On Wed, 2016-11-30 at 00:19 +0200, Saeed Mahameed wrote:
> From: Tariq Toukan <tar...@mellanox.com>
>
> Add new type of struct mlx5_frag_buf which is used to allocate fragmented
> buffers rather than contiguous, and make the Completion Queues (CQs) use
> it as they are big (default of 2MB per CQ in Striding RQ).
>
> This fixes the failures of type:
> "mlx5e_open_locked: mlx5e_open_channels failed, -12"
> due to dma_zalloc_coherent insufficient contiguous coherent memory to
> satisfy the driver's request when the user tries to setup more or larger
> rings.
>
> Signed-off-by: Tariq Toukan <tar...@mellanox.com>
> Reported-by: Sebastian Ott <seb...@linux.vnet.ibm.com>
> Signed-off-by: Saeed Mahameed <sae...@mellanox.com>
> ---
> drivers/net/ethernet/mellanox/mlx5/core/alloc.c | 66
> +++++++++++++++++++++++
> drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +-
> drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 ++--
> drivers/net/ethernet/mellanox/mlx5/core/wq.c | 26 ++++++---
> drivers/net/ethernet/mellanox/mlx5/core/wq.h | 18 +++++--
> include/linux/mlx5/driver.h | 11 ++++
> 6 files changed, 116 insertions(+), 17 deletions(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
> b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
> index 2c6e3c7..bc8357d 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
> @@ -106,6 +106,63 @@ void mlx5_buf_free(struct mlx5_core_dev *dev, struct
> mlx5_buf *buf)
> }
> EXPORT_SYMBOL_GPL(mlx5_buf_free);
>
> +int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
> + struct mlx5_frag_buf *buf, int node)
> +{
> + int i;
> +
> + buf->size = size;
> + buf->npages = 1 << get_order(size);
> + buf->page_shift = PAGE_SHIFT;
> + buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list),
> + GFP_KERNEL);
> + if (!buf->frags)
> + goto err_out;
> +
> + for (i = 0; i < buf->npages; i++) {
> + struct mlx5_buf_list *frag = &buf->frags[i];
> + int frag_sz = min_t(int, size, PAGE_SIZE);
> +
> + frag->buf = mlx5_dma_zalloc_coherent_node(dev, frag_sz,
> + &frag->map, node);
> + if (!frag->buf)
> + goto err_free_buf;
> + if (frag->map & ((1 << buf->page_shift) - 1)) {
> + dma_free_coherent(&dev->pdev->dev, frag_sz,
> + buf->frags[i].buf, buf->frags[i].map);
There is a bug if this happens with i = 0
> + mlx5_core_warn(dev, "unexpected map alignment: 0x%p,
> page_shift=%d\n",
> + (void *)frag->map, buf->page_shift);
> + goto err_free_buf;
> + }
> + size -= frag_sz;
> + }
> +
> + return 0;
> +
> +err_free_buf:
> + while (--i)
Because this loop will be done about 2^32 times.
> + dma_free_coherent(&dev->pdev->dev, PAGE_SIZE, buf->frags[i].buf,
> + buf->frags[i].map);
> + kfree(buf->frags);
> +err_out:
> + return -ENOMEM;
> +}
