RDMA/bnxt_re: Avoid CPU lockups due fifo occupancy check loop
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 |
|
|
6.6.756.11.66.12In the Linux kernel, the following vulnerability has been resolved:
RDMA/bnxt_re: Avoid CPU lockups due fifo occupancy check loop
Driver waits indefinitely for the fifo occupancy to go below a threshold as soon as the pacing interrupt is received. This can cause soft lockup on one of the processors, if the rate of DB is very high.
Add a loop count for FPGA and exit the __wait_for_fifo_occupancy_below_th if the loop is taking more time. Pacing will be continuing until the occupancy is below the threshold. This is ensured by the checks in bnxt_re_pacing_timer_exp and further scheduling the work for pacing based on the fifo occupancy.
From the CVE record · Linux
The Linux kernel's RDMA/bnxt_re driver can wait indefinitely for FIFO occupancy to fall after a pacing interrupt. A very high doorbell rate can cause a processor soft lockup; the input does not specify an attack route, authentication requirements, or user interaction.
Teams running Linux kernels with the RDMA/bnxt_re driver should check their versions against the vendor advisory; affected versions are not specified.