/*-
* BSD LICENSE
- *
- * Copyright(c) 2010-2013 Intel Corporation. All rights reserved.
+ *
+ * Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
* All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
* are met:
- *
- * * Redistributions of source code must retain the above copyright
+ *
+ * * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
* distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
*/
#include <stdio.h>
#include <stdlib.h>
#include <pthread.h>
#include <sys/queue.h>
-#include <malloc.h>
#include <stdarg.h>
#include <unistd.h>
#include <string.h>
#include <inttypes.h>
#include <sys/epoll.h>
#include <sys/signalfd.h>
+#include <sys/ioctl.h>
#include <rte_common.h>
#include <rte_interrupts.h>
#include <rte_memory.h>
#include <rte_memzone.h>
#include <rte_launch.h>
-#include <rte_tailq.h>
#include <rte_eal.h>
#include <rte_per_lcore.h>
#include <rte_lcore.h>
#include <rte_spinlock.h>
#include "eal_private.h"
+#include "eal_vfio.h"
#define EAL_INTR_EPOLL_WAIT_FOREVER (-1)
+static RTE_DEFINE_PER_LCORE(int, _epfd) = -1; /**< epoll fd per thread */
+
/**
* union for pipe fds.
*/
*/
union rte_intr_read_buffer {
int uio_intr_count; /* for uio device */
+#ifdef VFIO_PRESENT
+ uint64_t vfio_intr_count; /* for vfio device */
+#endif
uint64_t timerfd_num; /* for timerfd */
char charbuf[16]; /* for others */
};
/* interrupt handling thread */
static pthread_t intr_thread;
+/* VFIO interrupts */
+#ifdef VFIO_PRESENT
+
+#define IRQ_SET_BUF_LEN (sizeof(struct vfio_irq_set) + sizeof(int))
+
+/* enable legacy (INTx) interrupts */
+static int
+vfio_enable_intx(struct rte_intr_handle *intr_handle) {
+ struct vfio_irq_set *irq_set;
+ char irq_set_buf[IRQ_SET_BUF_LEN];
+ int len, ret;
+ int *fd_ptr;
+
+ len = sizeof(irq_set_buf);
+
+ /* enable INTx */
+ irq_set = (struct vfio_irq_set *) irq_set_buf;
+ irq_set->argsz = len;
+ irq_set->count = 1;
+ irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
+ irq_set->index = VFIO_PCI_INTX_IRQ_INDEX;
+ irq_set->start = 0;
+ fd_ptr = (int *) &irq_set->data;
+ *fd_ptr = intr_handle->fd;
+
+ ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set);
+
+ if (ret) {
+ RTE_LOG(ERR, EAL, "Error enabling INTx interrupts for fd %d\n",
+ intr_handle->fd);
+ return -1;
+ }
+
+ /* unmask INTx after enabling */
+ 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_UNMASK;
+ irq_set->index = VFIO_PCI_INTX_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 unmasking INTx interrupts for fd %d\n",
+ intr_handle->fd);
+ return -1;
+ }
+ return 0;
+}
+
+/* disable legacy (INTx) interrupts */
+static int
+vfio_disable_intx(struct rte_intr_handle *intr_handle) {
+ struct vfio_irq_set *irq_set;
+ char irq_set_buf[IRQ_SET_BUF_LEN];
+ int len, ret;
+
+ len = sizeof(struct vfio_irq_set);
+
+ /* mask interrupts before disabling */
+ irq_set = (struct vfio_irq_set *) irq_set_buf;
+ irq_set->argsz = len;
+ irq_set->count = 1;
+ irq_set->flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK;
+ irq_set->index = VFIO_PCI_INTX_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 unmasking INTx interrupts for fd %d\n",
+ intr_handle->fd);
+ return -1;
+ }
+
+ /* disable INTx*/
+ memset(irq_set, 0, len);
+ irq_set->argsz = len;
+ irq_set->count = 0;
+ irq_set->flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER;
+ irq_set->index = VFIO_PCI_INTX_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 disabling INTx interrupts for fd %d\n", intr_handle->fd);
+ return -1;
+ }
+ return 0;
+}
+
+/* enable MSI-X interrupts */
+static int
+vfio_enable_msi(struct rte_intr_handle *intr_handle) {
+ int len, ret;
+ char irq_set_buf[IRQ_SET_BUF_LEN];
+ struct vfio_irq_set *irq_set;
+ int *fd_ptr;
+
+ len = sizeof(irq_set_buf);
+
+ irq_set = (struct vfio_irq_set *) irq_set_buf;
+ irq_set->argsz = len;
+ irq_set->count = 1;
+ irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
+ irq_set->index = VFIO_PCI_MSI_IRQ_INDEX;
+ irq_set->start = 0;
+ fd_ptr = (int *) &irq_set->data;
+ *fd_ptr = intr_handle->fd;
+
+ ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set);
+
+ if (ret) {
+ RTE_LOG(ERR, EAL, "Error enabling MSI interrupts for fd %d\n",
+ 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 */
+static int
+vfio_disable_msi(struct rte_intr_handle *intr_handle) {
+ struct vfio_irq_set *irq_set;
+ char irq_set_buf[IRQ_SET_BUF_LEN];
+ int len, ret;
+
+ len = sizeof(struct vfio_irq_set);
+
+ irq_set = (struct vfio_irq_set *) irq_set_buf;
+ irq_set->argsz = len;
+ irq_set->count = 0;
+ 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 disabling MSI interrupts for fd %d\n", intr_handle->fd);
+
+ return ret;
+}
+
+/* enable MSI-X interrupts */
+static int
+vfio_enable_msix(struct rte_intr_handle *intr_handle) {
+ int len, ret;
+ char irq_set_buf[IRQ_SET_BUF_LEN];
+ struct vfio_irq_set *irq_set;
+ int *fd_ptr;
+
+ len = sizeof(irq_set_buf);
+
+ irq_set = (struct vfio_irq_set *) irq_set_buf;
+ irq_set->argsz = len;
+ irq_set->count = 1;
+ 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;
+
+ ret = ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set);
+
+ if (ret) {
+ RTE_LOG(ERR, EAL, "Error enabling MSI-X interrupts for fd %d\n",
+ 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_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;
+}
+
+/* disable MSI-X interrupts */
+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];
+ int len, ret;
+
+ len = sizeof(struct vfio_irq_set);
+
+ irq_set = (struct vfio_irq_set *) irq_set_buf;
+ irq_set->argsz = len;
+ irq_set->count = 0;
+ 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 disabling MSI-X interrupts for fd %d\n", intr_handle->fd);
+
+ return ret;
+}
+#endif
+
+static int
+uio_intx_intr_disable(struct rte_intr_handle *intr_handle)
+{
+ unsigned char command_high;
+
+ /* use UIO config file descriptor for uio_pci_generic */
+ if (pread(intr_handle->uio_cfg_fd, &command_high, 1, 5) != 1) {
+ RTE_LOG(ERR, EAL,
+ "Error reading interrupts status for fd %d\n",
+ intr_handle->uio_cfg_fd);
+ return -1;
+ }
+ /* disable interrupts */
+ command_high |= 0x4;
+ if (pwrite(intr_handle->uio_cfg_fd, &command_high, 1, 5) != 1) {
+ RTE_LOG(ERR, EAL,
+ "Error disabling interrupts for fd %d\n",
+ intr_handle->uio_cfg_fd);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int
+uio_intx_intr_enable(struct rte_intr_handle *intr_handle)
+{
+ unsigned char command_high;
+
+ /* use UIO config file descriptor for uio_pci_generic */
+ if (pread(intr_handle->uio_cfg_fd, &command_high, 1, 5) != 1) {
+ RTE_LOG(ERR, EAL,
+ "Error reading interrupts status for fd %d\n",
+ intr_handle->uio_cfg_fd);
+ return -1;
+ }
+ /* enable interrupts */
+ command_high &= ~0x4;
+ if (pwrite(intr_handle->uio_cfg_fd, &command_high, 1, 5) != 1) {
+ RTE_LOG(ERR, EAL,
+ "Error enabling interrupts for fd %d\n",
+ intr_handle->uio_cfg_fd);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int
+uio_intr_disable(struct rte_intr_handle *intr_handle)
+{
+ const int value = 0;
+
+ if (write(intr_handle->fd, &value, sizeof(value)) < 0) {
+ RTE_LOG(ERR, EAL,
+ "Error disabling interrupts for fd %d (%s)\n",
+ intr_handle->fd, strerror(errno));
+ return -1;
+ }
+ return 0;
+}
+
+static int
+uio_intr_enable(struct rte_intr_handle *intr_handle)
+{
+ const int value = 1;
+
+ if (write(intr_handle->fd, &value, sizeof(value)) < 0) {
+ RTE_LOG(ERR, EAL,
+ "Error enabling interrupts for fd %d (%s)\n",
+ intr_handle->fd, strerror(errno));
+ return -1;
+ }
+ return 0;
+}
+
int
rte_intr_callback_register(struct rte_intr_handle *intr_handle,
rte_intr_callback_fn cb, void *cb_arg)
if (write(intr_pipe.writefd, "1", 1) < 0)
return -EPIPE;
- return (ret);
+ return ret;
}
int
ret = -EPIPE;
}
- return (ret);
+ return ret;
}
int
rte_intr_enable(struct rte_intr_handle *intr_handle)
{
- const int value = 1;
-
- if (!intr_handle || intr_handle->fd < 0)
+ if (!intr_handle || intr_handle->fd < 0 || intr_handle->uio_cfg_fd < 0)
return -1;
switch (intr_handle->type){
/* write to the uio fd to enable the interrupt */
case RTE_INTR_HANDLE_UIO:
- if (write(intr_handle->fd, &value, sizeof(value)) < 0) {
- RTE_LOG(ERR, EAL,
- "Error enabling interrupts for fd %d\n",
- intr_handle->fd);
+ if (uio_intr_enable(intr_handle))
+ return -1;
+ break;
+ case RTE_INTR_HANDLE_UIO_INTX:
+ if (uio_intx_intr_enable(intr_handle))
return -1;
- }
break;
/* not used at this moment */
case RTE_INTR_HANDLE_ALARM:
return -1;
- /* unkown handle type */
+#ifdef VFIO_PRESENT
+ case RTE_INTR_HANDLE_VFIO_MSIX:
+ if (vfio_enable_msix(intr_handle))
+ return -1;
+ break;
+ case RTE_INTR_HANDLE_VFIO_MSI:
+ if (vfio_enable_msi(intr_handle))
+ return -1;
+ break;
+ case RTE_INTR_HANDLE_VFIO_LEGACY:
+ if (vfio_enable_intx(intr_handle))
+ return -1;
+ break;
+#endif
+ /* unknown handle type */
default:
RTE_LOG(ERR, EAL,
"Unknown handle type of fd %d\n",
int
rte_intr_disable(struct rte_intr_handle *intr_handle)
{
- const int value = 0;
-
- if (!intr_handle || intr_handle->fd < 0)
+ if (!intr_handle || intr_handle->fd < 0 || intr_handle->uio_cfg_fd < 0)
return -1;
switch (intr_handle->type){
/* write to the uio fd to disable the interrupt */
case RTE_INTR_HANDLE_UIO:
- if (write(intr_handle->fd, &value, sizeof(value)) < 0){
- RTE_LOG(ERR, EAL,
- "Error enabling interrupts for fd %d\n",
- intr_handle->fd);
+ if (uio_intr_disable(intr_handle))
+ return -1;
+ break;
+ case RTE_INTR_HANDLE_UIO_INTX:
+ if (uio_intx_intr_disable(intr_handle))
return -1;
- }
break;
/* not used at this moment */
case RTE_INTR_HANDLE_ALARM:
return -1;
- /* unkown handle type */
+#ifdef VFIO_PRESENT
+ case RTE_INTR_HANDLE_VFIO_MSIX:
+ if (vfio_disable_msix(intr_handle))
+ return -1;
+ break;
+ case RTE_INTR_HANDLE_VFIO_MSI:
+ if (vfio_disable_msi(intr_handle))
+ return -1;
+ break;
+ case RTE_INTR_HANDLE_VFIO_LEGACY:
+ if (vfio_disable_intx(intr_handle))
+ return -1;
+ break;
+#endif
+ /* unknown handle type */
default:
RTE_LOG(ERR, EAL,
"Unknown handle type of fd %d\n",
/* set the length to be read dor different handle type */
switch (src->intr_handle.type) {
case RTE_INTR_HANDLE_UIO:
- bytes_read = 4;
+ bytes_read = sizeof(buf.uio_intr_count);
break;
case RTE_INTR_HANDLE_ALARM:
- bytes_read = sizeof(uint64_t);
+ 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;
* 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, error: %d\n", events[n].data.fd, errno);
- }
- else if (bytes_read == 0) {
- RTE_LOG(ERR, EAL,
- "Read nothing from file descriptor %d.\n",
- events[n].data.fd);
- }
+ 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);
active_cb.cb_fn(&src->intr_handle,
active_cb.cb_arg);
- /*get the lcok back. */
+ /*get the lock back. */
rte_spinlock_lock(&intr_lock);
}
}
return -ret;
}
+static int
+eal_epoll_process_event(struct epoll_event *evs, unsigned int n,
+ struct rte_epoll_event *events)
+{
+ unsigned int i, count = 0;
+ struct rte_epoll_event *rev;
+
+ for (i = 0; i < n; i++) {
+ rev = evs[i].data.ptr;
+ if (!rev || !rte_atomic32_cmpset(&rev->status, RTE_EPOLL_VALID,
+ RTE_EPOLL_EXEC))
+ continue;
+
+ events[count].status = RTE_EPOLL_VALID;
+ events[count].fd = rev->fd;
+ events[count].epfd = rev->epfd;
+ events[count].epdata.event = rev->epdata.event;
+ events[count].epdata.data = rev->epdata.data;
+ if (rev->epdata.cb_fun)
+ rev->epdata.cb_fun(rev->fd,
+ rev->epdata.cb_arg);
+
+ rte_compiler_barrier();
+ rev->status = RTE_EPOLL_VALID;
+ count++;
+ }
+ return count;
+}
+
+static inline int
+eal_init_tls_epfd(void)
+{
+ int pfd = epoll_create(255);
+
+ if (pfd < 0) {
+ RTE_LOG(ERR, EAL,
+ "Cannot create epoll instance\n");
+ return -1;
+ }
+ return pfd;
+}
+
+int
+rte_intr_tls_epfd(void)
+{
+ if (RTE_PER_LCORE(_epfd) == -1)
+ RTE_PER_LCORE(_epfd) = eal_init_tls_epfd();
+
+ return RTE_PER_LCORE(_epfd);
+}
+
+int
+rte_epoll_wait(int epfd, struct rte_epoll_event *events,
+ int maxevents, int timeout)
+{
+ struct epoll_event evs[maxevents];
+ int rc;
+
+ if (!events) {
+ RTE_LOG(ERR, EAL, "rte_epoll_event can't be NULL\n");
+ return -1;
+ }
+
+ /* using per thread epoll fd */
+ if (epfd == RTE_EPOLL_PER_THREAD)
+ epfd = rte_intr_tls_epfd();
+
+ while (1) {
+ rc = epoll_wait(epfd, evs, maxevents, timeout);
+ if (likely(rc > 0)) {
+ /* epoll_wait has at least one fd ready to read */
+ rc = eal_epoll_process_event(evs, rc, events);
+ break;
+ } else if (rc < 0) {
+ if (errno == EINTR)
+ continue;
+ /* epoll_wait fail */
+ RTE_LOG(ERR, EAL, "epoll_wait returns with fail %s\n",
+ strerror(errno));
+ rc = -1;
+ break;
+ }
+ }
+
+ return rc;
+}
+
+static inline void
+eal_epoll_data_safe_free(struct rte_epoll_event *ev)
+{
+ while (!rte_atomic32_cmpset(&ev->status, RTE_EPOLL_VALID,
+ RTE_EPOLL_INVALID))
+ while (ev->status != RTE_EPOLL_VALID)
+ rte_pause();
+ memset(&ev->epdata, 0, sizeof(ev->epdata));
+ ev->fd = -1;
+ ev->epfd = -1;
+}
+
+int
+rte_epoll_ctl(int epfd, int op, int fd,
+ struct rte_epoll_event *event)
+{
+ struct epoll_event ev;
+
+ if (!event) {
+ RTE_LOG(ERR, EAL, "rte_epoll_event can't be NULL\n");
+ return -1;
+ }
+
+ /* using per thread epoll fd */
+ if (epfd == RTE_EPOLL_PER_THREAD)
+ epfd = rte_intr_tls_epfd();
+
+ if (op == EPOLL_CTL_ADD) {
+ event->status = RTE_EPOLL_VALID;
+ event->fd = fd; /* ignore fd in event */
+ event->epfd = epfd;
+ ev.data.ptr = (void *)event;
+ }
+
+ ev.events = event->epdata.event;
+ if (epoll_ctl(epfd, op, fd, &ev) < 0) {
+ RTE_LOG(ERR, EAL, "Error op %d fd %d epoll_ctl, %s\n",
+ op, fd, strerror(errno));
+ if (op == EPOLL_CTL_ADD)
+ /* rollback status when CTL_ADD fail */
+ event->status = RTE_EPOLL_INVALID;
+ return -1;
+ }
+
+ if (op == EPOLL_CTL_DEL && event->status != RTE_EPOLL_INVALID)
+ eal_epoll_data_safe_free(event);
+
+ return 0;
+}