[dpdk-dev,v2,1/4] net/ixgbevf: unregister irq handler when other interrupts
Checks
Commit Message
From: Tonghao Zhang <zhangtonghao@didichuxing.com>
When we bind the ixgbe VF (e.g 82599 card) to igb_uio and enable the
rx-interrupt, there will be more than one epoll_wait on intr_handle.fd.
One is in "eal-intr-thread" thread, and the others are in the thread
which call the "rte_epoll_wait". The problem is that sometiems
"eal-intr-thread" thread will process the rx interrupt, and rte_epoll_wait
can’t get the event any more, and the packets may be lost.
We should unregister the status interrupt handler in "eal-intr-thread"
thread and the ixgbe is in the same case.
Signed-off-by: Tonghao Zhang <zhangtonghao@didichuxing.com>
---
drivers/net/ixgbe/ixgbe_ethdev.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
Comments
On 10/26/2017 7:04 AM, xiangxia.m.yue@gmail.com wrote:
> From: Tonghao Zhang <zhangtonghao@didichuxing.com>
>
> When we bind the ixgbe VF (e.g 82599 card) to igb_uio and enable the
> rx-interrupt, there will be more than one epoll_wait on intr_handle.fd.
> One is in "eal-intr-thread" thread, and the others are in the thread
> which call the "rte_epoll_wait". The problem is that sometiems
> "eal-intr-thread" thread will process the rx interrupt, and rte_epoll_wait
> can’t get the event any more, and the packets may be lost.
>
> We should unregister the status interrupt handler in "eal-intr-thread"
> thread and the ixgbe is in the same case.
>
> Signed-off-by: Tonghao Zhang <zhangtonghao@didichuxing.com>
Thanks for the patches!
We are very close to 17.11 release and only fix patches are considered at this
phase, this patchset will be evaluated for next release.
Thanks,
ferruh
@@ -5070,6 +5070,15 @@ static int ixgbevf_dev_xstats_get_names(__rte_unused struct rte_eth_dev *dev,
}
ixgbevf_configure_msix(dev);
+ if (!rte_intr_allow_others(intr_handle)) {
+ rte_intr_callback_unregister(intr_handle,
+ ixgbevf_dev_interrupt_handler,
+ dev);
+ if (dev->data->dev_conf.intr_conf.lsc != 0)
+ PMD_INIT_LOG(INFO, "lsc won't enable because of"
+ " no intr multiplex");
+ }
+
/* When a VF port is bound to VFIO-PCI, only miscellaneous interrupt
* is mapped to VFIO vector 0 in eth_ixgbevf_dev_init( ).
* If previous VFIO interrupt mapping setting in eth_ixgbevf_dev_init( )
@@ -5112,6 +5121,12 @@ static int ixgbevf_dev_xstats_get_names(__rte_unused struct rte_eth_dev *dev,
ixgbe_dev_clear_queues(dev);
+ if (!rte_intr_allow_others(intr_handle))
+ /* resume to the default handler */
+ rte_intr_callback_register(intr_handle,
+ ixgbevf_dev_interrupt_handler,
+ (void *)dev);
+
/* Clean datapath event and queue/vec mapping */
rte_intr_efd_disable(intr_handle);
if (intr_handle->intr_vec != NULL) {