#include <sys/epoll.h>
#include <sys/signalfd.h>
#include <sys/ioctl.h>
+#include <sys/eventfd.h>
#include <rte_common.h>
#include <rte_interrupts.h>
#include "eal_private.h"
#include "eal_vfio.h"
+#include "eal_thread.h"
#define EAL_INTR_EPOLL_WAIT_FOREVER (-1)
+#define NB_OTHER_INTR 1
static RTE_DEFINE_PER_LCORE(int, _epfd) = -1; /**< epoll fd per thread */
#ifdef VFIO_PRESENT
#define IRQ_SET_BUF_LEN (sizeof(struct vfio_irq_set) + sizeof(int))
+/* irq set buffer length for queue interrupts and LSC interrupt */
+#define MSIX_IRQ_SET_BUF_LEN (sizeof(struct vfio_irq_set) + \
+ sizeof(int) * (RTE_MAX_RXTX_INTR_VEC_ID + 1))
/* enable legacy (INTx) interrupts */
static int
return 0;
}
-/* enable MSI-X interrupts */
+/* enable MSI interrupts */
static int
vfio_enable_msi(struct rte_intr_handle *intr_handle) {
int len, ret;
intr_handle->fd);
return -1;
}
-
- /* manually trigger interrupt to enable it */
- memset(irq_set, 0, len);
- len = sizeof(struct vfio_irq_set);
- irq_set->argsz = len;
- irq_set->count = 1;
- irq_set->flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER;
- irq_set->index = VFIO_PCI_MSI_IRQ_INDEX;
- irq_set->start = 0;
-
- ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set);
-
- if (ret) {
- RTE_LOG(ERR, EAL, "Error triggering MSI interrupts for fd %d\n",
- intr_handle->fd);
- return -1;
- }
return 0;
}
-/* disable MSI-X interrupts */
+/* disable MSI interrupts */
static int
vfio_disable_msi(struct rte_intr_handle *intr_handle) {
struct vfio_irq_set *irq_set;
static int
vfio_enable_msix(struct rte_intr_handle *intr_handle) {
int len, ret;
- char irq_set_buf[IRQ_SET_BUF_LEN];
+ char irq_set_buf[MSIX_IRQ_SET_BUF_LEN];
struct vfio_irq_set *irq_set;
int *fd_ptr;
irq_set = (struct vfio_irq_set *) irq_set_buf;
irq_set->argsz = len;
- irq_set->count = 1;
+ if (!intr_handle->max_intr)
+ intr_handle->max_intr = 1;
+ else if (intr_handle->max_intr > RTE_MAX_RXTX_INTR_VEC_ID)
+ intr_handle->max_intr = RTE_MAX_RXTX_INTR_VEC_ID + 1;
+
+ irq_set->count = intr_handle->max_intr;
irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX;
irq_set->start = 0;
fd_ptr = (int *) &irq_set->data;
- *fd_ptr = intr_handle->fd;
+ memcpy(fd_ptr, intr_handle->efds, sizeof(intr_handle->efds));
+ fd_ptr[intr_handle->max_intr - 1] = intr_handle->fd;
ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set);
return -1;
}
- /* manually trigger interrupt to enable it */
- memset(irq_set, 0, len);
- len = sizeof(struct vfio_irq_set);
- irq_set->argsz = len;
- irq_set->count = 1;
- irq_set->flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER;
- irq_set->index = VFIO_PCI_MSIX_IRQ_INDEX;
- irq_set->start = 0;
-
- ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set);
-
- if (ret) {
- RTE_LOG(ERR, EAL, "Error triggering MSI-X interrupts for fd %d\n",
- intr_handle->fd);
- return -1;
- }
return 0;
}
static int
vfio_disable_msix(struct rte_intr_handle *intr_handle) {
struct vfio_irq_set *irq_set;
- char irq_set_buf[IRQ_SET_BUF_LEN];
+ char irq_set_buf[MSIX_IRQ_SET_BUF_LEN];
int len, ret;
len = sizeof(struct vfio_irq_set);
/* set the length to be read dor different handle type */
switch (src->intr_handle.type) {
case RTE_INTR_HANDLE_UIO:
+ case RTE_INTR_HANDLE_UIO_INTX:
bytes_read = sizeof(buf.uio_intr_count);
break;
case RTE_INTR_HANDLE_ALARM:
bytes_read = sizeof(buf.vfio_intr_count);
break;
#endif
+ case RTE_INTR_HANDLE_EXT:
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) {
- if (errno == EINTR || errno == EWOULDBLOCK)
- continue;
-
- 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);
+ if (src->intr_handle.type != RTE_INTR_HANDLE_EXT) {
+ /**
+ * 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) {
+ if (errno == EINTR || errno == EWOULDBLOCK)
+ continue;
+
+ 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);
+ }
/* grab a lock, again to call callbacks and update status. */
rte_spinlock_lock(&intr_lock);
int
rte_eal_intr_init(void)
{
- int ret = 0;
+ int ret = 0, ret_1 = 0;
+ char thread_name[RTE_MAX_THREAD_NAME_LEN];
/* init the global interrupt source head */
TAILQ_INIT(&intr_sources);
/* create the host thread to wait/handle the interrupt */
ret = pthread_create(&intr_thread, NULL,
eal_intr_thread_main, NULL);
- if (ret != 0)
+ if (ret != 0) {
RTE_LOG(ERR, EAL,
"Failed to create thread for interrupt handling\n");
+ } else {
+ /* Set thread_name for aid in debugging. */
+ snprintf(thread_name, RTE_MAX_THREAD_NAME_LEN,
+ "eal-intr-thread");
+ ret_1 = pthread_setname_np(intr_thread, thread_name);
+ if (ret_1 != 0)
+ RTE_LOG(ERR, EAL,
+ "Failed to set thread name for interrupt handling\n");
+ }
return -ret;
}
+static void
+eal_intr_proc_rxtx_intr(int fd, const struct rte_intr_handle *intr_handle)
+{
+ union rte_intr_read_buffer buf;
+ int bytes_read = 1;
+
+ switch (intr_handle->type) {
+ case RTE_INTR_HANDLE_UIO:
+ case RTE_INTR_HANDLE_UIO_INTX:
+ bytes_read = sizeof(buf.uio_intr_count);
+ 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;
+ RTE_LOG(INFO, EAL, "unexpected intr type\n");
+ break;
+ }
+
+ /**
+ * read out to clear the ready-to-be-read flag
+ * for epoll_wait.
+ */
+ do {
+ bytes_read = read(fd, &buf, bytes_read);
+ if (bytes_read < 0) {
+ if (errno == EINTR || errno == EWOULDBLOCK ||
+ errno == EAGAIN)
+ continue;
+ RTE_LOG(ERR, EAL,
+ "Error reading from fd %d: %s\n",
+ fd, strerror(errno));
+ } else if (bytes_read == 0)
+ RTE_LOG(ERR, EAL, "Read nothing from fd %d\n", fd);
+ return;
+ } while (1);
+}
+
static int
eal_epoll_process_event(struct epoll_event *evs, unsigned int n,
struct rte_epoll_event *events)
strerror(errno));
rc = -1;
break;
+ } else {
+ /* rc == 0, epoll_wait timed out */
+ break;
}
}
return 0;
}
+
+int
+rte_intr_rx_ctl(struct rte_intr_handle *intr_handle, int epfd,
+ int op, unsigned int vec, void *data)
+{
+ struct rte_epoll_event *rev;
+ struct rte_epoll_data *epdata;
+ int epfd_op;
+ int rc = 0;
+
+ if (!intr_handle || intr_handle->nb_efd == 0 ||
+ vec >= intr_handle->nb_efd) {
+ RTE_LOG(ERR, EAL, "Wrong intr vector number.\n");
+ return -EPERM;
+ }
+
+ switch (op) {
+ case RTE_INTR_EVENT_ADD:
+ epfd_op = EPOLL_CTL_ADD;
+ rev = &intr_handle->elist[vec];
+ if (rev->status != RTE_EPOLL_INVALID) {
+ RTE_LOG(INFO, EAL, "Event already been added.\n");
+ return -EEXIST;
+ }
+
+ /* attach to intr vector fd */
+ epdata = &rev->epdata;
+ epdata->event = EPOLLIN | EPOLLPRI | EPOLLET;
+ epdata->data = data;
+ epdata->cb_fun = (rte_intr_event_cb_t)eal_intr_proc_rxtx_intr;
+ epdata->cb_arg = (void *)intr_handle;
+ rc = rte_epoll_ctl(epfd, epfd_op, intr_handle->efds[vec], rev);
+ if (!rc)
+ RTE_LOG(DEBUG, EAL,
+ "efd %d associated with vec %d added on epfd %d"
+ "\n", rev->fd, vec, epfd);
+ else
+ rc = -EPERM;
+ break;
+ case RTE_INTR_EVENT_DEL:
+ epfd_op = EPOLL_CTL_DEL;
+ rev = &intr_handle->elist[vec];
+ if (rev->status == RTE_EPOLL_INVALID) {
+ RTE_LOG(INFO, EAL, "Event does not exist.\n");
+ return -EPERM;
+ }
+
+ rc = rte_epoll_ctl(rev->epfd, epfd_op, rev->fd, rev);
+ if (rc)
+ rc = -EPERM;
+ break;
+ default:
+ RTE_LOG(ERR, EAL, "event op type mismatch\n");
+ rc = -EPERM;
+ }
+
+ return rc;
+}
+
+int
+rte_intr_efd_enable(struct rte_intr_handle *intr_handle, uint32_t nb_efd)
+{
+ uint32_t i;
+ int fd;
+ uint32_t n = RTE_MIN(nb_efd, (uint32_t)RTE_MAX_RXTX_INTR_VEC_ID);
+
+ if (intr_handle->type == RTE_INTR_HANDLE_VFIO_MSIX) {
+ for (i = 0; i < n; i++) {
+ fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
+ if (fd < 0) {
+ RTE_LOG(ERR, EAL,
+ "can't setup eventfd, error %i (%s)\n",
+ errno, strerror(errno));
+ return -1;
+ }
+ intr_handle->efds[i] = fd;
+ }
+ intr_handle->nb_efd = n;
+ intr_handle->max_intr = NB_OTHER_INTR + n;
+ } else {
+ intr_handle->efds[0] = intr_handle->fd;
+ intr_handle->nb_efd = RTE_MIN(nb_efd, 1U);
+ intr_handle->max_intr = NB_OTHER_INTR;
+ }
+
+ return 0;
+}
+
+void
+rte_intr_efd_disable(struct rte_intr_handle *intr_handle)
+{
+ uint32_t i;
+ struct rte_epoll_event *rev;
+
+ for (i = 0; i < intr_handle->nb_efd; i++) {
+ rev = &intr_handle->elist[i];
+ if (rev->status == RTE_EPOLL_INVALID)
+ continue;
+ if (rte_epoll_ctl(rev->epfd, EPOLL_CTL_DEL, rev->fd, rev)) {
+ /* force free if the entry valid */
+ eal_epoll_data_safe_free(rev);
+ rev->status = RTE_EPOLL_INVALID;
+ }
+ }
+
+ if (intr_handle->max_intr > intr_handle->nb_efd) {
+ for (i = 0; i < intr_handle->nb_efd; i++)
+ close(intr_handle->efds[i]);
+ }
+ intr_handle->nb_efd = 0;
+ intr_handle->max_intr = 0;
+}
+
+int
+rte_intr_dp_is_en(struct rte_intr_handle *intr_handle)
+{
+ return !(!intr_handle->nb_efd);
+}
+
+int
+rte_intr_allow_others(struct rte_intr_handle *intr_handle)
+{
+ return !!(intr_handle->max_intr - intr_handle->nb_efd);
+}
git.droids-corp.org / dpdk.git / blobdiff