diff mbox series

[v2,net,1/2] ipv4: avoid quadratic behavior in netns dismantle

Message ID 20220119100413.4077866-2-eric.dumazet@gmail.com (mailing list archive)
State Accepted
Delegated to: Netdev Maintainers
Headers show
Series ipv4: avoid pathological hash tables | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net
netdev/fixes_present success Fixes tag present in non-next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 2 this patch: 2
netdev/cc_maintainers fail 1 blamed authors not CCed: xemul@parallels.com; 2 maintainers not CCed: yoshfuji@linux-ipv6.org xemul@parallels.com
netdev/build_clang success Errors and warnings before: 22 this patch: 22
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 7 this patch: 7
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 93 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Eric Dumazet Jan. 19, 2022, 10:04 a.m. UTC 
From: Eric Dumazet <edumazet@google.com>

net/ipv4/fib_semantics.c uses an hash table of 256 slots,
keyed by device ifindexes: fib_info_devhash[DEVINDEX_HASHSIZE]

Problem is that with network namespaces, devices tend
to use the same ifindex.

lo device for instance has a fixed ifindex of one,
for all network namespaces.

This means that hosts with thousands of netns spend
a lot of time looking at some hash buckets with thousands
of elements, notably at netns dismantle.

Simply add a per netns perturbation (net_hash_mix())
to spread elements more uniformely.

Also change fib_devindex_hashfn() to use more entropy.

Fixes: aa79e66eee5d ("net: Make ifindex generation per-net namespace")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
---
 net/ipv4/fib_semantics.c | 36 +++++++++++++++++-------------------
 1 file changed, 17 insertions(+), 19 deletions(-)
diff mbox series

Patch

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 45619c005b8dddd7ccd5c7029efa4ed69b6ce1de..9813949da10493de36b9db797b6a5d94fd9bd3b1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -29,6 +29,7 @@ 
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/netlink.h>
+#include <linux/hash.h>
 
 #include <net/arp.h>
 #include <net/ip.h>
@@ -319,11 +320,15 @@  static inline int nh_comp(struct fib_info *fi, struct fib_info *ofi)
 
 static inline unsigned int fib_devindex_hashfn(unsigned int val)
 {
-	unsigned int mask = DEVINDEX_HASHSIZE - 1;
+	return hash_32(val, DEVINDEX_HASHBITS);
+}
 
-	return (val ^
-		(val >> DEVINDEX_HASHBITS) ^
-		(val >> (DEVINDEX_HASHBITS * 2))) & mask;
+static struct hlist_head *
+fib_info_devhash_bucket(const struct net_device *dev)
+{
+	u32 val = net_hash_mix(dev_net(dev)) ^ dev->ifindex;
+
+	return &fib_info_devhash[fib_devindex_hashfn(val)];
 }
 
 static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope,
@@ -433,12 +438,11 @@  int ip_fib_check_default(__be32 gw, struct net_device *dev)
 {
 	struct hlist_head *head;
 	struct fib_nh *nh;
-	unsigned int hash;
 
 	spin_lock(&fib_info_lock);
 
-	hash = fib_devindex_hashfn(dev->ifindex);
-	head = &fib_info_devhash[hash];
+	head = fib_info_devhash_bucket(dev);
+
 	hlist_for_each_entry(nh, head, nh_hash) {
 		if (nh->fib_nh_dev == dev &&
 		    nh->fib_nh_gw4 == gw &&
@@ -1609,12 +1613,10 @@  struct fib_info *fib_create_info(struct fib_config *cfg,
 	} else {
 		change_nexthops(fi) {
 			struct hlist_head *head;
-			unsigned int hash;
 
 			if (!nexthop_nh->fib_nh_dev)
 				continue;
-			hash = fib_devindex_hashfn(nexthop_nh->fib_nh_dev->ifindex);
-			head = &fib_info_devhash[hash];
+			head = fib_info_devhash_bucket(nexthop_nh->fib_nh_dev);
 			hlist_add_head(&nexthop_nh->nh_hash, head);
 		} endfor_nexthops(fi)
 	}
@@ -1966,8 +1968,7 @@  void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig)
 
 void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
 {
-	unsigned int hash = fib_devindex_hashfn(dev->ifindex);
-	struct hlist_head *head = &fib_info_devhash[hash];
+	struct hlist_head *head = fib_info_devhash_bucket(dev);
 	struct fib_nh *nh;
 
 	hlist_for_each_entry(nh, head, nh_hash) {
@@ -1986,12 +1987,11 @@  void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
  */
 int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 {
-	int ret = 0;
-	int scope = RT_SCOPE_NOWHERE;
+	struct hlist_head *head = fib_info_devhash_bucket(dev);
 	struct fib_info *prev_fi = NULL;
-	unsigned int hash = fib_devindex_hashfn(dev->ifindex);
-	struct hlist_head *head = &fib_info_devhash[hash];
+	int scope = RT_SCOPE_NOWHERE;
 	struct fib_nh *nh;
+	int ret = 0;
 
 	if (force)
 		scope = -1;
@@ -2136,7 +2136,6 @@  static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 int fib_sync_up(struct net_device *dev, unsigned char nh_flags)
 {
 	struct fib_info *prev_fi;
-	unsigned int hash;
 	struct hlist_head *head;
 	struct fib_nh *nh;
 	int ret;
@@ -2152,8 +2151,7 @@  int fib_sync_up(struct net_device *dev, unsigned char nh_flags)
 	}
 
 	prev_fi = NULL;
-	hash = fib_devindex_hashfn(dev->ifindex);
-	head = &fib_info_devhash[hash];
+	head = fib_info_devhash_bucket(dev);
 	ret = 0;
 
 	hlist_for_each_entry(nh, head, nh_hash) {