Merge branch 'bnxt_en-RDMA'

Michael Chan says:

====================
bnxt_en: Add interface to support RDMA driver.

This series adds an interface to support a brand new RDMA driver bnxt_re.
The first step is to re-arrange some code so that pci_enable_msix() can
be called during pci probe.  The purpose is to allow the RDMA driver to
initialize and stay initialized whether the netdev is up or down.

Then we make some changes to VF resource allocation so that there is
enough resources to support RDMA.

Finally the last patch adds a simple interface to allow the RDMA driver to
probe and register itself with any bnxt_en devices that support RDMA.
Once registered, the RDMA driver can request MSIX, send fw messages, and
receive some notifications.

v2: Fixed kbuild test robot warnings.

David, please consider this series for net-next.  Thanks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnxt/Makefile

 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

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 |		\
@@ -965,6 +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;
@@ -1021,9 +1031,9 @@ 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;
 	u8			mac_addr[ETH_ALEN];
 
 #ifdef CONFIG_BNXT_DCB
@@ -1233,8 +1243,15 @@ 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_vnic_cfg(struct bnxt *bp, u16 vnic_id);
 int bnxt_hwrm_set_coal(struct bnxt *);
-int bnxt_hwrm_func_qcaps(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);
 int bnxt_hwrm_set_pause(struct bnxt *);
@@ -1244,4 +1261,5 @@ 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

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)

drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c

+/* 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;
+	int i = 0;
+
+	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;
+	while (atomic_read(&ulp->ref_count) != 0 && i < 10) {
+		msleep(100);
+		i++;
+	}
+	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;
+}
+
+static void bnxt_ulp_get(struct bnxt_ulp *ulp)
+{
+	atomic_inc(&ulp->ref_count);
+}
+
+static void bnxt_ulp_put(struct bnxt_ulp *ulp)
+{
+	atomic_dec(&ulp->ref_count);
+}
+
+void bnxt_ulp_stop(struct bnxt *bp)
+{
+	struct bnxt_en_dev *edev = bp->edev;
+	struct bnxt_ulp_ops *ops;
+	int i;
+
+	if (!edev)
+		return;
+
+	for (i = 0; i < BNXT_MAX_ULP; i++) {
+		struct bnxt_ulp *ulp = &edev->ulp_tbl[i];
+
+		ops = rtnl_dereference(ulp->ulp_ops);
+		if (!ops || !ops->ulp_stop)
+			continue;
+		ops->ulp_stop(ulp->handle);
+	}
+}
+
+void bnxt_ulp_start(struct bnxt *bp)
+{
+	struct bnxt_en_dev *edev = bp->edev;
+	struct bnxt_ulp_ops *ops;
+	int i;
+
+	if (!edev)
+		return;
+
+	for (i = 0; i < BNXT_MAX_ULP; i++) {
+		struct bnxt_ulp *ulp = &edev->ulp_tbl[i];
+
+		ops = rtnl_dereference(ulp->ulp_ops);
+		if (!ops || !ops->ulp_start)
+			continue;
+		ops->ulp_start(ulp->handle);
+	}
+}
+
+void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs)
+{
+	struct bnxt_en_dev *edev = bp->edev;
+	struct bnxt_ulp_ops *ops;
+	int i;
+
+	if (!edev)
+		return;
+
+	for (i = 0; i < BNXT_MAX_ULP; i++) {
+		struct bnxt_ulp *ulp = &edev->ulp_tbl[i];
+
+		rcu_read_lock();
+		ops = rcu_dereference(ulp->ulp_ops);
+		if (!ops || !ops->ulp_sriov_config) {
+			rcu_read_unlock();
+			continue;
+		}
+		bnxt_ulp_get(ulp);
+		rcu_read_unlock();
+		ops->ulp_sriov_config(ulp->handle, num_vfs);
+		bnxt_ulp_put(ulp);
+	}
+}
+
+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;
+}

drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h

+/* 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_start(struct bnxt *bp);
+void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
+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