From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-oa1-f51.google.com (mail-oa1-f51.google.com [209.85.160.51]) (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 C2AED4756D2 for ; Mon, 12 Oct 2026 22:17:51 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.160.51 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791843474; cv=none; b=YgIJZDxm2kp7vajjkJRfJD5QUT+s+sl/RwQ47MYg3LOOWgdPByRcfOGRBjlqxK1VV1+z2QlqbCc4ZiUP1MtlS3lXMDZoFQhzgWXnvm6F1WlBIwbL2EcejY5kXnCUumIkp45t/2NiJQVJwDlHrZYkBAVJtKZYJpyqChOXnIkdgtw= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791843474; c=relaxed/simple; bh=gtoYvpUKjEumvZ9NZ4lgt37kt3RngiiSW4yRL0iX9gI=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=WurRSSBNQkC/stULM6ZXqQGEMLtGFoLGGhlnGqAprX0lRiyvu9WpHSeeREcHVuRwntwKrbHNr4XGy+JhSqRdE5rM0sGQw+kLIueZdWbYUrmltZCGGUNAJk2dS9jb3FC9xQYO7qgIpo61y33y/e7X4IizSz57GO1S3IeafXsEBVw= 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=bWCc2IaL; arc=none smtp.client-ip=209.85.160.51 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="bWCc2IaL" Received: by mail-oa1-f51.google.com with SMTP id 586e51a60fabf-49e09a20082so1278033fac.2 for ; Mon, 12 Oct 2026 15:17:51 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1791843470; x=1792448270; 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=F68EtWrkn2Wfb2ayNm/k6SKK8v3U+BQEExnVnz6byuA=; b=bWCc2IaLK/o6qI6vwYEcjeSWIN/rJxd/dA8grzptulSuyQkLJPWLsEq2PVfJXYkzff 4/WXVFnxjeAqHjMhBdISQmi/XpbC7vOX4VzgH+4u9+YCYXwRc04/MLsi+gBYyp47zQ9p 8aSOH85jehAI4xJ794cE+yZdI73PzLMg8WYugz1QRb3sXzSmQ7o/3GNJuqF8qWmxggSH oGzI6aAkXxYliEdgDY4Ad4DlmjD1M0ZNQLTc0ARnaxxdTAEREMo3m1e0jITD8ZIkXGnd KeOLu53fZKqNbmQ8eVfzhDfvgLkRlky//SB8K7aMsfjEfu3Sd054dIjM4sJZ3mZ1tQGo iEuw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1791843470; x=1792448270; 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=F68EtWrkn2Wfb2ayNm/k6SKK8v3U+BQEExnVnz6byuA=; b=p/vodzeObSEwXUM5XwbycUmk3dcM0uJNJFdRYjrLtRoooND8+rlih+hWGZAUIRaneZ 9JP47rzZn5mCK5j0Ih5nol7sZNjAAi0YqO/k3sRs7wvQ0yswavcef3wQ8gZS+Asw/w1x 9d+jeY8s9SkGoatPtyWraP2LB3B3dYoVw6a9qrY55W0BgJeJSApbTLLocjJygHdfGiLP CY0b+9NPvEd3mxT/tCxmygbXs2MKO0GUqCcUL4PRCT5f3Cj1qhwzRLDu3zOs/9acMTXK 42EEa7WxR3jOchz8L8mZdTcZf0X3/CZmUBvOdxrf83G0n0yuf1I+9G67hgrUuXk6dby7 FyVQ== X-Forwarded-Encrypted: i=1; AKwUvBx4Wgj7RwZL2K4JyWN0R72HJP/BTcE/VA181j+56tTkQeaxKZZASI8hFkR3p7LUT4GdZQ0=@vger.kernel.org X-Gm-Message-State: AFq9FYKQSZptmHtRsQwFl6V1ciBQOdLaXBatYfliJ290DQF/3+tJ2i/t 4H+bn20vP29cIk8h848B4SvlyN16gdEQpXsXyLHz3sVlXjOt/Hnr8QWN X-Gm-Gg: AYBFou0DjVj1Nd4XW+g8u/n6AQUOlRmCWQlULERf1rUtoeJ/apmcyHNgpBdBaPSetnz 3vZX8noP8Z0q1zSA6z/HDCvuNGNRy/397RtT1ysl/22WbTomrD56NLZGLa3QtMPJh3jaRTUtEq8 f1Ttyw3bu3gI6Lmpw2UeVP9avjBrjapNfgxhWIYyiScnZCWqUf2e6IRbsY7l7OAMzg5V7L/mmZO Wp+aTFoWpAu5HjpVCVcE3tfTCJ226BG1o6VfMMlyZ+pnnzxHHeDGyt6uKPTHa7Wl532+lpBhwRn ElRlY5sYcMX3F19JFb95c3Y57HDf6alOAMQ6iE1IP5LV6D+Hx8H64Rl4khJRAtjS+tRxho1f3Kx mD0jklSHnhAlymyXD8KfB4qAk3XoAzWgVC18kmAq4CQxDrcMwYsDcUeEGEoPxCqMLtuQ84u3kuq 0JF+t+AXBvMGCBlZgg7s9u6Ps/tBJm+1YzH0FDWpZb3Y0+f34hUYOdnVG7Dr48ibT4l19LToSGW 4gDyVIgKAsEFNx71fO0 X-Received: by 2002:a05:6870:c213:b0:448:a3d6:c2d2 with SMTP id 586e51a60fabf-4a2a8955927mr10013926fac.10.1791843470199; Mon, 12 Oct 2026 15:17:50 -0700 (PDT) Received: from devvm29614.prn0.facebook.com ([2a03:2880:ff:44::]) by smtp.gmail.com with ESMTPSA id 586e51a60fabf-4a2a85edf81sm10977018fac.15.2026.10.12.15.17.46 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 12 Oct 2026 15:17:48 -0700 (PDT) Date: Mon, 12 Oct 2026 15:17:45 -0700 From: Bobby Eshleman To: Jia Jia Cc: stefanha@redhat.com, sgarzare@redhat.com, netdev@vger.kernel.org, virtualization@lists.linux.dev, kvm@vger.kernel.org, mst@redhat.com, jasowangio@gmail.com, eperezma@redhat.com, xuanzhuo@linux.alibaba.com, davem@davemloft.net, edumazet@kernel.org, kuba@kernel.org, pabeni@redhat.com, horms@kernel.org, linux-kernel@vger.kernel.org, bpf@vger.kernel.org Subject: Re: [PATCH net-next v2 3/5] vsock/virtio: reuse same-flow socket lookup in RX batches Message-ID: References: <20261010142247.99223-1-physicalmtea@gmail.com> <20261010142247.99223-4-physicalmtea@gmail.com> Precedence: bulk X-Mailing-List: kvm@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: <20261010142247.99223-4-physicalmtea@gmail.com> On Sat, Oct 10, 2026 at 10:22:45PM +0800, Jia Jia wrote: > An RX lock batch still looks up the socket for every packet and takes a > temporary lookup reference, even though the batch already holds a reference > to the locked socket. > > Record the network namespace and packet address tuple when a batch starts. > Reuse the batch socket for later STREAM/RW packets with the same tuple, and > release the batch before looking up a different flow. > > The cached path still traces every packet, takes an skb owner reference, > validates socket state, source and transport, updates credit, and runs the > receive state machine. Only the socket table lookup and its temporary > reference are skipped. > > Signed-off-by: Jia Jia > --- > include/linux/virtio_vsock.h | 3 ++ > net/vmw_vsock/virtio_transport_common.c | 58 +++++++++++++++---------- > 2 files changed, 38 insertions(+), 23 deletions(-) > > diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h > index 26dde6909c4e..d6528681e052 100644 > --- a/include/linux/virtio_vsock.h > +++ b/include/linux/virtio_vsock.h > @@ -287,6 +287,9 @@ struct virtio_transport_rx_batch { > struct sock *sk; > unsigned int pkts; > size_t bytes; > + struct net *net; > + struct sockaddr_vm src; > + struct sockaddr_vm dst; > }; > > void virtio_transport_recv_pkt_batch(struct virtio_transport *t, > diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c > index e67dfcaa279c..73e5c7dfe8b4 100644 > --- a/net/vmw_vsock/virtio_transport_common.c > +++ b/net/vmw_vsock/virtio_transport_common.c > @@ -1977,6 +1977,7 @@ void virtio_transport_rx_batch_finish(struct virtio_transport_rx_batch *batch) > batch->sk = NULL; > batch->pkts = 0; > batch->bytes = 0; > + batch->net = NULL; > > if (!sk) > return; > @@ -2008,6 +2009,37 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, > virtio_transport_recv_pkt_init_addrs(skb, &src, &dst); > virtio_transport_trace_recv_pkt(skb, &src, &dst); > > + if (batch->sk) { > + if (batch->net == net && > + vsock_addr_equals_addr(&batch->src, &src) && > + vsock_addr_equals_addr(&batch->dst, &dst) && > + virtio_transport_recv_pkt_batchable(t, batch->sk)) { > + sk = batch->sk; > + if (!skb_set_owner_sk_safe(skb, sk)) { > + WARN_ONCE(1, "receiving vsock socket has sk_refcnt == 0\n"); > + virtio_transport_rx_batch_finish(batch); > + kfree_skb(skb); > + return; > + } > + > + ctx = (struct virtio_transport_rx_pkt_ctx) { > + .net = net, > + .src = &src, > + .dst = &dst, > + .batchable = &batchable, > + }; > + free_pkt = virtio_transport_recv_pkt_locked(t, skb, sk, &ctx); > + > + if (!batchable) > + virtio_transport_rx_batch_finish(batch); > + if (free_pkt) > + kfree_skb(skb); > + return; > + } > + > + virtio_transport_rx_batch_finish(batch); > + } > + > sk = virtio_transport_recv_pkt_find_socket(skb, &src, &dst, net); > if (!sk) { > virtio_transport_rx_batch_finish(batch); > @@ -2018,33 +2050,10 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, > > if (!skb_set_owner_sk_safe(skb, sk)) { > WARN_ONCE(1, "receiving vsock socket has sk_refcnt == 0\n"); > - virtio_transport_rx_batch_finish(batch); > kfree_skb(skb); > return; > } > > - if (batch->sk && batch->sk != sk) { > - /* Never acquire a second socket lock. */ > - virtio_transport_rx_batch_finish(batch); > - } > - > - if (batch->sk == sk) { > - /* Keep the batch reference; drop this packet's lookup reference. */ > - sock_put(sk); > - ctx = (struct virtio_transport_rx_pkt_ctx) { > - .net = net, > - .src = &src, > - .dst = &dst, > - .batchable = &batchable, > - }; > - free_pkt = virtio_transport_recv_pkt_locked(t, skb, sk, &ctx); > - if (!batchable) > - virtio_transport_rx_batch_finish(batch); > - if (free_pkt) > - kfree_skb(skb); > - return; > - } > - Not sure I love adding code and then removing it in the same series. Seems like these are asking to be squashed? > lock_sock(sk); > /* > * Sockmap removal restores the native protocol under sk_callback_lock. > @@ -2063,6 +2072,9 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, > free_pkt = virtio_transport_recv_pkt_locked(t, skb, sk, &ctx); > if (start_batch && batchable) { > /* Keep the lookup reference until the batch is released. */ > + batch->net = net; > + batch->src = src; > + batch->dst = dst; Similar to my comment in the other patch, seems these are all in sk already? Best, Bobby