Messages in this thread | ![/](/images/icornerl.gif) | | Date | Fri, 17 May 2024 16:08:03 +0200 | Subject | Re: [PATCH] x86/kvm/tdx: Save %rbp in TDX_MODULE_CALL | From | Juergen Gross <> |
| |
On 17.05.24 15:55, Kirill A. Shutemov wrote: > On Fri, May 17, 2024 at 02:14:50PM +0200, Juergen Gross wrote: >> While testing TDX host support patches, a crash of the host has been >> observed a few instructions after doing a seamcall. Reason was a >> clobbered %rbp (set to 0), which occurred in spite of the TDX module >> offering the feature NOT to modify %rbp across TDX module calls. >> >> In order not having to build the host kernel with CONFIG_FRAME_POINTER, >> save %rbp across a seamcall/tdcall. > > There's a feature in TDX module 1.5 that prevents RBP modification across > TDH.VP.ENTER SEAMCALL. See NO_RBP_MOD in TDX Module 1.5 ABI spec. > > I think it has to be enabled for all TDs and TDX modules that don't > support it need to be rejected. >
Yes, I know. I'm using the patch series:
[PATCH v19 000/130] KVM TDX basic feature support
which I think does exactly that (see setup_tdparams() and tdx_module_setup()).
Nevertheless the clobbering happened, and saving/restoring %rbp made the issue to go away. I suspect there is a path left still clobbering %rbp.
I was testing on an Emerald Rapids system:
# lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 47 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 256 On-line CPU(s) list: 0-255 Vendor ID: GenuineIntel BIOS Vendor ID: Intel(R) Corporation Model name: INTEL(R) XEON(R) PLATINUM 8592+ BIOS Model name: INTEL(R) XEON(R) PLATINUM 8592+ CPU @ 1.9GHz BIOS CPU family: 179 CPU family: 6 Model: 207 Thread(s) per core: 2 Core(s) per socket: 64 Socket(s): 2 Stepping: 2 ...
BIOS version as printed during boot:
[ 0.000000] DMI: Intel Corporation D50DNP/D50DNP, BIOS SE5C7411.86B.9535.D04.2312270518 12/27/2023
Juergen [unhandled content-type:application/pgp-keys][unhandled content-type:application/pgp-signature] | ![\](/images/icornerr.gif) |