@@ -327,7 +327,6 @@ Below is a script using namespaces and veth peer::
Limitations/Known Issues
------------------------
-#. Device's numa ID is always 0, need a way to find numa id from a netdev.
#. No QoS support because AF_XDP netdev by-pass the Linux TC layer. A possible
work-around is to use OpenFlow meter action.
#. Most of the tests are done using i40e single port. Multiple ports and
@@ -703,17 +703,6 @@ out:
return err;
}
-int
-netdev_afxdp_get_numa_id(const struct netdev *netdev)
-{
- /* FIXME: Get netdev's PCIe device ID, then find
- * its NUMA node id.
- */
- VLOG_INFO("FIXME: Device %s always use numa id 0.",
- netdev_get_name(netdev));
- return 0;
-}
-
static void
xsk_remove_xdp_program(uint32_t ifindex, enum afxdp_mode mode)
{
@@ -61,7 +61,6 @@ int netdev_afxdp_batch_send(struct netdev *netdev_, int qid,
int netdev_afxdp_set_config(struct netdev *netdev, const struct smap *args,
char **errp);
int netdev_afxdp_get_config(const struct netdev *netdev, struct smap *args);
-int netdev_afxdp_get_numa_id(const struct netdev *netdev);
int netdev_afxdp_get_stats(const struct netdev *netdev_,
struct netdev_stats *stats);
int netdev_afxdp_get_custom_stats(const struct netdev *netdev,
@@ -96,6 +96,8 @@ struct netdev_linux {
/* LAG information. */
bool is_lag_master; /* True if the netdev is a LAG master. */
+ int numa_id; /* NUMA node id. */
+
#ifdef HAVE_AF_XDP
/* AF_XDP information. */
struct xsk_socket_info **xsks;
@@ -236,6 +236,7 @@ enum {
VALID_VPORT_STAT_ERROR = 1 << 5,
VALID_DRVINFO = 1 << 6,
VALID_FEATURES = 1 << 7,
+ VALID_NUMA_ID = 1 << 8,
};
struct linux_lag_slave {
@@ -820,9 +821,9 @@ netdev_linux_update__(struct netdev_linux *dev,
{
if (rtnetlink_type_is_rtnlgrp_link(change->nlmsg_type)) {
if (change->nlmsg_type == RTM_NEWLINK) {
- /* Keep drv-info, and ip addresses. */
+ /* Keep drv-info, ip addresses, and NUMA id. */
netdev_linux_changed(dev, change->ifi_flags,
- VALID_DRVINFO | VALID_IN);
+ VALID_DRVINFO | VALID_IN | VALID_NUMA_ID);
/* Update netdev from rtnl-change msg. */
if (change->mtu) {
@@ -1391,6 +1392,66 @@ netdev_linux_tap_batch_send(struct netdev *netdev_,
return 0;
}
+static int
+netdev_linux_get_numa_id__(struct netdev_linux *netdev)
+ OVS_REQUIRES(netdev->mutex)
+{
+ char *numa_node_path;
+ const char *name;
+ int node_id;
+ FILE *stream;
+
+ if (netdev->cache_valid & VALID_NUMA_ID) {
+ return netdev->numa_id;
+ }
+
+ netdev->numa_id = 0;
+ netdev->cache_valid |= VALID_NUMA_ID;
+
+ name = netdev_get_name(&netdev->up);
+ if (strpbrk(name, "/\\")) {
+ VLOG_ERR_RL(&rl, "\"%s\" is not a valid name for a port. "
+ "A valid name must not include '/' or '\\'."
+ "Using numa_id 0", name);
+ return 0;
+ }
+
+ numa_node_path = xasprintf("/sys/class/net/%s/device/numa_node", name);
+
+ stream = fopen(numa_node_path, "r");
+ if (!stream) {
+ /* Virtual device does not have this info. */
+ VLOG_INFO_RL(&rl, "%s: Can't open '%s': %s, using numa_id 0",
+ name, numa_node_path, ovs_strerror(errno));
+ free(numa_node_path);
+ return 0;
+ }
+
+ if (fscanf(stream, "%d", &node_id) != 1
+ || !ovs_numa_numa_id_is_valid(node_id)) {
+ VLOG_WARN_RL(&rl, "%s: Can't detect NUMA node, using numa_id 0", name);
+ node_id = 0;
+ }
+
+ netdev->numa_id = node_id;
+ fclose(stream);
+ free(numa_node_path);
+ return node_id;
+}
+
+static int OVS_UNUSED
+netdev_linux_get_numa_id(const struct netdev *netdev_)
+{
+ struct netdev_linux *netdev = netdev_linux_cast(netdev_);
+ int numa_id;
+
+ ovs_mutex_lock(&netdev->mutex);
+ numa_id = netdev_linux_get_numa_id__(netdev);
+ ovs_mutex_unlock(&netdev->mutex);
+
+ return numa_id;
+}
+
/* Sends 'batch' on 'netdev'. Returns 0 if successful, otherwise a positive
* errno value. Returns EAGAIN without blocking if the packet cannot be queued
* immediately. Returns EMSGSIZE if a partial packet was transmitted or if
@@ -3310,7 +3371,7 @@ const struct netdev_class netdev_afxdp_class = {
.set_config = netdev_afxdp_set_config,
.get_config = netdev_afxdp_get_config,
.reconfigure = netdev_afxdp_reconfigure,
- .get_numa_id = netdev_afxdp_get_numa_id,
+ .get_numa_id = netdev_linux_get_numa_id,
.send = netdev_afxdp_batch_send,
.rxq_construct = netdev_afxdp_rxq_construct,
.rxq_destruct = netdev_afxdp_rxq_destruct,