On Tue, Dec 2, 2025 at 10:20 AM Josh Poimboeuf <[email protected]> wrote: > > BPF JIT programs and trampolines use a frame pointer, so the current ORC > unwinder strategy of falling back to frame pointers (when an ORC entry > is missing) usually works in practice when unwinding through BPF JIT > stack frames. > > However, that frame pointer fallback is just a guess, so the unwind gets > marked unreliable for live patching, which can cause livepatch > transition stalls. > > Make the common case reliable by calling the bpf_has_frame_pointer() > helper to detect the valid frame pointer region of BPF JIT programs and > trampolines. > > Fixes: ee9f8fce9964 ("x86/unwind: Add the ORC unwinder") > Reported-by: Andrey Grodzovsky <[email protected]> > Closes: > https://lore.kernel.org/[email protected] > Signed-off-by: Josh Poimboeuf <[email protected]>
Acked-by: Song Liu <[email protected]>
