Commit 13859d5d authored by Leon Romanovsky's avatar Leon Romanovsky Committed by Jason Gunthorpe
Browse files

RDMA/mlx5: Embed into the code flow the ODP config option 



Convert various places to more readable code, which embeds
CONFIG_INFINIBAND_ON_DEMAND_PAGING into the code flow.

Signed-off-by: default avatarLeon Romanovsky <leonro@mellanox.com>
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
parent 8b4d5bc5

drivers/infiniband/core/uverbs_cmd.c

+0 −3
Original line number Diff line number Diff line
@@ -234,14 +234,11 @@ static int ib_uverbs_get_context(struct uverbs_attr_bundle *attrs) 
	ucontext->closing = false;

	ucontext->cleanup_retryable = false;



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	mutex_init(&ucontext->per_mm_list_lock);

	INIT_LIST_HEAD(&ucontext->per_mm_list);

	if (!(ib_dev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING))

		ucontext->invalidate_range = NULL;



#endif



	resp.num_comp_vectors = file->device->num_comp_vectors;



	ret = get_unused_fd_flags(O_CLOEXEC);

drivers/infiniband/hw/mlx5/main.c

+20 −21
Original line number Diff line number Diff line
@@ -1763,9 +1763,9 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, 
	if (err)

		goto out_sys_pages;



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range;

#endif

	if (ibdev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING)

		context->ibucontext.invalidate_range =

			&mlx5_ib_invalidate_range;



	if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) {

		err = mlx5_ib_devx_create(dev, true);
@@ -1897,12 +1897,10 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext) 
	struct mlx5_ib_dev *dev = to_mdev(ibcontext->device);

	struct mlx5_bfreg_info *bfregi;



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	/* All umem's must be destroyed before destroying the ucontext. */

	mutex_lock(&ibcontext->per_mm_list_lock);

	WARN_ON(!list_empty(&ibcontext->per_mm_list));

	mutex_unlock(&ibcontext->per_mm_list_lock);

#endif



	bfregi = &context->bfregi;

	mlx5_ib_dealloc_transport_domain(dev, context->tdn, context->devx_uid);
@@ -5722,11 +5720,11 @@ static struct ib_counters *mlx5_ib_create_counters(struct ib_device *device, 
void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)

{

	mlx5_ib_cleanup_multiport_master(dev);

#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {

		cleanup_srcu_struct(&dev->mr_srcu);

		drain_workqueue(dev->advise_mr_wq);

		destroy_workqueue(dev->advise_mr_wq);

#endif

	}

	kfree(dev->port);

}
@@ -5779,8 +5777,9 @@ int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) 
	spin_lock_init(&dev->memic.memic_lock);

	dev->memic.dev = mdev;



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	dev->advise_mr_wq = alloc_ordered_workqueue("mlx5_ib_advise_mr_wq", 0);

	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {

		dev->advise_mr_wq =

			alloc_ordered_workqueue("mlx5_ib_advise_mr_wq", 0);

		if (!dev->advise_mr_wq) {

			err = -ENOMEM;

			goto err_mp;
@@ -5791,7 +5790,7 @@ int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) 
			destroy_workqueue(dev->advise_mr_wq);

			goto err_mp;

		}

#endif

	}



	return 0;

err_mp:

drivers/infiniband/hw/mlx5/mem.c

+1 −4
Original line number Diff line number Diff line
@@ -111,7 +111,6 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, 
	*count = i;

}



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

static u64 umem_dma_to_mtt(dma_addr_t umem_dma)

{

	u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK;
@@ -123,7 +122,6 @@ static u64 umem_dma_to_mtt(dma_addr_t umem_dma) 


	return mtt_entry;

}

#endif



/*

 * Populate the given array with bus addresses from the umem.
@@ -151,7 +149,7 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem, 
	int len;

	struct scatterlist *sg;

	int entry;

#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING



	if (umem->is_odp) {

		WARN_ON(shift != 0);

		WARN_ON(access_flags != (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE));
@@ -164,7 +162,6 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem, 
		}

		return;

	}

#endif



	i = 0;

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

drivers/infiniband/hw/mlx5/mr.c

+12 −16
Original line number Diff line number Diff line
@@ -71,10 +71,9 @@ static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) 
{

	int err = mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey);



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))

		/* Wait until all page fault handlers using the mr complete. */

		synchronize_srcu(&dev->mr_srcu);

#endif



	return err;

}
@@ -254,9 +253,8 @@ static void remove_keys(struct mlx5_ib_dev *dev, int c, int num) 
		mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey);

	}



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))

		synchronize_srcu(&dev->mr_srcu);

#endif



	list_for_each_entry_safe(mr, tmp_mr, &del_list, list) {

		list_del(&mr->list);
@@ -1329,8 +1327,8 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, 
	mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx, access_flags 0x%x\n",

		    start, virt_addr, length, access_flags);



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	if (!start && length == U64_MAX) {

	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && !start &&

	    length == U64_MAX) {

		if (!(access_flags & IB_ACCESS_ON_DEMAND) ||

		    !(dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))

			return ERR_PTR(-EINVAL);
@@ -1340,7 +1338,6 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, 
			return ERR_CAST(mr);

		return &mr->ibmr;

	}

#endif



	err = mr_umem_get(pd, start, length, access_flags, &umem, &npages,

			   &page_shift, &ncont, &order);
@@ -1401,9 +1398,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, 
		}

	}



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))

		mr->live = 1;

#endif



	return &mr->ibmr;

error:

	ib_umem_release(umem);
@@ -1518,9 +1515,8 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, 
		}



		mr->allocated_from_cache = 0;

#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING

		if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))

			mr->live = 1;

#endif

	} else {

		/*

		 * Send a UMR WQE

include/rdma/ib_umem_odp.h

+13 −13
Original line number Diff line number Diff line
@@ -83,6 +83,19 @@ static inline struct ib_umem_odp *to_ib_umem_odp(struct ib_umem *umem) 
	return container_of(umem, struct ib_umem_odp, umem);

}



/*

 * The lower 2 bits of the DMA address signal the R/W permissions for

 * the entry. To upgrade the permissions, provide the appropriate

 * bitmask to the map_dma_pages function.

 *

 * Be aware that upgrading a mapped address might result in change of

 * the DMA address for the page.

 */

#define ODP_READ_ALLOWED_BIT  (1<<0ULL)

#define ODP_WRITE_ALLOWED_BIT (1<<1ULL)



#define ODP_DMA_ADDR_MASK (~(ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT))



#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING



struct ib_ucontext_per_mm {
@@ -107,19 +120,6 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, 
				      unsigned long addr, size_t size);

void ib_umem_odp_release(struct ib_umem_odp *umem_odp);



/*

 * The lower 2 bits of the DMA address signal the R/W permissions for

 * the entry. To upgrade the permissions, provide the appropriate

 * bitmask to the map_dma_pages function.

 *

 * Be aware that upgrading a mapped address might result in change of

 * the DMA address for the page.

 */

#define ODP_READ_ALLOWED_BIT  (1<<0ULL)

#define ODP_WRITE_ALLOWED_BIT (1<<1ULL)



#define ODP_DMA_ADDR_MASK (~(ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT))



int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,

			      u64 bcnt, u64 access_mask,

			      unsigned long current_seq);

CRA Git | Maintained and supported by SUSTech CRA and CCSE