Merge analysis-overhaul/m4-classaware-probes

crates/xenia-analysis/SCHEMA.md

@@ -142,11 +142,27 @@ SELECT name FROM functions WHERE address = 2186674160;  -- 0x824D29F0
   (CompleteObjectLocator at vtable[-1]; TypeDescriptor at COL+0xC; mangled
   name at TD+0x8).
 
-## Layer M4 — Class-aware probe targeting (planned)
+## Layer M4 — Class-aware probe targeting (landed)
 
-CLI extension only — no schema changes. `--pc-probe=Class::method` and
+CLI extension only — no schema changes. The probe-token grammar adds three
-`--pc-probe-class=ClassName` resolve via M3's tables. See
+symbolic forms on top of the existing `0xADDR` literal:
-`crates/xenia-analysis/src/lookup.rs` (when landed).
+
+- `Class::method` — joins `classes` × `methods` × `demangled_names` to find
+  every PC whose vtable belongs to that class and whose demangled
+  `method_name` matches.
+- `Class::*` — joins `classes` × `methods` to find every method PC of that
+  class.
+- `function_name` — falls back to `functions.name` lookup for free functions
+  / saverestore stubs / labels.
+
+Numeric tokens never touch the DB (preserves zero-IO fast path; lockstep
+digest unaffected). Symbolic tokens require the DuckDB at `--probe-db PATH`
+or `XENIA_PROBE_DB`; default is `sylpheed.db` next to the .iso when present.
+
+Resolution happens BEFORE guest exec begins, so it cannot affect the
+lockstep digest.
+
+See `crates/xenia-analysis/src/lookup.rs`.
 
 ---
 

crates/xenia-analysis/src/lookup.rs

@@ -0,0 +1,222 @@
+//! Symbolic-name resolution for runtime probes (M4).
+//!
+//! Lets `--pc-probe` / `--branch-probe` / `--ctor-probe` accept names like
+//! `xe::apu::AudioSystem::Setup` or `MyClass::*` instead of bare PC literals.
+//! Resolution joins the M3-produced `classes` × `methods` × `functions` tables
+//! and the M2 `demangled_names` table.
+//!
+//! Numeric tokens (`0x824D6640`, `2186674160`) are returned unchanged; symbolic
+//! tokens require a path to an existing `sylpheed.db` (passed by the caller).
+//!
+//! All DB access is read-only and happens before guest execution, so the
+//! lockstep digest is unaffected.
+
+use std::path::Path;
+
+use anyhow::{anyhow, Result};
+use duckdb::params;
+
+/// Parse one probe token into one or more PCs.
+///
+/// Recognized forms:
+/// - `0xADDR` / `ADDR` (decimal) → returns one PC unchanged.
+/// - `Class::method` → all `methods.function_address` matching that
+///   `class_name` + `method_name` pair.
+/// - `Class::*` → all `methods.function_address` for that class.
+/// - `func::Name` (free function) → falls back to `functions.name` lookup.
+///
+/// `db_path` is consulted ONLY if the token is non-numeric. When `db_path` is
+/// `None` and the token is symbolic, returns an error suggesting the user
+/// either pass `--db` or use a numeric address.
+pub fn resolve_probe_token(db_path: Option<&Path>, token: &str) -> Result<Vec<u32>> {
+    let token = token.trim();
+    if token.is_empty() {
+        return Ok(vec![]);
+    }
+
+    if let Some(pc) = parse_numeric(token) {
+        return Ok(vec![pc]);
+    }
+
+    let db = db_path.ok_or_else(|| {
+        anyhow!(
+            "symbolic probe token {token:?} requires a sylpheed.db; \
+             pass --probe-db=PATH or use a numeric 0x… address",
+        )
+    })?;
+
+    if !db.exists() {
+        return Err(anyhow!("--probe-db not found: {}", db.display()));
+    }
+
+    let conn = duckdb::Connection::open_with_flags(
+        db,
+        duckdb::Config::default().access_mode(duckdb::AccessMode::ReadOnly)?,
+    )?;
+
+    // Class::method or Class::*
+    if let Some((class, method)) = token.split_once("::") {
+        if method == "*" {
+            return resolve_class_star(&conn, class);
+        }
+        // Try Class::method first, then fall back to functions.name lookup.
+        let pcs = resolve_class_method(&conn, class, method)?;
+        if !pcs.is_empty() {
+            return Ok(pcs);
+        }
+    }
+
+    // Last-resort: functions.name match (e.g. for `entry_point` or
+    // `__savegprlr_22`). Substring-free; user gets a clear error if missing.
+    resolve_function_name(&conn, token)
+}
+
+fn parse_numeric(token: &str) -> Option<u32> {
+    if let Some(hex) = token.strip_prefix("0x").or_else(|| token.strip_prefix("0X")) {
+        return u32::from_str_radix(hex, 16).ok();
+    }
+    token.parse::<u32>().ok()
+}
+
+fn resolve_class_method(conn: &duckdb::Connection, class: &str, method: &str) -> Result<Vec<u32>> {
+    // Two-step lookup so we can give better errors:
+    //   1. find matching methods rows joined to classes;
+    //   2. surface the function_address column.
+    let mut stmt = conn.prepare(
+        "SELECT DISTINCT m.function_address FROM methods m
+         JOIN classes c ON c.vtable_address = m.vtable_address
+         JOIN demangled_names dn ON dn.address = m.function_address
+         WHERE c.name = ? AND dn.method_name = ?",
+    )?;
+    let pcs: Vec<u32> = stmt
+        .query_map(params![class, method], |r| r.get::<_, i64>(0).map(|x| x as u32))?
+        .filter_map(|r| r.ok())
+        .collect();
+    Ok(pcs)
+}
+
+fn resolve_class_star(conn: &duckdb::Connection, class: &str) -> Result<Vec<u32>> {
+    let mut stmt = conn.prepare(
+        "SELECT DISTINCT m.function_address FROM methods m
+         JOIN classes c ON c.vtable_address = m.vtable_address
+         WHERE c.name = ?",
+    )?;
+    let pcs: Vec<u32> = stmt
+        .query_map(params![class], |r| r.get::<_, i64>(0).map(|x| x as u32))?
+        .filter_map(|r| r.ok())
+        .collect();
+    if pcs.is_empty() {
+        return Err(anyhow!(
+            "no class named {class:?} found in classes table — has --dis populated this DB?",
+        ));
+    }
+    Ok(pcs)
+}
+
+fn resolve_function_name(conn: &duckdb::Connection, name: &str) -> Result<Vec<u32>> {
+    let mut stmt = conn.prepare("SELECT address FROM functions WHERE name = ?")?;
+    let pcs: Vec<u32> = stmt
+        .query_map(params![name], |r| r.get::<_, i64>(0).map(|x| x as u32))?
+        .filter_map(|r| r.ok())
+        .collect();
+    if pcs.is_empty() {
+        return Err(anyhow!(
+            "probe token {name:?} did not match any classes::methods or functions row",
+        ));
+    }
+    Ok(pcs)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use duckdb::Connection;
+
+    fn build_synthetic_db(path: &Path) {
+        let conn = Connection::open(path).expect("open");
+        conn.execute_batch(
+            "
+            CREATE TABLE functions (
+                address BIGINT PRIMARY KEY,
+                name VARCHAR
+            );
+            CREATE TABLE classes (
+                name VARCHAR PRIMARY KEY,
+                vtable_address BIGINT,
+                rtti_present BOOLEAN,
+                base_classes_json VARCHAR
+            );
+            CREATE TABLE methods (
+                vtable_address BIGINT,
+                slot BIGINT,
+                function_address BIGINT,
+                mangled_name VARCHAR,
+                demangled_name VARCHAR,
+                PRIMARY KEY (vtable_address, slot)
+            );
+            CREATE TABLE demangled_names (
+                address BIGINT,
+                mangled VARCHAR,
+                raw_demangled VARCHAR,
+                namespace_path VARCHAR,
+                class_name VARCHAR,
+                method_name VARCHAR,
+                params_signature VARCHAR
+            );
+            INSERT INTO classes VALUES ('Foo', 11000, true, NULL);
+            INSERT INTO functions VALUES (12000, 'sub_2EE0'), (12100, 'sub_2F44');
+            INSERT INTO methods VALUES (11000, 0, 12000, NULL, NULL),
+                                       (11000, 1, 12100, NULL, NULL);
+            INSERT INTO demangled_names (address, mangled, raw_demangled, class_name, method_name)
+            VALUES (12000, '?bar@Foo@@QEAAXXZ', 'void Foo::bar(void)', 'Foo', 'bar'),
+                   (12100, '?baz@Foo@@QEAAXXZ', 'void Foo::baz(void)', 'Foo', 'baz');
+            ",
+        )
+        .expect("seed");
+    }
+
+    #[test]
+    fn numeric_passthrough_no_db_needed() {
+        let pcs = resolve_probe_token(None, "0x824D6640").unwrap();
+        assert_eq!(pcs, vec![0x824D6640]);
+        let pcs = resolve_probe_token(None, "2186095088").unwrap();
+        assert_eq!(pcs, vec![0x824D29F0]);
+    }
+
+    #[test]
+    fn symbolic_token_without_db_errors() {
+        let err = resolve_probe_token(None, "Foo::bar").unwrap_err();
+        assert!(format!("{err}").contains("requires a sylpheed.db"));
+    }
+
+    #[test]
+    fn class_method_resolves() {
+        let tmp = std::env::temp_dir().join("xenia_lookup_test.duckdb");
+        let _ = std::fs::remove_file(&tmp);
+        build_synthetic_db(&tmp);
+        let pcs = resolve_probe_token(Some(&tmp), "Foo::bar").unwrap();
+        assert_eq!(pcs, vec![12000]);
+        let _ = std::fs::remove_file(&tmp);
+    }
+
+    #[test]
+    fn class_star_returns_all_methods() {
+        let tmp = std::env::temp_dir().join("xenia_lookup_star.duckdb");
+        let _ = std::fs::remove_file(&tmp);
+        build_synthetic_db(&tmp);
+        let mut pcs = resolve_probe_token(Some(&tmp), "Foo::*").unwrap();
+        pcs.sort();
+        assert_eq!(pcs, vec![12000, 12100]);
+        let _ = std::fs::remove_file(&tmp);
+    }
+
+    #[test]
+    fn function_name_fallback() {
+        let tmp = std::env::temp_dir().join("xenia_lookup_fn.duckdb");
+        let _ = std::fs::remove_file(&tmp);
+        build_synthetic_db(&tmp);
+        let pcs = resolve_probe_token(Some(&tmp), "sub_2EE0").unwrap();
+        assert_eq!(pcs, vec![12000]);
+        let _ = std::fs::remove_file(&tmp);
+    }
+}

crates/xenia-app/src/main.rs

@@ -224,6 +224,12 @@ enum Commands {
         /// `--dump-section=BASE:LEN:PATH` end-of-run guest memory snapshot.
         #[arg(long)]
         dump_section: Option<String>,
+        /// Path to a `sylpheed.db` (M3-populated) for resolving symbolic
+        /// probe tokens like `Class::method` or `Class::*`. Required only
+        /// if any of the `--*-probe` flags contain a non-numeric token.
+        /// Default: `sylpheed.db` next to the .iso file when present.
+        #[arg(long)]
+        probe_db: Option<String>,
     },
     /// Browse XISO disc image contents
     Browse {
@@ -384,6 +390,7 @@ fn main() -> Result<()> {
             branch_probe,
             mem_watch,
             dump_section,
+            probe_db,
         } => cmd_exec(
             &path,
             max_instructions,
@@ -407,6 +414,7 @@ fn main() -> Result<()> {
             branch_probe.as_deref(),
             mem_watch.as_deref(),
             dump_section.as_deref(),
+            probe_db.as_deref(),
         ),
         Commands::Browse { path } => cmd_browse(&path),
         Commands::Info { path } => cmd_info(&path),
@@ -443,6 +451,28 @@ fn main() -> Result<()> {
     }
 }
 
+/// Resolve where to look for `sylpheed.db` when probe tokens are symbolic.
+/// Precedence:
+///   1. explicit `--probe-db` flag (cmd_arg)
+///   2. `XENIA_PROBE_DB` env var
+///   3. `sylpheed.db` next to the .iso path (if it exists)
+/// Returns `None` when no DB is available — resolve_probe_token will then
+/// only succeed for numeric tokens.
+fn resolve_probe_db_path(cmd_arg: Option<&str>, iso_path: &str) -> Option<std::path::PathBuf> {
+    if let Some(p) = cmd_arg {
+        return Some(std::path::PathBuf::from(p));
+    }
+    if let Ok(p) = std::env::var("XENIA_PROBE_DB") {
+        if !p.is_empty() { return Some(std::path::PathBuf::from(p)); }
+    }
+    let iso = std::path::Path::new(iso_path);
+    if let Some(parent) = iso.parent() {
+        let candidate = parent.join("sylpheed.db");
+        if candidate.exists() { return Some(candidate); }
+    }
+    None
+}
+
 /// Load XEX data from a path. If the path is an ISO, extract default.xex from it.
 #[instrument(skip_all, fields(path = %path))]
 fn load_xex_data(path: &str) -> Result<Vec<u8>> {
@@ -613,6 +643,7 @@ fn cmd_exec(
     branch_probe: Option<&str>,
     mem_watch: Option<&str>,
     dump_section: Option<&str>,
+    probe_db: Option<&str>,
 ) -> Result<()> {
     cmd_exec_inner(
         path,
@@ -637,6 +668,7 @@ fn cmd_exec(
         branch_probe,
         mem_watch,
         dump_section,
+        probe_db,
         None,
         None,
         false,
@@ -680,6 +712,7 @@ fn cmd_check(
         None, // branch_probe — diagnostic, never wanted on goldens
         None, // mem_watch — same
         None, // dump_section — same
+        None, // probe_db — same
         out,
         expect,
         stable_digest,
@@ -709,6 +742,7 @@ fn cmd_exec_inner(
     branch_probe: Option<&str>,
     mem_watch: Option<&str>,
     dump_section: Option<&str>,
+    probe_db: Option<&str>,
     digest_out: Option<&str>,
     digest_expect: Option<&str>,
     stable_digest: bool,
@@ -958,11 +992,15 @@ fn cmd_exec_inner(
         }
     }
 
-    // Diagnostic. Parse `--ctor-probe=0x8217C850,0x...` (or
+    // Diagnostic. Parse `--ctor-probe=0x8217C850,...` or symbolic forms like
-    // `XENIA_CTOR_PROBE=...`) into `kernel.ctor_probe_pcs`. The
+    // `Class::method`, `Class::*`, `function_name` (or `XENIA_CTOR_PROBE=...`)
-    // worker prologue checks this set on every step; on a hit it
+    // into `kernel.ctor_probe_pcs`. Symbolic resolution reads `--probe-db` /
-    // prints a single back-chain capture line. Empty set = no
+    // `XENIA_PROBE_DB` (or the `sylpheed.db` next to the .iso when present).
-    // probes = no-op fast path.
+    // Empty set = no probes = no-op fast path.
+    //
+    // Symbolic resolution happens BEFORE guest exec begins, so it cannot
+    // affect the lockstep digest.
+    let probe_db_path = resolve_probe_db_path(probe_db, path);
     let ctor_probe_combined: Option<String> = match (
         ctor_probe,
         std::env::var("XENIA_CTOR_PROBE").ok().or_else(|| std::env::var("XENIA_PC_PROBE").ok()),
@@ -973,7 +1011,7 @@ fn cmd_exec_inner(
     };
     if let Some(list) = ctor_probe_combined {
         for token in list.split(',').map(str::trim).filter(|s| !s.is_empty()) {
-            let (pc_str, consumer): (&str, Option<(u32, u32)>) = match token.split_once('@') {
+            let (pc_part, consumer): (&str, Option<(u32, u32)>) = match token.split_once('@') {
                 None => (token, None),
                 Some((pc_part, rest)) => {
                     let (disp_str, off_str) = rest.split_once(':').ok_or_else(|| {
@@ -990,12 +1028,13 @@ fn cmd_exec_inner(
                     (pc_part.trim(), Some((disp, off)))
                 }
             };
-            let pc = parse_hex_u32(pc_str).map_err(|e| {
+            let pcs = xenia_analysis::lookup::resolve_probe_token(probe_db_path.as_deref(), pc_part)
-                anyhow::anyhow!("invalid PC in --pc-probe: {token:?}: {e}")
+                .map_err(|e| anyhow::anyhow!("--pc-probe {token:?}: {e}"))?;
-            })?;
+            for pc in pcs {
-            kernel.ctor_probe_pcs.insert(pc);
+                kernel.ctor_probe_pcs.insert(pc);
-            if let Some(c) = consumer {
+                if let Some(c) = consumer {
-                kernel.pc_probe_consumers.insert(pc, c);
+                    kernel.pc_probe_consumers.insert(pc, c);
+                }
             }
         }
         if !quiet && !kernel.ctor_probe_pcs.is_empty() {
@@ -1023,10 +1062,11 @@ fn cmd_exec_inner(
     };
     if let Some(list) = branch_probe_combined {
         for token in list.split(',').map(str::trim).filter(|s| !s.is_empty()) {
-            let pc = parse_hex_u32(token).map_err(|e| {
+            let pcs = xenia_analysis::lookup::resolve_probe_token(probe_db_path.as_deref(), token)
-                anyhow::anyhow!("invalid PC in --branch-probe: {token:?}: {e}")
+                .map_err(|e| anyhow::anyhow!("--branch-probe {token:?}: {e}"))?;
-            })?;
+            for pc in pcs {
-            kernel.branch_probe_pcs.insert(pc);
+                kernel.branch_probe_pcs.insert(pc);
+            }
         }
         if !quiet && !kernel.branch_probe_pcs.is_empty() {
             let mut pcs: Vec<u32> = kernel.branch_probe_pcs.iter().copied().collect();