On Sun, 23 Apr 2017 18:31:36 -0700 John Fastabend <john.fastab...@gmail.com> wrote:
> +static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, > + struct xdp_buff *xdp) > +{ > + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; I was about to question whether is it always true that the array size can match the number of CPUs in the system, but I can see later in ixgbe_xdp_setup() that you reject XDP program if the system have more CPUs that MAX_XDP_QUEUES. > + struct ixgbe_tx_buffer *tx_buffer; > + union ixgbe_adv_tx_desc *tx_desc; > + u32 len, cmd_type; > + dma_addr_t dma; > + u16 i; > + > + len = xdp->data_end - xdp->data; > + > + if (unlikely(!ixgbe_desc_unused(ring))) > + return IXGBE_XDP_CONSUMED; > + > + dma = dma_map_single(ring->dev, xdp->data, len, DMA_TO_DEVICE); > + if (dma_mapping_error(ring->dev, dma)) > + return IXGBE_XDP_CONSUMED; > + > + /* record the location of the first descriptor for this packet */ > + tx_buffer = &ring->tx_buffer_info[ring->next_to_use]; > + tx_buffer->bytecount = len; > + tx_buffer->gso_segs = 1; > + tx_buffer->protocol = 0; > + > + i = ring->next_to_use; > + tx_desc = IXGBE_TX_DESC(ring, i); > + > + dma_unmap_len_set(tx_buffer, len, len); > + dma_unmap_addr_set(tx_buffer, dma, dma); > + tx_buffer->data = xdp->data; > + tx_desc->read.buffer_addr = cpu_to_le64(dma); > + > + /* put descriptor type bits */ > + cmd_type = IXGBE_ADVTXD_DTYP_DATA | > + IXGBE_ADVTXD_DCMD_DEXT | > + IXGBE_ADVTXD_DCMD_IFCS; > + cmd_type |= len | IXGBE_TXD_CMD; > + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); > + tx_desc->read.olinfo_status = > + cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT); > + > + /* Force memory writes to complete before letting h/w know there > + * are new descriptors to fetch. (Only applicable for weak-ordered > + * memory model archs, such as IA-64). > + * > + * We also need this memory barrier to make certain all of the > + * status bits have been updated before next_to_watch is written. > + */ > + wmb(); > + > + /* set next_to_watch value indicating a packet is present */ > + i++; > + if (i == ring->count) > + i = 0; > + > + tx_buffer->next_to_watch = tx_desc; > + ring->next_to_use = i; > + > + writel(i, ring->tail); A tailptr write for every XDP_TX packet is not going be fast, but you already mentioned that this is not optimal yet, so I guess you are aware. > + return IXGBE_XDP_TX; > +} On Sun, 23 Apr 2017 18:31:36 -0700 John Fastabend <john.fastab...@gmail.com> wrote: > @@ -9559,9 +9740,23 @@ static int ixgbe_xdp_setup(struct net_device *dev, > struct bpf_prog *prog) > return -EINVAL; > } > > + if (nr_cpu_ids > MAX_XDP_QUEUES) > + return -ENOMEM; > + -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer