xref: /freebsd-10.0-release/sys/ofed/drivers/infiniband/hw/mlx4/mr.c

/*
 * Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
 * Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include "mlx4_ib.h"

static u32 convert_access(int acc)
{
	return (acc & IB_ACCESS_REMOTE_ATOMIC ? MLX4_PERM_ATOMIC       : 0) |
	       (acc & IB_ACCESS_REMOTE_WRITE  ? MLX4_PERM_REMOTE_WRITE : 0) |
	       (acc & IB_ACCESS_REMOTE_READ   ? MLX4_PERM_REMOTE_READ  : 0) |
	       (acc & IB_ACCESS_LOCAL_WRITE   ? MLX4_PERM_LOCAL_WRITE  : 0) |
	       MLX4_PERM_LOCAL_READ;
}

struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
{
	struct mlx4_ib_mr *mr;
	int err;

	mr = kmalloc(sizeof *mr, GFP_KERNEL);
	if (!mr)
		return ERR_PTR(-ENOMEM);

	err = mlx4_mr_alloc(to_mdev(pd->device)->dev, to_mpd(pd)->pdn, 0,
			    ~0ull, convert_access(acc), 0, 0, &mr->mmr);
	if (err)
		goto err_free;

	err = mlx4_mr_enable(to_mdev(pd->device)->dev, &mr->mmr);
	if (err)
		goto err_mr;

	mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;
	mr->umem = NULL;

	return &mr->ibmr;

err_mr:
	mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);

err_free:
	kfree(mr);

	return ERR_PTR(err);
}

int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
			   struct ib_umem *umem)
{
	u64 *pages;
	struct ib_umem_chunk *chunk;
	int i, j, k;
	int n;
	int len;
	int err = 0;

	pages = (u64 *) __get_free_page(GFP_KERNEL);
	if (!pages)
		return -ENOMEM;

	i = n = 0;

	list_for_each_entry(chunk, &umem->chunk_list, list)
		for (j = 0; j < chunk->nmap; ++j) {
			len = sg_dma_len(&chunk->page_list[j]) >> mtt->page_shift;
			for (k = 0; k < len; ++k) {
				pages[i++] = sg_dma_address(&chunk->page_list[j]) +
					umem->page_size * k;
				/*
				 * Be friendly to mlx4_write_mtt() and
				 * pass it chunks of appropriate size.
				 */
				if (i == PAGE_SIZE / sizeof (u64)) {
					err = mlx4_write_mtt(dev->dev, mtt, n,
							     i, pages);
					if (err)
						goto out;
					n += i;
					i = 0;
				}
			}
		}

	if (i)
		err = mlx4_write_mtt(dev->dev, mtt, n, i, pages);

out:
	free_page((unsigned long) pages);
	return err;
}

static int handle_hugetlb_user_mr(struct ib_pd *pd, struct mlx4_ib_mr *mr,
				  u64 start, u64 virt_addr, int access_flags)
{
#if defined(CONFIG_HUGETLB_PAGE) && !defined(__powerpc__) && !defined(__ia64__)
	struct mlx4_ib_dev *dev = to_mdev(pd->device);
	struct ib_umem_chunk *chunk;
	unsigned dsize;
	dma_addr_t daddr;
	unsigned cur_size = 0;
	dma_addr_t uninitialized_var(cur_addr);
	int n;
	struct ib_umem	*umem = mr->umem;
	u64 *arr;
	int err = 0;
	int i;
	int j = 0;
	int off = start & (HPAGE_SIZE - 1);

	n = DIV_ROUND_UP(off + umem->length, HPAGE_SIZE);
	arr = kmalloc(n * sizeof *arr, GFP_KERNEL);
	if (!arr)
		return -ENOMEM;

	list_for_each_entry(chunk, &umem->chunk_list, list)
		for (i = 0; i < chunk->nmap; ++i) {
			daddr = sg_dma_address(&chunk->page_list[i]);
			dsize = sg_dma_len(&chunk->page_list[i]);
			if (!cur_size) {
				cur_addr = daddr;
				cur_size = dsize;
			} else if (cur_addr + cur_size != daddr) {
				err = -EINVAL;
				goto out;
			} else
				cur_size += dsize;

			if (cur_size > HPAGE_SIZE) {
				err = -EINVAL;
				goto out;
			} else if (cur_size == HPAGE_SIZE) {
				cur_size = 0;
				arr[j++] = cur_addr;
			}
		}

	if (cur_size) {
		arr[j++] = cur_addr;
	}

	err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, virt_addr, umem->length,
			    convert_access(access_flags), n, HPAGE_SHIFT, &mr->mmr);
	if (err)
		goto out;

	err = mlx4_write_mtt(dev->dev, &mr->mmr.mtt, 0, n, arr);

out:
	kfree(arr);
	return err;
#else
	return -ENOSYS;
#endif
}

struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
				  u64 virt_addr, int access_flags,
				  struct ib_udata *udata)
{
	struct mlx4_ib_dev *dev = to_mdev(pd->device);
	struct mlx4_ib_mr *mr;
	int shift;
	int err;
	int n;

	mr = kmalloc(sizeof *mr, GFP_KERNEL);
	if (!mr)
		return ERR_PTR(-ENOMEM);

	mr->umem = ib_umem_get(pd->uobject->context, start, length,
			       access_flags, 0);
	if (IS_ERR(mr->umem)) {
		err = PTR_ERR(mr->umem);
		goto err_free;
	}

	if (!mr->umem->hugetlb ||
	    handle_hugetlb_user_mr(pd, mr, start, virt_addr, access_flags)) {
		n = ib_umem_page_count(mr->umem);
		shift = ilog2(mr->umem->page_size);

		err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, virt_addr, length,
				    convert_access(access_flags), n, shift, &mr->mmr);
		if (err)
			goto err_umem;

		err = mlx4_ib_umem_write_mtt(dev, &mr->mmr.mtt, mr->umem);
		if (err)
			goto err_mr;
	}

	err = mlx4_mr_enable(dev->dev, &mr->mmr);
	if (err)
		goto err_mr;

	mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;

	return &mr->ibmr;

err_mr:
	mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);

err_umem:
	ib_umem_release(mr->umem);

err_free:
	kfree(mr);

	return ERR_PTR(err);
}

int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
{
	struct mlx4_ib_mr *mr = to_mmr(ibmr);

	mlx4_mr_free(to_mdev(ibmr->device)->dev, &mr->mmr);
	if (mr->umem)
		ib_umem_release(mr->umem);
	kfree(mr);

	return 0;
}

struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
					int max_page_list_len)
{
	struct mlx4_ib_dev *dev = to_mdev(pd->device);
	struct mlx4_ib_mr *mr;
	int err;

	mr = kmalloc(sizeof *mr, GFP_KERNEL);
	if (!mr)
		return ERR_PTR(-ENOMEM);

	err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, 0, 0, 0,
			    max_page_list_len, 0, &mr->mmr);
	if (err)
		goto err_free;

	err = mlx4_mr_enable(dev->dev, &mr->mmr);
	if (err)
		goto err_mr;

	mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;
	mr->umem = NULL;

	return &mr->ibmr;

err_mr:
	mlx4_mr_free(dev->dev, &mr->mmr);

err_free:
	kfree(mr);
	return ERR_PTR(err);
}

struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
							       int page_list_len)
{
	struct mlx4_ib_dev *dev = to_mdev(ibdev);
	struct mlx4_ib_fast_reg_page_list *mfrpl;
	int size = page_list_len * sizeof (u64);

	if (page_list_len > MAX_FAST_REG_PAGES)
		return ERR_PTR(-EINVAL);

	mfrpl = kmalloc(sizeof *mfrpl, GFP_KERNEL);
	if (!mfrpl)
		return ERR_PTR(-ENOMEM);

	mfrpl->ibfrpl.page_list = kmalloc(size, GFP_KERNEL);
	if (!mfrpl->ibfrpl.page_list)
		goto err_free;

	mfrpl->mapped_page_list = dma_alloc_coherent(&dev->dev->pdev->dev,
						     size, &mfrpl->map,
						     GFP_KERNEL);
	if (!mfrpl->mapped_page_list)
		goto err_free;

	WARN_ON(mfrpl->map & 0x3f);

	return &mfrpl->ibfrpl;

err_free:
	kfree(mfrpl->ibfrpl.page_list);
	kfree(mfrpl);
	return ERR_PTR(-ENOMEM);
}

void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
{
	struct mlx4_ib_dev *dev = to_mdev(page_list->device);
	struct mlx4_ib_fast_reg_page_list *mfrpl = to_mfrpl(page_list);
	int size = page_list->max_page_list_len * sizeof (u64);

	dma_free_coherent(&dev->dev->pdev->dev, size, mfrpl->mapped_page_list,
			  mfrpl->map);
	kfree(mfrpl->ibfrpl.page_list);
	kfree(mfrpl);
}

struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int acc,
				 struct ib_fmr_attr *fmr_attr)
{
	struct mlx4_ib_dev *dev = to_mdev(pd->device);
	struct mlx4_ib_fmr *fmr;
	int err = -ENOMEM;

	fmr = kmalloc(sizeof *fmr, GFP_KERNEL);
	if (!fmr)
		return ERR_PTR(-ENOMEM);

	err = mlx4_fmr_alloc(dev->dev, to_mpd(pd)->pdn, convert_access(acc),
			     fmr_attr->max_pages, fmr_attr->max_maps,
			     fmr_attr->page_shift, &fmr->mfmr);
	if (err)
		goto err_free;

	err = mlx4_fmr_enable(to_mdev(pd->device)->dev, &fmr->mfmr);
	if (err)
		goto err_mr;

	fmr->ibfmr.rkey = fmr->ibfmr.lkey = fmr->mfmr.mr.key;

	return &fmr->ibfmr;

err_mr:
	mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr);

err_free:
	kfree(fmr);

	return ERR_PTR(err);
}

int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
		      int npages, u64 iova)
{
	struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
	struct mlx4_ib_dev *dev = to_mdev(ifmr->ibfmr.device);

	return mlx4_map_phys_fmr(dev->dev, &ifmr->mfmr, page_list, npages, iova,
				 &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey);
}

int mlx4_ib_unmap_fmr(struct list_head *fmr_list)
{
	struct ib_fmr *ibfmr;
	int err;
	struct mlx4_dev *mdev = NULL;

	list_for_each_entry(ibfmr, fmr_list, list) {
		if (mdev && to_mdev(ibfmr->device)->dev != mdev)
			return -EINVAL;
		mdev = to_mdev(ibfmr->device)->dev;
	}

	if (!mdev)
		return 0;

	list_for_each_entry(ibfmr, fmr_list, list) {
		struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);

		mlx4_fmr_unmap(mdev, &ifmr->mfmr, &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey);
	}

	/*
	 * Make sure all MPT status updates are visible before issuing
	 * SYNC_TPT firmware command.
	 */
	wmb();

	err = mlx4_SYNC_TPT(mdev);
	if (err)
		printk(KERN_WARNING "mlx4_ib: SYNC_TPT error %d when "
		       "unmapping FMRs\n", err);

	return 0;
}

int mlx4_ib_fmr_dealloc(struct ib_fmr *ibfmr)
{
	struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
	struct mlx4_ib_dev *dev = to_mdev(ibfmr->device);
	int err;

	err = mlx4_fmr_free(dev->dev, &ifmr->mfmr);

	if (!err)
		kfree(ifmr);

	return err;
}