net: mana: Fix race on per-CQ variable napi work_done
Linux
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
| No fix yet |
| Linux Linux |
|
|
Linux
| Product | Affected | Fixed in |
|---|---|---|
| Linux Linux |
| No fix yet |
| Linux Linux |
|
|
5.15.836.0.136.1In the Linux kernel, the following vulnerability has been resolved:
net: mana: Fix race on per-CQ variable napi work_done
After calling napi_complete_done(), the NAPIF_STATE_SCHED bit may be cleared, and another CPU can start napi thread and access per-CQ variable, cq->work_done. If the other thread (for example, from busy_poll) sets it to a value >= budget, this thread will continue to run when it should stop, and cause memory corruption and panic.
To fix this issue, save the per-CQ work_done variable in a local variable before napi_complete_done(), so it won't be corrupted by a possible concurrent thread after napi_complete_done().
Also, add a flag bit to advertise to the NIC firmware: the NAPI work_done variable race is fixed, so the driver is able to reliably support features like busy_poll.
From the CVE record · Linux
A race in the Linux kernel's mana driver can occur when another CPU accesses a per-CQ work_done value after napi_complete_done(). Concurrent NAPI activity, such as busy_poll, can make the thread continue when it should stop, causing memory corruption and a panic. The input does not specify authentication, network access, or user-interaction requirements.
Engineers running Linux kernels with the mana network driver should check their kernel versions; affected versions are not specified.