From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-ot1-f54.google.com (mail-ot1-f54.google.com [209.85.210.54]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 20BD844E045 for ; Thu, 8 Oct 2026 08:30:04 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.210.54 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791448206; cv=none; b=DOE2EdLf7enmNlnwU/D7xUbGqlif8KLrsnZN0/17T71u5+m4V0s6OO+krofvNGLwhJuXJZjhow8jSbLwyNbal1cYsJif1zme0BAiQ9xUWGjBMeBTAdKowJQLvZb9QUsm/Mgb8VBOXrlGdmkKAlr8W2cLjGF5tn6/69a5DYcUynw= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791448206; c=relaxed/simple; bh=CvyAdXyi6xGDl736hpXlyaXN7OAQj1NiCSx0Yb1chNk=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=shSJ/fdB6VX4YbTLSBHpsAlrGcuPlT4Hx0pX6XxJsAz/jCLmvD25E0NHEgI7Kddd+huMHcgncKfKPZsIXBBQT8xgaaUz/CKzCIiklY6nE8lAvZJdEROHBNvizXD2yOaUPHQR2tqj6LzDRLOxXoDevEhB4Rbm2hSFY6XULjv3rVM= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=ZuDzrxFz; arc=none smtp.client-ip=209.85.210.54 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="ZuDzrxFz" Received: by mail-ot1-f54.google.com with SMTP id 46e09a7af769-8198a3a54d7so418399a34.1 for ; Thu, 08 Oct 2026 01:30:04 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1791448204; x=1792053004; darn=vger.kernel.org; h=in-reply-to:content-disposition:content-type:mime-version :references:message-id:subject:cc:to:from:date:from:to:cc:subject :date:message-id:reply-to:content-type; bh=x4YRBpZsbtDLH5v5QWzQXmBnOWEn6u15OsNxyb3RC5M=; b=ZuDzrxFzjtufOZL/Ul2k0Ae/mFbPQEw0yRBz2OtbMrghZOC5yvaY9Q4ViCBeqw6M3W aYS3LwWkC8YJerhdGqqMQzv4PakHOfeSjnWyso+2iNm/nzRWHmr/KK5YvuQzvTbmEU0E gixS7UB8B1uROnJjvkI6T5xywvcYjF8JAplM6LmcLsQvJEP8bAzA8jOeTwJK255LegLQ sJRXZ/9uutWw8ZF2k0mIEzSHwqqgaBymc59to3b5Gbw/qKTyEVgh2I2yosBEuIe4lRBO ZMhb6ronOCgqrCedTUAEFUUNdwUhZRk8/Ggq5wwxWQJGBWcbRmRJamG0oSJyssBZUvVH eD5g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1791448204; x=1792053004; h=in-reply-to:content-disposition:content-type:mime-version :references:message-id:subject:cc:to:from:date:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=x4YRBpZsbtDLH5v5QWzQXmBnOWEn6u15OsNxyb3RC5M=; b=NCK1UvN6CWanq/AnAStUVnT8LKd863OrQ7mzYamREKVJ3bPKDvqF1N/rEA7BsTtvg8 0mdkJGxwNPMS5PThteSXZP8Gf1gPADohD7hDgfxmtMQ4ayoTAgAfVy0+YikHCwZUHYAz AsS1QABxuq3z7UV+A1cx08xsn5SRSuwSmXlvq9UD7YQ5Mw8bWi7ivY24WrsJWZEClXid meoF9zVYw7vfsajC0av6I796oTTEoubWXcgunlCMGCAiNEq6jvQBhxoUMCGenUtkMnqZ j4jaqYsoY2HaAxEqlSxKCp9bM+ShPqRBuKFkyx7JPH424HMuuCPeDeVT2i/uzBwaI0F1 R++w== X-Forwarded-Encrypted: i=1; AKwUvByIOOqUQcf/TX+v8FsdKUtOq7+Oze7oeSYJjsKZ9gStJM5lJOdFvXU/9s90Cnh7uBa3Z83WH8E=@vger.kernel.org X-Gm-Message-State: AFuF++lFBRcZLkdVoUPoGkYOqINzNzMVmCVTfWH3wwJjyx1157GnUdRx WzN5WsLLaaGsk8t0L7JrJh5ghZrmnzFFrr7k/jC+KkR4QSU1b2/MZAJV X-Gm-Gg: AYBFou1M/a2+91STOlfR7K19yHAa0xHl13HB5u9VaK+YTLxc6NBBVcpWcna6XpRjQcg HlxWHHj8e5AnIYfW4zZXo8qNjrIn+lXQHJSZKmeDcB6XIUVs79VAYuJgu4x8fbSrFnoZ8f4ZlVx CUJrLUa4yn01oYG86nHYdKcG6hjwkEq3mY8pdk2g3J0f64SqyjsqQ/77/k8J2/8Ym+5/T3ZwxR/ 6r/PyYQBwExx5lgtfOgpje8GLVyIIUa8KJZ3pQlv/0IYnsHzEdfPFigUehFbkI586ZnWVlVp730 /2RCvq/DI7AlIVhhyWWSdk8Smc+ox0IMacFgytPpiMtKtmDnrEpcEa84BDFe6DD8+1uu7jbL3MG GPeaaRPdd8V7rLN6AKrJ34e2oGzOkQYP6BvxSqjbVJ4ylps84V+YDXtxi+f+PNMBY5RY6UfDpB0 ledpVSLFuBEHjO33BwxN+qQUFu6tg+PKjn8ik06DvUB0pWBr15ICBocFPLGVFTQcIY5eeaD1Boi RBlmkxNdX6IVouc7CC0 X-Received: by 2002:a05:6808:f93:b0:4b8:46e3:e223 with SMTP id 5614622812f47-504ab40d32cmr1090276b6e.15.1791448203704; Thu, 08 Oct 2026 01:30:03 -0700 (PDT) Received: from devvm29614.prn0.facebook.com ([2a03:2880:ff:4b::]) by smtp.gmail.com with ESMTPSA id 5614622812f47-4fc4627177esm4877103b6e.1.2026.10.08.01.30.01 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 08 Oct 2026 01:30:02 -0700 (PDT) Date: Thu, 8 Oct 2026 01:29:59 -0700 From: Bobby Eshleman To: Mina Almasry Cc: Stanislav Fomichev , Paolo Abeni , Kaiyuan Zhang , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, "David S. Miller" , Eric Dumazet , Jakub Kicinski , Simon Horman , Bobby Eshleman , Pavel Begunkov , Ralf Lici Subject: Re: [PATCH net v1] net: devmem: prevent mixing fragments from different bindings Message-ID: References: <20261008033952.1399670-1-almasrymina@google.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20261008033952.1399670-1-almasrymina@google.com> On Thu, Oct 08, 2026 at 03:39:26AM +0000, Mina Almasry wrote: > validate_xmit_unreadable_skb() only inspects shinfo->frags[0] and > assumes all fragments in an unreadable skb belong to that same devmem > binding. However, tcp_sendmsg_locked() only checks that readability > matches the presence of a binding (skb_frags_readable(skb) != !binding), > allowing consecutive sendmsg() calls with different dmabuf bindings to > collapse into the same skb and bypass per-device and unbind checks in > validate_xmit_unreadable_skb(). > > Add net_devmem_skb_binding() to query the binding associated with an > skb, reuse it in validate_xmit_unreadable_skb(), and check in > zerocopy_fill_skb_from_devmem() that existing fragments match the target > binding. > > Fixes: bd61848900bff ("net: devmem: Implement TX path") > Cc: Pavel Begunkov > Cc: Stanislav Fomichev > Cc: Bobby Eshleman > Signed-off-by: Mina Almasry > --- > net/core/datagram.c | 2 +- > net/core/dev.c | 14 ++++---------- > net/core/devmem.h | 23 +++++++++++++++++++++++ > 3 files changed, 28 insertions(+), 11 deletions(-) > > diff --git a/net/core/datagram.c b/net/core/datagram.c > index 173b5d97bd409..ed8f1045f3cca 100644 > --- a/net/core/datagram.c > +++ b/net/core/datagram.c > @@ -712,7 +712,7 @@ zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from, > size_t virt_addr, size, off; > struct net_iov *niov; > > - if (i && skb_frags_readable(skb)) > + if (i && net_devmem_skb_binding(skb) != binding) > return -EFAULT; > > /* Devmem filling works by taking an IOVEC from the user where the > diff --git a/net/core/dev.c b/net/core/dev.c > index e76762e29360e..ad2b587dfee27 100644 > --- a/net/core/dev.c > +++ b/net/core/dev.c > @@ -4054,8 +4054,7 @@ static struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, > static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, > struct net_device *dev) > { > - struct skb_shared_info *shinfo; > - struct net_iov *niov; > + struct net_devmem_dmabuf_binding *binding; > > if (likely(skb_frags_readable(skb) || > dev->netmem_tx == NETMEM_TX_NO_DMA)) > @@ -4064,14 +4063,9 @@ static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, > if (dev->netmem_tx == NETMEM_TX_NONE) > goto out_free; > > - shinfo = skb_shinfo(skb); > - > - if (shinfo->nr_frags > 0) { > - niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0])); > - if (net_is_devmem_iov(niov) && > - READ_ONCE(net_devmem_iov_binding(niov)->dev) != dev) > - goto out_free; > - } > + binding = net_devmem_skb_binding(skb); > + if (binding && READ_ONCE(binding->dev) != dev) > + goto out_free; > > out: > return skb; > diff --git a/net/core/devmem.h b/net/core/devmem.h > index 4a293a7d1149c..8c74037633ae8 100644 > --- a/net/core/devmem.h > +++ b/net/core/devmem.h > @@ -10,6 +10,7 @@ > #ifndef _NET_DEVMEM_H > #define _NET_DEVMEM_H > > +#include > #include > #include > > @@ -118,6 +119,22 @@ net_devmem_iov_binding(const struct net_iov *niov) > return net_devmem_iov_to_chunk_owner(niov)->binding; > } > > +static inline struct net_devmem_dmabuf_binding * > +net_devmem_skb_binding(const struct sk_buff *skb) > +{ > + const struct skb_shared_info *shinfo = skb_shinfo(skb); > + const struct net_iov *niov; > + > + if (skb_frags_readable(skb) || !shinfo->nr_frags) > + return NULL; > + > + niov = skb_frag_net_iov(&shinfo->frags[0]); > + if (!niov || !net_is_devmem_iov(niov)) > + return NULL; > + > + return net_devmem_iov_binding(niov); > +} > + > static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov) > { > return net_devmem_iov_binding(niov)->id; > @@ -243,6 +260,12 @@ net_devmem_iov_binding(const struct net_iov *niov) > { > return NULL; > } > + > +static inline struct net_devmem_dmabuf_binding * > +net_devmem_skb_binding(const struct sk_buff *skb) > +{ > + return NULL; > +} > #endif > > #endif /* _NET_DEVMEM_H */ > > base-commit: 6d25ffca055a77787c21a36b66c253f76239411b > -- > 2.56.0.385.gd3acb90ef8-goog > Makes sense to me. Thanks. Reviewed-by: Bobby Eshleman