From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-dy2-f42.google.com (mail-dy2-f42.google.com [74.125.229.42]) (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 1164C44163B for ; Fri, 2 Oct 2026 07:46:52 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.229.42 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790927214; cv=none; b=UXWVmfnC8XoUKhwdOJ8gX2CCNoxp9gP7NOGSsN1yK+DEHo1HVe8WnekpWl1ytlOlgBKl5vNC3OdddLhLOUqtseBo4S4SfAHNmVvUNhSAF2zjbZ2a5dYQ1rEnDuJ6qjuCq0bPm7Ie1kdh1ewd0eujCY7aErcQtJP8thIAVHzeICo= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790927214; c=relaxed/simple; bh=Iph8cQPjQlzJvVdwLAMxAEBkHSEKgnnbrMaq0iNc5dc=; h=From:To:Cc:Subject:Date:Message-ID:MIME-Version; b=beGGLG2qkYiwy064Ea8RhAGl3cv8pCEytv/HzL3/pne9iZuAW8nbo2qj1+Rj1wDzZeJAuQFmgkbm/WTV7TaXXKIU471I6WxTxq0fgz7fFm004Aqfdez25uKFMaqt2RRO/XrHFXl0xTcsxyhzYU/YcO1ODejHwK5OVMTfAtu63cA= 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=Hm6Z0LbE; arc=none smtp.client-ip=74.125.229.42 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="Hm6Z0LbE" Received: by mail-dy2-f42.google.com with SMTP id 5a478bee46e88-3428f70d7e7so4202407eec.3 for ; Fri, 02 Oct 2026 00:46:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1790927212; x=1791532012; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:from:to:cc:subject:date:message-id:reply-to:content-type; bh=pjJGZHeSlYSt0da6L8tYDnIpMtDpUH2iAs8gzn1WvfI=; b=Hm6Z0LbEMQSgcamMhN/vBIDwiCReIU5C9eVZJDOPMkXvYq5u5otrVCKRvFLbgVKSYJ nX63hikum8ie5Q4eHUweRKZAsOzwkgYm4AQvlHM4/CWp3Q7meLD2nYVFbuIeaiCYr7Tf CT9ig8NZH0cFqGxGDH7/w+IvpRT+h5cHb6aSekBTFpVYHLgenQc3PRiwnJh9YWJMdlcx ik3kTbTCj9zusS1x8Mx/xz8kBlR3IwTo1+fOhnltenzJnJV4HzecVxkGFqfLyu/hwKPx AbG5Br0ycitVJi5j9IRz0D4GUBTGb2RJyHViTfFwo5Q1urATiHRoQufxLtHwNXHmQAe9 txlQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1790927212; x=1791532012; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:x-gm-gg:x-gm-message-state:from:to:cc:subject:date :message-id:reply-to:content-type; bh=pjJGZHeSlYSt0da6L8tYDnIpMtDpUH2iAs8gzn1WvfI=; b=oUR9buqgKSdhl9OH5l8MgTGhW9qSrQ6pVXhey1kT63QL6A2xjHAhljk8W8VUzduZ+8 PocY6HukGyuw+s0TxZRVGLXXdNF/Nsckl4FbI0CDZZMrqaOZQafhUdMOPfUqs/PHUIqF S6aCkTeJkDnA5SxA3n3HX7hir5FMidX4FredcijuiwLyvDlfkZ850cSTItlNCUNi4DxA PfpSQ4An01N/IhxhZkWEceCQ9qwzjIXFd/3WDBFvBoAZIARB1qZ7jsVgV7yzUpHHZLvr pmwBMfo7SjboRHzxYvwcNMTvgZqRv8Nf9s2I3E2ffaoZkIxtD36wd4mJNVSOLKaRt/OY ciFw== X-Forwarded-Encrypted: i=1; AKwUvByHtW4GWXgICw6N3CZnqTXo8AcV6PJJU8P12/GwZqiqQ11UDSQiqh/vzye3lMdrzJnwsHDSkfWnm/ubhBQ=@vger.kernel.org X-Gm-Message-State: AFuF++nU8f1N0Yr06s6SgSDh0b56cL0IFko3oixDrYBYM13jTOKCh0Hs IN683KEV0A7JI+EYQgpag+TxMmqWUb7EIziDh0N7ogGGFsRAo5qdW/Bz X-Gm-Gg: AYBFou3wl0mNf173YkUqRg2EG+lV5Owf1wihsVAb45mOB6/khpmOPy1dme8amla6kVK zVON3YhDq8crNuzMnlDco1ZFJrSoLov3mMpx8mNLkYfZu/oYj1iGhQqRaCKJ1wqqEQ7BWDeJER9 1pjBzxXsRceGPM8v9B3DRbin2iPj0l8mo71UJAxUiQ/1tyPpELy6mvIs0nNjoCH7a/JBBCOXv3p iy/ckx5+h2S2eLW+odVKJDptZGfuJBswvGUopz20Ol2A7PggfSJYcBLKwLOigqKyBq8tFNdw//V qLvEhGY6svNpmRKf0iqKyl0iT402F8UCSCFWu4JwBN7mC/Eztcpo+zvThb1T/WdlZxGmzGGhXXr 8oCE6/MknNcc7ZnJc9gLvg6RZyig+WuycR6fR39XT5qupXTMXaEc0emhq/XyTZ6OAkHTkoYLtHi GKTg/kBRwe/l2D8sgY+Nkj1fTR622L8mRCTiNVwLM9kF1aPBTYg72Xg1HteW81ou7Sy/er X-Received: by 2002:a05:7301:df43:b0:340:7202:d7fc with SMTP id 5a478bee46e88-34f150d9568mr2038092eec.17.1790927211285; Fri, 02 Oct 2026 00:46:51 -0700 (PDT) Received: from dbg-srv ([123.118.75.63]) by smtp.gmail.com with ESMTPSA id 5a478bee46e88-34f0672c2d1sm5871618eec.4.2026.10.02.00.46.46 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 02 Oct 2026 00:46:50 -0700 (PDT) From: physicalmtea@gmail.com To: stefanha@redhat.com, sgarzare@redhat.com, mst@redhat.com Cc: 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, virtualization@lists.linux.dev, kvm@vger.kernel.org, netdev@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH 5/5] vsock: defer RX readable notifications until batch unlock Date: Fri, 2 Oct 2026 07:45:51 +0000 Message-ID: <20261002074551.318789-6-physicalmtea@gmail.com> X-Mailer: git-send-email 2.53.0 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit From: Jia Jia An RX batch can make a socket readable while the worker still owns its socket lock. Waking a reader at that point can make it immediately wait for the same lock. For the callback installed by sock_init_data(), record when the existing low-watermark condition is met and issue one notification after the batch releases the lock. Save the initial sock_def_readable() callback when the AF_VSOCK socket is created. virtio_transport_common can be built as a module and cannot refer to that unexported symbol directly. Custom data-ready callbacks retain per-packet notification behavior. If the callback changes while a default notification is pending, finish the batch before returning to the per-packet path. Keep the socket reference until the deferred callback completes. A sockmap attachment takes the socket lock, so data queued before the attachment is reported through the saved default callback. Control packets, state transitions, transport changes and non-batched sockets retain their existing behavior. Signed-off-by: Jia Jia --- include/linux/virtio_vsock.h | 1 + include/net/af_vsock.h | 3 +- net/vmw_vsock/af_vsock.c | 1 + net/vmw_vsock/virtio_transport_common.c | 53 ++++++++++++++++++++++++++----- 4 files changed, 49 insertions(+), 9 deletions(-) diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index f67fa99ec..d69c09d5c 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -289,6 +289,7 @@ struct virtio_transport_rx_batch { struct sockaddr_vm src; struct sockaddr_vm dst; bool write_space_pending; + bool data_ready_pending; }; void virtio_transport_recv_pkt_batch(struct virtio_transport *t, diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 9d8ae6220..a799f0855 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -63,7 +63,8 @@ struct vsock_sock { u32 peer_shutdown; bool sent_request; bool ignore_connecting_rst; - /* Initial callback, used to identify replacements. */ + /* Initial callbacks, used to identify replacements. */ + void (*default_data_ready)(struct sock *sk); void (*default_write_space)(struct sock *sk); /* Protected by lock_sock(sk) */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index e5290a3bb..1a25b5393 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -958,6 +958,7 @@ static struct sock *__vsock_create(struct net *net, sk->sk_type = type; vsk = vsock_sk(sk); + vsk->default_data_ready = sk->sk_data_ready; vsk->default_write_space = sk->sk_write_space; vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 78c4e2f9e..e337a7aaf 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1583,7 +1583,8 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, static int virtio_transport_recv_connected(struct sock *sk, - struct sk_buff *skb) + struct sk_buff *skb, + bool *data_ready_pending) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vsock_sock *vsk = vsock_sk(sk); @@ -1602,7 +1603,14 @@ virtio_transport_recv_connected(struct sock *sk, vsock_remove_sock(vsk); break; } - vsock_data_ready(sk); + if (!data_ready_pending || + READ_ONCE(sk->sk_data_ready) != vsk->default_data_ready) { + vsock_data_ready(sk); + } else if (!*data_ready_pending && + (vsock_stream_has_data(vsk) >= sk->sk_rcvlowat || + sock_flag(sk, SOCK_DONE))) { + *data_ready_pending = true; + } return err; case VIRTIO_VSOCK_OP_CREDIT_REQUEST: virtio_transport_send_credit_update(vsk); @@ -1836,6 +1844,7 @@ struct virtio_transport_rx_pkt_ctx { const struct sockaddr_vm *dst; bool *batchable; struct virtio_transport_rx_batch *batch; + bool defer_data_ready; }; static bool @@ -1852,9 +1861,11 @@ virtio_transport_recv_pkt_batchable(struct virtio_transport *t, } /* - * The caller holds sk's socket lock. Set @batchable if the socket can remain - * locked for another ordinary STREAM/RW packet. Return true if the caller - * must free @skb. + * The caller holds sk's socket lock. The packet context optionally records + * callbacks to deliver when the batch finishes. If defer_data_ready is true, + * defer the default data-ready callback in the batch. Set batchable if the + * socket can remain locked for another ordinary STREAM/RW packet. Return + * true if the caller must free skb. */ static bool virtio_transport_recv_pkt_locked(struct virtio_transport *t, @@ -1902,7 +1913,9 @@ virtio_transport_recv_pkt_locked(struct virtio_transport *t, kfree_skb(skb); break; case TCP_ESTABLISHED: - virtio_transport_recv_connected(sk, skb); + virtio_transport_recv_connected(sk, skb, + ctx->defer_data_ready && ctx->batch ? + &ctx->batch->data_ready_pending : NULL); break; case TCP_CLOSING: virtio_transport_recv_disconnecting(sk, skb); @@ -1971,10 +1984,12 @@ void virtio_transport_rx_batch_finish(struct virtio_transport_rx_batch *batch) { struct sock *sk = batch->sk; bool write_space_pending = batch->write_space_pending; + bool data_ready_pending = batch->data_ready_pending; batch->sk = NULL; batch->net = NULL; batch->write_space_pending = false; + batch->data_ready_pending = false; if (!sk) return; @@ -1983,6 +1998,16 @@ void virtio_transport_rx_batch_finish(struct virtio_transport_rx_batch *batch) if (write_space_pending) vsock_sk(sk)->default_write_space(sk); + release_sock(sk); + + /* + * This event covers data queued while the default callback was installed. + * A sockmap attachment takes the socket lock, so it is ordered after that + * enqueue even if it replaces the callback before this call. + */ + if (data_ready_pending) + vsock_sk(sk)->default_data_ready(sk); + sock_put(sk); } EXPORT_SYMBOL_GPL(virtio_transport_rx_batch_finish); @@ -1995,7 +2017,7 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, struct sockaddr_vm src, dst; struct sock *sk; struct virtio_transport_rx_pkt_ctx ctx; - bool batchable, start_batch; + bool batchable, defer_data_ready, start_batch; bool free_pkt; /* Only STREAM/RW packets can share a socket lock. */ @@ -2015,6 +2037,13 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, vsock_addr_equals_addr(&batch->dst, &dst) && virtio_transport_recv_pkt_batchable(t, batch->sk)) { sk = batch->sk; + defer_data_ready = READ_ONCE(sk->sk_data_ready) == + vsock_sk(sk)->default_data_ready; + if (batch->data_ready_pending && !defer_data_ready) { + virtio_transport_rx_batch_finish(batch); + goto lookup; + } + 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); @@ -2028,6 +2057,7 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, .dst = &dst, .batchable = &batchable, .batch = batch, + .defer_data_ready = defer_data_ready, }; free_pkt = virtio_transport_recv_pkt_locked(t, skb, sk, &ctx); if (!batchable) @@ -2040,6 +2070,7 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, virtio_transport_rx_batch_finish(batch); } +lookup: sk = virtio_transport_recv_pkt_find_socket(skb, &src, &dst, net); if (!sk) { (void)virtio_transport_reset_no_sock(t, skb, net); @@ -2060,6 +2091,8 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, */ read_lock_bh(&sk->sk_callback_lock); start_batch = virtio_transport_recv_pkt_batchable(t, sk); + defer_data_ready = start_batch && + READ_ONCE(sk->sk_data_ready) == vsock_sk(sk)->default_data_ready; read_unlock_bh(&sk->sk_callback_lock); if (start_batch) @@ -2070,10 +2103,11 @@ void virtio_transport_recv_pkt_batch(struct virtio_transport *t, .dst = &dst, .batchable = start_batch ? &batchable : NULL, .batch = start_batch ? batch : NULL, + .defer_data_ready = defer_data_ready, }; free_pkt = virtio_transport_recv_pkt_locked(t, skb, sk, &ctx); if (start_batch && batchable) { - /* Keep the lookup reference until the batch is released. */ + /* Keep the lookup reference until the batch finishes. */ batch->net = net; batch->src = src; batch->dst = dst; -- 2.53.0