Before this fix, running high rate traffic through XDP_REDIRECT
with multibuf could overrun the fifo used to release the
xdp frames after tx completion. This resulted in corrupted data
being consumed on the free side.
The culplirt was a miscalculation of the fifo size: the maximum ratio
between fifo entries / data segments was incorrect. This ratio serves to
calculate the max fifo size for a full sq where each packet uses the
worst case number of entries in the fifo.
This patch fixes the formula and names the constant. It also makes sure
that future values will use a power of 2 number of entries for the fifo
mask to work.
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Fixes:
3f734b8c594b ("net/mlx5e: XDP, Use multiple single-entry objects in xdpi_fifo")
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
* MLX5E_XDP_XMIT_MODE_XSK:
* none.
*/
+#define MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO 4
+
union mlx5e_xdp_info {
enum mlx5e_xdp_xmit_mode mode;
union {
{
struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
- int entries = wq_sz * MLX5_SEND_WQEBB_NUM_DS * 2; /* upper bound for maximum num of
- * entries of all xmit_modes.
- */
+ int entries;
size_t size;
+ /* upper bound for maximum num of entries of all xmit_modes. */
+ entries = roundup_pow_of_two(wq_sz * MLX5_SEND_WQEBB_NUM_DS *
+ MLX5E_XDP_FIFO_ENTRIES2DS_MAX_RATIO);
+
size = array_size(sizeof(*xdpi_fifo->xi), entries);
xdpi_fifo->xi = kvzalloc_node(size, GFP_KERNEL, numa);
if (!xdpi_fifo->xi)