All of lore.kernel.org
 help / color / mirror / Atom feed
From: Will Deacon <will@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: "Will Deacon" <will@kernel.org>, "Keir Fraser" <keirf@google.com>,
	"Steven Moreland" <smoreland@google.com>,
	"Frederick Mayle" <fmayle@google.com>,
	"Stefan Hajnoczi" <stefanha@redhat.com>,
	"Stefano Garzarella" <sgarzare@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"Jason Wang" <jasowang@redhat.com>,
	"Eugenio Pérez" <eperezma@redhat.com>,
	netdev@vger.kernel.org, virtualization@lists.linux.dev
Subject: [PATCH 5/5] vhost/vsock: Allocate nonlinear SKBs for handling large transmit buffers
Date: Wed, 25 Jun 2025 14:15:43 +0100	[thread overview]
Message-ID: <20250625131543.5155-6-will@kernel.org> (raw)
In-Reply-To: <20250625131543.5155-1-will@kernel.org>

When transmitting a vsock packet, virtio_transport_send_pkt_info() calls
virtio_transport_alloc_skb() to allocate and fill SKBs with the transmit
data. Unfortunately, these are always linear allocations and can
therefore result in significant pressure on kmalloc() considering that
the maximum packet size (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE +
VIRTIO_VSOCK_SKB_HEADROOM) is a little over 64KiB, resulting in a 128KiB
allocation for each packet.

Rework the vsock SKB allocation so that, for sizes with page order
greater than PAGE_ALLOC_COSTLY_ORDER, a nonlinear SKB is allocated
instead with the packet header in the SKB and the transmit data in the
fragments.

Signed-off-by: Will Deacon <will@kernel.org>
---
 net/vmw_vsock/virtio_transport_common.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 1b5d9896edae..424eb69e84f9 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -109,7 +109,8 @@ static int virtio_transport_fill_skb(struct sk_buff *skb,
 		return __zerocopy_sg_from_iter(info->msg, NULL, skb,
 					       &info->msg->msg_iter, len, NULL);
 
-	return memcpy_from_msg(skb_put(skb, len), info->msg, len);
+	virtio_vsock_skb_put(skb);
+	return skb_copy_datagram_from_iter(skb, 0, &info->msg->msg_iter, len);
 }
 
 static void virtio_transport_init_hdr(struct sk_buff *skb,
@@ -261,7 +262,11 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *
 	if (!zcopy)
 		skb_len += payload_len;
 
-	skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL);
+	if (skb_len > SKB_WITH_OVERHEAD(PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		skb = virtio_vsock_alloc_skb_with_frags(skb_len, GFP_KERNEL);
+	else
+		skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL);
+
 	if (!skb)
 		return NULL;
 
-- 
2.50.0.714.g196bf9f422-goog


  parent reply	other threads:[~2025-06-25 13:16 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-25 13:15 [PATCH 0/5] vsock/virtio: SKB allocation improvements Will Deacon
2025-06-25 13:15 ` [PATCH 1/5] vhost/vsock: Avoid allocating arbitrarily-sized SKBs Will Deacon
2025-06-27 10:36   ` Stefano Garzarella
2025-06-30 12:51     ` Will Deacon
2025-07-01 10:37       ` Stefano Garzarella
2025-06-25 13:15 ` [PATCH 2/5] vsock/virtio: Resize receive buffers so that each SKB fits in a page Will Deacon
2025-06-27 10:41   ` Stefano Garzarella
2025-06-30 13:06     ` Will Deacon
2025-06-25 13:15 ` [PATCH 3/5] vhost/vsock: Allocate nonlinear SKBs for handling large receive buffers Will Deacon
2025-06-27 10:45   ` Stefano Garzarella
2025-06-30 14:20     ` Will Deacon
2025-07-01 10:44       ` Stefano Garzarella
2025-07-01 13:52         ` Will Deacon
2025-06-25 13:15 ` [PATCH 4/5] vsock/virtio: Rename virtio_vsock_skb_rx_put() to virtio_vsock_skb_put() Will Deacon
2025-06-27 10:46   ` Stefano Garzarella
2025-06-25 13:15 ` Will Deacon [this message]
2025-06-27 10:50   ` [PATCH 5/5] vhost/vsock: Allocate nonlinear SKBs for handling large transmit buffers Stefano Garzarella
2025-06-30 14:21     ` Will Deacon
2025-06-27 10:51 ` [PATCH 0/5] vsock/virtio: SKB allocation improvements Stefano Garzarella
2025-06-30 12:50   ` Will Deacon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250625131543.5155-6-will@kernel.org \
    --to=will@kernel.org \
    --cc=eperezma@redhat.com \
    --cc=fmayle@google.com \
    --cc=jasowang@redhat.com \
    --cc=keirf@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=sgarzare@redhat.com \
    --cc=smoreland@google.com \
    --cc=stefanha@redhat.com \
    --cc=virtualization@lists.linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.