On Mon, Dec 16, 2019 at 8:33 PM Sunil Kumar Kori <sk...@marvell.com> wrote:
>
> After each mbox send operation, context waits for minimum 1ms to get
> corresponding response although response can come earlier.
> So reducing wait time to lower granularity.
>
> Signed-off-by: Sunil Kumar Kori <sk...@marvell.com>
Acked-by: Jerin Jacob <jer...@marvell.com>
Applied to dpdk-next-net-mrvl/master. Thanks
> ---
> drivers/common/octeontx2/otx2_mbox.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/common/octeontx2/otx2_mbox.c
> b/drivers/common/octeontx2/otx2_mbox.c
> index c359bf42f..cc341aac3 100644
> --- a/drivers/common/octeontx2/otx2_mbox.c
> +++ b/drivers/common/octeontx2/otx2_mbox.c
> @@ -278,8 +278,9 @@ mbox_wait(struct otx2_mbox *mbox, int devid, uint32_t
> rst_timo)
> volatile struct otx2_mbox_dev *mdev = &mbox->dev[devid];
> uint32_t timeout = 0, sleep = 1;
>
> + rst_timo = rst_timo * 1000; /* Milli seconds to micro seconds */
> while (mdev->num_msgs > mdev->msgs_acked) {
> - rte_delay_ms(sleep);
> + rte_delay_us(sleep);
> timeout += sleep;
> if (timeout >= rst_timo) {
> struct mbox_hdr *tx_hdr =
> --
> 2.17.1
>
