register_netdev(dev);
+	rc = bnxt_init_int_mode(bp);
 	if (rc)
 		goto init_err;
 
+	rc = register_netdev(dev);
+	if (rc)
+		goto init_err_clr_int;
+
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
 		    board_info[ent->driver_data].name,
 		    (long)pci_resource_start(pdev, 0), dev->dev_addr);
@@ -7002,6 +7044,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
+init_err_clr_int:
+	bnxt_clear_int_mode(bp);
+
 init_err:
 	pci_iounmap(pdev, bp->bar0);
 	pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 8327d0d..1461355 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1024,6 +1024,7 @@ struct bnxt {
 #define BNXT_STATE_FN_RST_DONE	2
 
 	struct bnxt_irq	*irq_tbl;
+	int			total_irqs;
 	u8			mac_addr[ETH_ALEN];
 
 #ifdef CONFIG_BNXT_DCB
-- 
2.5.5

[PATCH 03/28] bnxt_en: Move function reset to bnxt_init_one().

[Selvin Xavier]

From: Michael Chan <michael.chan@broadcom.com>

Now that MSIX is enabled in bnxt_init_one(), resources may be allocated by
the RDMA driver before the network device is opened.  So we cannot do
function reset in bnxt_open() which will clear all the resources.

The proper place to do function reset now is in bnxt_init_one().
If we get AER, we'll do function reset as well.

Cc: David Miller <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 25 ++++++-------------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 -
 2 files changed, 6 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9178bf8..8b00ef4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5613,22 +5613,7 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 static int bnxt_open(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	int rc = 0;
 
-	if (!test_bit(BNXT_STATE_FN_RST_DONE, &bp->state)) {
-		rc = bnxt_hwrm_func_reset(bp);
-		if (rc) {
-			netdev_err(bp->dev, "hwrm chip reset failure rc: %x\n",
-				   rc);
-			rc = -EBUSY;
-			return rc;
-		}
-		/* Do func_reset during the 1st PF open only to prevent killing
-		 * the VFs when the PF is brought down and up.
-		 */
-		if (BNXT_PF(bp))
-			set_bit(BNXT_STATE_FN_RST_DONE, &bp->state);
-	}
 	return __bnxt_open_nic(bp, true, true);
 }
 
@@ -7028,6 +7013,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err;
 
+	rc = bnxt_hwrm_func_reset(bp);
+	if (rc)
+		goto init_err;
+
 	rc = bnxt_init_int_mode(bp);
 	if (rc)
 		goto init_err;
@@ -7069,7 +7058,6 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 					       pci_channel_state_t state)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
-	struct bnxt *bp = netdev_priv(netdev);
 
 	netdev_info(netdev, "PCI I/O error detected\n");
 
@@ -7084,8 +7072,6 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	if (netif_running(netdev))
 		bnxt_close(netdev);
 
-	/* So that func_reset will be done during slot_reset */
-	clear_bit(BNXT_STATE_FN_RST_DONE, &bp->state);
 	pci_disable_device(pdev);
 	rtnl_unlock();
 
@@ -7119,7 +7105,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 	} else {
 		pci_set_master(pdev);
 
-		if (netif_running(netdev))
+		err = bnxt_hwrm_func_reset(bp);
+		if (!err && netif_running(netdev))
 			err = bnxt_open(netdev);
 
 		if (!err)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 1461355..0ee2cc4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1021,7 +1021,6 @@ struct bnxt {
 	unsigned long		state;
 #define BNXT_STATE_OPEN		0
 #define BNXT_STATE_IN_SP_TASK	1
-#define BNXT_STATE_FN_RST_DONE	2
 
 	struct bnxt_irq	*irq_tbl;
 	int			total_irqs;
-- 
2.5.5

[PATCH 04/28] bnxt_en: Improve completion ring allocation for VFs.

[Selvin Xavier]

From: Michael Chan <michael.chan@broadcom.com>

All available remaining completion rings not used by the PF should be
made available for the VFs so that there are enough rings in the VF to
support RDMA.  The earlier workaround code of capping the rings by the
statistics context is removed.

When SRIOV is disabled, call a new function bnxt_restore_pf_fw_resources()
to restore FW resources.  Later on we need to add some logic to account
for RDMA resources.

Cc: David Miller <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       |  8 +++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 14 ++++----------
 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8b00ef4..1f6be83 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4152,7 +4152,7 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 	return rc;
 }
 
-int bnxt_hwrm_func_qcaps(struct bnxt *bp)
+static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 {
 	int rc = 0;
 	struct hwrm_func_qcaps_input req = {0};
@@ -6856,6 +6856,12 @@ static int bnxt_set_dflt_rings(struct bnxt *bp)
 	return rc;
 }
 
+void bnxt_restore_pf_fw_resources(struct bnxt *bp)
+{
+	ASSERT_RTNL();
+	bnxt_hwrm_func_qcaps(bp);
+}
+
 static void bnxt_parse_log_pcie_link(struct bnxt *bp)
 {
 	enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 0ee2cc4..43a4b17 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1234,7 +1234,6 @@ int _hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_set_coal(struct bnxt *);
-int bnxt_hwrm_func_qcaps(struct bnxt *);
 void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
@@ -1245,4 +1244,5 @@ int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_close_nic(struct bnxt *, bool, bool);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
 int bnxt_get_max_rings(struct bnxt *, int *, int *, bool);
+void bnxt_restore_pf_fw_resources(struct bnxt *bp);
 #endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index bff626a..c696025 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -420,15 +420,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 
 	/* Remaining rings are distributed equally amongs VF's for now */
-	/* TODO: the following workaroud is needed to restrict total number
-	 * of vf_cp_rings not exceed number of HW ring groups. This WA should
-	 * be removed once new HWRM provides HW ring groups capability in
-	 * hwrm_func_qcap.
-	 */
-	vf_cp_rings = min_t(u16, pf->max_cp_rings, pf->max_stat_ctxs);
-	vf_cp_rings = (vf_cp_rings - bp->cp_nr_rings) / num_vfs;
-	/* TODO: restore this logic below once the WA above is removed */
-	/* vf_cp_rings = (pf->max_cp_rings - bp->cp_nr_rings) / num_vfs; */
+	vf_cp_rings = (pf->max_cp_rings - bp->cp_nr_rings) / num_vfs;
 	vf_stat_ctx = (pf->max_stat_ctxs - bp->num_stat_ctxs) / num_vfs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = (pf->max_rx_rings - bp->rx_nr_rings * 2) /
@@ -590,7 +582,9 @@ void bnxt_sriov_disable(struct bnxt *bp)
 
 	bp->pf.active_vfs = 0;
 	/* Reclaim all resources for the PF. */
-	bnxt_hwrm_func_qcaps(bp);
+	rtnl_lock();
+	bnxt_restore_pf_fw_resources(bp);
+	rtnl_unlock();
 }
 
 int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs)
-- 
2.5.5

[PATCH 05/28] bnxt_en: Reserve RDMA resources by default.

[Selvin Xavier]

From: Michael Chan <michael.chan@broadcom.com>

If the device supports RDMA, we'll setup network default rings so that
there are enough minimum resources for RDMA, if possible.  However, the
user can still increase network rings to the max if he wants.  The actual
RDMA resources won't be reserved until the RDMA driver registers.

Cc: David Miller <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 58 ++++++++++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  9 +++++
 2 files changed, 66 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1f6be83..7218d65 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4166,6 +4166,11 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 	if (rc)
 		goto hwrm_func_qcaps_exit;
 
+	if (resp->flags & cpu_to_le32(FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED))
+		bp->flags |= BNXT_FLAG_ROCEV1_CAP;
+	if (resp->flags & cpu_to_le32(FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED))
+		bp->flags |= BNXT_FLAG_ROCEV2_CAP;
+
 	bp->tx_push_thresh = 0;
 	if (resp->flags &
 	    cpu_to_le32(FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED))
@@ -4808,6 +4813,24 @@ static int bnxt_setup_int_mode(struct bnxt *bp)
 	return rc;
 }
 
+unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		return bp->pf.max_stat_ctxs;
+#if defined(CONFIG_BNXT_SRIOV)
+	return bp->vf.max_stat_ctxs;
+#endif
+}
+
+unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp)
+{
+	if (BNXT_PF(bp))
+		return bp->pf.max_cp_rings;
+#if defined(CONFIG_BNXT_SRIOV)
+	return bp->vf.max_cp_rings;
+#endif
+}
+
 static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	if (BNXT_PF(bp))
@@ -6832,6 +6855,39 @@ int bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, bool shared)
 	return bnxt_trim_rings(bp, max_rx, max_tx, cp, shared);
 }
 
+static int bnxt_get_dflt_rings(struct bnxt *bp, int *max_rx, int *max_tx,
+			       bool shared)
+{
+	int rc;
+
+	rc = bnxt_get_max_rings(bp, max_rx, max_tx, shared);
+	if (rc)
+		return rc;
+
+	if (bp->flags & BNXT_FLAG_ROCE_CAP) {
+		int max_cp, max_stat, max_irq;
+
+		/* Reserve minimum resources for RoCE */
+		max_cp = bnxt_get_max_func_cp_rings(bp);
+		max_stat = bnxt_get_max_func_stat_ctxs(bp);
+		max_irq = bnxt_get_max_func_irqs(bp);
+		if (max_cp <= BNXT_MIN_ROCE_CP_RINGS ||
+		    max_irq <= BNXT_MIN_ROCE_CP_RINGS ||
+		    max_stat <= BNXT_MIN_ROCE_STAT_CTXS)
+			return 0;
+
+		max_cp -= BNXT_MIN_ROCE_CP_RINGS;
+		max_irq -= BNXT_MIN_ROCE_CP_RINGS;
+		max_stat -= BNXT_MIN_ROCE_STAT_CTXS;
+		max_cp = min_t(int, max_cp, max_irq);
+		max_cp = min_t(int, max_cp, max_stat);
+		rc = bnxt_trim_rings(bp, max_rx, max_tx, max_cp, shared);
+		if (rc)
+			rc = 0;
+	}
+	return rc;
+}
+
 static int bnxt_set_dflt_rings(struct bnxt *bp)
 {
 	int dflt_rings, max_rx_rings, max_tx_rings, rc;
@@ -6840,7 +6896,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp)
 	if (sh)
 		bp->flags |= BNXT_FLAG_SHARED_RINGS;
 	dflt_rings = netif_get_num_default_rss_queues();
-	rc = bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, sh);
+	rc = bnxt_get_dflt_rings(bp, &max_rx_rings, &max_tx_rings, sh);
 	if (rc)
 		return rc;
 	bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 43a4b17..d796836 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -387,6 +387,9 @@ struct rx_tpa_end_cmp_ext {
 #define DB_KEY_TX_PUSH						(0x4 << 28)
 #define DB_LONG_TX_PUSH						(0x2 << 24)
 
+#define BNXT_MIN_ROCE_CP_RINGS	2
+#define BNXT_MIN_ROCE_STAT_CTXS	1
+
 #define INVALID_HW_RING_ID	((u16)-1)
 
 /* The hardware supports certain page sizes.  Use the supported page sizes
@@ -953,6 +956,10 @@ struct bnxt {
 	#define BNXT_FLAG_PORT_STATS	0x400
 	#define BNXT_FLAG_UDP_RSS_CAP	0x800
 	#define BNXT_FLAG_EEE_CAP	0x1000
+	#define BNXT_FLAG_ROCEV1_CAP	0x8000
+	#define BNXT_FLAG_ROCEV2_CAP	0x10000
+	#define BNXT_FLAG_ROCE_CAP	(BNXT_FLAG_ROCEV1_CAP |	\
+					 BNXT_FLAG_ROCEV2_CAP)
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
@@ -1234,6 +1241,8 @@ int _hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_set_coal(struct bnxt *);
+unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
+unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
 void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
-- 
2.5.5

[PATCH 01/28] bnxt_en: Add bnxt_set_max_func_irqs().

[Selvin Xavier]

From: Michael Chan <michael.chan-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>

By refactoring existing code into this new function.  The new function
will be used in subsequent patches.

Cc: David Miller <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
Cc: <netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Signed-off-by: Michael Chan <michael.chan-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>
Signed-off-by: Selvin Xavier <selvin.xavier-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 17 +++++++++++------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e8ab5fd..6cdfe3e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4743,6 +4743,16 @@ static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
 	return 0;
 }
 
+void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
+{
+	if (BNXT_PF(bp))
+		bp->pf.max_irqs = max_irqs;
+#if defined(CONFIG_BNXT_SRIOV)
+	else
+		bp->vf.max_irqs = max_irqs;
+#endif
+}
+
 static int bnxt_setup_msix(struct bnxt *bp)
 {
 	struct msix_entry *msix_ent;
@@ -6949,12 +6959,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
-	if (BNXT_PF(bp))
-		bp->pf.max_irqs = max_irqs;
-#if defined(CONFIG_BNXT_SRIOV)
-	else
-		bp->vf.max_irqs = max_irqs;
-#endif
+	bnxt_set_max_func_irqs(bp, max_irqs);
 	bnxt_set_dflt_rings(bp);
 
 	/* Default RSS hash cfg. */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index b4abc1b..8327d0d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1235,6 +1235,7 @@ int hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_set_coal(struct bnxt *);
 int bnxt_hwrm_func_qcaps(struct bnxt *);
+void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
 int bnxt_hwrm_set_pause(struct bnxt *);
-- 
2.5.5

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH 01/28] bnxt_en: Add bnxt_set_max_func_irqs().

[David Miller]

It really doesn't make any sense to only send 7 out of 28 of these
patches to the networking list.

In fact I would say that you need to split this series into two
components.

One that goes into the networking tree, and once that's accepted you
can submit the IB parts to that subsystem's maintainer.

Re: [PATCH 01/28] bnxt_en: Add bnxt_set_max_func_irqs().

[Michael Chan]

On Mon, Dec 5, 2016 at 8:47 AM, David Miller <davem@davemloft.net> wrote:
>
> It really doesn't make any sense to only send 7 out of 28 of these
> patches to the networking list.
>
> In fact I would say that you need to split this series into two
> components.

OK.  I will resend those bnxt_en patches later today as a separate series.

>
> One that goes into the networking tree, and once that's accepted you
> can submit the IB parts to that subsystem's maintainer.

[PATCH 06/28] bnxt_en: Refactor the driver registration function with firmware.

[Selvin Xavier]

From: Michael Chan <michael.chan-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>

The driver register function with firmware consists of passing version
information and registering for async events.  To support the RDMA driver,
the async events that we need to register may change.  Separate the
driver register function into 2 parts so that we can just update the
async events for the RDMA driver.

Cc: David Miller <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
Cc: <netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Signed-off-by: Michael Chan <michael.chan-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>
Signed-off-by: Selvin Xavier <selvin.xavier-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 34 ++++++++++++++++++++++++++-----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  2 ++
 2 files changed, 31 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7218d65..c26735ea 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3117,27 +3117,46 @@ int hwrm_send_message_silent(struct bnxt *bp, void *msg, u32 msg_len,
 	return rc;
 }
 
-static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
+int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
+				     int bmap_size)
 {
 	struct hwrm_func_drv_rgtr_input req = {0};
-	int i;
 	DECLARE_BITMAP(async_events_bmap, 256);
 	u32 *events = (u32 *)async_events_bmap;
+	int i;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_RGTR, -1, -1);
 
 	req.enables =
-		cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE |
-			    FUNC_DRV_RGTR_REQ_ENABLES_VER |
-			    FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
+		cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD);
 
 	memset(async_events_bmap, 0, sizeof(async_events_bmap));
 	for (i = 0; i < ARRAY_SIZE(bnxt_async_events_arr); i++)
 		__set_bit(bnxt_async_events_arr[i], async_events_bmap);
 
+	if (bmap && bmap_size) {
+		for (i = 0; i < bmap_size; i++) {
+			if (test_bit(i, bmap))
+				__set_bit(i, async_events_bmap);
+		}
+	}
+
 	for (i = 0; i < 8; i++)
 		req.async_event_fwd[i] |= cpu_to_le32(events[i]);
 
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
+{
+	struct hwrm_func_drv_rgtr_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_RGTR, -1, -1);
+
+	req.enables =
+		cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE |
+			    FUNC_DRV_RGTR_REQ_ENABLES_VER);
+
 	req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
 	req.ver_maj = DRV_VER_MAJ;
 	req.ver_min = DRV_VER_MIN;
@@ -3146,6 +3165,7 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 	if (BNXT_PF(bp)) {
 		DECLARE_BITMAP(vf_req_snif_bmap, 256);
 		u32 *data = (u32 *)vf_req_snif_bmap;
+		int i;
 
 		memset(vf_req_snif_bmap, 0, sizeof(vf_req_snif_bmap));
 		for (i = 0; i < ARRAY_SIZE(bnxt_vf_req_snif); i++)
@@ -7023,6 +7043,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err;
 
+	rc = bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0);
+	if (rc)
+		goto init_err;
+
 	/* Get the MAX capabilities for this function */
 	rc = bnxt_hwrm_func_qcaps(bp);
 	if (rc) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index d796836..eec2415 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1240,6 +1240,8 @@ void bnxt_hwrm_cmd_hdr_init(struct bnxt *, void *, u16, u16, u16);
 int _hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
+int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
+				     int bmap_size);
 int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
-- 
2.5.5

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 07/28] bnxt_en: Add interface to support RDMA driver.

[Selvin Xavier]

From: Michael Chan <michael.chan@broadcom.com>

Since the network driver and RDMA driver operate on the same PCI function,
we need to create an interface to allow the RDMA driver to share resources
with the network driver.

1. Create a new bnxt_en_dev struct which will be returned by
bnxt_ulp_probe() upon success.  After that, all calls from the RDMA driver
to bnxt_en will pass a pointer to this struct.

2. This struct contains additional function pointers to register, request
msix, send fw messages, register for async events.

3. If the RDMA driver wants to enable RDMA on the function, it needs to
call the function pointer bnxt_register_device().  A ulp_ops structure
is passed for upcalls from bnxt_en to the RDMA driver.

4. MSIX is requested by calling the function pointer bnxt_request_msix().

5. The RMDA driver can call firmware APIs using the bnxt_send_fw_msg()
function pointer.

6. 1 stats context is reserved when the RDMA driver registers.  MSIX
and completion rings are reserved when the RDMA driver requests for
MSIX.

7. When the RDMA driver calls bnxt_unregister_device(), all RDMA resources
will be cleaned up.

Cc: David Miller <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/Makefile   |   2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |  34 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |   6 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 288 ++++++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h |  91 ++++++++
 5 files changed, 417 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
 create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h

diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile
index b233a86..6082ed1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/Makefile
+++ b/drivers/net/ethernet/broadcom/bnxt/Makefile
@@ -1,3 +1,3 @@
 obj-$(CONFIG_BNXT) += bnxt_en.o
 
-bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o
+bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c26735ea..19f26b8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -52,6 +52,7 @@
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
+#include "bnxt_ulp.h"
 #include "bnxt_sriov.h"
 #include "bnxt_ethtool.h"
 #include "bnxt_dcb.h"
@@ -1528,12 +1529,11 @@ static int bnxt_async_event_process(struct bnxt *bp,
 		set_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event);
 		break;
 	default:
-		netdev_err(bp->dev, "unhandled ASYNC event (id 0x%x)\n",
-			   event_id);
 		goto async_event_process_exit;
 	}
 	schedule_work(&bp->sp_task);
 async_event_process_exit:
+	bnxt_ulp_async_events(bp, cmpl);
 	return 0;
 }
 
@@ -3547,7 +3547,7 @@ static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id, u16 ctx_idx)
 	return rc;
 }
 
-static int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
+int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 {
 	unsigned int ring = 0, grp_idx;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
@@ -3595,6 +3595,9 @@ static int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 #endif
 	if ((bp->flags & BNXT_FLAG_STRIP_VLAN) || def_vlan)
 		req.flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE);
+	if (!vnic_id && bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP))
+		req.flags |=
+			cpu_to_le32(VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE);
 
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
@@ -4842,6 +4845,16 @@ unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp)
 #endif
 }
 
+void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max)
+{
+	if (BNXT_PF(bp))
+		bp->pf.max_stat_ctxs = max;
+#if defined(CONFIG_BNXT_SRIOV)
+	else
+		bp->vf.max_stat_ctxs = max;
+#endif
+}
+
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp)
 {
 	if (BNXT_PF(bp))
@@ -4851,6 +4864,16 @@ unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp)
 #endif
 }
 
+void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max)
+{
+	if (BNXT_PF(bp))
+		bp->pf.max_cp_rings = max;
+#if defined(CONFIG_BNXT_SRIOV)
+	else
+		bp->vf.max_cp_rings = max;
+#endif
+}
+
 static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	if (BNXT_PF(bp))
@@ -6767,6 +6790,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	pci_iounmap(pdev, bp->bar2);
 	pci_iounmap(pdev, bp->bar1);
 	pci_iounmap(pdev, bp->bar0);
+	kfree(bp->edev);
+	bp->edev = NULL;
 	free_netdev(dev);
 
 	pci_release_regions(pdev);
@@ -6936,6 +6961,7 @@ void bnxt_restore_pf_fw_resources(struct bnxt *bp)
 {
 	ASSERT_RTNL();
 	bnxt_hwrm_func_qcaps(bp);
+	bnxt_subtract_ulp_resources(bp, BNXT_ROCE_ULP);
 }
 
 static void bnxt_parse_log_pcie_link(struct bnxt *bp)
@@ -7047,6 +7073,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err;
 
+	bp->ulp_probe = bnxt_ulp_probe;
+
 	/* Get the MAX capabilities for this function */
 	rc = bnxt_hwrm_func_qcaps(bp);
 	if (rc) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index eec2415..16defe9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -972,6 +972,9 @@ struct bnxt {
 #define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp))
 #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0)
 
+	struct bnxt_en_dev	*edev;
+	struct bnxt_en_dev *	(*ulp_probe)(struct net_device *);
+
 	struct bnxt_napi	**bnapi;
 
 	struct bnxt_rx_ring_info	*rx_ring;
@@ -1242,9 +1245,12 @@ int hwrm_send_message(struct bnxt *, void *, u32, int);
 int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
 				     int bmap_size);
+int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
 int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
+void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
+void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max);
 void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
new file mode 100644
index 0000000..a018f4b
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -0,0 +1,288 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2016 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <asm/byteorder.h>
+#include <linux/bitmap.h>
+
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_ulp.h"
+
+static int bnxt_register_dev(struct bnxt_en_dev *edev, int ulp_id,
+			     struct bnxt_ulp_ops *ulp_ops, void *handle)
+{
+	struct net_device *dev = edev->net;
+	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_ulp *ulp;
+
+	ASSERT_RTNL();
+	if (ulp_id >= BNXT_MAX_ULP)
+		return -EINVAL;
+
+	ulp = &edev->ulp_tbl[ulp_id];
+	if (rcu_access_pointer(ulp->ulp_ops)) {
+		netdev_err(bp->dev, "ulp id %d already registered\n", ulp_id);
+		return -EBUSY;
+	}
+	if (ulp_id == BNXT_ROCE_ULP) {
+		unsigned int max_stat_ctxs;
+
+		max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
+		if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS ||
+		    bp->num_stat_ctxs == max_stat_ctxs)
+			return -ENOMEM;
+		bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs -
+					    BNXT_MIN_ROCE_STAT_CTXS);
+	}
+
+	atomic_set(&ulp->ref_count, 0);
+	ulp->handle = handle;
+	rcu_assign_pointer(ulp->ulp_ops, ulp_ops);
+
+	if (ulp_id == BNXT_ROCE_ULP) {
+		if (test_bit(BNXT_STATE_OPEN, &bp->state))
+			bnxt_hwrm_vnic_cfg(bp, 0);
+	}
+
+	return 0;
+}
+
+static int bnxt_unregister_dev(struct bnxt_en_dev *edev, int ulp_id)
+{
+	struct net_device *dev = edev->net;
+	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_ulp *ulp;
+
+	ASSERT_RTNL();
+	if (ulp_id >= BNXT_MAX_ULP)
+		return -EINVAL;
+
+	ulp = &edev->ulp_tbl[ulp_id];
+	if (!rcu_access_pointer(ulp->ulp_ops)) {
+		netdev_err(bp->dev, "ulp id %d not registered\n", ulp_id);
+		return -EINVAL;
+	}
+	if (ulp_id == BNXT_ROCE_ULP) {
+		unsigned int max_stat_ctxs;
+
+		max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
+		bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs + 1);
+	}
+	if (ulp->max_async_event_id)
+		bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0);
+
+	RCU_INIT_POINTER(ulp->ulp_ops, NULL);
+	synchronize_rcu();
+	ulp->max_async_event_id = 0;
+	ulp->async_events_bmap = NULL;
+	return 0;
+}
+
+static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
+			      struct bnxt_msix_entry *ent, int num_msix)
+{
+	struct net_device *dev = edev->net;
+	struct bnxt *bp = netdev_priv(dev);
+	int max_idx, max_cp_rings;
+	int avail_msix, i, idx;
+
+	ASSERT_RTNL();
+	if (ulp_id != BNXT_ROCE_ULP)
+		return -EINVAL;
+
+	if (!(bp->flags & BNXT_FLAG_USING_MSIX))
+		return -ENODEV;
+
+	max_cp_rings = bnxt_get_max_func_cp_rings(bp);
+	max_idx = min_t(int, bp->total_irqs, max_cp_rings);
+	avail_msix = max_idx - bp->cp_nr_rings;
+	if (!avail_msix)
+		return -ENOMEM;
+	if (avail_msix > num_msix)
+		avail_msix = num_msix;
+
+	idx = max_idx - avail_msix;
+	for (i = 0; i < avail_msix; i++) {
+		ent[i].vector = bp->irq_tbl[idx + i].vector;
+		ent[i].ring_idx = idx + i;
+		ent[i].db_offset = (idx + i) * 0x80;
+	}
+	bnxt_set_max_func_irqs(bp, max_idx - avail_msix);
+	bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix);
+	edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
+	return avail_msix;
+}
+
+static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id)
+{
+	struct net_device *dev = edev->net;
+	struct bnxt *bp = netdev_priv(dev);
+	int max_cp_rings, msix_requested;
+
+	ASSERT_RTNL();
+	if (ulp_id != BNXT_ROCE_ULP)
+		return -EINVAL;
+
+	max_cp_rings = bnxt_get_max_func_cp_rings(bp);
+	msix_requested = edev->ulp_tbl[ulp_id].msix_requested;
+	bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested);
+	edev->ulp_tbl[ulp_id].msix_requested = 0;
+	bnxt_set_max_func_irqs(bp, bp->total_irqs);
+	return 0;
+}
+
+void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id)
+{
+	ASSERT_RTNL();
+	if (bnxt_ulp_registered(bp->edev, ulp_id)) {
+		struct bnxt_en_dev *edev = bp->edev;
+		unsigned int msix_req, max;
+
+		msix_req = edev->ulp_tbl[ulp_id].msix_requested;
+		max = bnxt_get_max_func_cp_rings(bp);
+		bnxt_set_max_func_cp_rings(bp, max - msix_req);
+		max = bnxt_get_max_func_stat_ctxs(bp);
+		bnxt_set_max_func_stat_ctxs(bp, max - 1);
+	}
+}
+
+static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id,
+			 struct bnxt_fw_msg *fw_msg)
+{
+	struct net_device *dev = edev->net;
+	struct bnxt *bp = netdev_priv(dev);
+	struct input *req;
+	int rc;
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	req = fw_msg->msg;
+	req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);
+	rc = _hwrm_send_message(bp, fw_msg->msg, fw_msg->msg_len,
+				fw_msg->timeout);
+	if (!rc) {
+		struct output *resp = bp->hwrm_cmd_resp_addr;
+		u32 len = le16_to_cpu(resp->resp_len);
+
+		if (fw_msg->resp_max_len < len)
+			len = fw_msg->resp_max_len;
+
+		memcpy(fw_msg->resp, resp, len);
+	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+void bnxt_ulp_stop(struct bnxt *bp)
+{
+	struct bnxt_en_dev *edev = bp->edev;
+	struct bnxt_ulp_ops *ops;
+	int i;
+
+	if (!edev)
+		return;
+
+	rcu_read_lock();
+	for (i = 0; i < BNXT_MAX_ULP; i++) {
+		struct bnxt_ulp *ulp = &edev->ulp_tbl[i];
+
+		ops = rcu_dereference(ulp->ulp_ops);
+		if (!ops || !ops->ulp_stop)
+			continue;
+	}
+	rcu_read_unlock();
+}
+
+void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl)
+{
+	u16 event_id = le16_to_cpu(cmpl->event_id);
+	struct bnxt_en_dev *edev = bp->edev;
+	struct bnxt_ulp_ops *ops;
+	int i;
+
+	if (!edev)
+		return;
+
+	rcu_read_lock();
+	for (i = 0; i < BNXT_MAX_ULP; i++) {
+		struct bnxt_ulp *ulp = &edev->ulp_tbl[i];
+
+		ops = rcu_dereference(ulp->ulp_ops);
+		if (!ops || !ops->ulp_async_notifier)
+			continue;
+		if (!ulp->async_events_bmap ||
+		    event_id > ulp->max_async_event_id)
+			continue;
+
+		/* Read max_async_event_id first before testing the bitmap. */
+		smp_rmb();
+		if (test_bit(event_id, ulp->async_events_bmap))
+			ops->ulp_async_notifier(ulp->handle, cmpl);
+	}
+	rcu_read_unlock();
+}
+
+static int bnxt_register_async_events(struct bnxt_en_dev *edev, int ulp_id,
+				      unsigned long *events_bmap, u16 max_id)
+{
+	struct net_device *dev = edev->net;
+	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_ulp *ulp;
+
+	if (ulp_id >= BNXT_MAX_ULP)
+		return -EINVAL;
+
+	ulp = &edev->ulp_tbl[ulp_id];
+	ulp->async_events_bmap = events_bmap;
+	/* Make sure bnxt_ulp_async_events() sees this order */
+	smp_wmb();
+	ulp->max_async_event_id = max_id;
+	bnxt_hwrm_func_rgtr_async_events(bp, events_bmap, max_id + 1);
+	return 0;
+}
+
+static const struct bnxt_en_ops bnxt_en_ops_tbl = {
+	.bnxt_register_device	= bnxt_register_dev,
+	.bnxt_unregister_device	= bnxt_unregister_dev,
+	.bnxt_request_msix	= bnxt_req_msix_vecs,
+	.bnxt_free_msix		= bnxt_free_msix_vecs,
+	.bnxt_send_fw_msg	= bnxt_send_msg,
+	.bnxt_register_fw_async_events	= bnxt_register_async_events,
+};
+
+struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_en_dev *edev;
+
+	edev = bp->edev;
+	if (!edev) {
+		edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+		if (!edev)
+			return ERR_PTR(-ENOMEM);
+		edev->en_ops = &bnxt_en_ops_tbl;
+		if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
+			edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
+		if (bp->flags & BNXT_FLAG_ROCEV2_CAP)
+			edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP;
+		edev->net = dev;
+		edev->pdev = bp->pdev;
+		bp->edev = edev;
+	}
+	return bp->edev;
+}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
new file mode 100644
index 0000000..1ebccd8
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -0,0 +1,91 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2016 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_ULP_H
+#define BNXT_ULP_H
+
+#define BNXT_ROCE_ULP	0
+#define BNXT_OTHER_ULP	1
+#define BNXT_MAX_ULP	2
+
+#define BNXT_MIN_ROCE_CP_RINGS	2
+#define BNXT_MIN_ROCE_STAT_CTXS	1
+
+struct hwrm_async_event_cmpl;
+struct bnxt;
+
+struct bnxt_ulp_ops {
+	/* async_notifier() cannot sleep (in BH context) */
+	void (*ulp_async_notifier)(void *, struct hwrm_async_event_cmpl *);
+	void (*ulp_stop)(void *);
+	void (*ulp_start)(void *);
+	void (*ulp_sriov_config)(void *, int);
+};
+
+struct bnxt_msix_entry {
+	u32	vector;
+	u32	ring_idx;
+	u32	db_offset;
+};
+
+struct bnxt_fw_msg {
+	void	*msg;
+	int	msg_len;
+	void	*resp;
+	int	resp_max_len;
+	int	timeout;
+};
+
+struct bnxt_ulp {
+	void		*handle;
+	struct bnxt_ulp_ops __rcu *ulp_ops;
+	unsigned long	*async_events_bmap;
+	u16		max_async_event_id;
+	u16		msix_requested;
+	atomic_t	ref_count;
+};
+
+struct bnxt_en_dev {
+	struct net_device *net;
+	struct pci_dev *pdev;
+	u32 flags;
+	#define BNXT_EN_FLAG_ROCEV1_CAP		0x1
+	#define BNXT_EN_FLAG_ROCEV2_CAP		0x2
+	#define BNXT_EN_FLAG_ROCE_CAP		(BNXT_EN_FLAG_ROCEV1_CAP | \
+						 BNXT_EN_FLAG_ROCEV2_CAP)
+	const struct bnxt_en_ops	*en_ops;
+	struct bnxt_ulp			ulp_tbl[BNXT_MAX_ULP];
+};
+
+struct bnxt_en_ops {
+	int (*bnxt_register_device)(struct bnxt_en_dev *, int,
+				    struct bnxt_ulp_ops *, void *);
+	int (*bnxt_unregister_device)(struct bnxt_en_dev *, int);
+	int (*bnxt_request_msix)(struct bnxt_en_dev *, int,
+				 struct bnxt_msix_entry *, int);
+	int (*bnxt_free_msix)(struct bnxt_en_dev *, int);
+	int (*bnxt_send_fw_msg)(struct bnxt_en_dev *, int,
+				struct bnxt_fw_msg *);
+	int (*bnxt_register_fw_async_events)(struct bnxt_en_dev *, int,
+					     unsigned long *, u16);
+};
+
+static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id)
+{
+	if (edev && rcu_access_pointer(edev->ulp_tbl[ulp_id].ulp_ops))
+		return true;
+	return false;
+}
+
+void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id);
+void bnxt_ulp_stop(struct bnxt *bp);
+void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl);
+struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev);
+
+#endif
-- 
2.5.5