| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Sat, 19 Aug 2023 17:32:45 +0800
From: "liujian (CE)" <liujian56@...wei.com>
To: Ferenc Fejes <fejes@....elte.hu>, <john.fastabend@...il.com>,
<jakub@...udflare.com>, <ast@...nel.org>, <daniel@...earbox.net>,
<andrii@...nel.org>, <martin.lau@...ux.dev>, <song@...nel.org>,
<yonghong.song@...ux.dev>, <kpsingh@...nel.org>, <sdf@...gle.com>,
<haoluo@...gle.com>, <jolsa@...nel.org>, <davem@...emloft.net>,
<edumazet@...gle.com>, <kuba@...nel.org>, <pabeni@...hat.com>,
<dsahern@...nel.org>
CC: <netdev@...r.kernel.org>, <bpf@...r.kernel.org>
Subject: Re: [PATCH bpf-next v2 1/7] bpf, sockmap: add BPF_F_PERMANENTLY flag
for skmsg redirect
On 2023/8/17 20:05, Ferenc Fejes wrote:
> Hi Liu!
>
> On Fri, 2023-08-11 at 17:32 +0800, Liu Jian wrote:
>> If the sockmap msg redirection function is used only to forward
>> packets
>> and no other operation, the execution result of the
>> BPF_SK_MSG_VERDICT
>> program is the same each time. In this case, the BPF program only
>> needs to
>> be run once. Add BPF_F_PERMANENTLY flag to bpf_msg_redirect_map() and
>> bpf_msg_redirect_hash() to implement this ability.
>
> Did you considered other names for this flag e.g. BPF_F_SPLICED or
> BPF_F_PIPED?
>
Yes, it's all ok for me.
> BTW good addition, makes sense for the skb case too.
>
Yes, I had planned to modify bpf_sk_redirect_map/hash() if this patch
can be incorporated into the mainline. However, John proposed an
existing solution for this patch, and this patch should not be needed.
I'll post the changes to bpf_sk_redirect_map/hash() separately later?
Hi, John, do you have any suggestions?
>>
>> Then we can enable this function in the bpf program as follows:
>> bpf_msg_redirect_hash(xx, xx, xx, BPF_F_INGRESS | BPF_F_PERMANENTLY);
>>
>> Test results using netperf TCP_STREAM mode:
>> for i in 1 64 128 512 1k 2k 32k 64k 100k 500k 1m;then
>> netperf -T 1,2 -t TCP_STREAM -H 127.0.0.1 -l 20 -- -m $i -s 100m,100m
>> -S 100m,100m
>> done
>>
>> before:
>> 3.84 246.52 496.89 1885.03 3415.29 6375.03 40749.09 48764.40 51611.34
>> 55678.26 55992.78
>> after:
>> 4.43 279.20 555.82 2080.79 3870.70 7105.44 41836.41 49709.75 51861.56
>> 55211.00 54566.85
>>
>> Signed-off-by: Liu Jian <liujian56@...wei.com>
>> ---
>> include/linux/skmsg.h | 1 +
>> include/uapi/linux/bpf.h | 7 +++++--
>> net/core/skmsg.c | 1 +
>> net/core/sock_map.c | 4 ++--
>> net/ipv4/tcp_bpf.c | 21 +++++++++++++++------
>> tools/include/uapi/linux/bpf.h | 7 +++++--
>> 6 files changed, 29 insertions(+), 12 deletions(-)
>>
>> diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
>> index 054d7911bfc9..b2da9c432f52 100644
>> --- a/include/linux/skmsg.h
>> +++ b/include/linux/skmsg.h
>> @@ -82,6 +82,7 @@ struct sk_psock {
>> u32 cork_bytes;
>> u32 eval;
>> bool redir_ingress; /* undefined
>> if sk_redir is null */
>> + bool eval_permanently;
>> struct sk_msg *cork;
>> struct sk_psock_progs progs;
>> #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
>> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
>> index 70da85200695..cf622ea4f018 100644
>> --- a/include/uapi/linux/bpf.h
>> +++ b/include/uapi/linux/bpf.h
>> @@ -3004,7 +3004,8 @@ union bpf_attr {
>> * egress interfaces can be used for redirection. The
>> * **BPF_F_INGRESS** value in *flags* is used to make
>> the
>> * distinction (ingress path is selected if the flag is
>> present,
>> - * egress path otherwise). This is the only flag
>> supported for now.
>> + * egress path otherwise). The **BPF_F_PERMANENTLY**
>> value in
>> + * *flags* is used to indicates whether the eBPF result
>> is permanent.
>> * Return
>> * **SK_PASS** on success, or **SK_DROP** on error.
>> *
>> @@ -3276,7 +3277,8 @@ union bpf_attr {
>> * egress interfaces can be used for redirection. The
>> * **BPF_F_INGRESS** value in *flags* is used to make
>> the
>> * distinction (ingress path is selected if the flag is
>> present,
>> - * egress path otherwise). This is the only flag
>> supported for now.
>> + * egress path otherwise). The **BPF_F_PERMANENTLY**
>> value in
>> + * *flags* is used to indicates whether the eBPF result
>> is permanent.
>> * Return
>> * **SK_PASS** on success, or **SK_DROP** on error.
>> *
>> @@ -5872,6 +5874,7 @@ enum {
>> /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
>> enum {
>> BPF_F_INGRESS = (1ULL << 0),
>> + BPF_F_PERMANENTLY = (1ULL << 1),
>> };
>>
>> /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key
>> flags. */
>> diff --git a/net/core/skmsg.c b/net/core/skmsg.c
>> index a29508e1ff35..b2bf9b5c4252 100644
>> --- a/net/core/skmsg.c
>> +++ b/net/core/skmsg.c
>> @@ -875,6 +875,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct
>> sk_psock *psock,
>> ret = bpf_prog_run_pin_on_cpu(prog, msg);
>> ret = sk_psock_map_verd(ret, msg->sk_redir);
>> psock->apply_bytes = msg->apply_bytes;
>> + psock->eval_permanently = msg->flags & BPF_F_PERMANENTLY;
>> if (ret == __SK_REDIRECT) {
>> if (psock->sk_redir) {
>> sock_put(psock->sk_redir);
>> diff --git a/net/core/sock_map.c b/net/core/sock_map.c
>> index 08ab108206bf..6a0c90be7f4f 100644
>> --- a/net/core/sock_map.c
>> +++ b/net/core/sock_map.c
>> @@ -662,7 +662,7 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *,
>> msg,
>> {
>> struct sock *sk;
>>
>> - if (unlikely(flags & ~(BPF_F_INGRESS)))
>> + if (unlikely(flags & ~(BPF_F_INGRESS | BPF_F_PERMANENTLY)))
>> return SK_DROP;
>>
>> sk = __sock_map_lookup_elem(map, key);
>> @@ -1261,7 +1261,7 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg
>> *, msg,
>> {
>> struct sock *sk;
>>
>> - if (unlikely(flags & ~(BPF_F_INGRESS)))
>> + if (unlikely(flags & ~(BPF_F_INGRESS | BPF_F_PERMANENTLY)))
>> return SK_DROP;
>>
>> sk = __sock_hash_lookup_elem(map, key);
>> diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
>> index 81f0dff69e0b..36cf2b0fa6f8 100644
>> --- a/net/ipv4/tcp_bpf.c
>> +++ b/net/ipv4/tcp_bpf.c
>> @@ -419,8 +419,10 @@ static int tcp_bpf_send_verdict(struct sock *sk,
>> struct sk_psock *psock,
>> if (!psock->apply_bytes) {
>> /* Clean up before releasing the sock lock.
>> */
>> eval = psock->eval;
>> - psock->eval = __SK_NONE;
>> - psock->sk_redir = NULL;
>> + if (!psock->eval_permanently) {
>> + psock->eval = __SK_NONE;
>> + psock->sk_redir = NULL;
>> + }
>> }
>> if (psock->cork) {
>> cork = true;
>> @@ -433,9 +435,15 @@ static int tcp_bpf_send_verdict(struct sock *sk,
>> struct sk_psock *psock,
>> ret = tcp_bpf_sendmsg_redir(sk_redir, redir_ingress,
>> msg, tosend, flags);
>> sent = origsize - msg->sg.size;
>> + /* disable the ability when something wrong */
>> + if (unlikely(ret < 0))
>> + psock->eval_permanently = 0;
>>
>> - if (eval == __SK_REDIRECT)
>> + if (!psock->eval_permanently && eval ==
>> __SK_REDIRECT) {
>> sock_put(sk_redir);
>> + psock->sk_redir = NULL;
>> + psock->eval = __SK_NONE;
>> + }
>>
>> lock_sock(sk);
>> if (unlikely(ret < 0)) {
>> @@ -460,8 +468,8 @@ static int tcp_bpf_send_verdict(struct sock *sk,
>> struct sk_psock *psock,
>> }
>>
>> if (likely(!ret)) {
>> - if (!psock->apply_bytes) {
>> - psock->eval = __SK_NONE;
>> + if (!psock->apply_bytes && !psock->eval_permanently)
>> {
>> + psock->eval = __SK_NONE;
>> if (psock->sk_redir) {
>> sock_put(psock->sk_redir);
>> psock->sk_redir = NULL;
>> @@ -540,7 +548,8 @@ static int tcp_bpf_sendmsg(struct sock *sk,
>> struct msghdr *msg, size_t size)
>> if (psock->cork_bytes && !enospc)
>> goto out_err;
>> /* All cork bytes are accounted, rerun the
>> prog. */
>> - psock->eval = __SK_NONE;
>> + if (!psock->eval_permanently)
>> + psock->eval = __SK_NONE;
>> psock->cork_bytes = 0;
>> }
>>
>> diff --git a/tools/include/uapi/linux/bpf.h
>> b/tools/include/uapi/linux/bpf.h
>> index 70da85200695..cf622ea4f018 100644
>> --- a/tools/include/uapi/linux/bpf.h
>> +++ b/tools/include/uapi/linux/bpf.h
>> @@ -3004,7 +3004,8 @@ union bpf_attr {
>> * egress interfaces can be used for redirection. The
>> * **BPF_F_INGRESS** value in *flags* is used to make
>> the
>> * distinction (ingress path is selected if the flag is
>> present,
>> - * egress path otherwise). This is the only flag
>> supported for now.
>> + * egress path otherwise). The **BPF_F_PERMANENTLY**
>> value in
>> + * *flags* is used to indicates whether the eBPF result
>> is permanent.
>> * Return
>> * **SK_PASS** on success, or **SK_DROP** on error.
>> *
>> @@ -3276,7 +3277,8 @@ union bpf_attr {
>> * egress interfaces can be used for redirection. The
>> * **BPF_F_INGRESS** value in *flags* is used to make
>> the
>> * distinction (ingress path is selected if the flag is
>> present,
>> - * egress path otherwise). This is the only flag
>> supported for now.
>> + * egress path otherwise). The **BPF_F_PERMANENTLY**
>> value in
>> + * *flags* is used to indicates whether the eBPF result
>> is permanent.
>> * Return
>> * **SK_PASS** on success, or **SK_DROP** on error.
>> *
>> @@ -5872,6 +5874,7 @@ enum {
>> /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
>> enum {
>> BPF_F_INGRESS = (1ULL << 0),
>> + BPF_F_PERMANENTLY = (1ULL << 1),
>> };
>>
>> /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key
>> flags. */
>
> Ferenc
>
Powered by blists - more mailing lists