summaryrefslogtreecommitdiff
path: root/net/ipv4/route.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/route.c')
-rw-r--r--net/ipv4/route.c228
1 files changed, 94 insertions, 134 deletions
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 02d81d79deeb..f6787c55f6ab 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -21,7 +21,7 @@
* Alan Cox : Added BSD route gw semantics
* Alan Cox : Super /proc >4K
* Alan Cox : MTU in route table
- * Alan Cox : MSS actually. Also added the window
+ * Alan Cox : MSS actually. Also added the window
* clamper.
* Sam Lantinga : Fixed route matching in rt_del()
* Alan Cox : Routing cache support.
@@ -41,7 +41,7 @@
* Olaf Erb : irtt wasn't being copied right.
* Bjorn Ekwall : Kerneld route support.
* Alan Cox : Multicast fixed (I hope)
- * Pavel Krauz : Limited broadcast fixed
+ * Pavel Krauz : Limited broadcast fixed
* Mike McLagan : Routing by source
* Alexey Kuznetsov : End of old history. Split to fib.c and
* route.c and rewritten from scratch.
@@ -54,8 +54,8 @@
* Robert Olsson : Added rt_cache statistics
* Arnaldo C. Melo : Convert proc stuff to seq_file
* Eric Dumazet : hashed spinlocks and rt_check_expire() fixes.
- * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect
- * Ilia Sotnikov : Removed TOS from hash calculations
+ * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect
+ * Ilia Sotnikov : Removed TOS from hash calculations
*/
#define pr_fmt(fmt) "IPv4: " fmt
@@ -66,6 +66,7 @@
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/memblock.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
@@ -234,19 +235,6 @@ static const struct seq_operations rt_cache_seq_ops = {
.show = rt_cache_seq_show,
};
-static int rt_cache_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &rt_cache_seq_ops);
-}
-
-static const struct proc_ops rt_cache_proc_ops = {
- .proc_open = rt_cache_seq_open,
- .proc_read = seq_read,
- .proc_lseek = seq_lseek,
- .proc_release = seq_release,
-};
-
-
static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos)
{
int cpu;
@@ -324,19 +312,6 @@ static const struct seq_operations rt_cpu_seq_ops = {
.show = rt_cpu_seq_show,
};
-
-static int rt_cpu_seq_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &rt_cpu_seq_ops);
-}
-
-static const struct proc_ops rt_cpu_proc_ops = {
- .proc_open = rt_cpu_seq_open,
- .proc_read = seq_read,
- .proc_lseek = seq_lseek,
- .proc_release = seq_release,
-};
-
#ifdef CONFIG_IP_ROUTE_CLASSID
static int rt_acct_proc_show(struct seq_file *m, void *v)
{
@@ -367,13 +342,13 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
- pde = proc_create("rt_cache", 0444, net->proc_net,
- &rt_cache_proc_ops);
+ pde = proc_create_seq("rt_cache", 0444, net->proc_net,
+ &rt_cache_seq_ops);
if (!pde)
goto err1;
- pde = proc_create("rt_cache", 0444,
- net->proc_net_stat, &rt_cpu_proc_ops);
+ pde = proc_create_seq("rt_cache", 0444, net->proc_net_stat,
+ &rt_cpu_seq_ops);
if (!pde)
goto err2;
@@ -478,8 +453,10 @@ static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr)
__ipv4_confirm_neigh(dev, *(__force u32 *)pkey);
}
-#define IP_IDENTS_SZ 2048u
-
+/* Hash tables of size 2048..262144 depending on RAM size.
+ * Each bucket uses 8 bytes.
+ */
+static u32 ip_idents_mask __read_mostly;
static atomic_t *ip_idents __read_mostly;
static u32 *ip_tstamps __read_mostly;
@@ -489,12 +466,16 @@ static u32 *ip_tstamps __read_mostly;
*/
u32 ip_idents_reserve(u32 hash, int segs)
{
- u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ;
- atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
- u32 old = READ_ONCE(*p_tstamp);
- u32 now = (u32)jiffies;
+ u32 bucket, old, now = (u32)jiffies;
+ atomic_t *p_id;
+ u32 *p_tstamp;
u32 delta = 0;
+ bucket = hash & ip_idents_mask;
+ p_tstamp = ip_tstamps + bucket;
+ p_id = ip_idents + bucket;
+ old = READ_ONCE(*p_tstamp);
+
if (old != now && cmpxchg(p_tstamp, old, now) == old)
delta = prandom_u32_max(now - old);
@@ -722,6 +703,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
for_each_possible_cpu(i) {
struct rtable __rcu **prt;
+
prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i);
rt = rcu_dereference(*prt);
if (rt)
@@ -1258,12 +1240,12 @@ static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb)
}
/*
- We do not cache source address of outgoing interface,
- because it is used only by IP RR, TS and SRR options,
- so that it out of fast path.
-
- BTW remember: "addr" is allowed to be not aligned
- in IP options!
+ * We do not cache source address of outgoing interface,
+ * because it is used only by IP RR, TS and SRR options,
+ * so that it out of fast path.
+ *
+ * BTW remember: "addr" is allowed to be not aligned
+ * in IP options!
*/
void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
@@ -2108,7 +2090,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
goto out;
/* Check for the most weird martians, which can be not detected
- by fib_lookup.
+ * by fib_lookup.
*/
tun_info = skb_tunnel_info(skb);
@@ -2246,7 +2228,7 @@ local_input:
if (res->type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
- rth->rt_flags &= ~RTCF_LOCAL;
+ rth->rt_flags &= ~RTCF_LOCAL;
}
if (do_cache) {
@@ -2317,15 +2299,15 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, struct fib_result *res)
{
/* Multicast recognition logic is moved from route cache to here.
- The problem was that too many Ethernet cards have broken/missing
- hardware multicast filters :-( As result the host on multicasting
- network acquires a lot of useless route cache entries, sort of
- SDR messages from all the world. Now we try to get rid of them.
- Really, provided software IP multicast filter is organized
- reasonably (at least, hashed), it does not result in a slowdown
- comparing with route cache reject entries.
- Note, that multicast routers are not affected, because
- route cache entry is created eventually.
+ * The problem was that too many Ethernet cards have broken/missing
+ * hardware multicast filters :-( As result the host on multicasting
+ * network acquires a lot of useless route cache entries, sort of
+ * SDR messages from all the world. Now we try to get rid of them.
+ * Really, provided software IP multicast filter is organized
+ * reasonably (at least, hashed), it does not result in a slowdown
+ * comparing with route cache reject entries.
+ * Note, that multicast routers are not affected, because
+ * route cache entry is created eventually.
*/
if (ipv4_is_multicast(daddr)) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -2537,11 +2519,11 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
rth = ERR_PTR(-ENETUNREACH);
/* I removed check for oif == dev_out->oif here.
- It was wrong for two reasons:
- 1. ip_dev_find(net, saddr) can return wrong iface, if saddr
- is assigned to multiple interfaces.
- 2. Moreover, we are allowed to send packets with saddr
- of another iface. --ANK
+ * It was wrong for two reasons:
+ * 1. ip_dev_find(net, saddr) can return wrong iface, if saddr
+ * is assigned to multiple interfaces.
+ * 2. Moreover, we are allowed to send packets with saddr
+ * of another iface. --ANK
*/
if (fl4->flowi4_oif == 0 &&
@@ -2553,18 +2535,18 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
goto out;
/* Special hack: user can direct multicasts
- and limited broadcast via necessary interface
- without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
- This hack is not just for fun, it allows
- vic,vat and friends to work.
- They bind socket to loopback, set ttl to zero
- and expect that it will work.
- From the viewpoint of routing cache they are broken,
- because we are not allowed to build multicast path
- with loopback source addr (look, routing cache
- cannot know, that ttl is zero, so that packet
- will not leave this host and route is valid).
- Luckily, this hack is good workaround.
+ * and limited broadcast via necessary interface
+ * without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
+ * This hack is not just for fun, it allows
+ * vic,vat and friends to work.
+ * They bind socket to loopback, set ttl to zero
+ * and expect that it will work.
+ * From the viewpoint of routing cache they are broken,
+ * because we are not allowed to build multicast path
+ * with loopback source addr (look, routing cache
+ * cannot know, that ttl is zero, so that packet
+ * will not leave this host and route is valid).
+ * Luckily, this hack is good workaround.
*/
fl4->flowi4_oif = dev_out->ifindex;
@@ -2627,21 +2609,21 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
(ipv4_is_multicast(fl4->daddr) ||
!netif_index_is_l3_master(net, fl4->flowi4_oif))) {
/* Apparently, routing tables are wrong. Assume,
- that the destination is on link.
-
- WHY? DW.
- Because we are allowed to send to iface
- even if it has NO routes and NO assigned
- addresses. When oif is specified, routing
- tables are looked up with only one purpose:
- to catch if destination is gatewayed, rather than
- direct. Moreover, if MSG_DONTROUTE is set,
- we send packet, ignoring both routing tables
- and ifaddr state. --ANK
-
-
- We could make it even if oif is unknown,
- likely IPv6, but we do not.
+ * that the destination is on link.
+ *
+ * WHY? DW.
+ * Because we are allowed to send to iface
+ * even if it has NO routes and NO assigned
+ * addresses. When oif is specified, routing
+ * tables are looked up with only one purpose:
+ * to catch if destination is gatewayed, rather than
+ * direct. Moreover, if MSG_DONTROUTE is set,
+ * we send packet, ignoring both routing tables
+ * and ifaddr state. --ANK
+ *
+ *
+ * We could make it even if oif is unknown,
+ * likely IPv6, but we do not.
*/
if (fl4->saddr == 0)
@@ -2687,44 +2669,15 @@ out:
return rth;
}
-static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
-{
- return NULL;
-}
-
-static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
-{
- unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
-
- return mtu ? : dst->dev->mtu;
-}
-
-static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu,
- bool confirm_neigh)
-{
-}
-
-static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb)
-{
-}
-
-static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
- unsigned long old)
-{
- return NULL;
-}
-
static struct dst_ops ipv4_dst_blackhole_ops = {
- .family = AF_INET,
- .check = ipv4_blackhole_dst_check,
- .mtu = ipv4_blackhole_mtu,
- .default_advmss = ipv4_default_advmss,
- .update_pmtu = ipv4_rt_blackhole_update_pmtu,
- .redirect = ipv4_rt_blackhole_redirect,
- .cow_metrics = ipv4_rt_blackhole_cow_metrics,
- .neigh_lookup = ipv4_neigh_lookup,
+ .family = AF_INET,
+ .default_advmss = ipv4_default_advmss,
+ .neigh_lookup = ipv4_neigh_lookup,
+ .check = dst_blackhole_check,
+ .cow_metrics = dst_blackhole_cow_metrics,
+ .update_pmtu = dst_blackhole_update_pmtu,
+ .redirect = dst_blackhole_redirect,
+ .mtu = dst_blackhole_mtu,
};
struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
@@ -3582,18 +3535,25 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
int __init ip_rt_init(void)
{
+ void *idents_hash;
int cpu;
- ip_idents = kmalloc_array(IP_IDENTS_SZ, sizeof(*ip_idents),
- GFP_KERNEL);
- if (!ip_idents)
- panic("IP: failed to allocate ip_idents\n");
+ /* For modern hosts, this will use 2 MB of memory */
+ idents_hash = alloc_large_system_hash("IP idents",
+ sizeof(*ip_idents) + sizeof(*ip_tstamps),
+ 0,
+ 16, /* one bucket per 64 KB */
+ HASH_ZERO,
+ NULL,
+ &ip_idents_mask,
+ 2048,
+ 256*1024);
+
+ ip_idents = idents_hash;
- prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+ prandom_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents));
- ip_tstamps = kcalloc(IP_IDENTS_SZ, sizeof(*ip_tstamps), GFP_KERNEL);
- if (!ip_tstamps)
- panic("IP: failed to allocate ip_tstamps\n");
+ ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents);
for_each_possible_cpu(cpu) {
struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
generated by cgit v1.2.3 (git 2.39.0) at 2024-07-09 20:49:45 +0300