summaryrefslogtreecommitdiff
path: root/drivers/net/hyperv
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/hyperv')
-rw-r--r--drivers/net/hyperv/hyperv_net.h13
-rw-r--r--drivers/net/hyperv/netvsc.c57
-rw-r--r--drivers/net/hyperv/netvsc_drv.c207
-rw-r--r--drivers/net/hyperv/rndis_filter.c60
4 files changed, 245 insertions, 92 deletions
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 1a924b867b07..a32ded5b4f41 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -210,7 +210,7 @@ int netvsc_recv_callback(struct net_device *net,
void netvsc_channel_cb(void *context);
int netvsc_poll(struct napi_struct *napi, int budget);
-void rndis_set_subchannel(struct work_struct *w);
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
int rndis_filter_open(struct netvsc_device *nvdev);
int rndis_filter_close(struct netvsc_device *nvdev);
struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
@@ -873,6 +873,17 @@ struct netvsc_ethtool_stats {
unsigned long wake_queue;
};
+struct netvsc_ethtool_pcpu_stats {
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 tx_packets;
+ u64 tx_bytes;
+ u64 vf_rx_packets;
+ u64 vf_rx_bytes;
+ u64 vf_tx_packets;
+ u64 vf_tx_bytes;
+};
+
struct netvsc_vf_pcpu_stats {
u64 rx_packets;
u64 rx_bytes;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 5d5bd513847f..fe01e141c8f8 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -65,6 +65,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
VM_PKT_DATA_INBAND, 0);
}
+/* Worker to setup sub channels on initial setup
+ * Initial hotplug event occurs in softirq context
+ * and can't wait for channels.
+ */
+static void netvsc_subchan_work(struct work_struct *w)
+{
+ struct netvsc_device *nvdev =
+ container_of(w, struct netvsc_device, subchan_work);
+ struct rndis_device *rdev;
+ int i, ret;
+
+ /* Avoid deadlock with device removal already under RTNL */
+ if (!rtnl_trylock()) {
+ schedule_work(w);
+ return;
+ }
+
+ rdev = nvdev->extension;
+ if (rdev) {
+ ret = rndis_set_subchannel(rdev->ndev, nvdev);
+ if (ret == 0) {
+ netif_device_attach(rdev->ndev);
+ } else {
+ /* fallback to only primary channel */
+ for (i = 1; i < nvdev->num_chn; i++)
+ netif_napi_del(&nvdev->chan_table[i].napi);
+
+ nvdev->max_chn = 1;
+ nvdev->num_chn = 1;
+ }
+ }
+
+ rtnl_unlock();
+}
+
static struct netvsc_device *alloc_net_device(void)
{
struct netvsc_device *net_device;
@@ -81,7 +116,7 @@ static struct netvsc_device *alloc_net_device(void)
init_completion(&net_device->channel_init_wait);
init_waitqueue_head(&net_device->subchan_open);
- INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
+ INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
return net_device;
}
@@ -1168,6 +1203,9 @@ static void netvsc_send_vf(struct net_device *ndev,
net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;
+ netdev_info(ndev, "VF slot %u %s\n",
+ net_device_ctx->vf_serial,
+ net_device_ctx->vf_alloc ? "added" : "removed");
}
static void netvsc_receive_inband(struct net_device *ndev,
@@ -1239,6 +1277,7 @@ int netvsc_poll(struct napi_struct *napi, int budget)
struct hv_device *device = netvsc_channel_to_device(channel);
struct net_device *ndev = hv_get_drvdata(device);
int work_done = 0;
+ int ret;
/* If starting a new interval */
if (!nvchan->desc)
@@ -1250,16 +1289,18 @@ int netvsc_poll(struct napi_struct *napi, int budget)
nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
}
- /* If send of pending receive completions suceeded
- * and did not exhaust NAPI budget this time
- * and not doing busy poll
+ /* Send any pending receive completions */
+ ret = send_recv_completions(ndev, net_device, nvchan);
+
+ /* If it did not exhaust NAPI budget this time
+ * and not doing busy poll
* then re-enable host interrupts
- * and reschedule if ring is not empty.
+ * and reschedule if ring is not empty
+ * or sending receive completion failed.
*/
- if (send_recv_completions(ndev, net_device, nvchan) == 0 &&
- work_done < budget &&
+ if (work_done < budget &&
napi_complete_done(napi, work_done) &&
- hv_end_read(&channel->inbound) &&
+ (ret || hv_end_read(&channel->inbound)) &&
napi_schedule_prep(napi)) {
hv_begin_read(&channel->inbound);
__napi_schedule(napi);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index fe2256bf1d13..3af6d8d15233 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -29,6 +29,7 @@
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
+#include <linux/pci.h>
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/in.h>
@@ -329,7 +330,7 @@ static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb)
}
static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
- void *accel_priv,
+ struct net_device *sb_dev,
select_queue_fallback_t fallback)
{
struct net_device_context *ndc = netdev_priv(ndev);
@@ -343,9 +344,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
if (vf_ops->ndo_select_queue)
txq = vf_ops->ndo_select_queue(vf_netdev, skb,
- accel_priv, fallback);
+ sb_dev, fallback);
else
- txq = fallback(vf_netdev, skb);
+ txq = fallback(vf_netdev, skb, NULL);
/* Record the queue selected by VF so that it can be
* used for common case where VF has more queues than
@@ -905,8 +906,20 @@ static int netvsc_attach(struct net_device *ndev,
if (IS_ERR(nvdev))
return PTR_ERR(nvdev);
- /* Note: enable and attach happen when sub-channels setup */
+ if (nvdev->num_chn > 1) {
+ ret = rndis_set_subchannel(ndev, nvdev);
+
+ /* if unavailable, just proceed with one queue */
+ if (ret) {
+ nvdev->max_chn = 1;
+ nvdev->num_chn = 1;
+ }
+ }
+
+ /* In any case device is now ready */
+ netif_device_attach(ndev);
+ /* Note: enable and attach happen when sub-channels setup */
netif_carrier_off(ndev);
if (netif_running(ndev)) {
@@ -1106,6 +1119,64 @@ static void netvsc_get_vf_stats(struct net_device *net,
}
}
+static void netvsc_get_pcpu_stats(struct net_device *net,
+ struct netvsc_ethtool_pcpu_stats *pcpu_tot)
+{
+ struct net_device_context *ndev_ctx = netdev_priv(net);
+ struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
+ int i;
+
+ /* fetch percpu stats of vf */
+ for_each_possible_cpu(i) {
+ const struct netvsc_vf_pcpu_stats *stats =
+ per_cpu_ptr(ndev_ctx->vf_stats, i);
+ struct netvsc_ethtool_pcpu_stats *this_tot = &pcpu_tot[i];
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&stats->syncp);
+ this_tot->vf_rx_packets = stats->rx_packets;
+ this_tot->vf_tx_packets = stats->tx_packets;
+ this_tot->vf_rx_bytes = stats->rx_bytes;
+ this_tot->vf_tx_bytes = stats->tx_bytes;
+ } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+ this_tot->rx_packets = this_tot->vf_rx_packets;
+ this_tot->tx_packets = this_tot->vf_tx_packets;
+ this_tot->rx_bytes = this_tot->vf_rx_bytes;
+ this_tot->tx_bytes = this_tot->vf_tx_bytes;
+ }
+
+ /* fetch percpu stats of netvsc */
+ for (i = 0; i < nvdev->num_chn; i++) {
+ const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
+ const struct netvsc_stats *stats;
+ struct netvsc_ethtool_pcpu_stats *this_tot =
+ &pcpu_tot[nvchan->channel->target_cpu];
+ u64 packets, bytes;
+ unsigned int start;
+
+ stats = &nvchan->tx_stats;
+ do {
+ start = u64_stats_fetch_begin_irq(&stats->syncp);
+ packets = stats->packets;
+ bytes = stats->bytes;
+ } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+ this_tot->tx_bytes += bytes;
+ this_tot->tx_packets += packets;
+
+ stats = &nvchan->rx_stats;
+ do {
+ start = u64_stats_fetch_begin_irq(&stats->syncp);
+ packets = stats->packets;
+ bytes = stats->bytes;
+ } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+ this_tot->rx_bytes += bytes;
+ this_tot->rx_packets += packets;
+ }
+}
+
static void netvsc_get_stats64(struct net_device *net,
struct rtnl_link_stats64 *t)
{
@@ -1203,6 +1274,23 @@ static const struct {
{ "rx_no_memory", offsetof(struct netvsc_ethtool_stats, rx_no_memory) },
{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
+}, pcpu_stats[] = {
+ { "cpu%u_rx_packets",
+ offsetof(struct netvsc_ethtool_pcpu_stats, rx_packets) },
+ { "cpu%u_rx_bytes",
+ offsetof(struct netvsc_ethtool_pcpu_stats, rx_bytes) },
+ { "cpu%u_tx_packets",
+ offsetof(struct netvsc_ethtool_pcpu_stats, tx_packets) },
+ { "cpu%u_tx_bytes",
+ offsetof(struct netvsc_ethtool_pcpu_stats, tx_bytes) },
+ { "cpu%u_vf_rx_packets",
+ offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_packets) },
+ { "cpu%u_vf_rx_bytes",
+ offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_bytes) },
+ { "cpu%u_vf_tx_packets",
+ offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_packets) },
+ { "cpu%u_vf_tx_bytes",
+ offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_bytes) },
}, vf_stats[] = {
{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
{ "vf_rx_bytes", offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
@@ -1214,6 +1302,9 @@ static const struct {
#define NETVSC_GLOBAL_STATS_LEN ARRAY_SIZE(netvsc_stats)
#define NETVSC_VF_STATS_LEN ARRAY_SIZE(vf_stats)
+/* statistics per queue (rx/tx packets/bytes) */
+#define NETVSC_PCPU_STATS_LEN (num_present_cpus() * ARRAY_SIZE(pcpu_stats))
+
/* 4 statistics per queue (rx/tx packets/bytes) */
#define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 4)
@@ -1229,7 +1320,8 @@ static int netvsc_get_sset_count(struct net_device *dev, int string_set)
case ETH_SS_STATS:
return NETVSC_GLOBAL_STATS_LEN
+ NETVSC_VF_STATS_LEN
- + NETVSC_QUEUE_STATS_LEN(nvdev);
+ + NETVSC_QUEUE_STATS_LEN(nvdev)
+ + NETVSC_PCPU_STATS_LEN;
default:
return -EINVAL;
}
@@ -1243,9 +1335,10 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
const void *nds = &ndc->eth_stats;
const struct netvsc_stats *qstats;
struct netvsc_vf_pcpu_stats sum;
+ struct netvsc_ethtool_pcpu_stats *pcpu_sum;
unsigned int start;
u64 packets, bytes;
- int i, j;
+ int i, j, cpu;
if (!nvdev)
return;
@@ -1277,6 +1370,19 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
data[i++] = packets;
data[i++] = bytes;
}
+
+ pcpu_sum = kvmalloc_array(num_possible_cpus(),
+ sizeof(struct netvsc_ethtool_pcpu_stats),
+ GFP_KERNEL);
+ netvsc_get_pcpu_stats(dev, pcpu_sum);
+ for_each_present_cpu(cpu) {
+ struct netvsc_ethtool_pcpu_stats *this_sum = &pcpu_sum[cpu];
+
+ for (j = 0; j < ARRAY_SIZE(pcpu_stats); j++)
+ data[i++] = *(u64 *)((void *)this_sum
+ + pcpu_stats[j].offset);
+ }
+ kvfree(pcpu_sum);
}
static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
@@ -1284,7 +1390,7 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
struct net_device_context *ndc = netdev_priv(dev);
struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
u8 *p = data;
- int i;
+ int i, cpu;
if (!nvdev)
return;
@@ -1312,6 +1418,13 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
p += ETH_GSTRING_LEN;
}
+ for_each_present_cpu(cpu) {
+ for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++) {
+ sprintf(p, pcpu_stats[i].name, cpu);
+ p += ETH_GSTRING_LEN;
+ }
+ }
+
break;
}
}
@@ -1781,20 +1894,6 @@ out_unlock:
rtnl_unlock();
}
-static struct net_device *get_netvsc_bymac(const u8 *mac)
-{
- struct net_device_context *ndev_ctx;
-
- list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
- struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx);
-
- if (ether_addr_equal(mac, dev->perm_addr))
- return dev;
- }
-
- return NULL;
-}
-
static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
{
struct net_device_context *net_device_ctx;
@@ -1923,22 +2022,48 @@ static void netvsc_vf_setup(struct work_struct *w)
rtnl_unlock();
}
+/* Find netvsc by VMBus serial number.
+ * The PCI hyperv controller records the serial number as the slot.
+ */
+static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
+{
+ struct device *parent = vf_netdev->dev.parent;
+ struct net_device_context *ndev_ctx;
+ struct pci_dev *pdev;
+
+ if (!parent || !dev_is_pci(parent))
+ return NULL; /* not a PCI device */
+
+ pdev = to_pci_dev(parent);
+ if (!pdev->slot) {
+ netdev_notice(vf_netdev, "no PCI slot information\n");
+ return NULL;
+ }
+
+ list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) {
+ if (!ndev_ctx->vf_alloc)
+ continue;
+
+ if (ndev_ctx->vf_serial == pdev->slot->number)
+ return hv_get_drvdata(ndev_ctx->device_ctx);
+ }
+
+ netdev_notice(vf_netdev,
+ "no netdev found for slot %u\n", pdev->slot->number);
+ return NULL;
+}
+
static int netvsc_register_vf(struct net_device *vf_netdev)
{
- struct net_device *ndev;
struct net_device_context *net_device_ctx;
struct netvsc_device *netvsc_dev;
+ struct net_device *ndev;
int ret;
if (vf_netdev->addr_len != ETH_ALEN)
return NOTIFY_DONE;
- /*
- * We will use the MAC address to locate the synthetic interface to
- * associate with the VF interface. If we don't find a matching
- * synthetic interface, move on.
- */
- ndev = get_netvsc_bymac(vf_netdev->perm_addr);
+ ndev = get_netvsc_byslot(vf_netdev);
if (!ndev)
return NOTIFY_DONE;
@@ -2089,6 +2214,19 @@ static int netvsc_probe(struct hv_device *dev,
memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
+ /* We must get rtnl lock before scheduling nvdev->subchan_work,
+ * otherwise netvsc_subchan_work() can get rtnl lock first and wait
+ * all subchannels to show up, but that may not happen because
+ * netvsc_probe() can't get rtnl lock and as a result vmbus_onoffer()
+ * -> ... -> device_add() -> ... -> __device_attach() can't get
+ * the device lock, so all the subchannels can't be processed --
+ * finally netvsc_subchan_work() hangs for ever.
+ */
+ rtnl_lock();
+
+ if (nvdev->num_chn > 1)
+ schedule_work(&nvdev->subchan_work);
+
/* hw_features computed in rndis_netdev_set_hwcaps() */
net->features = net->hw_features |
NETIF_F_HIGHDMA | NETIF_F_SG |
@@ -2104,7 +2242,6 @@ static int netvsc_probe(struct hv_device *dev,
else
net->max_mtu = ETH_DATA_LEN;
- rtnl_lock();
ret = register_netdevice(net);
if (ret != 0) {
pr_err("Unable to register netdev.\n");
@@ -2143,17 +2280,15 @@ static int netvsc_remove(struct hv_device *dev)
cancel_delayed_work_sync(&ndev_ctx->dwork);
- rcu_read_lock();
- nvdev = rcu_dereference(ndev_ctx->nvdev);
-
- if (nvdev)
+ rtnl_lock();
+ nvdev = rtnl_dereference(ndev_ctx->nvdev);
+ if (nvdev)
cancel_work_sync(&nvdev->subchan_work);
/*
* Call to the vsc driver to let it know that the device is being
* removed. Also blocks mtu and channel changes.
*/
- rtnl_lock();
vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
if (vf_netdev)
netvsc_unregister_vf(vf_netdev);
@@ -2165,7 +2300,6 @@ static int netvsc_remove(struct hv_device *dev)
list_del(&ndev_ctx->list);
rtnl_unlock();
- rcu_read_unlock();
hv_set_drvdata(dev, NULL);
@@ -2188,6 +2322,9 @@ static struct hv_driver netvsc_drv = {
.id_table = id_table,
.probe = netvsc_probe,
.remove = netvsc_remove,
+ .driver = {
+ .probe_type = PROBE_PREFER_ASYNCHRONOUS,
+ },
};
/*
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 5428bb261102..2a5209f23f29 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1062,29 +1062,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
* This breaks overlap of processing the host message for the
* new primary channel with the initialization of sub-channels.
*/
-void rndis_set_subchannel(struct work_struct *w)
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev)
{
- struct netvsc_device *nvdev
- = container_of(w, struct netvsc_device, subchan_work);
struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
- struct net_device_context *ndev_ctx;
- struct rndis_device *rdev;
- struct net_device *ndev;
- struct hv_device *hv_dev;
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
+ struct hv_device *hv_dev = ndev_ctx->device_ctx;
+ struct rndis_device *rdev = nvdev->extension;
int i, ret;
- if (!rtnl_trylock()) {
- schedule_work(w);
- return;
- }
-
- rdev = nvdev->extension;
- if (!rdev)
- goto unlock; /* device was removed */
-
- ndev = rdev->ndev;
- ndev_ctx = netdev_priv(ndev);
- hv_dev = ndev_ctx->device_ctx;
+ ASSERT_RTNL();
memset(init_packet, 0, sizeof(struct nvsp_message));
init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
@@ -1100,13 +1086,13 @@ void rndis_set_subchannel(struct work_struct *w)
VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
if (ret) {
netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
- goto failed;
+ return ret;
}
wait_for_completion(&nvdev->channel_init_wait);
if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
netdev_err(ndev, "sub channel request failed\n");
- goto failed;
+ return -EIO;
}
nvdev->num_chn = 1 +
@@ -1125,21 +1111,7 @@ void rndis_set_subchannel(struct work_struct *w)
for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
ndev_ctx->tx_table[i] = i % nvdev->num_chn;
- netif_device_attach(ndev);
- rtnl_unlock();
- return;
-
-failed:
- /* fallback to only primary channel */
- for (i = 1; i < nvdev->num_chn; i++)
- netif_napi_del(&nvdev->chan_table[i].napi);
-
- nvdev->max_chn = 1;
- nvdev->num_chn = 1;
-
- netif_device_attach(ndev);
-unlock:
- rtnl_unlock();
+ return 0;
}
static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
@@ -1360,20 +1332,12 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
netif_napi_add(net, &net_device->chan_table[i].napi,
netvsc_poll, NAPI_POLL_WEIGHT);
- if (net_device->num_chn > 1)
- schedule_work(&net_device->subchan_work);
+ return net_device;
out:
- /* if unavailable, just proceed with one queue */
- if (ret) {
- net_device->max_chn = 1;
- net_device->num_chn = 1;
- }
-
- /* No sub channels, device is ready */
- if (net_device->num_chn == 1)
- netif_device_attach(net);
-
+ /* setting up multiple channels failed */
+ net_device->max_chn = 1;
+ net_device->num_chn = 1;
return net_device;
err_dev_remv:
generated by cgit v1.2.3 (git 2.39.0) at 2025-10-04 18:12:13 +0300