[1/8] bnxt_en: Add auxiliary driver support

Message ID 20230108030208.26390-2-ajit.khaparde@broadcom.com
State New
Headers
Series Add Auxiliary driver support |

Commit Message

Ajit Khaparde Jan. 8, 2023, 3:02 a.m. UTC
  Add auxiliary driver support.
An auxiliary device will be created if the hardware indicates
support for RDMA.
The bnxt_ulp_probe() function has been removed and a new
bnxt_rdma_aux_device_add() function has been added.
The bnxt_free_msix_vecs() and bnxt_req_msix_vecs() will now hold
the RTNL lock when they call the bnxt_close_nic()and bnxt_open_nic()
since the device close and open need to be protected under RTNL lock.
The operations between the bnxt_en and bnxt_re will be protected
using the en_ops_lock.
This will be used by the bnxt_re driver in a follow-on patch
to create ROCE interfaces.

Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Selvin Xavier <selvin.xavier@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |   8 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |   8 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 185 +++++++++++++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h |   7 +-
 4 files changed, 177 insertions(+), 31 deletions(-)
  

Comments

Jakub Kicinski Jan. 10, 2023, 10:51 p.m. UTC | #1
On Sat,  7 Jan 2023 19:02:01 -0800 Ajit Khaparde wrote:
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
> index 2e54bf4fc7a7..6c697172f042 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
> @@ -25,32 +25,37 @@
>  #include "bnxt_hwrm.h"
>  #include "bnxt_ulp.h"
>  
> +static DEFINE_IDA(bnxt_aux_dev_ids);
> +
>  static int bnxt_register_dev(struct bnxt_en_dev *edev, unsigned 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;
> +	int rc = 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 already registered\n", ulp_id);
> -		return -EBUSY;
> +		rc = -EBUSY;
> +		goto exit;

The change to jump to the return statement rater than return directly
seems unrelated to the rest of the patch, and wrong.

>  	}
>  	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->cp_nr_rings == max_stat_ctxs)
> -			return -ENOMEM;
> +		    bp->cp_nr_rings == max_stat_ctxs) {
> +			rc = -ENOMEM;
> +			goto exit;
> +		}
>  	}
>  
> -	atomic_set(&ulp->ref_count, 0);
> +	atomic_set(&ulp->ref_count, 1);
>  	ulp->handle = handle;
>  	rcu_assign_pointer(ulp->ulp_ops, ulp_ops);
>  
> @@ -59,7 +64,8 @@ static int bnxt_register_dev(struct bnxt_en_dev *edev, unsigned int ulp_id,
>  			bnxt_hwrm_vnic_cfg(bp, 0);
>  	}
>  
> -	return 0;
> +exit:
> +	return rc;
>  }
>  
>  static int bnxt_unregister_dev(struct bnxt_en_dev *edev, unsigned int ulp_id)
> @@ -69,10 +75,11 @@ static int bnxt_unregister_dev(struct bnxt_en_dev *edev, unsigned int ulp_id)
>  	struct bnxt_ulp *ulp;
>  	int i = 0;
>  
> -	ASSERT_RTNL();
>  	if (ulp_id >= BNXT_MAX_ULP)
>  		return -EINVAL;
>  
> +	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
> +
>  	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);
> @@ -126,7 +133,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id,
>  	int total_vecs;
>  	int rc = 0;
>  
> -	ASSERT_RTNL();
>  	if (ulp_id != BNXT_ROCE_ULP)
>  		return -EINVAL;
>  
> @@ -149,6 +155,7 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id,
>  		max_idx = min_t(int, bp->total_irqs, max_cp_rings);
>  		idx = max_idx - avail_msix;
>  	}
> +
>  	edev->ulp_tbl[ulp_id].msix_base = idx;
>  	edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
>  	hw_resc = &bp->hw_resc;
> @@ -156,8 +163,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id,
>  	if (bp->total_irqs < total_vecs ||
>  	    (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) {
>  		if (netif_running(dev)) {
> +			rtnl_lock();

What prevents the device from going down after you check running 
but before you take the lock?

>  			bnxt_close_nic(bp, true, false);
>  			rc = bnxt_open_nic(bp, true, false);
> +			rtnl_unlock();
>  		} else {
>  			rc = bnxt_reserve_rings(bp, true);
>  		}

> @@ -475,6 +467,143 @@ static const struct bnxt_en_ops bnxt_en_ops_tbl = {
>  	.bnxt_register_fw_async_events	= bnxt_register_async_events,
>  };
>  
> +void bnxt_aux_dev_free(struct bnxt *bp)
> +{
> +	kfree(bp->aux_dev);
> +	bp->aux_dev = NULL;
> +}
> +
> +static struct bnxt_aux_dev *bnxt_aux_dev_alloc(struct bnxt *bp)
> +{
> +	struct bnxt_aux_dev *bnxt_adev;
> +
> +	bnxt_adev =  kzalloc(sizeof(*bnxt_adev), GFP_KERNEL);

double space

> +	if (!bnxt_adev)
> +		return NULL;
> +
> +	return bnxt_adev;

This entire function is rather pointless.

If you really want it - it can be simply written as:

static struct bnxt_aux_dev *bnxt_aux_dev_alloc(struct bnxt *bp)
{
	return kzalloc(sizeof(struct bnxt_aux_dev), GFP_KERNEL);
}

> +}
> +
> +void bnxt_rdma_aux_device_uninit(struct bnxt *bp)
> +{
> +	struct bnxt_aux_dev *bnxt_adev;
> +	struct auxiliary_device *adev;
> +
> +	/* Skip if no auxiliary device init was done. */
> +	if (!(bp->flags & BNXT_FLAG_ROCE_CAP))
> +		return;
> +
> +	bnxt_adev = bp->aux_dev;
> +	adev = &bnxt_adev->aux_dev;
> +	auxiliary_device_delete(adev);

auxiliary_device_delete() waits for all the references to disappear?
The lifetime rules between adev and "edev" seem a little odd to me,
maybe I'm not familiar enough with auxdev.

> +	auxiliary_device_uninit(adev);
> +	if (bnxt_adev->id >= 0)
> +		ida_free(&bnxt_aux_dev_ids, bnxt_adev->id);
> +}
> +
> +void bnxt_rdma_aux_device_init(struct bnxt *bp)
> +{
> +	int rc;
> +
> +	if (bp->flags & BNXT_FLAG_ROCE_CAP) {

flip the condition and return early, don't indent an entire function.

> +		bp->aux_dev = bnxt_aux_dev_alloc(bp);
> +		if (!bp->aux_dev)
> +			goto skip_ida_init;
> +
> +		bp->aux_dev->id = ida_alloc(&bnxt_aux_dev_ids, GFP_KERNEL);
> +		if (bp->aux_dev->id < 0) {
> +			netdev_warn(bp->dev,
> +				    "ida alloc failed for ROCE auxiliary device\n");
> +			goto skip_aux_init;
> +		}
> +
> +		/* If aux bus init fails, continue with netdev init. */
> +		rc = bnxt_rdma_aux_device_add(bp);
> +		if (rc) {
> +			netdev_warn(bp->dev,
> +				    "Failed to add auxiliary device for ROCE\n");
> +			goto aux_add_failed;
> +		}
> +	}
> +	return;
> +
> +aux_add_failed:
> +	ida_free(&bnxt_aux_dev_ids, bp->aux_dev->id);
> +	bp->aux_dev->id = -1;
> +skip_aux_init:
> +	bnxt_aux_dev_free(bp);
> +skip_ida_init:
> +	bp->flags &= ~BNXT_FLAG_ROCE_CAP;
> +}

> +static inline void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp)

Please don't use inline for no good reason.

> +{
> +	edev->en_ops = &bnxt_en_ops_tbl;
> +	edev->net = bp->dev;
> +	edev->pdev = bp->pdev;
> +	edev->l2_db_size = bp->db_size;
> +	edev->l2_db_size_nc = bp->db_size;
> +
> +	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;
> +}
> +
> +int bnxt_rdma_aux_device_add(struct bnxt *bp)
> +{
> +	struct bnxt_aux_dev *bnxt_adev = bp->aux_dev;
> +	struct bnxt_en_dev *edev = bnxt_adev->edev;
> +	struct auxiliary_device *aux_dev;
> +	int ret;
> +
> +	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
> +	if (!edev) {
> +		ret = -ENOMEM;
> +		goto cleanup_edev_failure;
> +	}
> +
> +	aux_dev = &bnxt_adev->aux_dev;
> +	aux_dev->id = bnxt_adev->id;
> +	aux_dev->name = "rdma";
> +	aux_dev->dev.parent = &bp->pdev->dev;
> +	aux_dev->dev.release = bnxt_aux_dev_release;
> +
> +	bnxt_adev->edev = edev;
> +	bp->edev = edev;
> +	bnxt_set_edev_info(edev, bp);
> +
> +	ret = auxiliary_device_init(aux_dev);
> +	if (ret)
> +		goto cleanup_init_failure;
> +
> +	ret = auxiliary_device_add(aux_dev);
> +	if (ret)
> +		goto cleanup_add_failure;
> +
> +	return 0;
> +
> +cleanup_add_failure:

Name your labels after what you clean up, not what failed.

> +	auxiliary_device_uninit(aux_dev);
> +cleanup_init_failure:
> +	kfree(edev);
> +	bp->edev = NULL;
> +cleanup_edev_failure:

Don't jump to the return statement, just return.

> +	return ret;
> +}
> +
>  struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev)
>  {
>  	struct bnxt *bp = netdev_priv(dev);
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
> index 42b50abc3e91..647147a68554 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
> @@ -17,6 +17,7 @@
>  #define BNXT_MIN_ROCE_STAT_CTXS	1
>  
>  struct hwrm_async_event_cmpl;
> +struct bnxt_aux_dev;

This forward declaration is not needed, at least in this patch.

>  struct bnxt;
>  
>  struct bnxt_msix_entry {
> @@ -102,10 +103,14 @@ int bnxt_get_ulp_stat_ctxs(struct bnxt *bp);
>  void bnxt_ulp_stop(struct bnxt *bp);
>  void bnxt_ulp_start(struct bnxt *bp, int err);
>  void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
> -void bnxt_ulp_shutdown(struct bnxt *bp);
>  void bnxt_ulp_irq_stop(struct bnxt *bp);
>  void bnxt_ulp_irq_restart(struct bnxt *bp, int err);
>  void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl);
> +void bnxt_aux_dev_release(struct device *dev);
> +int bnxt_rdma_aux_device_add(struct bnxt *bp);

This is only used in bnxt_ulp.c, please remove the declaration and make
it static. Please check other functions for the same problem.

> +void bnxt_rdma_aux_device_uninit(struct bnxt *bp);
> +void bnxt_rdma_aux_device_init(struct bnxt *bp);
> +void bnxt_aux_dev_free(struct bnxt *bp);
  
Ajit Khaparde Jan. 10, 2023, 11:49 p.m. UTC | #2
On Tue, Jan 10, 2023 at 2:51 PM Jakub Kicinski <kuba@kernel.org> wrote:
>
> On Sat,  7 Jan 2023 19:02:01 -0800 Ajit Khaparde wrote:
> > diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
:::: snip ::::
>
> This forward declaration is not needed, at least in this patch.
>
> >  struct bnxt;
> >
> >  struct bnxt_msix_entry {
> > @@ -102,10 +103,14 @@ int bnxt_get_ulp_stat_ctxs(struct bnxt *bp);
> >  void bnxt_ulp_stop(struct bnxt *bp);
> >  void bnxt_ulp_start(struct bnxt *bp, int err);
> >  void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
> > -void bnxt_ulp_shutdown(struct bnxt *bp);
> >  void bnxt_ulp_irq_stop(struct bnxt *bp);
> >  void bnxt_ulp_irq_restart(struct bnxt *bp, int err);
> >  void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl);
> > +void bnxt_aux_dev_release(struct device *dev);
> > +int bnxt_rdma_aux_device_add(struct bnxt *bp);
>
> This is only used in bnxt_ulp.c, please remove the declaration and make
> it static. Please check other functions for the same problem.
>
> > +void bnxt_rdma_aux_device_uninit(struct bnxt *bp);
> > +void bnxt_rdma_aux_device_init(struct bnxt *bp);
> > +void bnxt_aux_dev_free(struct bnxt *bp);
>
Thanks Kuba. I will go over the comments and send the next version.
  
kernel test robot Jan. 12, 2023, 7:08 p.m. UTC | #3
Hi Ajit,

I love your patch! Yet something to improve:

[auto build test ERROR on linus/master]
[also build test ERROR on v6.2-rc3 next-20230112]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Ajit-Khaparde/bnxt_en-Add-auxiliary-driver-support/20230108-110519
patch link:    https://lore.kernel.org/r/20230108030208.26390-2-ajit.khaparde%40broadcom.com
patch subject: [PATCH 1/8] bnxt_en: Add auxiliary driver support
config: i386-randconfig-a001-20220124
compiler: gcc-11 (Debian 11.3.0-8) 11.3.0
reproduce (this is a W=1 build):
        # https://github.com/intel-lab-lkp/linux/commit/d04297da18739e2bc3c9262f658ad880d58a2051
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Ajit-Khaparde/bnxt_en-Add-auxiliary-driver-support/20230108-110519
        git checkout d04297da18739e2bc3c9262f658ad880d58a2051
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        make W=1 O=build_dir ARCH=i386 olddefconfig
        make W=1 O=build_dir ARCH=i386 SHELL=/bin/bash

If you fix the issue, kindly add following tag where applicable
| Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>, old ones prefixed by <<):

>> ERROR: modpost: "auxiliary_device_init" [drivers/net/ethernet/broadcom/bnxt/bnxt_en.ko] undefined!
>> ERROR: modpost: "__auxiliary_device_add" [drivers/net/ethernet/broadcom/bnxt/bnxt_en.ko] undefined!
  

Patch

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 16ce7a90610c..c5cbf2307e07 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13178,6 +13178,9 @@  static void bnxt_remove_one(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(dev);
 
+	bnxt_rdma_aux_device_uninit(bp);
+	bnxt_aux_dev_free(bp);
+
 	if (BNXT_PF(bp))
 		bnxt_sriov_disable(bp);
 
@@ -13776,11 +13779,13 @@  static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	bnxt_dl_fw_reporters_create(bp);
 
+	bnxt_rdma_aux_device_init(bp);
+
 	bnxt_print_device_info(bp);
 
 	pci_save_state(pdev);
-	return 0;
 
+	return 0;
 init_err_cleanup:
 	bnxt_dl_unregister(bp);
 init_err_dl:
@@ -13824,7 +13829,6 @@  static void bnxt_shutdown(struct pci_dev *pdev)
 	if (netif_running(dev))
 		dev_close(dev);
 
-	bnxt_ulp_shutdown(bp);
 	bnxt_clear_int_mode(bp);
 	pci_disable_device(pdev);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 5163ef4a49ea..4df2da81708e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -24,6 +24,7 @@ 
 #include <linux/interrupt.h>
 #include <linux/rhashtable.h>
 #include <linux/crash_dump.h>
+#include <linux/auxiliary_bus.h>
 #include <net/devlink.h>
 #include <net/dst_metadata.h>
 #include <net/xdp.h>
@@ -1631,6 +1632,12 @@  struct bnxt_fw_health {
 #define BNXT_FW_IF_RETRY		10
 #define BNXT_FW_SLOT_RESET_RETRY	4
 
+struct bnxt_aux_dev {
+	struct auxiliary_device aux_dev;
+	struct bnxt_en_dev *edev;
+	int id;
+};
+
 enum board_idx {
 	BCM57301,
 	BCM57302,
@@ -1852,6 +1859,7 @@  struct bnxt {
 #define BNXT_CHIP_P4_PLUS(bp)			\
 	(BNXT_CHIP_P4(bp) || BNXT_CHIP_P5(bp))
 
+	struct bnxt_aux_dev	*aux_dev;
 	struct bnxt_en_dev	*edev;
 
 	struct bnxt_napi	**bnapi;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 2e54bf4fc7a7..6c697172f042 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -25,32 +25,37 @@ 
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
 
+static DEFINE_IDA(bnxt_aux_dev_ids);
+
 static int bnxt_register_dev(struct bnxt_en_dev *edev, unsigned 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;
+	int rc = 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 already registered\n", ulp_id);
-		return -EBUSY;
+		rc = -EBUSY;
+		goto exit;
 	}
 	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->cp_nr_rings == max_stat_ctxs)
-			return -ENOMEM;
+		    bp->cp_nr_rings == max_stat_ctxs) {
+			rc = -ENOMEM;
+			goto exit;
+		}
 	}
 
-	atomic_set(&ulp->ref_count, 0);
+	atomic_set(&ulp->ref_count, 1);
 	ulp->handle = handle;
 	rcu_assign_pointer(ulp->ulp_ops, ulp_ops);
 
@@ -59,7 +64,8 @@  static int bnxt_register_dev(struct bnxt_en_dev *edev, unsigned int ulp_id,
 			bnxt_hwrm_vnic_cfg(bp, 0);
 	}
 
-	return 0;
+exit:
+	return rc;
 }
 
 static int bnxt_unregister_dev(struct bnxt_en_dev *edev, unsigned int ulp_id)
@@ -69,10 +75,11 @@  static int bnxt_unregister_dev(struct bnxt_en_dev *edev, unsigned int ulp_id)
 	struct bnxt_ulp *ulp;
 	int i = 0;
 
-	ASSERT_RTNL();
 	if (ulp_id >= BNXT_MAX_ULP)
 		return -EINVAL;
 
+	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
+
 	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);
@@ -126,7 +133,6 @@  static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id,
 	int total_vecs;
 	int rc = 0;
 
-	ASSERT_RTNL();
 	if (ulp_id != BNXT_ROCE_ULP)
 		return -EINVAL;
 
@@ -149,6 +155,7 @@  static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id,
 		max_idx = min_t(int, bp->total_irqs, max_cp_rings);
 		idx = max_idx - avail_msix;
 	}
+
 	edev->ulp_tbl[ulp_id].msix_base = idx;
 	edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
 	hw_resc = &bp->hw_resc;
@@ -156,8 +163,10 @@  static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id,
 	if (bp->total_irqs < total_vecs ||
 	    (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) {
 		if (netif_running(dev)) {
+			rtnl_lock();
 			bnxt_close_nic(bp, true, false);
 			rc = bnxt_open_nic(bp, true, false);
+			rtnl_unlock();
 		} else {
 			rc = bnxt_reserve_rings(bp, true);
 		}
@@ -184,7 +193,6 @@  static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id)
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
 
-	ASSERT_RTNL();
 	if (ulp_id != BNXT_ROCE_ULP)
 		return -EINVAL;
 
@@ -194,9 +202,12 @@  static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id)
 	edev->ulp_tbl[ulp_id].msix_requested = 0;
 	edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
 	if (netif_running(dev) && !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED)) {
+		rtnl_lock();
 		bnxt_close_nic(bp, true, false);
 		bnxt_open_nic(bp, true, false);
+		rtnl_unlock();
 	}
+
 	return 0;
 }
 
@@ -347,25 +358,6 @@  void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs)
 	}
 }
 
-void bnxt_ulp_shutdown(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_shutdown)
-			continue;
-		ops->ulp_shutdown(ulp->handle);
-	}
-}
-
 void bnxt_ulp_irq_stop(struct bnxt *bp)
 {
 	struct bnxt_en_dev *edev = bp->edev;
@@ -475,6 +467,143 @@  static const struct bnxt_en_ops bnxt_en_ops_tbl = {
 	.bnxt_register_fw_async_events	= bnxt_register_async_events,
 };
 
+void bnxt_aux_dev_free(struct bnxt *bp)
+{
+	kfree(bp->aux_dev);
+	bp->aux_dev = NULL;
+}
+
+static struct bnxt_aux_dev *bnxt_aux_dev_alloc(struct bnxt *bp)
+{
+	struct bnxt_aux_dev *bnxt_adev;
+
+	bnxt_adev =  kzalloc(sizeof(*bnxt_adev), GFP_KERNEL);
+	if (!bnxt_adev)
+		return NULL;
+
+	return bnxt_adev;
+}
+
+void bnxt_rdma_aux_device_uninit(struct bnxt *bp)
+{
+	struct bnxt_aux_dev *bnxt_adev;
+	struct auxiliary_device *adev;
+
+	/* Skip if no auxiliary device init was done. */
+	if (!(bp->flags & BNXT_FLAG_ROCE_CAP))
+		return;
+
+	bnxt_adev = bp->aux_dev;
+	adev = &bnxt_adev->aux_dev;
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+	if (bnxt_adev->id >= 0)
+		ida_free(&bnxt_aux_dev_ids, bnxt_adev->id);
+}
+
+void bnxt_rdma_aux_device_init(struct bnxt *bp)
+{
+	int rc;
+
+	if (bp->flags & BNXT_FLAG_ROCE_CAP) {
+		bp->aux_dev = bnxt_aux_dev_alloc(bp);
+		if (!bp->aux_dev)
+			goto skip_ida_init;
+
+		bp->aux_dev->id = ida_alloc(&bnxt_aux_dev_ids, GFP_KERNEL);
+		if (bp->aux_dev->id < 0) {
+			netdev_warn(bp->dev,
+				    "ida alloc failed for ROCE auxiliary device\n");
+			goto skip_aux_init;
+		}
+
+		/* If aux bus init fails, continue with netdev init. */
+		rc = bnxt_rdma_aux_device_add(bp);
+		if (rc) {
+			netdev_warn(bp->dev,
+				    "Failed to add auxiliary device for ROCE\n");
+			goto aux_add_failed;
+		}
+	}
+	return;
+
+aux_add_failed:
+	ida_free(&bnxt_aux_dev_ids, bp->aux_dev->id);
+	bp->aux_dev->id = -1;
+skip_aux_init:
+	bnxt_aux_dev_free(bp);
+skip_ida_init:
+	bp->flags &= ~BNXT_FLAG_ROCE_CAP;
+}
+
+void bnxt_aux_dev_release(struct device *dev)
+{
+	struct bnxt_aux_dev *bnxt_adev =
+		container_of(dev, struct bnxt_aux_dev, aux_dev.dev);
+	struct bnxt *bp = netdev_priv(bnxt_adev->edev->net);
+
+	bnxt_adev->edev->en_ops = NULL;
+	kfree(bnxt_adev->edev);
+	bnxt_adev->edev = NULL;
+	bp->edev = NULL;
+}
+
+static inline void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp)
+{
+	edev->en_ops = &bnxt_en_ops_tbl;
+	edev->net = bp->dev;
+	edev->pdev = bp->pdev;
+	edev->l2_db_size = bp->db_size;
+	edev->l2_db_size_nc = bp->db_size;
+
+	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;
+}
+
+int bnxt_rdma_aux_device_add(struct bnxt *bp)
+{
+	struct bnxt_aux_dev *bnxt_adev = bp->aux_dev;
+	struct bnxt_en_dev *edev = bnxt_adev->edev;
+	struct auxiliary_device *aux_dev;
+	int ret;
+
+	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+	if (!edev) {
+		ret = -ENOMEM;
+		goto cleanup_edev_failure;
+	}
+
+	aux_dev = &bnxt_adev->aux_dev;
+	aux_dev->id = bnxt_adev->id;
+	aux_dev->name = "rdma";
+	aux_dev->dev.parent = &bp->pdev->dev;
+	aux_dev->dev.release = bnxt_aux_dev_release;
+
+	bnxt_adev->edev = edev;
+	bp->edev = edev;
+	bnxt_set_edev_info(edev, bp);
+
+	ret = auxiliary_device_init(aux_dev);
+	if (ret)
+		goto cleanup_init_failure;
+
+	ret = auxiliary_device_add(aux_dev);
+	if (ret)
+		goto cleanup_add_failure;
+
+	return 0;
+
+cleanup_add_failure:
+	auxiliary_device_uninit(aux_dev);
+cleanup_init_failure:
+	kfree(edev);
+	bp->edev = NULL;
+cleanup_edev_failure:
+	return ret;
+}
+
 struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 42b50abc3e91..647147a68554 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -17,6 +17,7 @@ 
 #define BNXT_MIN_ROCE_STAT_CTXS	1
 
 struct hwrm_async_event_cmpl;
+struct bnxt_aux_dev;
 struct bnxt;
 
 struct bnxt_msix_entry {
@@ -102,10 +103,14 @@  int bnxt_get_ulp_stat_ctxs(struct bnxt *bp);
 void bnxt_ulp_stop(struct bnxt *bp);
 void bnxt_ulp_start(struct bnxt *bp, int err);
 void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
-void bnxt_ulp_shutdown(struct bnxt *bp);
 void bnxt_ulp_irq_stop(struct bnxt *bp);
 void bnxt_ulp_irq_restart(struct bnxt *bp, int err);
 void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl);
+void bnxt_aux_dev_release(struct device *dev);
+int bnxt_rdma_aux_device_add(struct bnxt *bp);
+void bnxt_rdma_aux_device_uninit(struct bnxt *bp);
+void bnxt_rdma_aux_device_init(struct bnxt *bp);
+void bnxt_aux_dev_free(struct bnxt *bp);
 struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev);
 
 #endif