Re: [PATCH bpf-next v3 10/11] bpf: Allow nospec-protected var-offset stack access

2025-06-03 Thread Luis Gerhorst
Kumar Kartikeya Dwivedi writes: > Hmm, while reading related code, I noticed that sanitize_check_bounds > returns 0 in case the type is not map_value or stack. > It seems like it should be returning an error, cannot check right now > but I'm pretty sure these are not the two pointer types unprivi

Re: [PATCH bpf-next v3 10/11] bpf: Allow nospec-protected var-offset stack access

2025-05-13 Thread Kumar Kartikeya Dwivedi
On Thu, 1 May 2025 at 04:17, Luis Gerhorst wrote: > > Insert a nospec before the access to prevent it from ever using an index > that is subject to speculative scalar-confusion. > > The access itself can either happen directly in the BPF program (reads > only, check_stack_read_var_off()) or in a h

Re: [PATCH bpf-next v3 10/11] bpf: Allow nospec-protected var-offset stack access

2025-05-01 Thread Kumar Kartikeya Dwivedi
On Thu, 1 May 2025 at 10:17, Luis Gerhorst wrote: > > Insert a nospec before the access to prevent it from ever using an index > that is subject to speculative scalar-confusion. > > The access itself can either happen directly in the BPF program (reads > only, check_stack_read_var_off()) or in a h