Commit 877f075a authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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

Pull infiniband updates from Roland Dreier:
 "Main batch of InfiniBand/RDMA changes for 3.15:

   - The biggest change is core API extensions and mlx5 low-level driver
     support for handling DIF/DIX-style protection information, and the
     addition of PI support to the iSER initiator.  Target support will
     be arriving shortly through the SCSI target tree.

   - A nice simplification to the "umem" memory pinning library now that
     we have chained sg lists.  Kudos to Yishai Hadas for realizing our
     code didn't have to be so crazy.

   - Another nice simplification to the sg wrappers used by qib, ipath
     and ehca to handle their mapping of memory to adapter.

   - The usual batch of fixes to bugs found by static checkers etc.
     from intrepid people like Dan Carpenter and Yann Droneaud.

   - A large batch of cxgb4, ocrdma, qib driver updates"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (102 commits)
  RDMA/ocrdma: Unregister inet notifier when unloading ocrdma
  RDMA/ocrdma: Fix warnings about pointer <-> integer casts
  RDMA/ocrdma: Code clean-up
  RDMA/ocrdma: Display FW version
  RDMA/ocrdma: Query controller information
  RDMA/ocrdma: Support non-embedded mailbox commands
  RDMA/ocrdma: Handle CQ overrun error
  RDMA/ocrdma: Display proper value for max_mw
  RDMA/ocrdma: Use non-zero tag in SRQ posting
  RDMA/ocrdma: Memory leak fix in ocrdma_dereg_mr()
  RDMA/ocrdma: Increment abi version count
  RDMA/ocrdma: Update version string
  be2net: Add abi version between be2net and ocrdma
  RDMA/ocrdma: ABI versioning between ocrdma and be2net
  RDMA/ocrdma: Allow DPP QP creation
  RDMA/ocrdma: Read ASIC_ID register to select asic_gen
  RDMA/ocrdma: SQ and RQ doorbell offset clean up
  RDMA/ocrdma: EQ full catastrophe avoidance
  RDMA/cxgb4: Disable DSGL use by default
  RDMA/cxgb4: rx_data() needs to hold the ep mutex
  ...
parents 3cf59142 f7eaa7ed

drivers/infiniband/core/cm.c

+0 −17
Original line number Diff line number Diff line
@@ -349,23 +349,6 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc, 
			   grh, &av->ah_attr);

}



int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac)

{

	struct cm_id_private *cm_id_priv;



	cm_id_priv = container_of(id, struct cm_id_private, id);



	if (smac != NULL)

		memcpy(cm_id_priv->av.smac, smac, sizeof(cm_id_priv->av.smac));



	if (alt_smac != NULL)

		memcpy(cm_id_priv->alt_av.smac, alt_smac,

		       sizeof(cm_id_priv->alt_av.smac));



	return 0;

}

EXPORT_SYMBOL(ib_update_cm_av);



static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)

{

	struct cm_device *cm_dev;

drivers/infiniband/core/cma.c

+0 −26
Original line number Diff line number Diff line
@@ -1284,15 +1284,6 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) 
	struct rdma_id_private *listen_id, *conn_id;

	struct rdma_cm_event event;

	int offset, ret;

	u8 smac[ETH_ALEN];

	u8 alt_smac[ETH_ALEN];

	u8 *psmac = smac;

	u8 *palt_smac = alt_smac;

	int is_iboe = ((rdma_node_get_transport(cm_id->device->node_type) ==

			RDMA_TRANSPORT_IB) &&

		       (rdma_port_get_link_layer(cm_id->device,

			ib_event->param.req_rcvd.port) ==

			IB_LINK_LAYER_ETHERNET));



	listen_id = cm_id->context;

	if (!cma_check_req_qp_type(&listen_id->id, ib_event))
@@ -1336,28 +1327,11 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) 
	ret = conn_id->id.event_handler(&conn_id->id, &event);

	if (ret)

		goto err3;



	if (is_iboe) {

		if (ib_event->param.req_rcvd.primary_path != NULL)

			rdma_addr_find_smac_by_sgid(

				&ib_event->param.req_rcvd.primary_path->sgid,

				psmac, NULL);

		else

			psmac = NULL;

		if (ib_event->param.req_rcvd.alternate_path != NULL)

			rdma_addr_find_smac_by_sgid(

				&ib_event->param.req_rcvd.alternate_path->sgid,

				palt_smac, NULL);

		else

			palt_smac = NULL;

	}

	/*

	 * Acquire mutex to prevent user executing rdma_destroy_id()

	 * while we're accessing the cm_id.

	 */

	mutex_lock(&lock);

	if (is_iboe)

		ib_update_cm_av(cm_id, psmac, palt_smac);

	if (cma_comp(conn_id, RDMA_CM_CONNECT) &&

	    (conn_id->id.qp_type != IB_QPT_UD))

		ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);

drivers/infiniband/core/mad.c

+14 −0
Original line number Diff line number Diff line
@@ -1022,12 +1022,21 @@ int ib_send_mad(struct ib_mad_send_wr_private *mad_send_wr) 
					mad_send_wr->send_buf.mad,

					sge[0].length,

					DMA_TO_DEVICE);

	if (unlikely(ib_dma_mapping_error(mad_agent->device, sge[0].addr)))

		return -ENOMEM;



	mad_send_wr->header_mapping = sge[0].addr;



	sge[1].addr = ib_dma_map_single(mad_agent->device,

					ib_get_payload(mad_send_wr),

					sge[1].length,

					DMA_TO_DEVICE);

	if (unlikely(ib_dma_mapping_error(mad_agent->device, sge[1].addr))) {

		ib_dma_unmap_single(mad_agent->device,

				    mad_send_wr->header_mapping,

				    sge[0].length, DMA_TO_DEVICE);

		return -ENOMEM;

	}

	mad_send_wr->payload_mapping = sge[1].addr;



	spin_lock_irqsave(&qp_info->send_queue.lock, flags);
@@ -2590,6 +2599,11 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info, 
						 sizeof *mad_priv -

						   sizeof mad_priv->header,

						 DMA_FROM_DEVICE);

		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,

						  sg_list.addr))) {

			ret = -ENOMEM;

			break;

		}

		mad_priv->header.mapping = sg_list.addr;

		recv_wr.wr_id = (unsigned long)&mad_priv->header.mad_list;

		mad_priv->header.mad_list.mad_queue = recv_queue;

drivers/infiniband/core/umem.c

+56 −64
Original line number Diff line number Diff line
@@ -42,29 +42,29 @@ 


#include "uverbs.h"



#define IB_UMEM_MAX_PAGE_CHUNK						\

	((PAGE_SIZE - offsetof(struct ib_umem_chunk, page_list)) /	\

	 ((void *) &((struct ib_umem_chunk *) 0)->page_list[1] -	\

	  (void *) &((struct ib_umem_chunk *) 0)->page_list[0]))



static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty)

{

	struct ib_umem_chunk *chunk, *tmp;

	struct scatterlist *sg;

	struct page *page;

	int i;



	list_for_each_entry_safe(chunk, tmp, &umem->chunk_list, list) {

		ib_dma_unmap_sg(dev, chunk->page_list,

				chunk->nents, DMA_BIDIRECTIONAL);

		for (i = 0; i < chunk->nents; ++i) {

			struct page *page = sg_page(&chunk->page_list[i]);

	if (umem->nmap > 0)

		ib_dma_unmap_sg(dev, umem->sg_head.sgl,

				umem->nmap,

				DMA_BIDIRECTIONAL);



	for_each_sg(umem->sg_head.sgl, sg, umem->npages, i) {



		page = sg_page(sg);

		if (umem->writable && dirty)

			set_page_dirty_lock(page);

		put_page(page);

	}



		kfree(chunk);

	}

	sg_free_table(&umem->sg_head);

	return;



}



/**
@@ -81,15 +81,15 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, 
	struct ib_umem *umem;

	struct page **page_list;

	struct vm_area_struct **vma_list;

	struct ib_umem_chunk *chunk;

	unsigned long locked;

	unsigned long lock_limit;

	unsigned long cur_base;

	unsigned long npages;

	int ret;

	int off;

	int i;

	DEFINE_DMA_ATTRS(attrs);

	struct scatterlist *sg, *sg_list_start;

	int need_release = 0;



	if (dmasync)

		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
@@ -97,7 +97,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, 
	if (!can_do_mlock())

		return ERR_PTR(-EPERM);



	umem = kmalloc(sizeof *umem, GFP_KERNEL);

	umem = kzalloc(sizeof *umem, GFP_KERNEL);

	if (!umem)

		return ERR_PTR(-ENOMEM);
@@ -117,8 +117,6 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, 
	/* We assume the memory is from hugetlb until proved otherwise */

	umem->hugetlb   = 1;



	INIT_LIST_HEAD(&umem->chunk_list);



	page_list = (struct page **) __get_free_page(GFP_KERNEL);

	if (!page_list) {

		kfree(umem);
@@ -147,7 +145,18 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, 


	cur_base = addr & PAGE_MASK;



	ret = 0;

	if (npages == 0) {

		ret = -EINVAL;

		goto out;

	}



	ret = sg_alloc_table(&umem->sg_head, npages, GFP_KERNEL);

	if (ret)

		goto out;



	need_release = 1;

	sg_list_start = umem->sg_head.sgl;



	while (npages) {

		ret = get_user_pages(current, current->mm, cur_base,

				     min_t(unsigned long, npages,
@@ -157,53 +166,37 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, 
		if (ret < 0)

			goto out;



		umem->npages += ret;

		cur_base += ret * PAGE_SIZE;

		npages   -= ret;



		off = 0;

		for_each_sg(sg_list_start, sg, ret, i) {

			if (vma_list && !is_vm_hugetlb_page(vma_list[i]))

				umem->hugetlb = 0;



		while (ret) {

			chunk = kmalloc(sizeof *chunk + sizeof (struct scatterlist) *

					min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK),

					GFP_KERNEL);

			if (!chunk) {

				ret = -ENOMEM;

				goto out;

			sg_set_page(sg, page_list[i], PAGE_SIZE, 0);

		}



			chunk->nents = min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK);

			sg_init_table(chunk->page_list, chunk->nents);

			for (i = 0; i < chunk->nents; ++i) {

				if (vma_list &&

				    !is_vm_hugetlb_page(vma_list[i + off]))

					umem->hugetlb = 0;

				sg_set_page(&chunk->page_list[i], page_list[i + off], PAGE_SIZE, 0);

		/* preparing for next loop */

		sg_list_start = sg;

	}



			chunk->nmap = ib_dma_map_sg_attrs(context->device,

							  &chunk->page_list[0],

							  chunk->nents,

	umem->nmap = ib_dma_map_sg_attrs(context->device,

				  umem->sg_head.sgl,

				  umem->npages,

				  DMA_BIDIRECTIONAL,

				  &attrs);

			if (chunk->nmap <= 0) {

				for (i = 0; i < chunk->nents; ++i)

					put_page(sg_page(&chunk->page_list[i]));

				kfree(chunk);



	if (umem->nmap <= 0) {

		ret = -ENOMEM;

		goto out;

	}



			ret -= chunk->nents;

			off += chunk->nents;

			list_add_tail(&chunk->list, &umem->chunk_list);

		}



	ret = 0;

	}



out:

	if (ret < 0) {

		if (need_release)

			__ib_umem_release(context->device, umem, 0);

		kfree(umem);

	} else
@@ -278,17 +271,16 @@ EXPORT_SYMBOL(ib_umem_release); 


int ib_umem_page_count(struct ib_umem *umem)

{

	struct ib_umem_chunk *chunk;

	int shift;

	int i;

	int n;

	struct scatterlist *sg;



	shift = ilog2(umem->page_size);



	n = 0;

	list_for_each_entry(chunk, &umem->chunk_list, list)

		for (i = 0; i < chunk->nmap; ++i)

			n += sg_dma_len(&chunk->page_list[i]) >> shift;

	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i)

		n += sg_dma_len(sg) >> shift;



	return n;

}

drivers/infiniband/core/verbs.c

+47 −0
Original line number Diff line number Diff line
@@ -1169,6 +1169,45 @@ int ib_dereg_mr(struct ib_mr *mr) 
}

EXPORT_SYMBOL(ib_dereg_mr);



struct ib_mr *ib_create_mr(struct ib_pd *pd,

			   struct ib_mr_init_attr *mr_init_attr)

{

	struct ib_mr *mr;



	if (!pd->device->create_mr)

		return ERR_PTR(-ENOSYS);



	mr = pd->device->create_mr(pd, mr_init_attr);



	if (!IS_ERR(mr)) {

		mr->device  = pd->device;

		mr->pd      = pd;

		mr->uobject = NULL;

		atomic_inc(&pd->usecnt);

		atomic_set(&mr->usecnt, 0);

	}



	return mr;

}

EXPORT_SYMBOL(ib_create_mr);



int ib_destroy_mr(struct ib_mr *mr)

{

	struct ib_pd *pd;

	int ret;



	if (atomic_read(&mr->usecnt))

		return -EBUSY;



	pd = mr->pd;

	ret = mr->device->destroy_mr(mr);

	if (!ret)

		atomic_dec(&pd->usecnt);



	return ret;

}

EXPORT_SYMBOL(ib_destroy_mr);



struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len)

{

	struct ib_mr *mr;
@@ -1398,3 +1437,11 @@ int ib_destroy_flow(struct ib_flow *flow_id) 
	return err;

}

EXPORT_SYMBOL(ib_destroy_flow);



int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,

		       struct ib_mr_status *mr_status)

{

	return mr->device->check_mr_status ?

		mr->device->check_mr_status(mr, check_mask, mr_status) : -ENOSYS;

}

EXPORT_SYMBOL(ib_check_mr_status);

CRA Git | Maintained and supported by SUSTech CRA and CCSE