minor tweaks

src/pulse.rs

@@ -24,6 +24,9 @@
 //! declares. A layout change yields FEWER signatures, never wrong ones, and the profile floor turns
 //! "fewer" into a failed release.
 
+// Registers whose value a call destroys. The ONE list in `abi`, not a second copy of it — both loops
+// below that invalidate across a call read it directly.
+use crate::abi::CALLER_SAVED;
 use crate::elf::CodeImage;
 use iced_x86::{Decoder, DecoderOptions, FlowControl, Instruction, Mnemonic, OpKind, Register};
 use std::collections::{BTreeMap, HashMap, HashSet};
@@ -83,20 +86,6 @@ struct Trace {
     ret: Option<(u64, u64)>,
 }
 
-/// Registers whose value a call destroys. Anything else the pass cannot evaluate is invalidated as the
-/// instruction that writes it is seen, so the default is always "unknown" rather than "stale".
-const CALLER_SAVED: [Register; 9] = [
-    Register::RAX,
-    Register::RCX,
-    Register::RDX,
-    Register::RSI,
-    Register::RDI,
-    Register::R8,
-    Register::R9,
-    Register::R10,
-    Register::R11,
-];
-
 fn full(r: Register) -> Register {
     if r.is_gpr() { r.full_register() } else { r }
 }
@@ -362,26 +351,6 @@ fn record(img: &CodeImage, accessor: u64) -> Option<Record> {
     })
 }
 
-/// Every CODE pointer an accessor's initializer stores into its record region, with the region base:
-/// `(base, [(address written, code address written)])`.
-///
-/// A DIAGNOSTIC, and deliberately not part of any shipped artifact. The parameter records carry a
-/// function pointer whose ROLE is not established — the record reader already has to look at these in
-/// order to reject them as parameter names, so exposing them costs nothing and lets that question be
-/// settled against evidence collected elsewhere (a runtime call-edge trace) rather than guessed. Nothing
-/// here interprets them; they are raw measurements.
-pub fn code_stores(img: &CodeImage, accessor: u64) -> Option<(u64, Vec<(u64, u64)>)> {
-    let r = record(img, accessor)?;
-    let stores =
-        r.t.writes
-            .iter()
-            .filter(|&(a, _)| *a >= r.base)
-            .filter(|&(_, p)| img.is_code(*p))
-            .map(|(&a, &p)| (a, p))
-            .collect();
-    Some((r.base, stores))
-}
-
 /// The spacings at which this record's `count` names could sit, given that element 0's name is at
 /// `base + 8` and the array is contiguous. Usually one; a record carrying a second identifier-shaped
 /// string of its own offers more, which is why the stride is settled per IMAGE and not per record.
@@ -582,10 +551,10 @@ const SHIM_SLOTS: [Register; 6] = [
 /// What an invocation shim was measured to read, and therefore what a caller has to supply.
 #[derive(Clone, Debug, Default, PartialEq, Eq)]
 pub struct ShimReads {
-    /// The argument slots actually read, named — `rcx`, `r8`, `stack0`.
+    /// The argument slots actually read, named — `rcx`, `r8`, `stack0`. The argument array (`r8`) is
+    /// stated here and nowhere else: reading it is the ordinary case and constrains a caller in no way,
+    /// so it needs no flag of its own beside the three that do.
     pub reads: Vec<&'static str>,
-    /// Does it read the argument array (`r8`)?
-    pub args: bool,
     /// Does it read the output sink (the first stack slot)? True for exactly the bindings that declare a
     /// return, measured across both games with no exceptions.
     pub sink: bool,
@@ -634,6 +603,24 @@ pub fn record_region(img: &CodeImage, accessor: u64) -> Option<(u64, u64)> {
     (r.base != 0).then_some((r.base, r.count))
 }
 
+/// What a read of one argument slot demands of a HOST caller.
+///
+/// The argument array (`r8`) demands nothing — the caller builds it, so reading it is the ordinary case
+/// and `reads` already states it. The Pulse context (`rcx`) is VM-owned and cannot be supplied at all.
+/// Everything else is a slot the caller would otherwise pass null.
+///
+/// A named arm rather than a fall-through for `r8` specifically: dropping it into the `_` catch-all would
+/// mark every ordinary binding as needing a slot no host can fill, retiring the entire `args-only`
+/// callable tier — a collapse that reads as "this build has no callable bindings", which is a legitimate
+/// answer for a game and therefore invisible.
+fn slot_need(r: Register, out: &mut ShimReads) {
+    match r {
+        Register::RCX => out.context = true,
+        Register::R8 => {}
+        _ => out.other = true,
+    }
+}
+
 /// Measure which of a shim's seven arguments it reads.
 ///
 /// Reachable instructions in ADDRESS order, which needs two guards that cost real time to find:
@@ -725,11 +712,7 @@ pub fn shim_reads(img: &CodeImage, entry: u64) -> Option<ShimReads> {
     {
         if live.contains_key(r) {
             out.reads.push(name);
-            match *r {
-                Register::RCX => out.context = true,
-                Register::R8 => out.args = true,
-                _ => out.other = true,
-            }
+            slot_need(*r, &mut out);
         }
     }
     if sink {
@@ -802,26 +785,26 @@ mod tests {
         let ctx = ShimReads {
             context: true,
             sink: true,
-            args: true,
+            reads: vec!["rcx", "r8", "stack0"],
             ..Default::default()
         };
         assert_eq!(ctx.needs(), "pulse-context");
         let other = ShimReads {
             other: true,
             sink: true,
-            args: true,
+            reads: vec!["rdi", "r8", "stack0"],
             ..Default::default()
         };
         assert_eq!(other.needs(), "other-slots");
         let sink = ShimReads {
             sink: true,
-            args: true,
+            reads: vec!["r8", "stack0"],
             ..Default::default()
         };
         assert_eq!(sink.needs(), "output-sink");
         // The callable tier: the argument array and nothing else.
         let only = ShimReads {
-            args: true,
+            reads: vec!["r8"],
             ..Default::default()
         };
         assert_eq!(only.needs(), "args-only");
@@ -829,6 +812,24 @@ mod tests {
         assert_eq!(ShimReads::default().needs(), "args-only");
     }
 
+    #[test]
+    fn reading_the_argument_array_leaves_a_shim_host_callable() {
+        // Asserted against the shipped rule rather than a copy of it. `r8` is the argument array the
+        // CALLER builds, so a read of it must impose nothing; the arm exists only to keep it out of the
+        // catch-all, where it would mark every ordinary binding uncallable at once.
+        let mut r8 = ShimReads::default();
+        slot_need(Register::R8, &mut r8);
+        assert_eq!(r8.needs(), "args-only");
+        let mut rcx = ShimReads::default();
+        slot_need(Register::RCX, &mut rcx);
+        assert_eq!(rcx.needs(), "pulse-context");
+        for r in [Register::RDI, Register::RSI, Register::RDX, Register::R9] {
+            let mut o = ShimReads::default();
+            slot_need(r, &mut o);
+            assert_eq!(o.needs(), "other-slots", "{r:?} is a slot a host must fill");
+        }
+    }
+
     #[test]
     fn pval_void_is_negative_one_and_still_a_type() {
         assert!(valid_pval(0)); // PVAL_BOOL