From: Kuniyuki Iwashima <kuniyu@amazon.com>
To: "David S. Miller" <davem@davemloft.net>,
David Ahern <dsahern@kernel.org>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>,
"Paolo Abeni" <pabeni@redhat.com>,
Simon Horman <horms@kernel.org>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>,
Kuniyuki Iwashima <kuni1840@gmail.com>, <netdev@vger.kernel.org>
Subject: [PATCH v3 net-next 08/12] ipv4: fib: Namespacify fib_info hash tables.
Date: Thu, 27 Feb 2025 20:23:24 -0800 [thread overview]
Message-ID: <20250228042328.96624-9-kuniyu@amazon.com> (raw)
In-Reply-To: <20250228042328.96624-1-kuniyu@amazon.com>
We will convert RTM_NEWROUTE and RTM_DELROUTE to per-netns RTNL.
Then, we need to have per-netns hash tables for struct fib_info.
Let's allocate the hash tables per netns.
fib_info_hash, fib_info_hash_bits, and fib_info_cnt are now moved
to struct netns_ipv4 and accessed with net->ipv4.fib_XXX.
Also, the netns checks are removed from fib_find_info_nh() and
fib_find_info().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
---
include/net/netns/ipv4.h | 3 ++
net/ipv4/fib_semantics.c | 61 +++++++++++++++++-----------------------
2 files changed, 29 insertions(+), 35 deletions(-)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 45ac125e8aeb..650b2dc9199f 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -111,6 +111,9 @@ struct netns_ipv4 {
#endif
struct hlist_head *fib_table_hash;
struct sock *fibnl;
+ struct hlist_head *fib_info_hash;
+ unsigned int fib_info_hash_bits;
+ unsigned int fib_info_cnt;
struct sock *mc_autojoin_sk;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0cd40ff18d8b..f68bb9e34c34 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -50,10 +50,6 @@
#include "fib_lookup.h"
-static struct hlist_head *fib_info_hash;
-static unsigned int fib_info_hash_bits;
-static unsigned int fib_info_cnt;
-
/* for_nexthops and change_nexthops only used when nexthop object
* is not set in a fib_info. The logic within can reference fib_nh.
*/
@@ -256,8 +252,7 @@ void fib_release_info(struct fib_info *fi)
ASSERT_RTNL();
if (fi && refcount_dec_and_test(&fi->fib_treeref)) {
hlist_del(&fi->fib_hash);
-
- fib_info_cnt--;
+ fi->fib_net->ipv4.fib_info_cnt--;
if (fi->fib_prefsrc)
hlist_del(&fi->fib_lhash);
@@ -333,11 +328,12 @@ static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope,
static unsigned int fib_info_hashfn_result(const struct net *net,
unsigned int val)
{
- return hash_32(val ^ net_hash_mix(net), fib_info_hash_bits);
+ return hash_32(val ^ net_hash_mix(net), net->ipv4.fib_info_hash_bits);
}
static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi)
{
+ struct net *net = fi->fib_net;
unsigned int val;
val = fib_info_hashfn_1(fi->fib_nhs, fi->fib_protocol,
@@ -352,16 +348,18 @@ static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi)
} endfor_nexthops(fi)
}
- return &fib_info_hash[fib_info_hashfn_result(fi->fib_net, val)];
+ return &net->ipv4.fib_info_hash[fib_info_hashfn_result(net, val)];
}
static struct hlist_head *fib_info_laddrhash_bucket(const struct net *net,
__be32 val)
{
- u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val,
- fib_info_hash_bits);
+ unsigned int hash_bits = net->ipv4.fib_info_hash_bits;
+ u32 slot;
- return &fib_info_hash[(1 << fib_info_hash_bits) + slot];
+ slot = hash_32(net_hash_mix(net) ^ (__force u32)val, hash_bits);
+
+ return &net->ipv4.fib_info_hash[(1 << hash_bits) + slot];
}
static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits)
@@ -376,22 +374,22 @@ static void fib_info_hash_free(struct hlist_head *head)
kvfree(head);
}
-static void fib_info_hash_grow(void)
+static void fib_info_hash_grow(struct net *net)
{
+ unsigned int old_size = 1 << net->ipv4.fib_info_hash_bits;
struct hlist_head *new_info_hash, *old_info_hash;
- unsigned int old_size = 1 << fib_info_hash_bits;
unsigned int i;
- if (fib_info_cnt < old_size)
+ if (net->ipv4.fib_info_cnt < old_size)
return;
- new_info_hash = fib_info_hash_alloc(fib_info_hash_bits + 1);
+ new_info_hash = fib_info_hash_alloc(net->ipv4.fib_info_hash_bits + 1);
if (!new_info_hash)
return;
- old_info_hash = fib_info_hash;
- fib_info_hash = new_info_hash;
- fib_info_hash_bits += 1;
+ old_info_hash = net->ipv4.fib_info_hash;
+ net->ipv4.fib_info_hash = new_info_hash;
+ net->ipv4.fib_info_hash_bits += 1;
for (i = 0; i < old_size; i++) {
struct hlist_head *head = &old_info_hash[i];
@@ -429,13 +427,12 @@ static struct fib_info *fib_find_info_nh(struct net *net,
(__force u32)cfg->fc_prefsrc,
cfg->fc_priority);
hash = fib_info_hashfn_result(net, hash);
- head = &fib_info_hash[hash];
+ head = &net->ipv4.fib_info_hash[hash];
hlist_for_each_entry(fi, head, fib_hash) {
- if (!net_eq(fi->fib_net, net))
- continue;
if (!fi->nh || fi->nh->id != cfg->fc_nh_id)
continue;
+
if (cfg->fc_protocol == fi->fib_protocol &&
cfg->fc_scope == fi->fib_scope &&
cfg->fc_prefsrc == fi->fib_prefsrc &&
@@ -455,10 +452,9 @@ static struct fib_info *fib_find_info(struct fib_info *nfi)
struct fib_info *fi;
hlist_for_each_entry(fi, head, fib_hash) {
- if (!net_eq(fi->fib_net, nfi->fib_net))
- continue;
if (fi->fib_nhs != nfi->fib_nhs)
continue;
+
if (nfi->fib_protocol == fi->fib_protocol &&
nfi->fib_scope == fi->fib_scope &&
nfi->fib_prefsrc == fi->fib_prefsrc &&
@@ -1406,7 +1402,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
}
#endif
- fib_info_hash_grow();
+ fib_info_hash_grow(net);
fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
if (!fi) {
@@ -1550,7 +1546,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
refcount_set(&fi->fib_treeref, 1);
refcount_set(&fi->fib_clntref, 1);
- fib_info_cnt++;
+ net->ipv4.fib_info_cnt++;
hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
if (fi->fib_prefsrc) {
@@ -2241,22 +2237,17 @@ int __net_init fib4_semantics_init(struct net *net)
{
unsigned int hash_bits = 4;
- if (!net_eq(net, &init_net))
- return 0;
-
- fib_info_hash = fib_info_hash_alloc(hash_bits);
- if (!fib_info_hash)
+ net->ipv4.fib_info_hash = fib_info_hash_alloc(hash_bits);
+ if (!net->ipv4.fib_info_hash)
return -ENOMEM;
- fib_info_hash_bits = hash_bits;
+ net->ipv4.fib_info_hash_bits = hash_bits;
+ net->ipv4.fib_info_cnt = 0;
return 0;
}
void __net_exit fib4_semantics_exit(struct net *net)
{
- if (!net_eq(net, &init_net))
- return;
-
- fib_info_hash_free(fib_info_hash);
+ fib_info_hash_free(net->ipv4.fib_info_hash);
}
--
2.39.5 (Apple Git-154)
next prev parent reply other threads:[~2025-02-28 4:27 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-28 4:23 [PATCH v3 net-next 00/12] ipv4: fib: Convert RTM_NEWROUTE and RTM_DELROUTE to per-netns RTNL Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 01/12] ipv4: fib: Use cached net in fib_inetaddr_event() Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 02/12] ipv4: fib: Allocate fib_info_hash[] and fib_info_laddrhash[] by kvcalloc() Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 03/12] ipv4: fib: Allocate fib_info_hash[] during netns initialisation Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 04/12] ipv4: fib: Make fib_info_hashfn() return struct hlist_head Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 05/12] ipv4: fib: Remove fib_info_laddrhash pointer Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 06/12] ipv4: fib: Remove fib_info_hash_size Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 07/12] ipv4: fib: Add fib_info_hash_grow() Kuniyuki Iwashima
2025-02-28 4:23 ` Kuniyuki Iwashima [this message]
2025-02-28 4:23 ` [PATCH v3 net-next 09/12] ipv4: fib: Hold rtnl_net_lock() for ip_fib_net_exit() Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 10/12] ipv4: fib: Hold rtnl_net_lock() in ip_rt_ioctl() Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 11/12] ipv4: fib: Move fib_valid_key_len() to rtm_to_fib_config() Kuniyuki Iwashima
2025-02-28 4:23 ` [PATCH v3 net-next 12/12] ipv4: fib: Convert RTM_NEWROUTE and RTM_DELROUTE to per-netns RTNL Kuniyuki Iwashima
2025-03-03 23:36 ` [PATCH v3 net-next 00/12] " patchwork-bot+netdevbpf
2025-03-04 14:39 ` Jakub Kicinski
2025-03-04 18:49 ` Kuniyuki Iwashima
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250228042328.96624-9-kuniyu@amazon.com \
--to=kuniyu@amazon.com \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=edumazet@google.com \
--cc=horms@kernel.org \
--cc=kuba@kernel.org \
--cc=kuni1840@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).