diff mbox series

[v2,net,2/2] ipv4: add net_hash_mix() dispersion to fib_info_laddrhash keys

Message ID 20220119100413.4077866-3-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 warning 1 maintainers not CCed: yoshfuji@linux-ipv6.org
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 No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 7 this patch: 7
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 84 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 1 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 a hash table (fib_info_laddrhash)
in which fib_sync_down_addr() can locate fib_info
based on IPv4 local address.

This hash table is resized based on total number of
hashed fib_info, but the hash function is only
using the local address.

For hosts having many active network namespaces,
all fib_info for loopback devices (IPv4 address 127.0.0.1)
are hashed into a single bucket, making netns dismantles
very slow.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/ipv4/fib_semantics.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

Comments

David Ahern Jan. 19, 2022, 3:40 p.m. UTC | #1 
On 1/19/22 3:04 AM, Eric Dumazet wrote:
> From: Eric Dumazet <edumazet@google.com>
> 
> net/ipv4/fib_semantics.c uses a hash table (fib_info_laddrhash)
> in which fib_sync_down_addr() can locate fib_info
> based on IPv4 local address.
> 
> This hash table is resized based on total number of
> hashed fib_info, but the hash function is only
> using the local address.
> 
> For hosts having many active network namespaces,
> all fib_info for loopback devices (IPv4 address 127.0.0.1)
> are hashed into a single bucket, making netns dismantles
> very slow.
> 
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> ---
>  net/ipv4/fib_semantics.c | 29 +++++++++++++++--------------
>  1 file changed, 15 insertions(+), 14 deletions(-)
> 

Reviewed-by: David Ahern <dsahern@kernel.org>
diff mbox series

Patch

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 9813949da10493de36b9db797b6a5d94fd9bd3b1..b4589861b84c6bc4daa7149e078ad63749c7622f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -52,6 +52,7 @@  static DEFINE_SPINLOCK(fib_info_lock);
 static struct hlist_head *fib_info_hash;
 static struct hlist_head *fib_info_laddrhash;
 static unsigned int fib_info_hash_size;
+static unsigned int fib_info_hash_bits;
 static unsigned int fib_info_cnt;
 
 #define DEVINDEX_HASHBITS 8
@@ -1247,13 +1248,13 @@  int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
 	return err;
 }
 
-static inline unsigned int fib_laddr_hashfn(__be32 val)
+static struct hlist_head *
+fib_info_laddrhash_bucket(const struct net *net, __be32 val)
 {
-	unsigned int mask = (fib_info_hash_size - 1);
+	u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val,
+			   fib_info_hash_bits);
 
-	return ((__force u32)val ^
-		((__force u32)val >> 7) ^
-		((__force u32)val >> 14)) & mask;
+	return &fib_info_laddrhash[slot];
 }
 
 static struct hlist_head *fib_info_hash_alloc(int bytes)
@@ -1289,6 +1290,7 @@  static void fib_info_hash_move(struct hlist_head *new_info_hash,
 	old_info_hash = fib_info_hash;
 	old_laddrhash = fib_info_laddrhash;
 	fib_info_hash_size = new_size;
+	fib_info_hash_bits = ilog2(new_size);
 
 	for (i = 0; i < old_size; i++) {
 		struct hlist_head *head = &fib_info_hash[i];
@@ -1306,21 +1308,20 @@  static void fib_info_hash_move(struct hlist_head *new_info_hash,
 	}
 	fib_info_hash = new_info_hash;
 
+	fib_info_laddrhash = new_laddrhash;
 	for (i = 0; i < old_size; i++) {
-		struct hlist_head *lhead = &fib_info_laddrhash[i];
+		struct hlist_head *lhead = &old_laddrhash[i];
 		struct hlist_node *n;
 		struct fib_info *fi;
 
 		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
 			struct hlist_head *ldest;
-			unsigned int new_hash;
 
-			new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
-			ldest = &new_laddrhash[new_hash];
+			ldest = fib_info_laddrhash_bucket(fi->fib_net,
+							  fi->fib_prefsrc);
 			hlist_add_head(&fi->fib_lhash, ldest);
 		}
 	}
-	fib_info_laddrhash = new_laddrhash;
 
 	spin_unlock_bh(&fib_info_lock);
 
@@ -1605,7 +1606,7 @@  struct fib_info *fib_create_info(struct fib_config *cfg,
 	if (fi->fib_prefsrc) {
 		struct hlist_head *head;
 
-		head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
+		head = fib_info_laddrhash_bucket(net, fi->fib_prefsrc);
 		hlist_add_head(&fi->fib_lhash, head);
 	}
 	if (fi->nh) {
@@ -1877,16 +1878,16 @@  int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
  */
 int fib_sync_down_addr(struct net_device *dev, __be32 local)
 {
-	int ret = 0;
-	unsigned int hash = fib_laddr_hashfn(local);
-	struct hlist_head *head = &fib_info_laddrhash[hash];
 	int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
 	struct net *net = dev_net(dev);
+	struct hlist_head *head;
 	struct fib_info *fi;
+	int ret = 0;
 
 	if (!fib_info_laddrhash || local == 0)
 		return 0;
 
+	head = fib_info_laddrhash_bucket(net, local);
 	hlist_for_each_entry(fi, head, fib_lhash) {
 		if (!net_eq(fi->fib_net, net) ||
 		    fi->fib_tb_id != tb_id)