From 3aa6f189d43add0dc937facbd7dab2a7ccace23b Mon Sep 17 00:00:00 2001 From: Steve Klabnik Date: Tue, 28 Feb 2017 14:09:27 -0500 Subject: [PATCH 01/24] add unstable book to the bookshelf --- src/doc/index.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/doc/index.md b/src/doc/index.md index 982e24ef69549..8c33c44390fe5 100644 --- a/src/doc/index.md +++ b/src/doc/index.md @@ -28,6 +28,7 @@ Rust provides a number of book-length sets of documentation, collectively nicknamed 'The Rust Bookshelf.' * [The Rust Programming Language][book] teaches you how to program in Rust. +* [The Unstable Book][unstable-book] has documentation for unstable features. * [The Rustonomicon][nomicon] is your guidebook to the dark arts of unsafe Rust. * [The Reference][ref] is not a formal spec, but is more detailed and comprehensive than the book. @@ -42,6 +43,7 @@ landed before then. That work is being tracked [here][38643]. [ref]: reference/index.html [38643]: https://github.com/rust-lang/rust/issues/38643 [err]: error-index.html -[book]: book/index.html +[unstable-book]: book/index.html [nomicon]: nomicon/index.html +[unstable-book]: unstable-book/index.html From ae2c9d2cf9a061110fd0900171796a9437546a39 Mon Sep 17 00:00:00 2001 From: Steve Klabnik Date: Thu, 2 Mar 2017 16:36:54 -0500 Subject: [PATCH 02/24] fix link --- src/doc/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/doc/index.md b/src/doc/index.md index 8c33c44390fe5..1f262b360e3ed 100644 --- a/src/doc/index.md +++ b/src/doc/index.md @@ -43,7 +43,7 @@ landed before then. That work is being tracked [here][38643]. [ref]: reference/index.html [38643]: https://github.com/rust-lang/rust/issues/38643 [err]: error-index.html -[unstable-book]: book/index.html +[book]: book/index.html [nomicon]: nomicon/index.html [unstable-book]: unstable-book/index.html From 6698fb6029d93b992e8f89b5a89bfee2b12a80c6 Mon Sep 17 00:00:00 2001 From: Taylor Cramer Date: Fri, 17 Feb 2017 15:12:47 -0800 Subject: [PATCH 03/24] Add catch expr to AST and disallow catch as a struct name --- src/librustc/hir/lowering.rs | 37 +++++++++++++++++-- src/libsyntax/ast.rs | 2 + src/libsyntax/feature_gate.rs | 6 +++ src/libsyntax/fold.rs | 1 + src/libsyntax/parse/parser.rs | 35 ++++++++++++++++++ src/libsyntax/print/pprust.rs | 5 +++ src/libsyntax/symbol.rs | 3 +- src/libsyntax/visit.rs | 3 ++ .../compile-fail/catch-empty-struct-name.rs | 15 ++++++++ src/test/compile-fail/catch-enum-variant.rs | 17 +++++++++ src/test/compile-fail/catch-struct-name.rs | 15 ++++++++ .../compile-fail/catch-tuple-struct-name.rs | 15 ++++++++ .../compile-fail/feature-gate-catch_expr.rs | 17 +++++++++ src/test/run-pass/catch-expr.rs | 30 +++++++++++++++ 14 files changed, 196 insertions(+), 5 deletions(-) create mode 100644 src/test/compile-fail/catch-empty-struct-name.rs create mode 100644 src/test/compile-fail/catch-enum-variant.rs create mode 100644 src/test/compile-fail/catch-struct-name.rs create mode 100644 src/test/compile-fail/catch-tuple-struct-name.rs create mode 100644 src/test/compile-fail/feature-gate-catch_expr.rs create mode 100644 src/test/run-pass/catch-expr.rs diff --git a/src/librustc/hir/lowering.rs b/src/librustc/hir/lowering.rs index 257cdb960d529..3d51a64c22132 100644 --- a/src/librustc/hir/lowering.rs +++ b/src/librustc/hir/lowering.rs @@ -83,6 +83,7 @@ pub struct LoweringContext<'a> { trait_impls: BTreeMap>, trait_default_impl: BTreeMap, + catch_scopes: Vec, loop_scopes: Vec, is_in_loop_condition: bool, @@ -121,6 +122,7 @@ pub fn lower_crate(sess: &Session, bodies: BTreeMap::new(), trait_impls: BTreeMap::new(), trait_default_impl: BTreeMap::new(), + catch_scopes: Vec::new(), loop_scopes: Vec::new(), is_in_loop_condition: false, type_def_lifetime_params: DefIdMap(), @@ -259,6 +261,21 @@ impl<'a> LoweringContext<'a> { span } + fn with_catch_scope(&mut self, catch_id: NodeId, f: F) -> T + where F: FnOnce(&mut LoweringContext) -> T + { + let len = self.catch_scopes.len(); + self.catch_scopes.push(catch_id); + + let result = f(self); + assert_eq!(len + 1, self.catch_scopes.len(), + "catch scopes should be added and removed in stack order"); + + self.catch_scopes.pop().unwrap(); + + result + } + fn with_loop_scope(&mut self, loop_id: NodeId, f: F) -> T where F: FnOnce(&mut LoweringContext) -> T { @@ -293,15 +310,17 @@ impl<'a> LoweringContext<'a> { result } - fn with_new_loop_scopes(&mut self, f: F) -> T + fn with_new_scopes(&mut self, f: F) -> T where F: FnOnce(&mut LoweringContext) -> T { let was_in_loop_condition = self.is_in_loop_condition; self.is_in_loop_condition = false; + let catch_scopes = mem::replace(&mut self.catch_scopes, Vec::new()); let loop_scopes = mem::replace(&mut self.loop_scopes, Vec::new()); let result = f(self); - mem::replace(&mut self.loop_scopes, loop_scopes); + self.catch_scopes = catch_scopes; + self.loop_scopes = loop_scopes; self.is_in_loop_condition = was_in_loop_condition; @@ -1063,7 +1082,7 @@ impl<'a> LoweringContext<'a> { self.record_body(value, None)) } ItemKind::Fn(ref decl, unsafety, constness, abi, ref generics, ref body) => { - self.with_new_loop_scopes(|this| { + self.with_new_scopes(|this| { let body = this.lower_block(body); let body = this.expr_block(body, ThinVec::new()); let body_id = this.record_body(body, Some(decl)); @@ -1660,13 +1679,17 @@ impl<'a> LoweringContext<'a> { this.lower_opt_sp_ident(opt_ident), hir::LoopSource::Loop)) } + ExprKind::Catch(ref body) => { + // FIXME(cramertj): Add catch to HIR + self.with_catch_scope(e.id, |this| hir::ExprBlock(this.lower_block(body))) + } ExprKind::Match(ref expr, ref arms) => { hir::ExprMatch(P(self.lower_expr(expr)), arms.iter().map(|x| self.lower_arm(x)).collect(), hir::MatchSource::Normal) } ExprKind::Closure(capture_clause, ref decl, ref body, fn_decl_span) => { - self.with_new_loop_scopes(|this| { + self.with_new_scopes(|this| { this.with_parent_def(e.id, |this| { let expr = this.lower_expr(body); hir::ExprClosure(this.lower_capture_clause(capture_clause), @@ -2064,6 +2087,12 @@ impl<'a> LoweringContext<'a> { // Err(err) => #[allow(unreachable_code)] // return Carrier::from_error(From::from(err)), // } + + // FIXME(cramertj): implement breaking to catch + if !self.catch_scopes.is_empty() { + bug!("`?` in catch scopes is unimplemented") + } + let unstable_span = self.allow_internal_unstable("?", e.span); // Carrier::translate() diff --git a/src/libsyntax/ast.rs b/src/libsyntax/ast.rs index 09fb369cd3568..bb0aa6e94b72a 100644 --- a/src/libsyntax/ast.rs +++ b/src/libsyntax/ast.rs @@ -936,6 +936,8 @@ pub enum ExprKind { Closure(CaptureBy, P, P, Span), /// A block (`{ ... }`) Block(P), + /// A catch block (`catch { ... }`) + Catch(P), /// An assignment (`a = foo()`) Assign(P, P), diff --git a/src/libsyntax/feature_gate.rs b/src/libsyntax/feature_gate.rs index 6eb7d449f2692..b776441079ef0 100644 --- a/src/libsyntax/feature_gate.rs +++ b/src/libsyntax/feature_gate.rs @@ -340,6 +340,9 @@ declare_features! ( // `extern "x86-interrupt" fn()` (active, abi_x86_interrupt, "1.17.0", Some(40180)), + + // Allows the `catch {...}` expression + (active, catch_expr, "1.17.0", Some(31436)), ); declare_features! ( @@ -1288,6 +1291,9 @@ impl<'a> Visitor<'a> for PostExpansionVisitor<'a> { } } } + ast::ExprKind::Catch(_) => { + gate_feature_post!(&self, catch_expr, e.span, "`catch` expression is experimental"); + } _ => {} } visit::walk_expr(self, e); diff --git a/src/libsyntax/fold.rs b/src/libsyntax/fold.rs index 257b7efba5c8e..3150ab0be0bea 100644 --- a/src/libsyntax/fold.rs +++ b/src/libsyntax/fold.rs @@ -1276,6 +1276,7 @@ pub fn noop_fold_expr(Expr {id, node, span, attrs}: Expr, folder: &mu }; } ExprKind::Try(ex) => ExprKind::Try(folder.fold_expr(ex)), + ExprKind::Catch(body) => ExprKind::Catch(folder.fold_block(body)), }, id: folder.new_id(id), span: folder.new_span(span), diff --git a/src/libsyntax/parse/parser.rs b/src/libsyntax/parse/parser.rs index 71274c4fdaa4e..eef252319bcc2 100644 --- a/src/libsyntax/parse/parser.rs +++ b/src/libsyntax/parse/parser.rs @@ -515,6 +515,12 @@ impl<'a> Parser<'a> { } } + pub fn error_if_typename_is_catch(&mut self, ident: ast::Ident) { + if ident.name == keywords::Catch.name() { + self.span_err(self.span, "cannot use `catch` as the name of a type"); + } + } + /// Check if the next token is `tok`, and return `true` if so. /// /// This method will automatically add `tok` to `expected_tokens` if `tok` is not @@ -2196,6 +2202,11 @@ impl<'a> Parser<'a> { BlockCheckMode::Unsafe(ast::UserProvided), attrs); } + if self.is_catch_expr() { + assert!(self.eat_keyword(keywords::Catch)); + let lo = self.prev_span.lo; + return self.parse_catch_expr(lo, attrs); + } if self.eat_keyword(keywords::Return) { if self.token.can_begin_expr() { let e = self.parse_expr()?; @@ -3006,6 +3017,16 @@ impl<'a> Parser<'a> { Ok(self.mk_expr(span_lo, hi, ExprKind::Loop(body, opt_ident), attrs)) } + /// Parse a `catch {...}` expression (`catch` token already eaten) + pub fn parse_catch_expr(&mut self, span_lo: BytePos, mut attrs: ThinVec) + -> PResult<'a, P> + { + let (iattrs, body) = self.parse_inner_attrs_and_block()?; + attrs.extend(iattrs); + let hi = body.span.hi; + Ok(self.mk_expr(span_lo, hi, ExprKind::Catch(body), attrs)) + } + // `match` token already eaten fn parse_match_expr(&mut self, mut attrs: ThinVec) -> PResult<'a, P> { let match_span = self.prev_span; @@ -3613,6 +3634,14 @@ impl<'a> Parser<'a> { }) } + fn is_catch_expr(&mut self) -> bool { + self.token.is_keyword(keywords::Catch) && + self.look_ahead(1, |t| *t == token::OpenDelim(token::Brace)) && + + // prevent `while catch {} {}`, `if catch {} {} else {}`, etc. + !self.restrictions.contains(Restrictions::RESTRICTION_NO_STRUCT_LITERAL) + } + fn is_union_item(&mut self) -> bool { self.token.is_keyword(keywords::Union) && self.look_ahead(1, |t| t.is_ident() && !t.is_any_keyword()) @@ -4753,6 +4782,8 @@ impl<'a> Parser<'a> { /// Parse struct Foo { ... } fn parse_item_struct(&mut self) -> PResult<'a, ItemInfo> { let class_name = self.parse_ident()?; + self.error_if_typename_is_catch(class_name); + let mut generics = self.parse_generics()?; // There is a special case worth noting here, as reported in issue #17904. @@ -4802,6 +4833,8 @@ impl<'a> Parser<'a> { /// Parse union Foo { ... } fn parse_item_union(&mut self) -> PResult<'a, ItemInfo> { let class_name = self.parse_ident()?; + self.error_if_typename_is_catch(class_name); + let mut generics = self.parse_generics()?; let vdata = if self.token.is_keyword(keywords::Where) { @@ -5318,6 +5351,7 @@ impl<'a> Parser<'a> { let struct_def; let mut disr_expr = None; let ident = self.parse_ident()?; + self.error_if_typename_is_catch(ident); if self.check(&token::OpenDelim(token::Brace)) { // Parse a struct variant. all_nullary = false; @@ -5359,6 +5393,7 @@ impl<'a> Parser<'a> { /// Parse an "enum" declaration fn parse_item_enum(&mut self) -> PResult<'a, ItemInfo> { let id = self.parse_ident()?; + self.error_if_typename_is_catch(id); let mut generics = self.parse_generics()?; generics.where_clause = self.parse_where_clause()?; self.expect(&token::OpenDelim(token::Brace))?; diff --git a/src/libsyntax/print/pprust.rs b/src/libsyntax/print/pprust.rs index ec962d03458d1..a827d2c6bdbf2 100644 --- a/src/libsyntax/print/pprust.rs +++ b/src/libsyntax/print/pprust.rs @@ -2270,6 +2270,11 @@ impl<'a> State<'a> { self.print_expr(e)?; word(&mut self.s, "?")? } + ast::ExprKind::Catch(ref blk) => { + self.head("catch")?; + space(&mut self.s)?; + self.print_block_with_attrs(&blk, attrs)? + } } self.ann.post(self, NodeExpr(expr))?; self.end() diff --git a/src/libsyntax/symbol.rs b/src/libsyntax/symbol.rs index c278171aa109a..6642c60d256b3 100644 --- a/src/libsyntax/symbol.rs +++ b/src/libsyntax/symbol.rs @@ -221,9 +221,10 @@ declare_keywords! { (53, Default, "default") (54, StaticLifetime, "'static") (55, Union, "union") + (56, Catch, "catch") // A virtual keyword that resolves to the crate root when used in a lexical scope. - (56, CrateRoot, "{{root}}") + (57, CrateRoot, "{{root}}") } // If an interner exists in TLS, return it. Otherwise, prepare a fresh one. diff --git a/src/libsyntax/visit.rs b/src/libsyntax/visit.rs index 013632141dee6..c76846cdf8e27 100644 --- a/src/libsyntax/visit.rs +++ b/src/libsyntax/visit.rs @@ -787,6 +787,9 @@ pub fn walk_expr<'a, V: Visitor<'a>>(visitor: &mut V, expression: &'a Expr) { ExprKind::Try(ref subexpression) => { visitor.visit_expr(subexpression) } + ExprKind::Catch(ref body) => { + visitor.visit_block(body) + } } visitor.visit_expr_post(expression) diff --git a/src/test/compile-fail/catch-empty-struct-name.rs b/src/test/compile-fail/catch-empty-struct-name.rs new file mode 100644 index 0000000000000..257cb802cc0f8 --- /dev/null +++ b/src/test/compile-fail/catch-empty-struct-name.rs @@ -0,0 +1,15 @@ +// Copyright 2017 The Rust Project Developers. See the COPYRIGHT +// file at the top-level directory of this distribution and at +// http://rust-lang.org/COPYRIGHT. +// +// Licensed under the Apache License, Version 2.0 or the MIT license +// , at your +// option. This file may not be copied, modified, or distributed +// except according to those terms. + +#![allow(non_camel_case_types)] +#![allow(dead_code)] +#![feature(catch_expr)] + +struct catch; //~ ERROR cannot use `catch` as the name of a type diff --git a/src/test/compile-fail/catch-enum-variant.rs b/src/test/compile-fail/catch-enum-variant.rs new file mode 100644 index 0000000000000..7aa162750d189 --- /dev/null +++ b/src/test/compile-fail/catch-enum-variant.rs @@ -0,0 +1,17 @@ +// Copyright 2017 The Rust Project Developers. See the COPYRIGHT +// file at the top-level directory of this distribution and at +// http://rust-lang.org/COPYRIGHT. +// +// Licensed under the Apache License, Version 2.0 or the MIT license +// , at your +// option. This file may not be copied, modified, or distributed +// except according to those terms. + +#![allow(non_camel_case_types)] +#![allow(dead_code)] +#![feature(catch_expr)] + +enum Enum { + catch {} //~ ERROR cannot use `catch` as the name of a type +} diff --git a/src/test/compile-fail/catch-struct-name.rs b/src/test/compile-fail/catch-struct-name.rs new file mode 100644 index 0000000000000..63661ccf607a0 --- /dev/null +++ b/src/test/compile-fail/catch-struct-name.rs @@ -0,0 +1,15 @@ +// Copyright 2017 The Rust Project Developers. See the COPYRIGHT +// file at the top-level directory of this distribution and at +// http://rust-lang.org/COPYRIGHT. +// +// Licensed under the Apache License, Version 2.0 or the MIT license +// , at your +// option. This file may not be copied, modified, or distributed +// except according to those terms. + +#![allow(non_camel_case_types)] +#![allow(dead_code)] +#![feature(catch_expr)] + +struct catch {} //~ ERROR cannot use `catch` as the name of a type \ No newline at end of file diff --git a/src/test/compile-fail/catch-tuple-struct-name.rs b/src/test/compile-fail/catch-tuple-struct-name.rs new file mode 100644 index 0000000000000..1a8866d85430d --- /dev/null +++ b/src/test/compile-fail/catch-tuple-struct-name.rs @@ -0,0 +1,15 @@ +// Copyright 2017 The Rust Project Developers. See the COPYRIGHT +// file at the top-level directory of this distribution and at +// http://rust-lang.org/COPYRIGHT. +// +// Licensed under the Apache License, Version 2.0 or the MIT license +// , at your +// option. This file may not be copied, modified, or distributed +// except according to those terms. + +#![allow(non_camel_case_types)] +#![allow(dead_code)] +#![feature(catch_expr)] + +struct catch(); //~ ERROR cannot use `catch` as the name of a type diff --git a/src/test/compile-fail/feature-gate-catch_expr.rs b/src/test/compile-fail/feature-gate-catch_expr.rs new file mode 100644 index 0000000000000..8a1a5ceae89e0 --- /dev/null +++ b/src/test/compile-fail/feature-gate-catch_expr.rs @@ -0,0 +1,17 @@ +// Copyright 2017 The Rust Project Developers. See the COPYRIGHT +// file at the top-level directory of this distribution and at +// http://rust-lang.org/COPYRIGHT. +// +// Licensed under the Apache License, Version 2.0 or the MIT license +// , at your +// option. This file may not be copied, modified, or distributed +// except according to those terms. + +pub fn main() { + let catch_result = catch { //~ ERROR `catch` expression is experimental + let x = 5; + x + }; + assert_eq!(catch_result, 5); +} diff --git a/src/test/run-pass/catch-expr.rs b/src/test/run-pass/catch-expr.rs new file mode 100644 index 0000000000000..c70b6100efe4f --- /dev/null +++ b/src/test/run-pass/catch-expr.rs @@ -0,0 +1,30 @@ +// Copyright 2017 The Rust Project Developers. See the COPYRIGHT +// file at the top-level directory of this distribution and at +// http://rust-lang.org/COPYRIGHT. +// +// Licensed under the Apache License, Version 2.0 or the MIT license +// , at your +// option. This file may not be copied, modified, or distributed +// except according to those terms. + +#![feature(catch_expr)] + +pub fn main() { + let catch_result = catch { + let x = 5; + x + }; + assert_eq!(catch_result, 5); + + let mut catch = true; + while catch { catch = false; } + assert_eq!(catch, false); + + catch = if catch { false } else { true }; + assert_eq!(catch, true); + + match catch { + _ => {} + }; +} From ace24bb653850e5955ec14cc6aef1af61022f85e Mon Sep 17 00:00:00 2001 From: Taylor Cramer Date: Fri, 3 Mar 2017 14:41:07 -0800 Subject: [PATCH 04/24] Temporarily prefix catch block with do keyword --- src/libsyntax/parse/parser.rs | 18 +++++------------- src/libsyntax/parse/token.rs | 1 + .../compile-fail/catch-empty-struct-name.rs | 15 --------------- src/test/compile-fail/catch-enum-variant.rs | 17 ----------------- src/test/compile-fail/catch-struct-name.rs | 15 --------------- .../compile-fail/catch-tuple-struct-name.rs | 15 --------------- .../compile-fail/feature-gate-catch_expr.rs | 2 +- src/test/run-pass/catch-expr.rs | 4 +++- 8 files changed, 10 insertions(+), 77 deletions(-) delete mode 100644 src/test/compile-fail/catch-empty-struct-name.rs delete mode 100644 src/test/compile-fail/catch-enum-variant.rs delete mode 100644 src/test/compile-fail/catch-struct-name.rs delete mode 100644 src/test/compile-fail/catch-tuple-struct-name.rs diff --git a/src/libsyntax/parse/parser.rs b/src/libsyntax/parse/parser.rs index eef252319bcc2..c654ad066c861 100644 --- a/src/libsyntax/parse/parser.rs +++ b/src/libsyntax/parse/parser.rs @@ -515,12 +515,6 @@ impl<'a> Parser<'a> { } } - pub fn error_if_typename_is_catch(&mut self, ident: ast::Ident) { - if ident.name == keywords::Catch.name() { - self.span_err(self.span, "cannot use `catch` as the name of a type"); - } - } - /// Check if the next token is `tok`, and return `true` if so. /// /// This method will automatically add `tok` to `expected_tokens` if `tok` is not @@ -2203,6 +2197,7 @@ impl<'a> Parser<'a> { attrs); } if self.is_catch_expr() { + assert!(self.eat_keyword(keywords::Do)); assert!(self.eat_keyword(keywords::Catch)); let lo = self.prev_span.lo; return self.parse_catch_expr(lo, attrs); @@ -3017,7 +3012,7 @@ impl<'a> Parser<'a> { Ok(self.mk_expr(span_lo, hi, ExprKind::Loop(body, opt_ident), attrs)) } - /// Parse a `catch {...}` expression (`catch` token already eaten) + /// Parse a `do catch {...}` expression (`do catch` token already eaten) pub fn parse_catch_expr(&mut self, span_lo: BytePos, mut attrs: ThinVec) -> PResult<'a, P> { @@ -3635,8 +3630,9 @@ impl<'a> Parser<'a> { } fn is_catch_expr(&mut self) -> bool { - self.token.is_keyword(keywords::Catch) && - self.look_ahead(1, |t| *t == token::OpenDelim(token::Brace)) && + self.token.is_keyword(keywords::Do) && + self.look_ahead(1, |t| t.is_keyword(keywords::Catch)) && + self.look_ahead(2, |t| *t == token::OpenDelim(token::Brace)) && // prevent `while catch {} {}`, `if catch {} {} else {}`, etc. !self.restrictions.contains(Restrictions::RESTRICTION_NO_STRUCT_LITERAL) @@ -4782,7 +4778,6 @@ impl<'a> Parser<'a> { /// Parse struct Foo { ... } fn parse_item_struct(&mut self) -> PResult<'a, ItemInfo> { let class_name = self.parse_ident()?; - self.error_if_typename_is_catch(class_name); let mut generics = self.parse_generics()?; @@ -4833,7 +4828,6 @@ impl<'a> Parser<'a> { /// Parse union Foo { ... } fn parse_item_union(&mut self) -> PResult<'a, ItemInfo> { let class_name = self.parse_ident()?; - self.error_if_typename_is_catch(class_name); let mut generics = self.parse_generics()?; @@ -5351,7 +5345,6 @@ impl<'a> Parser<'a> { let struct_def; let mut disr_expr = None; let ident = self.parse_ident()?; - self.error_if_typename_is_catch(ident); if self.check(&token::OpenDelim(token::Brace)) { // Parse a struct variant. all_nullary = false; @@ -5393,7 +5386,6 @@ impl<'a> Parser<'a> { /// Parse an "enum" declaration fn parse_item_enum(&mut self) -> PResult<'a, ItemInfo> { let id = self.parse_ident()?; - self.error_if_typename_is_catch(id); let mut generics = self.parse_generics()?; generics.where_clause = self.parse_where_clause()?; self.expect(&token::OpenDelim(token::Brace))?; diff --git a/src/libsyntax/parse/token.rs b/src/libsyntax/parse/token.rs index 5b65aac92b81c..25601f2420e8a 100644 --- a/src/libsyntax/parse/token.rs +++ b/src/libsyntax/parse/token.rs @@ -86,6 +86,7 @@ fn ident_can_begin_expr(ident: ast::Ident) -> bool { !ident_token.is_any_keyword() || ident_token.is_path_segment_keyword() || [ + keywords::Do.name(), keywords::Box.name(), keywords::Break.name(), keywords::Continue.name(), diff --git a/src/test/compile-fail/catch-empty-struct-name.rs b/src/test/compile-fail/catch-empty-struct-name.rs deleted file mode 100644 index 257cb802cc0f8..0000000000000 --- a/src/test/compile-fail/catch-empty-struct-name.rs +++ /dev/null @@ -1,15 +0,0 @@ -// Copyright 2017 The Rust Project Developers. See the COPYRIGHT -// file at the top-level directory of this distribution and at -// http://rust-lang.org/COPYRIGHT. -// -// Licensed under the Apache License, Version 2.0 or the MIT license -// , at your -// option. This file may not be copied, modified, or distributed -// except according to those terms. - -#![allow(non_camel_case_types)] -#![allow(dead_code)] -#![feature(catch_expr)] - -struct catch; //~ ERROR cannot use `catch` as the name of a type diff --git a/src/test/compile-fail/catch-enum-variant.rs b/src/test/compile-fail/catch-enum-variant.rs deleted file mode 100644 index 7aa162750d189..0000000000000 --- a/src/test/compile-fail/catch-enum-variant.rs +++ /dev/null @@ -1,17 +0,0 @@ -// Copyright 2017 The Rust Project Developers. See the COPYRIGHT -// file at the top-level directory of this distribution and at -// http://rust-lang.org/COPYRIGHT. -// -// Licensed under the Apache License, Version 2.0 or the MIT license -// , at your -// option. This file may not be copied, modified, or distributed -// except according to those terms. - -#![allow(non_camel_case_types)] -#![allow(dead_code)] -#![feature(catch_expr)] - -enum Enum { - catch {} //~ ERROR cannot use `catch` as the name of a type -} diff --git a/src/test/compile-fail/catch-struct-name.rs b/src/test/compile-fail/catch-struct-name.rs deleted file mode 100644 index 63661ccf607a0..0000000000000 --- a/src/test/compile-fail/catch-struct-name.rs +++ /dev/null @@ -1,15 +0,0 @@ -// Copyright 2017 The Rust Project Developers. See the COPYRIGHT -// file at the top-level directory of this distribution and at -// http://rust-lang.org/COPYRIGHT. -// -// Licensed under the Apache License, Version 2.0 or the MIT license -// , at your -// option. This file may not be copied, modified, or distributed -// except according to those terms. - -#![allow(non_camel_case_types)] -#![allow(dead_code)] -#![feature(catch_expr)] - -struct catch {} //~ ERROR cannot use `catch` as the name of a type \ No newline at end of file diff --git a/src/test/compile-fail/catch-tuple-struct-name.rs b/src/test/compile-fail/catch-tuple-struct-name.rs deleted file mode 100644 index 1a8866d85430d..0000000000000 --- a/src/test/compile-fail/catch-tuple-struct-name.rs +++ /dev/null @@ -1,15 +0,0 @@ -// Copyright 2017 The Rust Project Developers. See the COPYRIGHT -// file at the top-level directory of this distribution and at -// http://rust-lang.org/COPYRIGHT. -// -// Licensed under the Apache License, Version 2.0 or the MIT license -// , at your -// option. This file may not be copied, modified, or distributed -// except according to those terms. - -#![allow(non_camel_case_types)] -#![allow(dead_code)] -#![feature(catch_expr)] - -struct catch(); //~ ERROR cannot use `catch` as the name of a type diff --git a/src/test/compile-fail/feature-gate-catch_expr.rs b/src/test/compile-fail/feature-gate-catch_expr.rs index 8a1a5ceae89e0..5568a5cf0aac2 100644 --- a/src/test/compile-fail/feature-gate-catch_expr.rs +++ b/src/test/compile-fail/feature-gate-catch_expr.rs @@ -9,7 +9,7 @@ // except according to those terms. pub fn main() { - let catch_result = catch { //~ ERROR `catch` expression is experimental + let catch_result = do catch { //~ ERROR `catch` expression is experimental let x = 5; x }; diff --git a/src/test/run-pass/catch-expr.rs b/src/test/run-pass/catch-expr.rs index c70b6100efe4f..a9b28a534a348 100644 --- a/src/test/run-pass/catch-expr.rs +++ b/src/test/run-pass/catch-expr.rs @@ -10,8 +10,10 @@ #![feature(catch_expr)] +struct catch {} + pub fn main() { - let catch_result = catch { + let catch_result = do catch { let x = 5; x }; From b55f1e5342a948b546ad61b437ede6096ffee613 Mon Sep 17 00:00:00 2001 From: est31 Date: Sat, 4 Mar 2017 14:31:34 +0100 Subject: [PATCH 05/24] Fix description of closure coercion feature --- src/libsyntax/feature_gate.rs | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/src/libsyntax/feature_gate.rs b/src/libsyntax/feature_gate.rs index 6eb7d449f2692..e7bf16eae9ee6 100644 --- a/src/libsyntax/feature_gate.rs +++ b/src/libsyntax/feature_gate.rs @@ -330,8 +330,7 @@ declare_features! ( // `extern "msp430-interrupt" fn()` (active, abi_msp430_interrupt, "1.16.0", Some(38487)), - // Used to identify crates that contain sanitizer runtimes - // rustc internal + // Coerces non capturing closures to function pointers (active, closure_to_fn_coercion, "1.17.0", Some(39817)), // Used to identify crates that contain sanitizer runtimes From 3a97fc9c2bec65fa49b162d140bc3944eaec1ae9 Mon Sep 17 00:00:00 2001 From: Jake Goulding Date: Sat, 4 Mar 2017 10:07:55 -0500 Subject: [PATCH 06/24] Fix botched member variable rename --- src/tools/build-manifest/src/main.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/tools/build-manifest/src/main.rs b/src/tools/build-manifest/src/main.rs index ceefcc9e0ec46..cbafa9e0bd272 100644 --- a/src/tools/build-manifest/src/main.rs +++ b/src/tools/build-manifest/src/main.rs @@ -218,7 +218,7 @@ impl Builder { self.package("rust-docs", &mut manifest.pkg, TARGETS); self.package("rust-src", &mut manifest.pkg, &["*"]); - if self.channel == "nightly" { + if self.rust_release == "nightly" { self.package("rust-analysis", &mut manifest.pkg, TARGETS); } @@ -271,7 +271,7 @@ impl Builder { target: target.to_string(), }); } - if self.channel == "nightly" { + if self.rust_release == "nightly" { extensions.push(Component { pkg: "rust-analysis".to_string(), target: target.to_string(), From cac4bf3d574cbc0c5ec6550ff6b17d904f8e2577 Mon Sep 17 00:00:00 2001 From: Jake Goulding Date: Thu, 2 Mar 2017 23:39:15 -0500 Subject: [PATCH 07/24] Restore creating the channel-rust-$channel-date.txt files --- src/tools/build-manifest/src/main.rs | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/src/tools/build-manifest/src/main.rs b/src/tools/build-manifest/src/main.rs index cbafa9e0bd272..b9c8a84844465 100644 --- a/src/tools/build-manifest/src/main.rs +++ b/src/tools/build-manifest/src/main.rs @@ -183,15 +183,19 @@ impl Builder { let mut manifest = BTreeMap::new(); manifest.insert("manifest-version".to_string(), toml::Value::String(manifest_version)); - manifest.insert("date".to_string(), toml::Value::String(date)); + manifest.insert("date".to_string(), toml::Value::String(date.clone())); manifest.insert("pkg".to_string(), toml::encode(&pkg)); let manifest = toml::Value::Table(manifest).to_string(); let filename = format!("channel-rust-{}.toml", self.rust_release); self.write_manifest(&manifest, &filename); + let filename = format!("channel-rust-{}-date.txt", self.rust_release); + self.write_date_stamp(&date, &filename); + if self.rust_release != "beta" && self.rust_release != "nightly" { self.write_manifest(&manifest, "channel-rust-stable.toml"); + self.write_date_stamp(&date, "channel-rust-stable-date.txt"); } } @@ -411,4 +415,11 @@ impl Builder { self.hash(&dst); self.sign(&dst); } + + fn write_date_stamp(&self, date: &str, name: &str) { + let dst = self.output.join(name); + t!(t!(File::create(&dst)).write_all(date.as_bytes())); + self.hash(&dst); + self.sign(&dst); + } } From 5a644f417e870533a1f73b4cd14a4be816b36c4f Mon Sep 17 00:00:00 2001 From: steveklabnik Date: Thu, 2 Mar 2017 20:14:40 -0500 Subject: [PATCH 08/24] remove nomicon --- src/doc/nomicon/src/README.md | 38 --- src/doc/nomicon/src/SUMMARY.md | 55 ---- src/doc/nomicon/src/arc-and-mutex.md | 7 - src/doc/nomicon/src/atomics.md | 255 ---------------- src/doc/nomicon/src/borrow-splitting.md | 291 ------------------ src/doc/nomicon/src/casts.md | 71 ----- src/doc/nomicon/src/chapter_1.md | 1 - src/doc/nomicon/src/checked-uninit.md | 117 ------- src/doc/nomicon/src/coercions.md | 72 ----- src/doc/nomicon/src/concurrency.md | 13 - src/doc/nomicon/src/constructors.md | 59 ---- src/doc/nomicon/src/conversions.md | 34 --- src/doc/nomicon/src/data.md | 5 - src/doc/nomicon/src/destructors.md | 190 ------------ src/doc/nomicon/src/dot-operator.md | 6 - src/doc/nomicon/src/drop-flags.md | 83 ----- src/doc/nomicon/src/dropck.md | 295 ------------------ src/doc/nomicon/src/exception-safety.md | 217 ------------- src/doc/nomicon/src/exotic-sizes.md | 137 --------- src/doc/nomicon/src/hrtb.md | 73 ----- src/doc/nomicon/src/leaking.md | 251 --------------- src/doc/nomicon/src/lifetime-elision.md | 64 ---- src/doc/nomicon/src/lifetime-mismatch.md | 81 ----- src/doc/nomicon/src/lifetimes.md | 215 ------------- src/doc/nomicon/src/meet-safe-and-unsafe.md | 98 ------ src/doc/nomicon/src/obrm.md | 14 - src/doc/nomicon/src/other-reprs.md | 79 ----- src/doc/nomicon/src/ownership.md | 66 ---- src/doc/nomicon/src/phantom-data.md | 104 ------- src/doc/nomicon/src/poisoning.md | 35 --- src/doc/nomicon/src/races.md | 86 ------ src/doc/nomicon/src/references.md | 177 ----------- src/doc/nomicon/src/repr-rust.md | 154 ---------- src/doc/nomicon/src/safe-unsafe-meaning.md | 123 -------- src/doc/nomicon/src/send-and-sync.md | 80 ----- src/doc/nomicon/src/subtyping.md | 213 ------------- src/doc/nomicon/src/transmutes.md | 35 --- src/doc/nomicon/src/unbounded-lifetimes.md | 36 --- src/doc/nomicon/src/unchecked-uninit.md | 85 ------ src/doc/nomicon/src/uninitialized.md | 10 - src/doc/nomicon/src/unwinding.md | 49 --- src/doc/nomicon/src/vec-alloc.md | 223 -------------- src/doc/nomicon/src/vec-dealloc.md | 29 -- src/doc/nomicon/src/vec-deref.md | 42 --- src/doc/nomicon/src/vec-drain.md | 152 --------- src/doc/nomicon/src/vec-final.md | 321 -------------------- src/doc/nomicon/src/vec-insert-remove.md | 51 ---- src/doc/nomicon/src/vec-into-iter.md | 147 --------- src/doc/nomicon/src/vec-layout.md | 100 ------ src/doc/nomicon/src/vec-push-pop.md | 55 ---- src/doc/nomicon/src/vec-raw.md | 136 --------- src/doc/nomicon/src/vec-zsts.md | 176 ----------- src/doc/nomicon/src/vec.md | 20 -- src/doc/nomicon/src/working-with-unsafe.md | 119 -------- 54 files changed, 5645 deletions(-) delete mode 100644 src/doc/nomicon/src/README.md delete mode 100644 src/doc/nomicon/src/SUMMARY.md delete mode 100644 src/doc/nomicon/src/arc-and-mutex.md delete mode 100644 src/doc/nomicon/src/atomics.md delete mode 100644 src/doc/nomicon/src/borrow-splitting.md delete mode 100644 src/doc/nomicon/src/casts.md delete mode 100644 src/doc/nomicon/src/chapter_1.md delete mode 100644 src/doc/nomicon/src/checked-uninit.md delete mode 100644 src/doc/nomicon/src/coercions.md delete mode 100644 src/doc/nomicon/src/concurrency.md delete mode 100644 src/doc/nomicon/src/constructors.md delete mode 100644 src/doc/nomicon/src/conversions.md delete mode 100644 src/doc/nomicon/src/data.md delete mode 100644 src/doc/nomicon/src/destructors.md delete mode 100644 src/doc/nomicon/src/dot-operator.md delete mode 100644 src/doc/nomicon/src/drop-flags.md delete mode 100644 src/doc/nomicon/src/dropck.md delete mode 100644 src/doc/nomicon/src/exception-safety.md delete mode 100644 src/doc/nomicon/src/exotic-sizes.md delete mode 100644 src/doc/nomicon/src/hrtb.md delete mode 100644 src/doc/nomicon/src/leaking.md delete mode 100644 src/doc/nomicon/src/lifetime-elision.md delete mode 100644 src/doc/nomicon/src/lifetime-mismatch.md delete mode 100644 src/doc/nomicon/src/lifetimes.md delete mode 100644 src/doc/nomicon/src/meet-safe-and-unsafe.md delete mode 100644 src/doc/nomicon/src/obrm.md delete mode 100644 src/doc/nomicon/src/other-reprs.md delete mode 100644 src/doc/nomicon/src/ownership.md delete mode 100644 src/doc/nomicon/src/phantom-data.md delete mode 100644 src/doc/nomicon/src/poisoning.md delete mode 100644 src/doc/nomicon/src/races.md delete mode 100644 src/doc/nomicon/src/references.md delete mode 100644 src/doc/nomicon/src/repr-rust.md delete mode 100644 src/doc/nomicon/src/safe-unsafe-meaning.md delete mode 100644 src/doc/nomicon/src/send-and-sync.md delete mode 100644 src/doc/nomicon/src/subtyping.md delete mode 100644 src/doc/nomicon/src/transmutes.md delete mode 100644 src/doc/nomicon/src/unbounded-lifetimes.md delete mode 100644 src/doc/nomicon/src/unchecked-uninit.md delete mode 100644 src/doc/nomicon/src/uninitialized.md delete mode 100644 src/doc/nomicon/src/unwinding.md delete mode 100644 src/doc/nomicon/src/vec-alloc.md delete mode 100644 src/doc/nomicon/src/vec-dealloc.md delete mode 100644 src/doc/nomicon/src/vec-deref.md delete mode 100644 src/doc/nomicon/src/vec-drain.md delete mode 100644 src/doc/nomicon/src/vec-final.md delete mode 100644 src/doc/nomicon/src/vec-insert-remove.md delete mode 100644 src/doc/nomicon/src/vec-into-iter.md delete mode 100644 src/doc/nomicon/src/vec-layout.md delete mode 100644 src/doc/nomicon/src/vec-push-pop.md delete mode 100644 src/doc/nomicon/src/vec-raw.md delete mode 100644 src/doc/nomicon/src/vec-zsts.md delete mode 100644 src/doc/nomicon/src/vec.md delete mode 100644 src/doc/nomicon/src/working-with-unsafe.md diff --git a/src/doc/nomicon/src/README.md b/src/doc/nomicon/src/README.md deleted file mode 100644 index d577d7b5cc91b..0000000000000 --- a/src/doc/nomicon/src/README.md +++ /dev/null @@ -1,38 +0,0 @@ -# The Rustonomicon - -#### The Dark Arts of Advanced and Unsafe Rust Programming - -# NOTE: This is a draft document, and may contain serious errors - -> Instead of the programs I had hoped for, there came only a shuddering blackness -and ineffable loneliness; and I saw at last a fearful truth which no one had -ever dared to breathe before — the unwhisperable secret of secrets — The fact -that this language of stone and stridor is not a sentient perpetuation of Rust -as London is of Old London and Paris of Old Paris, but that it is in fact -quite unsafe, its sprawling body imperfectly embalmed and infested with queer -animate things which have nothing to do with it as it was in compilation. - -This book digs into all the awful details that are necessary to understand in -order to write correct Unsafe Rust programs. Due to the nature of this problem, -it may lead to unleashing untold horrors that shatter your psyche into a billion -infinitesimal fragments of despair. - -Should you wish a long and happy career of writing Rust programs, you should -turn back now and forget you ever saw this book. It is not necessary. However -if you intend to write unsafe code -- or just want to dig into the guts of the -language -- this book contains invaluable information. - -Unlike [The Book][trpl] we will be assuming considerable prior knowledge. In -particular, you should be comfortable with basic systems programming and Rust. -If you don't feel comfortable with these topics, you should consider [reading -The Book][trpl] first. Though we will not be assuming that you have, and will -take care to occasionally give a refresher on the basics where appropriate. You -can skip straight to this book if you want; just know that we won't be -explaining everything from the ground up. - -To be clear, this book goes into deep detail. We're going to dig into -exception-safety, pointer aliasing, memory models, and even some type-theory. -We will also be spending a lot of time talking about the different kinds -of safety and guarantees. - -[trpl]: ../book/index.html diff --git a/src/doc/nomicon/src/SUMMARY.md b/src/doc/nomicon/src/SUMMARY.md deleted file mode 100644 index e33dcbbb4188e..0000000000000 --- a/src/doc/nomicon/src/SUMMARY.md +++ /dev/null @@ -1,55 +0,0 @@ -# Summary - -[Introduction](README.md) - -* [Meet Safe and Unsafe](meet-safe-and-unsafe.md) - * [How Safe and Unsafe Interact](safe-unsafe-meaning.md) - * [Working with Unsafe](working-with-unsafe.md) -* [Data Layout](data.md) - * [repr(Rust)](repr-rust.md) - * [Exotically Sized Types](exotic-sizes.md) - * [Other reprs](other-reprs.md) -* [Ownership](ownership.md) - * [References](references.md) - * [Lifetimes](lifetimes.md) - * [Limits of Lifetimes](lifetime-mismatch.md) - * [Lifetime Elision](lifetime-elision.md) - * [Unbounded Lifetimes](unbounded-lifetimes.md) - * [Higher-Rank Trait Bounds](hrtb.md) - * [Subtyping and Variance](subtyping.md) - * [Drop Check](dropck.md) - * [PhantomData](phantom-data.md) - * [Splitting Borrows](borrow-splitting.md) -* [Type Conversions](conversions.md) - * [Coercions](coercions.md) - * [The Dot Operator](dot-operator.md) - * [Casts](casts.md) - * [Transmutes](transmutes.md) -* [Uninitialized Memory](uninitialized.md) - * [Checked](checked-uninit.md) - * [Drop Flags](drop-flags.md) - * [Unchecked](unchecked-uninit.md) -* [Ownership Based Resource Management](obrm.md) - * [Constructors](constructors.md) - * [Destructors](destructors.md) - * [Leaking](leaking.md) -* [Unwinding](unwinding.md) - * [Exception Safety](exception-safety.md) - * [Poisoning](poisoning.md) -* [Concurrency](concurrency.md) - * [Races](races.md) - * [Send and Sync](send-and-sync.md) - * [Atomics](atomics.md) -* [Implementing Vec](vec.md) - * [Layout](vec-layout.md) - * [Allocating](vec-alloc.md) - * [Push and Pop](vec-push-pop.md) - * [Deallocating](vec-dealloc.md) - * [Deref](vec-deref.md) - * [Insert and Remove](vec-insert-remove.md) - * [IntoIter](vec-into-iter.md) - * [RawVec](vec-raw.md) - * [Drain](vec-drain.md) - * [Handling Zero-Sized Types](vec-zsts.md) - * [Final Code](vec-final.md) -* [Implementing Arc and Mutex](arc-and-mutex.md) diff --git a/src/doc/nomicon/src/arc-and-mutex.md b/src/doc/nomicon/src/arc-and-mutex.md deleted file mode 100644 index fedc7b8bd6a18..0000000000000 --- a/src/doc/nomicon/src/arc-and-mutex.md +++ /dev/null @@ -1,7 +0,0 @@ -# Implementing Arc and Mutex - -Knowing the theory is all fine and good, but the *best* way to understand -something is to use it. To better understand atomics and interior mutability, -we'll be implementing versions of the standard library's Arc and Mutex types. - -TODO: ALL OF THIS OMG diff --git a/src/doc/nomicon/src/atomics.md b/src/doc/nomicon/src/atomics.md deleted file mode 100644 index e9ed21a93e00a..0000000000000 --- a/src/doc/nomicon/src/atomics.md +++ /dev/null @@ -1,255 +0,0 @@ -# Atomics - -Rust pretty blatantly just inherits C11's memory model for atomics. This is not -due to this model being particularly excellent or easy to understand. Indeed, -this model is quite complex and known to have [several flaws][C11-busted]. -Rather, it is a pragmatic concession to the fact that *everyone* is pretty bad -at modeling atomics. At very least, we can benefit from existing tooling and -research around C. - -Trying to fully explain the model in this book is fairly hopeless. It's defined -in terms of madness-inducing causality graphs that require a full book to -properly understand in a practical way. If you want all the nitty-gritty -details, you should check out [C's specification (Section 7.17)][C11-model]. -Still, we'll try to cover the basics and some of the problems Rust developers -face. - -The C11 memory model is fundamentally about trying to bridge the gap between the -semantics we want, the optimizations compilers want, and the inconsistent chaos -our hardware wants. *We* would like to just write programs and have them do -exactly what we said but, you know, fast. Wouldn't that be great? - - - - -# Compiler Reordering - -Compilers fundamentally want to be able to do all sorts of complicated -transformations to reduce data dependencies and eliminate dead code. In -particular, they may radically change the actual order of events, or make events -never occur! If we write something like - -```rust,ignore -x = 1; -y = 3; -x = 2; -``` - -The compiler may conclude that it would be best if your program did - -```rust,ignore -x = 2; -y = 3; -``` - -This has inverted the order of events and completely eliminated one event. -From a single-threaded perspective this is completely unobservable: after all -the statements have executed we are in exactly the same state. But if our -program is multi-threaded, we may have been relying on `x` to actually be -assigned to 1 before `y` was assigned. We would like the compiler to be -able to make these kinds of optimizations, because they can seriously improve -performance. On the other hand, we'd also like to be able to depend on our -program *doing the thing we said*. - - - - -# Hardware Reordering - -On the other hand, even if the compiler totally understood what we wanted and -respected our wishes, our hardware might instead get us in trouble. Trouble -comes from CPUs in the form of memory hierarchies. There is indeed a global -shared memory space somewhere in your hardware, but from the perspective of each -CPU core it is *so very far away* and *so very slow*. Each CPU would rather work -with its local cache of the data and only go through all the anguish of -talking to shared memory only when it doesn't actually have that memory in -cache. - -After all, that's the whole point of the cache, right? If every read from the -cache had to run back to shared memory to double check that it hadn't changed, -what would the point be? The end result is that the hardware doesn't guarantee -that events that occur in the same order on *one* thread, occur in the same -order on *another* thread. To guarantee this, we must issue special instructions -to the CPU telling it to be a bit less smart. - -For instance, say we convince the compiler to emit this logic: - -```text -initial state: x = 0, y = 1 - -THREAD 1 THREAD2 -y = 3; if x == 1 { -x = 1; y *= 2; - } -``` - -Ideally this program has 2 possible final states: - -* `y = 3`: (thread 2 did the check before thread 1 completed) -* `y = 6`: (thread 2 did the check after thread 1 completed) - -However there's a third potential state that the hardware enables: - -* `y = 2`: (thread 2 saw `x = 1`, but not `y = 3`, and then overwrote `y = 3`) - -It's worth noting that different kinds of CPU provide different guarantees. It -is common to separate hardware into two categories: strongly-ordered and weakly- -ordered. Most notably x86/64 provides strong ordering guarantees, while ARM -provides weak ordering guarantees. This has two consequences for concurrent -programming: - -* Asking for stronger guarantees on strongly-ordered hardware may be cheap or - even free because they already provide strong guarantees unconditionally. - Weaker guarantees may only yield performance wins on weakly-ordered hardware. - -* Asking for guarantees that are too weak on strongly-ordered hardware is - more likely to *happen* to work, even though your program is strictly - incorrect. If possible, concurrent algorithms should be tested on - weakly-ordered hardware. - - - - - -# Data Accesses - -The C11 memory model attempts to bridge the gap by allowing us to talk about the -*causality* of our program. Generally, this is by establishing a *happens -before* relationship between parts of the program and the threads that are -running them. This gives the hardware and compiler room to optimize the program -more aggressively where a strict happens-before relationship isn't established, -but forces them to be more careful where one is established. The way we -communicate these relationships are through *data accesses* and *atomic -accesses*. - -Data accesses are the bread-and-butter of the programming world. They are -fundamentally unsynchronized and compilers are free to aggressively optimize -them. In particular, data accesses are free to be reordered by the compiler on -the assumption that the program is single-threaded. The hardware is also free to -propagate the changes made in data accesses to other threads as lazily and -inconsistently as it wants. Most critically, data accesses are how data races -happen. Data accesses are very friendly to the hardware and compiler, but as -we've seen they offer *awful* semantics to try to write synchronized code with. -Actually, that's too weak. - -**It is literally impossible to write correct synchronized code using only data -accesses.** - -Atomic accesses are how we tell the hardware and compiler that our program is -multi-threaded. Each atomic access can be marked with an *ordering* that -specifies what kind of relationship it establishes with other accesses. In -practice, this boils down to telling the compiler and hardware certain things -they *can't* do. For the compiler, this largely revolves around re-ordering of -instructions. For the hardware, this largely revolves around how writes are -propagated to other threads. The set of orderings Rust exposes are: - -* Sequentially Consistent (SeqCst) -* Release -* Acquire -* Relaxed - -(Note: We explicitly do not expose the C11 *consume* ordering) - -TODO: negative reasoning vs positive reasoning? TODO: "can't forget to -synchronize" - - - -# Sequentially Consistent - -Sequentially Consistent is the most powerful of all, implying the restrictions -of all other orderings. Intuitively, a sequentially consistent operation -cannot be reordered: all accesses on one thread that happen before and after a -SeqCst access stay before and after it. A data-race-free program that uses -only sequentially consistent atomics and data accesses has the very nice -property that there is a single global execution of the program's instructions -that all threads agree on. This execution is also particularly nice to reason -about: it's just an interleaving of each thread's individual executions. This -does not hold if you start using the weaker atomic orderings. - -The relative developer-friendliness of sequential consistency doesn't come for -free. Even on strongly-ordered platforms sequential consistency involves -emitting memory fences. - -In practice, sequential consistency is rarely necessary for program correctness. -However sequential consistency is definitely the right choice if you're not -confident about the other memory orders. Having your program run a bit slower -than it needs to is certainly better than it running incorrectly! It's also -mechanically trivial to downgrade atomic operations to have a weaker -consistency later on. Just change `SeqCst` to `Relaxed` and you're done! Of -course, proving that this transformation is *correct* is a whole other matter. - - - - -# Acquire-Release - -Acquire and Release are largely intended to be paired. Their names hint at their -use case: they're perfectly suited for acquiring and releasing locks, and -ensuring that critical sections don't overlap. - -Intuitively, an acquire access ensures that every access after it stays after -it. However operations that occur before an acquire are free to be reordered to -occur after it. Similarly, a release access ensures that every access before it -stays before it. However operations that occur after a release are free to be -reordered to occur before it. - -When thread A releases a location in memory and then thread B subsequently -acquires *the same* location in memory, causality is established. Every write -that happened before A's release will be observed by B after its release. -However no causality is established with any other threads. Similarly, no -causality is established if A and B access *different* locations in memory. - -Basic use of release-acquire is therefore simple: you acquire a location of -memory to begin the critical section, and then release that location to end it. -For instance, a simple spinlock might look like: - -```rust -use std::sync::Arc; -use std::sync::atomic::{AtomicBool, Ordering}; -use std::thread; - -fn main() { - let lock = Arc::new(AtomicBool::new(false)); // value answers "am I locked?" - - // ... distribute lock to threads somehow ... - - // Try to acquire the lock by setting it to true - while lock.compare_and_swap(false, true, Ordering::Acquire) { } - // broke out of the loop, so we successfully acquired the lock! - - // ... scary data accesses ... - - // ok we're done, release the lock - lock.store(false, Ordering::Release); -} -``` - -On strongly-ordered platforms most accesses have release or acquire semantics, -making release and acquire often totally free. This is not the case on -weakly-ordered platforms. - - - - -# Relaxed - -Relaxed accesses are the absolute weakest. They can be freely re-ordered and -provide no happens-before relationship. Still, relaxed operations are still -atomic. That is, they don't count as data accesses and any read-modify-write -operations done to them occur atomically. Relaxed operations are appropriate for -things that you definitely want to happen, but don't particularly otherwise care -about. For instance, incrementing a counter can be safely done by multiple -threads using a relaxed `fetch_add` if you're not using the counter to -synchronize any other accesses. - -There's rarely a benefit in making an operation relaxed on strongly-ordered -platforms, since they usually provide release-acquire semantics anyway. However -relaxed operations can be cheaper on weakly-ordered platforms. - - - - - -[C11-busted]: http://plv.mpi-sws.org/c11comp/popl15.pdf -[C11-model]: http://www.open-std.org/jtc1/sc22/wg14/www/standards.html#9899 diff --git a/src/doc/nomicon/src/borrow-splitting.md b/src/doc/nomicon/src/borrow-splitting.md deleted file mode 100644 index 28ddb507ae27d..0000000000000 --- a/src/doc/nomicon/src/borrow-splitting.md +++ /dev/null @@ -1,291 +0,0 @@ -# Splitting Borrows - -The mutual exclusion property of mutable references can be very limiting when -working with a composite structure. The borrow checker understands some basic -stuff, but will fall over pretty easily. It does understand structs -sufficiently to know that it's possible to borrow disjoint fields of a struct -simultaneously. So this works today: - -```rust -struct Foo { - a: i32, - b: i32, - c: i32, -} - -let mut x = Foo {a: 0, b: 0, c: 0}; -let a = &mut x.a; -let b = &mut x.b; -let c = &x.c; -*b += 1; -let c2 = &x.c; -*a += 10; -println!("{} {} {} {}", a, b, c, c2); -``` - -However borrowck doesn't understand arrays or slices in any way, so this doesn't -work: - -```rust,ignore -let mut x = [1, 2, 3]; -let a = &mut x[0]; -let b = &mut x[1]; -println!("{} {}", a, b); -``` - -```text -:4:14: 4:18 error: cannot borrow `x[..]` as mutable more than once at a time -:4 let b = &mut x[1]; - ^~~~ -:3:14: 3:18 note: previous borrow of `x[..]` occurs here; the mutable borrow prevents subsequent moves, borrows, or modification of `x[..]` until the borrow ends -:3 let a = &mut x[0]; - ^~~~ -:6:2: 6:2 note: previous borrow ends here -:1 fn main() { -:2 let mut x = [1, 2, 3]; -:3 let a = &mut x[0]; -:4 let b = &mut x[1]; -:5 println!("{} {}", a, b); -:6 } - ^ -error: aborting due to 2 previous errors -``` - -While it was plausible that borrowck could understand this simple case, it's -pretty clearly hopeless for borrowck to understand disjointness in general -container types like a tree, especially if distinct keys actually *do* map -to the same value. - -In order to "teach" borrowck that what we're doing is ok, we need to drop down -to unsafe code. For instance, mutable slices expose a `split_at_mut` function -that consumes the slice and returns two mutable slices. One for everything to -the left of the index, and one for everything to the right. Intuitively we know -this is safe because the slices don't overlap, and therefore alias. However -the implementation requires some unsafety: - -```rust,ignore -fn split_at_mut(&mut self, mid: usize) -> (&mut [T], &mut [T]) { - let len = self.len(); - let ptr = self.as_mut_ptr(); - assert!(mid <= len); - unsafe { - (from_raw_parts_mut(ptr, mid), - from_raw_parts_mut(ptr.offset(mid as isize), len - mid)) - } -} -``` - -This is actually a bit subtle. So as to avoid ever making two `&mut`'s to the -same value, we explicitly construct brand-new slices through raw pointers. - -However more subtle is how iterators that yield mutable references work. -The iterator trait is defined as follows: - -```rust -trait Iterator { - type Item; - - fn next(&mut self) -> Option; -} -``` - -Given this definition, Self::Item has *no* connection to `self`. This means that -we can call `next` several times in a row, and hold onto all the results -*concurrently*. This is perfectly fine for by-value iterators, which have -exactly these semantics. It's also actually fine for shared references, as they -admit arbitrarily many references to the same thing (although the iterator needs -to be a separate object from the thing being shared). - -But mutable references make this a mess. At first glance, they might seem -completely incompatible with this API, as it would produce multiple mutable -references to the same object! - -However it actually *does* work, exactly because iterators are one-shot objects. -Everything an IterMut yields will be yielded at most once, so we don't -actually ever yield multiple mutable references to the same piece of data. - -Perhaps surprisingly, mutable iterators don't require unsafe code to be -implemented for many types! - -For instance here's a singly linked list: - -```rust -# fn main() {} -type Link = Option>>; - -struct Node { - elem: T, - next: Link, -} - -pub struct LinkedList { - head: Link, -} - -pub struct IterMut<'a, T: 'a>(Option<&'a mut Node>); - -impl LinkedList { - fn iter_mut(&mut self) -> IterMut { - IterMut(self.head.as_mut().map(|node| &mut **node)) - } -} - -impl<'a, T> Iterator for IterMut<'a, T> { - type Item = &'a mut T; - - fn next(&mut self) -> Option { - self.0.take().map(|node| { - self.0 = node.next.as_mut().map(|node| &mut **node); - &mut node.elem - }) - } -} -``` - -Here's a mutable slice: - -```rust -# fn main() {} -use std::mem; - -pub struct IterMut<'a, T: 'a>(&'a mut[T]); - -impl<'a, T> Iterator for IterMut<'a, T> { - type Item = &'a mut T; - - fn next(&mut self) -> Option { - let slice = mem::replace(&mut self.0, &mut []); - if slice.is_empty() { return None; } - - let (l, r) = slice.split_at_mut(1); - self.0 = r; - l.get_mut(0) - } -} - -impl<'a, T> DoubleEndedIterator for IterMut<'a, T> { - fn next_back(&mut self) -> Option { - let slice = mem::replace(&mut self.0, &mut []); - if slice.is_empty() { return None; } - - let new_len = slice.len() - 1; - let (l, r) = slice.split_at_mut(new_len); - self.0 = l; - r.get_mut(0) - } -} -``` - -And here's a binary tree: - -```rust -# fn main() {} -use std::collections::VecDeque; - -type Link = Option>>; - -struct Node { - elem: T, - left: Link, - right: Link, -} - -pub struct Tree { - root: Link, -} - -struct NodeIterMut<'a, T: 'a> { - elem: Option<&'a mut T>, - left: Option<&'a mut Node>, - right: Option<&'a mut Node>, -} - -enum State<'a, T: 'a> { - Elem(&'a mut T), - Node(&'a mut Node), -} - -pub struct IterMut<'a, T: 'a>(VecDeque>); - -impl Tree { - pub fn iter_mut(&mut self) -> IterMut { - let mut deque = VecDeque::new(); - self.root.as_mut().map(|root| deque.push_front(root.iter_mut())); - IterMut(deque) - } -} - -impl Node { - pub fn iter_mut(&mut self) -> NodeIterMut { - NodeIterMut { - elem: Some(&mut self.elem), - left: self.left.as_mut().map(|node| &mut **node), - right: self.right.as_mut().map(|node| &mut **node), - } - } -} - - -impl<'a, T> Iterator for NodeIterMut<'a, T> { - type Item = State<'a, T>; - - fn next(&mut self) -> Option { - match self.left.take() { - Some(node) => Some(State::Node(node)), - None => match self.elem.take() { - Some(elem) => Some(State::Elem(elem)), - None => match self.right.take() { - Some(node) => Some(State::Node(node)), - None => None, - } - } - } - } -} - -impl<'a, T> DoubleEndedIterator for NodeIterMut<'a, T> { - fn next_back(&mut self) -> Option { - match self.right.take() { - Some(node) => Some(State::Node(node)), - None => match self.elem.take() { - Some(elem) => Some(State::Elem(elem)), - None => match self.left.take() { - Some(node) => Some(State::Node(node)), - None => None, - } - } - } - } -} - -impl<'a, T> Iterator for IterMut<'a, T> { - type Item = &'a mut T; - fn next(&mut self) -> Option { - loop { - match self.0.front_mut().and_then(|node_it| node_it.next()) { - Some(State::Elem(elem)) => return Some(elem), - Some(State::Node(node)) => self.0.push_front(node.iter_mut()), - None => if let None = self.0.pop_front() { return None }, - } - } - } -} - -impl<'a, T> DoubleEndedIterator for IterMut<'a, T> { - fn next_back(&mut self) -> Option { - loop { - match self.0.back_mut().and_then(|node_it| node_it.next_back()) { - Some(State::Elem(elem)) => return Some(elem), - Some(State::Node(node)) => self.0.push_back(node.iter_mut()), - None => if let None = self.0.pop_back() { return None }, - } - } - } -} -``` - -All of these are completely safe and work on stable Rust! This ultimately -falls out of the simple struct case we saw before: Rust understands that you -can safely split a mutable reference into subfields. We can then encode -permanently consuming a reference via Options (or in the case of slices, -replacing with an empty slice). diff --git a/src/doc/nomicon/src/casts.md b/src/doc/nomicon/src/casts.md deleted file mode 100644 index 31b7858724540..0000000000000 --- a/src/doc/nomicon/src/casts.md +++ /dev/null @@ -1,71 +0,0 @@ -# Casts - -Casts are a superset of coercions: every coercion can be explicitly -invoked via a cast. However some conversions require a cast. -While coercions are pervasive and largely harmless, these "true casts" -are rare and potentially dangerous. As such, casts must be explicitly invoked -using the `as` keyword: `expr as Type`. - -True casts generally revolve around raw pointers and the primitive numeric -types. Even though they're dangerous, these casts are infallible at runtime. -If a cast triggers some subtle corner case no indication will be given that -this occurred. The cast will simply succeed. That said, casts must be valid -at the type level, or else they will be prevented statically. For instance, -`7u8 as bool` will not compile. - -That said, casts aren't `unsafe` because they generally can't violate memory -safety *on their own*. For instance, converting an integer to a raw pointer can -very easily lead to terrible things. However the act of creating the pointer -itself is safe, because actually using a raw pointer is already marked as -`unsafe`. - -Here's an exhaustive list of all the true casts. For brevity, we will use `*` -to denote either a `*const` or `*mut`, and `integer` to denote any integral -primitive: - - * `*T as *U` where `T, U: Sized` - * `*T as *U` TODO: explain unsized situation - * `*T as integer` - * `integer as *T` - * `number as number` - * `C-like-enum as integer` - * `bool as integer` - * `char as integer` - * `u8 as char` - * `&[T; n] as *const T` - * `fn as *T` where `T: Sized` - * `fn as integer` - -Note that lengths are not adjusted when casting raw slices - -`*const [u16] as *const [u8]` creates a slice that only includes -half of the original memory. - -Casting is not transitive, that is, even if `e as U1 as U2` is a valid -expression, `e as U2` is not necessarily so. - -For numeric casts, there are quite a few cases to consider: - -* casting between two integers of the same size (e.g. i32 -> u32) is a no-op -* casting from a larger integer to a smaller integer (e.g. u32 -> u8) will - truncate -* casting from a smaller integer to a larger integer (e.g. u8 -> u32) will - * zero-extend if the source is unsigned - * sign-extend if the source is signed -* casting from a float to an integer will round the float towards zero - * **[NOTE: currently this will cause Undefined Behavior if the rounded - value cannot be represented by the target integer type][float-int]**. - This includes Inf and NaN. This is a bug and will be fixed. -* casting from an integer to float will produce the floating point - representation of the integer, rounded if necessary (rounding strategy - unspecified) -* casting from an f32 to an f64 is perfect and lossless -* casting from an f64 to an f32 will produce the closest possible value - (rounding strategy unspecified) - * **[NOTE: currently this will cause Undefined Behavior if the value - is finite but larger or smaller than the largest or smallest finite - value representable by f32][float-float]**. This is a bug and will - be fixed. - - -[float-int]: https://github.com/rust-lang/rust/issues/10184 -[float-float]: https://github.com/rust-lang/rust/issues/15536 diff --git a/src/doc/nomicon/src/chapter_1.md b/src/doc/nomicon/src/chapter_1.md deleted file mode 100644 index b743fda354692..0000000000000 --- a/src/doc/nomicon/src/chapter_1.md +++ /dev/null @@ -1 +0,0 @@ -# Chapter 1 diff --git a/src/doc/nomicon/src/checked-uninit.md b/src/doc/nomicon/src/checked-uninit.md deleted file mode 100644 index 4423404fe6e9c..0000000000000 --- a/src/doc/nomicon/src/checked-uninit.md +++ /dev/null @@ -1,117 +0,0 @@ -# Checked Uninitialized Memory - -Like C, all stack variables in Rust are uninitialized until a value is -explicitly assigned to them. Unlike C, Rust statically prevents you from ever -reading them until you do: - -```rust,ignore -fn main() { - let x: i32; - println!("{}", x); -} -``` - -```text -src/main.rs:3:20: 3:21 error: use of possibly uninitialized variable: `x` -src/main.rs:3 println!("{}", x); - ^ -``` - -This is based off of a basic branch analysis: every branch must assign a value -to `x` before it is first used. Interestingly, Rust doesn't require the variable -to be mutable to perform a delayed initialization if every branch assigns -exactly once. However the analysis does not take advantage of constant analysis -or anything like that. So this compiles: - -```rust -fn main() { - let x: i32; - - if true { - x = 1; - } else { - x = 2; - } - - println!("{}", x); -} -``` - -but this doesn't: - -```rust,ignore -fn main() { - let x: i32; - if true { - x = 1; - } - println!("{}", x); -} -``` - -```text -src/main.rs:6:17: 6:18 error: use of possibly uninitialized variable: `x` -src/main.rs:6 println!("{}", x); -``` - -while this does: - -```rust -fn main() { - let x: i32; - if true { - x = 1; - println!("{}", x); - } - // Don't care that there are branches where it's not initialized - // since we don't use the value in those branches -} -``` - -Of course, while the analysis doesn't consider actual values, it does -have a relatively sophisticated understanding of dependencies and control -flow. For instance, this works: - -```rust -let x: i32; - -loop { - // Rust doesn't understand that this branch will be taken unconditionally, - // because it relies on actual values. - if true { - // But it does understand that it will only be taken once because - // we unconditionally break out of it. Therefore `x` doesn't - // need to be marked as mutable. - x = 0; - break; - } -} -// It also knows that it's impossible to get here without reaching the break. -// And therefore that `x` must be initialized here! -println!("{}", x); -``` - -If a value is moved out of a variable, that variable becomes logically -uninitialized if the type of the value isn't Copy. That is: - -```rust -fn main() { - let x = 0; - let y = Box::new(0); - let z1 = x; // x is still valid because i32 is Copy - let z2 = y; // y is now logically uninitialized because Box isn't Copy -} -``` - -However reassigning `y` in this example *would* require `y` to be marked as -mutable, as a Safe Rust program could observe that the value of `y` changed: - -```rust -fn main() { - let mut y = Box::new(0); - let z = y; // y is now logically uninitialized because Box isn't Copy - y = Box::new(1); // reinitialize y -} -``` - -Otherwise it's like `y` is a brand new variable. diff --git a/src/doc/nomicon/src/coercions.md b/src/doc/nomicon/src/coercions.md deleted file mode 100644 index 1a51bb5a9c614..0000000000000 --- a/src/doc/nomicon/src/coercions.md +++ /dev/null @@ -1,72 +0,0 @@ -# Coercions - -Types can implicitly be coerced to change in certain contexts. These changes are -generally just *weakening* of types, largely focused around pointers and -lifetimes. They mostly exist to make Rust "just work" in more cases, and are -largely harmless. - -Here's all the kinds of coercion: - -Coercion is allowed between the following types: - -* Transitivity: `T_1` to `T_3` where `T_1` coerces to `T_2` and `T_2` coerces to - `T_3` -* Pointer Weakening: - * `&mut T` to `&T` - * `*mut T` to `*const T` - * `&T` to `*const T` - * `&mut T` to `*mut T` -* Unsizing: `T` to `U` if `T` implements `CoerceUnsized` -* Deref coercion: Expression `&x` of type `&T` to `&*x` of type `&U` if `T` derefs to `U` (i.e. `T: Deref`) - -`CoerceUnsized> for Pointer where T: Unsize` is implemented -for all pointer types (including smart pointers like Box and Rc). Unsize is -only implemented automatically, and enables the following transformations: - -* `[T; n]` => `[T]` -* `T` => `Trait` where `T: Trait` -* `Foo<..., T, ...>` => `Foo<..., U, ...>` where: - * `T: Unsize` - * `Foo` is a struct - * Only the last field of `Foo` has type involving `T` - * `T` is not part of the type of any other fields - * `Bar: Unsize>`, if the last field of `Foo` has type `Bar` - -Coercions occur at a *coercion site*. Any location that is explicitly typed -will cause a coercion to its type. If inference is necessary, the coercion will -not be performed. Exhaustively, the coercion sites for an expression `e` to -type `U` are: - -* let statements, statics, and consts: `let x: U = e` -* Arguments to functions: `takes_a_U(e)` -* Any expression that will be returned: `fn foo() -> U { e }` -* Struct literals: `Foo { some_u: e }` -* Array literals: `let x: [U; 10] = [e, ..]` -* Tuple literals: `let x: (U, ..) = (e, ..)` -* The last expression in a block: `let x: U = { ..; e }` - -Note that we do not perform coercions when matching traits (except for -receivers, see below). If there is an impl for some type `U` and `T` coerces to -`U`, that does not constitute an implementation for `T`. For example, the -following will not type check, even though it is OK to coerce `t` to `&T` and -there is an impl for `&T`: - -```rust,ignore -trait Trait {} - -fn foo(t: X) {} - -impl<'a> Trait for &'a i32 {} - - -fn main() { - let t: &mut i32 = &mut 0; - foo(t); -} -``` - -```text -:10:5: 10:8 error: the trait bound `&mut i32 : Trait` is not satisfied [E0277] -:10 foo(t); - ^~~ -``` diff --git a/src/doc/nomicon/src/concurrency.md b/src/doc/nomicon/src/concurrency.md deleted file mode 100644 index 6205199bfcc44..0000000000000 --- a/src/doc/nomicon/src/concurrency.md +++ /dev/null @@ -1,13 +0,0 @@ -# Concurrency and Parallelism - -Rust as a language doesn't *really* have an opinion on how to do concurrency or -parallelism. The standard library exposes OS threads and blocking sys-calls -because everyone has those, and they're uniform enough that you can provide -an abstraction over them in a relatively uncontroversial way. Message passing, -green threads, and async APIs are all diverse enough that any abstraction over -them tends to involve trade-offs that we weren't willing to commit to for 1.0. - -However the way Rust models concurrency makes it relatively easy to design your own -concurrency paradigm as a library and have everyone else's code Just Work -with yours. Just require the right lifetimes and Send and Sync where appropriate -and you're off to the races. Or rather, off to the... not... having... races. diff --git a/src/doc/nomicon/src/constructors.md b/src/doc/nomicon/src/constructors.md deleted file mode 100644 index b79e72dbae2bf..0000000000000 --- a/src/doc/nomicon/src/constructors.md +++ /dev/null @@ -1,59 +0,0 @@ -# Constructors - -There is exactly one way to create an instance of a user-defined type: name it, -and initialize all its fields at once: - -```rust -struct Foo { - a: u8, - b: u32, - c: bool, -} - -enum Bar { - X(u32), - Y(bool), -} - -struct Unit; - -let foo = Foo { a: 0, b: 1, c: false }; -let bar = Bar::X(0); -let empty = Unit; -``` - -That's it. Every other way you make an instance of a type is just calling a -totally vanilla function that does some stuff and eventually bottoms out to The -One True Constructor. - -Unlike C++, Rust does not come with a slew of built-in kinds of constructor. -There are no Copy, Default, Assignment, Move, or whatever constructors. The -reasons for this are varied, but it largely boils down to Rust's philosophy of -*being explicit*. - -Move constructors are meaningless in Rust because we don't enable types to -"care" about their location in memory. Every type must be ready for it to be -blindly memcopied to somewhere else in memory. This means pure on-the-stack-but- -still-movable intrusive linked lists are simply not happening in Rust (safely). - -Assignment and copy constructors similarly don't exist because move semantics -are the only semantics in Rust. At most `x = y` just moves the bits of y into -the x variable. Rust does provide two facilities for providing C++'s copy- -oriented semantics: `Copy` and `Clone`. Clone is our moral equivalent of a copy -constructor, but it's never implicitly invoked. You have to explicitly call -`clone` on an element you want to be cloned. Copy is a special case of Clone -where the implementation is just "copy the bits". Copy types *are* implicitly -cloned whenever they're moved, but because of the definition of Copy this just -means not treating the old copy as uninitialized -- a no-op. - -While Rust provides a `Default` trait for specifying the moral equivalent of a -default constructor, it's incredibly rare for this trait to be used. This is -because variables [aren't implicitly initialized][uninit]. Default is basically -only useful for generic programming. In concrete contexts, a type will provide a -static `new` method for any kind of "default" constructor. This has no relation -to `new` in other languages and has no special meaning. It's just a naming -convention. - -TODO: talk about "placement new"? - -[uninit]: uninitialized.html diff --git a/src/doc/nomicon/src/conversions.md b/src/doc/nomicon/src/conversions.md deleted file mode 100644 index 388d003d9b6c2..0000000000000 --- a/src/doc/nomicon/src/conversions.md +++ /dev/null @@ -1,34 +0,0 @@ -# Type Conversions - -At the end of the day, everything is just a pile of bits somewhere, and type -systems are just there to help us use those bits right. There are two common -problems with typing bits: needing to reinterpret those exact bits as a -different type, and needing to change the bits to have equivalent meaning for -a different type. Because Rust encourages encoding important properties in the -type system, these problems are incredibly pervasive. As such, Rust -consequently gives you several ways to solve them. - -First we'll look at the ways that Safe Rust gives you to reinterpret values. -The most trivial way to do this is to just destructure a value into its -constituent parts and then build a new type out of them. e.g. - -```rust -struct Foo { - x: u32, - y: u16, -} - -struct Bar { - a: u32, - b: u16, -} - -fn reinterpret(foo: Foo) -> Bar { - let Foo { x, y } = foo; - Bar { a: x, b: y } -} -``` - -But this is, at best, annoying. For common conversions, Rust provides -more ergonomic alternatives. - diff --git a/src/doc/nomicon/src/data.md b/src/doc/nomicon/src/data.md deleted file mode 100644 index bf202ada08e95..0000000000000 --- a/src/doc/nomicon/src/data.md +++ /dev/null @@ -1,5 +0,0 @@ -# Data Representation in Rust - -Low-level programming cares a lot about data layout. It's a big deal. It also -pervasively influences the rest of the language, so we're going to start by -digging into how data is represented in Rust. diff --git a/src/doc/nomicon/src/destructors.md b/src/doc/nomicon/src/destructors.md deleted file mode 100644 index 8c395fe3dc947..0000000000000 --- a/src/doc/nomicon/src/destructors.md +++ /dev/null @@ -1,190 +0,0 @@ -# Destructors - -What the language *does* provide is full-blown automatic destructors through the -`Drop` trait, which provides the following method: - -```rust,ignore -fn drop(&mut self); -``` - -This method gives the type time to somehow finish what it was doing. - -**After `drop` is run, Rust will recursively try to drop all of the fields -of `self`.** - -This is a convenience feature so that you don't have to write "destructor -boilerplate" to drop children. If a struct has no special logic for being -dropped other than dropping its children, then it means `Drop` doesn't need to -be implemented at all! - -**There is no stable way to prevent this behavior in Rust 1.0.** - -Note that taking `&mut self` means that even if you could suppress recursive -Drop, Rust will prevent you from e.g. moving fields out of self. For most types, -this is totally fine. - -For instance, a custom implementation of `Box` might write `Drop` like this: - -```rust -#![feature(alloc, heap_api, unique)] - -extern crate alloc; - -use std::ptr::{drop_in_place, Unique}; -use std::mem; - -use alloc::heap; - -struct Box{ ptr: Unique } - -impl Drop for Box { - fn drop(&mut self) { - unsafe { - drop_in_place(*self.ptr); - heap::deallocate((*self.ptr) as *mut u8, - mem::size_of::(), - mem::align_of::()); - } - } -} -# fn main() {} -``` - -and this works fine because when Rust goes to drop the `ptr` field it just sees -a [Unique] that has no actual `Drop` implementation. Similarly nothing can -use-after-free the `ptr` because when drop exits, it becomes inaccessible. - -However this wouldn't work: - -```rust -#![feature(alloc, heap_api, unique)] - -extern crate alloc; - -use std::ptr::{drop_in_place, Unique}; -use std::mem; - -use alloc::heap; - -struct Box{ ptr: Unique } - -impl Drop for Box { - fn drop(&mut self) { - unsafe { - drop_in_place(*self.ptr); - heap::deallocate((*self.ptr) as *mut u8, - mem::size_of::(), - mem::align_of::()); - } - } -} - -struct SuperBox { my_box: Box } - -impl Drop for SuperBox { - fn drop(&mut self) { - unsafe { - // Hyper-optimized: deallocate the box's contents for it - // without `drop`ing the contents - heap::deallocate((*self.my_box.ptr) as *mut u8, - mem::size_of::(), - mem::align_of::()); - } - } -} -# fn main() {} -``` - -After we deallocate the `box`'s ptr in SuperBox's destructor, Rust will -happily proceed to tell the box to Drop itself and everything will blow up with -use-after-frees and double-frees. - -Note that the recursive drop behavior applies to all structs and enums -regardless of whether they implement Drop. Therefore something like - -```rust -struct Boxy { - data1: Box, - data2: Box, - info: u32, -} -``` - -will have its data1 and data2's fields destructors whenever it "would" be -dropped, even though it itself doesn't implement Drop. We say that such a type -*needs Drop*, even though it is not itself Drop. - -Similarly, - -```rust -enum Link { - Next(Box), - None, -} -``` - -will have its inner Box field dropped if and only if an instance stores the -Next variant. - -In general this works really nicely because you don't need to worry about -adding/removing drops when you refactor your data layout. Still there's -certainly many valid usecases for needing to do trickier things with -destructors. - -The classic safe solution to overriding recursive drop and allowing moving out -of Self during `drop` is to use an Option: - -```rust -#![feature(alloc, heap_api, unique)] - -extern crate alloc; - -use std::ptr::{drop_in_place, Unique}; -use std::mem; - -use alloc::heap; - -struct Box{ ptr: Unique } - -impl Drop for Box { - fn drop(&mut self) { - unsafe { - drop_in_place(*self.ptr); - heap::deallocate((*self.ptr) as *mut u8, - mem::size_of::(), - mem::align_of::()); - } - } -} - -struct SuperBox { my_box: Option> } - -impl Drop for SuperBox { - fn drop(&mut self) { - unsafe { - // Hyper-optimized: deallocate the box's contents for it - // without `drop`ing the contents. Need to set the `box` - // field as `None` to prevent Rust from trying to Drop it. - let my_box = self.my_box.take().unwrap(); - heap::deallocate((*my_box.ptr) as *mut u8, - mem::size_of::(), - mem::align_of::()); - mem::forget(my_box); - } - } -} -# fn main() {} -``` - -However this has fairly odd semantics: you're saying that a field that *should* -always be Some *may* be None, just because that happens in the destructor. Of -course this conversely makes a lot of sense: you can call arbitrary methods on -self during the destructor, and this should prevent you from ever doing so after -deinitializing the field. Not that it will prevent you from producing any other -arbitrarily invalid state in there. - -On balance this is an ok choice. Certainly what you should reach for by default. -However, in the future we expect there to be a first-class way to announce that -a field shouldn't be automatically dropped. - -[Unique]: phantom-data.html diff --git a/src/doc/nomicon/src/dot-operator.md b/src/doc/nomicon/src/dot-operator.md deleted file mode 100644 index a1fc33bdc1e33..0000000000000 --- a/src/doc/nomicon/src/dot-operator.md +++ /dev/null @@ -1,6 +0,0 @@ -# The Dot Operator - -The dot operator will perform a lot of magic to convert types. It will perform -auto-referencing, auto-dereferencing, and coercion until types match. - -TODO: steal information from http://stackoverflow.com/questions/28519997/what-are-rusts-exact-auto-dereferencing-rules/28552082#28552082 diff --git a/src/doc/nomicon/src/drop-flags.md b/src/doc/nomicon/src/drop-flags.md deleted file mode 100644 index e69264f281c99..0000000000000 --- a/src/doc/nomicon/src/drop-flags.md +++ /dev/null @@ -1,83 +0,0 @@ -# Drop Flags - -The examples in the previous section introduce an interesting problem for Rust. -We have seen that it's possible to conditionally initialize, deinitialize, and -reinitialize locations of memory totally safely. For Copy types, this isn't -particularly notable since they're just a random pile of bits. However types -with destructors are a different story: Rust needs to know whether to call a -destructor whenever a variable is assigned to, or a variable goes out of scope. -How can it do this with conditional initialization? - -Note that this is not a problem that all assignments need worry about. In -particular, assigning through a dereference unconditionally drops, and assigning -in a `let` unconditionally doesn't drop: - -``` -let mut x = Box::new(0); // let makes a fresh variable, so never need to drop -let y = &mut x; -*y = Box::new(1); // Deref assumes the referent is initialized, so always drops -``` - -This is only a problem when overwriting a previously initialized variable or -one of its subfields. - -It turns out that Rust actually tracks whether a type should be dropped or not -*at runtime*. As a variable becomes initialized and uninitialized, a *drop flag* -for that variable is toggled. When a variable might need to be dropped, this -flag is evaluated to determine if it should be dropped. - -Of course, it is often the case that a value's initialization state can be -statically known at every point in the program. If this is the case, then the -compiler can theoretically generate more efficient code! For instance, straight- -line code has such *static drop semantics*: - -```rust -let mut x = Box::new(0); // x was uninit; just overwrite. -let mut y = x; // y was uninit; just overwrite and make x uninit. -x = Box::new(0); // x was uninit; just overwrite. -y = x; // y was init; Drop y, overwrite it, and make x uninit! - // y goes out of scope; y was init; Drop y! - // x goes out of scope; x was uninit; do nothing. -``` - -Similarly, branched code where all branches have the same behavior with respect -to initialization has static drop semantics: - -```rust -# let condition = true; -let mut x = Box::new(0); // x was uninit; just overwrite. -if condition { - drop(x) // x gets moved out; make x uninit. -} else { - println!("{}", x); - drop(x) // x gets moved out; make x uninit. -} -x = Box::new(0); // x was uninit; just overwrite. - // x goes out of scope; x was init; Drop x! -``` - -However code like this *requires* runtime information to correctly Drop: - -```rust -# let condition = true; -let x; -if condition { - x = Box::new(0); // x was uninit; just overwrite. - println!("{}", x); -} - // x goes out of scope; x might be uninit; - // check the flag! -``` - -Of course, in this case it's trivial to retrieve static drop semantics: - -```rust -# let condition = true; -if condition { - let x = Box::new(0); - println!("{}", x); -} -``` - -The drop flags are tracked on the stack and no longer stashed in types that -implement drop. diff --git a/src/doc/nomicon/src/dropck.md b/src/doc/nomicon/src/dropck.md deleted file mode 100644 index 39039694be674..0000000000000 --- a/src/doc/nomicon/src/dropck.md +++ /dev/null @@ -1,295 +0,0 @@ -# Drop Check - -We have seen how lifetimes provide us some fairly simple rules for ensuring -that we never read dangling references. However up to this point we have only ever -interacted with the *outlives* relationship in an inclusive manner. That is, -when we talked about `'a: 'b`, it was ok for `'a` to live *exactly* as long as -`'b`. At first glance, this seems to be a meaningless distinction. Nothing ever -gets dropped at the same time as another, right? This is why we used the -following desugaring of `let` statements: - -```rust,ignore -let x; -let y; -``` - -```rust,ignore -{ - let x; - { - let y; - } -} -``` - -Each creates its own scope, clearly establishing that one drops before the -other. However, what if we do the following? - -```rust,ignore -let (x, y) = (vec![], vec![]); -``` - -Does either value strictly outlive the other? The answer is in fact *no*, -neither value strictly outlives the other. Of course, one of x or y will be -dropped before the other, but the actual order is not specified. Tuples aren't -special in this regard; composite structures just don't guarantee their -destruction order as of Rust 1.0. - -We *could* specify this for the fields of built-in composites like tuples and -structs. However, what about something like Vec? Vec has to manually drop its -elements via pure-library code. In general, anything that implements Drop has -a chance to fiddle with its innards during its final death knell. Therefore -the compiler can't sufficiently reason about the actual destruction order -of the contents of any type that implements Drop. - -So why do we care? We care because if the type system isn't careful, it could -accidentally make dangling pointers. Consider the following simple program: - -```rust -struct Inspector<'a>(&'a u8); - -fn main() { - let (inspector, days); - days = Box::new(1); - inspector = Inspector(&days); -} -``` - -This program is totally sound and compiles today. The fact that `days` does -not *strictly* outlive `inspector` doesn't matter. As long as the `inspector` -is alive, so is days. - -However if we add a destructor, the program will no longer compile! - -```rust,ignore -struct Inspector<'a>(&'a u8); - -impl<'a> Drop for Inspector<'a> { - fn drop(&mut self) { - println!("I was only {} days from retirement!", self.0); - } -} - -fn main() { - let (inspector, days); - days = Box::new(1); - inspector = Inspector(&days); - // Let's say `days` happens to get dropped first. - // Then when Inspector is dropped, it will try to read free'd memory! -} -``` - -```text -:12:28: 12:32 error: `days` does not live long enough -:12 inspector = Inspector(&days); - ^~~~ -:9:11: 15:2 note: reference must be valid for the block at 9:10... -:9 fn main() { -:10 let (inspector, days); -:11 days = Box::new(1); -:12 inspector = Inspector(&days); -:13 // Let's say `days` happens to get dropped first. -:14 // Then when Inspector is dropped, it will try to read free'd memory! - ... -:10:27: 15:2 note: ...but borrowed value is only valid for the block suffix following statement 0 at 10:26 -:10 let (inspector, days); -:11 days = Box::new(1); -:12 inspector = Inspector(&days); -:13 // Let's say `days` happens to get dropped first. -:14 // Then when Inspector is dropped, it will try to read free'd memory! -:15 } -``` - -Implementing Drop lets the Inspector execute some arbitrary code during its -death. This means it can potentially observe that types that are supposed to -live as long as it does actually were destroyed first. - -Interestingly, only generic types need to worry about this. If they aren't -generic, then the only lifetimes they can harbor are `'static`, which will truly -live *forever*. This is why this problem is referred to as *sound generic drop*. -Sound generic drop is enforced by the *drop checker*. As of this writing, some -of the finer details of how the drop checker validates types is totally up in -the air. However The Big Rule is the subtlety that we have focused on this whole -section: - -**For a generic type to soundly implement drop, its generics arguments must -strictly outlive it.** - -Obeying this rule is (usually) necessary to satisfy the borrow -checker; obeying it is sufficient but not necessary to be -sound. That is, if your type obeys this rule then it's definitely -sound to drop. - -The reason that it is not always necessary to satisfy the above rule -is that some Drop implementations will not access borrowed data even -though their type gives them the capability for such access. - -For example, this variant of the above `Inspector` example will never -access borrowed data: - -```rust,ignore -struct Inspector<'a>(&'a u8, &'static str); - -impl<'a> Drop for Inspector<'a> { - fn drop(&mut self) { - println!("Inspector(_, {}) knows when *not* to inspect.", self.1); - } -} - -fn main() { - let (inspector, days); - days = Box::new(1); - inspector = Inspector(&days, "gadget"); - // Let's say `days` happens to get dropped first. - // Even when Inspector is dropped, its destructor will not access the - // borrowed `days`. -} -``` - -Likewise, this variant will also never access borrowed data: - -```rust,ignore -use std::fmt; - -struct Inspector(T, &'static str); - -impl Drop for Inspector { - fn drop(&mut self) { - println!("Inspector(_, {}) knows when *not* to inspect.", self.1); - } -} - -fn main() { - let (inspector, days): (Inspector<&u8>, Box); - days = Box::new(1); - inspector = Inspector(&days, "gadget"); - // Let's say `days` happens to get dropped first. - // Even when Inspector is dropped, its destructor will not access the - // borrowed `days`. -} -``` - -However, *both* of the above variants are rejected by the borrow -checker during the analysis of `fn main`, saying that `days` does not -live long enough. - -The reason is that the borrow checking analysis of `main` does not -know about the internals of each Inspector's Drop implementation. As -far as the borrow checker knows while it is analyzing `main`, the body -of an inspector's destructor might access that borrowed data. - -Therefore, the drop checker forces all borrowed data in a value to -strictly outlive that value. - -# An Escape Hatch - -The precise rules that govern drop checking may be less restrictive in -the future. - -The current analysis is deliberately conservative and trivial; it forces all -borrowed data in a value to outlive that value, which is certainly sound. - -Future versions of the language may make the analysis more precise, to -reduce the number of cases where sound code is rejected as unsafe. -This would help address cases such as the two Inspectors above that -know not to inspect during destruction. - -In the meantime, there is an unstable attribute that one can use to -assert (unsafely) that a generic type's destructor is *guaranteed* to -not access any expired data, even if its type gives it the capability -to do so. - -That attribute is called `may_dangle` and was introduced in [RFC 1327] -(https://github.com/rust-lang/rfcs/blob/master/text/1327-dropck-param-eyepatch.md). -To deploy it on the Inspector example from above, we would write: - -```rust,ignore -struct Inspector<'a>(&'a u8, &'static str); - -unsafe impl<#[may_dangle] 'a> Drop for Inspector<'a> { - fn drop(&mut self) { - println!("Inspector(_, {}) knows when *not* to inspect.", self.1); - } -} -``` - -Use of this attribute requires the `Drop` impl to be marked `unsafe` because the -compiler is not checking the implicit assertion that no potentially expired data -(e.g. `self.0` above) is accessed. - -The attribute can be applied to any number of lifetime and type parameters. In -the following example, we assert that we access no data behind a reference of -lifetime `'b` and that the only uses of `T` will be moves or drops, but omit -the attribute from `'a` and `U`, because we do access data with that lifetime -and that type: - -```rust,ignore -use std::fmt::Display; - -struct Inspector<'a, 'b, T, U: Display>(&'a u8, &'b u8, T, U); - -unsafe impl<'a, #[may_dangle] 'b, #[may_dangle] T, U: Display> Drop for Inspector<'a, 'b, T, U> { - fn drop(&mut self) { - println!("Inspector({}, _, _, {})", self.0, self.3); - } -} -``` - -It is sometimes obvious that no such access can occur, like the case above. -However, when dealing with a generic type parameter, such access can -occur indirectly. Examples of such indirect access are: - - * invoking a callback, - * via a trait method call. - -(Future changes to the language, such as impl specialization, may add -other avenues for such indirect access.) - -Here is an example of invoking a callback: - -```rust,ignore -struct Inspector(T, &'static str, Box fn(&'r T) -> String>); - -impl Drop for Inspector { - fn drop(&mut self) { - // The `self.2` call could access a borrow e.g. if `T` is `&'a _`. - println!("Inspector({}, {}) unwittingly inspects expired data.", - (self.2)(&self.0), self.1); - } -} -``` - -Here is an example of a trait method call: - -```rust,ignore -use std::fmt; - -struct Inspector(T, &'static str); - -impl Drop for Inspector { - fn drop(&mut self) { - // There is a hidden call to `::fmt` below, which - // could access a borrow e.g. if `T` is `&'a _` - println!("Inspector({}, {}) unwittingly inspects expired data.", - self.0, self.1); - } -} -``` - -And of course, all of these accesses could be further hidden within -some other method invoked by the destructor, rather than being written -directly within it. - -In all of the above cases where the `&'a u8` is accessed in the -destructor, adding the `#[may_dangle]` -attribute makes the type vulnerable to misuse that the borrower -checker will not catch, inviting havoc. It is better to avoid adding -the attribute. - -# Is that all about drop checker? - -It turns out that when writing unsafe code, we generally don't need to -worry at all about doing the right thing for the drop checker. However there -is one special case that you need to worry about, which we will look at in -the next section. - diff --git a/src/doc/nomicon/src/exception-safety.md b/src/doc/nomicon/src/exception-safety.md deleted file mode 100644 index a3cbc6abd69cc..0000000000000 --- a/src/doc/nomicon/src/exception-safety.md +++ /dev/null @@ -1,217 +0,0 @@ -# Exception Safety - -Although programs should use unwinding sparingly, there's a lot of code that -*can* panic. If you unwrap a None, index out of bounds, or divide by 0, your -program will panic. On debug builds, every arithmetic operation can panic -if it overflows. Unless you are very careful and tightly control what code runs, -pretty much everything can unwind, and you need to be ready for it. - -Being ready for unwinding is often referred to as *exception safety* -in the broader programming world. In Rust, there are two levels of exception -safety that one may concern themselves with: - -* In unsafe code, we *must* be exception safe to the point of not violating - memory safety. We'll call this *minimal* exception safety. - -* In safe code, it is *good* to be exception safe to the point of your program - doing the right thing. We'll call this *maximal* exception safety. - -As is the case in many places in Rust, Unsafe code must be ready to deal with -bad Safe code when it comes to unwinding. Code that transiently creates -unsound states must be careful that a panic does not cause that state to be -used. Generally this means ensuring that only non-panicking code is run while -these states exist, or making a guard that cleans up the state in the case of -a panic. This does not necessarily mean that the state a panic witnesses is a -fully coherent state. We need only guarantee that it's a *safe* state. - -Most Unsafe code is leaf-like, and therefore fairly easy to make exception-safe. -It controls all the code that runs, and most of that code can't panic. However -it is not uncommon for Unsafe code to work with arrays of temporarily -uninitialized data while repeatedly invoking caller-provided code. Such code -needs to be careful and consider exception safety. - - - - - -## Vec::push_all - -`Vec::push_all` is a temporary hack to get extending a Vec by a slice reliably -efficient without specialization. Here's a simple implementation: - -```rust,ignore -impl Vec { - fn push_all(&mut self, to_push: &[T]) { - self.reserve(to_push.len()); - unsafe { - // can't overflow because we just reserved this - self.set_len(self.len() + to_push.len()); - - for (i, x) in to_push.iter().enumerate() { - self.ptr().offset(i as isize).write(x.clone()); - } - } - } -} -``` - -We bypass `push` in order to avoid redundant capacity and `len` checks on the -Vec that we definitely know has capacity. The logic is totally correct, except -there's a subtle problem with our code: it's not exception-safe! `set_len`, -`offset`, and `write` are all fine; `clone` is the panic bomb we over-looked. - -Clone is completely out of our control, and is totally free to panic. If it -does, our function will exit early with the length of the Vec set too large. If -the Vec is looked at or dropped, uninitialized memory will be read! - -The fix in this case is fairly simple. If we want to guarantee that the values -we *did* clone are dropped, we can set the `len` every loop iteration. If we -just want to guarantee that uninitialized memory can't be observed, we can set -the `len` after the loop. - - - - - -## BinaryHeap::sift_up - -Bubbling an element up a heap is a bit more complicated than extending a Vec. -The pseudocode is as follows: - -```text -bubble_up(heap, index): - while index != 0 && heap[index] < heap[parent(index)]: - heap.swap(index, parent(index)) - index = parent(index) - -``` - -A literal transcription of this code to Rust is totally fine, but has an annoying -performance characteristic: the `self` element is swapped over and over again -uselessly. We would rather have the following: - -```text -bubble_up(heap, index): - let elem = heap[index] - while index != 0 && elem < heap[parent(index)]: - heap[index] = heap[parent(index)] - index = parent(index) - heap[index] = elem -``` - -This code ensures that each element is copied as little as possible (it is in -fact necessary that elem be copied twice in general). However it now exposes -some exception safety trouble! At all times, there exists two copies of one -value. If we panic in this function something will be double-dropped. -Unfortunately, we also don't have full control of the code: that comparison is -user-defined! - -Unlike Vec, the fix isn't as easy here. One option is to break the user-defined -code and the unsafe code into two separate phases: - -```text -bubble_up(heap, index): - let end_index = index; - while end_index != 0 && heap[end_index] < heap[parent(end_index)]: - end_index = parent(end_index) - - let elem = heap[index] - while index != end_index: - heap[index] = heap[parent(index)] - index = parent(index) - heap[index] = elem -``` - -If the user-defined code blows up, that's no problem anymore, because we haven't -actually touched the state of the heap yet. Once we do start messing with the -heap, we're working with only data and functions that we trust, so there's no -concern of panics. - -Perhaps you're not happy with this design. Surely it's cheating! And we have -to do the complex heap traversal *twice*! Alright, let's bite the bullet. Let's -intermix untrusted and unsafe code *for reals*. - -If Rust had `try` and `finally` like in Java, we could do the following: - -```text -bubble_up(heap, index): - let elem = heap[index] - try: -        while index != 0 && elem < heap[parent(index)]: - heap[index] = heap[parent(index)] - index = parent(index) - finally: - heap[index] = elem -``` - -The basic idea is simple: if the comparison panics, we just toss the loose -element in the logically uninitialized index and bail out. Anyone who observes -the heap will see a potentially *inconsistent* heap, but at least it won't -cause any double-drops! If the algorithm terminates normally, then this -operation happens to coincide precisely with the how we finish up regardless. - -Sadly, Rust has no such construct, so we're going to need to roll our own! The -way to do this is to store the algorithm's state in a separate struct with a -destructor for the "finally" logic. Whether we panic or not, that destructor -will run and clean up after us. - -```rust,ignore -struct Hole<'a, T: 'a> { - data: &'a mut [T], - /// `elt` is always `Some` from new until drop. - elt: Option, - pos: usize, -} - -impl<'a, T> Hole<'a, T> { - fn new(data: &'a mut [T], pos: usize) -> Self { - unsafe { - let elt = ptr::read(&data[pos]); - Hole { - data: data, - elt: Some(elt), - pos: pos, - } - } - } - - fn pos(&self) -> usize { self.pos } - - fn removed(&self) -> &T { self.elt.as_ref().unwrap() } - - unsafe fn get(&self, index: usize) -> &T { &self.data[index] } - - unsafe fn move_to(&mut self, index: usize) { - let index_ptr: *const _ = &self.data[index]; - let hole_ptr = &mut self.data[self.pos]; - ptr::copy_nonoverlapping(index_ptr, hole_ptr, 1); - self.pos = index; - } -} - -impl<'a, T> Drop for Hole<'a, T> { - fn drop(&mut self) { - // fill the hole again - unsafe { - let pos = self.pos; - ptr::write(&mut self.data[pos], self.elt.take().unwrap()); - } - } -} - -impl BinaryHeap { - fn sift_up(&mut self, pos: usize) { - unsafe { - // Take out the value at `pos` and create a hole. - let mut hole = Hole::new(&mut self.data, pos); - - while hole.pos() != 0 { - let parent = parent(hole.pos()); - if hole.removed() <= hole.get(parent) { break } - hole.move_to(parent); - } - // Hole will be unconditionally filled here; panic or not! - } - } -} -``` diff --git a/src/doc/nomicon/src/exotic-sizes.md b/src/doc/nomicon/src/exotic-sizes.md deleted file mode 100644 index 9f858d11dbbb9..0000000000000 --- a/src/doc/nomicon/src/exotic-sizes.md +++ /dev/null @@ -1,137 +0,0 @@ -# Exotically Sized Types - -Most of the time, we think in terms of types with a fixed, positive size. This -is not always the case, however. - - - - - -# Dynamically Sized Types (DSTs) - -Rust in fact supports Dynamically Sized Types (DSTs): types without a statically -known size or alignment. On the surface, this is a bit nonsensical: Rust *must* -know the size and alignment of something in order to correctly work with it! In -this regard, DSTs are not normal types. Due to their lack of a statically known -size, these types can only exist behind some kind of pointer. Any pointer to a -DST consequently becomes a *fat* pointer consisting of the pointer and the -information that "completes" them (more on this below). - -There are two major DSTs exposed by the language: trait objects, and slices. - -A trait object represents some type that implements the traits it specifies. -The exact original type is *erased* in favor of runtime reflection -with a vtable containing all the information necessary to use the type. -This is the information that completes a trait object: a pointer to its vtable. - -A slice is simply a view into some contiguous storage -- typically an array or -`Vec`. The information that completes a slice is just the number of elements -it points to. - -Structs can actually store a single DST directly as their last field, but this -makes them a DST as well: - -```rust -// Can't be stored on the stack directly -struct Foo { - info: u32, - data: [u8], -} -``` - -**NOTE: [As of Rust 1.0 struct DSTs are broken if the last field has -a variable position based on its alignment][dst-issue].** - - - - - -# Zero Sized Types (ZSTs) - -Rust actually allows types to be specified that occupy no space: - -```rust -struct Foo; // No fields = no size - -// All fields have no size = no size -struct Baz { - foo: Foo, - qux: (), // empty tuple has no size - baz: [u8; 0], // empty array has no size -} -``` - -On their own, Zero Sized Types (ZSTs) are, for obvious reasons, pretty useless. -However as with many curious layout choices in Rust, their potential is realized -in a generic context: Rust largely understands that any operation that produces -or stores a ZST can be reduced to a no-op. First off, storing it doesn't even -make sense -- it doesn't occupy any space. Also there's only one value of that -type, so anything that loads it can just produce it from the aether -- which is -also a no-op since it doesn't occupy any space. - -One of the most extreme example's of this is Sets and Maps. Given a -`Map`, it is common to implement a `Set` as just a thin wrapper -around `Map`. In many languages, this would necessitate -allocating space for UselessJunk and doing work to store and load UselessJunk -only to discard it. Proving this unnecessary would be a difficult analysis for -the compiler. - -However in Rust, we can just say that `Set = Map`. Now Rust -statically knows that every load and store is useless, and no allocation has any -size. The result is that the monomorphized code is basically a custom -implementation of a HashSet with none of the overhead that HashMap would have to -support values. - -Safe code need not worry about ZSTs, but *unsafe* code must be careful about the -consequence of types with no size. In particular, pointer offsets are no-ops, -and standard allocators (including jemalloc, the one used by default in Rust) -may return `nullptr` when a zero-sized allocation is requested, which is -indistinguishable from out of memory. - - - - - -# Empty Types - -Rust also enables types to be declared that *cannot even be instantiated*. These -types can only be talked about at the type level, and never at the value level. -Empty types can be declared by specifying an enum with no variants: - -```rust -enum Void {} // No variants = EMPTY -``` - -Empty types are even more marginal than ZSTs. The primary motivating example for -Void types is type-level unreachability. For instance, suppose an API needs to -return a Result in general, but a specific case actually is infallible. It's -actually possible to communicate this at the type level by returning a -`Result`. Consumers of the API can confidently unwrap such a Result -knowing that it's *statically impossible* for this value to be an `Err`, as -this would require providing a value of type `Void`. - -In principle, Rust can do some interesting analyses and optimizations based -on this fact. For instance, `Result` could be represented as just `T`, -because the `Err` case doesn't actually exist. The following *could* also -compile: - -```rust,ignore -enum Void {} - -let res: Result = Ok(0); - -// Err doesn't exist anymore, so Ok is actually irrefutable. -let Ok(num) = res; -``` - -But neither of these tricks work today, so all Void types get you is -the ability to be confident that certain situations are statically impossible. - -One final subtle detail about empty types is that raw pointers to them are -actually valid to construct, but dereferencing them is Undefined Behavior -because that doesn't actually make sense. That is, you could model C's `void *` -type with `*const Void`, but this doesn't necessarily gain anything over using -e.g. `*const ()`, which *is* safe to randomly dereference. - - -[dst-issue]: https://github.com/rust-lang/rust/issues/26403 diff --git a/src/doc/nomicon/src/hrtb.md b/src/doc/nomicon/src/hrtb.md deleted file mode 100644 index 645986af13ace..0000000000000 --- a/src/doc/nomicon/src/hrtb.md +++ /dev/null @@ -1,73 +0,0 @@ -# Higher-Rank Trait Bounds (HRTBs) - -Rust's `Fn` traits are a little bit magic. For instance, we can write the -following code: - -```rust -struct Closure { - data: (u8, u16), - func: F, -} - -impl Closure - where F: Fn(&(u8, u16)) -> &u8, -{ - fn call(&self) -> &u8 { - (self.func)(&self.data) - } -} - -fn do_it(data: &(u8, u16)) -> &u8 { &data.0 } - -fn main() { - let clo = Closure { data: (0, 1), func: do_it }; - println!("{}", clo.call()); -} -``` - -If we try to naively desugar this code in the same way that we did in the -lifetimes section, we run into some trouble: - -```rust,ignore -struct Closure { - data: (u8, u16), - func: F, -} - -impl Closure - // where F: Fn(&'??? (u8, u16)) -> &'??? u8, -{ - fn call<'a>(&'a self) -> &'a u8 { - (self.func)(&self.data) - } -} - -fn do_it<'b>(data: &'b (u8, u16)) -> &'b u8 { &'b data.0 } - -fn main() { - 'x: { - let clo = Closure { data: (0, 1), func: do_it }; - println!("{}", clo.call()); - } -} -``` - -How on earth are we supposed to express the lifetimes on `F`'s trait bound? We -need to provide some lifetime there, but the lifetime we care about can't be -named until we enter the body of `call`! Also, that isn't some fixed lifetime; -`call` works with *any* lifetime `&self` happens to have at that point. - -This job requires The Magic of Higher-Rank Trait Bounds (HRTBs). The way we -desugar this is as follows: - -```rust,ignore -where for<'a> F: Fn(&'a (u8, u16)) -> &'a u8, -``` - -(Where `Fn(a, b, c) -> d` is itself just sugar for the unstable *real* `Fn` -trait) - -`for<'a>` can be read as "for all choices of `'a`", and basically produces an -*infinite list* of trait bounds that F must satisfy. Intense. There aren't many -places outside of the `Fn` traits where we encounter HRTBs, and even for -those we have a nice magic sugar for the common cases. diff --git a/src/doc/nomicon/src/leaking.md b/src/doc/nomicon/src/leaking.md deleted file mode 100644 index 38b70b85b576a..0000000000000 --- a/src/doc/nomicon/src/leaking.md +++ /dev/null @@ -1,251 +0,0 @@ -# Leaking - -Ownership-based resource management is intended to simplify composition. You -acquire resources when you create the object, and you release the resources when -it gets destroyed. Since destruction is handled for you, it means you can't -forget to release the resources, and it happens as soon as possible! Surely this -is perfect and all of our problems are solved. - -Everything is terrible and we have new and exotic problems to try to solve. - -Many people like to believe that Rust eliminates resource leaks. In practice, -this is basically true. You would be surprised to see a Safe Rust program -leak resources in an uncontrolled way. - -However from a theoretical perspective this is absolutely not the case, no -matter how you look at it. In the strictest sense, "leaking" is so abstract as -to be unpreventable. It's quite trivial to initialize a collection at the start -of a program, fill it with tons of objects with destructors, and then enter an -infinite event loop that never refers to it. The collection will sit around -uselessly, holding on to its precious resources until the program terminates (at -which point all those resources would have been reclaimed by the OS anyway). - -We may consider a more restricted form of leak: failing to drop a value that is -unreachable. Rust also doesn't prevent this. In fact Rust *has a function for -doing this*: `mem::forget`. This function consumes the value it is passed *and -then doesn't run its destructor*. - -In the past `mem::forget` was marked as unsafe as a sort of lint against using -it, since failing to call a destructor is generally not a well-behaved thing to -do (though useful for some special unsafe code). However this was generally -determined to be an untenable stance to take: there are many ways to fail to -call a destructor in safe code. The most famous example is creating a cycle of -reference-counted pointers using interior mutability. - -It is reasonable for safe code to assume that destructor leaks do not happen, as -any program that leaks destructors is probably wrong. However *unsafe* code -cannot rely on destructors to be run in order to be safe. For most types this -doesn't matter: if you leak the destructor then the type is by definition -inaccessible, so it doesn't matter, right? For instance, if you leak a `Box` -then you waste some memory but that's hardly going to violate memory-safety. - -However where we must be careful with destructor leaks are *proxy* types. These -are types which manage access to a distinct object, but don't actually own it. -Proxy objects are quite rare. Proxy objects you'll need to care about are even -rarer. However we'll focus on three interesting examples in the standard -library: - -* `vec::Drain` -* `Rc` -* `thread::scoped::JoinGuard` - - - -## Drain - -`drain` is a collections API that moves data out of the container without -consuming the container. This enables us to reuse the allocation of a `Vec` -after claiming ownership over all of its contents. It produces an iterator -(Drain) that returns the contents of the Vec by-value. - -Now, consider Drain in the middle of iteration: some values have been moved out, -and others haven't. This means that part of the Vec is now full of logically -uninitialized data! We could backshift all the elements in the Vec every time we -remove a value, but this would have pretty catastrophic performance -consequences. - -Instead, we would like Drain to fix the Vec's backing storage when it is -dropped. It should run itself to completion, backshift any elements that weren't -removed (drain supports subranges), and then fix Vec's `len`. It's even -unwinding-safe! Easy! - -Now consider the following: - -```rust,ignore -let mut vec = vec![Box::new(0); 4]; - -{ - // start draining, vec can no longer be accessed - let mut drainer = vec.drain(..); - - // pull out two elements and immediately drop them - drainer.next(); - drainer.next(); - - // get rid of drainer, but don't call its destructor - mem::forget(drainer); -} - -// Oops, vec[0] was dropped, we're reading a pointer into free'd memory! -println!("{}", vec[0]); -``` - -This is pretty clearly Not Good. Unfortunately, we're kind of stuck between a -rock and a hard place: maintaining consistent state at every step has an -enormous cost (and would negate any benefits of the API). Failing to maintain -consistent state gives us Undefined Behavior in safe code (making the API -unsound). - -So what can we do? Well, we can pick a trivially consistent state: set the Vec's -len to be 0 when we start the iteration, and fix it up if necessary in the -destructor. That way, if everything executes like normal we get the desired -behavior with minimal overhead. But if someone has the *audacity* to -mem::forget us in the middle of the iteration, all that does is *leak even more* -(and possibly leave the Vec in an unexpected but otherwise consistent state). -Since we've accepted that mem::forget is safe, this is definitely safe. We call -leaks causing more leaks a *leak amplification*. - - - - -## Rc - -Rc is an interesting case because at first glance it doesn't appear to be a -proxy value at all. After all, it manages the data it points to, and dropping -all the Rcs for a value will drop that value. Leaking an Rc doesn't seem like it -would be particularly dangerous. It will leave the refcount permanently -incremented and prevent the data from being freed or dropped, but that seems -just like Box, right? - -Nope. - -Let's consider a simplified implementation of Rc: - -```rust,ignore -struct Rc { - ptr: *mut RcBox, -} - -struct RcBox { - data: T, - ref_count: usize, -} - -impl Rc { - fn new(data: T) -> Self { - unsafe { - // Wouldn't it be nice if heap::allocate worked like this? - let ptr = heap::allocate::>(); - ptr::write(ptr, RcBox { - data: data, - ref_count: 1, - }); - Rc { ptr: ptr } - } - } - - fn clone(&self) -> Self { - unsafe { - (*self.ptr).ref_count += 1; - } - Rc { ptr: self.ptr } - } -} - -impl Drop for Rc { - fn drop(&mut self) { - unsafe { - (*self.ptr).ref_count -= 1; - if (*self.ptr).ref_count == 0 { - // drop the data and then free it - ptr::read(self.ptr); - heap::deallocate(self.ptr); - } - } - } -} -``` - -This code contains an implicit and subtle assumption: `ref_count` can fit in a -`usize`, because there can't be more than `usize::MAX` Rcs in memory. However -this itself assumes that the `ref_count` accurately reflects the number of Rcs -in memory, which we know is false with `mem::forget`. Using `mem::forget` we can -overflow the `ref_count`, and then get it down to 0 with outstanding Rcs. Then -we can happily use-after-free the inner data. Bad Bad Not Good. - -This can be solved by just checking the `ref_count` and doing *something*. The -standard library's stance is to just abort, because your program has become -horribly degenerate. Also *oh my gosh* it's such a ridiculous corner case. - - - - -## thread::scoped::JoinGuard - -The thread::scoped API intends to allow threads to be spawned that reference -data on their parent's stack without any synchronization over that data by -ensuring the parent joins the thread before any of the shared data goes out -of scope. - -```rust,ignore -pub fn scoped<'a, F>(f: F) -> JoinGuard<'a> - where F: FnOnce() + Send + 'a -``` - -Here `f` is some closure for the other thread to execute. Saying that -`F: Send +'a` is saying that it closes over data that lives for `'a`, and it -either owns that data or the data was Sync (implying `&data` is Send). - -Because JoinGuard has a lifetime, it keeps all the data it closes over -borrowed in the parent thread. This means the JoinGuard can't outlive -the data that the other thread is working on. When the JoinGuard *does* get -dropped it blocks the parent thread, ensuring the child terminates before any -of the closed-over data goes out of scope in the parent. - -Usage looked like: - -```rust,ignore -let mut data = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]; -{ - let guards = vec![]; - for x in &mut data { - // Move the mutable reference into the closure, and execute - // it on a different thread. The closure has a lifetime bound - // by the lifetime of the mutable reference `x` we store in it. - // The guard that is returned is in turn assigned the lifetime - // of the closure, so it also mutably borrows `data` as `x` did. - // This means we cannot access `data` until the guard goes away. - let guard = thread::scoped(move || { - *x *= 2; - }); - // store the thread's guard for later - guards.push(guard); - } - // All guards are dropped here, forcing the threads to join - // (this thread blocks here until the others terminate). - // Once the threads join, the borrow expires and the data becomes - // accessible again in this thread. -} -// data is definitely mutated here. -``` - -In principle, this totally works! Rust's ownership system perfectly ensures it! -...except it relies on a destructor being called to be safe. - -```rust,ignore -let mut data = Box::new(0); -{ - let guard = thread::scoped(|| { - // This is at best a data race. At worst, it's also a use-after-free. - *data += 1; - }); - // Because the guard is forgotten, expiring the loan without blocking this - // thread. - mem::forget(guard); -} -// So the Box is dropped here while the scoped thread may or may not be trying -// to access it. -``` - -Dang. Here the destructor running was pretty fundamental to the API, and it had -to be scrapped in favor of a completely different design. diff --git a/src/doc/nomicon/src/lifetime-elision.md b/src/doc/nomicon/src/lifetime-elision.md deleted file mode 100644 index e92d735a01d69..0000000000000 --- a/src/doc/nomicon/src/lifetime-elision.md +++ /dev/null @@ -1,64 +0,0 @@ -# Lifetime Elision - -In order to make common patterns more ergonomic, Rust allows lifetimes to be -*elided* in function signatures. - -A *lifetime position* is anywhere you can write a lifetime in a type: - -```rust,ignore -&'a T -&'a mut T -T<'a> -``` - -Lifetime positions can appear as either "input" or "output": - -* For `fn` definitions, input refers to the types of the formal arguments - in the `fn` definition, while output refers to - result types. So `fn foo(s: &str) -> (&str, &str)` has elided one lifetime in - input position and two lifetimes in output position. - Note that the input positions of a `fn` method definition do not - include the lifetimes that occur in the method's `impl` header - (nor lifetimes that occur in the trait header, for a default method). - -* In the future, it should be possible to elide `impl` headers in the same manner. - -Elision rules are as follows: - -* Each elided lifetime in input position becomes a distinct lifetime - parameter. - -* If there is exactly one input lifetime position (elided or not), that lifetime - is assigned to *all* elided output lifetimes. - -* If there are multiple input lifetime positions, but one of them is `&self` or - `&mut self`, the lifetime of `self` is assigned to *all* elided output lifetimes. - -* Otherwise, it is an error to elide an output lifetime. - -Examples: - -```rust,ignore -fn print(s: &str); // elided -fn print<'a>(s: &'a str); // expanded - -fn debug(lvl: uint, s: &str); // elided -fn debug<'a>(lvl: uint, s: &'a str); // expanded - -fn substr(s: &str, until: uint) -> &str; // elided -fn substr<'a>(s: &'a str, until: uint) -> &'a str; // expanded - -fn get_str() -> &str; // ILLEGAL - -fn frob(s: &str, t: &str) -> &str; // ILLEGAL - -fn get_mut(&mut self) -> &mut T; // elided -fn get_mut<'a>(&'a mut self) -> &'a mut T; // expanded - -fn args(&mut self, args: &[T]) -> &mut Command // elided -fn args<'a, 'b, T: ToCStr>(&'a mut self, args: &'b [T]) -> &'a mut Command // expanded - -fn new(buf: &mut [u8]) -> BufWriter; // elided -fn new<'a>(buf: &'a mut [u8]) -> BufWriter<'a> // expanded - -``` diff --git a/src/doc/nomicon/src/lifetime-mismatch.md b/src/doc/nomicon/src/lifetime-mismatch.md deleted file mode 100644 index 30b4f09f9032d..0000000000000 --- a/src/doc/nomicon/src/lifetime-mismatch.md +++ /dev/null @@ -1,81 +0,0 @@ -# Limits of Lifetimes - -Given the following code: - -```rust,ignore -struct Foo; - -impl Foo { - fn mutate_and_share(&mut self) -> &Self { &*self } - fn share(&self) {} -} - -fn main() { - let mut foo = Foo; - let loan = foo.mutate_and_share(); - foo.share(); -} -``` - -One might expect it to compile. We call `mutate_and_share`, which mutably borrows -`foo` temporarily, but then returns only a shared reference. Therefore we -would expect `foo.share()` to succeed as `foo` shouldn't be mutably borrowed. - -However when we try to compile it: - -```text -:11:5: 11:8 error: cannot borrow `foo` as immutable because it is also borrowed as mutable -:11 foo.share(); - ^~~ -:10:16: 10:19 note: previous borrow of `foo` occurs here; the mutable borrow prevents subsequent moves, borrows, or modification of `foo` until the borrow ends -:10 let loan = foo.mutate_and_share(); - ^~~ -:12:2: 12:2 note: previous borrow ends here -:8 fn main() { -:9 let mut foo = Foo; -:10 let loan = foo.mutate_and_share(); -:11 foo.share(); -:12 } - ^ -``` - -What happened? Well, we got the exact same reasoning as we did for -[Example 2 in the previous section][ex2]. We desugar the program and we get -the following: - -```rust,ignore -struct Foo; - -impl Foo { - fn mutate_and_share<'a>(&'a mut self) -> &'a Self { &'a *self } - fn share<'a>(&'a self) {} -} - -fn main() { - 'b: { - let mut foo: Foo = Foo; - 'c: { - let loan: &'c Foo = Foo::mutate_and_share::<'c>(&'c mut foo); - 'd: { - Foo::share::<'d>(&'d foo); - } - } - } -} -``` - -The lifetime system is forced to extend the `&mut foo` to have lifetime `'c`, -due to the lifetime of `loan` and mutate_and_share's signature. Then when we -try to call `share`, and it sees we're trying to alias that `&'c mut foo` and -blows up in our face! - -This program is clearly correct according to the reference semantics we actually -care about, but the lifetime system is too coarse-grained to handle that. - - -TODO: other common problems? SEME regions stuff, mostly? - - - - -[ex2]: lifetimes.html#example-aliasing-a-mutable-reference diff --git a/src/doc/nomicon/src/lifetimes.md b/src/doc/nomicon/src/lifetimes.md deleted file mode 100644 index e2f0cc8677230..0000000000000 --- a/src/doc/nomicon/src/lifetimes.md +++ /dev/null @@ -1,215 +0,0 @@ -# Lifetimes - -Rust enforces these rules through *lifetimes*. Lifetimes are effectively -just names for scopes somewhere in the program. Each reference, -and anything that contains a reference, is tagged with a lifetime specifying -the scope it's valid for. - -Within a function body, Rust generally doesn't let you explicitly name the -lifetimes involved. This is because it's generally not really necessary -to talk about lifetimes in a local context; Rust has all the information and -can work out everything as optimally as possible. Many anonymous scopes and -temporaries that you would otherwise have to write are often introduced to -make your code Just Work. - -However once you cross the function boundary, you need to start talking about -lifetimes. Lifetimes are denoted with an apostrophe: `'a`, `'static`. To dip -our toes with lifetimes, we're going to pretend that we're actually allowed -to label scopes with lifetimes, and desugar the examples from the start of -this chapter. - -Originally, our examples made use of *aggressive* sugar -- high fructose corn -syrup even -- around scopes and lifetimes, because writing everything out -explicitly is *extremely noisy*. All Rust code relies on aggressive inference -and elision of "obvious" things. - -One particularly interesting piece of sugar is that each `let` statement implicitly -introduces a scope. For the most part, this doesn't really matter. However it -does matter for variables that refer to each other. As a simple example, let's -completely desugar this simple piece of Rust code: - -```rust -let x = 0; -let y = &x; -let z = &y; -``` - -The borrow checker always tries to minimize the extent of a lifetime, so it will -likely desugar to the following: - -```rust,ignore -// NOTE: `'a: {` and `&'b x` is not valid syntax! -'a: { - let x: i32 = 0; - 'b: { - // lifetime used is 'b because that's good enough. - let y: &'b i32 = &'b x; - 'c: { - // ditto on 'c - let z: &'c &'b i32 = &'c y; - } - } -} -``` - -Wow. That's... awful. Let's all take a moment to thank Rust for making this easier. - -Actually passing references to outer scopes will cause Rust to infer -a larger lifetime: - -```rust -let x = 0; -let z; -let y = &x; -z = y; -``` - -```rust,ignore -'a: { - let x: i32 = 0; - 'b: { - let z: &'b i32; - 'c: { - // Must use 'b here because this reference is - // being passed to that scope. - let y: &'b i32 = &'b x; - z = y; - } - } -} -``` - - - -# Example: references that outlive referents - -Alright, let's look at some of those examples from before: - -```rust,ignore -fn as_str(data: &u32) -> &str { - let s = format!("{}", data); - &s -} -``` - -desugars to: - -```rust,ignore -fn as_str<'a>(data: &'a u32) -> &'a str { - 'b: { - let s = format!("{}", data); - return &'a s; - } -} -``` - -This signature of `as_str` takes a reference to a u32 with *some* lifetime, and -promises that it can produce a reference to a str that can live *just as long*. -Already we can see why this signature might be trouble. That basically implies -that we're going to find a str somewhere in the scope the reference -to the u32 originated in, or somewhere *even earlier*. That's a bit of a tall -order. - -We then proceed to compute the string `s`, and return a reference to it. Since -the contract of our function says the reference must outlive `'a`, that's the -lifetime we infer for the reference. Unfortunately, `s` was defined in the -scope `'b`, so the only way this is sound is if `'b` contains `'a` -- which is -clearly false since `'a` must contain the function call itself. We have therefore -created a reference whose lifetime outlives its referent, which is *literally* -the first thing we said that references can't do. The compiler rightfully blows -up in our face. - -To make this more clear, we can expand the example: - -```rust,ignore -fn as_str<'a>(data: &'a u32) -> &'a str { - 'b: { - let s = format!("{}", data); - return &'a s - } -} - -fn main() { - 'c: { - let x: u32 = 0; - 'd: { - // An anonymous scope is introduced because the borrow does not - // need to last for the whole scope x is valid for. The return - // of as_str must find a str somewhere before this function - // call. Obviously not happening. - println!("{}", as_str::<'d>(&'d x)); - } - } -} -``` - -Shoot! - -Of course, the right way to write this function is as follows: - -```rust -fn to_string(data: &u32) -> String { - format!("{}", data) -} -``` - -We must produce an owned value inside the function to return it! The only way -we could have returned an `&'a str` would have been if it was in a field of the -`&'a u32`, which is obviously not the case. - -(Actually we could have also just returned a string literal, which as a global -can be considered to reside at the bottom of the stack; though this limits -our implementation *just a bit*.) - - - - - -# Example: aliasing a mutable reference - -How about the other example: - -```rust,ignore -let mut data = vec![1, 2, 3]; -let x = &data[0]; -data.push(4); -println!("{}", x); -``` - -```rust,ignore -'a: { - let mut data: Vec = vec![1, 2, 3]; - 'b: { - // 'b is as big as we need this borrow to be - // (just need to get to `println!`) - let x: &'b i32 = Index::index::<'b>(&'b data, 0); - 'c: { - // Temporary scope because we don't need the - // &mut to last any longer. - Vec::push(&'c mut data, 4); - } - println!("{}", x); - } -} -``` - -The problem here is a bit more subtle and interesting. We want Rust to -reject this program for the following reason: We have a live shared reference `x` -to a descendant of `data` when we try to take a mutable reference to `data` -to `push`. This would create an aliased mutable reference, which would -violate the *second* rule of references. - -However this is *not at all* how Rust reasons that this program is bad. Rust -doesn't understand that `x` is a reference to a subpath of `data`. It doesn't -understand Vec at all. What it *does* see is that `x` has to live for `'b` to -be printed. The signature of `Index::index` subsequently demands that the -reference we take to `data` has to survive for `'b`. When we try to call `push`, -it then sees us try to make an `&'c mut data`. Rust knows that `'c` is contained -within `'b`, and rejects our program because the `&'b data` must still be live! - -Here we see that the lifetime system is much more coarse than the reference -semantics we're actually interested in preserving. For the most part, *that's -totally ok*, because it keeps us from spending all day explaining our program -to the compiler. However it does mean that several programs that are totally -correct with respect to Rust's *true* semantics are rejected because lifetimes -are too dumb. diff --git a/src/doc/nomicon/src/meet-safe-and-unsafe.md b/src/doc/nomicon/src/meet-safe-and-unsafe.md deleted file mode 100644 index d42d0b6d7255c..0000000000000 --- a/src/doc/nomicon/src/meet-safe-and-unsafe.md +++ /dev/null @@ -1,98 +0,0 @@ -# Meet Safe and Unsafe - -Programmers in safe "high-level" languages face a fundamental dilemma. On one -hand, it would be *really* great to just say what you want and not worry about -how it's done. On the other hand, that can lead to unacceptably poor -performance. It may be necessary to drop down to less clear or idiomatic -practices to get the performance characteristics you want. Or maybe you just -throw up your hands in disgust and decide to shell out to an implementation in -a less sugary-wonderful *unsafe* language. - -Worse, when you want to talk directly to the operating system, you *have* to -talk to an unsafe language: *C*. C is ever-present and unavoidable. It's the -lingua-franca of the programming world. -Even other safe languages generally expose C interfaces for the world at large! -Regardless of why you're doing it, as soon as your program starts talking to -C it stops being safe. - -With that said, Rust is *totally* a safe programming language. - -Well, Rust *has* a safe programming language. Let's step back a bit. - -Rust can be thought of as being composed of two programming languages: *Safe -Rust* and *Unsafe Rust*. Safe Rust is For Reals Totally Safe. Unsafe Rust, -unsurprisingly, is *not* For Reals Totally Safe. In fact, Unsafe Rust lets you -do some really, *really* unsafe things. - -Safe Rust is the *true* Rust programming language. If all you do is write Safe -Rust, you will never have to worry about type-safety or memory-safety. You will -never endure a null or dangling pointer, or any of that Undefined Behavior -nonsense. - -*That's totally awesome.* - -The standard library also gives you enough utilities out-of-the-box that you'll -be able to write awesome high-performance applications and libraries in pure -idiomatic Safe Rust. - -But maybe you want to talk to another language. Maybe you're writing a -low-level abstraction not exposed by the standard library. Maybe you're -*writing* the standard library (which is written entirely in Rust). Maybe you -need to do something the type-system doesn't understand and just *frob some dang -bits*. Maybe you need Unsafe Rust. - -Unsafe Rust is exactly like Safe Rust with all the same rules and semantics. -However Unsafe Rust lets you do some *extra* things that are Definitely Not Safe. - -The only things that are different in Unsafe Rust are that you can: - -* Dereference raw pointers -* Call `unsafe` functions (including C functions, intrinsics, and the raw allocator) -* Implement `unsafe` traits -* Mutate statics - -That's it. The reason these operations are relegated to Unsafe is that misusing -any of these things will cause the ever dreaded Undefined Behavior. Invoking -Undefined Behavior gives the compiler full rights to do arbitrarily bad things -to your program. You definitely *should not* invoke Undefined Behavior. - -Unlike C, Undefined Behavior is pretty limited in scope in Rust. All the core -language cares about is preventing the following things: - -* Dereferencing null or dangling pointers -* Reading [uninitialized memory] -* Breaking the [pointer aliasing rules] -* Producing invalid primitive values: - * dangling/null references - * a `bool` that isn't 0 or 1 - * an undefined `enum` discriminant - * a `char` outside the ranges [0x0, 0xD7FF] and [0xE000, 0x10FFFF] - * A non-utf8 `str` -* Unwinding into another language -* Causing a [data race][race] - -That's it. That's all the causes of Undefined Behavior baked into Rust. Of -course, unsafe functions and traits are free to declare arbitrary other -constraints that a program must maintain to avoid Undefined Behavior. However, -generally violations of these constraints will just transitively lead to one of -the above problems. Some additional constraints may also derive from compiler -intrinsics that make special assumptions about how code can be optimized. - -Rust is otherwise quite permissive with respect to other dubious operations. -Rust considers it "safe" to: - -* Deadlock -* Have a [race condition][race] -* Leak memory -* Fail to call destructors -* Overflow integers -* Abort the program -* Delete the production database - -However any program that actually manages to do such a thing is *probably* -incorrect. Rust provides lots of tools to make these things rare, but -these problems are considered impractical to categorically prevent. - -[pointer aliasing rules]: references.html -[uninitialized memory]: uninitialized.html -[race]: races.html diff --git a/src/doc/nomicon/src/obrm.md b/src/doc/nomicon/src/obrm.md deleted file mode 100644 index 19e5ec382595c..0000000000000 --- a/src/doc/nomicon/src/obrm.md +++ /dev/null @@ -1,14 +0,0 @@ -# The Perils Of Ownership Based Resource Management (OBRM) - -OBRM (AKA RAII: Resource Acquisition Is Initialization) is something you'll -interact with a lot in Rust. Especially if you use the standard library. - -Roughly speaking the pattern is as follows: to acquire a resource, you create an -object that manages it. To release the resource, you simply destroy the object, -and it cleans up the resource for you. The most common "resource" this pattern -manages is simply *memory*. `Box`, `Rc`, and basically everything in -`std::collections` is a convenience to enable correctly managing memory. This is -particularly important in Rust because we have no pervasive GC to rely on for -memory management. Which is the point, really: Rust is about control. However we -are not limited to just memory. Pretty much every other system resource like a -thread, file, or socket is exposed through this kind of API. diff --git a/src/doc/nomicon/src/other-reprs.md b/src/doc/nomicon/src/other-reprs.md deleted file mode 100644 index 02f39e3c4dd27..0000000000000 --- a/src/doc/nomicon/src/other-reprs.md +++ /dev/null @@ -1,79 +0,0 @@ -# Alternative representations - -Rust allows you to specify alternative data layout strategies from the default. - - - - -# repr(C) - -This is the most important `repr`. It has fairly simple intent: do what C does. -The order, size, and alignment of fields is exactly what you would expect from C -or C++. Any type you expect to pass through an FFI boundary should have -`repr(C)`, as C is the lingua-franca of the programming world. This is also -necessary to soundly do more elaborate tricks with data layout such as -reinterpreting values as a different type. - -However, the interaction with Rust's more exotic data layout features must be -kept in mind. Due to its dual purpose as "for FFI" and "for layout control", -`repr(C)` can be applied to types that will be nonsensical or problematic if -passed through the FFI boundary. - -* ZSTs are still zero-sized, even though this is not a standard behavior in -C, and is explicitly contrary to the behavior of an empty type in C++, which -still consumes a byte of space. - -* DSTs, tuples, and tagged unions are not a concept in C and as such are never -FFI safe. - -* Tuple structs are like structs with regards to `repr(C)`, as the only - difference from a struct is that the fields aren’t named. - -* **If the type would have any [drop flags], they will still be added** - -* This is equivalent to one of `repr(u*)` (see the next section) for enums. The -chosen size is the default enum size for the target platform's C ABI. Note that -enum representation in C is implementation defined, so this is really a "best -guess". In particular, this may be incorrect when the C code of interest is -compiled with certain flags. - - - -# repr(u8), repr(u16), repr(u32), repr(u64) - -These specify the size to make a C-like enum. If the discriminant overflows the -integer it has to fit in, it will produce a compile-time error. You can manually -ask Rust to allow this by setting the overflowing element to explicitly be 0. -However Rust will not allow you to create an enum where two variants have the -same discriminant. - -On non-C-like enums, this will inhibit certain optimizations like the null- -pointer optimization. - -These reprs have no effect on a struct. - - - - -# repr(packed) - -`repr(packed)` forces Rust to strip any padding, and only align the type to a -byte. This may improve the memory footprint, but will likely have other negative -side-effects. - -In particular, most architectures *strongly* prefer values to be aligned. This -may mean the unaligned loads are penalized (x86), or even fault (some ARM -chips). For simple cases like directly loading or storing a packed field, the -compiler might be able to paper over alignment issues with shifts and masks. -However if you take a reference to a packed field, it's unlikely that the -compiler will be able to emit code to avoid an unaligned load. - -**[As of Rust 1.0 this can cause undefined behavior.][ub loads]** - -`repr(packed)` is not to be used lightly. Unless you have extreme requirements, -this should not be used. - -This repr is a modifier on `repr(C)` and `repr(rust)`. - -[drop flags]: drop-flags.html -[ub loads]: https://github.com/rust-lang/rust/issues/27060 diff --git a/src/doc/nomicon/src/ownership.md b/src/doc/nomicon/src/ownership.md deleted file mode 100644 index dd9e9db244a81..0000000000000 --- a/src/doc/nomicon/src/ownership.md +++ /dev/null @@ -1,66 +0,0 @@ -# Ownership and Lifetimes - -Ownership is the breakout feature of Rust. It allows Rust to be completely -memory-safe and efficient, while avoiding garbage collection. Before getting -into the ownership system in detail, we will consider the motivation of this -design. - -We will assume that you accept that garbage collection (GC) is not always an -optimal solution, and that it is desirable to manually manage memory in some -contexts. If you do not accept this, might I interest you in a different -language? - -Regardless of your feelings on GC, it is pretty clearly a *massive* boon to -making code safe. You never have to worry about things going away *too soon* -(although whether you still wanted to be pointing at that thing is a different -issue...). This is a pervasive problem that C and C++ programs need to deal -with. Consider this simple mistake that all of us who have used a non-GC'd -language have made at one point: - -```rust,ignore -fn as_str(data: &u32) -> &str { - // compute the string - let s = format!("{}", data); - - // OH NO! We returned a reference to something that - // exists only in this function! - // Dangling pointer! Use after free! Alas! - // (this does not compile in Rust) - &s -} -``` - -This is exactly what Rust's ownership system was built to solve. -Rust knows the scope in which the `&s` lives, and as such can prevent it from -escaping. However this is a simple case that even a C compiler could plausibly -catch. Things get more complicated as code gets bigger and pointers get fed through -various functions. Eventually, a C compiler will fall down and won't be able to -perform sufficient escape analysis to prove your code unsound. It will consequently -be forced to accept your program on the assumption that it is correct. - -This will never happen to Rust. It's up to the programmer to prove to the -compiler that everything is sound. - -Of course, Rust's story around ownership is much more complicated than just -verifying that references don't escape the scope of their referent. That's -because ensuring pointers are always valid is much more complicated than this. -For instance in this code, - -```rust,ignore -let mut data = vec![1, 2, 3]; -// get an internal reference -let x = &data[0]; - -// OH NO! `push` causes the backing storage of `data` to be reallocated. -// Dangling pointer! Use after free! Alas! -// (this does not compile in Rust) -data.push(4); - -println!("{}", x); -``` - -naive scope analysis would be insufficient to prevent this bug, because `data` -does in fact live as long as we needed. However it was *changed* while we had -a reference into it. This is why Rust requires any references to freeze the -referent and its owners. - diff --git a/src/doc/nomicon/src/phantom-data.md b/src/doc/nomicon/src/phantom-data.md deleted file mode 100644 index 32539c2d01f6d..0000000000000 --- a/src/doc/nomicon/src/phantom-data.md +++ /dev/null @@ -1,104 +0,0 @@ -# PhantomData - -When working with unsafe code, we can often end up in a situation where -types or lifetimes are logically associated with a struct, but not actually -part of a field. This most commonly occurs with lifetimes. For instance, the -`Iter` for `&'a [T]` is (approximately) defined as follows: - -```rust,ignore -struct Iter<'a, T: 'a> { - ptr: *const T, - end: *const T, -} -``` - -However because `'a` is unused within the struct's body, it's *unbounded*. -Because of the troubles this has historically caused, unbounded lifetimes and -types are *forbidden* in struct definitions. Therefore we must somehow refer -to these types in the body. Correctly doing this is necessary to have -correct variance and drop checking. - -We do this using `PhantomData`, which is a special marker type. `PhantomData` -consumes no space, but simulates a field of the given type for the purpose of -static analysis. This was deemed to be less error-prone than explicitly telling -the type-system the kind of variance that you want, while also providing other -useful such as the information needed by drop check. - -Iter logically contains a bunch of `&'a T`s, so this is exactly what we tell -the PhantomData to simulate: - -``` -use std::marker; - -struct Iter<'a, T: 'a> { - ptr: *const T, - end: *const T, - _marker: marker::PhantomData<&'a T>, -} -``` - -and that's it. The lifetime will be bounded, and your iterator will be variant -over `'a` and `T`. Everything Just Works. - -Another important example is Vec, which is (approximately) defined as follows: - -``` -struct Vec { - data: *const T, // *const for variance! - len: usize, - cap: usize, -} -``` - -Unlike the previous example, it *appears* that everything is exactly as we -want. Every generic argument to Vec shows up in at least one field. -Good to go! - -Nope. - -The drop checker will generously determine that `Vec` does not own any values -of type T. This will in turn make it conclude that it doesn't need to worry -about Vec dropping any T's in its destructor for determining drop check -soundness. This will in turn allow people to create unsoundness using -Vec's destructor. - -In order to tell dropck that we *do* own values of type T, and therefore may -drop some T's when *we* drop, we must add an extra PhantomData saying exactly -that: - -``` -use std::marker; - -struct Vec { - data: *const T, // *const for covariance! - len: usize, - cap: usize, - _marker: marker::PhantomData, -} -``` - -Raw pointers that own an allocation is such a pervasive pattern that the -standard library made a utility for itself called `Unique` which: - -* wraps a `*const T` for variance -* includes a `PhantomData` -* auto-derives `Send`/`Sync` as if T was contained -* marks the pointer as `NonZero` for the null-pointer optimization - -## Table of `PhantomData` patterns - -Here’s a table of all the wonderful ways `PhantomData` could be used: - -| Phantom type | `'a` | `T` | -|-----------------------------|-----------|---------------------------| -| `PhantomData` | - | variant (with drop check) | -| `PhantomData<&'a T>` | variant | variant | -| `PhantomData<&'a mut T>` | variant | invariant | -| `PhantomData<*const T>` | - | variant | -| `PhantomData<*mut T>` | - | invariant | -| `PhantomData` | - | contravariant (*) | -| `PhantomData T>` | - | variant | -| `PhantomData T>` | - | invariant | -| `PhantomData>` | invariant | - | - -(*) If contravariance gets scrapped, this would be invariant. diff --git a/src/doc/nomicon/src/poisoning.md b/src/doc/nomicon/src/poisoning.md deleted file mode 100644 index 9b5dec3eec384..0000000000000 --- a/src/doc/nomicon/src/poisoning.md +++ /dev/null @@ -1,35 +0,0 @@ -# Poisoning - -Although all unsafe code *must* ensure it has minimal exception safety, not all -types ensure *maximal* exception safety. Even if the type does, your code may -ascribe additional meaning to it. For instance, an integer is certainly -exception-safe, but has no semantics on its own. It's possible that code that -panics could fail to correctly update the integer, producing an inconsistent -program state. - -This is *usually* fine, because anything that witnesses an exception is about -to get destroyed. For instance, if you send a Vec to another thread and that -thread panics, it doesn't matter if the Vec is in a weird state. It will be -dropped and go away forever. However some types are especially good at smuggling -values across the panic boundary. - -These types may choose to explicitly *poison* themselves if they witness a panic. -Poisoning doesn't entail anything in particular. Generally it just means -preventing normal usage from proceeding. The most notable example of this is the -standard library's Mutex type. A Mutex will poison itself if one of its -MutexGuards (the thing it returns when a lock is obtained) is dropped during a -panic. Any future attempts to lock the Mutex will return an `Err` or panic. - -Mutex poisons not for true safety in the sense that Rust normally cares about. It -poisons as a safety-guard against blindly using the data that comes out of a Mutex -that has witnessed a panic while locked. The data in such a Mutex was likely in the -middle of being modified, and as such may be in an inconsistent or incomplete state. -It is important to note that one cannot violate memory safety with such a type -if it is correctly written. After all, it must be minimally exception-safe! - -However if the Mutex contained, say, a BinaryHeap that does not actually have the -heap property, it's unlikely that any code that uses it will do -what the author intended. As such, the program should not proceed normally. -Still, if you're double-plus-sure that you can do *something* with the value, -the Mutex exposes a method to get the lock anyway. It *is* safe, after all. -Just maybe nonsense. diff --git a/src/doc/nomicon/src/races.md b/src/doc/nomicon/src/races.md deleted file mode 100644 index c9b8c3d01b2f8..0000000000000 --- a/src/doc/nomicon/src/races.md +++ /dev/null @@ -1,86 +0,0 @@ -# Data Races and Race Conditions - -Safe Rust guarantees an absence of data races, which are defined as: - -* two or more threads concurrently accessing a location of memory -* one of them is a write -* one of them is unsynchronized - -A data race has Undefined Behavior, and is therefore impossible to perform -in Safe Rust. Data races are *mostly* prevented through rust's ownership system: -it's impossible to alias a mutable reference, so it's impossible to perform a -data race. Interior mutability makes this more complicated, which is largely why -we have the Send and Sync traits (see below). - -**However Rust does not prevent general race conditions.** - -This is pretty fundamentally impossible, and probably honestly undesirable. Your -hardware is racy, your OS is racy, the other programs on your computer are racy, -and the world this all runs in is racy. Any system that could genuinely claim to -prevent *all* race conditions would be pretty awful to use, if not just -incorrect. - -So it's perfectly "fine" for a Safe Rust program to get deadlocked or do -something nonsensical with incorrect synchronization. Obviously such a program -isn't very good, but Rust can only hold your hand so far. Still, a race -condition can't violate memory safety in a Rust program on its own. Only in -conjunction with some other unsafe code can a race condition actually violate -memory safety. For instance: - -```rust,no_run -use std::thread; -use std::sync::atomic::{AtomicUsize, Ordering}; -use std::sync::Arc; - -let data = vec![1, 2, 3, 4]; -// Arc so that the memory the AtomicUsize is stored in still exists for -// the other thread to increment, even if we completely finish executing -// before it. Rust won't compile the program without it, because of the -// lifetime requirements of thread::spawn! -let idx = Arc::new(AtomicUsize::new(0)); -let other_idx = idx.clone(); - -// `move` captures other_idx by-value, moving it into this thread -thread::spawn(move || { - // It's ok to mutate idx because this value - // is an atomic, so it can't cause a Data Race. - other_idx.fetch_add(10, Ordering::SeqCst); -}); - -// Index with the value loaded from the atomic. This is safe because we -// read the atomic memory only once, and then pass a copy of that value -// to the Vec's indexing implementation. This indexing will be correctly -// bounds checked, and there's no chance of the value getting changed -// in the middle. However our program may panic if the thread we spawned -// managed to increment before this ran. A race condition because correct -// program execution (panicking is rarely correct) depends on order of -// thread execution. -println!("{}", data[idx.load(Ordering::SeqCst)]); -``` - -```rust,no_run -use std::thread; -use std::sync::atomic::{AtomicUsize, Ordering}; -use std::sync::Arc; - -let data = vec![1, 2, 3, 4]; - -let idx = Arc::new(AtomicUsize::new(0)); -let other_idx = idx.clone(); - -// `move` captures other_idx by-value, moving it into this thread -thread::spawn(move || { - // It's ok to mutate idx because this value - // is an atomic, so it can't cause a Data Race. - other_idx.fetch_add(10, Ordering::SeqCst); -}); - -if idx.load(Ordering::SeqCst) < data.len() { - unsafe { - // Incorrectly loading the idx after we did the bounds check. - // It could have changed. This is a race condition, *and dangerous* - // because we decided to do `get_unchecked`, which is `unsafe`. - println!("{}", data.get_unchecked(idx.load(Ordering::SeqCst))); - } -} -``` diff --git a/src/doc/nomicon/src/references.md b/src/doc/nomicon/src/references.md deleted file mode 100644 index 5d80f1edd964a..0000000000000 --- a/src/doc/nomicon/src/references.md +++ /dev/null @@ -1,177 +0,0 @@ -# References - -This section gives a high-level view of the memory model that *all* Rust -programs must satisfy to be correct. Safe code is statically verified -to obey this model by the borrow checker. Unsafe code may go above -and beyond the borrow checker while still satisfying this model. The borrow -checker may also be extended to allow more programs to compile, as long as -this more fundamental model is satisfied. - -There are two kinds of reference: - -* Shared reference: `&` -* Mutable reference: `&mut` - -Which obey the following rules: - -* A reference cannot outlive its referent -* A mutable reference cannot be aliased - -That's it. That's the whole model. Of course, we should probably define -what *aliased* means. To define aliasing, we must define the notion of -*paths* and *liveness*. - - -**NOTE: The model that follows is generally agreed to be dubious and have -issues. It's ok-ish as an intuitive model, but fails to capture the desired -semantics. We leave this here to be able to use notions introduced here in later -sections. This will be significantly changed in the future. TODO: do that.** - - -# Paths - -If all Rust had were values (no pointers), then every value would be uniquely -owned by a variable or composite structure. From this we naturally derive a -*tree* of ownership. The stack itself is the root of the tree, with every -variable as its direct children. Each variable's direct children would be their -fields (if any), and so on. - -From this view, every value in Rust has a unique *path* in the tree of -ownership. Of particular interest are *ancestors* and *descendants*: if `x` owns -`y`, then `x` is an ancestor of `y`, and `y` is a descendant of `x`. Note -that this is an inclusive relationship: `x` is a descendant and ancestor of -itself. - -We can then define references as simply *names* for paths. When you create a -reference, you're declaring that an ownership path exists to this address -of memory. - -Tragically, plenty of data doesn't reside on the stack, and we must also -accommodate this. Globals and thread-locals are simple enough to model as -residing at the bottom of the stack (though we must be careful with mutable -globals). Data on the heap poses a different problem. - -If all Rust had on the heap was data uniquely owned by a pointer on the stack, -then we could just treat such a pointer as a struct that owns the value on the -heap. Box, Vec, String, and HashMap, are examples of types which uniquely -own data on the heap. - -Unfortunately, data on the heap is not *always* uniquely owned. Rc for instance -introduces a notion of *shared* ownership. Shared ownership of a value means -there is no unique path to it. A value with no unique path limits what we can do -with it. - -In general, only shared references can be created to non-unique paths. However -mechanisms which ensure mutual exclusion may establish One True Owner -temporarily, establishing a unique path to that value (and therefore all -its children). If this is done, the value may be mutated. In particular, a -mutable reference can be taken. - -The most common way to establish such a path is through *interior mutability*, -in contrast to the *inherited mutability* that everything in Rust normally uses. -Cell, RefCell, Mutex, and RWLock are all examples of interior mutability types. -These types provide exclusive access through runtime restrictions. - -An interesting case of this effect is Rc itself: if an Rc has refcount 1, -then it is safe to mutate or even move its internals. Note however that the -refcount itself uses interior mutability. - -In order to correctly communicate to the type system that a variable or field of -a struct can have interior mutability, it must be wrapped in an UnsafeCell. This -does not in itself make it safe to perform interior mutability operations on -that value. You still must yourself ensure that mutual exclusion is upheld. - - - - -# Liveness - -Note: Liveness is not the same thing as a *lifetime*, which will be explained -in detail in the next section of this chapter. - -Roughly, a reference is *live* at some point in a program if it can be -dereferenced. Shared references are always live unless they are literally -unreachable (for instance, they reside in freed or leaked memory). Mutable -references can be reachable but *not* live through the process of *reborrowing*. - -A mutable reference can be reborrowed to either a shared or mutable reference to -one of its descendants. A reborrowed reference will only be live again once all -reborrows derived from it expire. For instance, a mutable reference can be -reborrowed to point to a field of its referent: - -```rust -let x = &mut (1, 2); -{ - // reborrow x to a subfield - let y = &mut x.0; - // y is now live, but x isn't - *y = 3; -} -// y goes out of scope, so x is live again -*x = (5, 7); -``` - -It is also possible to reborrow into *multiple* mutable references, as long as -they are *disjoint*: no reference is an ancestor of another. Rust -explicitly enables this to be done with disjoint struct fields, because -disjointness can be statically proven: - -```rust -let x = &mut (1, 2); -{ - // reborrow x to two disjoint subfields - let y = &mut x.0; - let z = &mut x.1; - - // y and z are now live, but x isn't - *y = 3; - *z = 4; -} -// y and z go out of scope, so x is live again -*x = (5, 7); -``` - -However it's often the case that Rust isn't sufficiently smart to prove that -multiple borrows are disjoint. *This does not mean it is fundamentally illegal -to make such a borrow*, just that Rust isn't as smart as you want. - -To simplify things, we can model variables as a fake type of reference: *owned* -references. Owned references have much the same semantics as mutable references: -they can be re-borrowed in a mutable or shared manner, which makes them no -longer live. Live owned references have the unique property that they can be -moved out of (though mutable references *can* be swapped out of). This power is -only given to *live* owned references because moving its referent would of -course invalidate all outstanding references prematurely. - -As a local lint against inappropriate mutation, only variables that are marked -as `mut` can be borrowed mutably. - -It is interesting to note that Box behaves exactly like an owned reference. It -can be moved out of, and Rust understands it sufficiently to reason about its -paths like a normal variable. - - - - -# Aliasing - -With liveness and paths defined, we can now properly define *aliasing*: - -**A mutable reference is aliased if there exists another live reference to one -of its ancestors or descendants.** - -(If you prefer, you may also say the two live references alias *each other*. -This has no semantic consequences, but is probably a more useful notion when -verifying the soundness of a construct.) - -That's it. Super simple right? Except for the fact that it took us two pages to -define all of the terms in that definition. You know: Super. Simple. - -Actually it's a bit more complicated than that. In addition to references, Rust -has *raw pointers*: `*const T` and `*mut T`. Raw pointers have no inherent -ownership or aliasing semantics. As a result, Rust makes absolutely no effort to -track that they are used correctly, and they are wildly unsafe. - -**It is an open question to what degree raw pointers have alias semantics. -However it is important for these definitions to be sound that the existence of -a raw pointer does not imply some kind of live path.** diff --git a/src/doc/nomicon/src/repr-rust.md b/src/doc/nomicon/src/repr-rust.md deleted file mode 100644 index c02cf44189f1a..0000000000000 --- a/src/doc/nomicon/src/repr-rust.md +++ /dev/null @@ -1,154 +0,0 @@ -# repr(Rust) - -First and foremost, all types have an alignment specified in bytes. The -alignment of a type specifies what addresses are valid to store the value at. A -value of alignment `n` must only be stored at an address that is a multiple of -`n`. So alignment 2 means you must be stored at an even address, and 1 means -that you can be stored anywhere. Alignment is at least 1, and always a power of -2. Most primitives are generally aligned to their size, although this is -platform-specific behavior. In particular, on x86 `u64` and `f64` may be only -aligned to 32 bits. - -A type's size must always be a multiple of its alignment. This ensures that an -array of that type may always be indexed by offsetting by a multiple of its -size. Note that the size and alignment of a type may not be known -statically in the case of [dynamically sized types][dst]. - -Rust gives you the following ways to lay out composite data: - -* structs (named product types) -* tuples (anonymous product types) -* arrays (homogeneous product types) -* enums (named sum types -- tagged unions) - -An enum is said to be *C-like* if none of its variants have associated data. - -Composite structures will have an alignment equal to the maximum -of their fields' alignment. Rust will consequently insert padding where -necessary to ensure that all fields are properly aligned and that the overall -type's size is a multiple of its alignment. For instance: - -```rust -struct A { - a: u8, - b: u32, - c: u16, -} -``` - -will be 32-bit aligned on an architecture that aligns these primitives to their -respective sizes. The whole struct will therefore have a size that is a multiple -of 32-bits. It will potentially become: - -```rust -struct A { - a: u8, - _pad1: [u8; 3], // to align `b` - b: u32, - c: u16, - _pad2: [u8; 2], // to make overall size multiple of 4 -} -``` - -There is *no indirection* for these types; all data is stored within the struct, -as you would expect in C. However with the exception of arrays (which are -densely packed and in-order), the layout of data is not by default specified in -Rust. Given the two following struct definitions: - -```rust -struct A { - a: i32, - b: u64, -} - -struct B { - a: i32, - b: u64, -} -``` - -Rust *does* guarantee that two instances of A have their data laid out in -exactly the same way. However Rust *does not* currently guarantee that an -instance of A has the same field ordering or padding as an instance of B, though -in practice there's no reason why they wouldn't. - -With A and B as written, this point would seem to be pedantic, but several other -features of Rust make it desirable for the language to play with data layout in -complex ways. - -For instance, consider this struct: - -```rust -struct Foo { - count: u16, - data1: T, - data2: U, -} -``` - -Now consider the monomorphizations of `Foo` and `Foo`. If -Rust lays out the fields in the order specified, we expect it to pad the -values in the struct to satisfy their alignment requirements. So if Rust -didn't reorder fields, we would expect it to produce the following: - -```rust,ignore -struct Foo { - count: u16, - data1: u16, - data2: u32, -} - -struct Foo { - count: u16, - _pad1: u16, - data1: u32, - data2: u16, - _pad2: u16, -} -``` - -The latter case quite simply wastes space. An optimal use of space therefore -requires different monomorphizations to have *different field orderings*. - -**Note: this is a hypothetical optimization that is not yet implemented in Rust -1.0** - -Enums make this consideration even more complicated. Naively, an enum such as: - -```rust -enum Foo { - A(u32), - B(u64), - C(u8), -} -``` - -would be laid out as: - -```rust -struct FooRepr { - data: u64, // this is either a u64, u32, or u8 based on `tag` - tag: u8, // 0 = A, 1 = B, 2 = C -} -``` - -And indeed this is approximately how it would be laid out in general (modulo the -size and position of `tag`). - -However there are several cases where such a representation is inefficient. The -classic case of this is Rust's "null pointer optimization": an enum consisting -of a single outer unit variant (e.g. `None`) and a (potentially nested) non- -nullable pointer variant (e.g. `&T`) makes the tag unnecessary, because a null -pointer value can safely be interpreted to mean that the unit variant is chosen -instead. The net result is that, for example, `size_of::>() == -size_of::<&T>()`. - -There are many types in Rust that are, or contain, non-nullable pointers such as -`Box`, `Vec`, `String`, `&T`, and `&mut T`. Similarly, one can imagine -nested enums pooling their tags into a single discriminant, as they are by -definition known to have a limited range of valid values. In principle enums could -use fairly elaborate algorithms to cache bits throughout nested types with -special constrained representations. As such it is *especially* desirable that -we leave enum layout unspecified today. - -[dst]: exotic-sizes.html#dynamically-sized-types-dsts diff --git a/src/doc/nomicon/src/safe-unsafe-meaning.md b/src/doc/nomicon/src/safe-unsafe-meaning.md deleted file mode 100644 index 0a655a3f53a21..0000000000000 --- a/src/doc/nomicon/src/safe-unsafe-meaning.md +++ /dev/null @@ -1,123 +0,0 @@ -# How Safe and Unsafe Interact - -What's the relationship between Safe Rust and Unsafe Rust? How do they -interact? - -The separation between Safe Rust and Unsafe Rust is controlled with the -`unsafe` keyword, which acts as an interface from one to the other. This is -why we can say Safe Rust is a safe language: all the unsafe parts are kept -exclusively behind the boundary. - -The `unsafe` keyword has two uses: to declare the existence of contracts the -compiler can't check, and to declare that the adherence of some code to -those contracts has been checked by the programmer. - -You can use `unsafe` to indicate the existence of unchecked contracts on -_functions_ and on _trait declarations_. On functions, `unsafe` means that -users of the function must check that function's documentation to ensure -they are using it in a way that maintains the contracts the function -requires. On trait declarations, `unsafe` means that implementors of the -trait must check the trait documentation to ensure their implementation -maintains the contracts the trait requires. - -You can use `unsafe` on a block to declare that all constraints required -by an unsafe function within the block have been adhered to, and the code -can therefore be trusted. You can use `unsafe` on a trait implementation -to declare that the implementation of that trait has adhered to whatever -contracts the trait's documentation requires. - -The standard library has a number of unsafe functions, including: - -* `slice::get_unchecked`, which performs unchecked indexing, allowing - memory safety to be freely violated. -* `mem::transmute` reinterprets some value as having a given type, bypassing - type safety in arbitrary ways (see [conversions] for details). -* Every raw pointer to a sized type has an intrinstic `offset` method that - invokes Undefined Behavior if the passed offset is not "in bounds" as - defined by LLVM. -* All FFI functions are `unsafe` because the other language can do arbitrary - operations that the Rust compiler can't check. - -As of Rust 1.0 there are exactly two unsafe traits: - -* `Send` is a marker trait (a trait with no API) that promises implementors are - safe to send (move) to another thread. -* `Sync` is a marker trait that promises threads can safely share implementors - through a shared reference. - -Much of the Rust standard library also uses Unsafe Rust internally, although -these implementations are rigorously manually checked, and the Safe Rust -interfaces provided on top of these implementations can be assumed to be safe. - -The need for all of this separation boils down a single fundamental property -of Safe Rust: - -**No matter what, Safe Rust can't cause Undefined Behavior.** - -The design of the safe/unsafe split means that Safe Rust inherently has to -trust that any Unsafe Rust it touches has been written correctly (meaning -the Unsafe Rust actually maintains whatever contracts it is supposed to -maintain). On the other hand, Unsafe Rust has to be very careful about -trusting Safe Rust. - -As an example, Rust has the `PartialOrd` and `Ord` traits to differentiate -between types which can "just" be compared, and those that provide a total -ordering (where every value of the type is either equal to, greater than, -or less than any other value of the same type). The sorted map type -`BTreeMap` doesn't make sense for partially-ordered types, and so it -requires that any key type for it implements the `Ord` trait. However, -`BTreeMap` has Unsafe Rust code inside of its implementation, and this -Unsafe Rust code cannot assume that any `Ord` implementation it gets makes -sense. The unsafe portions of `BTreeMap`'s internals have to be careful to -maintain all necessary contracts, even if a key type's `Ord` implementation -does not implement a total ordering. - -Unsafe Rust cannot automatically trust Safe Rust. When writing Unsafe Rust, -you must be careful to only rely on specific Safe Rust code, and not make -assumptions about potential future Safe Rust code providing the same -guarantees. - -This is the problem that `unsafe` traits exist to resolve. The `BTreeMap` -type could theoretically require that keys implement a new trait called -`UnsafeOrd`, rather than `Ord`, that might look like this: - -```rust -use std::cmp::Ordering; - -unsafe trait UnsafeOrd { - fn cmp(&self, other: &Self) -> Ordering; -} -``` - -Then, a type would use `unsafe` to implement `UnsafeOrd`, indicating that -they've ensured their implementation maintains whatever contracts the -trait expects. In this situation, the Unsafe Rust in the internals of -`BTreeMap` could trust that the key type's `UnsafeOrd` implementation is -correct. If it isn't, it's the fault of the unsafe trait implementation -code, which is consistent with Rust's safety guarantees. - -The decision of whether to mark a trait `unsafe` is an API design choice. -Rust has traditionally avoided marking traits unsafe because it makes Unsafe -Rust pervasive, which is not desirable. `Send` and `Sync` are marked unsafe -because thread safety is a *fundamental property* that unsafe code can't -possibly hope to defend against in the way it could defend against a bad -`Ord` implementation. The decision of whether to mark your own traits `unsafe` -depends on the same sort of consideration. If `unsafe` code cannot reasonably -expect to defend against a bad implementation of the trait, then marking the -trait `unsafe` is a reasonable choice. - -As an aside, while `Send` and `Sync` are `unsafe` traits, they are -automatically implemented for types when such derivations are provably safe -to do. `Send` is automatically derived for all types composed only of values -whose types also implement `Send`. `Sync` is automatically derived for all -types composed only of values whose types also implement `Sync`. - -This is the dance of Safe Rust and Unsafe Rust. It is designed to make using -Safe Rust as ergonomic as possible, but requires extra effort and care when -writing Unsafe Rust. The rest of the book is largely a discussion of the sort -of care that must be taken, and what contracts it is expected of Unsafe Rust -to uphold. - -[drop flags]: drop-flags.html -[conversions]: conversions.html - diff --git a/src/doc/nomicon/src/send-and-sync.md b/src/doc/nomicon/src/send-and-sync.md deleted file mode 100644 index 959f870d4e645..0000000000000 --- a/src/doc/nomicon/src/send-and-sync.md +++ /dev/null @@ -1,80 +0,0 @@ -# Send and Sync - -Not everything obeys inherited mutability, though. Some types allow you to -multiply alias a location in memory while mutating it. Unless these types use -synchronization to manage this access, they are absolutely not thread safe. Rust -captures this through the `Send` and `Sync` traits. - -* A type is Send if it is safe to send it to another thread. -* A type is Sync if it is safe to share between threads (`&T` is Send). - -Send and Sync are fundamental to Rust's concurrency story. As such, a -substantial amount of special tooling exists to make them work right. First and -foremost, they're [unsafe traits]. This means that they are unsafe to -implement, and other unsafe code can assume that they are correctly -implemented. Since they're *marker traits* (they have no associated items like -methods), correctly implemented simply means that they have the intrinsic -properties an implementor should have. Incorrectly implementing Send or Sync can -cause Undefined Behavior. - -Send and Sync are also automatically derived traits. This means that, unlike -every other trait, if a type is composed entirely of Send or Sync types, then it -is Send or Sync. Almost all primitives are Send and Sync, and as a consequence -pretty much all types you'll ever interact with are Send and Sync. - -Major exceptions include: - -* raw pointers are neither Send nor Sync (because they have no safety guards). -* `UnsafeCell` isn't Sync (and therefore `Cell` and `RefCell` aren't). -* `Rc` isn't Send or Sync (because the refcount is shared and unsynchronized). - -`Rc` and `UnsafeCell` are very fundamentally not thread-safe: they enable -unsynchronized shared mutable state. However raw pointers are, strictly -speaking, marked as thread-unsafe as more of a *lint*. Doing anything useful -with a raw pointer requires dereferencing it, which is already unsafe. In that -sense, one could argue that it would be "fine" for them to be marked as thread -safe. - -However it's important that they aren't thread safe to prevent types that -contain them from being automatically marked as thread safe. These types have -non-trivial untracked ownership, and it's unlikely that their author was -necessarily thinking hard about thread safety. In the case of Rc, we have a nice -example of a type that contains a `*mut` that is definitely not thread safe. - -Types that aren't automatically derived can simply implement them if desired: - -```rust -struct MyBox(*mut u8); - -unsafe impl Send for MyBox {} -unsafe impl Sync for MyBox {} -``` - -In the *incredibly rare* case that a type is inappropriately automatically -derived to be Send or Sync, then one can also unimplement Send and Sync: - -```rust -#![feature(optin_builtin_traits)] - -// I have some magic semantics for some synchronization primitive! -struct SpecialThreadToken(u8); - -impl !Send for SpecialThreadToken {} -impl !Sync for SpecialThreadToken {} -``` - -Note that *in and of itself* it is impossible to incorrectly derive Send and -Sync. Only types that are ascribed special meaning by other unsafe code can -possible cause trouble by being incorrectly Send or Sync. - -Most uses of raw pointers should be encapsulated behind a sufficient abstraction -that Send and Sync can be derived. For instance all of Rust's standard -collections are Send and Sync (when they contain Send and Sync types) in spite -of their pervasive use of raw pointers to manage allocations and complex ownership. -Similarly, most iterators into these collections are Send and Sync because they -largely behave like an `&` or `&mut` into the collection. - -TODO: better explain what can or can't be Send or Sync. Sufficient to appeal -only to data races? - -[unsafe traits]: safe-unsafe-meaning.html diff --git a/src/doc/nomicon/src/subtyping.md b/src/doc/nomicon/src/subtyping.md deleted file mode 100644 index d771712d05013..0000000000000 --- a/src/doc/nomicon/src/subtyping.md +++ /dev/null @@ -1,213 +0,0 @@ -# Subtyping and Variance - -Although Rust doesn't have any notion of structural inheritance, it *does* -include subtyping. In Rust, subtyping derives entirely from lifetimes. Since -lifetimes are scopes, we can partially order them based on the *contains* -(outlives) relationship. We can even express this as a generic bound. - -Subtyping on lifetimes is in terms of that relationship: if `'a: 'b` ("a contains -b" or "a outlives b"), then `'a` is a subtype of `'b`. This is a large source of -confusion, because it seems intuitively backwards to many: the bigger scope is a -*subtype* of the smaller scope. - -This does in fact make sense, though. The intuitive reason for this is that if -you expect an `&'a u8`, then it's totally fine for me to hand you an `&'static -u8`, in the same way that if you expect an Animal in Java, it's totally fine for -me to hand you a Cat. Cats are just Animals *and more*, just as `'static` is -just `'a` *and more*. - -(Note, the subtyping relationship and typed-ness of lifetimes is a fairly -arbitrary construct that some disagree with. However it simplifies our analysis -to treat lifetimes and types uniformly.) - -Higher-ranked lifetimes are also subtypes of every concrete lifetime. This is -because taking an arbitrary lifetime is strictly more general than taking a -specific one. - - - -# Variance - -Variance is where things get a bit complicated. - -Variance is a property that *type constructors* have with respect to their -arguments. A type constructor in Rust is a generic type with unbound arguments. -For instance `Vec` is a type constructor that takes a `T` and returns a -`Vec`. `&` and `&mut` are type constructors that take two inputs: a -lifetime, and a type to point to. - -A type constructor's *variance* is how the subtyping of its inputs affects the -subtyping of its outputs. There are two kinds of variance in Rust: - -* F is *variant* over `T` if `T` being a subtype of `U` implies - `F` is a subtype of `F` (subtyping "passes through") -* F is *invariant* over `T` otherwise (no subtyping relation can be derived) - -(For those of you who are familiar with variance from other languages, what we -refer to as "just" variance is in fact *covariance*. Rust has *contravariance* -for functions. The future of contravariance is uncertain and it may be -scrapped. For now, `fn(T)` is contravariant in `T`, which is used in matching -methods in trait implementations to the trait definition. Traits don't have -inferred variance, so `Fn(T)` is invariant in `T`). - -Some important variances: - -* `&'a T` is variant over `'a` and `T` (as is `*const T` by metaphor) -* `&'a mut T` is variant over `'a` but invariant over `T` -* `Fn(T) -> U` is invariant over `T`, but variant over `U` -* `Box`, `Vec`, and all other collections are variant over the types of - their contents -* `UnsafeCell`, `Cell`, `RefCell`, `Mutex` and all other - interior mutability types are invariant over T (as is `*mut T` by metaphor) - -To understand why these variances are correct and desirable, we will consider -several examples. - - -We have already covered why `&'a T` should be variant over `'a` when -introducing subtyping: it's desirable to be able to pass longer-lived things -where shorter-lived things are needed. - -Similar reasoning applies to why it should be variant over T. It is reasonable -to be able to pass `&&'static str` where an `&&'a str` is expected. The -additional level of indirection does not change the desire to be able to pass -longer lived things where shorted lived things are expected. - -However this logic doesn't apply to `&mut`. To see why `&mut` should -be invariant over T, consider the following code: - -```rust,ignore -fn overwrite(input: &mut T, new: &mut T) { - *input = *new; -} - -fn main() { - let mut forever_str: &'static str = "hello"; - { - let string = String::from("world"); - overwrite(&mut forever_str, &mut &*string); - } - // Oops, printing free'd memory - println!("{}", forever_str); -} -``` - -The signature of `overwrite` is clearly valid: it takes mutable references to -two values of the same type, and overwrites one with the other. If `&mut T` was -variant over T, then `&mut &'static str` would be a subtype of `&mut &'a str`, -since `&'static str` is a subtype of `&'a str`. Therefore the lifetime of -`forever_str` would successfully be "shrunk" down to the shorter lifetime of -`string`, and `overwrite` would be called successfully. `string` would -subsequently be dropped, and `forever_str` would point to freed memory when we -print it! Therefore `&mut` should be invariant. - -This is the general theme of variance vs invariance: if variance would allow you -to store a short-lived value into a longer-lived slot, then you must be -invariant. - -However it *is* sound for `&'a mut T` to be variant over `'a`. The key difference -between `'a` and T is that `'a` is a property of the reference itself, -while T is something the reference is borrowing. If you change T's type, then -the source still remembers the original type. However if you change the -lifetime's type, no one but the reference knows this information, so it's fine. -Put another way: `&'a mut T` owns `'a`, but only *borrows* T. - -`Box` and `Vec` are interesting cases because they're variant, but you can -definitely store values in them! This is where Rust gets really clever: it's -fine for them to be variant because you can only store values -in them *via a mutable reference*! The mutable reference makes the whole type -invariant, and therefore prevents you from smuggling a short-lived type into -them. - -Being variant allows `Box` and `Vec` to be weakened when shared -immutably. So you can pass a `&Box<&'static str>` where a `&Box<&'a str>` is -expected. - -However what should happen when passing *by-value* is less obvious. It turns out -that, yes, you can use subtyping when passing by-value. That is, this works: - -```rust -fn get_box<'a>(str: &'a str) -> Box<&'a str> { - // string literals are `&'static str`s - Box::new("hello") -} -``` - -Weakening when you pass by-value is fine because there's no one else who -"remembers" the old lifetime in the Box. The reason a variant `&mut` was -trouble was because there's always someone else who remembers the original -subtype: the actual owner. - -The invariance of the cell types can be seen as follows: `&` is like an `&mut` -for a cell, because you can still store values in them through an `&`. Therefore -cells must be invariant to avoid lifetime smuggling. - -`Fn` is the most subtle case because it has mixed variance. To see why -`Fn(T) -> U` should be invariant over T, consider the following function -signature: - -```rust,ignore -// 'a is derived from some parent scope -fn foo(&'a str) -> usize; -``` - -This signature claims that it can handle any `&str` that lives at least as -long as `'a`. Now if this signature was variant over `&'a str`, that -would mean - -```rust,ignore -fn foo(&'static str) -> usize; -``` - -could be provided in its place, as it would be a subtype. However this function -has a stronger requirement: it says that it can only handle `&'static str`s, -and nothing else. Giving `&'a str`s to it would be unsound, as it's free to -assume that what it's given lives forever. Therefore functions are not variant -over their arguments. - -To see why `Fn(T) -> U` should be variant over U, consider the following -function signature: - -```rust,ignore -// 'a is derived from some parent scope -fn foo(usize) -> &'a str; -``` - -This signature claims that it will return something that outlives `'a`. It is -therefore completely reasonable to provide - -```rust,ignore -fn foo(usize) -> &'static str; -``` - -in its place. Therefore functions are variant over their return type. - -`*const` has the exact same semantics as `&`, so variance follows. `*mut` on the -other hand can dereference to an `&mut` whether shared or not, so it is marked -as invariant just like cells. - -This is all well and good for the types the standard library provides, but -how is variance determined for type that *you* define? A struct, informally -speaking, inherits the variance of its fields. If a struct `Foo` -has a generic argument `A` that is used in a field `a`, then Foo's variance -over `A` is exactly `a`'s variance. However this is complicated if `A` is used -in multiple fields. - -* If all uses of A are variant, then Foo is variant over A -* Otherwise, Foo is invariant over A - -```rust -use std::cell::Cell; - -struct Foo<'a, 'b, A: 'a, B: 'b, C, D, E, F, G, H> { - a: &'a A, // variant over 'a and A - b: &'b mut B, // variant over 'b and invariant over B - c: *const C, // variant over C - d: *mut D, // invariant over D - e: Vec, // variant over E - f: Cell, // invariant over F - g: G, // variant over G - h1: H, // would also be variant over H except... - h2: Cell, // invariant over H, because invariance wins -} -``` diff --git a/src/doc/nomicon/src/transmutes.md b/src/doc/nomicon/src/transmutes.md deleted file mode 100644 index 043c8fe462595..0000000000000 --- a/src/doc/nomicon/src/transmutes.md +++ /dev/null @@ -1,35 +0,0 @@ -# Transmutes - -Get out of our way type system! We're going to reinterpret these bits or die -trying! Even though this book is all about doing things that are unsafe, I -really can't emphasize that you should deeply think about finding Another Way -than the operations covered in this section. This is really, truly, the most -horribly unsafe thing you can do in Rust. The railguards here are dental floss. - -`mem::transmute` takes a value of type `T` and reinterprets it to have -type `U`. The only restriction is that the `T` and `U` are verified to have the -same size. The ways to cause Undefined Behavior with this are mind boggling. - -* First and foremost, creating an instance of *any* type with an invalid state - is going to cause arbitrary chaos that can't really be predicted. -* Transmute has an overloaded return type. If you do not specify the return type - it may produce a surprising type to satisfy inference. -* Making a primitive with an invalid value is UB -* Transmuting between non-repr(C) types is UB -* Transmuting an & to &mut is UB - * Transmuting an & to &mut is *always* UB - * No you can't do it - * No you're not special -* Transmuting to a reference without an explicitly provided lifetime - produces an [unbounded lifetime] - -`mem::transmute_copy` somehow manages to be *even more* wildly unsafe than -this. It copies `size_of` bytes out of an `&T` and interprets them as a `U`. -The size check that `mem::transmute` has is gone (as it may be valid to copy -out a prefix), though it is Undefined Behavior for `U` to be larger than `T`. - -Also of course you can get most of the functionality of these functions using -pointer casts. - - -[unbounded lifetime]: unbounded-lifetimes.html diff --git a/src/doc/nomicon/src/unbounded-lifetimes.md b/src/doc/nomicon/src/unbounded-lifetimes.md deleted file mode 100644 index b41cf8b4ed914..0000000000000 --- a/src/doc/nomicon/src/unbounded-lifetimes.md +++ /dev/null @@ -1,36 +0,0 @@ -# Unbounded Lifetimes - -Unsafe code can often end up producing references or lifetimes out of thin air. -Such lifetimes come into the world as *unbounded*. The most common source of this -is dereferencing a raw pointer, which produces a reference with an unbounded lifetime. -Such a lifetime becomes as big as context demands. This is in fact more powerful -than simply becoming `'static`, because for instance `&'static &'a T` -will fail to typecheck, but the unbound lifetime will perfectly mold into -`&'a &'a T` as needed. However for most intents and purposes, such an unbounded -lifetime can be regarded as `'static`. - -Almost no reference is `'static`, so this is probably wrong. `transmute` and -`transmute_copy` are the two other primary offenders. One should endeavor to -bound an unbounded lifetime as quickly as possible, especially across function -boundaries. - -Given a function, any output lifetimes that don't derive from inputs are -unbounded. For instance: - -```rust,ignore -fn get_str<'a>() -> &'a str; -``` - -will produce an `&str` with an unbounded lifetime. The easiest way to avoid -unbounded lifetimes is to use lifetime elision at the function boundary. -If an output lifetime is elided, then it *must* be bounded by an input lifetime. -Of course it might be bounded by the *wrong* lifetime, but this will usually -just cause a compiler error, rather than allow memory safety to be trivially -violated. - -Within a function, bounding lifetimes is more error-prone. The safest and easiest -way to bound a lifetime is to return it from a function with a bound lifetime. -However if this is unacceptable, the reference can be placed in a location with -a specific lifetime. Unfortunately it's impossible to name all lifetimes involved -in a function. - diff --git a/src/doc/nomicon/src/unchecked-uninit.md b/src/doc/nomicon/src/unchecked-uninit.md deleted file mode 100644 index ef31a3535d6a0..0000000000000 --- a/src/doc/nomicon/src/unchecked-uninit.md +++ /dev/null @@ -1,85 +0,0 @@ -# Unchecked Uninitialized Memory - -One interesting exception to this rule is working with arrays. Safe Rust doesn't -permit you to partially initialize an array. When you initialize an array, you -can either set every value to the same thing with `let x = [val; N]`, or you can -specify each member individually with `let x = [val1, val2, val3]`. -Unfortunately this is pretty rigid, especially if you need to initialize your -array in a more incremental or dynamic way. - -Unsafe Rust gives us a powerful tool to handle this problem: -`mem::uninitialized`. This function pretends to return a value when really -it does nothing at all. Using it, we can convince Rust that we have initialized -a variable, allowing us to do trickier things with conditional and incremental -initialization. - -Unfortunately, this opens us up to all kinds of problems. Assignment has a -different meaning to Rust based on whether it believes that a variable is -initialized or not. If it's believed uninitialized, then Rust will semantically -just memcopy the bits over the uninitialized ones, and do nothing else. However -if Rust believes a value to be initialized, it will try to `Drop` the old value! -Since we've tricked Rust into believing that the value is initialized, we can no -longer safely use normal assignment. - -This is also a problem if you're working with a raw system allocator, which -returns a pointer to uninitialized memory. - -To handle this, we must use the `ptr` module. In particular, it provides -three functions that allow us to assign bytes to a location in memory without -dropping the old value: `write`, `copy`, and `copy_nonoverlapping`. - -* `ptr::write(ptr, val)` takes a `val` and moves it into the address pointed - to by `ptr`. -* `ptr::copy(src, dest, count)` copies the bits that `count` T's would occupy - from src to dest. (this is equivalent to memmove -- note that the argument - order is reversed!) -* `ptr::copy_nonoverlapping(src, dest, count)` does what `copy` does, but a - little faster on the assumption that the two ranges of memory don't overlap. - (this is equivalent to memcpy -- note that the argument order is reversed!) - -It should go without saying that these functions, if misused, will cause serious -havoc or just straight up Undefined Behavior. The only things that these -functions *themselves* require is that the locations you want to read and write -are allocated. However the ways writing arbitrary bits to arbitrary -locations of memory can break things are basically uncountable! - -Putting this all together, we get the following: - -```rust -use std::mem; -use std::ptr; - -// size of the array is hard-coded but easy to change. This means we can't -// use [a, b, c] syntax to initialize the array, though! -const SIZE: usize = 10; - -let mut x: [Box; SIZE]; - -unsafe { - // convince Rust that x is Totally Initialized - x = mem::uninitialized(); - for i in 0..SIZE { - // very carefully overwrite each index without reading it - // NOTE: exception safety is not a concern; Box can't panic - ptr::write(&mut x[i], Box::new(i as u32)); - } -} - -println!("{:?}", x); -``` - -It's worth noting that you don't need to worry about `ptr::write`-style -shenanigans with types which don't implement `Drop` or contain `Drop` types, -because Rust knows not to try to drop them. Similarly you should be able to -assign to fields of partially initialized structs directly if those fields don't -contain any `Drop` types. - -However when working with uninitialized memory you need to be ever-vigilant for -Rust trying to drop values you make like this before they're fully initialized. -Every control path through that variable's scope must initialize the value -before it ends, if it has a destructor. -*[This includes code panicking](unwinding.html)*. - -And that's about it for working with uninitialized memory! Basically nothing -anywhere expects to be handed uninitialized memory, so if you're going to pass -it around at all, be sure to be *really* careful. diff --git a/src/doc/nomicon/src/uninitialized.md b/src/doc/nomicon/src/uninitialized.md deleted file mode 100644 index eafc67907f2af..0000000000000 --- a/src/doc/nomicon/src/uninitialized.md +++ /dev/null @@ -1,10 +0,0 @@ -# Working With Uninitialized Memory - -All runtime-allocated memory in a Rust program begins its life as -*uninitialized*. In this state the value of the memory is an indeterminate pile -of bits that may or may not even reflect a valid state for the type that is -supposed to inhabit that location of memory. Attempting to interpret this memory -as a value of *any* type will cause Undefined Behavior. Do Not Do This. - -Rust provides mechanisms to work with uninitialized memory in checked (safe) and -unchecked (unsafe) ways. diff --git a/src/doc/nomicon/src/unwinding.md b/src/doc/nomicon/src/unwinding.md deleted file mode 100644 index 6dc396d515348..0000000000000 --- a/src/doc/nomicon/src/unwinding.md +++ /dev/null @@ -1,49 +0,0 @@ -# Unwinding - -Rust has a *tiered* error-handling scheme: - -* If something might reasonably be absent, Option is used. -* If something goes wrong and can reasonably be handled, Result is used. -* If something goes wrong and cannot reasonably be handled, the thread panics. -* If something catastrophic happens, the program aborts. - -Option and Result are overwhelmingly preferred in most situations, especially -since they can be promoted into a panic or abort at the API user's discretion. -Panics cause the thread to halt normal execution and unwind its stack, calling -destructors as if every function instantly returned. - -As of 1.0, Rust is of two minds when it comes to panics. In the long-long-ago, -Rust was much more like Erlang. Like Erlang, Rust had lightweight tasks, -and tasks were intended to kill themselves with a panic when they reached an -untenable state. Unlike an exception in Java or C++, a panic could not be -caught at any time. Panics could only be caught by the owner of the task, at which -point they had to be handled or *that* task would itself panic. - -Unwinding was important to this story because if a task's -destructors weren't called, it would cause memory and other system resources to -leak. Since tasks were expected to die during normal execution, this would make -Rust very poor for long-running systems! - -As the Rust we know today came to be, this style of programming grew out of -fashion in the push for less-and-less abstraction. Light-weight tasks were -killed in the name of heavy-weight OS threads. Still, on stable Rust as of 1.0 -panics can only be caught by the parent thread. This means catching a panic -requires spinning up an entire OS thread! This unfortunately stands in conflict -to Rust's philosophy of zero-cost abstractions. - -There is an unstable API called `catch_panic` that enables catching a panic -without spawning a thread. Still, we would encourage you to only do this -sparingly. In particular, Rust's current unwinding implementation is heavily -optimized for the "doesn't unwind" case. If a program doesn't unwind, there -should be no runtime cost for the program being *ready* to unwind. As a -consequence, actually unwinding will be more expensive than in e.g. Java. -Don't build your programs to unwind under normal circumstances. Ideally, you -should only panic for programming errors or *extreme* problems. - -Rust's unwinding strategy is not specified to be fundamentally compatible -with any other language's unwinding. As such, unwinding into Rust from another -language, or unwinding into another language from Rust is Undefined Behavior. -You must *absolutely* catch any panics at the FFI boundary! What you do at that -point is up to you, but *something* must be done. If you fail to do this, -at best, your application will crash and burn. At worst, your application *won't* -crash and burn, and will proceed with completely clobbered state. diff --git a/src/doc/nomicon/src/vec-alloc.md b/src/doc/nomicon/src/vec-alloc.md deleted file mode 100644 index ef4c52793433f..0000000000000 --- a/src/doc/nomicon/src/vec-alloc.md +++ /dev/null @@ -1,223 +0,0 @@ -# Allocating Memory - -Using Unique throws a wrench in an important feature of Vec (and indeed all of -the std collections): an empty Vec doesn't actually allocate at all. So if we -can't allocate, but also can't put a null pointer in `ptr`, what do we do in -`Vec::new`? Well, we just put some other garbage in there! - -This is perfectly fine because we already have `cap == 0` as our sentinel for no -allocation. We don't even need to handle it specially in almost any code because -we usually need to check if `cap > len` or `len > 0` anyway. The traditional -Rust value to put here is `0x01`. The standard library actually exposes this -as `alloc::heap::EMPTY`. There are quite a few places where we'll -want to use `heap::EMPTY` because there's no real allocation to talk about but -`null` would make the compiler do bad things. - -All of the `heap` API is totally unstable under the `heap_api` feature, though. -We could trivially define `heap::EMPTY` ourselves, but we'll want the rest of -the `heap` API anyway, so let's just get that dependency over with. - -So: - -```rust,ignore -#![feature(alloc, heap_api)] - -use std::mem; - -use alloc::heap::EMPTY; - -impl Vec { - fn new() -> Self { - assert!(mem::size_of::() != 0, "We're not ready to handle ZSTs"); - unsafe { - // need to cast EMPTY to the actual ptr type we want, let - // inference handle it. - Vec { ptr: Unique::new(heap::EMPTY as *mut _), len: 0, cap: 0 } - } - } -} -``` - -I slipped in that assert there because zero-sized types will require some -special handling throughout our code, and I want to defer the issue for now. -Without this assert, some of our early drafts will do some Very Bad Things. - -Next we need to figure out what to actually do when we *do* want space. For -that, we'll need to use the rest of the heap APIs. These basically allow us to -talk directly to Rust's allocator (jemalloc by default). - -We'll also need a way to handle out-of-memory (OOM) conditions. The standard -library calls the `abort` intrinsic, which just calls an illegal instruction to -crash the whole program. The reason we abort and don't panic is because -unwinding can cause allocations to happen, and that seems like a bad thing to do -when your allocator just came back with "hey I don't have any more memory". - -Of course, this is a bit silly since most platforms don't actually run out of -memory in a conventional way. Your operating system will probably kill the -application by another means if you legitimately start using up all the memory. -The most likely way we'll trigger OOM is by just asking for ludicrous quantities -of memory at once (e.g. half the theoretical address space). As such it's -*probably* fine to panic and nothing bad will happen. Still, we're trying to be -like the standard library as much as possible, so we'll just kill the whole -program. - -We said we don't want to use intrinsics, so doing exactly what `std` does is -out. Instead, we'll call `std::process::exit` with some random number. - -```rust -fn oom() { - ::std::process::exit(-9999); -} -``` - -Okay, now we can write growing. Roughly, we want to have this logic: - -```text -if cap == 0: - allocate() - cap = 1 -else: - reallocate() - cap *= 2 -``` - -But Rust's only supported allocator API is so low level that we'll need to do a -fair bit of extra work. We also need to guard against some special -conditions that can occur with really large allocations or empty allocations. - -In particular, `ptr::offset` will cause us a lot of trouble, because it has -the semantics of LLVM's GEP inbounds instruction. If you're fortunate enough to -not have dealt with this instruction, here's the basic story with GEP: alias -analysis, alias analysis, alias analysis. It's super important to an optimizing -compiler to be able to reason about data dependencies and aliasing. - -As a simple example, consider the following fragment of code: - -```rust -# let x = &mut 0; -# let y = &mut 0; -*x *= 7; -*y *= 3; -``` - -If the compiler can prove that `x` and `y` point to different locations in -memory, the two operations can in theory be executed in parallel (by e.g. -loading them into different registers and working on them independently). -However the compiler can't do this in general because if x and y point to -the same location in memory, the operations need to be done to the same value, -and they can't just be merged afterwards. - -When you use GEP inbounds, you are specifically telling LLVM that the offsets -you're about to do are within the bounds of a single "allocated" entity. The -ultimate payoff being that LLVM can assume that if two pointers are known to -point to two disjoint objects, all the offsets of those pointers are *also* -known to not alias (because you won't just end up in some random place in -memory). LLVM is heavily optimized to work with GEP offsets, and inbounds -offsets are the best of all, so it's important that we use them as much as -possible. - -So that's what GEP's about, how can it cause us trouble? - -The first problem is that we index into arrays with unsigned integers, but -GEP (and as a consequence `ptr::offset`) takes a signed integer. This means -that half of the seemingly valid indices into an array will overflow GEP and -actually go in the wrong direction! As such we must limit all allocations to -`isize::MAX` elements. This actually means we only need to worry about -byte-sized objects, because e.g. `> isize::MAX` `u16`s will truly exhaust all of -the system's memory. However in order to avoid subtle corner cases where someone -reinterprets some array of `< isize::MAX` objects as bytes, std limits all -allocations to `isize::MAX` bytes. - -On all 64-bit targets that Rust currently supports we're artificially limited -to significantly less than all 64 bits of the address space (modern x64 -platforms only expose 48-bit addressing), so we can rely on just running out of -memory first. However on 32-bit targets, particularly those with extensions to -use more of the address space (PAE x86 or x32), it's theoretically possible to -successfully allocate more than `isize::MAX` bytes of memory. - -However since this is a tutorial, we're not going to be particularly optimal -here, and just unconditionally check, rather than use clever platform-specific -`cfg`s. - -The other corner-case we need to worry about is empty allocations. There will -be two kinds of empty allocations we need to worry about: `cap = 0` for all T, -and `cap > 0` for zero-sized types. - -These cases are tricky because they come -down to what LLVM means by "allocated". LLVM's notion of an -allocation is significantly more abstract than how we usually use it. Because -LLVM needs to work with different languages' semantics and custom allocators, -it can't really intimately understand allocation. Instead, the main idea behind -allocation is "doesn't overlap with other stuff". That is, heap allocations, -stack allocations, and globals don't randomly overlap. Yep, it's about alias -analysis. As such, Rust can technically play a bit fast and loose with the notion of -an allocation as long as it's *consistent*. - -Getting back to the empty allocation case, there are a couple of places where -we want to offset by 0 as a consequence of generic code. The question is then: -is it consistent to do so? For zero-sized types, we have concluded that it is -indeed consistent to do a GEP inbounds offset by an arbitrary number of -elements. This is a runtime no-op because every element takes up no space, -and it's fine to pretend that there's infinite zero-sized types allocated -at `0x01`. No allocator will ever allocate that address, because they won't -allocate `0x00` and they generally allocate to some minimal alignment higher -than a byte. Also generally the whole first page of memory is -protected from being allocated anyway (a whole 4k, on many platforms). - -However what about for positive-sized types? That one's a bit trickier. In -principle, you can argue that offsetting by 0 gives LLVM no information: either -there's an element before the address or after it, but it can't know which. -However we've chosen to conservatively assume that it may do bad things. As -such we will guard against this case explicitly. - -*Phew* - -Ok with all the nonsense out of the way, let's actually allocate some memory: - -```rust,ignore -fn grow(&mut self) { - // this is all pretty delicate, so let's say it's all unsafe - unsafe { - // current API requires us to specify size and alignment manually. - let align = mem::align_of::(); - let elem_size = mem::size_of::(); - - let (new_cap, ptr) = if self.cap == 0 { - let ptr = heap::allocate(elem_size, align); - (1, ptr) - } else { - // as an invariant, we can assume that `self.cap < isize::MAX`, - // so this doesn't need to be checked. - let new_cap = self.cap * 2; - // Similarly this can't overflow due to previously allocating this - let old_num_bytes = self.cap * elem_size; - - // check that the new allocation doesn't exceed `isize::MAX` at all - // regardless of the actual size of the capacity. This combines the - // `new_cap <= isize::MAX` and `new_num_bytes <= usize::MAX` checks - // we need to make. We lose the ability to allocate e.g. 2/3rds of - // the address space with a single Vec of i16's on 32-bit though. - // Alas, poor Yorick -- I knew him, Horatio. - assert!(old_num_bytes <= (::std::isize::MAX as usize) / 2, - "capacity overflow"); - - let new_num_bytes = old_num_bytes * 2; - let ptr = heap::reallocate(*self.ptr as *mut _, - old_num_bytes, - new_num_bytes, - align); - (new_cap, ptr) - }; - - // If allocate or reallocate fail, we'll get `null` back - if ptr.is_null() { oom(); } - - self.ptr = Unique::new(ptr as *mut _); - self.cap = new_cap; - } -} -``` - -Nothing particularly tricky here. Just computing sizes and alignments and doing -some careful multiplication checks. - diff --git a/src/doc/nomicon/src/vec-dealloc.md b/src/doc/nomicon/src/vec-dealloc.md deleted file mode 100644 index 83ab5b24b0245..0000000000000 --- a/src/doc/nomicon/src/vec-dealloc.md +++ /dev/null @@ -1,29 +0,0 @@ -# Deallocating - -Next we should implement Drop so that we don't massively leak tons of resources. -The easiest way is to just call `pop` until it yields None, and then deallocate -our buffer. Note that calling `pop` is unneeded if `T: !Drop`. In theory we can -ask Rust if `T` `needs_drop` and omit the calls to `pop`. However in practice -LLVM is *really* good at removing simple side-effect free code like this, so I -wouldn't bother unless you notice it's not being stripped (in this case it is). - -We must not call `heap::deallocate` when `self.cap == 0`, as in this case we -haven't actually allocated any memory. - - -```rust,ignore -impl Drop for Vec { - fn drop(&mut self) { - if self.cap != 0 { - while let Some(_) = self.pop() { } - - let align = mem::align_of::(); - let elem_size = mem::size_of::(); - let num_bytes = elem_size * self.cap; - unsafe { - heap::deallocate(*self.ptr as *mut _, num_bytes, align); - } - } - } -} -``` diff --git a/src/doc/nomicon/src/vec-deref.md b/src/doc/nomicon/src/vec-deref.md deleted file mode 100644 index e21542c955aeb..0000000000000 --- a/src/doc/nomicon/src/vec-deref.md +++ /dev/null @@ -1,42 +0,0 @@ -# Deref - -Alright! We've got a decent minimal stack implemented. We can push, we can -pop, and we can clean up after ourselves. However there's a whole mess of -functionality we'd reasonably want. In particular, we have a proper array, but -none of the slice functionality. That's actually pretty easy to solve: we can -implement `Deref`. This will magically make our Vec coerce to, and -behave like, a slice in all sorts of conditions. - -All we need is `slice::from_raw_parts`. It will correctly handle empty slices -for us. Later once we set up zero-sized type support it will also Just Work -for those too. - -```rust,ignore -use std::ops::Deref; - -impl Deref for Vec { - type Target = [T]; - fn deref(&self) -> &[T] { - unsafe { - ::std::slice::from_raw_parts(*self.ptr, self.len) - } - } -} -``` - -And let's do DerefMut too: - -```rust,ignore -use std::ops::DerefMut; - -impl DerefMut for Vec { - fn deref_mut(&mut self) -> &mut [T] { - unsafe { - ::std::slice::from_raw_parts_mut(*self.ptr, self.len) - } - } -} -``` - -Now we have `len`, `first`, `last`, indexing, slicing, sorting, `iter`, -`iter_mut`, and all other sorts of bells and whistles provided by slice. Sweet! diff --git a/src/doc/nomicon/src/vec-drain.md b/src/doc/nomicon/src/vec-drain.md deleted file mode 100644 index 5bd2bf05d8c08..0000000000000 --- a/src/doc/nomicon/src/vec-drain.md +++ /dev/null @@ -1,152 +0,0 @@ -# Drain - -Let's move on to Drain. Drain is largely the same as IntoIter, except that -instead of consuming the Vec, it borrows the Vec and leaves its allocation -untouched. For now we'll only implement the "basic" full-range version. - -```rust,ignore -use std::marker::PhantomData; - -struct Drain<'a, T: 'a> { - // Need to bound the lifetime here, so we do it with `&'a mut Vec` - // because that's semantically what we contain. We're "just" calling - // `pop()` and `remove(0)`. - vec: PhantomData<&'a mut Vec> - start: *const T, - end: *const T, -} - -impl<'a, T> Iterator for Drain<'a, T> { - type Item = T; - fn next(&mut self) -> Option { - if self.start == self.end { - None -``` - --- wait, this is seeming familiar. Let's do some more compression. Both -IntoIter and Drain have the exact same structure, let's just factor it out. - -```rust -struct RawValIter { - start: *const T, - end: *const T, -} - -impl RawValIter { - // unsafe to construct because it has no associated lifetimes. - // This is necessary to store a RawValIter in the same struct as - // its actual allocation. OK since it's a private implementation - // detail. - unsafe fn new(slice: &[T]) -> Self { - RawValIter { - start: slice.as_ptr(), - end: if slice.len() == 0 { - // if `len = 0`, then this is not actually allocated memory. - // Need to avoid offsetting because that will give wrong - // information to LLVM via GEP. - slice.as_ptr() - } else { - slice.as_ptr().offset(slice.len() as isize) - } - } - } -} - -// Iterator and DoubleEndedIterator impls identical to IntoIter. -``` - -And IntoIter becomes the following: - -```rust,ignore -pub struct IntoIter { - _buf: RawVec, // we don't actually care about this. Just need it to live. - iter: RawValIter, -} - -impl Iterator for IntoIter { - type Item = T; - fn next(&mut self) -> Option { self.iter.next() } - fn size_hint(&self) -> (usize, Option) { self.iter.size_hint() } -} - -impl DoubleEndedIterator for IntoIter { - fn next_back(&mut self) -> Option { self.iter.next_back() } -} - -impl Drop for IntoIter { - fn drop(&mut self) { - for _ in &mut self.iter {} - } -} - -impl Vec { - pub fn into_iter(self) -> IntoIter { - unsafe { - let iter = RawValIter::new(&self); - - let buf = ptr::read(&self.buf); - mem::forget(self); - - IntoIter { - iter: iter, - _buf: buf, - } - } - } -} -``` - -Note that I've left a few quirks in this design to make upgrading Drain to work -with arbitrary subranges a bit easier. In particular we *could* have RawValIter -drain itself on drop, but that won't work right for a more complex Drain. -We also take a slice to simplify Drain initialization. - -Alright, now Drain is really easy: - -```rust,ignore -use std::marker::PhantomData; - -pub struct Drain<'a, T: 'a> { - vec: PhantomData<&'a mut Vec>, - iter: RawValIter, -} - -impl<'a, T> Iterator for Drain<'a, T> { - type Item = T; - fn next(&mut self) -> Option { self.iter.next() } - fn size_hint(&self) -> (usize, Option) { self.iter.size_hint() } -} - -impl<'a, T> DoubleEndedIterator for Drain<'a, T> { - fn next_back(&mut self) -> Option { self.iter.next_back() } -} - -impl<'a, T> Drop for Drain<'a, T> { - fn drop(&mut self) { - for _ in &mut self.iter {} - } -} - -impl Vec { - pub fn drain(&mut self) -> Drain { - unsafe { - let iter = RawValIter::new(&self); - - // this is a mem::forget safety thing. If Drain is forgotten, we just - // leak the whole Vec's contents. Also we need to do this *eventually* - // anyway, so why not do it now? - self.len = 0; - - Drain { - iter: iter, - vec: PhantomData, - } - } - } -} -``` - -For more details on the `mem::forget` problem, see the -[section on leaks][leaks]. - -[leaks]: leaking.html diff --git a/src/doc/nomicon/src/vec-final.md b/src/doc/nomicon/src/vec-final.md deleted file mode 100644 index 39746cad781f8..0000000000000 --- a/src/doc/nomicon/src/vec-final.md +++ /dev/null @@ -1,321 +0,0 @@ -# The Final Code - -```rust -#![feature(unique)] -#![feature(alloc, heap_api)] - -extern crate alloc; - -use std::ptr::{Unique, self}; -use std::mem; -use std::ops::{Deref, DerefMut}; -use std::marker::PhantomData; - -use alloc::heap; - -struct RawVec { - ptr: Unique, - cap: usize, -} - -impl RawVec { - fn new() -> Self { - unsafe { - // !0 is usize::MAX. This branch should be stripped at compile time. - let cap = if mem::size_of::() == 0 { !0 } else { 0 }; - - // heap::EMPTY doubles as "unallocated" and "zero-sized allocation" - RawVec { ptr: Unique::new(heap::EMPTY as *mut T), cap: cap } - } - } - - fn grow(&mut self) { - unsafe { - let elem_size = mem::size_of::(); - - // since we set the capacity to usize::MAX when elem_size is - // 0, getting to here necessarily means the Vec is overfull. - assert!(elem_size != 0, "capacity overflow"); - - let align = mem::align_of::(); - - let (new_cap, ptr) = if self.cap == 0 { - let ptr = heap::allocate(elem_size, align); - (1, ptr) - } else { - let new_cap = 2 * self.cap; - let ptr = heap::reallocate(*self.ptr as *mut _, - self.cap * elem_size, - new_cap * elem_size, - align); - (new_cap, ptr) - }; - - // If allocate or reallocate fail, we'll get `null` back - if ptr.is_null() { oom() } - - self.ptr = Unique::new(ptr as *mut _); - self.cap = new_cap; - } - } -} - -impl Drop for RawVec { - fn drop(&mut self) { - let elem_size = mem::size_of::(); - if self.cap != 0 && elem_size != 0 { - let align = mem::align_of::(); - - let num_bytes = elem_size * self.cap; - unsafe { - heap::deallocate(*self.ptr as *mut _, num_bytes, align); - } - } - } -} - - - - - -pub struct Vec { - buf: RawVec, - len: usize, -} - -impl Vec { - fn ptr(&self) -> *mut T { *self.buf.ptr } - - fn cap(&self) -> usize { self.buf.cap } - - pub fn new() -> Self { - Vec { buf: RawVec::new(), len: 0 } - } - pub fn push(&mut self, elem: T) { - if self.len == self.cap() { self.buf.grow(); } - - unsafe { - ptr::write(self.ptr().offset(self.len as isize), elem); - } - - // Can't fail, we'll OOM first. - self.len += 1; - } - - pub fn pop(&mut self) -> Option { - if self.len == 0 { - None - } else { - self.len -= 1; - unsafe { - Some(ptr::read(self.ptr().offset(self.len as isize))) - } - } - } - - pub fn insert(&mut self, index: usize, elem: T) { - assert!(index <= self.len, "index out of bounds"); - if self.cap() == self.len { self.buf.grow(); } - - unsafe { - if index < self.len { - ptr::copy(self.ptr().offset(index as isize), - self.ptr().offset(index as isize + 1), - self.len - index); - } - ptr::write(self.ptr().offset(index as isize), elem); - self.len += 1; - } - } - - pub fn remove(&mut self, index: usize) -> T { - assert!(index < self.len, "index out of bounds"); - unsafe { - self.len -= 1; - let result = ptr::read(self.ptr().offset(index as isize)); - ptr::copy(self.ptr().offset(index as isize + 1), - self.ptr().offset(index as isize), - self.len - index); - result - } - } - - pub fn into_iter(self) -> IntoIter { - unsafe { - let iter = RawValIter::new(&self); - let buf = ptr::read(&self.buf); - mem::forget(self); - - IntoIter { - iter: iter, - _buf: buf, - } - } - } - - pub fn drain(&mut self) -> Drain { - unsafe { - let iter = RawValIter::new(&self); - - // this is a mem::forget safety thing. If Drain is forgotten, we just - // leak the whole Vec's contents. Also we need to do this *eventually* - // anyway, so why not do it now? - self.len = 0; - - Drain { - iter: iter, - vec: PhantomData, - } - } - } -} - -impl Drop for Vec { - fn drop(&mut self) { - while let Some(_) = self.pop() {} - // allocation is handled by RawVec - } -} - -impl Deref for Vec { - type Target = [T]; - fn deref(&self) -> &[T] { - unsafe { - ::std::slice::from_raw_parts(self.ptr(), self.len) - } - } -} - -impl DerefMut for Vec { - fn deref_mut(&mut self) -> &mut [T] { - unsafe { - ::std::slice::from_raw_parts_mut(self.ptr(), self.len) - } - } -} - - - - - -struct RawValIter { - start: *const T, - end: *const T, -} - -impl RawValIter { - unsafe fn new(slice: &[T]) -> Self { - RawValIter { - start: slice.as_ptr(), - end: if mem::size_of::() == 0 { - ((slice.as_ptr() as usize) + slice.len()) as *const _ - } else if slice.len() == 0 { - slice.as_ptr() - } else { - slice.as_ptr().offset(slice.len() as isize) - } - } - } -} - -impl Iterator for RawValIter { - type Item = T; - fn next(&mut self) -> Option { - if self.start == self.end { - None - } else { - unsafe { - let result = ptr::read(self.start); - self.start = if mem::size_of::() == 0 { - (self.start as usize + 1) as *const _ - } else { - self.start.offset(1) - }; - Some(result) - } - } - } - - fn size_hint(&self) -> (usize, Option) { - let elem_size = mem::size_of::(); - let len = (self.end as usize - self.start as usize) - / if elem_size == 0 { 1 } else { elem_size }; - (len, Some(len)) - } -} - -impl DoubleEndedIterator for RawValIter { - fn next_back(&mut self) -> Option { - if self.start == self.end { - None - } else { - unsafe { - self.end = if mem::size_of::() == 0 { - (self.end as usize - 1) as *const _ - } else { - self.end.offset(-1) - }; - Some(ptr::read(self.end)) - } - } - } -} - - - - -pub struct IntoIter { - _buf: RawVec, // we don't actually care about this. Just need it to live. - iter: RawValIter, -} - -impl Iterator for IntoIter { - type Item = T; - fn next(&mut self) -> Option { self.iter.next() } - fn size_hint(&self) -> (usize, Option) { self.iter.size_hint() } -} - -impl DoubleEndedIterator for IntoIter { - fn next_back(&mut self) -> Option { self.iter.next_back() } -} - -impl Drop for IntoIter { - fn drop(&mut self) { - for _ in &mut *self {} - } -} - - - - -pub struct Drain<'a, T: 'a> { - vec: PhantomData<&'a mut Vec>, - iter: RawValIter, -} - -impl<'a, T> Iterator for Drain<'a, T> { - type Item = T; - fn next(&mut self) -> Option { self.iter.next_back() } - fn size_hint(&self) -> (usize, Option) { self.iter.size_hint() } -} - -impl<'a, T> DoubleEndedIterator for Drain<'a, T> { - fn next_back(&mut self) -> Option { self.iter.next_back() } -} - -impl<'a, T> Drop for Drain<'a, T> { - fn drop(&mut self) { - // pre-drain the iter - for _ in &mut self.iter {} - } -} - -/// Abort the process, we're out of memory! -/// -/// In practice this is probably dead code on most OSes -fn oom() { - ::std::process::exit(-9999); -} - -# fn main() {} -``` diff --git a/src/doc/nomicon/src/vec-insert-remove.md b/src/doc/nomicon/src/vec-insert-remove.md deleted file mode 100644 index 2c14bc4522722..0000000000000 --- a/src/doc/nomicon/src/vec-insert-remove.md +++ /dev/null @@ -1,51 +0,0 @@ -# Insert and Remove - -Something *not* provided by slice is `insert` and `remove`, so let's do those -next. - -Insert needs to shift all the elements at the target index to the right by one. -To do this we need to use `ptr::copy`, which is our version of C's `memmove`. -This copies some chunk of memory from one location to another, correctly -handling the case where the source and destination overlap (which will -definitely happen here). - -If we insert at index `i`, we want to shift the `[i .. len]` to `[i+1 .. len+1]` -using the old len. - -```rust,ignore -pub fn insert(&mut self, index: usize, elem: T) { - // Note: `<=` because it's valid to insert after everything - // which would be equivalent to push. - assert!(index <= self.len, "index out of bounds"); - if self.cap == self.len { self.grow(); } - - unsafe { - if index < self.len { - // ptr::copy(src, dest, len): "copy from source to dest len elems" - ptr::copy(self.ptr.offset(index as isize), - self.ptr.offset(index as isize + 1), - self.len - index); - } - ptr::write(self.ptr.offset(index as isize), elem); - self.len += 1; - } -} -``` - -Remove behaves in the opposite manner. We need to shift all the elements from -`[i+1 .. len + 1]` to `[i .. len]` using the *new* len. - -```rust,ignore -pub fn remove(&mut self, index: usize) -> T { - // Note: `<` because it's *not* valid to remove after everything - assert!(index < self.len, "index out of bounds"); - unsafe { - self.len -= 1; - let result = ptr::read(self.ptr.offset(index as isize)); - ptr::copy(self.ptr.offset(index as isize + 1), - self.ptr.offset(index as isize), - self.len - index); - result - } -} -``` diff --git a/src/doc/nomicon/src/vec-into-iter.md b/src/doc/nomicon/src/vec-into-iter.md deleted file mode 100644 index f2f5995ec1cbf..0000000000000 --- a/src/doc/nomicon/src/vec-into-iter.md +++ /dev/null @@ -1,147 +0,0 @@ -# IntoIter - -Let's move on to writing iterators. `iter` and `iter_mut` have already been -written for us thanks to The Magic of Deref. However there's two interesting -iterators that Vec provides that slices can't: `into_iter` and `drain`. - -IntoIter consumes the Vec by-value, and can consequently yield its elements -by-value. In order to enable this, IntoIter needs to take control of Vec's -allocation. - -IntoIter needs to be DoubleEnded as well, to enable reading from both ends. -Reading from the back could just be implemented as calling `pop`, but reading -from the front is harder. We could call `remove(0)` but that would be insanely -expensive. Instead we're going to just use ptr::read to copy values out of -either end of the Vec without mutating the buffer at all. - -To do this we're going to use a very common C idiom for array iteration. We'll -make two pointers; one that points to the start of the array, and one that -points to one-element past the end. When we want an element from one end, we'll -read out the value pointed to at that end and move the pointer over by one. When -the two pointers are equal, we know we're done. - -Note that the order of read and offset are reversed for `next` and `next_back` -For `next_back` the pointer is always after the element it wants to read next, -while for `next` the pointer is always at the element it wants to read next. -To see why this is, consider the case where every element but one has been -yielded. - -The array looks like this: - -```text - S E -[X, X, X, O, X, X, X] -``` - -If E pointed directly at the element it wanted to yield next, it would be -indistinguishable from the case where there are no more elements to yield. - -Although we don't actually care about it during iteration, we also need to hold -onto the Vec's allocation information in order to free it once IntoIter is -dropped. - -So we're going to use the following struct: - -```rust,ignore -struct IntoIter { - buf: Unique, - cap: usize, - start: *const T, - end: *const T, -} -``` - -And this is what we end up with for initialization: - -```rust,ignore -impl Vec { - fn into_iter(self) -> IntoIter { - // Can't destructure Vec since it's Drop - let ptr = self.ptr; - let cap = self.cap; - let len = self.len; - - // Make sure not to drop Vec since that will free the buffer - mem::forget(self); - - unsafe { - IntoIter { - buf: ptr, - cap: cap, - start: *ptr, - end: if cap == 0 { - // can't offset off this pointer, it's not allocated! - *ptr - } else { - ptr.offset(len as isize) - } - } - } - } -} -``` - -Here's iterating forward: - -```rust,ignore -impl Iterator for IntoIter { - type Item = T; - fn next(&mut self) -> Option { - if self.start == self.end { - None - } else { - unsafe { - let result = ptr::read(self.start); - self.start = self.start.offset(1); - Some(result) - } - } - } - - fn size_hint(&self) -> (usize, Option) { - let len = (self.end as usize - self.start as usize) - / mem::size_of::(); - (len, Some(len)) - } -} -``` - -And here's iterating backwards. - -```rust,ignore -impl DoubleEndedIterator for IntoIter { - fn next_back(&mut self) -> Option { - if self.start == self.end { - None - } else { - unsafe { - self.end = self.end.offset(-1); - Some(ptr::read(self.end)) - } - } - } -} -``` - -Because IntoIter takes ownership of its allocation, it needs to implement Drop -to free it. However it also wants to implement Drop to drop any elements it -contains that weren't yielded. - - -```rust,ignore -impl Drop for IntoIter { - fn drop(&mut self) { - if self.cap != 0 { - // drop any remaining elements - for _ in &mut *self {} - - let align = mem::align_of::(); - let elem_size = mem::size_of::(); - let num_bytes = elem_size * self.cap; - unsafe { - heap::deallocate(*self.buf as *mut _, num_bytes, align); - } - } - } -} -``` diff --git a/src/doc/nomicon/src/vec-layout.md b/src/doc/nomicon/src/vec-layout.md deleted file mode 100644 index 1dc09aef6ad28..0000000000000 --- a/src/doc/nomicon/src/vec-layout.md +++ /dev/null @@ -1,100 +0,0 @@ -# Layout - -First off, we need to come up with the struct layout. A Vec has three parts: -a pointer to the allocation, the size of the allocation, and the number of -elements that have been initialized. - -Naively, this means we just want this design: - -```rust -pub struct Vec { - ptr: *mut T, - cap: usize, - len: usize, -} -# fn main() {} -``` - -And indeed this would compile. Unfortunately, it would be incorrect. First, the -compiler will give us too strict variance. So a `&Vec<&'static str>` -couldn't be used where an `&Vec<&'a str>` was expected. More importantly, it -will give incorrect ownership information to the drop checker, as it will -conservatively assume we don't own any values of type `T`. See [the chapter -on ownership and lifetimes][ownership] for all the details on variance and -drop check. - -As we saw in the ownership chapter, we should use `Unique` in place of -`*mut T` when we have a raw pointer to an allocation we own. Unique is unstable, -so we'd like to not use it if possible, though. - -As a recap, Unique is a wrapper around a raw pointer that declares that: - -* We are variant over `T` -* We may own a value of type `T` (for drop check) -* We are Send/Sync if `T` is Send/Sync -* We deref to `*mut T` (so it largely acts like a `*mut` in our code) -* Our pointer is never null (so `Option>` is null-pointer-optimized) - -We can implement all of the above requirements except for the last -one in stable Rust: - -```rust -use std::marker::PhantomData; -use std::ops::Deref; -use std::mem; - -struct Unique { - ptr: *const T, // *const for variance - _marker: PhantomData, // For the drop checker -} - -// Deriving Send and Sync is safe because we are the Unique owners -// of this data. It's like Unique is "just" T. -unsafe impl Send for Unique {} -unsafe impl Sync for Unique {} - -impl Unique { - pub fn new(ptr: *mut T) -> Self { - Unique { ptr: ptr, _marker: PhantomData } - } -} - -impl Deref for Unique { - type Target = *mut T; - fn deref(&self) -> &*mut T { - // There's no way to cast the *const to a *mut - // while also taking a reference. So we just - // transmute it since it's all "just pointers". - unsafe { mem::transmute(&self.ptr) } - } -} -# fn main() {} -``` - -Unfortunately the mechanism for stating that your value is non-zero is -unstable and unlikely to be stabilized soon. As such we're just going to -take the hit and use std's Unique: - - -```rust -#![feature(unique)] - -use std::ptr::{Unique, self}; - -pub struct Vec { - ptr: Unique, - cap: usize, - len: usize, -} - -# fn main() {} -``` - -If you don't care about the null-pointer optimization, then you can use the -stable code. However we will be designing the rest of the code around enabling -the optimization. In particular, `Unique::new` is unsafe to call, because -putting `null` inside of it is Undefined Behavior. Our stable Unique doesn't -need `new` to be unsafe because it doesn't make any interesting guarantees about -its contents. - -[ownership]: ownership.html diff --git a/src/doc/nomicon/src/vec-push-pop.md b/src/doc/nomicon/src/vec-push-pop.md deleted file mode 100644 index d31a74cc308d9..0000000000000 --- a/src/doc/nomicon/src/vec-push-pop.md +++ /dev/null @@ -1,55 +0,0 @@ -# Push and Pop - -Alright. We can initialize. We can allocate. Let's actually implement some -functionality! Let's start with `push`. All it needs to do is check if we're -full to grow, unconditionally write to the next index, and then increment our -length. - -To do the write we have to be careful not to evaluate the memory we want to write -to. At worst, it's truly uninitialized memory from the allocator. At best it's the -bits of some old value we popped off. Either way, we can't just index to the memory -and dereference it, because that will evaluate the memory as a valid instance of -T. Worse, `foo[idx] = x` will try to call `drop` on the old value of `foo[idx]`! - -The correct way to do this is with `ptr::write`, which just blindly overwrites the -target address with the bits of the value we provide. No evaluation involved. - -For `push`, if the old len (before push was called) is 0, then we want to write -to the 0th index. So we should offset by the old len. - -```rust,ignore -pub fn push(&mut self, elem: T) { - if self.len == self.cap { self.grow(); } - - unsafe { - ptr::write(self.ptr.offset(self.len as isize), elem); - } - - // Can't fail, we'll OOM first. - self.len += 1; -} -``` - -Easy! How about `pop`? Although this time the index we want to access is -initialized, Rust won't just let us dereference the location of memory to move -the value out, because that would leave the memory uninitialized! For this we -need `ptr::read`, which just copies out the bits from the target address and -interprets it as a value of type T. This will leave the memory at this address -logically uninitialized, even though there is in fact a perfectly good instance -of T there. - -For `pop`, if the old len is 1, we want to read out of the 0th index. So we -should offset by the new len. - -```rust,ignore -pub fn pop(&mut self) -> Option { - if self.len == 0 { - None - } else { - self.len -= 1; - unsafe { - Some(ptr::read(self.ptr.offset(self.len as isize))) - } - } -} -``` diff --git a/src/doc/nomicon/src/vec-raw.md b/src/doc/nomicon/src/vec-raw.md deleted file mode 100644 index 20fa8ab92c24c..0000000000000 --- a/src/doc/nomicon/src/vec-raw.md +++ /dev/null @@ -1,136 +0,0 @@ -# RawVec - -We've actually reached an interesting situation here: we've duplicated the logic -for specifying a buffer and freeing its memory in Vec and IntoIter. Now that -we've implemented it and identified *actual* logic duplication, this is a good -time to perform some logic compression. - -We're going to abstract out the `(ptr, cap)` pair and give them the logic for -allocating, growing, and freeing: - -```rust,ignore -struct RawVec { - ptr: Unique, - cap: usize, -} - -impl RawVec { - fn new() -> Self { - assert!(mem::size_of::() != 0, "TODO: implement ZST support"); - unsafe { - RawVec { ptr: Unique::new(heap::EMPTY as *mut T), cap: 0 } - } - } - - // unchanged from Vec - fn grow(&mut self) { - unsafe { - let align = mem::align_of::(); - let elem_size = mem::size_of::(); - - let (new_cap, ptr) = if self.cap == 0 { - let ptr = heap::allocate(elem_size, align); - (1, ptr) - } else { - let new_cap = 2 * self.cap; - let ptr = heap::reallocate(*self.ptr as *mut _, - self.cap * elem_size, - new_cap * elem_size, - align); - (new_cap, ptr) - }; - - // If allocate or reallocate fail, we'll get `null` back - if ptr.is_null() { oom() } - - self.ptr = Unique::new(ptr as *mut _); - self.cap = new_cap; - } - } -} - - -impl Drop for RawVec { - fn drop(&mut self) { - if self.cap != 0 { - let align = mem::align_of::(); - let elem_size = mem::size_of::(); - let num_bytes = elem_size * self.cap; - unsafe { - heap::deallocate(*self.ptr as *mut _, num_bytes, align); - } - } - } -} -``` - -And change Vec as follows: - -```rust,ignore -pub struct Vec { - buf: RawVec, - len: usize, -} - -impl Vec { - fn ptr(&self) -> *mut T { *self.buf.ptr } - - fn cap(&self) -> usize { self.buf.cap } - - pub fn new() -> Self { - Vec { buf: RawVec::new(), len: 0 } - } - - // push/pop/insert/remove largely unchanged: - // * `self.ptr -> self.ptr()` - // * `self.cap -> self.cap()` - // * `self.grow -> self.buf.grow()` -} - -impl Drop for Vec { - fn drop(&mut self) { - while let Some(_) = self.pop() {} - // deallocation is handled by RawVec - } -} -``` - -And finally we can really simplify IntoIter: - -```rust,ignore -struct IntoIter { - _buf: RawVec, // we don't actually care about this. Just need it to live. - start: *const T, - end: *const T, -} - -// next and next_back literally unchanged since they never referred to the buf - -impl Drop for IntoIter { - fn drop(&mut self) { - // only need to ensure all our elements are read; - // buffer will clean itself up afterwards. - for _ in &mut *self {} - } -} - -impl Vec { - pub fn into_iter(self) -> IntoIter { - unsafe { - // need to use ptr::read to unsafely move the buf out since it's - // not Copy, and Vec implements Drop (so we can't destructure it). - let buf = ptr::read(&self.buf); - let len = self.len; - mem::forget(self); - - IntoIter { - start: *buf.ptr, - end: buf.ptr.offset(len as isize), - _buf: buf, - } - } - } -} -``` - -Much better. diff --git a/src/doc/nomicon/src/vec-zsts.md b/src/doc/nomicon/src/vec-zsts.md deleted file mode 100644 index 5ae9bdd327473..0000000000000 --- a/src/doc/nomicon/src/vec-zsts.md +++ /dev/null @@ -1,176 +0,0 @@ -# Handling Zero-Sized Types - -It's time. We're going to fight the specter that is zero-sized types. Safe Rust -*never* needs to care about this, but Vec is very intensive on raw pointers and -raw allocations, which are exactly the two things that care about -zero-sized types. We need to be careful of two things: - -* The raw allocator API has undefined behavior if you pass in 0 for an - allocation size. -* raw pointer offsets are no-ops for zero-sized types, which will break our - C-style pointer iterator. - -Thankfully we abstracted out pointer-iterators and allocating handling into -RawValIter and RawVec respectively. How mysteriously convenient. - - - - -## Allocating Zero-Sized Types - -So if the allocator API doesn't support zero-sized allocations, what on earth -do we store as our allocation? Why, `heap::EMPTY` of course! Almost every operation -with a ZST is a no-op since ZSTs have exactly one value, and therefore no state needs -to be considered to store or load them. This actually extends to `ptr::read` and -`ptr::write`: they won't actually look at the pointer at all. As such we never need -to change the pointer. - -Note however that our previous reliance on running out of memory before overflow is -no longer valid with zero-sized types. We must explicitly guard against capacity -overflow for zero-sized types. - -Due to our current architecture, all this means is writing 3 guards, one in each -method of RawVec. - -```rust,ignore -impl RawVec { - fn new() -> Self { - unsafe { - // !0 is usize::MAX. This branch should be stripped at compile time. - let cap = if mem::size_of::() == 0 { !0 } else { 0 }; - - // heap::EMPTY doubles as "unallocated" and "zero-sized allocation" - RawVec { ptr: Unique::new(heap::EMPTY as *mut T), cap: cap } - } - } - - fn grow(&mut self) { - unsafe { - let elem_size = mem::size_of::(); - - // since we set the capacity to usize::MAX when elem_size is - // 0, getting to here necessarily means the Vec is overfull. - assert!(elem_size != 0, "capacity overflow"); - - let align = mem::align_of::(); - - let (new_cap, ptr) = if self.cap == 0 { - let ptr = heap::allocate(elem_size, align); - (1, ptr) - } else { - let new_cap = 2 * self.cap; - let ptr = heap::reallocate(*self.ptr as *mut _, - self.cap * elem_size, - new_cap * elem_size, - align); - (new_cap, ptr) - }; - - // If allocate or reallocate fail, we'll get `null` back - if ptr.is_null() { oom() } - - self.ptr = Unique::new(ptr as *mut _); - self.cap = new_cap; - } - } -} - -impl Drop for RawVec { - fn drop(&mut self) { - let elem_size = mem::size_of::(); - - // don't free zero-sized allocations, as they were never allocated. - if self.cap != 0 && elem_size != 0 { - let align = mem::align_of::(); - - let num_bytes = elem_size * self.cap; - unsafe { - heap::deallocate(*self.ptr as *mut _, num_bytes, align); - } - } - } -} -``` - -That's it. We support pushing and popping zero-sized types now. Our iterators -(that aren't provided by slice Deref) are still busted, though. - - - - -## Iterating Zero-Sized Types - -Zero-sized offsets are no-ops. This means that our current design will always -initialize `start` and `end` as the same value, and our iterators will yield -nothing. The current solution to this is to cast the pointers to integers, -increment, and then cast them back: - -```rust,ignore -impl RawValIter { - unsafe fn new(slice: &[T]) -> Self { - RawValIter { - start: slice.as_ptr(), - end: if mem::size_of::() == 0 { - ((slice.as_ptr() as usize) + slice.len()) as *const _ - } else if slice.len() == 0 { - slice.as_ptr() - } else { - slice.as_ptr().offset(slice.len() as isize) - } - } - } -} -``` - -Now we have a different bug. Instead of our iterators not running at all, our -iterators now run *forever*. We need to do the same trick in our iterator impls. -Also, our size_hint computation code will divide by 0 for ZSTs. Since we'll -basically be treating the two pointers as if they point to bytes, we'll just -map size 0 to divide by 1. - -```rust,ignore -impl Iterator for RawValIter { - type Item = T; - fn next(&mut self) -> Option { - if self.start == self.end { - None - } else { - unsafe { - let result = ptr::read(self.start); - self.start = if mem::size_of::() == 0 { - (self.start as usize + 1) as *const _ - } else { - self.start.offset(1) - }; - Some(result) - } - } - } - - fn size_hint(&self) -> (usize, Option) { - let elem_size = mem::size_of::(); - let len = (self.end as usize - self.start as usize) - / if elem_size == 0 { 1 } else { elem_size }; - (len, Some(len)) - } -} - -impl DoubleEndedIterator for RawValIter { - fn next_back(&mut self) -> Option { - if self.start == self.end { - None - } else { - unsafe { - self.end = if mem::size_of::() == 0 { - (self.end as usize - 1) as *const _ - } else { - self.end.offset(-1) - }; - Some(ptr::read(self.end)) - } - } - } -} -``` - -And that's it. Iteration works! diff --git a/src/doc/nomicon/src/vec.md b/src/doc/nomicon/src/vec.md deleted file mode 100644 index ad98e45f197b3..0000000000000 --- a/src/doc/nomicon/src/vec.md +++ /dev/null @@ -1,20 +0,0 @@ -# Example: Implementing Vec - -To bring everything together, we're going to write `std::Vec` from scratch. -Because all the best tools for writing unsafe code are unstable, this -project will only work on nightly (as of Rust 1.9.0). With the exception of the -allocator API, much of the unstable code we'll use is expected to be stabilized -in a similar form as it is today. - -However we will generally try to avoid unstable code where possible. In -particular we won't use any intrinsics that could make a code a little -bit nicer or efficient because intrinsics are permanently unstable. Although -many intrinsics *do* become stabilized elsewhere (`std::ptr` and `str::mem` -consist of many intrinsics). - -Ultimately this means our implementation may not take advantage of all -possible optimizations, though it will be by no means *naive*. We will -definitely get into the weeds over nitty-gritty details, even -when the problem doesn't *really* merit it. - -You wanted advanced. We're gonna go advanced. diff --git a/src/doc/nomicon/src/working-with-unsafe.md b/src/doc/nomicon/src/working-with-unsafe.md deleted file mode 100644 index 5724f3d09a302..0000000000000 --- a/src/doc/nomicon/src/working-with-unsafe.md +++ /dev/null @@ -1,119 +0,0 @@ -# Working with Unsafe - -Rust generally only gives us the tools to talk about Unsafe Rust in a scoped and -binary manner. Unfortunately, reality is significantly more complicated than -that. For instance, consider the following toy function: - -```rust -fn index(idx: usize, arr: &[u8]) -> Option { - if idx < arr.len() { - unsafe { - Some(*arr.get_unchecked(idx)) - } - } else { - None - } -} -``` - -Clearly, this function is safe. We check that the index is in bounds, and if it -is, index into the array in an unchecked manner. But even in such a trivial -function, the scope of the unsafe block is questionable. Consider changing the -`<` to a `<=`: - -```rust -fn index(idx: usize, arr: &[u8]) -> Option { - if idx <= arr.len() { - unsafe { - Some(*arr.get_unchecked(idx)) - } - } else { - None - } -} -``` - -This program is now unsound, and yet *we only modified safe code*. This is the -fundamental problem of safety: it's non-local. The soundness of our unsafe -operations necessarily depends on the state established by otherwise -"safe" operations. - -Safety is modular in the sense that opting into unsafety doesn't require you -to consider arbitrary other kinds of badness. For instance, doing an unchecked -index into a slice doesn't mean you suddenly need to worry about the slice being -null or containing uninitialized memory. Nothing fundamentally changes. However -safety *isn't* modular in the sense that programs are inherently stateful and -your unsafe operations may depend on arbitrary other state. - -Trickier than that is when we get into actual statefulness. Consider a simple -implementation of `Vec`: - -```rust -use std::ptr; - -// Note this definition is insufficient. See the section on implementing Vec. -pub struct Vec { - ptr: *mut T, - len: usize, - cap: usize, -} - -// Note this implementation does not correctly handle zero-sized types. -// We currently live in a nice imaginary world of only positive fixed-size -// types. -impl Vec { - pub fn push(&mut self, elem: T) { - if self.len == self.cap { - // not important for this example - self.reallocate(); - } - unsafe { - ptr::write(self.ptr.offset(self.len as isize), elem); - self.len += 1; - } - } - - # fn reallocate(&mut self) { } -} - -# fn main() {} -``` - -This code is simple enough to reasonably audit and verify. Now consider -adding the following method: - -```rust,ignore -fn make_room(&mut self) { - // grow the capacity - self.cap += 1; -} -``` - -This code is 100% Safe Rust but it is also completely unsound. Changing the -capacity violates the invariants of Vec (that `cap` reflects the allocated space -in the Vec). This is not something the rest of Vec can guard against. It *has* -to trust the capacity field because there's no way to verify it. - -`unsafe` does more than pollute a whole function: it pollutes a whole *module*. -Generally, the only bullet-proof way to limit the scope of unsafe code is at the -module boundary with privacy. - -However this works *perfectly*. The existence of `make_room` is *not* a -problem for the soundness of Vec because we didn't mark it as public. Only the -module that defines this function can call it. Also, `make_room` directly -accesses the private fields of Vec, so it can only be written in the same module -as Vec. - -It is therefore possible for us to write a completely safe abstraction that -relies on complex invariants. This is *critical* to the relationship between -Safe Rust and Unsafe Rust. We have already seen that Unsafe code must trust -*some* Safe code, but can't trust *generic* Safe code. It can't trust an -arbitrary implementor of a trait or any function that was passed to it to be -well-behaved in a way that safe code doesn't care about. - -However if unsafe code couldn't prevent client safe code from messing with its -state in arbitrary ways, safety would be a lost cause. Thankfully, it *can* -prevent arbitrary code from messing with critical state due to privacy. - -Safety lives! - From 4369aee65742207f7eece100018fbc4ab6b42b2c Mon Sep 17 00:00:00 2001 From: steveklabnik Date: Thu, 2 Mar 2017 20:15:41 -0500 Subject: [PATCH 09/24] import nomicon submodule --- .gitmodules | 3 +++ src/doc/nomicon | 1 + 2 files changed, 4 insertions(+) create mode 160000 src/doc/nomicon diff --git a/.gitmodules b/.gitmodules index 2beff77267efa..2b2d8a0150ef6 100644 --- a/.gitmodules +++ b/.gitmodules @@ -18,6 +18,9 @@ [submodule "src/liblibc"] path = src/liblibc url = https://github.com/rust-lang/libc.git +[submodule "src/doc/nomicon"] + path = src/doc/nomicon + url = https://github.com/rust-lang-nursery/nomicon [submodule "src/tools/cargo"] path = src/tools/cargo url = https://github.com/rust-lang/cargo diff --git a/src/doc/nomicon b/src/doc/nomicon new file mode 160000 index 0000000000000..d08fe97d12b41 --- /dev/null +++ b/src/doc/nomicon @@ -0,0 +1 @@ +Subproject commit d08fe97d12b41c1ed8cc7701e545864132783941 From 03b83a01add2167d81b57ff137359ec382d4dcf5 Mon Sep 17 00:00:00 2001 From: Jack O'Connor Date: Sun, 5 Mar 2017 16:39:24 -0500 Subject: [PATCH 10/24] clarify docs for Args and ArgsOs The args() and args_os() docs include a line about how the first element is usually the program name. Include that line in the struct docs too. --- src/libstd/env.rs | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/src/libstd/env.rs b/src/libstd/env.rs index dd4f1ff4f5ed7..64eb52e28bc42 100644 --- a/src/libstd/env.rs +++ b/src/libstd/env.rs @@ -590,6 +590,10 @@ pub fn current_exe() -> io::Result { /// /// This structure is created through the [`std::env::args`] function. /// +/// The first element is traditionally the path of the executable, but it can be +/// set to arbitrary text, and may not even exist. This means this property should +/// not be relied upon for security purposes. +/// /// [`String`]: ../string/struct.String.html /// [`std::env::args`]: ./fn.args.html #[stable(feature = "env", since = "1.0.0")] @@ -600,6 +604,10 @@ pub struct Args { inner: ArgsOs } /// /// This structure is created through the [`std::env::args_os`] function. /// +/// The first element is traditionally the path of the executable, but it can be +/// set to arbitrary text, and may not even exist. This means this property should +/// not be relied upon for security purposes. +/// /// [`OsString`]: ../ffi/struct.OsString.html /// [`std::env::args_os`]: ./fn.args_os.html #[stable(feature = "env", since = "1.0.0")] From 86bad49ec1f787a4f69a77ccffa06e4967d0c796 Mon Sep 17 00:00:00 2001 From: Joshua Horwitz Date: Fri, 3 Mar 2017 01:24:19 -0500 Subject: [PATCH 11/24] Issue #39688 - Help people find String::as_bytes() for UTF-8 r? @steveklabnik --- src/libcollections/string.rs | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/src/libcollections/string.rs b/src/libcollections/string.rs index 4979107ccadc7..43323676ab459 100644 --- a/src/libcollections/string.rs +++ b/src/libcollections/string.rs @@ -433,6 +433,10 @@ impl String { /// /// [`str::from_utf8()`]: ../../std/str/fn.from_utf8.html /// + /// The inverse of this method is [`as_bytes`]. + /// + /// [`as_bytes`]: #method.as_bytes + /// /// # Errors /// /// Returns `Err` if the slice is not UTF-8 with a description as to why the @@ -979,6 +983,10 @@ impl String { /// Returns a byte slice of this `String`'s contents. /// + /// The inverse of this method is [`from_utf8`]. + /// + /// [`from_utf8`]: #method.from_utf8 + /// /// # Examples /// /// Basic usage: From f121e6180b448f798cd13a097244386772c78b40 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=C3=A1ty=C3=A1s=20Mustoha?= Date: Mon, 6 Mar 2017 12:29:52 +0100 Subject: [PATCH 12/24] Fix text formatting in README --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 93415adc423f4..79f11144a073d 100644 --- a/README.md +++ b/README.md @@ -149,7 +149,7 @@ $ ./configure $ make && sudo make install ``` -When using the configure script, the generated config.mk` file may override the +When using the configure script, the generated `config.mk` file may override the `config.toml` file. To go back to the `config.toml` file, delete the generated `config.mk` file. From 2e5b38018089823cd9db733af37f773e29b9f9d5 Mon Sep 17 00:00:00 2001 From: Marco A L Barbosa Date: Mon, 6 Mar 2017 10:05:31 -0300 Subject: [PATCH 13/24] Remove extra space in test description (of a mod test) --- src/librustdoc/test.rs | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/src/librustdoc/test.rs b/src/librustdoc/test.rs index c7000ee1e40e7..c1ecc241b7b63 100644 --- a/src/librustdoc/test.rs +++ b/src/librustdoc/test.rs @@ -422,8 +422,11 @@ impl Collector { as_test_harness: bool, compile_fail: bool, error_codes: Vec, line: usize, filename: String) { let name = if self.use_headers { - let s = self.current_header.as_ref().map(|s| &**s).unwrap_or(""); - format!("{} - {} (line {})", filename, s, line) + if let Some(ref header) = self.current_header { + format!("{} - {} (line {})", filename, header, line) + } else { + format!("{} - (line {})", filename, line) + } } else { format!("{} - {} (line {})", filename, self.names.join("::"), line) }; From 2bb2a2975f25e8ba7a372898e7e112f1cec5db01 Mon Sep 17 00:00:00 2001 From: Wesley Wiser Date: Wed, 15 Feb 2017 20:21:25 -0500 Subject: [PATCH 14/24] Improve the style of the sidebar in rustdoc output Makes the sidebar a light grey and highlights the currently viewed item in the sidebar more prominently. All visual design credit goes to @johnwhelchel (#37856) --- src/librustdoc/html/static/rustdoc.css | 11 ++++++++++- src/librustdoc/html/static/styles/main.css | 11 ++++++++++- 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/src/librustdoc/html/static/rustdoc.css b/src/librustdoc/html/static/rustdoc.css index b0bf69b0181f2..6bd9cf6620b0e 100644 --- a/src/librustdoc/html/static/rustdoc.css +++ b/src/librustdoc/html/static/rustdoc.css @@ -167,7 +167,11 @@ nav.sub { position: absolute; left: 0; top: 0; - min-height: 100%; + min-height: 100vh; +} + +.sidebar .current { + margin-right: -20px; } .content, nav { max-width: 960px; } @@ -185,11 +189,16 @@ nav.sub { } .sidebar .location { + border: 1px solid; font-size: 17px; margin: 30px 0 20px 0; text-align: center; } +.location:empty { + border: none; +} + .location a:first-child { font-weight: 500; } .block { diff --git a/src/librustdoc/html/static/styles/main.css b/src/librustdoc/html/static/styles/main.css index 862d6d12b9ad9..f1e81900d1eec 100644 --- a/src/librustdoc/html/static/styles/main.css +++ b/src/librustdoc/html/static/styles/main.css @@ -37,8 +37,17 @@ pre { background-color: #F5F5F5; } +.sidebar { + background-color: #F1F1F1; +} + +.sidebar .current { + background-color: #fff; +} + .sidebar .location { - background: #e1e1e1; + border-color: #000; + background-color: #fff; color: #333; } From 4f424b3c5a3e47732ca39cc14466b0e0d21f488a Mon Sep 17 00:00:00 2001 From: Taylor Cramer Date: Mon, 6 Mar 2017 18:16:57 -0800 Subject: [PATCH 15/24] Add compile-fail tests for catch expr in match or condition --- src/test/compile-fail/catch-in-match.rs | 15 +++++++++++++++ src/test/compile-fail/catch-in-while.rs | 15 +++++++++++++++ 2 files changed, 30 insertions(+) create mode 100644 src/test/compile-fail/catch-in-match.rs create mode 100644 src/test/compile-fail/catch-in-while.rs diff --git a/src/test/compile-fail/catch-in-match.rs b/src/test/compile-fail/catch-in-match.rs new file mode 100644 index 0000000000000..9f9968e81242a --- /dev/null +++ b/src/test/compile-fail/catch-in-match.rs @@ -0,0 +1,15 @@ +// Copyright 2017 The Rust Project Developers. See the COPYRIGHT +// file at the top-level directory of this distribution and at +// http://rust-lang.org/COPYRIGHT. +// +// Licensed under the Apache License, Version 2.0 or the MIT license +// , at your +// option. This file may not be copied, modified, or distributed +// except according to those terms. + +#![feature(catch_expr)] + +fn main() { + match do catch { false } { _ => {} } //~ ERROR expected expression, found reserved keyword `do` +} diff --git a/src/test/compile-fail/catch-in-while.rs b/src/test/compile-fail/catch-in-while.rs new file mode 100644 index 0000000000000..cb8613ee60b42 --- /dev/null +++ b/src/test/compile-fail/catch-in-while.rs @@ -0,0 +1,15 @@ +// Copyright 2017 The Rust Project Developers. See the COPYRIGHT +// file at the top-level directory of this distribution and at +// http://rust-lang.org/COPYRIGHT. +// +// Licensed under the Apache License, Version 2.0 or the MIT license +// , at your +// option. This file may not be copied, modified, or distributed +// except according to those terms. + +#![feature(catch_expr)] + +fn main() { + while do catch { false } {} //~ ERROR expected expression, found reserved keyword `do` +} From acd8fe8fe875d51ea4fa723f1e73819a56bfec8a Mon Sep 17 00:00:00 2001 From: Oliver Schneider Date: Tue, 7 Mar 2017 10:45:13 +0100 Subject: [PATCH 16/24] Fix a typo in the docs --- src/librustc/ty/mod.rs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/librustc/ty/mod.rs b/src/librustc/ty/mod.rs index d7efee06db2b5..be04b0e6577f0 100644 --- a/src/librustc/ty/mod.rs +++ b/src/librustc/ty/mod.rs @@ -1286,7 +1286,7 @@ pub struct Destructor { /// invoked even when there are lifetimes in the type-structure of /// `adt` that do not strictly outlive the adt value itself. /// (This allows programs to make cyclic structures without - /// resorting to unasfe means; see RFCs 769 and 1238). + /// resorting to unsafe means; see RFCs 769 and 1238). pub is_dtorck: bool, } From 4fd93df90b9feca64ca5d915aa79b336e1aa2edd Mon Sep 17 00:00:00 2001 From: Marco A L Barbosa Date: Tue, 7 Mar 2017 10:17:55 -0300 Subject: [PATCH 17/24] Update libc to 0.2.21 --- src/liblibc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/liblibc b/src/liblibc index 64d954c6a76e8..05a2d197356ef 160000 --- a/src/liblibc +++ b/src/liblibc @@ -1 +1 @@ -Subproject commit 64d954c6a76e896fbf7ed5c17e77c40e388abe84 +Subproject commit 05a2d197356ef253dfd985166576619ac9b6947f From f283141656e0cd340ebbd7285c7b22ccf2276091 Mon Sep 17 00:00:00 2001 From: Joel Gallant Date: Tue, 7 Mar 2017 09:00:33 -0700 Subject: [PATCH 18/24] README formatting in configure/make section --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 93415adc423f4..79f11144a073d 100644 --- a/README.md +++ b/README.md @@ -149,7 +149,7 @@ $ ./configure $ make && sudo make install ``` -When using the configure script, the generated config.mk` file may override the +When using the configure script, the generated `config.mk` file may override the `config.toml` file. To go back to the `config.toml` file, delete the generated `config.mk` file. From b5533d2953941a7dab5677b3c34151fe5d6d0656 Mon Sep 17 00:00:00 2001 From: CrazyMerlyn Date: Tue, 7 Mar 2017 23:13:31 +0530 Subject: [PATCH 19/24] Update link to COMPILER_TESTS.md in CONTRIBUTING.md --- CONTRIBUTING.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 1e983cfd726d6..f921fb2c94233 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -406,5 +406,5 @@ are: [rr]: https://doc.rust-lang.org/book/README.html [tlgba]: http://tomlee.co/2014/04/a-more-detailed-tour-of-the-rust-compiler/ [ro]: http://www.rustaceans.org/ -[rctd]: ./COMPILER_TESTS.md +[rctd]: ./src/test/COMPILER_TESTS.md [cheatsheet]: https://buildbot.rust-lang.org/homu/ From df617195f06c27821803acc87e0b1b0dd288799a Mon Sep 17 00:00:00 2001 From: madseagames Date: Sat, 3 Dec 2016 12:47:27 -0400 Subject: [PATCH 20/24] Added remove_from to vec.rs --- src/libcollections/vec.rs | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/src/libcollections/vec.rs b/src/libcollections/vec.rs index 3134e3c2ce12f..d38c9f6e1cf80 100644 --- a/src/libcollections/vec.rs +++ b/src/libcollections/vec.rs @@ -1335,6 +1335,27 @@ impl Vec { pub fn dedup(&mut self) { self.dedup_by(|a, b| a == b) } + + /// Removes the first instance of `item` from the vector if the item exists. + /// + /// # Examples + /// + /// ``` + ///# #![feature(vec_remove_item)] + /// let mut vec = vec![1, 2, 3, 1]; + /// + /// vec.remove_item(&1); + /// + /// assert_eq!(vec, vec![2, 3, 1]); + /// ``` + #[unstable(feature = "vec_remove_item", reason = "recently added", issue = "40062")] + pub fn remove_item(&mut self, item: &T) -> Option { + let pos = match self.iter().position(|x| *x == *item) { + Some(x) => x, + None => return None, + }; + Some(self.remove(pos)) + } } //////////////////////////////////////////////////////////////////////////////// From 65ac1e92fe0f77ce5d64960c32c6fa074e1442ce Mon Sep 17 00:00:00 2001 From: Guillaume Gomez Date: Tue, 7 Mar 2017 19:13:17 +0100 Subject: [PATCH 21/24] Add missing urls in some macros doc --- src/libcore/macros.rs | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/src/libcore/macros.rs b/src/libcore/macros.rs index 66a923f8e588a..b22f7fa17077b 100644 --- a/src/libcore/macros.rs +++ b/src/libcore/macros.rs @@ -32,11 +32,11 @@ macro_rules! panic { /// Ensure that a boolean expression is `true` at runtime. /// -/// This will invoke the `panic!` macro if the provided expression cannot be +/// This will invoke the [`panic!`] macro if the provided expression cannot be /// evaluated to `true` at runtime. /// /// Assertions are always checked in both debug and release builds, and cannot -/// be disabled. See `debug_assert!` for assertions that are not enabled in +/// be disabled. See [`debug_assert!`] for assertions that are not enabled in /// release builds by default. /// /// Unsafe code relies on `assert!` to enforce run-time invariants that, if @@ -48,6 +48,8 @@ macro_rules! panic { /// This macro has a second version, where a custom panic message can /// be provided with or without arguments for formatting. /// +/// [`panic!`]: macro.panic.html +/// [`debug_assert!`]: macro.debug_assert.html /// [testing]: ../book/testing.html /// /// # Examples @@ -88,9 +90,11 @@ macro_rules! assert { /// On panic, this macro will print the values of the expressions with their /// debug representations. /// -/// Like `assert!()`, this macro has a second version, where a custom +/// Like [`assert!()`], this macro has a second version, where a custom /// panic message can be provided. /// +/// [`assert!()`]: macro.assert.html +/// /// # Examples /// /// ``` @@ -134,6 +138,8 @@ macro_rules! assert_eq { /// Like `assert!()`, this macro has a second version, where a custom /// panic message can be provided. /// +/// [`assert!`]: macro.assert.html +/// /// # Examples /// /// ``` @@ -171,13 +177,13 @@ macro_rules! assert_ne { /// Ensure that a boolean expression is `true` at runtime. /// -/// This will invoke the `panic!` macro if the provided expression cannot be +/// This will invoke the [`panic!`] macro if the provided expression cannot be /// evaluated to `true` at runtime. /// -/// Like `assert!`, this macro also has a second version, where a custom panic +/// Like [`assert!`], this macro also has a second version, where a custom panic /// message can be provided. /// -/// Unlike `assert!`, `debug_assert!` statements are only enabled in non +/// Unlike [`assert!`], `debug_assert!` statements are only enabled in non /// optimized builds by default. An optimized build will omit all /// `debug_assert!` statements unless `-C debug-assertions` is passed to the /// compiler. This makes `debug_assert!` useful for checks that are too @@ -187,10 +193,13 @@ macro_rules! assert_ne { /// An unchecked assertion allows a program in an inconsistent state to keep /// running, which might have unexpected consequences but does not introduce /// unsafety as long as this only happens in safe code. The performance cost -/// of assertions, is however, not measurable in general. Replacing `assert!` +/// of assertions, is however, not measurable in general. Replacing [`assert!`] /// with `debug_assert!` is thus only encouraged after thorough profiling, and /// more importantly, only in safe code! /// +/// [`panic!`]: macro.panic.html +/// [`assert!`]: macro.assert.html +/// /// # Examples /// /// ``` From 025bf9582eb97d72d71ed54fc52941dbb836cf48 Mon Sep 17 00:00:00 2001 From: Tobias Bucher Date: Tue, 7 Mar 2017 23:39:49 +0100 Subject: [PATCH 22/24] Clarify handling of `src` in `ptr::write` Fixes #39733. --- src/libcore/ptr.rs | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/src/libcore/ptr.rs b/src/libcore/ptr.rs index 02851c224e2e3..260fdab9d58fb 100644 --- a/src/libcore/ptr.rs +++ b/src/libcore/ptr.rs @@ -191,6 +191,10 @@ pub unsafe fn read_unaligned(src: *const T) -> T { /// allocations or resources, so care must be taken not to overwrite an object /// that should be dropped. /// +/// It does not immediately drop the contents of `src` either; it is rather +/// *moved* into the memory location `dst` and will be dropped whenever that +/// location goes out of scope. +/// /// This is appropriate for initializing uninitialized memory, or overwriting /// memory that has previously been `read` from. /// From f3a2f90c88c9d890b67955f0b88def40ce372914 Mon Sep 17 00:00:00 2001 From: Tobias Bucher Date: Wed, 8 Mar 2017 00:06:09 +0100 Subject: [PATCH 23/24] Document why `str.to_{lower,upper}case` return `String` Fixes #39201. --- src/libcollections/str.rs | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/src/libcollections/str.rs b/src/libcollections/str.rs index 87315fff0a07d..e27c45773441a 100644 --- a/src/libcollections/str.rs +++ b/src/libcollections/str.rs @@ -1646,6 +1646,10 @@ impl str { /// 'Lowercase' is defined according to the terms of the Unicode Derived Core Property /// `Lowercase`. /// + /// Since some characters can expand into multiple characters when changing + /// the case, this function returns a [`String`] instead of modifying the + /// parameter in-place. + /// /// [`String`]: string/struct.String.html /// /// # Examples @@ -1718,6 +1722,10 @@ impl str { /// 'Uppercase' is defined according to the terms of the Unicode Derived Core Property /// `Uppercase`. /// + /// Since some characters can expand into multiple characters when changing + /// the case, this function returns a [`String`] instead of modifying the + /// parameter in-place. + /// /// [`String`]: string/struct.String.html /// /// # Examples From e412af2a887da25c987d4ca367b7b471b6c5fb55 Mon Sep 17 00:00:00 2001 From: Alex Crichton Date: Tue, 7 Mar 2017 15:24:36 -0800 Subject: [PATCH 24/24] rustbuild: Assert directory creation succeeds I've been seeing failures on the bots when building jemalloc and my assumption is that it's because cwd isn't created. That may be possible if this `create_dir_all` call change in this commit fails, in which case we ignore the error. This commit updates the location to call `create_dir_racy` which handles concurrent invocations, as multiple build scripts may be trying to create the `native` dir. --- src/build_helper/lib.rs | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/src/build_helper/lib.rs b/src/build_helper/lib.rs index dffaebbd92914..cb58a916fb797 100644 --- a/src/build_helper/lib.rs +++ b/src/build_helper/lib.rs @@ -12,10 +12,11 @@ extern crate filetime; -use std::{fs, env}; use std::fs::File; -use std::process::{Command, Stdio}; +use std::io; use std::path::{Path, PathBuf}; +use std::process::{Command, Stdio}; +use std::{fs, env}; use filetime::FileTime; @@ -196,7 +197,7 @@ pub fn native_lib_boilerplate(src_name: &str, let out_dir = env::var_os("RUSTBUILD_NATIVE_DIR").unwrap_or(env::var_os("OUT_DIR").unwrap()); let out_dir = PathBuf::from(out_dir).join(out_name); - let _ = fs::create_dir_all(&out_dir); + t!(create_dir_racy(&out_dir)); println!("cargo:rustc-link-lib=static={}", link_name); println!("cargo:rustc-link-search=native={}", out_dir.join(search_subdir).display()); @@ -223,3 +224,21 @@ fn fail(s: &str) -> ! { println!("\n\n{}\n\n", s); std::process::exit(1); } + +fn create_dir_racy(path: &Path) -> io::Result<()> { + match fs::create_dir(path) { + Ok(()) => return Ok(()), + Err(ref e) if e.kind() == io::ErrorKind::AlreadyExists => return Ok(()), + Err(ref e) if e.kind() == io::ErrorKind::NotFound => {} + Err(e) => return Err(e), + } + match path.parent() { + Some(p) => try!(create_dir_racy(p)), + None => return Err(io::Error::new(io::ErrorKind::Other, "failed to create whole tree")), + } + match fs::create_dir(path) { + Ok(()) => Ok(()), + Err(ref e) if e.kind() == io::ErrorKind::AlreadyExists => Ok(()), + Err(e) => Err(e), + } +}