Auto merge of #96867 - michaelwoerister:path-prefix-fixes-2, r=davidtwco

--remap-path-prefix: Fix duplicated path components in debuginfo

This PR fixes an issue with `--remap-path-prefix` where path components could appear twice in the remapped version of the path (e.g. https://github.com/rust-lang/rust/issues/78479). The underlying problem was that `--remap-path-prefix` is often used to map an absolute path to something that looks like a relative path, e.g.:

```
--remap-path-prefix=/home/calvin/.cargo/registry/src/github.com-1ecc6299db9ec823=crates.io",
```

and relative paths in debuginfo are interpreted as being relative to the compilation directory. So if Cargo invokes the compiler with `/home/calvin/.cargo/registry/src/github.com-1ecc6299db9ec823/some_crate-0.1.0/src/lib.rs` as input and `/home/calvin/.cargo/registry/src/github.com-1ecc6299db9ec823/some_crate-0.1.0` as the compiler's working directory, then debuginfo will state that the working directory was `crates.io/some_crate-0.1.0` and the file is question was `crates.io/some_crate-0.1.0/src/lib.rs`, which combined gives the path:

```
crates.io/some_crate-0.1.0/crates.io/some_crate-0.1.0/src/lib.rs
```

With this PR the compiler will detect this situation and set up debuginfo in LLVM in a way that makes it strip the duplicated path components when emitting DWARF.

The PR also extracts the logic for making remapped paths absolute into a common helper function that is now used by debuginfo too (instead of just during crate metadata generation).

4 files changed, 84 insertions, 1 deletions

diff --git a/src/bootstrap/dist.rs b/src/bootstrap/dist.rs
index 6181a611ec3..16727f4398d 100644
--- a/src/bootstrap/dist.rs
+++ b/src/bootstrap/dist.rs
@@ -2047,6 +2047,7 @@ impl Step for RustDev {
             "llvm-cov",
             "llvm-dwp",
             "llvm-nm",
+            "llvm-dwarfdump",
         ] {
             tarball.add_file(src_bindir.join(exe(bin, target)), "bin", 0o755);
         }
diff --git a/src/test/codegen/remap_path_prefix/main.rs b/src/test/codegen/remap_path_prefix/main.rs
index b13d576295c..381f11ff1ef 100644
--- a/src/test/codegen/remap_path_prefix/main.rs
+++ b/src/test/codegen/remap_path_prefix/main.rs
@@ -22,7 +22,7 @@ fn main() {
 }
 
 // Here we check that local debuginfo is mapped correctly.
-// CHECK: !DIFile(filename: "/the/src/remap_path_prefix/main.rs", directory: "/the/cwd"
+// CHECK: !DIFile(filename: "/the/src/remap_path_prefix/main.rs", directory: ""
 
 // And here that debuginfo from other crates are expanded to absolute paths.
 // CHECK: !DIFile(filename: "/the/aux-src/remap_path_prefix_aux.rs", directory: ""
diff --git a/src/test/run-make/remap-path-prefix-dwarf/Makefile b/src/test/run-make/remap-path-prefix-dwarf/Makefile
new file mode 100644
index 00000000000..561a343d60b
--- /dev/null
+++ b/src/test/run-make/remap-path-prefix-dwarf/Makefile
@@ -0,0 +1,77 @@
+# This test makes sure that --remap-path-prefix has the expected effects on paths in debuginfo.
+# It tests several cases, each of them has a detailed description attached to it.
+
+# ignore-windows
+
+SRC_DIR := $(abspath .)
+SRC_DIR_PARENT := $(abspath ..)
+
+-include ../../run-make-fulldeps/tools.mk
+
+all: \
+  abs_input_outside_working_dir \
+  rel_input_remap_working_dir \
+  rel_input_remap_working_dir_parent \
+  rel_input_remap_working_dir_child \
+  abs_input_inside_working_dir \
+  abs_input_outside_working_dir
+
+# The compiler is called with an *ABSOLUTE PATH* as input, and that absolute path *is* within
+# the working directory of the compiler. We are remapping the path that contains `src`.
+abs_input_inside_working_dir:
+	# We explicitly switch to a directory that *is* a prefix of the directory our
+	# source code is contained in.
+	cd $(SRC_DIR) && $(RUSTC) $(SRC_DIR)/src/quux.rs -o "$(TMPDIR)/abs_input_inside_working_dir.rlib" -Cdebuginfo=2 --remap-path-prefix $(SRC_DIR)=REMAPPED
+	# We expect the path to the main source file to be remapped.
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump $(TMPDIR)/abs_input_inside_working_dir.rlib | $(CGREP) "REMAPPED/src/quux.rs"
+	# No weird duplication of remapped components (see #78479)
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump $(TMPDIR)/abs_input_inside_working_dir.rlib | $(CGREP) -v "REMAPPED/REMAPPED"
+
+# The compiler is called with an *ABSOLUTE PATH* as input, and that absolute path is *not* within
+# the working directory of the compiler. We are remapping both the path that contains `src` and
+# the working directory to the same thing. This setup corresponds to a workaround that is needed
+# when trying to remap everything to something that looks like a local path.
+# Relative paths are interpreted as relative to the compiler's working directory (e.g. in
+# debuginfo). If we also remap the working directory, the compiler strip it from other paths so
+# that the final outcome is the desired one again.
+abs_input_outside_working_dir:
+	# We explicitly switch to a directory that is *not* a prefix of the directory our
+	# source code is contained in.
+	cd $(TMPDIR) && $(RUSTC) $(SRC_DIR)/src/quux.rs -o "$(TMPDIR)/abs_input_outside_working_dir.rlib" -Cdebuginfo=2 --remap-path-prefix $(SRC_DIR)=REMAPPED --remap-path-prefix $(TMPDIR)=REMAPPED
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump $(TMPDIR)/abs_input_outside_working_dir.rlib | $(CGREP) "REMAPPED/src/quux.rs"
+	# No weird duplication of remapped components (see #78479)
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump $(TMPDIR)/abs_input_outside_working_dir.rlib | $(CGREP) -v "REMAPPED/REMAPPED"
+
+# The compiler is called with a *RELATIVE PATH* as input. We are remapping the working directory of
+# the compiler, which naturally is an implicit prefix of our relative input path. Debuginfo will
+# expand the relative path to an absolute path and we expect the working directory to be remapped
+# in that expansion.
+rel_input_remap_working_dir:
+	cd $(SRC_DIR) && $(RUSTC) src/quux.rs -o "$(TMPDIR)/rel_input_remap_working_dir.rlib" -Cdebuginfo=2 --remap-path-prefix "$(SRC_DIR)=REMAPPED"
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump "$(TMPDIR)/rel_input_remap_working_dir.rlib" | $(CGREP) "REMAPPED/src/quux.rs"
+	# No weird duplication of remapped components (see #78479)
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump "$(TMPDIR)/rel_input_remap_working_dir.rlib" | $(CGREP) -v "REMAPPED/REMAPPED"
+
+# The compiler is called with a *RELATIVE PATH* as input. We are remapping a *SUB-DIRECTORY* of the
+# compiler's working directory. This test makes sure that that directory is remapped even though it
+# won't actually show up in this form in the compiler's SourceMap and instead is only constructed
+# on demand during debuginfo generation.
+rel_input_remap_working_dir_child:
+	cd $(SRC_DIR) && $(RUSTC) src/quux.rs -o "$(TMPDIR)/rel_input_remap_working_dir_child.rlib" -Cdebuginfo=2 --remap-path-prefix "$(SRC_DIR)/src=REMAPPED"
+	# We expect `src/quux.rs` to have been remapped to `REMAPPED/quux.rs`.
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump "$(TMPDIR)/rel_input_remap_working_dir_child.rlib" | $(CGREP) "REMAPPED/quux.rs"
+	# We don't want to find the path that we just remapped anywhere in the DWARF
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump "$(TMPDIR)/rel_input_remap_working_dir_child.rlib" | $(CGREP) -v "$(SRC_DIR)/src"
+	# No weird duplication of remapped components (see #78479)
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump "$(TMPDIR)/rel_input_remap_working_dir_child.rlib" | $(CGREP) -v "REMAPPED/REMAPPED"
+
+# The compiler is called with a *RELATIVE PATH* as input. We are remapping a *PARENT DIRECTORY* of
+# the compiler's working directory.
+rel_input_remap_working_dir_parent:
+	cd $(SRC_DIR) && $(RUSTC) src/quux.rs -o "$(TMPDIR)/rel_input_remap_working_dir_parent.rlib" -Cdebuginfo=2 --remap-path-prefix "$(SRC_DIR_PARENT)=REMAPPED"
+	# We expect `src/quux.rs` to have been remapped to `REMAPPED/remap-path-prefix-dwarf/src/quux.rs`.
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump "$(TMPDIR)/rel_input_remap_working_dir_parent.rlib" | $(CGREP) "REMAPPED/remap-path-prefix-dwarf/src/quux.rs"
+	# We don't want to find the path that we just remapped anywhere in the DWARF
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump "$(TMPDIR)/rel_input_remap_working_dir_parent.rlib" | $(CGREP) -v "$(SRC_DIR_PARENT)"
+	# No weird duplication of remapped components (see #78479)
+	"$(LLVM_BIN_DIR)"/llvm-dwarfdump "$(TMPDIR)/rel_input_remap_working_dir_parent.rlib" | $(CGREP) -v "REMAPPED/REMAPPED"
diff --git a/src/test/run-make/remap-path-prefix-dwarf/src/quux.rs b/src/test/run-make/remap-path-prefix-dwarf/src/quux.rs
new file mode 100644
index 00000000000..38d5ef6194c
--- /dev/null
+++ b/src/test/run-make/remap-path-prefix-dwarf/src/quux.rs
@@ -0,0 +1,5 @@
+#![crate_type = "rlib"]
+
+pub fn foo() {
+    println!("foo");
+}