adfd671676
Long ago we set out to remove the kitchen sink on kernel/sysctl.c arrays and placings sysctls to their own sybsystem or file to help avoid merge conflicts. Matthew Wilcox pointed out though that if we're going to do that we might as well also *save* space while at it and try to remove the extra last sysctl entry added at the end of each array, a sentintel, instead of bloating the kernel by adding a new sentinel with each array moved. Doing that was not so trivial, and has required slowing down the moves of kernel/sysctl.c arrays and measuring the impact on size by each new move. The complex part of the effort to help reduce the size of each sysctl is being done by the patient work of el señor Don Joel Granados. A lot of this is truly painful code refactoring and testing and then trying to measure the savings of each move and removing the sentinels. Although Joel already has code which does most of this work, experience with sysctl moves in the past shows is we need to be careful due to the slew of odd build failures that are possible due to the amount of random Kconfig options sysctls use. To that end Joel's work is split by first addressing the major housekeeping needed to remove the sentinels, which is part of this merge request. The rest of the work to actually remove the sentinels will be done later in future kernel releases. At first I was only going to send his first 7 patches of his patch series, posted 1 month ago, but in retrospect due to the testing the changes have received in linux-next and the minor changes they make this goes with the entire set of patches Joel had planned: just sysctl house keeping. There are networking changes but these are part of the house keeping too. The preliminary math is showing this will all help reduce the overall build time size of the kernel and run time memory consumed by the kernel by about ~64 bytes per array where we are able to remove each sentinel in the future. That also means there is no more bloating the kernel with the extra ~64 bytes per array moved as no new sentinels are created. Most of this has been in linux-next for about a month, the last 7 patches took a minor refresh 2 week ago based on feedback. -----BEGIN PGP SIGNATURE----- iQJGBAABCgAwFiEENnNq2KuOejlQLZofziMdCjCSiKcFAmTuVnMSHG1jZ3JvZkBr ZXJuZWwub3JnAAoJEM4jHQowkoinIckP/imvRlfkO6L0IP7MmJBRPtwY01rsTAKO Q14dZ//bG4DVQeGl1FdzrF6hhuLgekU0qW1YDFIWiCXO7CbaxaNBPSUkeW6ReVoC R/VHNUPxSR1PWQy1OTJV2t4XKri2sB7ijmUsfsATtISwhei9bggTHEysShtP4tv+ U87DzhoqMnbYIsfMo49KCqOa1Qm7TmjC1a7WAp6Fph3GJuXAzZR5pXpsd0NtOZ9x Ud5RT22icnQpMl7K+yPsqY6XcS5JkgBe/WbSzMAUkYZvBZFBq9t2D+OW5h9TZMhw piJWQ9X0Rm7qI2D15mJfXwaOhhyDhWci391hzdJmS6DI0prf6Ma2NFdAWOt/zomI uiRujS4bGeBUaK5F4TX2WQ1+jdMtAZ+0FncFnzt4U8q7dzUc91uVCm6iHW3gcfAb N7OEg2ZL0gkkgCZHqKxN8wpNQiC2KwnNk+HLAbnL2a/oJYfBtdopQmlxWfrN2hpF xxROiENqk483BRdMXDq6DR/gyDZmZWCobXIglSzlqCOjCOcLbDziIJ7pJk83ok09 h/QnXTYHf9protBq9OIQesgh2pwNzBBLifK84KZLKcb7IbdIKjpQrW5STp04oNGf wcGJzEz8tXUe0UKyMM47AcHQGzIy6cdXNLjyF8a+m7rnZzr1ndnMqZyRStZzuQin AUg2VWHKPmW9 =sq2p -----END PGP SIGNATURE----- Merge tag 'sysctl-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux Pull sysctl updates from Luis Chamberlain: "Long ago we set out to remove the kitchen sink on kernel/sysctl.c arrays and placings sysctls to their own sybsystem or file to help avoid merge conflicts. Matthew Wilcox pointed out though that if we're going to do that we might as well also *save* space while at it and try to remove the extra last sysctl entry added at the end of each array, a sentintel, instead of bloating the kernel by adding a new sentinel with each array moved. Doing that was not so trivial, and has required slowing down the moves of kernel/sysctl.c arrays and measuring the impact on size by each new move. The complex part of the effort to help reduce the size of each sysctl is being done by the patient work of el señor Don Joel Granados. A lot of this is truly painful code refactoring and testing and then trying to measure the savings of each move and removing the sentinels. Although Joel already has code which does most of this work, experience with sysctl moves in the past shows is we need to be careful due to the slew of odd build failures that are possible due to the amount of random Kconfig options sysctls use. To that end Joel's work is split by first addressing the major housekeeping needed to remove the sentinels, which is part of this merge request. The rest of the work to actually remove the sentinels will be done later in future kernel releases. The preliminary math is showing this will all help reduce the overall build time size of the kernel and run time memory consumed by the kernel by about ~64 bytes per array where we are able to remove each sentinel in the future. That also means there is no more bloating the kernel with the extra ~64 bytes per array moved as no new sentinels are created" * tag 'sysctl-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux: sysctl: Use ctl_table_size as stopping criteria for list macro sysctl: SIZE_MAX->ARRAY_SIZE in register_net_sysctl vrf: Update to register_net_sysctl_sz networking: Update to register_net_sysctl_sz netfilter: Update to register_net_sysctl_sz ax.25: Update to register_net_sysctl_sz sysctl: Add size to register_net_sysctl function sysctl: Add size arg to __register_sysctl_init sysctl: Add size to register_sysctl sysctl: Add a size arg to __register_sysctl_table sysctl: Add size argument to init_header sysctl: Add ctl_table_size to ctl_table_header sysctl: Use ctl_table_header in list_for_each_table_entry sysctl: Prefer ctl_table_header in proc_sysctl
250 lines
5.7 KiB
C
250 lines
5.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* xfrm4_policy.c
|
|
*
|
|
* Changes:
|
|
* Kazunori MIYAZAWA @USAGI
|
|
* YOSHIFUJI Hideaki @USAGI
|
|
* Split up af-specific portion
|
|
*
|
|
*/
|
|
|
|
#include <linux/err.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/inetdevice.h>
|
|
#include <net/dst.h>
|
|
#include <net/xfrm.h>
|
|
#include <net/ip.h>
|
|
#include <net/l3mdev.h>
|
|
|
|
static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4,
|
|
int tos, int oif,
|
|
const xfrm_address_t *saddr,
|
|
const xfrm_address_t *daddr,
|
|
u32 mark)
|
|
{
|
|
struct rtable *rt;
|
|
|
|
memset(fl4, 0, sizeof(*fl4));
|
|
fl4->daddr = daddr->a4;
|
|
fl4->flowi4_tos = tos;
|
|
fl4->flowi4_l3mdev = l3mdev_master_ifindex_by_index(net, oif);
|
|
fl4->flowi4_mark = mark;
|
|
if (saddr)
|
|
fl4->saddr = saddr->a4;
|
|
|
|
rt = __ip_route_output_key(net, fl4);
|
|
if (!IS_ERR(rt))
|
|
return &rt->dst;
|
|
|
|
return ERR_CAST(rt);
|
|
}
|
|
|
|
static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif,
|
|
const xfrm_address_t *saddr,
|
|
const xfrm_address_t *daddr,
|
|
u32 mark)
|
|
{
|
|
struct flowi4 fl4;
|
|
|
|
return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark);
|
|
}
|
|
|
|
static int xfrm4_get_saddr(struct net *net, int oif,
|
|
xfrm_address_t *saddr, xfrm_address_t *daddr,
|
|
u32 mark)
|
|
{
|
|
struct dst_entry *dst;
|
|
struct flowi4 fl4;
|
|
|
|
dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark);
|
|
if (IS_ERR(dst))
|
|
return -EHOSTUNREACH;
|
|
|
|
saddr->a4 = fl4.saddr;
|
|
dst_release(dst);
|
|
return 0;
|
|
}
|
|
|
|
static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
|
|
const struct flowi *fl)
|
|
{
|
|
struct rtable *rt = (struct rtable *)xdst->route;
|
|
const struct flowi4 *fl4 = &fl->u.ip4;
|
|
|
|
xdst->u.rt.rt_iif = fl4->flowi4_iif;
|
|
|
|
xdst->u.dst.dev = dev;
|
|
netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC);
|
|
|
|
/* Sheit... I remember I did this right. Apparently,
|
|
* it was magically lost, so this code needs audit */
|
|
xdst->u.rt.rt_is_input = rt->rt_is_input;
|
|
xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
|
|
RTCF_LOCAL);
|
|
xdst->u.rt.rt_type = rt->rt_type;
|
|
xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
|
|
xdst->u.rt.rt_gw_family = rt->rt_gw_family;
|
|
if (rt->rt_gw_family == AF_INET)
|
|
xdst->u.rt.rt_gw4 = rt->rt_gw4;
|
|
else if (rt->rt_gw_family == AF_INET6)
|
|
xdst->u.rt.rt_gw6 = rt->rt_gw6;
|
|
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
|
|
xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked;
|
|
rt_add_uncached_list(&xdst->u.rt);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
|
|
struct sk_buff *skb, u32 mtu,
|
|
bool confirm_neigh)
|
|
{
|
|
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
|
|
struct dst_entry *path = xdst->route;
|
|
|
|
path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
|
|
}
|
|
|
|
static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
|
|
struct dst_entry *path = xdst->route;
|
|
|
|
path->ops->redirect(path, sk, skb);
|
|
}
|
|
|
|
static void xfrm4_dst_destroy(struct dst_entry *dst)
|
|
{
|
|
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
|
|
|
|
dst_destroy_metrics_generic(dst);
|
|
rt_del_uncached_list(&xdst->u.rt);
|
|
xfrm_dst_destroy(xdst);
|
|
}
|
|
|
|
static struct dst_ops xfrm4_dst_ops_template = {
|
|
.family = AF_INET,
|
|
.update_pmtu = xfrm4_update_pmtu,
|
|
.redirect = xfrm4_redirect,
|
|
.cow_metrics = dst_cow_metrics_generic,
|
|
.destroy = xfrm4_dst_destroy,
|
|
.ifdown = xfrm_dst_ifdown,
|
|
.local_out = __ip_local_out,
|
|
.gc_thresh = 32768,
|
|
};
|
|
|
|
static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
|
|
.dst_ops = &xfrm4_dst_ops_template,
|
|
.dst_lookup = xfrm4_dst_lookup,
|
|
.get_saddr = xfrm4_get_saddr,
|
|
.fill_dst = xfrm4_fill_dst,
|
|
.blackhole_route = ipv4_blackhole_route,
|
|
};
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
static struct ctl_table xfrm4_policy_table[] = {
|
|
{
|
|
.procname = "xfrm4_gc_thresh",
|
|
.data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh,
|
|
.maxlen = sizeof(int),
|
|
.mode = 0644,
|
|
.proc_handler = proc_dointvec,
|
|
},
|
|
{ }
|
|
};
|
|
|
|
static __net_init int xfrm4_net_sysctl_init(struct net *net)
|
|
{
|
|
struct ctl_table *table;
|
|
struct ctl_table_header *hdr;
|
|
|
|
table = xfrm4_policy_table;
|
|
if (!net_eq(net, &init_net)) {
|
|
table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL);
|
|
if (!table)
|
|
goto err_alloc;
|
|
|
|
table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh;
|
|
}
|
|
|
|
hdr = register_net_sysctl_sz(net, "net/ipv4", table,
|
|
ARRAY_SIZE(xfrm4_policy_table));
|
|
if (!hdr)
|
|
goto err_reg;
|
|
|
|
net->ipv4.xfrm4_hdr = hdr;
|
|
return 0;
|
|
|
|
err_reg:
|
|
if (!net_eq(net, &init_net))
|
|
kfree(table);
|
|
err_alloc:
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static __net_exit void xfrm4_net_sysctl_exit(struct net *net)
|
|
{
|
|
struct ctl_table *table;
|
|
|
|
if (!net->ipv4.xfrm4_hdr)
|
|
return;
|
|
|
|
table = net->ipv4.xfrm4_hdr->ctl_table_arg;
|
|
unregister_net_sysctl_table(net->ipv4.xfrm4_hdr);
|
|
if (!net_eq(net, &init_net))
|
|
kfree(table);
|
|
}
|
|
#else /* CONFIG_SYSCTL */
|
|
static inline int xfrm4_net_sysctl_init(struct net *net)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void xfrm4_net_sysctl_exit(struct net *net)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
static int __net_init xfrm4_net_init(struct net *net)
|
|
{
|
|
int ret;
|
|
|
|
memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
|
|
sizeof(xfrm4_dst_ops_template));
|
|
ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = xfrm4_net_sysctl_init(net);
|
|
if (ret)
|
|
dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void __net_exit xfrm4_net_exit(struct net *net)
|
|
{
|
|
xfrm4_net_sysctl_exit(net);
|
|
dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
|
|
}
|
|
|
|
static struct pernet_operations __net_initdata xfrm4_net_ops = {
|
|
.init = xfrm4_net_init,
|
|
.exit = xfrm4_net_exit,
|
|
};
|
|
|
|
static void __init xfrm4_policy_init(void)
|
|
{
|
|
xfrm_policy_register_afinfo(&xfrm4_policy_afinfo, AF_INET);
|
|
}
|
|
|
|
void __init xfrm4_init(void)
|
|
{
|
|
xfrm4_state_init();
|
|
xfrm4_policy_init();
|
|
xfrm4_protocol_init();
|
|
register_pernet_subsys(&xfrm4_net_ops);
|
|
}
|