Received-SPF: pass (google.com: domain of linux-kernel+bounces-158120-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Message-ID: <3878c16b-d6be-4935-a1ca-7f37dc677c59@redhat.com>
Date: Thu, 25 Apr 2024 09:23:50 +0200
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH net-next 2/8] net: psample: add multicast filtering on
 group_id
To: Jiri Pirko <jiri@resnulli.us>
Cc: netdev@vger.kernel.org, aconole@redhat.com, echaudro@redhat.com,
 horms@kernel.org, i.maximets@ovn.org, Yotam Gigi <yotam.gi@gmail.com>,
 "David S. Miller" <davem@davemloft.net>, Eric Dumazet <edumazet@google.com>,
 Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
 linux-kernel@vger.kernel.org
References: <20240424135109.3524355-1-amorenoz@redhat.com>
 <20240424135109.3524355-3-amorenoz@redhat.com> <ZikdFbmAbT5bWNxa@nanopsycho>
Content-Language: en-US
From: Adrian Moreno <amorenoz@redhat.com>
In-Reply-To: <ZikdFbmAbT5bWNxa@nanopsycho>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit


On 4/24/24 16:54, Jiri Pirko wrote:
> Wed, Apr 24, 2024 at 03:50:49PM CEST, amorenoz@redhat.com wrote:
>> Packet samples can come from several places (e.g: different tc sample
>> actions), typically using the sample group (PSAMPLE_ATTR_SAMPLE_GROUP)
>> to differentiate them.
>>
>> Likewise, sample consumers that listen on the multicast group may only
>> be interested on a single group. However, they are currently forced to
>> receive all samples and discard the ones that are not relevant, causing
>> unnecessary overhead.
>>
>> Allow users to filter on the desired group_id by adding a new command
>> PSAMPLE_SET_FILTER that can be used to pass the desired group id.
>> Store this filter on the per-socket private pointer and use it for
>> filtering multicasted samples.
>>
>> Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
>> ---
>> include/uapi/linux/psample.h |   1 +
>> net/psample/psample.c        | 110 +++++++++++++++++++++++++++++++++--
>> 2 files changed, 105 insertions(+), 6 deletions(-)
>>
>> diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h
>> index e585db5bf2d2..9d62983af0a4 100644
>> --- a/include/uapi/linux/psample.h
>> +++ b/include/uapi/linux/psample.h
>> @@ -28,6 +28,7 @@ enum psample_command {
>> 	PSAMPLE_CMD_GET_GROUP,
>> 	PSAMPLE_CMD_NEW_GROUP,
>> 	PSAMPLE_CMD_DEL_GROUP,
>> +	PSAMPLE_CMD_SET_FILTER,
>> };
>>
>> enum psample_tunnel_key_attr {
>> diff --git a/net/psample/psample.c b/net/psample/psample.c
>> index a5d9b8446f77..f5f77515b969 100644
>> --- a/net/psample/psample.c
>> +++ b/net/psample/psample.c
>> @@ -98,13 +98,77 @@ static int psample_nl_cmd_get_group_dumpit(struct sk_buff *msg,
>> 	return msg->len;
>> }
>>
>> -static const struct genl_small_ops psample_nl_ops[] = {
>> +struct psample_obj_desc {
>> +	struct rcu_head rcu;
>> +	u32 group_num;
>> +};
>> +
>> +struct psample_nl_sock_priv {
>> +	struct psample_obj_desc __rcu *filter;
>> +	spinlock_t filter_lock; /* Protects filter. */
>> +};
>> +
>> +static void psample_nl_sock_priv_init(void *priv)
>> +{
>> +	struct psample_nl_sock_priv *sk_priv = priv;
>> +
>> +	spin_lock_init(&sk_priv->filter_lock);
>> +}
>> +
>> +static void psample_nl_sock_priv_destroy(void *priv)
>> +{
>> +	struct psample_nl_sock_priv *sk_priv = priv;
>> +	struct psample_obj_desc *filter;
>> +
>> +	filter = rcu_dereference_protected(sk_priv->filter, true);
>> +	kfree_rcu(filter, rcu);
>> +}
>> +
>> +static int psample_nl_set_filter_doit(struct sk_buff *skb,
>> +				      struct genl_info *info)
>> +{
>> +	struct psample_obj_desc *filter = NULL;
>> +	struct psample_nl_sock_priv *sk_priv;
>> +	struct nlattr **attrs = info->attrs;
>> +
>> +	if (attrs[PSAMPLE_ATTR_SAMPLE_GROUP]) {
>> +		filter = kzalloc(sizeof(*filter), GFP_KERNEL);
>> +		filter->group_num =
>> +			nla_get_u32(attrs[PSAMPLE_ATTR_SAMPLE_GROUP]);
>> +	}
>> +
>> +	sk_priv = genl_sk_priv_get(&psample_nl_family, NETLINK_CB(skb).sk);
>> +	if (IS_ERR(sk_priv)) {
>> +		kfree(filter);
>> +		return PTR_ERR(sk_priv);
>> +	}
>> +
>> +	spin_lock(&sk_priv->filter_lock);
>> +	filter = rcu_replace_pointer(sk_priv->filter, filter,
>> +				     lockdep_is_held(&sk_priv->filter_lock));
>> +	spin_unlock(&sk_priv->filter_lock);
>> +	kfree_rcu(filter, rcu);
>> +	return 0;
>> +}
>> +
>> +static const struct nla_policy
>> +psample_set_filter_policy[PSAMPLE_ATTR_SAMPLE_GROUP + 1] = {
>> +	[PSAMPLE_ATTR_SAMPLE_GROUP] = { .type = NLA_U32, },
>> +};
>> +
>> +static const struct genl_ops psample_nl_ops[] = {
>> 	{
>> 		.cmd = PSAMPLE_CMD_GET_GROUP,
>> 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
>> 		.dumpit = psample_nl_cmd_get_group_dumpit,
>> 		/* can be retrieved by unprivileged users */
>> -	}
>> +	},
>> +	{
>> +		.cmd		= PSAMPLE_CMD_SET_FILTER,
>> +		.doit		= psample_nl_set_filter_doit,
>> +		.policy		= psample_set_filter_policy,
>> +		.flags		= 0,
>> +	},
> 
> Sidenote:
> Did you think about converting psample to split ops and to introcude
> ynl spec file for it?
>  

If split opts are preferred then sure, I can do that.

Thanks.

>> };
>>
>> static struct genl_family psample_nl_family __ro_after_init = {
>> @@ -114,10 +178,13 @@ static struct genl_family psample_nl_family __ro_after_init = {
>> 	.netnsok	= true,
>> 	.module		= THIS_MODULE,
>> 	.mcgrps		= psample_nl_mcgrps,
>> -	.small_ops	= psample_nl_ops,
>> -	.n_small_ops	= ARRAY_SIZE(psample_nl_ops),
>> +	.ops		= psample_nl_ops,
>> +	.n_ops		= ARRAY_SIZE(psample_nl_ops),
>> 	.resv_start_op	= PSAMPLE_CMD_GET_GROUP + 1,
>> 	.n_mcgrps	= ARRAY_SIZE(psample_nl_mcgrps),
>> +	.sock_priv_size		= sizeof(struct psample_nl_sock_priv),
>> +	.sock_priv_init		= psample_nl_sock_priv_init,
>> +	.sock_priv_destroy	= psample_nl_sock_priv_destroy,
>> };
>>
>> static void psample_group_notify(struct psample_group *group,
>> @@ -360,6 +427,32 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info)
>> }
>> #endif
>>
>> +static inline void psample_nl_obj_desc_init(struct psample_obj_desc *desc,
>> +					    u32 group_num)
>> +{
>> +	memset(desc, 0, sizeof(*desc));
>> +	desc->group_num = group_num;
>> +}
>> +
>> +static int psample_nl_sample_filter(struct sock *dsk, struct sk_buff *skb,
>> +				    void *data)
>> +{
>> +	struct psample_obj_desc *desc = data;
>> +	struct psample_nl_sock_priv *sk_priv;
>> +	struct psample_obj_desc *filter;
>> +	int ret = 0;
>> +
>> +	rcu_read_lock();
>> +	sk_priv = __genl_sk_priv_get(&psample_nl_family, dsk);
>> +	if (!IS_ERR_OR_NULL(sk_priv)) {
>> +		filter = rcu_dereference(sk_priv->filter);
>> +		if (filter && desc)
>> +			ret = (filter->group_num != desc->group_num);
>> +	}
>> +	rcu_read_unlock();
>> +	return ret;
>> +}
>> +
>> void psample_sample_packet(struct psample_group *group, struct sk_buff *skb,
>> 			   u32 sample_rate, const struct psample_metadata *md)
>> {
>> @@ -370,6 +463,7 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb,
>> #ifdef CONFIG_INET
>> 	struct ip_tunnel_info *tun_info;
>> #endif
>> +	struct psample_obj_desc desc;
>> 	struct sk_buff *nl_skb;
>> 	int data_len;
>> 	int meta_len;
>> @@ -487,8 +581,12 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb,
>> #endif
>>
>> 	genlmsg_end(nl_skb, data);
>> -	genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0,
>> -				PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC);
>> +	psample_nl_obj_desc_init(&desc, group->group_num);
>> +	genlmsg_multicast_netns_filtered(&psample_nl_family,
>> +					 group->net, nl_skb, 0,
>> +					 PSAMPLE_NL_MCGRP_SAMPLE,
>> +					 GFP_ATOMIC, psample_nl_sample_filter,
>> +					 &desc);
>>
>> 	return;
>> error:
>> -- 
>> 2.44.0
>>
>>
>