From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from out-170.mta1.migadu.com (out-170.mta1.migadu.com [95.215.58.170]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EDCB133A6EB for ; Tue, 24 Mar 2026 18:31:04 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=95.215.58.170 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774377066; cv=none; b=D7KWZXF6i2vxdi55zO5fNuzBIXaJxuiv0S+tOme+6BzMQ9JVqtKv1oMVMRzY4J5/aA8a/xEf/H2HxivFeTBzq9/1M+DfZd67zzlEQfmKTbG1IYy8KZpurTHLoLUePzTGFaseWDyRpALmFyDdZA/NPaYXDb6RU6m8mNFxV670HeM= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1774377066; c=relaxed/simple; bh=CkRrkLNRGh2zCKqsmt+SPMhud/dqY9HlhebCsfTZwIk=; h=Message-ID:Date:MIME-Version:Subject:To:Cc:References:From: In-Reply-To:Content-Type; b=Zu79p7Q6JT9wm3Ejzo49u3cnvy870LWMxPTbhqSKK+UflJfArSaZ6Gt6tqAnRuhfBboSSx83adI+6MeaU/rTQfx9/NRYUcve38t4qPWOoyrJQIMU8b/aVy5ac05FhlYGOB/kjARdHpndTUTJZfyW9ldqLVF3CIvh1ff6AB81+f4= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=Z8NJKZP7; arc=none smtp.client-ip=95.215.58.170 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="Z8NJKZP7" Message-ID: <60a0b32d-b02b-419d-9d71-3293261333cb@linux.dev> DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1774377053; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=L9fTdPH1aCElwFWRzX6/IMyrZGmyXLUmrj2QhF1Rny8=; b=Z8NJKZP7HM7wGHfKLM8Ss8Ax9rDQPBpQYbWcL07MZeQyaZOv2IO9cTyo9gxuocOvQVRXZ7 xXfOsngesNEjmU2La6z3/JHRpyeiUq2oDdPmK1AhF6mgWipwraJAlFd04xtHSJCLSG/zmp 9eYQy+0MUyARbKGBLLoYBuInpOinqSc= Date: Tue, 24 Mar 2026 11:30:43 -0700 Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Subject: Re: [PATCH v2 4/5] bpf: allow new DECAP flags and add guard rails To: Nick Hudson Cc: Willem de Bruijn , Max Tottenham , Anna Glasgall , Daniel Borkmann , Alexei Starovoitov , Andrii Nakryiko , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , bpf@vger.kernel.org, netdev@vger.kernel.org, linux-kernel@vger.kernel.org References: <20260318134242.2725749-1-nhudson@akamai.com> <20260318134242.2725749-5-nhudson@akamai.com> Content-Language: en-US X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. From: Martin KaFai Lau In-Reply-To: <20260318134242.2725749-5-nhudson@akamai.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Migadu-Flow: FLOW_OUT On 3/18/26 6:42 AM, Nick Hudson wrote: > Add checks to require shrink-only decap, reject conflicting decap flag > combinations, and verify removed length is sufficient for claimed header > decapsulation. > > Co-developed-by: Max Tottenham > Signed-off-by: Max Tottenham > Co-developed-by: Anna Glasgall > Signed-off-by: Anna Glasgall > Signed-off-by: Nick Hudson > --- > net/core/filter.c | 47 +++++++++++++++++++++++++++++++++++++---------- > 1 file changed, 37 insertions(+), 10 deletions(-) > > diff --git a/net/core/filter.c b/net/core/filter.c > index 7c2871b40fe4..47aec44a9cd3 100644 > --- a/net/core/filter.c > +++ b/net/core/filter.c > @@ -56,6 +56,7 @@ > #include > #include > #include > +#include > #include > #include > #include > @@ -3496,7 +3497,9 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb) > BPF_F_ADJ_ROOM_ENCAP_L2( \ > BPF_ADJ_ROOM_ENCAP_L2_MASK)) > > -#define BPF_F_ADJ_ROOM_DECAP_MASK (BPF_F_ADJ_ROOM_DECAP_L3_MASK) > +#define BPF_F_ADJ_ROOM_DECAP_MASK (BPF_F_ADJ_ROOM_DECAP_L3_MASK | \ > + BPF_F_ADJ_ROOM_DECAP_L4_MASK | \ > + BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK) > > #define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \ > BPF_F_ADJ_ROOM_ENCAP_MASK | \ > @@ -3743,20 +3746,44 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, > return -ENOTSUPP; > } > > - if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { > + if (flags & BPF_F_ADJ_ROOM_DECAP_MASK) { This change should be done together with the macro refactoring patch mentioned in patch 3. > + u32 len_decap_min = 0; > + > if (!shrink) > return -EINVAL; > > - switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { > - case BPF_F_ADJ_ROOM_DECAP_L3_IPV4: > + /* Reject mutually exclusive decap flag pairs. */ > + if ((flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) == > + BPF_F_ADJ_ROOM_DECAP_L3_MASK) iiuc, this 'if' and the len_min assignment changes below replace the existing switch case. Please separate this no-op change from the new flag validation logic. It is small enough to be done together in the macro refactoring patch also. > + return -EINVAL; > + > + if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_MASK) == > + BPF_F_ADJ_ROOM_DECAP_L4_MASK) > + return -EINVAL; > + > + if ((flags & BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK) == > + BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK) > + return -EINVAL; > + > + /* Reject mutually exclusive decap tunnel type flags. */ > + if ((flags & BPF_F_ADJ_ROOM_DECAP_L4_MASK) && > + (flags & BPF_F_ADJ_ROOM_DECAP_IPXIP_MASK)) > + return -EINVAL; > + > + if (flags & BPF_F_ADJ_ROOM_DECAP_L4_UDP) > + len_decap_min += sizeof(struct udphdr); > + > + if (flags & BPF_F_ADJ_ROOM_DECAP_L4_GRE) > + len_decap_min += sizeof(struct gre_base_hdr); > + > + if (len_diff_abs < len_decap_min) > + return -EINVAL; > + > + if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4) > len_min = sizeof(struct iphdr); > - break; > - case BPF_F_ADJ_ROOM_DECAP_L3_IPV6: > + > + if (flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6) > len_min = sizeof(struct ipv6hdr); > - break; > - default: > - return -EINVAL; > - } > } > > len_cur = skb->len - skb_network_offset(skb);