Re: [PATCH net] netfilter: nf_nat_masquerade: recalculate TCP TS offset when port is randomized

[Jiayuan Chen]

On 6/29/26 5:34 PM, xietangxin wrote:
> Problem observed in Kubernetes environments where MASQUERADE target with
> --random-fully is configured by default. after commit
> 165573e41f2f ("tcp: secure_seq: add back ports to TS offset") TCP short
> connection QPS dropped from ~20000 to ~10000. This added source and
> destination ports into TS offset calculation.
>
> However, with MASQUERADE --random-fully, when multiple internal connections
> (e.g sport 10000,20000) are mapped to the same external port (e.g 30000),
> their TS offsets are calculated as ts_offset(10000) and ts_offset(20000).
> If the server reuses the TIME_WAIT slot from the first connection, there is
> a chance that ts_offset(20000) < ts_offset(10000), breaking TSval
> monotonicity for the same 4-tuple and causing RST packets:
>    Client -> Server 24870 -> 80 [SYN] TSval=2294041168
>    Server -> Client 80 -> 24870 [ACK] TSecr=2846236456
>    Client -> Server 24870 -> 80 [RST] Seq=855605690
>
> After nf_nat_setup_info() successfully assigns a new randomized
> source port, recalculate the TS offset using the new port and
> update the SYN packet's TSval accordingly.
>
> Test results on 4U4G VM with
> `./wrk -t8 -c200 -H "Connection: close" -d10s --latency http://5.5.5.5:80`
> Before:
>    random:10712 req/s, random-fully:10986 req/s
> After:
>    random:21463 req/s, random-fully:19181 req/s
>
> Fixes: 165573e41f2f ("tcp: secure_seq: add back ports to TS offset")
> Cc: stable@xxxxxxxxxxxxxxx


I'd treat it as a feature not a fix.


> Closes:https://lore.kernel.org/all/92935c00-e0be-4591-ac44-5978c7804d57@xxxxxxxx/
> Signed-off-by: xietangxin <xietangxin@xxxxxxxxxxxxxx>
> ---
>   net/netfilter/nf_nat_masquerade.c | 91 ++++++++++++++++++++++++++++++-
>   1 file changed, 89 insertions(+), 2 deletions(-)
>
> diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c
> index 4de6e0a51701..8c9ca5a051cc 100644
> --- a/net/netfilter/nf_nat_masquerade.c
> +++ b/net/netfilter/nf_nat_masquerade.c
> @@ -6,8 +6,11 @@
>   #include <linux/netfilter.h>
>   #include <linux/netfilter_ipv4.h>
>   #include <linux/netfilter_ipv6.h>
> +#include <linux/tcp.h>
>   
> +#include <net/tcp.h>
>   #include <net/netfilter/nf_nat_masquerade.h>
> +#include <net/secure_seq.h>
>   
>   struct masq_dev_work {
>   	struct work_struct work;
> @@ -24,6 +27,76 @@ static DEFINE_MUTEX(masq_mutex);
>   static unsigned int masq_refcnt __read_mostly;
>   static atomic_t masq_worker_count __read_mostly;
>   
> +static __be32 *tcp_ts_option_ptr(const struct sk_buff *skb)
> +{
> +	const struct tcphdr *th;
> +	unsigned char *ptr;
> +	unsigned char opsize;
> +	unsigned int optlen, offset;
> +
> +	th = tcp_hdr(skb);
> +	optlen = (th->doff - 5) * 4;
> +	ptr = (unsigned char *)(th + 1);
> +	offset = 0;
> +
> +	while (offset < optlen) {
> +		unsigned char opcode = ptr[offset];
> +
> +		if (opcode == TCPOPT_EOL)
> +			break;
> +		if (opcode == TCPOPT_NOP) {
> +			offset++;
> +			continue;
> +		}
> +
> +		if (offset + 1 >= optlen)
> +			break;
> +
> +		opsize = ptr[offset + 1];
> +		if (opsize < 2 || offset + opsize > optlen)
> +			break;
> +
> +		if (opcode == TCPOPT_TIMESTAMP && opsize == TCPOLEN_TIMESTAMP)
> +			return (__be32 *)(ptr + offset + 2);
> +
> +		offset += opsize;
> +	}
> +
> +	return NULL;
> +}
> +
> +static void masquerade_update_tcp_ts_offset(struct nf_conn *ct, struct sk_buff *skb)
> +{
> +	__be32 *tsptr;
> +	struct net *net;
> +	struct tcphdr *th;
> +	struct tcp_sock *tp;
> +	union tcp_seq_and_ts_off st;
> +	struct nf_conntrack_tuple *tuple;
> +
> +	th = tcp_hdr(skb);
> +	net = nf_ct_net(ct);
> +	tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
> +

why use reply not original, or do I miss something ?