summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2026-01-20 18:04:55 -0800
committerJakub Kicinski <kuba@kernel.org>2026-01-20 18:06:01 -0800
commit8766d61a1d33cb5f15bfdd6ce9832bbe1fc649c2 (patch)
tree3b48f0bfd96379e5b19d9b78017512016f7cda91 /net
parent77b9c4a438fc66e2ab004c411056b3fb71a54f2c (diff)
downloadlinux-next-8766d61a1d33cb5f15bfdd6ce9832bbe1fc649c2.tar.gz
linux-next-8766d61a1d33cb5f15bfdd6ce9832bbe1fc649c2.zip
Revert "Merge branch 'netkit-support-for-io_uring-zero-copy-and-af_xdp'"
This reverts commit 77b9c4a438fc66e2ab004c411056b3fb71a54f2c, reversing changes made to 4515ec4ad58a37e70a9e1256c0b993958c9b7497: 931420a2fc36 ("selftests/net: Add netkit container tests") ab771c938d9a ("selftests/net: Make NetDrvContEnv support queue leasing") 6be87fbb2776 ("selftests/net: Add env for container based tests") 61d99ce3dfc2 ("selftests/net: Add bpf skb forwarding program") 920da3634194 ("netkit: Add xsk support for af_xdp applications") eef51113f8af ("netkit: Add netkit notifier to check for unregistering devices") b5ef109d22d4 ("netkit: Implement rtnl_link_ops->alloc and ndo_queue_create") b5c3fa4a0b16 ("netkit: Add single device mode for netkit") 0073d2fd679d ("xsk: Proxy pool management for leased queues") 1ecea95dd3b5 ("xsk: Extend xsk_rcv_check validation") 804bf334d08a ("net: Proxy netdev_queue_get_dma_dev for leased queues") 0caa9a8ddec3 ("net: Proxy net_mp_{open,close}_rxq for leased queues") ff8889ff9107 ("net, ethtool: Disallow leased real rxqs to be resized") 9e2103f36110 ("net: Add lease info to queue-get response") 31127deddef4 ("net: Implement netdev_nl_queue_create_doit") a5546e18f77c ("net: Add queue-create operation") The series will conflict with io_uring work, and the code needs more polish. Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r--net/core/dev.c7
-rw-r--r--net/core/dev.h2
-rw-r--r--net/core/netdev-genl-gen.c20
-rw-r--r--net/core/netdev-genl-gen.h2
-rw-r--r--net/core/netdev-genl.c185
-rw-r--r--net/core/netdev_queues.c74
-rw-r--r--net/core/netdev_rx_queue.c169
-rw-r--r--net/ethtool/channels.c12
-rw-r--r--net/ethtool/ioctl.c9
-rw-r--r--net/xdp/xsk.c79
10 files changed, 50 insertions, 509 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 13a3de63a825..2661b68f5be3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1115,13 +1115,6 @@ netdev_get_by_index_lock_ops_compat(struct net *net, int ifindex)
}
struct net_device *
-netdev_put_lock(struct net_device *dev, netdevice_tracker *tracker)
-{
- netdev_tracker_free(dev, tracker);
- return __netdev_put_lock(dev, dev_net(dev));
-}
-
-struct net_device *
netdev_xa_find_lock(struct net *net, struct net_device *dev,
unsigned long *index)
{
diff --git a/net/core/dev.h b/net/core/dev.h
index 9bcb76b325d0..da18536cbd35 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -30,8 +30,6 @@ netdev_napi_by_id_lock(struct net *net, unsigned int napi_id);
struct net_device *dev_get_by_napi_id(unsigned int napi_id);
struct net_device *__netdev_put_lock(struct net_device *dev, struct net *net);
-struct net_device *netdev_put_lock(struct net_device *dev,
- netdevice_tracker *tracker);
struct net_device *
netdev_xa_find_lock(struct net *net, struct net_device *dev,
unsigned long *index);
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 52ba99c019e7..ba673e81716f 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -28,12 +28,6 @@ static const struct netlink_range_validation netdev_a_napi_defer_hard_irqs_range
};
/* Common nested types */
-const struct nla_policy netdev_lease_nl_policy[NETDEV_A_LEASE_NETNS_ID + 1] = {
- [NETDEV_A_LEASE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
- [NETDEV_A_LEASE_QUEUE] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy),
- [NETDEV_A_LEASE_NETNS_ID] = { .type = NLA_S32, },
-};
-
const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = {
[NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range),
[NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range),
@@ -113,13 +107,6 @@ static const struct nla_policy netdev_bind_tx_nl_policy[NETDEV_A_DMABUF_FD + 1]
[NETDEV_A_DMABUF_FD] = { .type = NLA_U32, },
};
-/* NETDEV_CMD_QUEUE_CREATE - do */
-static const struct nla_policy netdev_queue_create_nl_policy[NETDEV_A_QUEUE_LEASE + 1] = {
- [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
- [NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1),
- [NETDEV_A_QUEUE_LEASE] = NLA_POLICY_NESTED(netdev_lease_nl_policy),
-};
-
/* Ops table for netdev */
static const struct genl_split_ops netdev_nl_ops[] = {
{
@@ -218,13 +205,6 @@ static const struct genl_split_ops netdev_nl_ops[] = {
.maxattr = NETDEV_A_DMABUF_FD,
.flags = GENL_CMD_CAP_DO,
},
- {
- .cmd = NETDEV_CMD_QUEUE_CREATE,
- .doit = netdev_nl_queue_create_doit,
- .policy = netdev_queue_create_nl_policy,
- .maxattr = NETDEV_A_QUEUE_LEASE,
- .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
- },
};
static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index d71b435d72c1..cffc08517a41 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -14,7 +14,6 @@
#include <net/netdev_netlink.h>
/* Common nested types */
-extern const struct nla_policy netdev_lease_nl_policy[NETDEV_A_LEASE_NETNS_ID + 1];
extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1];
extern const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1];
@@ -37,7 +36,6 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info);
int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info);
int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info);
-int netdev_nl_queue_create_doit(struct sk_buff *skb, struct genl_info *info);
enum {
NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 51c830f88f10..470fabbeacd9 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -391,11 +391,8 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
u32 q_idx, u32 q_type, const struct genl_info *info)
{
struct pp_memory_provider_params *params;
- struct net_device *orig_netdev = netdev;
- struct nlattr *nest_lease, *nest_queue;
struct netdev_rx_queue *rxq;
struct netdev_queue *txq;
- u32 lease_q_idx = q_idx;
void *hdr;
hdr = genlmsg_iput(rsp, info);
@@ -413,37 +410,6 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
if (nla_put_napi_id(rsp, rxq->napi))
goto nla_put_failure;
- if (netif_rx_queue_lease_get_owner(&netdev, &lease_q_idx)) {
- struct net *net, *peer_net;
-
- nest_lease = nla_nest_start(rsp, NETDEV_A_QUEUE_LEASE);
- if (!nest_lease)
- goto nla_put_failure;
- nest_queue = nla_nest_start(rsp, NETDEV_A_LEASE_QUEUE);
- if (!nest_queue)
- goto nla_put_failure;
- if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, lease_q_idx))
- goto nla_put_failure;
- if (nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type))
- goto nla_put_failure;
- nla_nest_end(rsp, nest_queue);
- if (nla_put_u32(rsp, NETDEV_A_LEASE_IFINDEX,
- READ_ONCE(netdev->ifindex)))
- goto nla_put_failure;
- rcu_read_lock();
- peer_net = dev_net_rcu(netdev);
- net = dev_net_rcu(orig_netdev);
- if (!net_eq(net, peer_net)) {
- s32 id = peernet2id_alloc(net, peer_net, GFP_ATOMIC);
-
- if (nla_put_s32(rsp, NETDEV_A_LEASE_NETNS_ID, id))
- goto nla_put_failure_unlock;
- }
- rcu_read_unlock();
- nla_nest_end(rsp, nest_lease);
- netdev = orig_netdev;
- }
-
params = &rxq->mp_params;
if (params->mp_ops &&
params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
@@ -471,8 +437,6 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
return 0;
-nla_put_failure_unlock:
- rcu_read_unlock();
nla_put_failure:
genlmsg_cancel(rsp, hdr);
return -EMSGSIZE;
@@ -1156,155 +1120,6 @@ err_genlmsg_free:
return err;
}
-int netdev_nl_queue_create_doit(struct sk_buff *skb, struct genl_info *info)
-{
- const int qmaxtype = ARRAY_SIZE(netdev_queue_id_nl_policy) - 1;
- const int lmaxtype = ARRAY_SIZE(netdev_lease_nl_policy) - 1;
- int err, ifindex, ifindex_lease, queue_id, queue_id_lease;
- struct nlattr *qtb[ARRAY_SIZE(netdev_queue_id_nl_policy)];
- struct nlattr *ltb[ARRAY_SIZE(netdev_lease_nl_policy)];
- struct netdev_rx_queue *rxq, *rxq_lease;
- struct net_device *dev, *dev_lease;
- netdevice_tracker dev_tracker;
- struct nlattr *nest;
- struct sk_buff *rsp;
- void *hdr;
-
- if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX) ||
- GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) ||
- GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_LEASE))
- return -EINVAL;
- if (nla_get_u32(info->attrs[NETDEV_A_QUEUE_TYPE]) !=
- NETDEV_QUEUE_TYPE_RX) {
- NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_QUEUE_TYPE]);
- return -EINVAL;
- }
-
- ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]);
-
- nest = info->attrs[NETDEV_A_QUEUE_LEASE];
- err = nla_parse_nested(ltb, lmaxtype, nest,
- netdev_lease_nl_policy, info->extack);
- if (err < 0)
- return err;
- if (NL_REQ_ATTR_CHECK(info->extack, nest, ltb, NETDEV_A_LEASE_IFINDEX) ||
- NL_REQ_ATTR_CHECK(info->extack, nest, ltb, NETDEV_A_LEASE_QUEUE))
- return -EINVAL;
- if (ltb[NETDEV_A_LEASE_NETNS_ID]) {
- NL_SET_BAD_ATTR(info->extack, ltb[NETDEV_A_LEASE_NETNS_ID]);
- return -EINVAL;
- }
-
- ifindex_lease = nla_get_u32(ltb[NETDEV_A_LEASE_IFINDEX]);
-
- nest = ltb[NETDEV_A_LEASE_QUEUE];
- err = nla_parse_nested(qtb, qmaxtype, nest,
- netdev_queue_id_nl_policy, info->extack);
- if (err < 0)
- return err;
- if (NL_REQ_ATTR_CHECK(info->extack, nest, qtb, NETDEV_A_QUEUE_ID) ||
- NL_REQ_ATTR_CHECK(info->extack, nest, qtb, NETDEV_A_QUEUE_TYPE))
- return -EINVAL;
- if (nla_get_u32(qtb[NETDEV_A_QUEUE_TYPE]) != NETDEV_QUEUE_TYPE_RX) {
- NL_SET_BAD_ATTR(info->extack, qtb[NETDEV_A_QUEUE_TYPE]);
- return -EINVAL;
- }
- if (ifindex == ifindex_lease) {
- NL_SET_ERR_MSG(info->extack,
- "Lease ifindex cannot be the same as queue creation ifindex");
- return -EINVAL;
- }
-
- queue_id_lease = nla_get_u32(qtb[NETDEV_A_QUEUE_ID]);
-
- rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!rsp)
- return -ENOMEM;
-
- hdr = genlmsg_iput(rsp, info);
- if (!hdr) {
- err = -EMSGSIZE;
- goto err_genlmsg_free;
- }
-
- /* Locking order is always from the virtual to the physical device
- * since this is also the same order when applications open the
- * memory provider later on.
- */
- dev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
- if (!dev) {
- err = -ENODEV;
- goto err_genlmsg_free;
- }
- if (!netdev_can_create_queue(dev, info->extack)) {
- err = -EINVAL;
- goto err_unlock_dev;
- }
-
- dev_lease = netdev_get_by_index(genl_info_net(info), ifindex_lease,
- &dev_tracker, GFP_KERNEL);
- if (!dev_lease) {
- err = -ENODEV;
- goto err_unlock_dev;
- }
- if (!netdev_can_lease_queue(dev_lease, info->extack)) {
- netdev_put(dev_lease, &dev_tracker);
- err = -EINVAL;
- goto err_unlock_dev;
- }
-
- dev_lease = netdev_put_lock(dev_lease, &dev_tracker);
- if (!dev_lease) {
- err = -ENODEV;
- goto err_unlock_dev;
- }
- if (queue_id_lease >= dev_lease->real_num_rx_queues) {
- err = -ERANGE;
- NL_SET_BAD_ATTR(info->extack, qtb[NETDEV_A_QUEUE_ID]);
- goto err_unlock_dev_lease;
- }
- if (netdev_queue_busy(dev_lease, queue_id_lease, info->extack)) {
- err = -EBUSY;
- goto err_unlock_dev_lease;
- }
-
- rxq_lease = __netif_get_rx_queue(dev_lease, queue_id_lease);
- rxq = __netif_get_rx_queue(dev, dev->real_num_rx_queues - 1);
-
- if (rxq->lease && rxq->lease->dev != dev_lease) {
- err = -EOPNOTSUPP;
- NL_SET_ERR_MSG(info->extack,
- "Leasing multiple queues from different devices not supported");
- goto err_unlock_dev_lease;
- }
-
- err = queue_id = dev->queue_mgmt_ops->ndo_queue_create(dev);
- if (err < 0) {
- NL_SET_ERR_MSG(info->extack,
- "Device is unable to create a new queue");
- goto err_unlock_dev_lease;
- }
-
- rxq = __netif_get_rx_queue(dev, queue_id);
- netdev_rx_queue_lease(rxq, rxq_lease);
-
- nla_put_u32(rsp, NETDEV_A_QUEUE_ID, queue_id);
- genlmsg_end(rsp, hdr);
-
- netdev_unlock(dev_lease);
- netdev_unlock(dev);
-
- return genlmsg_reply(rsp, info);
-
-err_unlock_dev_lease:
- netdev_unlock(dev_lease);
-err_unlock_dev:
- netdev_unlock(dev);
-err_genlmsg_free:
- nlmsg_free(rsp);
- return err;
-}
-
void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv)
{
INIT_LIST_HEAD(&priv->bindings);
diff --git a/net/core/netdev_queues.c b/net/core/netdev_queues.c
index 97acf6440829..251f27a8307f 100644
--- a/net/core/netdev_queues.c
+++ b/net/core/netdev_queues.c
@@ -1,37 +1,22 @@
// SPDX-License-Identifier: GPL-2.0-or-later
#include <net/netdev_queues.h>
-#include <net/netdev_rx_queue.h>
-#include <net/xdp_sock_drv.h>
/**
* netdev_queue_get_dma_dev() - get dma device for zero-copy operations
* @dev: net_device
* @idx: queue index
*
- * Get dma device for zero-copy operations to be used for this queue. If the
- * queue is leased to a physical queue, we retrieve the latter's dma device.
+ * Get dma device for zero-copy operations to be used for this queue.
* When such device is not available or valid, the function will return NULL.
*
* Return: Device or NULL on error
*/
struct device *netdev_queue_get_dma_dev(struct net_device *dev, int idx)
{
- const struct netdev_queue_mgmt_ops *queue_ops;
+ const struct netdev_queue_mgmt_ops *queue_ops = dev->queue_mgmt_ops;
struct device *dma_dev;
- if (idx < dev->real_num_rx_queues) {
- struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, idx);
-
- if (rxq->lease) {
- rxq = rxq->lease;
- dev = rxq->dev;
- idx = get_netdev_rx_queue_index(rxq);
- }
- }
-
- queue_ops = dev->queue_mgmt_ops;
-
if (queue_ops && queue_ops->ndo_queue_get_dma_dev)
dma_dev = queue_ops->ndo_queue_get_dma_dev(dev, idx);
else
@@ -40,58 +25,3 @@ struct device *netdev_queue_get_dma_dev(struct net_device *dev, int idx)
return dma_dev && dma_dev->dma_mask ? dma_dev : NULL;
}
-bool netdev_can_create_queue(const struct net_device *dev,
- struct netlink_ext_ack *extack)
-{
- if (dev->dev.parent) {
- NL_SET_ERR_MSG(extack, "Device is not a virtual device");
- return false;
- }
- if (!dev->queue_mgmt_ops ||
- !dev->queue_mgmt_ops->ndo_queue_create) {
- NL_SET_ERR_MSG(extack, "Device does not support queue creation");
- return false;
- }
- if (dev->real_num_rx_queues < 1 ||
- dev->real_num_tx_queues < 1) {
- NL_SET_ERR_MSG(extack, "Device must have at least one real queue");
- return false;
- }
- return true;
-}
-
-bool netdev_can_lease_queue(const struct net_device *dev,
- struct netlink_ext_ack *extack)
-{
- if (!dev->dev.parent) {
- NL_SET_ERR_MSG(extack, "Lease device is a virtual device");
- return false;
- }
- if (!netif_device_present(dev)) {
- NL_SET_ERR_MSG(extack, "Lease device has been removed from the system");
- return false;
- }
- if (!dev->queue_mgmt_ops) {
- NL_SET_ERR_MSG(extack, "Lease device does not support queue management operations");
- return false;
- }
- return true;
-}
-
-bool netdev_queue_busy(struct net_device *dev, int idx,
- struct netlink_ext_ack *extack)
-{
- if (netif_rxq_is_leased(dev, idx)) {
- NL_SET_ERR_MSG(extack, "Lease device queue is already leased");
- return true;
- }
- if (xsk_get_pool_from_qid(dev, idx)) {
- NL_SET_ERR_MSG(extack, "Lease device queue in use by AF_XDP");
- return true;
- }
- if (netif_rxq_has_mp(dev, idx)) {
- NL_SET_ERR_MSG(extack, "Lease device queue in use by memory provider");
- return true;
- }
- return false;
-}
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index 75c7a68cb90d..c7d9341b7630 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -9,120 +9,14 @@
#include "page_pool_priv.h"
-void netdev_rx_queue_lease(struct netdev_rx_queue *rxq_dst,
- struct netdev_rx_queue *rxq_src)
-{
- netdev_assert_locked(rxq_src->dev);
- netdev_assert_locked(rxq_dst->dev);
-
- netdev_hold(rxq_src->dev, &rxq_src->lease_tracker, GFP_KERNEL);
-
- WRITE_ONCE(rxq_src->lease, rxq_dst);
- WRITE_ONCE(rxq_dst->lease, rxq_src);
-}
-
-void netdev_rx_queue_unlease(struct netdev_rx_queue *rxq_dst,
- struct netdev_rx_queue *rxq_src)
-{
- netdev_assert_locked(rxq_dst->dev);
- netdev_assert_locked(rxq_src->dev);
-
- WRITE_ONCE(rxq_src->lease, NULL);
- WRITE_ONCE(rxq_dst->lease, NULL);
-
- netdev_put(rxq_src->dev, &rxq_src->lease_tracker);
-}
-
-bool netif_rxq_is_leased(struct net_device *dev, unsigned int rxq_idx)
-{
- if (rxq_idx < dev->real_num_rx_queues)
- return READ_ONCE(__netif_get_rx_queue(dev, rxq_idx)->lease);
- return false;
-}
-
-static bool netif_lease_dir_ok(const struct net_device *dev,
- enum netif_lease_dir dir)
-{
- if (dir == NETIF_VIRT_TO_PHYS && !dev->dev.parent)
- return true;
- if (dir == NETIF_PHYS_TO_VIRT && dev->dev.parent)
- return true;
- return false;
-}
-
-struct netdev_rx_queue *
-__netif_get_rx_queue_lease(struct net_device **dev, unsigned int *rxq_idx,
- enum netif_lease_dir dir)
-{
- struct net_device *orig_dev = *dev;
- struct netdev_rx_queue *rxq = __netif_get_rx_queue(orig_dev, *rxq_idx);
-
- if (rxq->lease) {
- if (!netif_lease_dir_ok(orig_dev, dir))
- return NULL;
- rxq = rxq->lease;
- *rxq_idx = get_netdev_rx_queue_index(rxq);
- *dev = rxq->dev;
- }
- return rxq;
-}
-
-struct netdev_rx_queue *
-netif_get_rx_queue_lease_locked(struct net_device **dev, unsigned int *rxq_idx)
-{
- struct net_device *orig_dev = *dev;
- struct netdev_rx_queue *rxq;
-
- /* Locking order is always from the virtual to the physical device
- * see netdev_nl_queue_create_doit().
- */
- netdev_ops_assert_locked(orig_dev);
- rxq = __netif_get_rx_queue_lease(dev, rxq_idx, NETIF_VIRT_TO_PHYS);
- if (rxq && orig_dev != *dev)
- netdev_lock(*dev);
- return rxq;
-}
-
-void netif_put_rx_queue_lease_locked(struct net_device *orig_dev,
- struct net_device *dev)
-{
- if (orig_dev != dev)
- netdev_unlock(dev);
-}
-
-bool netif_rx_queue_lease_get_owner(struct net_device **dev,
- unsigned int *rxq_idx)
-{
- struct net_device *orig_dev = *dev;
- struct netdev_rx_queue *rxq;
-
- /* The physical device needs to be locked. If there is indeed a lease,
- * then the virtual device holds a reference on the physical device
- * and the lease stays active until the virtual device is torn down.
- * When queues get {un,}leased both devices are always locked.
- */
- netdev_ops_assert_locked(orig_dev);
- rxq = __netif_get_rx_queue_lease(dev, rxq_idx, NETIF_PHYS_TO_VIRT);
- if (rxq && orig_dev != *dev)
- return true;
- return false;
-}
-
/* See also page_pool_is_unreadable() */
-bool netif_rxq_has_unreadable_mp(struct net_device *dev, unsigned int rxq_idx)
+bool netif_rxq_has_unreadable_mp(struct net_device *dev, int idx)
{
- if (rxq_idx < dev->real_num_rx_queues)
- return __netif_get_rx_queue(dev, rxq_idx)->mp_params.mp_ops;
- return false;
-}
-EXPORT_SYMBOL(netif_rxq_has_unreadable_mp);
+ struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, idx);
-bool netif_rxq_has_mp(struct net_device *dev, unsigned int rxq_idx)
-{
- if (rxq_idx < dev->real_num_rx_queues)
- return __netif_get_rx_queue(dev, rxq_idx)->mp_params.mp_priv;
- return false;
+ return !!rxq->mp_params.mp_ops;
}
+EXPORT_SYMBOL(netif_rxq_has_unreadable_mp);
int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
{
@@ -206,63 +100,49 @@ int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
const struct pp_memory_provider_params *p,
struct netlink_ext_ack *extack)
{
- struct net_device *orig_dev = dev;
struct netdev_rx_queue *rxq;
int ret;
if (!netdev_need_ops_lock(dev))
return -EOPNOTSUPP;
+
if (rxq_idx >= dev->real_num_rx_queues) {
NL_SET_ERR_MSG(extack, "rx queue index out of range");
return -ERANGE;
}
-
rxq_idx = array_index_nospec(rxq_idx, dev->real_num_rx_queues);
- rxq = netif_get_rx_queue_lease_locked(&dev, &rxq_idx);
- if (!rxq) {
- NL_SET_ERR_MSG(extack, "rx queue peered to a virtual netdev");
- return -EBUSY;
- }
- if (!dev->dev.parent) {
- NL_SET_ERR_MSG(extack, "rx queue is mapped to a virtual netdev");
- ret = -EBUSY;
- goto out;
- }
+
if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) {
NL_SET_ERR_MSG(extack, "tcp-data-split is disabled");
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
if (dev->cfg->hds_thresh) {
NL_SET_ERR_MSG(extack, "hds-thresh is not zero");
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
if (dev_xdp_prog_count(dev)) {
NL_SET_ERR_MSG(extack, "unable to custom memory provider to device with XDP program attached");
- ret = -EEXIST;
- goto out;
+ return -EEXIST;
}
+
+ rxq = __netif_get_rx_queue(dev, rxq_idx);
if (rxq->mp_params.mp_ops) {
NL_SET_ERR_MSG(extack, "designated queue already memory provider bound");
- ret = -EEXIST;
- goto out;
+ return -EEXIST;
}
#ifdef CONFIG_XDP_SOCKETS
if (rxq->pool) {
NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP");
- ret = -EBUSY;
- goto out;
+ return -EBUSY;
}
#endif
+
rxq->mp_params = *p;
ret = netdev_rx_queue_restart(dev, rxq_idx);
if (ret) {
rxq->mp_params.mp_ops = NULL;
rxq->mp_params.mp_priv = NULL;
}
-out:
- netif_put_rx_queue_lease_locked(orig_dev, dev);
return ret;
}
@@ -277,43 +157,38 @@ int net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
return ret;
}
-void __net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx,
+void __net_mp_close_rxq(struct net_device *dev, unsigned int ifq_idx,
const struct pp_memory_provider_params *old_p)
{
- struct net_device *orig_dev = dev;
struct netdev_rx_queue *rxq;
int err;
- if (WARN_ON_ONCE(rxq_idx >= dev->real_num_rx_queues))
+ if (WARN_ON_ONCE(ifq_idx >= dev->real_num_rx_queues))
return;
- rxq = netif_get_rx_queue_lease_locked(&dev, &rxq_idx);
- if (WARN_ON_ONCE(!rxq))
- return;
+ rxq = __netif_get_rx_queue(dev, ifq_idx);
/* Callers holding a netdev ref may get here after we already
* went thru shutdown via dev_memory_provider_uninstall().
*/
if (dev->reg_state > NETREG_REGISTERED &&
!rxq->mp_params.mp_ops)
- goto out;
+ return;
if (WARN_ON_ONCE(rxq->mp_params.mp_ops != old_p->mp_ops ||
rxq->mp_params.mp_priv != old_p->mp_priv))
- goto out;
+ return;
rxq->mp_params.mp_ops = NULL;
rxq->mp_params.mp_priv = NULL;
- err = netdev_rx_queue_restart(dev, rxq_idx);
+ err = netdev_rx_queue_restart(dev, ifq_idx);
WARN_ON(err && err != -ENETDOWN);
-out:
- netif_put_rx_queue_lease_locked(orig_dev, dev);
}
-void net_mp_close_rxq(struct net_device *dev, unsigned int rxq_idx,
+void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
struct pp_memory_provider_params *old_p)
{
netdev_lock(dev);
- __net_mp_close_rxq(dev, rxq_idx, old_p);
+ __net_mp_close_rxq(dev, ifq_idx, old_p);
netdev_unlock(dev);
}
diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index 797d2a08c515..ca4f80282448 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
-#include <net/netdev_queues.h>
+#include <net/xdp_sock_drv.h>
#include "netlink.h"
#include "common.h"
@@ -169,16 +169,14 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info)
if (ret)
return ret;
- /* ensure channels are not busy at the moment */
+ /* Disabling channels, query zero-copy AF_XDP sockets */
from_channel = channels.combined_count +
min(channels.rx_count, channels.tx_count);
- for (i = from_channel; i < old_total; i++) {
- if (netdev_queue_busy(dev, i, NULL)) {
- GENL_SET_ERR_MSG(info,
- "requested channel counts are too low due to busy queues (AF_XDP or queue leasing)");
+ for (i = from_channel; i < old_total; i++)
+ if (xsk_get_pool_from_qid(dev, i)) {
+ GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets");
return -EINVAL;
}
- }
ret = dev->ethtool_ops->set_channels(dev, &channels);
return ret < 0 ? ret : 1;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 02a3454234d6..9431e305b233 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -27,13 +27,12 @@
#include <linux/net.h>
#include <linux/pm_runtime.h>
#include <linux/utsname.h>
-#include <linux/ethtool_netlink.h>
#include <net/devlink.h>
#include <net/ipv6.h>
+#include <net/xdp_sock_drv.h>
#include <net/flow_offload.h>
#include <net/netdev_lock.h>
-#include <net/netdev_queues.h>
-
+#include <linux/ethtool_netlink.h>
#include "common.h"
/* State held across locks and calls for commands which have devlink fallback */
@@ -2283,12 +2282,12 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
if (ret)
return ret;
- /* Disabling channels, query busy queues (AF_XDP, queue leasing) */
+ /* Disabling channels, query zero-copy AF_XDP sockets */
from_channel = channels.combined_count +
min(channels.rx_count, channels.tx_count);
to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count);
for (i = from_channel; i < to_channel; i++)
- if (netdev_queue_busy(dev, i, NULL))
+ if (xsk_get_pool_from_qid(dev, i))
return -EINVAL;
ret = dev->ethtool_ops->set_channels(dev, &channels);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 92f791433725..3b46bc635c43 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -23,8 +23,6 @@
#include <linux/netdevice.h>
#include <linux/rculist.h>
#include <linux/vmalloc.h>
-
-#include <net/netdev_queues.h>
#include <net/xdp_sock_drv.h>
#include <net/busy_poll.h>
#include <net/netdev_lock.h>
@@ -105,7 +103,7 @@ bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
}
EXPORT_SYMBOL(xsk_uses_need_wakeup);
-struct xsk_buff_pool *xsk_get_pool_from_qid(const struct net_device *dev,
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
u16 queue_id)
{
if (queue_id < dev->real_num_rx_queues)
@@ -119,18 +117,10 @@ EXPORT_SYMBOL(xsk_get_pool_from_qid);
void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id)
{
- struct net_device *orig_dev = dev;
- unsigned int id = queue_id;
-
- if (id < dev->real_num_rx_queues)
- WARN_ON_ONCE(!netif_get_rx_queue_lease_locked(&dev, &id));
-
- if (id < dev->real_num_rx_queues)
- dev->_rx[id].pool = NULL;
- if (id < dev->real_num_tx_queues)
- dev->_tx[id].pool = NULL;
-
- netif_put_rx_queue_lease_locked(orig_dev, dev);
+ if (queue_id < dev->num_rx_queues)
+ dev->_rx[queue_id].pool = NULL;
+ if (queue_id < dev->num_tx_queues)
+ dev->_tx[queue_id].pool = NULL;
}
/* The buffer pool is stored both in the _rx struct and the _tx struct as we do
@@ -140,29 +130,17 @@ void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id)
int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
u16 queue_id)
{
- struct net_device *orig_dev = dev;
- unsigned int id = queue_id;
- int ret = 0;
-
- if (id >= max(dev->real_num_rx_queues,
- dev->real_num_tx_queues))
+ if (queue_id >= max_t(unsigned int,
+ dev->real_num_rx_queues,
+ dev->real_num_tx_queues))
return -EINVAL;
- if (id < dev->real_num_rx_queues) {
- if (!netif_get_rx_queue_lease_locked(&dev, &id))
- return -EBUSY;
- if (xsk_get_pool_from_qid(dev, id)) {
- ret = -EBUSY;
- goto out;
- }
- }
- if (id < dev->real_num_rx_queues)
- dev->_rx[id].pool = pool;
- if (id < dev->real_num_tx_queues)
- dev->_tx[id].pool = pool;
-out:
- netif_put_rx_queue_lease_locked(orig_dev, dev);
- return ret;
+ if (queue_id < dev->real_num_rx_queues)
+ dev->_rx[queue_id].pool = pool;
+ if (queue_id < dev->real_num_tx_queues)
+ dev->_tx[queue_id].pool = pool;
+
+ return 0;
}
static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len,
@@ -346,37 +324,14 @@ static bool xsk_is_bound(struct xdp_sock *xs)
return false;
}
-static bool xsk_dev_queue_valid(const struct xdp_sock *xs,
- const struct xdp_rxq_info *info)
-{
- struct net_device *dev = xs->dev;
- u32 queue_index = xs->queue_id;
- struct netdev_rx_queue *rxq;
-
- if (info->dev == dev &&
- info->queue_index == queue_index)
- return true;
-
- if (queue_index < dev->real_num_rx_queues) {
- rxq = READ_ONCE(__netif_get_rx_queue(dev, queue_index)->lease);
- if (!rxq)
- return false;
-
- dev = rxq->dev;
- queue_index = get_netdev_rx_queue_index(rxq);
-
- return info->dev == dev &&
- info->queue_index == queue_index;
- }
- return false;
-}
-
static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
{
if (!xsk_is_bound(xs))
return -ENXIO;
- if (!xsk_dev_queue_valid(xs, xdp->rxq))
+
+ if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
return -EINVAL;
+
if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) {
xs->rx_dropped++;
return -ENOSPC;