Commit dce45af5 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma 

Pull rdma updates from Jason Gunthorpe:
 "This has been a smaller cycle than normal. One new driver was
  accepted, which is unusual, and at least one more driver remains in
  review on the list.

  Summary:

   - Driver fixes for hns, hfi1, nes, rxe, i40iw, mlx5, cxgb4,
     vmw_pvrdma

   - Many patches from MatthewW converting radix tree and IDR users to
     use xarray

   - Introduction of tracepoints to the MAD layer

   - Build large SGLs at the start for DMA mapping and get the driver to
     split them

   - Generally clean SGL handling code throughout the subsystem

   - Support for restricting RDMA devices to net namespaces for
     containers

   - Progress to remove object allocation boilerplate code from drivers

   - Change in how the mlx5 driver shows representor ports linked to VFs

   - mlx5 uapi feature to access the on chip SW ICM memory

   - Add a new driver for 'EFA'. This is HW that supports user space
     packet processing through QPs in Amazon's cloud"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (186 commits)
  RDMA/ipoib: Allow user space differentiate between valid dev_port
  IB/core, ipoib: Do not overreact to SM LID change event
  RDMA/device: Don't fire uevent before device is fully initialized
  lib/scatterlist: Remove leftover from sg_page_iter comment
  RDMA/efa: Add driver to Kconfig/Makefile
  RDMA/efa: Add the efa module
  RDMA/efa: Add EFA verbs implementation
  RDMA/efa: Add common command handlers
  RDMA/efa: Implement functions that submit and complete admin commands
  RDMA/efa: Add the ABI definitions
  RDMA/efa: Add the com service API definitions
  RDMA/efa: Add the efa_com.h file
  RDMA/efa: Add the efa.h header file
  RDMA/efa: Add EFA device definitions
  RDMA: Add EFA related definitions
  RDMA/umem: Remove hugetlb flag
  RDMA/bnxt_re: Use core helpers to get aligned DMA address
  RDMA/i40iw: Use core helpers to get aligned DMA address within a supported page size
  RDMA/verbs: Add a DMA iterator to return aligned contiguous memory blocks
  RDMA/umem: Add API to find best driver supported page size in an MR
  ...
parents 055128ee b79656ed

MAINTAINERS

+15 −2
Original line number Diff line number Diff line
@@ -745,6 +745,15 @@ S: Supported 
F:	Documentation/networking/device_drivers/amazon/ena.txt

F:	drivers/net/ethernet/amazon/



AMAZON RDMA EFA DRIVER

M:	Gal Pressman <galpress@amazon.com>

R:	Yossi Leybovich <sleybo@amazon.com>

L:	linux-rdma@vger.kernel.org

Q:	https://patchwork.kernel.org/project/linux-rdma/list/

S:	Supported

F:	drivers/infiniband/hw/efa/

F:	include/uapi/rdma/efa-abi.h



AMD CRYPTOGRAPHIC COPROCESSOR (CCP) DRIVER

M:	Tom Lendacky <thomas.lendacky@amd.com>

M:	Gary Hook <gary.hook@amd.com>
@@ -4279,7 +4288,7 @@ S: Supported 
F:	drivers/scsi/cxgbi/cxgb3i



CXGB3 IWARP RNIC DRIVER (IW_CXGB3)

M:	Steve Wise <swise@chelsio.com>

M:	Potnuri Bharat Teja <bharat@chelsio.com>

L:	linux-rdma@vger.kernel.org

W:	http://www.openfabrics.org

S:	Supported
@@ -4308,7 +4317,7 @@ S: Supported 
F:	drivers/scsi/cxgbi/cxgb4i



CXGB4 IWARP RNIC DRIVER (IW_CXGB4)

M:	Steve Wise <swise@chelsio.com>

M:	Potnuri Bharat Teja <bharat@chelsio.com>

L:	linux-rdma@vger.kernel.org

W:	http://www.openfabrics.org

S:	Supported
@@ -7727,6 +7736,10 @@ F: drivers/infiniband/ 
F:	include/uapi/linux/if_infiniband.h

F:	include/uapi/rdma/

F:	include/rdma/

F:	include/trace/events/ib_mad.h

F:	include/trace/events/ib_umad.h

F:	samples/bpf/ibumad_kern.c

F:	samples/bpf/ibumad_user.c



INGENIC JZ4780 DMA Driver

M:	Zubair Lutfullah Kakakhel <Zubair.Kakakhel@imgtec.com>

drivers/infiniband/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -93,6 +93,7 @@ source "drivers/infiniband/hw/mthca/Kconfig" 
source "drivers/infiniband/hw/qib/Kconfig"

source "drivers/infiniband/hw/cxgb3/Kconfig"

source "drivers/infiniband/hw/cxgb4/Kconfig"

source "drivers/infiniband/hw/efa/Kconfig"

source "drivers/infiniband/hw/i40iw/Kconfig"

source "drivers/infiniband/hw/mlx4/Kconfig"

source "drivers/infiniband/hw/mlx5/Kconfig"

drivers/infiniband/core/addr.c

+1 −0
Original line number Diff line number Diff line
@@ -45,6 +45,7 @@ 
#include <net/ipv6_stubs.h>

#include <net/ip6_route.h>

#include <rdma/ib_addr.h>

#include <rdma/ib_cache.h>

#include <rdma/ib_sa.h>

#include <rdma/ib.h>

#include <rdma/rdma_netlink.h>

drivers/infiniband/core/cache.c

+115 −30
Original line number Diff line number Diff line
@@ -78,11 +78,22 @@ enum gid_table_entry_state { 
	GID_TABLE_ENTRY_PENDING_DEL	= 3,

};



struct roce_gid_ndev_storage {

	struct rcu_head rcu_head;

	struct net_device *ndev;

};



struct ib_gid_table_entry {

	struct kref			kref;

	struct work_struct		del_work;

	struct ib_gid_attr		attr;

	void				*context;

	/* Store the ndev pointer to release reference later on in

	 * call_rcu context because by that time gid_table_entry

	 * and attr might be already freed. So keep a copy of it.

	 * ndev_storage is freed by rcu callback.

	 */

	struct roce_gid_ndev_storage	*ndev_storage;

	enum gid_table_entry_state	state;

};
@@ -206,6 +217,20 @@ static void schedule_free_gid(struct kref *kref) 
	queue_work(ib_wq, &entry->del_work);

}



static void put_gid_ndev(struct rcu_head *head)

{

	struct roce_gid_ndev_storage *storage =

		container_of(head, struct roce_gid_ndev_storage, rcu_head);



	WARN_ON(!storage->ndev);

	/* At this point its safe to release netdev reference,

	 * as all callers working on gid_attr->ndev are done

	 * using this netdev.

	 */

	dev_put(storage->ndev);

	kfree(storage);

}



static void free_gid_entry_locked(struct ib_gid_table_entry *entry)

{

	struct ib_device *device = entry->attr.device;
@@ -228,8 +253,8 @@ static void free_gid_entry_locked(struct ib_gid_table_entry *entry) 
	/* Now this index is ready to be allocated */

	write_unlock_irq(&table->rwlock);



	if (entry->attr.ndev)

		dev_put(entry->attr.ndev);

	if (entry->ndev_storage)

		call_rcu(&entry->ndev_storage->rcu_head, put_gid_ndev);

	kfree(entry);

}
@@ -266,14 +291,25 @@ static struct ib_gid_table_entry * 
alloc_gid_entry(const struct ib_gid_attr *attr)

{

	struct ib_gid_table_entry *entry;

	struct net_device *ndev;



	entry = kzalloc(sizeof(*entry), GFP_KERNEL);

	if (!entry)

		return NULL;



	ndev = rcu_dereference_protected(attr->ndev, 1);

	if (ndev) {

		entry->ndev_storage = kzalloc(sizeof(*entry->ndev_storage),

					      GFP_KERNEL);

		if (!entry->ndev_storage) {

			kfree(entry);

			return NULL;

		}

		dev_hold(ndev);

		entry->ndev_storage->ndev = ndev;

	}

	kref_init(&entry->kref);

	memcpy(&entry->attr, attr, sizeof(*attr));

	if (entry->attr.ndev)

		dev_hold(entry->attr.ndev);

	INIT_WORK(&entry->del_work, free_gid_work);

	entry->state = GID_TABLE_ENTRY_INVALID;

	return entry;
@@ -343,6 +379,7 @@ static int add_roce_gid(struct ib_gid_table_entry *entry) 
static void del_gid(struct ib_device *ib_dev, u8 port,

		    struct ib_gid_table *table, int ix)

{

	struct roce_gid_ndev_storage *ndev_storage;

	struct ib_gid_table_entry *entry;



	lockdep_assert_held(&table->lock);
@@ -360,6 +397,13 @@ static void del_gid(struct ib_device *ib_dev, u8 port, 
		table->data_vec[ix] = NULL;

	write_unlock_irq(&table->rwlock);



	ndev_storage = entry->ndev_storage;

	if (ndev_storage) {

		entry->ndev_storage = NULL;

		rcu_assign_pointer(entry->attr.ndev, NULL);

		call_rcu(&ndev_storage->rcu_head, put_gid_ndev);

	}



	if (rdma_cap_roce_gid_table(ib_dev, port))

		ib_dev->ops.del_gid(&entry->attr, &entry->context);
@@ -543,30 +587,11 @@ out_unlock: 
int ib_cache_gid_add(struct ib_device *ib_dev, u8 port,

		     union ib_gid *gid, struct ib_gid_attr *attr)

{

	struct net_device *idev;

	unsigned long mask;

	int ret;



	idev = ib_device_get_netdev(ib_dev, port);

	if (idev && attr->ndev != idev) {

		union ib_gid default_gid;



		/* Adding default GIDs is not permitted */

		make_default_gid(idev, &default_gid);

		if (!memcmp(gid, &default_gid, sizeof(*gid))) {

			dev_put(idev);

			return -EPERM;

		}

	}

	if (idev)

		dev_put(idev);



	mask = GID_ATTR_FIND_MASK_GID |

	unsigned long mask = GID_ATTR_FIND_MASK_GID |

			     GID_ATTR_FIND_MASK_GID_TYPE |

			     GID_ATTR_FIND_MASK_NETDEV;



	ret = __ib_cache_gid_add(ib_dev, port, gid, attr, mask, false);

	return ret;

	return __ib_cache_gid_add(ib_dev, port, gid, attr, mask, false);

}



static int
@@ -1263,11 +1288,72 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr) 


	read_lock_irqsave(&table->rwlock, flags);

	valid = is_gid_entry_valid(table->data_vec[attr->index]);

	if (valid && attr->ndev && (READ_ONCE(attr->ndev->flags) & IFF_UP))

		ndev = attr->ndev;

	if (valid) {

		ndev = rcu_dereference(attr->ndev);

		if (!ndev ||

		    (ndev && ((READ_ONCE(ndev->flags) & IFF_UP) == 0)))

			ndev = ERR_PTR(-ENODEV);

	}

	read_unlock_irqrestore(&table->rwlock, flags);

	return ndev;

}

EXPORT_SYMBOL(rdma_read_gid_attr_ndev_rcu);



static int get_lower_dev_vlan(struct net_device *lower_dev, void *data)

{

	u16 *vlan_id = data;



	if (is_vlan_dev(lower_dev))

		*vlan_id = vlan_dev_vlan_id(lower_dev);



	/* We are interested only in first level vlan device, so

	 * always return 1 to stop iterating over next level devices.

	 */

	return 1;

}



/**

 * rdma_read_gid_l2_fields - Read the vlan ID and source MAC address

 *			     of a GID entry.

 *

 * @attr:	GID attribute pointer whose L2 fields to be read

 * @vlan_id:	Pointer to vlan id to fill up if the GID entry has

 *		vlan id. It is optional.

 * @smac:	Pointer to smac to fill up for a GID entry. It is optional.

 *

 * rdma_read_gid_l2_fields() returns 0 on success and returns vlan id

 * (if gid entry has vlan) and source MAC, or returns error.

 */

int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr,

			    u16 *vlan_id, u8 *smac)

{

	struct net_device *ndev;



	rcu_read_lock();

	ndev = rcu_dereference(attr->ndev);

	if (!ndev) {

		rcu_read_unlock();

		return -ENODEV;

	}

	if (smac)

		ether_addr_copy(smac, ndev->dev_addr);

	if (vlan_id) {

		*vlan_id = 0xffff;

		if (is_vlan_dev(ndev)) {

			*vlan_id = vlan_dev_vlan_id(ndev);

		} else {

			/* If the netdev is upper device and if it's lower

			 * device is vlan device, consider vlan id of the

			 * the lower vlan device for this gid entry.

			 */

			netdev_walk_all_lower_dev_rcu(attr->ndev,

					get_lower_dev_vlan, vlan_id);

		}

	}

	rcu_read_unlock();

	return 0;

}

EXPORT_SYMBOL(rdma_read_gid_l2_fields);



static int config_non_roce_gid_cache(struct ib_device *device,

				     u8 port, int gid_tbl_len)
@@ -1392,7 +1478,6 @@ static void ib_cache_event(struct ib_event_handler *handler, 
	    event->event == IB_EVENT_PORT_ACTIVE ||

	    event->event == IB_EVENT_LID_CHANGE  ||

	    event->event == IB_EVENT_PKEY_CHANGE ||

	    event->event == IB_EVENT_SM_CHANGE   ||

	    event->event == IB_EVENT_CLIENT_REREGISTER ||

	    event->event == IB_EVENT_GID_CHANGE) {

		work = kmalloc(sizeof *work, GFP_ATOMIC);

drivers/infiniband/core/cm.c

+29 −65
Original line number Diff line number Diff line
@@ -52,6 +52,7 @@ 
#include <rdma/ib_cache.h>

#include <rdma/ib_cm.h>

#include "cm_msgs.h"

#include "core_priv.h"



MODULE_AUTHOR("Sean Hefty");

MODULE_DESCRIPTION("InfiniBand CM");
@@ -124,7 +125,8 @@ static struct ib_cm { 
	struct rb_root remote_qp_table;

	struct rb_root remote_id_table;

	struct rb_root remote_sidr_table;

	struct idr local_id_table;

	struct xarray local_id_table;

	u32 local_id_next;

	__be32 random_id_operand;

	struct list_head timewait_list;

	struct workqueue_struct *wq;
@@ -219,7 +221,6 @@ struct cm_port { 
struct cm_device {

	struct list_head list;

	struct ib_device *ib_device;

	struct device *device;

	u8 ack_delay;

	int going_down;

	struct cm_port *port[0];
@@ -598,35 +599,31 @@ static int cm_init_av_by_path(struct sa_path_rec *path, 


static int cm_alloc_id(struct cm_id_private *cm_id_priv)

{

	unsigned long flags;

	int id;



	idr_preload(GFP_KERNEL);

	spin_lock_irqsave(&cm.lock, flags);



	id = idr_alloc_cyclic(&cm.local_id_table, cm_id_priv, 0, 0, GFP_NOWAIT);

	int err;

	u32 id;



	spin_unlock_irqrestore(&cm.lock, flags);

	idr_preload_end();

	err = xa_alloc_cyclic_irq(&cm.local_id_table, &id, cm_id_priv,

			xa_limit_32b, &cm.local_id_next, GFP_KERNEL);



	cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand;

	return id < 0 ? id : 0;

	return err;

}



static u32 cm_local_id(__be32 local_id)

{

	return (__force u32) (local_id ^ cm.random_id_operand);

}



static void cm_free_id(__be32 local_id)

{

	spin_lock_irq(&cm.lock);

	idr_remove(&cm.local_id_table,

		   (__force int) (local_id ^ cm.random_id_operand));

	spin_unlock_irq(&cm.lock);

	xa_erase_irq(&cm.local_id_table, cm_local_id(local_id));

}



static struct cm_id_private * cm_get_id(__be32 local_id, __be32 remote_id)

{

	struct cm_id_private *cm_id_priv;



	cm_id_priv = idr_find(&cm.local_id_table,

			      (__force int) (local_id ^ cm.random_id_operand));

	cm_id_priv = xa_load(&cm.local_id_table, cm_local_id(local_id));

	if (cm_id_priv) {

		if (cm_id_priv->id.remote_id == remote_id)

			atomic_inc(&cm_id_priv->refcount);
@@ -1988,11 +1985,12 @@ static int cm_req_handler(struct cm_work *work) 
	grh = rdma_ah_read_grh(&cm_id_priv->av.ah_attr);

	gid_attr = grh->sgid_attr;



	if (gid_attr && gid_attr->ndev) {

	if (gid_attr &&

	    rdma_protocol_roce(work->port->cm_dev->ib_device,

			       work->port->port_num)) {

		work->path[0].rec_type =

			sa_conv_gid_to_pathrec_type(gid_attr->gid_type);

	} else {

		/* If no GID attribute or ndev is null, it is not RoCE. */

		cm_path_set_rec_type(work->port->cm_dev->ib_device,

				     work->port->port_num,

				     &work->path[0],
@@ -2824,9 +2822,8 @@ static struct cm_id_private * cm_acquire_rejected_id(struct cm_rej_msg *rej_msg) 
			spin_unlock_irq(&cm.lock);

			return NULL;

		}

		cm_id_priv = idr_find(&cm.local_id_table, (__force int)

				      (timewait_info->work.local_id ^

				       cm.random_id_operand));

		cm_id_priv = xa_load(&cm.local_id_table,

				cm_local_id(timewait_info->work.local_id));

		if (cm_id_priv) {

			if (cm_id_priv->id.remote_id == remote_id)

				atomic_inc(&cm_id_priv->refcount);
@@ -4276,18 +4273,6 @@ static struct kobj_type cm_counter_obj_type = { 
	.default_attrs = cm_counter_default_attrs

};



static void cm_release_port_obj(struct kobject *obj)

{

	struct cm_port *cm_port;



	cm_port = container_of(obj, struct cm_port, port_obj);

	kfree(cm_port);

}



static struct kobj_type cm_port_obj_type = {

	.release = cm_release_port_obj

};



static char *cm_devnode(struct device *dev, umode_t *mode)

{

	if (mode)
@@ -4306,19 +4291,12 @@ static int cm_create_port_fs(struct cm_port *port) 
{

	int i, ret;



	ret = kobject_init_and_add(&port->port_obj, &cm_port_obj_type,

				   &port->cm_dev->device->kobj,

				   "%d", port->port_num);

	if (ret) {

		kfree(port);

		return ret;

	}



	for (i = 0; i < CM_COUNTER_GROUPS; i++) {

		ret = kobject_init_and_add(&port->counter_group[i].obj,

		ret = ib_port_register_module_stat(port->cm_dev->ib_device,

						   port->port_num,

						   &port->counter_group[i].obj,

						   &cm_counter_obj_type,

					   &port->port_obj,

					   "%s", counter_group_names[i]);

						   counter_group_names[i]);

		if (ret)

			goto error;

	}
@@ -4327,8 +4305,7 @@ static int cm_create_port_fs(struct cm_port *port) 


error:

	while (i--)

		kobject_put(&port->counter_group[i].obj);

	kobject_put(&port->port_obj);

		ib_port_unregister_module_stat(&port->counter_group[i].obj);

	return ret;



}
@@ -4338,9 +4315,8 @@ static void cm_remove_port_fs(struct cm_port *port) 
	int i;



	for (i = 0; i < CM_COUNTER_GROUPS; i++)

		kobject_put(&port->counter_group[i].obj);

		ib_port_unregister_module_stat(&port->counter_group[i].obj);



	kobject_put(&port->port_obj);

}



static void cm_add_one(struct ib_device *ib_device)
@@ -4367,13 +4343,6 @@ static void cm_add_one(struct ib_device *ib_device) 
	cm_dev->ib_device = ib_device;

	cm_dev->ack_delay = ib_device->attrs.local_ca_ack_delay;

	cm_dev->going_down = 0;

	cm_dev->device = device_create(&cm_class, &ib_device->dev,

				       MKDEV(0, 0), NULL,

				       "%s", dev_name(&ib_device->dev));

	if (IS_ERR(cm_dev->device)) {

		kfree(cm_dev);

		return;

	}



	set_bit(IB_MGMT_METHOD_SEND, reg_req.method_mask);

	for (i = 1; i <= ib_device->phys_port_cnt; i++) {
@@ -4440,7 +4409,6 @@ error1: 
		cm_remove_port_fs(port);

	}

free:

	device_unregister(cm_dev->device);

	kfree(cm_dev);

}
@@ -4494,7 +4462,6 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data) 
		cm_remove_port_fs(port);

	}



	device_unregister(cm_dev->device);

	kfree(cm_dev);

}
@@ -4502,7 +4469,6 @@ static int __init ib_cm_init(void) 
{

	int ret;



	memset(&cm, 0, sizeof cm);

	INIT_LIST_HEAD(&cm.device_list);

	rwlock_init(&cm.device_lock);

	spin_lock_init(&cm.lock);
@@ -4512,7 +4478,7 @@ static int __init ib_cm_init(void) 
	cm.remote_id_table = RB_ROOT;

	cm.remote_qp_table = RB_ROOT;

	cm.remote_sidr_table = RB_ROOT;

	idr_init(&cm.local_id_table);

	xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);

	get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand);

	INIT_LIST_HEAD(&cm.timewait_list);
@@ -4538,7 +4504,6 @@ error3: 
error2:

	class_unregister(&cm_class);

error1:

	idr_destroy(&cm.local_id_table);

	return ret;

}
@@ -4560,9 +4525,8 @@ static void __exit ib_cm_cleanup(void) 
	}



	class_unregister(&cm_class);

	idr_destroy(&cm.local_id_table);

	WARN_ON(!xa_empty(&cm.local_id_table));

}



module_init(ib_cm_init);

module_exit(ib_cm_cleanup);

CRA Git | Maintained and supported by SUSTech CRA and CCSE