diff options
| author | Jack Morgenstein <jackm@dev.mellanox.co.il> | 2008-01-28 11:40:51 +0300 |
|---|---|---|
| committer | Roland Dreier <rolandd@cisco.com> | 2008-02-07 08:17:45 +0300 |
| commit | 313abe55a87bc10e55d00f337d609e17ad5f8c9a (patch) | |
| tree | 833ff3c4b33f83d4ca64ed322c2d8efa21529d71 /include/linux/mlx4 | |
| parent | 1c69fc2a9012e160c8d459f63df74a6b01db8322 (diff) | |
| download | linux-313abe55a87bc10e55d00f337d609e17ad5f8c9a.tar.xz | |
mlx4_core: For 64-bit systems, vmap() kernel queue buffers
Since kernel virtual memory is not a problem on 64-bit systems, there
is no reason to use our own 2-layer page mapping scheme for large
kernel queue buffers on such systems. Instead, map the page list to a
single virtually contiguous buffer with vmap(), so that can we access
buffer memory via direct indexing.
Signed-off-by: Michael S. Tsirkin <mst@dev.mellanox.co.il>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Diffstat (limited to 'include/linux/mlx4')
| -rw-r--r-- | include/linux/mlx4/device.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index a0afa7511a30..631607788f83 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -189,7 +189,7 @@ struct mlx4_buf_list { }; struct mlx4_buf { - union { + struct { struct mlx4_buf_list direct; struct mlx4_buf_list *page_list; } u; @@ -310,7 +310,7 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf); static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset) { - if (buf->nbufs == 1) + if (BITS_PER_LONG == 64 || buf->nbufs == 1) return buf->u.direct.buf + offset; else return buf->u.page_list[offset >> PAGE_SHIFT].buf + |