linux-stable/net/core/netdev-genl.c

187 lines
4 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#include <linux/netdevice.h>
#include <linux/notifier.h>
#include <linux/rtnetlink.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/xdp.h>
xsk: Add TX timestamp and TX checksum offload support This change actually defines the (initial) metadata layout that should be used by AF_XDP userspace (xsk_tx_metadata). The first field is flags which requests appropriate offloads, followed by the offload-specific fields. The supported per-device offloads are exported via netlink (new xsk-flags). The offloads themselves are still implemented in a bit of a framework-y fashion that's left from my initial kfunc attempt. I'm introducing new xsk_tx_metadata_ops which drivers are supposed to implement. The drivers are also supposed to call xsk_tx_metadata_request/xsk_tx_metadata_complete in the right places. Since xsk_tx_metadata_{request,_complete} are static inline, we don't incur any extra overhead doing indirect calls. The benefit of this scheme is as follows: - keeps all metadata layout parsing away from driver code - makes it easy to grep and see which drivers implement what - don't need any extra flags to maintain to keep track of what offloads are implemented; if the callback is implemented - the offload is supported (used by netlink reporting code) Two offloads are defined right now: 1. XDP_TXMD_FLAGS_CHECKSUM: skb-style csum_start+csum_offset 2. XDP_TXMD_FLAGS_TIMESTAMP: writes TX timestamp back into metadata area upon completion (tx_timestamp field) XDP_TXMD_FLAGS_TIMESTAMP is also implemented for XDP_COPY mode: it writes SW timestamp from the skb destructor (note I'm reusing hwtstamps to pass metadata pointer). The struct is forward-compatible and can be extended in the future by appending more fields. Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Acked-by: Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/r/20231127190319.1190813-3-sdf@google.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-11-27 19:03:08 +00:00
#include <net/xdp_sock.h>
#include "netdev-genl-gen.h"
static int
netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
const struct genl_info *info)
{
xsk: Add TX timestamp and TX checksum offload support This change actually defines the (initial) metadata layout that should be used by AF_XDP userspace (xsk_tx_metadata). The first field is flags which requests appropriate offloads, followed by the offload-specific fields. The supported per-device offloads are exported via netlink (new xsk-flags). The offloads themselves are still implemented in a bit of a framework-y fashion that's left from my initial kfunc attempt. I'm introducing new xsk_tx_metadata_ops which drivers are supposed to implement. The drivers are also supposed to call xsk_tx_metadata_request/xsk_tx_metadata_complete in the right places. Since xsk_tx_metadata_{request,_complete} are static inline, we don't incur any extra overhead doing indirect calls. The benefit of this scheme is as follows: - keeps all metadata layout parsing away from driver code - makes it easy to grep and see which drivers implement what - don't need any extra flags to maintain to keep track of what offloads are implemented; if the callback is implemented - the offload is supported (used by netlink reporting code) Two offloads are defined right now: 1. XDP_TXMD_FLAGS_CHECKSUM: skb-style csum_start+csum_offset 2. XDP_TXMD_FLAGS_TIMESTAMP: writes TX timestamp back into metadata area upon completion (tx_timestamp field) XDP_TXMD_FLAGS_TIMESTAMP is also implemented for XDP_COPY mode: it writes SW timestamp from the skb destructor (note I'm reusing hwtstamps to pass metadata pointer). The struct is forward-compatible and can be extended in the future by appending more fields. Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Acked-by: Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/r/20231127190319.1190813-3-sdf@google.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-11-27 19:03:08 +00:00
u64 xsk_features = 0;
u64 xdp_rx_meta = 0;
void *hdr;
hdr = genlmsg_iput(rsp, info);
if (!hdr)
return -EMSGSIZE;
#define XDP_METADATA_KFUNC(_, flag, __, xmo) \
if (netdev->xdp_metadata_ops && netdev->xdp_metadata_ops->xmo) \
xdp_rx_meta |= flag;
XDP_METADATA_KFUNC_xxx
#undef XDP_METADATA_KFUNC
xsk: Add TX timestamp and TX checksum offload support This change actually defines the (initial) metadata layout that should be used by AF_XDP userspace (xsk_tx_metadata). The first field is flags which requests appropriate offloads, followed by the offload-specific fields. The supported per-device offloads are exported via netlink (new xsk-flags). The offloads themselves are still implemented in a bit of a framework-y fashion that's left from my initial kfunc attempt. I'm introducing new xsk_tx_metadata_ops which drivers are supposed to implement. The drivers are also supposed to call xsk_tx_metadata_request/xsk_tx_metadata_complete in the right places. Since xsk_tx_metadata_{request,_complete} are static inline, we don't incur any extra overhead doing indirect calls. The benefit of this scheme is as follows: - keeps all metadata layout parsing away from driver code - makes it easy to grep and see which drivers implement what - don't need any extra flags to maintain to keep track of what offloads are implemented; if the callback is implemented - the offload is supported (used by netlink reporting code) Two offloads are defined right now: 1. XDP_TXMD_FLAGS_CHECKSUM: skb-style csum_start+csum_offset 2. XDP_TXMD_FLAGS_TIMESTAMP: writes TX timestamp back into metadata area upon completion (tx_timestamp field) XDP_TXMD_FLAGS_TIMESTAMP is also implemented for XDP_COPY mode: it writes SW timestamp from the skb destructor (note I'm reusing hwtstamps to pass metadata pointer). The struct is forward-compatible and can be extended in the future by appending more fields. Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Acked-by: Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/r/20231127190319.1190813-3-sdf@google.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-11-27 19:03:08 +00:00
if (netdev->xsk_tx_metadata_ops) {
if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp)
xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP;
if (netdev->xsk_tx_metadata_ops->tmo_request_checksum)
xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM;
}
if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES,
netdev->xdp_features, NETDEV_A_DEV_PAD) ||
nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
xsk: Add TX timestamp and TX checksum offload support This change actually defines the (initial) metadata layout that should be used by AF_XDP userspace (xsk_tx_metadata). The first field is flags which requests appropriate offloads, followed by the offload-specific fields. The supported per-device offloads are exported via netlink (new xsk-flags). The offloads themselves are still implemented in a bit of a framework-y fashion that's left from my initial kfunc attempt. I'm introducing new xsk_tx_metadata_ops which drivers are supposed to implement. The drivers are also supposed to call xsk_tx_metadata_request/xsk_tx_metadata_complete in the right places. Since xsk_tx_metadata_{request,_complete} are static inline, we don't incur any extra overhead doing indirect calls. The benefit of this scheme is as follows: - keeps all metadata layout parsing away from driver code - makes it easy to grep and see which drivers implement what - don't need any extra flags to maintain to keep track of what offloads are implemented; if the callback is implemented - the offload is supported (used by netlink reporting code) Two offloads are defined right now: 1. XDP_TXMD_FLAGS_CHECKSUM: skb-style csum_start+csum_offset 2. XDP_TXMD_FLAGS_TIMESTAMP: writes TX timestamp back into metadata area upon completion (tx_timestamp field) XDP_TXMD_FLAGS_TIMESTAMP is also implemented for XDP_COPY mode: it writes SW timestamp from the skb destructor (note I'm reusing hwtstamps to pass metadata pointer). The struct is forward-compatible and can be extended in the future by appending more fields. Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Acked-by: Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/r/20231127190319.1190813-3-sdf@google.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-11-27 19:03:08 +00:00
xdp_rx_meta, NETDEV_A_DEV_PAD) ||
nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES,
xsk_features, NETDEV_A_DEV_PAD)) {
genlmsg_cancel(rsp, hdr);
return -EINVAL;
}
if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) {
if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
netdev->xdp_zc_max_segs)) {
genlmsg_cancel(rsp, hdr);
return -EINVAL;
}
}
genlmsg_end(rsp, hdr);
return 0;
}
static void
netdev_genl_dev_notify(struct net_device *netdev, int cmd)
{
struct genl_info info;
struct sk_buff *ntf;
if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev),
NETDEV_NLGRP_MGMT))
return;
genl_info_init_ntf(&info, &netdev_nl_family, cmd);
ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!ntf)
return;
if (netdev_nl_dev_fill(netdev, ntf, &info)) {
nlmsg_free(ntf);
return;
}
genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf,
0, NETDEV_NLGRP_MGMT, GFP_KERNEL);
}
int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info)
{
struct net_device *netdev;
struct sk_buff *rsp;
u32 ifindex;
int err;
if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX))
return -EINVAL;
ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!rsp)
return -ENOMEM;
rtnl_lock();
netdev = __dev_get_by_index(genl_info_net(info), ifindex);
if (netdev)
err = netdev_nl_dev_fill(netdev, rsp, info);
else
err = -ENODEV;
rtnl_unlock();
if (err)
goto err_free_msg;
return genlmsg_reply(rsp, info);
err_free_msg:
nlmsg_free(rsp);
return err;
}
int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct net_device *netdev;
int err = 0;
rtnl_lock();
for_each_netdev_dump(net, netdev, cb->args[0]) {
err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb));
if (err < 0)
break;
}
rtnl_unlock();
if (err != -EMSGSIZE)
return err;
return skb->len;
}
static int netdev_genl_netdevice_event(struct notifier_block *nb,
unsigned long event, void *ptr)
{
struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
switch (event) {
case NETDEV_REGISTER:
netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF);
break;
case NETDEV_UNREGISTER:
netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF);
break;
case NETDEV_XDP_FEAT_CHANGE:
netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF);
break;
}
return NOTIFY_OK;
}
static struct notifier_block netdev_genl_nb = {
.notifier_call = netdev_genl_netdevice_event,
};
static int __init netdev_genl_init(void)
{
int err;
err = register_netdevice_notifier(&netdev_genl_nb);
if (err)
return err;
err = genl_register_family(&netdev_nl_family);
if (err)
goto err_unreg_ntf;
return 0;
err_unreg_ntf:
unregister_netdevice_notifier(&netdev_genl_nb);
return err;
}
subsys_initcall(netdev_genl_init);