]> git.hungrycats.org Git - linux/commit
Merge branch 'vsock-virtio-collapse-receive-queue-under-memory-pressure'
authorPaolo Abeni <pabeni@redhat.com>
Tue, 21 Jul 2026 10:11:08 +0000 (12:11 +0200)
committerPaolo Abeni <pabeni@redhat.com>
Tue, 21 Jul 2026 10:11:08 +0000 (12:11 +0200)
commit0f1570553e650343c40d577e221ab5f8a98e9017
tree6e04e3757ae07cf956ea76087a163b6988d576a0
parent745fb794c3e933c023af9dbb5876a5e16ad2dc71
parent30c82aa0a8b116989bc4d8f75e1936bd83c0134e
Merge branch 'vsock-virtio-collapse-receive-queue-under-memory-pressure'

Stefano Garzarella says:

====================
vsock/virtio: collapse receive queue under memory pressure

This series contains a patch (the first one) that is part of work I'm
doing to improve the tracking of memory used by AF_VSOCK sockets.
The second patch is a test for our suite that highlights the issue.

Since Brien reported an issue with his environment (based on Linux 6.12.y)
related to the work I’m doing, I extracted this patch and tried to make it
as easy as possible to backport. Brien tested it by backporting it to
6.12.y, which now contains the backport of the 059b7dbd20a6
("vsock/virtio: fix potential unbounded skb queue").

This patch primarily fixes STREAM sockets, but also partially fixes
SEQPACKET (with the exception of EOMs, which are kept in separate skbs to
avoid overcomplicating the code).

The rest of the work, I feel, is more net-next material and still needs
some work to be completed.

v1: https://lore.kernel.org/netdev/20260626134823.206676-1-sgarzare@redhat.com/
====================

Link: https://patch.msgid.link/20260708102904.50732-1-sgarzare@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>