Commit 0cda6113 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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

Pull base rdma updates from Doug Ledford:
 "Round one of 4.8 code: while this is mostly normal, there is a new
  driver in here (the driver was hosted outside the kernel for several
  years and is actually a fairly mature and well coded driver).  It
  amounts to 13,000 of the 16,000 lines of added code in here.

  Summary:

   - Updates/fixes for iw_cxgb4 driver
   - Updates/fixes for mlx5 driver
   - Add flow steering and RSS API
   - Add hardware stats to mlx4 and mlx5 drivers
   - Add firmware version API for RDMA driver use
   - Add the rxe driver (this is a software RoCE driver that makes any
     Ethernet device a RoCE device)
   - Fixes for i40iw driver
   - Support for send only multicast joins in the cma layer
   - Other minor fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (72 commits)
  Soft RoCE driver
  IB/core: Support for CMA multicast join flags
  IB/sa: Add cached attribute containing SM information to SA port
  IB/uverbs: Fix race between uverbs_close and remove_one
  IB/mthca: Clean up error unwind flow in mthca_reset()
  IB/mthca: NULL arg to pci_dev_put is OK
  IB/hfi1: NULL arg to sc_return_credits is OK
  IB/mlx4: Add diagnostic hardware counters
  net/mlx4: Query performance and diagnostics counters
  net/mlx4: Add diagnostic counters capability bit
  Use smaller 512 byte messages for portmapper messages
  IB/ipoib: Report SG feature regardless of HW UD CSUM capability
  IB/mlx4: Don't use GFP_ATOMIC for CQ resize struct
  IB/hfi1: Disable by default
  IB/rdmavt: Disable by default
  IB/mlx5: Fix port counter ID association to QP offset
  IB/mlx5: Fix iteration overrun in GSI qps
  i40iw: Add NULL check for puda buffer
  i40iw: Change dup_ack_thresh to u8
  i40iw: Remove unnecessary check for moving CQ head
  ...
parents fdf1f7ff 7f1d25b4

MAINTAINERS

+9 −0
Original line number Diff line number Diff line
@@ -7647,6 +7647,15 @@ W: http://www.mellanox.com 
Q:	http://patchwork.ozlabs.org/project/netdev/list/

F:	drivers/net/ethernet/mellanox/mlxsw/



SOFT-ROCE DRIVER (rxe)

M:	Moni Shoua <monis@mellanox.com>

L:	linux-rdma@vger.kernel.org

S:	Supported

W:	https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home

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

F:	drivers/infiniband/hw/rxe/

F:	include/uapi/rdma/rdma_user_rxe.h



MEMBARRIER SUPPORT

M:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

drivers/infiniband/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -84,6 +84,7 @@ source "drivers/infiniband/ulp/iser/Kconfig" 
source "drivers/infiniband/ulp/isert/Kconfig"



source "drivers/infiniband/sw/rdmavt/Kconfig"

source "drivers/infiniband/sw/rxe/Kconfig"



source "drivers/infiniband/hw/hfi1/Kconfig"

drivers/infiniband/core/cma.c

+92 −6
Original line number Diff line number Diff line
@@ -68,6 +68,7 @@ MODULE_DESCRIPTION("Generic RDMA CM Agent"); 
MODULE_LICENSE("Dual BSD/GPL");



#define CMA_CM_RESPONSE_TIMEOUT 20

#define CMA_QUERY_CLASSPORT_INFO_TIMEOUT 3000

#define CMA_MAX_CM_RETRIES 15

#define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)

#define CMA_IBOE_PACKET_LIFETIME 18
@@ -162,6 +163,14 @@ struct rdma_bind_list { 
	unsigned short		port;

};



struct class_port_info_context {

	struct ib_class_port_info	*class_port_info;

	struct ib_device		*device;

	struct completion		done;

	struct ib_sa_query		*sa_query;

	u8				port_num;

};



static int cma_ps_alloc(struct net *net, enum rdma_port_space ps,

			struct rdma_bind_list *bind_list, int snum)

{
@@ -306,6 +315,7 @@ struct cma_multicast { 
	struct sockaddr_storage	addr;

	struct kref		mcref;

	bool			igmp_joined;

	u8			join_state;

};



struct cma_work {
@@ -3752,10 +3762,63 @@ static void cma_set_mgid(struct rdma_id_private *id_priv, 
	}

}



static void cma_query_sa_classport_info_cb(int status,

					   struct ib_class_port_info *rec,

					   void *context)

{

	struct class_port_info_context *cb_ctx = context;



	WARN_ON(!context);



	if (status || !rec) {

		pr_debug("RDMA CM: %s port %u failed query ClassPortInfo status: %d\n",

			 cb_ctx->device->name, cb_ctx->port_num, status);

		goto out;

	}



	memcpy(cb_ctx->class_port_info, rec, sizeof(struct ib_class_port_info));



out:

	complete(&cb_ctx->done);

}



static int cma_query_sa_classport_info(struct ib_device *device, u8 port_num,

				       struct ib_class_port_info *class_port_info)

{

	struct class_port_info_context *cb_ctx;

	int ret;



	cb_ctx = kmalloc(sizeof(*cb_ctx), GFP_KERNEL);

	if (!cb_ctx)

		return -ENOMEM;



	cb_ctx->device = device;

	cb_ctx->class_port_info = class_port_info;

	cb_ctx->port_num = port_num;

	init_completion(&cb_ctx->done);



	ret = ib_sa_classport_info_rec_query(&sa_client, device, port_num,

					     CMA_QUERY_CLASSPORT_INFO_TIMEOUT,

					     GFP_KERNEL, cma_query_sa_classport_info_cb,

					     cb_ctx, &cb_ctx->sa_query);

	if (ret < 0) {

		pr_err("RDMA CM: %s port %u failed to send ClassPortInfo query, ret: %d\n",

		       device->name, port_num, ret);

		goto out;

	}



	wait_for_completion(&cb_ctx->done);



out:

	kfree(cb_ctx);

	return ret;

}



static int cma_join_ib_multicast(struct rdma_id_private *id_priv,

				 struct cma_multicast *mc)

{

	struct ib_sa_mcmember_rec rec;

	struct ib_class_port_info class_port_info;

	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;

	ib_sa_comp_mask comp_mask;

	int ret;
@@ -3774,7 +3837,24 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, 
	rec.qkey = cpu_to_be32(id_priv->qkey);

	rdma_addr_get_sgid(dev_addr, &rec.port_gid);

	rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr));

	rec.join_state = 1;

	rec.join_state = mc->join_state;



	if (rec.join_state == BIT(SENDONLY_FULLMEMBER_JOIN)) {

		ret = cma_query_sa_classport_info(id_priv->id.device,

						  id_priv->id.port_num,

						  &class_port_info);



		if (ret)

			return ret;



		if (!(ib_get_cpi_capmask2(&class_port_info) &

		      IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT)) {

			pr_warn("RDMA CM: %s port %u Unable to multicast join\n"

				"RDMA CM: SM doesn't support Send Only Full Member option\n",

				id_priv->id.device->name, id_priv->id.port_num);

			return -EOPNOTSUPP;

		}

	}



	comp_mask = IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID |

		    IB_SA_MCMEMBER_REC_PKEY | IB_SA_MCMEMBER_REC_JOIN_STATE |
@@ -3843,6 +3923,9 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, 
	struct sockaddr *addr = (struct sockaddr *)&mc->addr;

	struct net_device *ndev = NULL;

	enum ib_gid_type gid_type;

	bool send_only;



	send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN);



	if (cma_zero_addr((struct sockaddr *)&mc->addr))

		return -EINVAL;
@@ -3878,11 +3961,13 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, 
	if (addr->sa_family == AF_INET) {

		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {

			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;

			if (!send_only) {

				err = cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid,

						    true);

				if (!err)

					mc->igmp_joined = true;

			}

		}

	} else {

		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)

			err = -ENOTSUPP;
@@ -3911,7 +3996,7 @@ out1: 
}



int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,

			void *context)

			u8 join_state, void *context)

{

	struct rdma_id_private *id_priv;

	struct cma_multicast *mc;
@@ -3930,6 +4015,7 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, 
	mc->context = context;

	mc->id_priv = id_priv;

	mc->igmp_joined = false;

	mc->join_state = join_state;

	spin_lock(&id_priv->lock);

	list_add(&mc->list, &id_priv->mc_list);

	spin_unlock(&id_priv->lock);

drivers/infiniband/core/device.c

+9 −0
Original line number Diff line number Diff line
@@ -311,6 +311,15 @@ static int read_port_immutable(struct ib_device *device) 
	return 0;

}



void ib_get_device_fw_str(struct ib_device *dev, char *str, size_t str_len)

{

	if (dev->get_dev_fw_str)

		dev->get_dev_fw_str(dev, str, str_len);

	else

		str[0] = '\0';

}

EXPORT_SYMBOL(ib_get_device_fw_str);



/**

 * ib_register_device - Register an IB device with IB core

 * @device:Device to register

drivers/infiniband/core/iwcm.c

+17 −37
Original line number Diff line number Diff line
@@ -183,15 +183,14 @@ static void free_cm_id(struct iwcm_id_private *cm_id_priv) 


/*

 * Release a reference on cm_id. If the last reference is being

 * released, enable the waiting thread (in iw_destroy_cm_id) to

 * get woken up, and return 1 if a thread is already waiting.

 * released, free the cm_id and return 1.

 */

static int iwcm_deref_id(struct iwcm_id_private *cm_id_priv)

{

	BUG_ON(atomic_read(&cm_id_priv->refcount)==0);

	if (atomic_dec_and_test(&cm_id_priv->refcount)) {

		BUG_ON(!list_empty(&cm_id_priv->work_list));

		complete(&cm_id_priv->destroy_comp);

		free_cm_id(cm_id_priv);

		return 1;

	}
@@ -208,19 +207,10 @@ static void add_ref(struct iw_cm_id *cm_id) 
static void rem_ref(struct iw_cm_id *cm_id)

{

	struct iwcm_id_private *cm_id_priv;

	int cb_destroy;



	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);



	/*

	 * Test bit before deref in case the cm_id gets freed on another

	 * thread.

	 */

	cb_destroy = test_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags);

	if (iwcm_deref_id(cm_id_priv) && cb_destroy) {

		BUG_ON(!list_empty(&cm_id_priv->work_list));

		free_cm_id(cm_id_priv);

	}

	(void)iwcm_deref_id(cm_id_priv);

}



static int cm_event_handler(struct iw_cm_id *cm_id, struct iw_cm_event *event);
@@ -370,6 +360,12 @@ static void destroy_cm_id(struct iw_cm_id *cm_id) 
	wait_event(cm_id_priv->connect_wait,

		   !test_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags));



	/*

	 * Since we're deleting the cm_id, drop any events that

	 * might arrive before the last dereference.

	 */

	set_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags);



	spin_lock_irqsave(&cm_id_priv->lock, flags);

	switch (cm_id_priv->state) {

	case IW_CM_STATE_LISTEN:
@@ -433,13 +429,7 @@ void iw_destroy_cm_id(struct iw_cm_id *cm_id) 
	struct iwcm_id_private *cm_id_priv;



	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);

	BUG_ON(test_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags));



	destroy_cm_id(cm_id);



	wait_for_completion(&cm_id_priv->destroy_comp);



	free_cm_id(cm_id_priv);

}

EXPORT_SYMBOL(iw_destroy_cm_id);
@@ -809,10 +799,7 @@ static void cm_conn_req_handler(struct iwcm_id_private *listen_id_priv, 
	ret = cm_id->cm_handler(cm_id, iw_event);

	if (ret) {

		iw_cm_reject(cm_id, NULL, 0);

		set_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags);

		destroy_cm_id(cm_id);

		if (atomic_read(&cm_id_priv->refcount)==0)

			free_cm_id(cm_id_priv);

		iw_destroy_cm_id(cm_id);

	}



out:
@@ -1000,7 +987,6 @@ static void cm_work_handler(struct work_struct *_work) 
	unsigned long flags;

	int empty;

	int ret = 0;

	int destroy_id;



	spin_lock_irqsave(&cm_id_priv->lock, flags);

	empty = list_empty(&cm_id_priv->work_list);
@@ -1013,20 +999,14 @@ static void cm_work_handler(struct work_struct *_work) 
		put_work(work);

		spin_unlock_irqrestore(&cm_id_priv->lock, flags);



		if (!test_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags)) {

			ret = process_event(cm_id_priv, &levent);

		if (ret) {

			set_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags);

			if (ret)

				destroy_cm_id(&cm_id_priv->id);

		}

		BUG_ON(atomic_read(&cm_id_priv->refcount)==0);

		destroy_id = test_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags);

		if (iwcm_deref_id(cm_id_priv)) {

			if (destroy_id) {

				BUG_ON(!list_empty(&cm_id_priv->work_list));

				free_cm_id(cm_id_priv);

			}

		} else

			pr_debug("dropping event %d\n", levent.event);

		if (iwcm_deref_id(cm_id_priv))

			return;

		}

		if (empty)

			return;

		spin_lock_irqsave(&cm_id_priv->lock, flags);

CRA Git | Maintained and supported by SUSTech CRA and CCSE