On 5/19/2015 1:40 AM, Stephen Hemminger wrote:
> +/* enable MSI-X interrupts */
> +static int
> +uio_msix_enable(struct rte_intr_handle *intr_handle)
> +{
> + int i, max_intr;
> +
> + if (!intr_handle->max_intr ||
> + intr_handle->max_intr > RTE_MAX_RXTX_INTR_VEC_ID)
> +
On Mon, 25 May 2015 16:55:23 +0800
"Liang, Cunming" wrote:
> > + irqs.fd = intr_handle->fd;
> > +
> > + if (ioctl(intr_handle->vfio_dev_fd, UIO_MSI_IRQ_SET, &irqs) <
> > 0) {
> It would be strange if using vfio_dev_fd in 'uio_msix_' related function.
Just minor var
Add the new uio_msi as a supported driver model.
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/include/rte_pci.h| 1 +
lib/librte_eal/linuxapp/eal/eal_interrupts.c | 94 +++---
lib/librte_eal/linuxapp/eal/eal_pci.c | 4 +
lib/librte_e
3 matches
Mail list logo
