On Tue, Jan 27, 2026 at 06:31:36PM +0000, Carlos Llamas wrote:
> On Wed, Dec 03, 2025 at 02:48:09PM +0000, Alice Ryhl wrote:
> > This patch adds the binder_transaction tracepoint to Rust Binder. This
> > was chosen as the next tracepoint to add as it is the most complex
> > tracepoint. (And it's also an important tracepoint known to perfetto.)
> >
> > Signed-off-by: Alice Ryhl <[email protected]>
> > ---
>
> This approach seems to work well considering the limitations. I wonder
> though if it would be more practical to simply pass the individual
> primitive values used by TP_prinkt() from the start? I suppose the
> downside would be the extra overhead with the tracepoints disabled.
> However, this might be neglectable and the solution much simpler?
I decided to go down this road because the same kinds of helpers would
be useful for vendor hooks.
> > +static inline rust_binder_node
> > rust_binder_transaction_target_node(rust_binder_transaction t)
> > +{
> > + void *p = *(void **) (t + RUST_BINDER_LAYOUT.t.target_node);
> > +
> > + if (p)
> > + p = p + RUST_BINDER_LAYOUT.n.arc_offset;
> > + return NULL;
>
> It looks like this should have 'return p' right? Sorry for the late
> review this has been picked up so we might need a fixes for this.
Fix sent:
https://lore.kernel.org/r/20260128-binder-fix-target-node-null-v1-1-78d198ef5...@google.com
No idea how this happened. Thanks.
Alice
