nvmet: fix a possible leak when destroy a ctrl during qp establishment
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
|
≥ 0f5be6a4ff7b3f8bf3db15f904e3e76797a43d9a · < c758b77d4a0a0ed3a1292b3fd7a2aeccd1a169a4| No fix yet |
| Linux Linux |
|
|
In the Linux kernel, the following vulnerability has been resolved:
nvmet: fix a possible leak when destroy a ctrl during qp establishment
In nvmet_sq_destroy we capture sq->ctrl early and if it is non-NULL we know that a ctrl was allocated (in the admin connect request handler) and we need to release pending AERs, clear ctrl->sqs and sq->ctrl (for nvme-loop primarily), and drop the final reference on the ctrl.
However, a small window is possible where nvmet_sq_destroy starts (as a result of the client giving up and disconnecting) concurrently with the nvme admin connect cmd (which may be in an early stage). But *before* kill_and_confirm of sq->ref (i.e. the admin connect managed to get an sq live reference). In this case, sq->ctrl was allocated however after it was captured in a local variable in nvmet_sq_destroy. This prevented the final reference drop on the ctrl.
Solve this by re-capturing the sq->ctrl after all inflight request has completed, where for sure sq->ctrl reference is final, and move forward based on that.
This issue was observed in an environment with many hosts connecting multiple ctrls simoutanuosly, creating a delay in allocating a ctrl leading up to this race window.
From the CVE record · Linux
A race during NVMe target controller setup and disconnection can prevent the Linux kernel from releasing a controller reference, causing a memory leak. It can occur when a client disconnects while an admin connect command is still in progress; the input does not specify authentication requirements.
Engineers running Linux kernel NVMe targets should check their deployments; affected versions are not specified.