From: Kuniyuki Iwashima <kuniyu@amazon.com>
To: "David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Jeff Layton <jlayton@kernel.org>,
Chuck Lever <chuck.lever@oracle.com>,
Luis Chamberlain <mcgrof@kernel.org>,
Kees Cook <keescook@chromium.org>,
Iurii Zaikin <yzaikin@google.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>,
Kuniyuki Iwashima <kuni1840@gmail.com>, <netdev@vger.kernel.org>,
<linux-fsdevel@vger.kernel.org>
Subject: [PATCH v1 net-next 12/13] udp: Access &udp_table via net.
Date: Thu, 25 Aug 2022 17:04:44 -0700 [thread overview]
Message-ID: <20220826000445.46552-13-kuniyu@amazon.com> (raw)
In-Reply-To: <20220826000445.46552-1-kuniyu@amazon.com>
We will soon introduce an optional per-netns hash table
for UDP.
This means we cannot use udp_table directly in most places.
Instead, access it via net->ipv4.udp_table.
The access will be valid only while initialising udp_table
itself and creating/destroying each netns.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
---
net/core/filter.c | 4 ++--
net/ipv4/udp.c | 23 +++++++++++++----------
net/ipv4/udp_diag.c | 6 +++---
net/ipv4/udp_offload.c | 5 +++--
net/ipv6/udp.c | 19 +++++++++++--------
net/ipv6/udp_offload.c | 5 +++--
6 files changed, 35 insertions(+), 27 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index dd5844033b66..38b247f5de24 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6484,7 +6484,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
else
sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport,
dst4, tuple->ipv4.dport,
- dif, sdif, &udp_table, NULL);
+ dif, sdif, net->ipv4.udp_table, NULL);
#if IS_ENABLED(CONFIG_IPV6)
} else {
struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
@@ -6500,7 +6500,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
src6, tuple->ipv6.sport,
dst6, tuple->ipv6.dport,
dif, sdif,
- &udp_table, NULL);
+ net->ipv4.udp_table, NULL);
#endif
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 17b4b175fc67..f4825e38762a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -478,7 +478,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net,
struct sock *sk, *reuse_sk;
bool no_reuseport;
- if (udptable != &udp_table)
+ if (udptable != net->ipv4.udp_table)
return NULL; /* only UDP is supported */
no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport,
@@ -559,10 +559,11 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
- return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+ return __udp4_lib_lookup(net, iph->saddr, sport,
iph->daddr, dport, inet_iif(skb),
- inet_sdif(skb), &udp_table, NULL);
+ inet_sdif(skb), net->ipv4.udp_table, NULL);
}
/* Must be called under rcu_read_lock().
@@ -575,7 +576,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
struct sock *sk;
sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,
- dif, 0, &udp_table, NULL);
+ dif, 0, net->ipv4.udp_table, NULL);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
@@ -810,7 +811,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
int udp_err(struct sk_buff *skb, u32 info)
{
- return __udp4_lib_err(skb, info, &udp_table);
+ return __udp4_lib_err(skb, info, dev_net(skb->dev)->ipv4.udp_table);
}
/*
@@ -2535,13 +2536,14 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
__be16 rmt_port, __be32 rmt_addr,
int dif, int sdif)
{
+ struct udp_table *udptable = net->ipv4.udp_table;
unsigned short hnum = ntohs(loc_port);
struct sock *sk, *result;
struct udp_hslot *hslot;
unsigned int slot;
- slot = udp_hashfn(net, hnum, udp_table.mask);
- hslot = &udp_table.hash[slot];
+ slot = udp_hashfn(net, hnum, udptable->mask);
+ hslot = &udptable->hash[slot];
/* Do not bother scanning a too big list */
if (hslot->count > 10)
@@ -2569,6 +2571,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
__be16 rmt_port, __be32 rmt_addr,
int dif, int sdif)
{
+ struct udp_table *udptable = net->ipv4.udp_table;
INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr);
unsigned short hnum = ntohs(loc_port);
unsigned int hash2, slot2;
@@ -2577,8 +2580,8 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
struct sock *sk;
hash2 = ipv4_portaddr_hash(net, loc_addr, hnum);
- slot2 = hash2 & udp_table.mask;
- hslot2 = &udp_table.hash2[slot2];
+ slot2 = hash2 & udptable->mask;
+ hslot2 = &udptable->hash2[slot2];
ports = INET_COMBINED_PORTS(rmt_port, hnum);
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
@@ -2660,7 +2663,7 @@ int udp_v4_early_demux(struct sk_buff *skb)
int udp_rcv(struct sk_buff *skb)
{
- return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP);
+ return __udp4_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP);
}
void udp_destroy_sock(struct sock *sk)
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 1ed8c4d78e5c..de3f2d31f510 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -147,13 +147,13 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb,
static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
const struct inet_diag_req_v2 *r)
{
- udp_dump(&udp_table, skb, cb, r);
+ udp_dump(sock_net(cb->skb->sk)->ipv4.udp_table, skb, cb, r);
}
static int udp_diag_dump_one(struct netlink_callback *cb,
const struct inet_diag_req_v2 *req)
{
- return udp_dump_one(&udp_table, cb, req);
+ return udp_dump_one(sock_net(cb->skb->sk)->ipv4.udp_table, cb, req);
}
static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
@@ -225,7 +225,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
static int udp_diag_destroy(struct sk_buff *in_skb,
const struct inet_diag_req_v2 *req)
{
- return __udp_diag_destroy(in_skb, req, &udp_table);
+ return __udp_diag_destroy(in_skb, req, sock_net(in_skb->sk)->ipv4.udp_table);
}
static int udplite_diag_destroy(struct sk_buff *in_skb,
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 6d1a4bec2614..aedde65e2268 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -600,10 +600,11 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
__be16 dport)
{
const struct iphdr *iph = skb_gro_network_header(skb);
+ struct net *net = dev_net(skb->dev);
- return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+ return __udp4_lib_lookup(net, iph->saddr, sport,
iph->daddr, dport, inet_iif(skb),
- inet_sdif(skb), &udp_table, NULL);
+ inet_sdif(skb), net->ipv4.udp_table, NULL);
}
INDIRECT_CALLABLE_SCOPE
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 8abf16c5a8a1..739a8c86f0b6 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -203,7 +203,7 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net,
struct sock *sk, *reuse_sk;
bool no_reuseport;
- if (udptable != &udp_table)
+ if (udptable != net->ipv4.udp_table)
return NULL; /* only UDP is supported */
no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport,
@@ -284,10 +284,11 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
+ struct net *net = dev_net(skb->dev);
- return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
+ return __udp6_lib_lookup(net, &iph->saddr, sport,
&iph->daddr, dport, inet6_iif(skb),
- inet6_sdif(skb), &udp_table, NULL);
+ inet6_sdif(skb), net->ipv4.udp_table, NULL);
}
/* Must be called under rcu_read_lock().
@@ -300,7 +301,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be
struct sock *sk;
sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport,
- dif, 0, &udp_table, NULL);
+ dif, 0, net->ipv4.udp_table, NULL);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
@@ -667,7 +668,8 @@ static __inline__ int udpv6_err(struct sk_buff *skb,
struct inet6_skb_parm *opt, u8 type,
u8 code, int offset, __be32 info)
{
- return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
+ return __udp6_lib_err(skb, opt, type, code, offset, info,
+ dev_net(skb->dev)->ipv4.udp_table);
}
static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
@@ -1035,6 +1037,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
__be16 rmt_port, const struct in6_addr *rmt_addr,
int dif, int sdif)
{
+ struct udp_table *udptable = net->ipv4.udp_table;
unsigned short hnum = ntohs(loc_port);
unsigned int hash2, slot2;
struct udp_hslot *hslot2;
@@ -1042,8 +1045,8 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
struct sock *sk;
hash2 = ipv6_portaddr_hash(net, loc_addr, hnum);
- slot2 = hash2 & udp_table.mask;
- hslot2 = &udp_table.hash2[slot2];
+ slot2 = hash2 & udptable->mask;
+ hslot2 = &udptable->hash2[slot2];
ports = INET_COMBINED_PORTS(rmt_port, hnum);
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
@@ -1099,7 +1102,7 @@ void udp_v6_early_demux(struct sk_buff *skb)
INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb)
{
- return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
+ return __udp6_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP);
}
/*
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 7720d04ed396..e0e10f6bcdc1 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -116,10 +116,11 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
__be16 dport)
{
const struct ipv6hdr *iph = skb_gro_network_header(skb);
+ struct net *net = dev_net(skb->dev);
- return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
+ return __udp6_lib_lookup(net, &iph->saddr, sport,
&iph->daddr, dport, inet6_iif(skb),
- inet6_sdif(skb), &udp_table, NULL);
+ inet6_sdif(skb), net->ipv4.udp_table, NULL);
}
INDIRECT_CALLABLE_SCOPE
--
2.30.2
next prev parent reply other threads:[~2022-08-26 0:09 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-26 0:04 [PATCH v1 net-next 00/13] tcp/udp: Introduce optional per-netns hash table Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 01/13] fs/lock: Revive LOCK_MAND Kuniyuki Iwashima
2022-08-26 10:02 ` Jeff Layton
2022-08-26 16:48 ` Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 02/13] sysctl: Support LOCK_MAND for read/write Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 03/13] selftest: sysctl: Add test for flock(LOCK_MAND) Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 04/13] net: Introduce init2() for pernet_operations Kuniyuki Iwashima
2022-08-26 15:20 ` Eric Dumazet
2022-08-26 17:03 ` Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 05/13] tcp: Clean up some functions Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 06/13] tcp: Set NULL to sk->sk_prot->h.hashinfo Kuniyuki Iwashima
2022-08-26 15:40 ` Eric Dumazet
2022-08-26 17:26 ` Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 07/13] tcp: Access &tcp_hashinfo via net Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 08/13] tcp: Introduce optional per-netns ehash Kuniyuki Iwashima
2022-08-26 15:24 ` Eric Dumazet
2022-08-26 17:19 ` Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 09/13] udp: Clean up some functions Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 10/13] udp: Set NULL to sk->sk_prot->h.udp_table Kuniyuki Iwashima
2022-08-26 0:04 ` [PATCH v1 net-next 11/13] udp: Set NULL to udp_seq_afinfo.udp_table Kuniyuki Iwashima
2022-08-26 0:04 ` Kuniyuki Iwashima [this message]
2022-08-26 0:04 ` [PATCH v1 net-next 13/13] udp: Introduce optional per-netns hash table Kuniyuki Iwashima
2022-08-26 15:17 ` [PATCH v1 net-next 00/13] tcp/udp: " Eric Dumazet
2022-08-26 16:51 ` 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=20220826000445.46552-13-kuniyu@amazon.com \
--to=kuniyu@amazon.com \
--cc=chuck.lever@oracle.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=jlayton@kernel.org \
--cc=keescook@chromium.org \
--cc=kuba@kernel.org \
--cc=kuni1840@gmail.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=mcgrof@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=yzaikin@google.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).