eal: add ack interrupt API

Add new ack interrupt API to avoid using
VFIO_IRQ_SET_ACTION_TRIGGER(rte_intr_enable()) for
acking interrupt purpose for VFIO based interrupt handlers.
This implementation is specific to Linux.

Using rte_intr_enable() for acking interrupt has below issues

 * Time consuming to do for every interrupt received as it will
   free_irq() followed by request_irq() and all other initializations
 * A race condition because of a window between free_irq() and
   request_irq() with packet reception still on and device still
   enabled and would throw warning messages like below.
   [158764.159833] do_IRQ: 9.34 No irq handler for vector

In this patch, rte_intr_ack() is a no-op for VFIO_MSIX/VFIO_MSI interrupts
as they are edge triggered and kernel would not mask the interrupt before
delivering the event to userspace and we don't need to ack.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Tested-by: Shahed Shaikh <shshaikh@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>

diff --git a/lib/librte_eal/common/include/rte_interrupts.h b/lib/librte_eal/common/include/rte_interrupts.h
index c1e912c..e3b406a 100644 (file)
--- a/lib/librte_eal/common/include/rte_interrupts.h
+++ b/lib/librte_eal/common/include/rte_interrupts.h
@@ -118,6 +118,26 @@ int rte_intr_enable(const struct rte_intr_handle *intr_handle);
  */
 int rte_intr_disable(const struct rte_intr_handle *intr_handle);
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * It acknowledges an interrupt raised for the specified handle.
+ *
+ * This function should be called at the end of each interrupt handler either
+ * from application or driver, so that currently raised interrupt is acked and
+ * further new interrupts are raised.
+ *
+ * @param intr_handle
+ *  pointer to the interrupt handle.
+ *
+ * @return
+ *  - On success, zero.
+ *  - On failure, a negative value.
+ */
+__rte_experimental
+int rte_intr_ack(const struct rte_intr_handle *intr_handle);
+
 #ifdef __cplusplus
 }
 #endif

diff --git a/lib/librte_eal/freebsd/eal/eal_interrupts.c b/lib/librte_eal/freebsd/eal/eal_interrupts.c
index 10375bd..f6831b7 100644 (file)
--- a/lib/librte_eal/freebsd/eal/eal_interrupts.c
+++ b/lib/librte_eal/freebsd/eal/eal_interrupts.c
@@ -387,6 +387,15 @@ rte_intr_disable(const struct rte_intr_handle *intr_handle)
        return 0;
 }
 
+int
+rte_intr_ack(const struct rte_intr_handle *intr_handle)
+{
+       if (intr_handle && intr_handle->type == RTE_INTR_HANDLE_VDEV)
+               return 0;
+
+       return -1;
+}
+
 static void
 eal_intr_process_interrupts(struct kevent *events, int nfds)
 {

diff --git a/lib/librte_eal/linux/eal/eal_interrupts.c b/lib/librte_eal/linux/eal/eal_interrupts.c
index 79ad5e8..1955324 100644 (file)
--- a/lib/librte_eal/linux/eal/eal_interrupts.c
+++ b/lib/librte_eal/linux/eal/eal_interrupts.c
@@ -197,6 +197,28 @@ vfio_disable_intx(const struct rte_intr_handle *intr_handle) {
        return 0;
 }
 
+/* unmask/ack legacy (INTx) interrupts */
+static int
+vfio_ack_intx(const struct rte_intr_handle *intr_handle)
+{
+       struct vfio_irq_set irq_set;
+
+       /* unmask INTx */
+       memset(&irq_set, 0, sizeof(irq_set));
+       irq_set.argsz = sizeof(irq_set);
+       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;
+
+       if (ioctl(intr_handle->vfio_dev_fd, VFIO_DEVICE_SET_IRQS, &irq_set)) {
+               RTE_LOG(ERR, EAL, "Error unmasking INTx interrupts for fd %d\n",
+                       intr_handle->fd);
+               return -1;
+       }
+       return 0;
+}
+
 /* enable MSI interrupts */
 static int
 vfio_enable_msi(const struct rte_intr_handle *intr_handle) {
@@ -693,6 +715,66 @@ rte_intr_enable(const struct rte_intr_handle *intr_handle)
        return 0;
 }
 
+/**
+ * PMD generally calls this function at the end of its IRQ callback.
+ * Internally, it unmasks the interrupt if possible.
+ *
+ * For INTx, unmasking is required as the interrupt is auto-masked prior to
+ * invoking callback.
+ *
+ * For MSI/MSI-X, unmasking is typically not needed as the interrupt is not
+ * auto-masked. In fact, for interrupt handle types VFIO_MSIX and VFIO_MSI,
+ * this function is no-op.
+ */
+int
+rte_intr_ack(const struct rte_intr_handle *intr_handle)
+{
+       if (intr_handle && intr_handle->type == RTE_INTR_HANDLE_VDEV)
+               return 0;
+
+       if (!intr_handle || intr_handle->fd < 0 || intr_handle->uio_cfg_fd < 0)
+               return -1;
+
+       switch (intr_handle->type) {
+       /* Both acking and enabling are same for UIO */
+       case RTE_INTR_HANDLE_UIO:
+               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;
+#ifdef VFIO_PRESENT
+       /* VFIO MSI* is implicitly acked unlike INTx, nothing to do */
+       case RTE_INTR_HANDLE_VFIO_MSIX:
+       case RTE_INTR_HANDLE_VFIO_MSI:
+               return 0;
+       case RTE_INTR_HANDLE_VFIO_LEGACY:
+               if (vfio_ack_intx(intr_handle))
+                       return -1;
+               break;
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+       case RTE_INTR_HANDLE_VFIO_REQ:
+               return -1;
+#endif
+#endif
+       /* not used at this moment */
+       case RTE_INTR_HANDLE_DEV_EVENT:
+               return -1;
+       /* unknown handle type */
+       default:
+               RTE_LOG(ERR, EAL, "Unknown handle type of fd %d\n",
+                       intr_handle->fd);
+               return -1;
+       }
+
+       return 0;
+}
+
 int
 rte_intr_disable(const struct rte_intr_handle *intr_handle)
 {

diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index 1892d9e..2344877 100644 (file)
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -403,6 +403,7 @@ EXPERIMENTAL {
        rte_realloc_socket;
 
        # added in 19.08
+       rte_intr_ack;
        rte_lcore_cpuset;
        rte_lcore_to_cpu_id;
        rte_mcfg_timer_lock;