linux/net/core/netdev-genl.c

721 lines
16 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 22:03:08 +03:00
#include <net/xdp_sock.h>
#include <net/netdev_rx_queue.h>
netdev: add per-queue statistics The ethtool-nl family does a good job exposing various protocol related and IEEE/IETF statistics which used to get dumped under ethtool -S, with creative names. Queue stats don't have a netlink API, yet, and remain a lion's share of ethtool -S output for new drivers. Not only is that bad because the names differ driver to driver but it's also bug-prone. Intuitively drivers try to report only the stats for active queues, but querying ethtool stats involves multiple system calls, and the number of stats is read separately from the stats themselves. Worse still when user space asks for values of the stats, it doesn't inform the kernel how big the buffer is. If number of stats increases in the meantime kernel will overflow user buffer. Add a netlink API for dumping queue stats. Queue information is exposed via the netdev-genl family, so add the stats there. Support per-queue and sum-for-device dumps. Latter will be useful when subsequent patches add more interesting common stats than just bytes and packets. The API does not currently distinguish between HW and SW stats. The expectation is that the source of the stats will either not matter much (good packets) or be obvious (skb alloc errors). Acked-by: Stanislav Fomichev <sdf@google.com> Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com> Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Link: https://lore.kernel.org/r/20240306195509.1502746-2-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-03-06 22:55:07 +03:00
#include <net/netdev_queues.h>
#include <net/busy_poll.h>
#include "netdev-genl-gen.h"
#include "dev.h"
struct netdev_nl_dump_ctx {
unsigned long ifindex;
unsigned int rxq_idx;
unsigned int txq_idx;
unsigned int napi_id;
};
static struct netdev_nl_dump_ctx *netdev_dump_ctx(struct netlink_callback *cb)
{
NL_ASSERT_DUMP_CTX_FITS(struct netdev_nl_dump_ctx);
return (struct netdev_nl_dump_ctx *)cb->ctx;
}
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 22:03:08 +03:00
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 22:03:08 +03:00
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 22:03:08 +03:00
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 netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
struct net *net = sock_net(skb->sk);
struct net_device *netdev;
int err = 0;
rtnl_lock();
for_each_netdev_dump(net, netdev, ctx->ifindex) {
err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb));
if (err < 0)
break;
}
rtnl_unlock();
return err;
}
static int
netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
const struct genl_info *info)
{
void *hdr;
pid_t pid;
if (WARN_ON_ONCE(!napi->dev))
return -EINVAL;
if (!(napi->dev->flags & IFF_UP))
return 0;
hdr = genlmsg_iput(rsp, info);
if (!hdr)
return -EMSGSIZE;
if (napi->napi_id >= MIN_NAPI_ID &&
nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id))
goto nla_put_failure;
if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex))
goto nla_put_failure;
if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq))
goto nla_put_failure;
if (napi->thread) {
pid = task_pid_nr(napi->thread);
if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
goto nla_put_failure;
}
genlmsg_end(rsp, hdr);
return 0;
nla_put_failure:
genlmsg_cancel(rsp, hdr);
return -EMSGSIZE;
}
int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info)
{
struct napi_struct *napi;
struct sk_buff *rsp;
u32 napi_id;
int err;
if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID))
return -EINVAL;
napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]);
rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!rsp)
return -ENOMEM;
rtnl_lock();
napi = napi_by_id(napi_id);
if (napi)
err = netdev_nl_napi_fill_one(rsp, napi, info);
else
err = -EINVAL;
rtnl_unlock();
if (err)
goto err_free_msg;
return genlmsg_reply(rsp, info);
err_free_msg:
nlmsg_free(rsp);
return err;
}
static int
netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp,
const struct genl_info *info,
struct netdev_nl_dump_ctx *ctx)
{
struct napi_struct *napi;
int err = 0;
if (!(netdev->flags & IFF_UP))
return err;
list_for_each_entry(napi, &netdev->napi_list, dev_list) {
if (ctx->napi_id && napi->napi_id >= ctx->napi_id)
continue;
err = netdev_nl_napi_fill_one(rsp, napi, info);
if (err)
return err;
ctx->napi_id = napi->napi_id;
}
return err;
}
int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
{
struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
const struct genl_info *info = genl_info_dump(cb);
struct net *net = sock_net(skb->sk);
struct net_device *netdev;
u32 ifindex = 0;
int err = 0;
if (info->attrs[NETDEV_A_NAPI_IFINDEX])
ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]);
rtnl_lock();
if (ifindex) {
netdev = __dev_get_by_index(net, ifindex);
if (netdev)
err = netdev_nl_napi_dump_one(netdev, skb, info, ctx);
else
err = -ENODEV;
} else {
for_each_netdev_dump(net, netdev, ctx->ifindex) {
err = netdev_nl_napi_dump_one(netdev, skb, info, ctx);
if (err < 0)
break;
ctx->napi_id = 0;
}
}
rtnl_unlock();
return err;
}
static int
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 netdev_rx_queue *rxq;
struct netdev_queue *txq;
void *hdr;
hdr = genlmsg_iput(rsp, info);
if (!hdr)
return -EMSGSIZE;
if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, q_idx) ||
nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type) ||
nla_put_u32(rsp, NETDEV_A_QUEUE_IFINDEX, netdev->ifindex))
goto nla_put_failure;
switch (q_type) {
case NETDEV_QUEUE_TYPE_RX:
rxq = __netif_get_rx_queue(netdev, q_idx);
if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
rxq->napi->napi_id))
goto nla_put_failure;
break;
case NETDEV_QUEUE_TYPE_TX:
txq = netdev_get_tx_queue(netdev, q_idx);
if (txq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
txq->napi->napi_id))
goto nla_put_failure;
}
genlmsg_end(rsp, hdr);
return 0;
nla_put_failure:
genlmsg_cancel(rsp, hdr);
return -EMSGSIZE;
}
static int netdev_nl_queue_validate(struct net_device *netdev, u32 q_id,
u32 q_type)
{
switch (q_type) {
case NETDEV_QUEUE_TYPE_RX:
if (q_id >= netdev->real_num_rx_queues)
return -EINVAL;
return 0;
case NETDEV_QUEUE_TYPE_TX:
if (q_id >= netdev->real_num_tx_queues)
return -EINVAL;
}
return 0;
}
static int
netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx,
u32 q_type, const struct genl_info *info)
{
int err = 0;
if (!(netdev->flags & IFF_UP))
return err;
err = netdev_nl_queue_validate(netdev, q_idx, q_type);
if (err)
return err;
return netdev_nl_queue_fill_one(rsp, netdev, q_idx, q_type, info);
}
int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info)
{
u32 q_id, q_type, ifindex;
struct net_device *netdev;
struct sk_buff *rsp;
int err;
if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_ID) ||
GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) ||
GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX))
return -EINVAL;
q_id = nla_get_u32(info->attrs[NETDEV_A_QUEUE_ID]);
q_type = nla_get_u32(info->attrs[NETDEV_A_QUEUE_TYPE]);
ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_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_queue_fill(rsp, netdev, q_id, q_type, 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;
}
static int
netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp,
const struct genl_info *info,
struct netdev_nl_dump_ctx *ctx)
{
int err = 0;
int i;
if (!(netdev->flags & IFF_UP))
return err;
for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) {
err = netdev_nl_queue_fill_one(rsp, netdev, i,
NETDEV_QUEUE_TYPE_RX, info);
if (err)
return err;
ctx->rxq_idx = i++;
}
for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) {
err = netdev_nl_queue_fill_one(rsp, netdev, i,
NETDEV_QUEUE_TYPE_TX, info);
if (err)
return err;
ctx->txq_idx = i++;
}
return err;
}
int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
{
struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
const struct genl_info *info = genl_info_dump(cb);
struct net *net = sock_net(skb->sk);
struct net_device *netdev;
u32 ifindex = 0;
int err = 0;
if (info->attrs[NETDEV_A_QUEUE_IFINDEX])
ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]);
rtnl_lock();
if (ifindex) {
netdev = __dev_get_by_index(net, ifindex);
if (netdev)
err = netdev_nl_queue_dump_one(netdev, skb, info, ctx);
else
err = -ENODEV;
} else {
for_each_netdev_dump(net, netdev, ctx->ifindex) {
err = netdev_nl_queue_dump_one(netdev, skb, info, ctx);
if (err < 0)
break;
ctx->rxq_idx = 0;
ctx->txq_idx = 0;
}
}
rtnl_unlock();
return err;
}
netdev: add per-queue statistics The ethtool-nl family does a good job exposing various protocol related and IEEE/IETF statistics which used to get dumped under ethtool -S, with creative names. Queue stats don't have a netlink API, yet, and remain a lion's share of ethtool -S output for new drivers. Not only is that bad because the names differ driver to driver but it's also bug-prone. Intuitively drivers try to report only the stats for active queues, but querying ethtool stats involves multiple system calls, and the number of stats is read separately from the stats themselves. Worse still when user space asks for values of the stats, it doesn't inform the kernel how big the buffer is. If number of stats increases in the meantime kernel will overflow user buffer. Add a netlink API for dumping queue stats. Queue information is exposed via the netdev-genl family, so add the stats there. Support per-queue and sum-for-device dumps. Latter will be useful when subsequent patches add more interesting common stats than just bytes and packets. The API does not currently distinguish between HW and SW stats. The expectation is that the source of the stats will either not matter much (good packets) or be obvious (skb alloc errors). Acked-by: Stanislav Fomichev <sdf@google.com> Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com> Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Link: https://lore.kernel.org/r/20240306195509.1502746-2-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-03-06 22:55:07 +03:00
#define NETDEV_STAT_NOT_SET (~0ULL)
static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size)
{
const u64 *add = _add;
u64 *sum = _sum;
while (size) {
if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET)
*sum += *add;
sum++;
add++;
size -= 8;
}
}
static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value)
{
if (value == NETDEV_STAT_NOT_SET)
return 0;
return nla_put_uint(rsp, attr_id, value);
}
static int
netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx)
{
if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) ||
netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) ||
netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail))
netdev: add per-queue statistics The ethtool-nl family does a good job exposing various protocol related and IEEE/IETF statistics which used to get dumped under ethtool -S, with creative names. Queue stats don't have a netlink API, yet, and remain a lion's share of ethtool -S output for new drivers. Not only is that bad because the names differ driver to driver but it's also bug-prone. Intuitively drivers try to report only the stats for active queues, but querying ethtool stats involves multiple system calls, and the number of stats is read separately from the stats themselves. Worse still when user space asks for values of the stats, it doesn't inform the kernel how big the buffer is. If number of stats increases in the meantime kernel will overflow user buffer. Add a netlink API for dumping queue stats. Queue information is exposed via the netdev-genl family, so add the stats there. Support per-queue and sum-for-device dumps. Latter will be useful when subsequent patches add more interesting common stats than just bytes and packets. The API does not currently distinguish between HW and SW stats. The expectation is that the source of the stats will either not matter much (good packets) or be obvious (skb alloc errors). Acked-by: Stanislav Fomichev <sdf@google.com> Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com> Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Link: https://lore.kernel.org/r/20240306195509.1502746-2-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-03-06 22:55:07 +03:00
return -EMSGSIZE;
return 0;
}
static int
netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx)
{
if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) ||
netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes))
return -EMSGSIZE;
return 0;
}
static int
netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp,
u32 q_type, int i, const struct genl_info *info)
{
const struct netdev_stat_ops *ops = netdev->stat_ops;
struct netdev_queue_stats_rx rx;
struct netdev_queue_stats_tx tx;
void *hdr;
hdr = genlmsg_iput(rsp, info);
if (!hdr)
return -EMSGSIZE;
if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) ||
nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) ||
nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i))
goto nla_put_failure;
switch (q_type) {
case NETDEV_QUEUE_TYPE_RX:
memset(&rx, 0xff, sizeof(rx));
ops->get_queue_stats_rx(netdev, i, &rx);
if (!memchr_inv(&rx, 0xff, sizeof(rx)))
goto nla_cancel;
if (netdev_nl_stats_write_rx(rsp, &rx))
goto nla_put_failure;
break;
case NETDEV_QUEUE_TYPE_TX:
memset(&tx, 0xff, sizeof(tx));
ops->get_queue_stats_tx(netdev, i, &tx);
if (!memchr_inv(&tx, 0xff, sizeof(tx)))
goto nla_cancel;
if (netdev_nl_stats_write_tx(rsp, &tx))
goto nla_put_failure;
break;
}
genlmsg_end(rsp, hdr);
return 0;
nla_cancel:
genlmsg_cancel(rsp, hdr);
return 0;
nla_put_failure:
genlmsg_cancel(rsp, hdr);
return -EMSGSIZE;
}
static int
netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
const struct genl_info *info,
struct netdev_nl_dump_ctx *ctx)
{
const struct netdev_stat_ops *ops = netdev->stat_ops;
int i, err;
if (!(netdev->flags & IFF_UP))
return 0;
i = ctx->rxq_idx;
while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) {
err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX,
i, info);
if (err)
return err;
ctx->rxq_idx = i++;
}
i = ctx->txq_idx;
while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) {
err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX,
i, info);
if (err)
return err;
ctx->txq_idx = i++;
}
ctx->rxq_idx = 0;
ctx->txq_idx = 0;
return 0;
}
static int
netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
const struct genl_info *info)
{
struct netdev_queue_stats_rx rx_sum, rx;
struct netdev_queue_stats_tx tx_sum, tx;
const struct netdev_stat_ops *ops;
void *hdr;
int i;
ops = netdev->stat_ops;
/* Netdev can't guarantee any complete counters */
if (!ops->get_base_stats)
return 0;
memset(&rx_sum, 0xff, sizeof(rx_sum));
memset(&tx_sum, 0xff, sizeof(tx_sum));
ops->get_base_stats(netdev, &rx_sum, &tx_sum);
/* The op was there, but nothing reported, don't bother */
if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) &&
!memchr_inv(&tx_sum, 0xff, sizeof(tx_sum)))
return 0;
hdr = genlmsg_iput(rsp, info);
if (!hdr)
return -EMSGSIZE;
if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex))
goto nla_put_failure;
for (i = 0; i < netdev->real_num_rx_queues; i++) {
memset(&rx, 0xff, sizeof(rx));
if (ops->get_queue_stats_rx)
ops->get_queue_stats_rx(netdev, i, &rx);
netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx));
}
for (i = 0; i < netdev->real_num_tx_queues; i++) {
memset(&tx, 0xff, sizeof(tx));
if (ops->get_queue_stats_tx)
ops->get_queue_stats_tx(netdev, i, &tx);
netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx));
}
if (netdev_nl_stats_write_rx(rsp, &rx_sum) ||
netdev_nl_stats_write_tx(rsp, &tx_sum))
goto nla_put_failure;
genlmsg_end(rsp, hdr);
return 0;
nla_put_failure:
genlmsg_cancel(rsp, hdr);
return -EMSGSIZE;
}
int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
struct netlink_callback *cb)
{
struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
const struct genl_info *info = genl_info_dump(cb);
struct net *net = sock_net(skb->sk);
struct net_device *netdev;
unsigned int scope;
int err = 0;
scope = 0;
if (info->attrs[NETDEV_A_QSTATS_SCOPE])
scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]);
rtnl_lock();
for_each_netdev_dump(net, netdev, ctx->ifindex) {
if (!netdev->stat_ops)
continue;
switch (scope) {
case 0:
err = netdev_nl_stats_by_netdev(netdev, skb, info);
break;
case NETDEV_QSTATS_SCOPE_QUEUE:
err = netdev_nl_stats_by_queue(netdev, skb, info, ctx);
break;
}
if (err < 0)
break;
}
rtnl_unlock();
return err;
}
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);