From 3afda4322c34dedc2319701fdfac3505c8d311e9 Mon Sep 17 00:00:00 2001 From: mlugg Date: Mon, 23 Dec 2024 20:39:19 +0000 Subject: compiler: analyze type and value of global declaration separately This commit separates semantic analysis of the annotated type vs value of a global declaration, therefore allowing recursive and mutually recursive values to be declared. Every `Nav` which undergoes analysis now has *two* corresponding `AnalUnit`s: `.{ .nav_val = n }` and `.{ .nav_ty = n }`. The `nav_val` unit is responsible for *fully resolving* the `Nav`: determining its value, linksection, addrspace, etc. The `nav_ty` unit, on the other hand, resolves only the information necessary to construct a *pointer* to the `Nav`: its type, addrspace, etc. (It does also analyze its linksection, but that could be moved to `nav_val` I think; it doesn't make any difference). Analyzing a `nav_ty` for a declaration with no type annotation will just mark a dependency on the `nav_val`, analyze it, and finish. Conversely, analyzing a `nav_val` for a declaration *with* a type annotation will first mark a dependency on the `nav_ty` and analyze it, using this as the result type when evaluating the value body. The `nav_val` and `nav_ty` units always have references to one another: so, if a `Nav`'s type is referenced, its value implicitly is too, and vice versa. However, these dependencies are trivial, so, to save memory, are only known implicitly by logic in `resolveReferences`. In general, analyzing ZIR `decl_val` will only analyze `nav_ty` of the corresponding `Nav`. There are two exceptions to this. If the declaration is an `extern` declaration, then we immediately ensure the `Nav` value is resolved (which doesn't actually require any more analysis, since such a declaration has no value body anyway). Additionally, if the resolved type has type tag `.@"fn"`, we again immediately resolve the `Nav` value. The latter restriction is in place for two reasons: * Functions are special, in that their externs are allowed to trivially alias; i.e. with a declaration `extern fn foo(...)`, you can write `const bar = foo;`. This is not allowed for non-function externs, and it means that function types are the only place where it is possible for a declaration `Nav` to have a `.@"extern"` value without actually being declared `extern`. We need to identify this situation immediately so that the `decl_ref` can create a pointer to the *real* extern `Nav`, not this alias. * In certain situations, such as taking a pointer to a `Nav`, Sema needs to queue analysis of a runtime function if the value is a function. To do this, the function value needs to be known, so we need to resolve the value immediately upon `&foo` where `foo` is a function. This restriction is simple to codify into the eventual language specification, and doesn't limit the utility of this feature in practice. A consequence of this commit is that codegen and linking logic needs to be more careful when looking at `Nav`s. In general: * When `updateNav` or `updateFunc` is called, it is safe to assume that the `Nav` being updated (the owner `Nav` for `updateFunc`) is fully resolved. * Any `Nav` whose value is/will be an `@"extern"` or a function is fully resolved; see `Nav.getExtern` for a helper for a common case here. * Any other `Nav` may only have its type resolved. This didn't seem to be too tricky to satisfy in any of the existing codegen/linker backends. Resolves: #131 --- src/Compilation.zig | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'src/Compilation.zig') diff --git a/src/Compilation.zig b/src/Compilation.zig index 6f9b2e18d6..28c5efab6c 100644 --- a/src/Compilation.zig +++ b/src/Compilation.zig @@ -2906,6 +2906,7 @@ const Header = extern struct { file_deps_len: u32, src_hash_deps_len: u32, nav_val_deps_len: u32, + nav_ty_deps_len: u32, namespace_deps_len: u32, namespace_name_deps_len: u32, first_dependency_len: u32, @@ -2949,6 +2950,7 @@ pub fn saveState(comp: *Compilation) !void { .file_deps_len = @intCast(ip.file_deps.count()), .src_hash_deps_len = @intCast(ip.src_hash_deps.count()), .nav_val_deps_len = @intCast(ip.nav_val_deps.count()), + .nav_ty_deps_len = @intCast(ip.nav_ty_deps.count()), .namespace_deps_len = @intCast(ip.namespace_deps.count()), .namespace_name_deps_len = @intCast(ip.namespace_name_deps.count()), .first_dependency_len = @intCast(ip.first_dependency.count()), @@ -2979,6 +2981,8 @@ pub fn saveState(comp: *Compilation) !void { addBuf(&bufs, mem.sliceAsBytes(ip.src_hash_deps.values())); addBuf(&bufs, mem.sliceAsBytes(ip.nav_val_deps.keys())); addBuf(&bufs, mem.sliceAsBytes(ip.nav_val_deps.values())); + addBuf(&bufs, mem.sliceAsBytes(ip.nav_ty_deps.keys())); + addBuf(&bufs, mem.sliceAsBytes(ip.nav_ty_deps.values())); addBuf(&bufs, mem.sliceAsBytes(ip.namespace_deps.keys())); addBuf(&bufs, mem.sliceAsBytes(ip.namespace_deps.values())); addBuf(&bufs, mem.sliceAsBytes(ip.namespace_name_deps.keys())); @@ -3145,7 +3149,7 @@ pub fn getAllErrorsAlloc(comp: *Compilation) !ErrorBundle { const file_index = switch (anal_unit.unwrap()) { .@"comptime" => |cu| ip.getComptimeUnit(cu).zir_index.resolveFile(ip), - .nav_val => |nav| ip.getNav(nav).analysis.?.zir_index.resolveFile(ip), + .nav_val, .nav_ty => |nav| ip.getNav(nav).analysis.?.zir_index.resolveFile(ip), .type => |ty| Type.fromInterned(ty).typeDeclInst(zcu).?.resolveFile(ip), .func => |ip_index| zcu.funcInfo(ip_index).zir_body_inst.resolveFile(ip), }; @@ -3380,7 +3384,7 @@ pub fn addModuleErrorMsg( defer gpa.free(rt_file_path); const name = switch (ref.referencer.unwrap()) { .@"comptime" => "comptime", - .nav_val => |nav| ip.getNav(nav).name.toSlice(ip), + .nav_val, .nav_ty => |nav| ip.getNav(nav).name.toSlice(ip), .type => |ty| Type.fromInterned(ty).containerTypeName(ip).toSlice(ip), .func => |f| ip.getNav(zcu.funcInfo(f).owner_nav).name.toSlice(ip), }; @@ -3647,6 +3651,7 @@ fn performAllTheWorkInner( try comp.queueJob(switch (outdated.unwrap()) { .func => |f| .{ .analyze_func = f }, .@"comptime", + .nav_ty, .nav_val, .type, => .{ .analyze_comptime_unit = outdated }, @@ -3679,7 +3684,7 @@ fn processOneJob(tid: usize, comp: *Compilation, job: Job, prog_node: std.Progre return; } } - assert(nav.status == .resolved); + assert(nav.status == .fully_resolved); comp.dispatchCodegenTask(tid, .{ .codegen_nav = nav_index }); }, .codegen_func => |func| { @@ -3709,6 +3714,7 @@ fn processOneJob(tid: usize, comp: *Compilation, job: Job, prog_node: std.Progre const maybe_err: Zcu.SemaError!void = switch (unit.unwrap()) { .@"comptime" => |cu| pt.ensureComptimeUnitUpToDate(cu), + .nav_ty => |nav| pt.ensureNavTypeUpToDate(nav), .nav_val => |nav| pt.ensureNavValUpToDate(nav), .type => |ty| if (pt.ensureTypeUpToDate(ty)) |_| {} else |err| err, .func => unreachable, @@ -3734,7 +3740,7 @@ fn processOneJob(tid: usize, comp: *Compilation, job: Job, prog_node: std.Progre // Tests are always emitted in test binaries. The decl_refs are created by // Zcu.populateTestFunctions, but this will not queue body analysis, so do // that now. - try pt.zcu.ensureFuncBodyAnalysisQueued(ip.getNav(nav).status.resolved.val); + try pt.zcu.ensureFuncBodyAnalysisQueued(ip.getNav(nav).status.fully_resolved.val); } }, .resolve_type_fully => |ty| { -- cgit v1.2.3