fix(runner-shared): always set PYTHONPERFSUPPORT (#577)

The runtime env only set PYTHONPERFSUPPORT=1 in memory mode. Since
exec-harness 1.4.0 relies on that env, Python exec targets in simulation
mode write no /tmp/perf-<pid>.map, and valgrind callgraphs lose every
Python frame. exec-harness 1.3.0 set it per command in simulation mode.

Set it in every mode. In walltime, PYTHON_PERF_JIT_SUPPORT=1 takes
precedence in CPython, so Linux still uses jitdump. On macOS walltime,
where jitdump stays off, Python now emits the perf map.

The perf trampoline adds instructions: a Python exec benchmark measured
under callgrind goes from 2.22e9 to 2.51e9 Ir (+13%), back to the 1.3.0
level.

Closes COD-3820

Author: not-matthias

crates/runner-shared/src/runtime_env/python.rs

@@ -9,16 +9,14 @@ const PYTHONPERFSUPPORT: &str = "PYTHONPERFSUPPORT";
 /// - `PYTHON_PERF_JIT_SUPPORT`: perf jitdump for walltime profiles.
 ///   FIXME(COD-2645): Keep this disabled on macOS. Enabling it causes
 ///   many unresolved addresses on the stack when profiling with samply.
-/// - `PYTHONPERFSUPPORT=1`: `/tmp/perf-<pid>.map` so memory flamegraphs can name Python frames.
+/// - `PYTHONPERFSUPPORT=1`: `/tmp/perf-<pid>.map` so valgrind and memory flamegraphs can
+///   name Python frames. When `PYTHON_PERF_JIT_SUPPORT=1` is also set, CPython uses jitdump.
 pub(super) fn env(mode: MeasurementMode) -> Vec<(&'static str, String)> {
     let perf_jit = mode == MeasurementMode::Walltime && !cfg!(target_os = "macos");
     let perf_jit_value = if perf_jit { "1" } else { "0" };
-    let mut env = vec![
+    vec![
         (PYTHONHASHSEED, "0".to_owned()),
         (PYTHON_PERF_JIT_SUPPORT, perf_jit_value.to_owned()),
-    ];
-    if mode == MeasurementMode::Memory {
-        env.push((PYTHONPERFSUPPORT, "1".to_owned()));
-    }
-    env
+        (PYTHONPERFSUPPORT, "1".to_owned()),
+    ]
 }