Hi Vivien,
On Thu, Jun 25, 2020 at 03:01:17PM -0400, Vivien Didelot wrote:
> From: Patrick Keroulas <patrick.kerou...@radio-canada.ca>
>
> While some devices update their own clock info to provide current time,
> mlx5dv part of libibverbs already handles this and also converts any
> raw counter cycle to nanoseconds.
>
> Signed-off-by: Patrick Keroulas <patrick.kerou...@radio-canada.ca>
> ---
> drivers/common/mlx5/linux/mlx5_glue.c | 16 +++++++++++++
> drivers/common/mlx5/linux/mlx5_glue.h | 4 ++++
> drivers/net/mlx5/linux/mlx5_ethdev_os.c | 30 +++++++++++++++++++++++++
> drivers/net/mlx5/linux/mlx5_os.c | 1 +
> drivers/net/mlx5/mlx5.h | 1 +
> 5 files changed, 52 insertions(+)
>
> diff --git a/drivers/common/mlx5/linux/mlx5_glue.c
> b/drivers/common/mlx5/linux/mlx5_glue.c
> index c91ee33bb..cac24015b 100644
> --- a/drivers/common/mlx5/linux/mlx5_glue.c
> +++ b/drivers/common/mlx5/linux/mlx5_glue.c
> @@ -80,6 +80,20 @@ mlx5_glue_query_rt_values_ex(struct ibv_context *context,
> return ibv_query_rt_values_ex(context, values);
> }
>
> +static int
> +mlx5_glue_get_clock_info(struct ibv_context *context,
> + struct mlx5dv_clock_info *clock_info)
> +{
> + return mlx5dv_get_clock_info(context, clock_info);
> +}
> +
> +static uint64_t
> +mlx5_glue_mlx5dv_ts_to_ns(struct mlx5dv_clock_info *clock_info,
> + uint64_t device_timestamp)
> +{
> + return mlx5dv_ts_to_ns(clock_info, device_timestamp);
> +}
> +
> static int
> mlx5_glue_query_port(struct ibv_context *context, uint8_t port_num,
> struct ibv_port_attr *port_attr)
> @@ -1207,6 +1221,8 @@ const struct mlx5_glue *mlx5_glue = &(const struct
> mlx5_glue) {
> .query_device = mlx5_glue_query_device,
> .query_device_ex = mlx5_glue_query_device_ex,
> .query_rt_values_ex = mlx5_glue_query_rt_values_ex,
> + .get_clock_info = mlx5_glue_get_clock_info,
> + .convert_ts_to_ns = mlx5_glue_mlx5dv_ts_to_ns,
> .query_port = mlx5_glue_query_port,
> .create_comp_channel = mlx5_glue_create_comp_channel,
> .destroy_comp_channel = mlx5_glue_destroy_comp_channel,
> diff --git a/drivers/common/mlx5/linux/mlx5_glue.h
> b/drivers/common/mlx5/linux/mlx5_glue.h
> index 5d238a40a..8d05e7398 100644
> --- a/drivers/common/mlx5/linux/mlx5_glue.h
> +++ b/drivers/common/mlx5/linux/mlx5_glue.h
> @@ -123,6 +123,10 @@ struct mlx5_glue {
> struct ibv_port_attr *port_attr);
> struct ibv_comp_channel *(*create_comp_channel)
> (struct ibv_context *context);
> + int (*get_clock_info)(struct ibv_context *context,
> + struct mlx5dv_clock_info *clock_info);
> + uint64_t (*convert_ts_to_ns)(struct mlx5dv_clock_info *clock_info,
> + uint64_t device_timestamp);
> int (*destroy_comp_channel)(struct ibv_comp_channel *channel);
> struct ibv_cq *(*create_cq)(struct ibv_context *context, int cqe,
> void *cq_context,
> diff --git a/drivers/net/mlx5/linux/mlx5_ethdev_os.c
> b/drivers/net/mlx5/linux/mlx5_ethdev_os.c
> index ab47cb531..86bec111b 100644
> --- a/drivers/net/mlx5/linux/mlx5_ethdev_os.c
> +++ b/drivers/net/mlx5/linux/mlx5_ethdev_os.c
> @@ -355,6 +355,36 @@ mlx5_set_flags(struct rte_eth_dev *dev, unsigned int
> keep, unsigned int flags)
> return mlx5_ifreq(dev, SIOCSIFFLAGS, &request);
> }
>
> +/**
> + * Convert raw clock counter to nanoseconds
> + *
> + * @param dev
> + * Pointer to Ethernet device structure.
> + * @param[in&out] timestamp
> + * Pointer to the timestamp to be converted.
> + *
> + * @return
> + * 0 if the clock has correctly been read
> + * The value of errno in case of error
> + */
> +int
> +mlx5_convert_ts_to_ns(struct rte_eth_dev *dev, uint64_t *timestamp)
> +{
> + struct mlx5_priv *priv = dev->data->dev_private;
> + struct ibv_context *ctx = priv->sh->ctx;
> + struct mlx5dv_clock_info clock_info;
> +
> + int err = mlx5_glue->get_clock_info(ctx, &clock_info);
> + if (err != 0) {
> + DRV_LOG(WARNING, "Could not get the clock info!");
> + return err;
> + }
> +
> + *timestamp = mlx5_glue->convert_ts_to_ns(&clock_info, *timestamp);
> +
> + return err;
> +}
Should mlx5dv_get_clock_info() be called for each convesion? In the man
page [1], we can read this:
If the clock_info becomes too old then time conversion will return
wrong conversion results. The user must ensure that
mlx5dv_get_clock_info(3) is called at least once every
max_clock_info_update_nsec as returned by the mlx5dv_query_device(3)
function.
I understand this as mlx5dv_get_clock_info() being slower than
mlx5dv_ts_to_ns(), and should not be called for each packet.
I suppose that when rdma-core library does a conversion to nanosec, it
takes in account the fact that system and device are not synchronized
(are they?).
[1] https://man7.org/linux/man-pages/man3/mlx5dv_get_clock_info.3.html
Olivier
