On Thu Jan 29, 2026 at 10:54 PM +08, bot+bpf-ci wrote: >> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c >> index e7ff8394e0..6e0693ac72 100644 >> --- a/kernel/bpf/verifier.c >> +++ b/kernel/bpf/verifier.c >> @@ -24874,6 +24874,9 @@ int bpf_check_attach_target(struct bpf_verifier_log >> *log, >> case BPF_TRACE_FENTRY: >> case BPF_TRACE_FEXIT: >> case BPF_TRACE_FSESSION: >> + if (prog->expected_attach_type == BPF_TRACE_FSESSION && >> + !bpf_jit_supports_fsession()) >> + return -EOPNOTSUPP; > > This isn't a bug, but other similar bpf_jit_supports_*() checks in > this file include a bpf_log() message before returning an error. For > example: > > bpf_jit_supports_kfunc_call() -> "JIT does not support calling kernel > function" > bpf_jit_supports_exceptions() -> "JIT does not support calling kfunc..." > bpf_jit_supports_arena() -> "JIT doesn't support arena" > bpf_jit_supports_private_stack() -> "Private stack not supported by jit" > > Should this check also include a message like "JIT does not support > fsession" for consistency with other similar checks in the verifier? >
That makes sense. Let me add the log message. Thanks, Leon > > --- > AI reviewed your patch. Please fix the bug or email reply why it's not a bug. > See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md > > CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21482297342 > > AI-authorship-score: low > AI-authorship-explanation: The commit demonstrates specific debugging context > with actual test output and errno values, correct understanding of kernel BPF > conventions, and follows established patterns - typical of experienced human > kernel developers. > issues-found: 1 > issue-severity-score: low > issue-severity-explanation: Minor consistency issue - missing bpf_log() error > message compared to similar checks in the same file; does not affect > functionality or stability.
