Rollup merge of #127581 - fmease:fix-crate_name-validation, r=bjorn3

Fix crate name validation

Reject macro calls inside attribute `#![crate_name]` like in `#![crate_name = concat!("na", "me")]`.

Prior to #117584, the result of the expansion (here: `"name"`) would actually be properly picked up by the compiler and used as the crate name. However since #117584 / on master, we extract the "value" (i.e., the *literal* string literal) of the `#![crate_name]` much earlier in the pipeline way before macro expansion and **skip**/**ignore** any `#![crate_name]`s "assigned to" a macro call. See also #122001.

T-lang has ruled to reject `#![crate_name = MACRO!(...)]` outright very similar to other built-in attributes whose value we need early like `#![crate_type]`. See accepted FCP: https://github.com/rust-lang/rust/issues/122001#issuecomment-2023203182.

Note that the check as implemented in this PR is even more "aggressive" compared to the one of `#![crate_type]` by running as early as possible in order to reject `#![crate_name = MACRO!(...)]` even in "non-normal" executions of `rustc`, namely on *print requests* (e.g., `--print=crate-name` and `--print=file-names`). If I were to move the validation step a bit further back close to the `#![crate_type]` one, `--print=crate-name` (etc.) would *not* exit fatally with an error in this kind of situation but happily report an incorrect crate name (i.e., the "crate name" as if `#![crate_name]` didn't exist / deduced from other sources like `--crate-name` or the file name) which would match the behavior on master. Again, see also #122001.

I'm mentioning this explicitly because I'm not sure if it was that clear in the FCP'ed issue. I argue that my current approach is the most reasonable one. I know (from reading the code and from past experiments) that various print requests are still quite broken (mostly lack of validation).

To the best of my knowledge, there's no print request whose output references/contains a crate *type*, so there's no "inherent need" to move `#![crate_type]`'s validation to happen earlier.

---

Fixes #122001.

https://github.com/rust-lang/rust/labels/relnotes: Compatibility. Breaking change.

3 files changed, 102 insertions, 24 deletions

diff --git a/compiler/rustc_interface/src/errors.rs b/compiler/rustc_interface/src/errors.rs
index b62950d6709..c3b858d4f2e 100644
--- a/compiler/rustc_interface/src/errors.rs
+++ b/compiler/rustc_interface/src/errors.rs
@@ -5,6 +5,21 @@ use rustc_macros::Diagnostic;
 use rustc_span::{Span, Symbol};
 
 #[derive(Diagnostic)]
+#[diag(interface_crate_name_does_not_match)]
+pub(crate) struct CrateNameDoesNotMatch {
+    #[primary_span]
+    pub(crate) span: Span,
+    pub(crate) crate_name: Symbol,
+    pub(crate) attr_crate_name: Symbol,
+}
+
+#[derive(Diagnostic)]
+#[diag(interface_crate_name_invalid)]
+pub(crate) struct CrateNameInvalid<'a> {
+    pub(crate) crate_name: &'a str,
+}
+
+#[derive(Diagnostic)]
 #[diag(interface_ferris_identifier)]
 pub struct FerrisIdentifier {
     #[primary_span]
diff --git a/compiler/rustc_interface/src/passes.rs b/compiler/rustc_interface/src/passes.rs
index e5adcdb244f..fcebca3ecc9 100644
--- a/compiler/rustc_interface/src/passes.rs
+++ b/compiler/rustc_interface/src/passes.rs
@@ -28,10 +28,12 @@ use rustc_passes::{abi_test, input_stats, layout_test};
 use rustc_resolve::Resolver;
 use rustc_session::config::{CrateType, Input, OutFileName, OutputFilenames, OutputType};
 use rustc_session::cstore::Untracked;
-use rustc_session::output::{collect_crate_types, filename_for_input, find_crate_name};
+use rustc_session::output::{collect_crate_types, filename_for_input};
 use rustc_session::search_paths::PathKind;
 use rustc_session::{Limit, Session};
-use rustc_span::{ErrorGuaranteed, FileName, SourceFileHash, SourceFileHashAlgorithm, Symbol, sym};
+use rustc_span::{
+    ErrorGuaranteed, FileName, SourceFileHash, SourceFileHashAlgorithm, Span, Symbol, sym,
+};
 use rustc_target::spec::PanicStrategy;
 use rustc_trait_selection::traits;
 use tracing::{info, instrument};
@@ -725,8 +727,7 @@ pub fn create_and_enter_global_ctxt<T, F: for<'tcx> FnOnce(TyCtxt<'tcx>) -> T>(
 
     let pre_configured_attrs = rustc_expand::config::pre_configure_attrs(sess, &krate.attrs);
 
-    // parse `#[crate_name]` even if `--crate-name` was passed, to make sure it matches.
-    let crate_name = find_crate_name(sess, &pre_configured_attrs);
+    let crate_name = get_crate_name(sess, &pre_configured_attrs);
     let crate_types = collect_crate_types(sess, &pre_configured_attrs);
     let stable_crate_id = StableCrateId::new(
         crate_name,
@@ -735,7 +736,7 @@ pub fn create_and_enter_global_ctxt<T, F: for<'tcx> FnOnce(TyCtxt<'tcx>) -> T>(
         sess.cfg_version,
     );
     let outputs = util::build_output_filenames(&pre_configured_attrs, sess);
-    let dep_graph = setup_dep_graph(sess);
+    let dep_graph = setup_dep_graph(sess, crate_name);
 
     let cstore =
         FreezeLock::new(Box::new(CStore::new(compiler.codegen_backend.metadata_loader())) as _);
@@ -1080,23 +1081,85 @@ pub(crate) fn start_codegen<'tcx>(
     codegen
 }
 
-fn get_recursion_limit(krate_attrs: &[ast::Attribute], sess: &Session) -> Limit {
-    if let Some(attr) = krate_attrs
-        .iter()
-        .find(|attr| attr.has_name(sym::recursion_limit) && attr.value_str().is_none())
+/// Compute and validate the crate name.
+pub fn get_crate_name(sess: &Session, krate_attrs: &[ast::Attribute]) -> Symbol {
+    // We validate *all* occurrences of `#![crate_name]`, pick the first find and
+    // if a crate name was passed on the command line via `--crate-name` we enforce
+    // that they match.
+    // We perform the validation step here instead of later to ensure it gets run
+    // in all code paths that require the crate name very early on, namely before
+    // macro expansion.
+
+    let attr_crate_name =
+        validate_and_find_value_str_builtin_attr(sym::crate_name, sess, krate_attrs);
+
+    let validate = |name, span| {
+        rustc_session::output::validate_crate_name(sess, name, span);
+        name
+    };
+
+    if let Some(crate_name) = &sess.opts.crate_name {
+        let crate_name = Symbol::intern(crate_name);
+        if let Some((attr_crate_name, span)) = attr_crate_name
+            && attr_crate_name != crate_name
+        {
+            sess.dcx().emit_err(errors::CrateNameDoesNotMatch {
+                span,
+                crate_name,
+                attr_crate_name,
+            });
+        }
+        return validate(crate_name, None);
+    }
+
+    if let Some((crate_name, span)) = attr_crate_name {
+        return validate(crate_name, Some(span));
+    }
+
+    if let Input::File(ref path) = sess.io.input
+        && let Some(file_stem) = path.file_stem().and_then(|s| s.to_str())
     {
-        // This is here mainly to check for using a macro, such as
-        // #![recursion_limit = foo!()]. That is not supported since that
-        // would require expanding this while in the middle of expansion,
-        // which needs to know the limit before expanding. Otherwise,
-        // validation would normally be caught in AstValidator (via
-        // `check_builtin_attribute`), but by the time that runs the macro
-        // is expanded, and it doesn't give an error.
-        validate_attr::emit_fatal_malformed_builtin_attribute(
-            &sess.psess,
-            attr,
-            sym::recursion_limit,
-        );
+        if file_stem.starts_with('-') {
+            sess.dcx().emit_err(errors::CrateNameInvalid { crate_name: file_stem });
+        } else {
+            return validate(Symbol::intern(&file_stem.replace('-', "_")), None);
+        }
     }
+
+    sym::rust_out
+}
+
+fn get_recursion_limit(krate_attrs: &[ast::Attribute], sess: &Session) -> Limit {
+    // We don't permit macro calls inside of the attribute (e.g., #![recursion_limit = `expand!()`])
+    // because that would require expanding this while in the middle of expansion, which needs to
+    // know the limit before expanding.
+    let _ = validate_and_find_value_str_builtin_attr(sym::recursion_limit, sess, krate_attrs);
     rustc_middle::middle::limits::get_recursion_limit(krate_attrs, sess)
 }
+
+/// Validate *all* occurrences of the given "[value-str]" built-in attribute and return the first find.
+///
+/// This validator is intended for built-in attributes whose value needs to be known very early
+/// during compilation (namely, before macro expansion) and it mainly exists to reject macro calls
+/// inside of the attributes, such as in `#![name = expand!()]`. Normal attribute validation happens
+/// during semantic analysis via [`TyCtxt::check_mod_attrs`] which happens *after* macro expansion
+/// when such macro calls (here: `expand`) have already been expanded and we can no longer check for
+/// their presence.
+///
+/// [value-str]: ast::Attribute::value_str
+fn validate_and_find_value_str_builtin_attr(
+    name: Symbol,
+    sess: &Session,
+    krate_attrs: &[ast::Attribute],
+) -> Option<(Symbol, Span)> {
+    let mut result = None;
+    // Validate *all* relevant attributes, not just the first occurrence.
+    for attr in ast::attr::filter_by_name(krate_attrs, name) {
+        let Some(value) = attr.value_str() else {
+            validate_attr::emit_fatal_malformed_builtin_attribute(&sess.psess, attr, name)
+        };
+        // Choose the first occurrence as our result.
+        result.get_or_insert((value, attr.span));
+    }
+    result
+}
diff --git a/compiler/rustc_interface/src/util.rs b/compiler/rustc_interface/src/util.rs
index e900ec14fca..bc2aae7cd87 100644
--- a/compiler/rustc_interface/src/util.rs
+++ b/compiler/rustc_interface/src/util.rs
@@ -433,11 +433,11 @@ pub(crate) fn check_attr_crate_type(
                 }
             } else {
                 // This is here mainly to check for using a macro, such as
-                // #![crate_type = foo!()]. That is not supported since the
+                // `#![crate_type = foo!()]`. That is not supported since the
                 // crate type needs to be known very early in compilation long
                 // before expansion. Otherwise, validation would normally be
-                // caught in AstValidator (via `check_builtin_attribute`), but
-                // by the time that runs the macro is expanded, and it doesn't
+                // caught during semantic analysis via `TyCtxt::check_mod_attrs`,
+                // but by the time that runs the macro is expanded, and it doesn't
                 // give an error.
                 validate_attr::emit_fatal_malformed_builtin_attribute(
                     &sess.psess,