Rollup merge of #105286 - willcrichton:maximal-hir-to-mir-coverage, r=cjgillot

Add -Z maximal-hir-to-mir-coverage flag

This PR adds a new unstable flag `-Z maximal-hir-to-mir-coverage` that changes the behavior of `maybe_lint_level_root_bounded`, pursuant to [a discussion on Zulip](https://rust-lang.zulipchat.com/#narrow/stream/131828-t-compiler/topic/Mapping.20MIR.20to.20HIR). When enabled, this function will not search upwards for a lint root, but rather immediately return the provided HIR node ID. This change increases the granularity of the mapping between MIR locations and HIR nodes inside the `SourceScopeLocalData` data structures. This increase in granularity is useful for rustc consumers like [Flowistry](https://github.com/willcrichton/flowistry) that rely on getting source-mapping information about the MIR CFG that is as precise as possible.

A test `maximal_mir_to_hir_coverage.rs` has been added to verify that this flag does not break anything.

r? `@cjgillot`

cc `@gavinleroy`

6 files changed, 59 insertions, 32 deletions

diff --git a/compiler/rustc_interface/src/tests.rs b/compiler/rustc_interface/src/tests.rs
index a6205f4d3a5..2b8f6557c82 100644
--- a/compiler/rustc_interface/src/tests.rs
+++ b/compiler/rustc_interface/src/tests.rs
@@ -747,6 +747,7 @@ fn test_unstable_options_tracking_hash() {
     tracked!(link_only, true);
     tracked!(llvm_plugins, vec![String::from("plugin_name")]);
     tracked!(location_detail, LocationDetail { file: true, line: false, column: false });
+    tracked!(maximal_hir_to_mir_coverage, true);
     tracked!(merge_functions, Some(MergeFunctions::Disabled));
     tracked!(mir_emit_retag, true);
     tracked!(mir_enable_passes, vec![("DestProp".to_string(), false)]);
diff --git a/compiler/rustc_mir_build/src/build/mod.rs b/compiler/rustc_mir_build/src/build/mod.rs
index b456e2aa37a..007f3b55ec8 100644
--- a/compiler/rustc_mir_build/src/build/mod.rs
+++ b/compiler/rustc_mir_build/src/build/mod.rs
@@ -948,20 +948,12 @@ impl<'a, 'tcx> Builder<'a, 'tcx> {
         original_source_scope: SourceScope,
         pattern_span: Span,
     ) {
-        let tcx = self.tcx;
-        let current_root = tcx.maybe_lint_level_root_bounded(arg_hir_id, self.hir_id);
-        let parent_root = tcx.maybe_lint_level_root_bounded(
-            self.source_scopes[original_source_scope]
-                .local_data
-                .as_ref()
-                .assert_crate_local()
-                .lint_root,
-            self.hir_id,
-        );
-        if current_root != parent_root {
-            self.source_scope =
-                self.new_source_scope(pattern_span, LintLevel::Explicit(current_root), None);
-        }
+        let parent_id = self.source_scopes[original_source_scope]
+            .local_data
+            .as_ref()
+            .assert_crate_local()
+            .lint_root;
+        self.maybe_new_source_scope(pattern_span, None, arg_hir_id, parent_id);
     }
 
     fn get_unit_temp(&mut self) -> Place<'tcx> {
diff --git a/compiler/rustc_mir_build/src/build/scope.rs b/compiler/rustc_mir_build/src/build/scope.rs
index 5ddae5f5300..33f49ffdaf6 100644
--- a/compiler/rustc_mir_build/src/build/scope.rs
+++ b/compiler/rustc_mir_build/src/build/scope.rs
@@ -85,6 +85,7 @@ use std::mem;
 
 use crate::build::{BlockAnd, BlockAndExtension, BlockFrame, Builder, CFG};
 use rustc_data_structures::fx::FxHashMap;
+use rustc_hir::HirId;
 use rustc_index::vec::IndexVec;
 use rustc_middle::middle::region;
 use rustc_middle::mir::*;
@@ -567,25 +568,10 @@ impl<'a, 'tcx> Builder<'a, 'tcx> {
         F: FnOnce(&mut Builder<'a, 'tcx>) -> BlockAnd<R>,
     {
         let source_scope = self.source_scope;
-        let tcx = self.tcx;
         if let LintLevel::Explicit(current_hir_id) = lint_level {
-            // Use `maybe_lint_level_root_bounded` with `root_lint_level` as a bound
-            // to avoid adding Hir dependencies on our parents.
-            // We estimate the true lint roots here to avoid creating a lot of source scopes.
-
-            let parent_root = tcx.maybe_lint_level_root_bounded(
-                self.source_scopes[source_scope].local_data.as_ref().assert_crate_local().lint_root,
-                self.hir_id,
-            );
-            let current_root = tcx.maybe_lint_level_root_bounded(current_hir_id, self.hir_id);
-
-            if parent_root != current_root {
-                self.source_scope = self.new_source_scope(
-                    region_scope.1.span,
-                    LintLevel::Explicit(current_root),
-                    None,
-                );
-            }
+            let parent_id =
+                self.source_scopes[source_scope].local_data.as_ref().assert_crate_local().lint_root;
+            self.maybe_new_source_scope(region_scope.1.span, None, current_hir_id, parent_id);
         }
         self.push_scope(region_scope);
         let mut block;
@@ -758,6 +744,40 @@ impl<'a, 'tcx> Builder<'a, 'tcx> {
         ))
     }
 
+    /// Possibly creates a new source scope if `current_root` and `parent_root`
+    /// are different, or if -Zmaximal-hir-to-mir-coverage is enabled.
+    pub(crate) fn maybe_new_source_scope(
+        &mut self,
+        span: Span,
+        safety: Option<Safety>,
+        current_id: HirId,
+        parent_id: HirId,
+    ) {
+        let (current_root, parent_root) =
+            if self.tcx.sess.opts.unstable_opts.maximal_hir_to_mir_coverage {
+                // Some consumers of rustc need to map MIR locations back to HIR nodes. Currently the
+                // the only part of rustc that tracks MIR -> HIR is the `SourceScopeLocalData::lint_root`
+                // field that tracks lint levels for MIR locations.  Normally the number of source scopes
+                // is limited to the set of nodes with lint annotations. The -Zmaximal-hir-to-mir-coverage
+                // flag changes this behavior to maximize the number of source scopes, increasing the
+                // granularity of the MIR->HIR mapping.
+                (current_id, parent_id)
+            } else {
+                // Use `maybe_lint_level_root_bounded` with `self.hir_id` as a bound
+                // to avoid adding Hir dependencies on our parents.
+                // We estimate the true lint roots here to avoid creating a lot of source scopes.
+                (
+                    self.tcx.maybe_lint_level_root_bounded(current_id, self.hir_id),
+                    self.tcx.maybe_lint_level_root_bounded(parent_id, self.hir_id),
+                )
+            };
+
+        if current_root != parent_root {
+            let lint_level = LintLevel::Explicit(current_root);
+            self.source_scope = self.new_source_scope(span, lint_level, safety);
+        }
+    }
+
     /// Creates a new source scope, nested in the current one.
     pub(crate) fn new_source_scope(
         &mut self,
diff --git a/compiler/rustc_session/src/options.rs b/compiler/rustc_session/src/options.rs
index 01a9361e786..8e9198b79df 100644
--- a/compiler/rustc_session/src/options.rs
+++ b/compiler/rustc_session/src/options.rs
@@ -1382,6 +1382,9 @@ options! {
         "list the symbols defined by a library crate (default: no)"),
     macro_backtrace: bool = (false, parse_bool, [UNTRACKED],
         "show macro backtraces (default: no)"),
+    maximal_hir_to_mir_coverage: bool = (false, parse_bool, [TRACKED],
+        "save as much information as possible about the correspondence between MIR and HIR \
+        as source scopes (default: no)"),
     merge_functions: Option<MergeFunctions> = (None, parse_merge_functions, [TRACKED],
         "control the operation of the MergeFunctions LLVM pass, taking \
         the same values as the target option of the same name"),
diff --git a/src/test/rustdoc-ui/z-help.stdout b/src/test/rustdoc-ui/z-help.stdout
index 55154803098..94cf7b94241 100644
--- a/src/test/rustdoc-ui/z-help.stdout
+++ b/src/test/rustdoc-ui/z-help.stdout
@@ -77,6 +77,7 @@
     -Z                         location-detail=val -- what location details should be tracked when using caller_location, either `none`, or a comma separated list of location details, for which valid options are `file`, `line`, and `column` (default: `file,line,column`)
     -Z                                      ls=val -- list the symbols defined by a library crate (default: no)
     -Z                         macro-backtrace=val -- show macro backtraces (default: no)
+    -Z             maximal-hir-to-mir-coverage=val -- save as much information as possible about the correspondence between MIR and HIR as source scopes (default: no)
     -Z                         merge-functions=val -- control the operation of the MergeFunctions LLVM pass, taking the same values as the target option of the same name
     -Z                              meta-stats=val -- gather metadata statistics (default: no)
     -Z                          mir-emit-retag=val -- emit Retagging MIR statements, interpreted e.g., by miri; implies -Zmir-opt-level=0 (default: no)
diff --git a/src/test/ui/maximal_mir_to_hir_coverage.rs b/src/test/ui/maximal_mir_to_hir_coverage.rs
new file mode 100644
index 00000000000..5ca54633f21
--- /dev/null
+++ b/src/test/ui/maximal_mir_to_hir_coverage.rs
@@ -0,0 +1,10 @@
+// compile-flags: -Zmaximal-hir-to-mir-coverage
+// run-pass
+
+// Just making sure this flag is accepted and doesn't crash the compiler
+
+fn main() {
+  let x = 1;
+  let y = x + 1;
+  println!("{y}");
+}