PT-2026-151775
CVE-2026-99564
·
Published
2026-11-19
·
Updated
2026-11-19
Description by
Score
N/A
Not availableNo severity ratings or metrics are available. When they are, we'll update the corresponding info on the page.
In the Linux kernel, the following vulnerability has been resolved:
smb: smbdirect: don't wait for RDMA CM EVENT DISCONNECTED in smbdirect socket destroy sync()
smbdirect socket destroy sync() waited for RDMA CM EVENT DISCONNECTED
after smbdirect socket cleanup work() called rdma disconnect(). That
can take very long, e.g. if the peer just disappeared, until the
rdma cm gives up, or forever if the event already happened, but the
status was overwritten afterwards.
This is not needed: smbdirect socket destroy() drains the qp under
rdma lock handler(), destroys it and calls rdma destroy id(), which
only waits for a currently running event handler and makes sure no
further events are delivered. The rest of the disconnect protocol
(DREQ/DREP and timewait for IB, abrupt close for iWarp) is handled
by the rdma core asynchronously. drivers/nvme/host/rdma.c also just
calls rdma disconnect() and ib drain qp() before rdma destroy id().
So smbdirect socket destroy() now also accepts
SMBDIRECT SOCKET DISCONNECTING and changes the status to
SMBDIRECT SOCKET DISCONNECTED itself under rdma lock handler().
We could still get RDMA CM EVENT DISCONNECTED in the small
windows between rdma unlock handler() and rdma destroy id(),
but in that case smbdirect connection rdma event handler()
is basically a no-op.
Found an issue in the description? Have something to add? Feel free to write us 👾