On Tue, 2020-11-03 at 09:46 -0800, David Awogbemila wrote:
> From: Catherine Sullivan <csu...@google.com>
>
> Add support to describe device for parsing device options. As
> the first device option, add raw addressing.
>
> "Raw Addressing" mode (as opposed to the current "qpl" mode) is an
> operational mode which allows the driver avoid bounce buffer copies
> which it currently performs using pre-allocated qpls
> (queue_page_lists)
> when sending and receiving packets.
> For egress packets, the provided skb data addresses will be
> dma_map'ed and
> passed to the device, allowing the NIC can perform DMA directly - the
> driver will not have to copy the buffer content into pre-allocated
> buffers/qpls (as in qpl mode).
> For ingress packets, copies are also eliminated as buffers are handed
> to
> the networking stack and then recycled or re-allocated as
> necessary, avoiding the use of skb_copy_to_linear_data().
>
> This patch only introduces the option to the driver.
> Subsequent patches will add the ingress and egress functionality.
>
> Reviewed-by: Yangchun Fu <yangc...@google.com>
> Signed-off-by: Catherine Sullivan <csu...@google.com>
> Signed-off-by: David Awogbemila <awogbem...@google.com>
> ---
> drivers/net/ethernet/google/gve/gve.h | 1 +
> drivers/net/ethernet/google/gve/gve_adminq.c | 52
> ++++++++++++++++++++
> drivers/net/ethernet/google/gve/gve_adminq.h | 15 ++++--
> drivers/net/ethernet/google/gve/gve_main.c | 9 ++++
> 4 files changed, 73 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/ethernet/google/gve/gve.h
> b/drivers/net/ethernet/google/gve/gve.h
> index f5c80229ea96..80cdae06ee39 100644
> --- a/drivers/net/ethernet/google/gve/gve.h
> +++ b/drivers/net/ethernet/google/gve/gve.h
> @@ -199,6 +199,7 @@ struct gve_priv {
> u64 num_registered_pages; /* num pages registered with NIC */
> u32 rx_copybreak; /* copy packets smaller than this */
> u16 default_num_queues; /* default num queues to set up */
> + bool raw_addressing; /* true if this dev supports raw
> addressing */
>
> struct gve_queue_config tx_cfg;
> struct gve_queue_config rx_cfg;
> diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c
> b/drivers/net/ethernet/google/gve/gve_adminq.c
> index 24ae6a28a806..0b7a2653fe33 100644
> --- a/drivers/net/ethernet/google/gve/gve_adminq.c
> +++ b/drivers/net/ethernet/google/gve/gve_adminq.c
> @@ -460,11 +460,14 @@ int gve_adminq_destroy_rx_queues(struct
> gve_priv *priv, u32 num_queues)
> int gve_adminq_describe_device(struct gve_priv *priv)
> {
> struct gve_device_descriptor *descriptor;
> + struct gve_device_option *dev_opt;
> union gve_adminq_command cmd;
> dma_addr_t descriptor_bus;
> + u16 num_options;
> int err = 0;
> u8 *mac;
> u16 mtu;
> + int i;
>
> memset(&cmd, 0, sizeof(cmd));
> descriptor = dma_alloc_coherent(&priv->pdev->dev, PAGE_SIZE,
> @@ -518,6 +521,55 @@ int gve_adminq_describe_device(struct gve_priv
> *priv)
> priv->rx_desc_cnt = priv->rx_pages_per_qpl;
> }
> priv->default_num_queues = be16_to_cpu(descriptor-
> >default_num_queues);
> + dev_opt = (void *)(descriptor + 1);
> +
> + num_options = be16_to_cpu(descriptor->num_device_options);
> + for (i = 0; i < num_options; i++) {
> + u16 option_length = be16_to_cpu(dev_opt-
> >option_length);
> + u16 option_id = be16_to_cpu(dev_opt->option_id);
> + void *option_end;
> +
> + option_end = (void *)dev_opt + sizeof(*dev_opt) +
> option_length;
> + if (option_end > (void *)descriptor +
> be16_to_cpu(descriptor->total_length)) {
> + dev_err(&priv->dev->dev,
> + "options exceed device_descriptor's
> total length.\n");
> + err = -EINVAL;
> + goto free_device_descriptor;
> + }
> +
> + switch (option_id) {
> + case GVE_DEV_OPT_ID_RAW_ADDRESSING:
> + /* If the length or feature mask doesn't match,
> + * continue without enabling the feature.
> + */
> + if (option_length !=
> GVE_DEV_OPT_LEN_RAW_ADDRESSING ||
> + dev_opt->feat_mask !=
> + cpu_to_be32(GVE_DEV_OPT_FEAT_MASK_RAW_ADDRE
> SSING)) {
> + dev_warn(&priv->pdev->dev,
> + "Raw addressing option
> error:\n"
> + " Expected: length=%d,
> feature_mask=%x.\n"
> + " Actual: length=%d,
> feature_mask=%x.\n",
> + GVE_DEV_OPT_LEN_RAW_ADDRESSING
> ,
> + cpu_to_be32(GVE_DEV_OPT_FEAT_M
> ASK_RAW_ADDRESSING),
> + option_length, dev_opt-
> >feat_mask);
> + priv->raw_addressing = false;
> + } else {
> + dev_info(&priv->pdev->dev,
> + "Raw addressing device option
> enabled.\n");
> + priv->raw_addressing = true;
> + }
> + break;
> + default:
> + /* If we don't recognize the option just
> continue
> + * without doing anything.
> + */
> + dev_dbg(&priv->pdev->dev,
> + "Unrecognized device option 0x%hx not
> enabled.\n",
> + option_id);
> + break;
> + }
> + dev_opt = (void *)dev_opt + sizeof(*dev_opt) +
> option_length;
This was already calculated above, "option_end"
Suggestion: you can make an iterator macro to return the next opt
next_opt = GET_NEXT_OPT(descriptor, curr_opt);
you can make it check boundaries and return null on last iteration or
when total length is exceeded, and just use it in a more readable
iterator loop.
