> -----Original Message-----
> From: Qiu, Michael
> Sent: Thursday, January 29, 2015 1:07 PM
> To: Zhou, Danny; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v1 4/5] eal: add per rx queue interrupt
> handling based on VFIO
>
> On 1/28/2015 5:52 PM, Danny Zhou wrote:
> > Signed-off-by: Danny Zhou <danny.zhou at intel.com>
> > Signed-off-by: Yong Liu <yong.liu at intel.com>
> > ---
>
> [...]
>
> > +static void
> > +eal_intr_process_rx_interrupts(uint8_t port_id, struct epoll_event
> > *events, int nfds)
> > +{
> > + int n, bytes_read;
> > + union rte_intr_read_buffer buf;
> > + struct rte_intr_handle intr_handle =
> > rte_eth_devices[port_id].pci_dev->intr_handle;
> > +
> > + for (n = 0; n < nfds; n++) {
> > + /* set the length to be read dor different handle type */
> > + switch (intr_handle.type) {
> > + case RTE_INTR_HANDLE_UIO:
> > + bytes_read = sizeof(buf.uio_intr_count);
> > + break;
> > + case RTE_INTR_HANDLE_ALARM:
> > + bytes_read = sizeof(buf.timerfd_num);
> > + break;
> > +#ifdef VFIO_PRESENT
> > + case RTE_INTR_HANDLE_VFIO_MSIX:
> > + case RTE_INTR_HANDLE_VFIO_MSI:
> > + case RTE_INTR_HANDLE_VFIO_LEGACY:
> > + bytes_read = sizeof(buf.vfio_intr_count);
> > + break;
> > +#endif
> > + default:
> > + bytes_read = 1;
> > + break;
> > + }
> > +
> > + /**
> > + * read out to clear the ready-to-be-read flag
> > + * for epoll_wait.
> > + */
> > + bytes_read = read(events[n].data.fd, &buf, bytes_read);
> > + if (bytes_read < 0)
> > + RTE_LOG(ERR, EAL, "Error reading from file "
> > + "descriptor %d: %s\n", events[n].data.fd,
> > + strerror(errno));
> > + else if (bytes_read == 0)
> > + RTE_LOG(ERR, EAL, "Read nothing from file "
> > + "descriptor %d\n", events[n].data.fd);
>
> Is there any issue while bytes_read is not equal to the count need to be
> read?
>
Not a problem as long as bytes_read > 0.
> > + }
> > +}
> > +
> > +static void
> > +eal_intr_handle_rx_interrupts(uint8_t port_id, int pfd, unsigned totalfds)
> > +{
> > + struct epoll_event events[totalfds];
> > + int nfds = 0;
> > +
> > +m_wait:
> > + nfds = epoll_wait(pfd, events, totalfds,
> > + EAL_INTR_EPOLL_WAIT_FOREVER);
> > + /* epoll_wait fail */
> > + if (nfds < 0) {
> > + RTE_LOG(ERR, EAL,
> > + "epoll_wait returns with fail\n");
> > + return;
> > + }
> > + /* epoll_wait timeout, will never happens here */
> > + else if (nfds == 0)
> > + goto m_wait;
> > + /* epoll_wait has at least one fd ready to read */
> > + eal_intr_process_rx_interrupts(port_id, events, nfds);
> > +}
> > +
> > +int
> > +rte_eal_wait_rx_intr(uint8_t port_id, uint8_t queue_id)
> > +{
> > + struct rte_intr_handle intr_handle =
> > rte_eth_devices[port_id].pci_dev->intr_handle;
> > + struct epoll_event ev;
> > + unsigned numfds = 0;
> > +
> > + /* create epoll fd */
> > + int pfd = epoll_create(1);
> > + if (pfd < 0) {
> > + RTE_LOG(ERR, EAL, "Cannot create epoll instance\n");
> > + return -1;
> > + }
> > +
> > + rte_spinlock_lock(&intr_lock);
> > +
> > + ev.events = EPOLLIN | EPOLLPRI;
> > + switch (intr_handle.type) {
> > + case RTE_INTR_HANDLE_UIO:
> > + ev.data.fd = intr_handle.fd;
> > + break;
> > +#ifdef VFIO_PRESENT
> > + case RTE_INTR_HANDLE_VFIO_MSIX:
> > + ev.data.fd = intr_handle.queue_fd[queue_id];
> > + break;
> > + case RTE_INTR_HANDLE_VFIO_MSI:
> > + ev.data.fd = intr_handle.queue_fd[queue_id];
> > + break;
> > + case RTE_INTR_HANDLE_VFIO_LEGACY:
> > + ev.data.fd = intr_handle.queue_fd[queue_id];
> > + break;
>
> As those three branches are all the same, why not combine to one?
>
> + case RTE_INTR_HANDLE_VFIO_MSIX:
> + case RTE_INTR_HANDLE_VFIO_MSI:
> + case RTE_INTR_HANDLE_VFIO_LEGACY:
> + ev.data.fd = intr_handle.queue_fd[queue_id];
> + break;
>
Accepted.
>
> > +#endif
> > + default:
> > + break;
> > + close(pfd);
> > + return -1;
>
> Here Steve has pointed out, but indentation should be a issue.
>
To be fixed in V2.
> > + }
> > +
> > + if (epoll_ctl(pfd, EPOLL_CTL_ADD, ev.data.fd, &ev) < 0) {
> > + RTE_LOG(ERR, EAL, "Error adding fd %d epoll_ctl, %s\n",
> > + intr_handle.queue_fd[queue_id],
> > strerror(errno));
> > + } else
> > + numfds++;
> > +
> > + rte_spinlock_unlock(&intr_lock);
> > + /* serve the interrupt */
> > + eal_intr_handle_rx_interrupts(port_id, pfd, numfds);
> > +
> > + /**
> > + * when we return, we need to rebuild the
> > + * list of fds to monitor.
> > + */
> > + close(pfd);
> > +
> > + return 0;
> > +}
> > diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
> > b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
> > index 20e0977..63d0ae8 100644
> > --- a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
> > +++ b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
> > @@ -283,7 +283,6 @@ pci_vfio_setup_interrupts(struct rte_pci_device *dev,
> > int vfio_dev_fd)
> >
> > dev->intr_handle.fd = fd;
> > dev->intr_handle.vfio_dev_fd = vfio_dev_fd;
> > -
> > switch (i) {
> > case VFIO_PCI_MSIX_IRQ_INDEX:
> > internal_config.vfio_intr_mode = RTE_INTR_MODE_MSIX;
> > @@ -302,6 +301,16 @@ pci_vfio_setup_interrupts(struct rte_pci_device *dev,
> > int vfio_dev_fd)
> > return -1;
> > }
> >
> > + for (i = 0; i < VFIO_MAX_QUEUE_ID; i++) {
> > + fd = eventfd(0, 0);
> > + if (fd < 0) {
> > + RTE_LOG(ERR, EAL, " cannot set up eventfd, "
> > + "error %i (%s)\n", errno,
> > strerror(errno));
> > + return -1;
> > + }
> > + dev->intr_handle.queue_fd[i] = fd;
> > + }
> > +
> > return 0;
> > }
> >
> > diff --git a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
> b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
> > index 23eafd9..c6982cf 100644
> > --- a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
> > +++ b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
> > @@ -38,6 +38,8 @@
> > #ifndef _RTE_LINUXAPP_INTERRUPTS_H_
> > #define _RTE_LINUXAPP_INTERRUPTS_H_
> >
> > +#define VFIO_MAX_QUEUE_ID 32
> > +
> > enum rte_intr_handle_type {
> > RTE_INTR_HANDLE_UNKNOWN = 0,
> > RTE_INTR_HANDLE_UIO, /**< uio device handle */
> > @@ -52,6 +54,8 @@ enum rte_intr_handle_type {
> > struct rte_intr_handle {
> > int vfio_dev_fd; /**< VFIO device file descriptor */
> > int fd; /**< file descriptor */
> > + int max_intr; /**< max interrupt requested */
> > + int queue_fd[VFIO_MAX_QUEUE_ID]; /**< rx and tx queue interrupt file
> > descriptor */
> > enum rte_intr_handle_type type; /**< handle type */
> > };
> >
