2
0
mirror of https://github.com/openvswitch/ovs synced 2025-08-22 01:51:26 +00:00

netdev-dpdk: Check pending reset when adding device.

When a device reset interrupt event (RTE_ETH_EVENT_INTR_RESET)
is detected for a DPDK device added to OVS, a device reset is
performed.

If a device reset interrupt event is detected for a device before
it is added to OVS, device reset is not called.

If that device is later attempted to be added to OVS, it may fail
while being configured if it is still pending a reset as pending
reset is not checked when adding a device.

A simple way to force a reset event from the ice driver for an
iavf device is to set the mac address after binding iavf dev to
vfio but before adding to OVS. (note: should not be set like this
in normal case). e.g.

$ echo 2 > /sys/class/net/ens3f0/device/sriov_numvfs
$ ./devbind.py -b vfio-pci 0000:d8:01.1
$ ip link set ens3f0 vf 1 mac 26🆎e6:6f:79:4d
$ ovs-vsctl add-port br0 dpdk0 -- set Interface dpdk0 type=dpdk \
      options:dpdk-devargs=0000:d8:01.1

|dpdk|ERR|Port1 dev_configure = -1
|netdev_dpdk|WARN|Interface dpdk0 eth_dev setup error
    Operation not permitted
|netdev_dpdk|ERR|Interface dpdk0(rxq:1 txq:5 lsc interrupt mode:false)
    configure error: Operation not permitted
|dpif_netdev|ERR|Failed to set interface dpdk0 new configuration

Add a check if there was any previous device reset interrupt events
when a device is added to OVS. If there was, perform the reset
before continuing with the rest of the configuration.

netdev_dpdk_pending_reset[] already tracks device reset interrupt
events for all devices, so it can be reused to check if there is a
reset needed during configuration of newly added devices. By extending
it's usage, dev->reset_needed is no longer needed.

Fixes: 3eb91a8d1b9a ("netdev-dpdk: Trigger port reconfiguration in main thread for resets.")
Reviewed-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Kevin Traynor <ktraynor@redhat.com>
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
This commit is contained in:
Kevin Traynor 2024-06-12 15:32:55 +01:00 committed by Ilya Maximets
parent 4811849449
commit 639fcf2005

View File

@ -464,9 +464,8 @@ struct netdev_dpdk {
bool attached;
/* If true, rte_eth_dev_start() was successfully called */
bool started;
bool reset_needed;
/* 1 pad byte here. */
struct eth_addr hwaddr;
/* 2 pad bytes here. */
int mtu;
int socket_id;
int buf_size;
@ -1531,7 +1530,6 @@ common_construct(struct netdev *netdev, dpdk_port_t port_no,
dev->virtio_features_state = OVS_VIRTIO_F_CLEAN;
dev->attached = false;
dev->started = false;
dev->reset_needed = false;
ovsrcu_init(&dev->qos_conf, NULL);
@ -2154,13 +2152,11 @@ netdev_dpdk_run(const struct netdev_class *netdev_class OVS_UNUSED)
if (!pending_reset) {
continue;
}
atomic_store_relaxed(&netdev_dpdk_pending_reset[port_id], false);
ovs_mutex_lock(&dpdk_mutex);
dev = netdev_dpdk_lookup_by_port_id(port_id);
if (dev) {
ovs_mutex_lock(&dev->mutex);
dev->reset_needed = true;
netdev_request_reconfigure(&dev->up);
VLOG_DBG_RL(&rl, "%s: Device reset requested.",
netdev_get_name(&dev->up));
@ -6083,6 +6079,7 @@ static int
netdev_dpdk_reconfigure(struct netdev *netdev)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
bool pending_reset;
bool try_rx_steer;
int err = 0;
@ -6094,6 +6091,9 @@ netdev_dpdk_reconfigure(struct netdev *netdev)
dev->requested_n_rxq += 1;
}
atomic_read_relaxed(&netdev_dpdk_pending_reset[dev->port_id],
&pending_reset);
if (netdev->n_txq == dev->requested_n_txq
&& netdev->n_rxq == dev->requested_n_rxq
&& dev->rx_steer_flags == dev->requested_rx_steer_flags
@ -6103,7 +6103,7 @@ netdev_dpdk_reconfigure(struct netdev *netdev)
&& dev->txq_size == dev->requested_txq_size
&& eth_addr_equals(dev->hwaddr, dev->requested_hwaddr)
&& dev->socket_id == dev->requested_socket_id
&& dev->started && !dev->reset_needed) {
&& dev->started && !pending_reset) {
/* Reconfiguration is unnecessary */
goto out;
@ -6112,10 +6112,14 @@ netdev_dpdk_reconfigure(struct netdev *netdev)
retry:
dpdk_rx_steer_unconfigure(dev);
if (dev->reset_needed) {
if (pending_reset) {
/*
* Set false before reset to avoid missing a new reset interrupt event
* in a race with event callback.
*/
atomic_store_relaxed(&netdev_dpdk_pending_reset[dev->port_id], false);
rte_eth_dev_reset(dev->port_id);
if_notifier_manual_report();
dev->reset_needed = false;
} else {
rte_eth_dev_stop(dev->port_id);
}