Open pkubaj opened 5 years ago
the script currently doesn't recognize Power CPUs, and any unrecognized CPU is assumed to be vulnerable to all variants.
https://www.ibm.com/blogs/psirt/potential-impact-processors-power-family/ mentions patches (both firmware and OS) to mitigate L1TF on Power 9.
variant 3a is not only relevant for Intel CPUs. ARM's Cortex A15, A57, and A72 are affected by it, so assuming a CPU isn't vulnerable to 3a only because it's not Intel is not valid, especially when the CPU is known to be vulnerable to 1, 2, 3, 4, and L1TF.
regarding firmware mitigating the vulnerabilities, the readme does say:
other architectures will work, but mitigations (if they exist) might not always be detected
When running on FreeBSD on powerpc64 architecture (POWER9 CPU) I get:
This output is completely wrong. POWER CPUs are vulnerable to variant , but variants 2, 3 and 4 were fixed in firmware (so no need for either Retpoline nor PTI). Variant 3a is only relevant for Intel CPUs, as are LT1F variants.