auto merge of #19654 : aturon/rust/merge-rt, r=alexcrichton

This PR substantially narrows the notion of a "runtime" in Rust, and allows calling into Rust code directly without any setup or teardown. 

After this PR, the basic "runtime support" in Rust will consist of:

* Unwinding and backtrace support
* Stack guards

Other support, such as helper threads for timers or the notion of a "current thread" are initialized automatically upon first use.

When using Rust in an embedded context, it should now be possible to call a Rust function directly as a C function with absolutely no setup, though in that case panics will cause the process to abort. In this regard, the C/Rust interface will look much like the C/C++ interface.

In more detail, this PR:

* Merges `librustrt` back into `std::rt`, undoing the facade. While doing so, it removes a substantial amount of redundant functionality (such as mutexes defined in the `rt` module). Code using `librustrt` can now call into `std::rt` to e.g. start executing Rust code with unwinding support.

* Allows all runtime data to be initialized lazily, including the "current thread", the "at_exit" infrastructure, and the "args" storage.

* Deprecates and largely removes `std::task` along with the widespread requirement that there be a "current task" for many APIs in `std`. The entire task infrastructure is replaced with `std::thread`, which provides a more standard API for manipulating and creating native OS threads. In particular, it's possible to join on a created thread, and to get a handle to the currently-running thread. In addition, threads are equipped with some basic blocking support in the form of `park`/`unpark` operations (following a tradition in some OSes as well as the JVM). See the `std::thread` documentation for more details.

* Channels are refactored to use a new internal blocking infrastructure that itself sits on top of `park`/`unpark`.

One important change here is that a Rust program ends when its main thread does, following most threading models. On the other hand, threads will often be created with an RAII-style join handle that will re-institute blocking semantics naturally (and with finer control).

This is very much a:

[breaking-change]

Closes #18000
r? @alexcrichton 

7 files changed, 578 insertions, 11 deletions

diff --git a/src/libstd/sys/common/backtrace.rs b/src/libstd/sys/common/backtrace.rs
new file mode 100644
index 00000000000..a39c8d6d8fe
--- /dev/null
+++ b/src/libstd/sys/common/backtrace.rs
@@ -0,0 +1,139 @@
+// Copyright 2014 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 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+use io::{IoResult, Writer};
+use iter::{Iterator, IteratorExt};
+use option::Option::{Some, None};
+use result::Result::{Ok, Err};
+use str::{StrPrelude, from_str};
+use unicode::char::UnicodeChar;
+
+#[cfg(target_word_size = "64")] pub const HEX_WIDTH: uint = 18;
+#[cfg(target_word_size = "32")] pub const HEX_WIDTH: uint = 10;
+
+// All rust symbols are in theory lists of "::"-separated identifiers. Some
+// assemblers, however, can't handle these characters in symbol names. To get
+// around this, we use C++-style mangling. The mangling method is:
+//
+// 1. Prefix the symbol with "_ZN"
+// 2. For each element of the path, emit the length plus the element
+// 3. End the path with "E"
+//
+// For example, "_ZN4testE" => "test" and "_ZN3foo3bar" => "foo::bar".
+//
+// We're the ones printing our backtraces, so we can't rely on anything else to
+// demangle our symbols. It's *much* nicer to look at demangled symbols, so
+// this function is implemented to give us nice pretty output.
+//
+// Note that this demangler isn't quite as fancy as it could be. We have lots
+// of other information in our symbols like hashes, version, type information,
+// etc. Additionally, this doesn't handle glue symbols at all.
+pub fn demangle(writer: &mut Writer, s: &str) -> IoResult<()> {
+    // First validate the symbol. If it doesn't look like anything we're
+    // expecting, we just print it literally. Note that we must handle non-rust
+    // symbols because we could have any function in the backtrace.
+    let mut valid = true;
+    let mut inner = s;
+    if s.len() > 4 && s.starts_with("_ZN") && s.ends_with("E") {
+        inner = s.slice(3, s.len() - 1);
+    // On Windows, dbghelp strips leading underscores, so we accept "ZN...E" form too.
+    } else if s.len() > 3 && s.starts_with("ZN") && s.ends_with("E") {
+        inner = s.slice(2, s.len() - 1);
+    } else {
+        valid = false;
+    }
+
+    if valid {
+        let mut chars = inner.chars();
+        while valid {
+            let mut i = 0;
+            for c in chars {
+                if c.is_numeric() {
+                    i = i * 10 + c as uint - '0' as uint;
+                } else {
+                    break
+                }
+            }
+            if i == 0 {
+                valid = chars.next().is_none();
+                break
+            } else if chars.by_ref().take(i - 1).count() != i - 1 {
+                valid = false;
+            }
+        }
+    }
+
+    // Alright, let's do this.
+    if !valid {
+        try!(writer.write_str(s));
+    } else {
+        let mut first = true;
+        while inner.len() > 0 {
+            if !first {
+                try!(writer.write_str("::"));
+            } else {
+                first = false;
+            }
+            let mut rest = inner;
+            while rest.char_at(0).is_numeric() {
+                rest = rest.slice_from(1);
+            }
+            let i: uint = from_str(inner.slice_to(inner.len() - rest.len())).unwrap();
+            inner = rest.slice_from(i);
+            rest = rest.slice_to(i);
+            while rest.len() > 0 {
+                if rest.starts_with("$") {
+                    macro_rules! demangle {
+                        ($($pat:expr => $demangled:expr),*) => ({
+                            $(if rest.starts_with($pat) {
+                                try!(writer.write_str($demangled));
+                                rest = rest.slice_from($pat.len());
+                              } else)*
+                            {
+                                try!(writer.write_str(rest));
+                                break;
+                            }
+
+                        })
+                    }
+
+                    // see src/librustc/back/link.rs for these mappings
+                    demangle! (
+                        "$SP$" => "@",
+                        "$UP$" => "Box",
+                        "$RP$" => "*",
+                        "$BP$" => "&",
+                        "$LT$" => "<",
+                        "$GT$" => ">",
+                        "$LP$" => "(",
+                        "$RP$" => ")",
+                        "$C$"  => ",",
+
+                        // in theory we can demangle any Unicode code point, but
+                        // for simplicity we just catch the common ones.
+                        "$x20" => " ",
+                        "$x27" => "'",
+                        "$x5b" => "[",
+                        "$x5d" => "]"
+                    )
+                } else {
+                    let idx = match rest.find('$') {
+                        None => rest.len(),
+                        Some(i) => i,
+                    };
+                    try!(writer.write_str(rest.slice_to(idx)));
+                    rest = rest.slice_from(idx);
+                }
+            }
+        }
+    }
+
+    Ok(())
+}
diff --git a/src/libstd/sys/common/helper_thread.rs b/src/libstd/sys/common/helper_thread.rs
index 96b4accd4bd..421778e2012 100644
--- a/src/libstd/sys/common/helper_thread.rs
+++ b/src/libstd/sys/common/helper_thread.rs
@@ -24,12 +24,11 @@ use prelude::*;
 
 use cell::UnsafeCell;
 use mem;
-use rustrt::bookkeeping;
-use rustrt;
 use sync::{StaticMutex, StaticCondvar};
+use rt;
 use sys::helper_signal;
 
-use task;
+use thread::Thread;
 
 /// A structure for management of a helper thread.
 ///
@@ -83,15 +82,14 @@ impl<M: Send> Helper<M> {
                 *self.signal.get() = send as uint;
 
                 let t = f();
-                task::spawn(move |:| {
-                    bookkeeping::decrement();
+                Thread::spawn(move |:| {
                     helper(receive, rx, t);
                     let _g = self.lock.lock();
                     *self.shutdown.get() = true;
                     self.cond.notify_one()
-                });
+                }).detach();
 
-                rustrt::at_exit(move|:| { self.shutdown() });
+                rt::at_exit(move|:| { self.shutdown() });
                 *self.initialized.get() = true;
             }
         }
diff --git a/src/libstd/sys/common/mod.rs b/src/libstd/sys/common/mod.rs
index 73e1c7bd9e5..dc0ad08cdbe 100644
--- a/src/libstd/sys/common/mod.rs
+++ b/src/libstd/sys/common/mod.rs
@@ -19,11 +19,15 @@ use num::Int;
 use path::BytesContainer;
 use collections;
 
+pub mod backtrace;
 pub mod condvar;
 pub mod helper_thread;
 pub mod mutex;
 pub mod net;
 pub mod rwlock;
+pub mod stack;
+pub mod thread;
+pub mod thread_info;
 pub mod thread_local;
 
 // common error constructors
diff --git a/src/libstd/sys/common/stack.rs b/src/libstd/sys/common/stack.rs
new file mode 100644
index 00000000000..2a88e20c8fa
--- /dev/null
+++ b/src/libstd/sys/common/stack.rs
@@ -0,0 +1,325 @@
+// Copyright 2013 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 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+//! Rust stack-limit management
+//!
+//! Currently Rust uses a segmented-stack-like scheme in order to detect stack
+//! overflow for rust tasks. In this scheme, the prologue of all functions are
+//! preceded with a check to see whether the current stack limits are being
+//! exceeded.
+//!
+//! This module provides the functionality necessary in order to manage these
+//! stack limits (which are stored in platform-specific locations). The
+//! functions here are used at the borders of the task lifetime in order to
+//! manage these limits.
+//!
+//! This function is an unstable module because this scheme for stack overflow
+//! detection is not guaranteed to continue in the future. Usage of this module
+//! is discouraged unless absolutely necessary.
+
+// iOS related notes
+//
+// It is possible to implement it using idea from
+// http://www.opensource.apple.com/source/Libc/Libc-825.40.1/pthreads/pthread_machdep.h
+//
+// In short: _pthread_{get,set}_specific_direct allows extremely fast
+// access, exactly what is required for segmented stack
+// There is a pool of reserved slots for Apple internal use (0..119)
+// First dynamic allocated pthread key starts with 257 (on iOS7)
+// So using slot 149 should be pretty safe ASSUMING space is reserved
+// for every key < first dynamic key
+//
+// There is also an opportunity to steal keys reserved for Garbage Collection
+// ranges 80..89 and 110..119, especially considering the fact Garbage Collection
+// never supposed to work on iOS. But as everybody knows it - there is a chance
+// that those slots will be re-used, like it happened with key 95 (moved from
+// JavaScriptCore to CoreText)
+//
+// Unfortunately Apple rejected patch to LLVM which generated
+// corresponding prolog, decision was taken to disable segmented
+// stack support on iOS.
+
+pub const RED_ZONE: uint = 20 * 1024;
+
+/// This function is invoked from rust's current __morestack function. Segmented
+/// stacks are currently not enabled as segmented stacks, but rather one giant
+/// stack segment. This means that whenever we run out of stack, we want to
+/// truly consider it to be stack overflow rather than allocating a new stack.
+#[cfg(not(test))] // in testing, use the original libstd's version
+#[lang = "stack_exhausted"]
+extern fn stack_exhausted() {
+    use intrinsics;
+
+    unsafe {
+        // We're calling this function because the stack just ran out. We need
+        // to call some other rust functions, but if we invoke the functions
+        // right now it'll just trigger this handler being called again. In
+        // order to alleviate this, we move the stack limit to be inside of the
+        // red zone that was allocated for exactly this reason.
+        let limit = get_sp_limit();
+        record_sp_limit(limit - RED_ZONE / 2);
+
+        // This probably isn't the best course of action. Ideally one would want
+        // to unwind the stack here instead of just aborting the entire process.
+        // This is a tricky problem, however. There's a few things which need to
+        // be considered:
+        //
+        //  1. We're here because of a stack overflow, yet unwinding will run
+        //     destructors and hence arbitrary code. What if that code overflows
+        //     the stack? One possibility is to use the above allocation of an
+        //     extra 10k to hope that we don't hit the limit, and if we do then
+        //     abort the whole program. Not the best, but kind of hard to deal
+        //     with unless we want to switch stacks.
+        //
+        //  2. LLVM will optimize functions based on whether they can unwind or
+        //     not. It will flag functions with 'nounwind' if it believes that
+        //     the function cannot trigger unwinding, but if we do unwind on
+        //     stack overflow then it means that we could unwind in any function
+        //     anywhere. We would have to make sure that LLVM only places the
+        //     nounwind flag on functions which don't call any other functions.
+        //
+        //  3. The function that overflowed may have owned arguments. These
+        //     arguments need to have their destructors run, but we haven't even
+        //     begun executing the function yet, so unwinding will not run the
+        //     any landing pads for these functions. If this is ignored, then
+        //     the arguments will just be leaked.
+        //
+        // Exactly what to do here is a very delicate topic, and is possibly
+        // still up in the air for what exactly to do. Some relevant issues:
+        //
+        //  #3555 - out-of-stack failure leaks arguments
+        //  #3695 - should there be a stack limit?
+        //  #9855 - possible strategies which could be taken
+        //  #9854 - unwinding on windows through __morestack has never worked
+        //  #2361 - possible implementation of not using landing pads
+
+        ::rt::util::report_overflow();
+
+        intrinsics::abort();
+    }
+}
+
+// Windows maintains a record of upper and lower stack bounds in the Thread Information
+// Block (TIB), and some syscalls do check that addresses which are supposed to be in
+// the stack, indeed lie between these two values.
+// (See https://github.com/rust-lang/rust/issues/3445#issuecomment-26114839)
+//
+// When using Rust-managed stacks (libgreen), we must maintain these values accordingly.
+// For OS-managed stacks (libnative), we let the OS manage them for us.
+//
+// On all other platforms both variants behave identically.
+
+#[inline(always)]
+pub unsafe fn record_os_managed_stack_bounds(stack_lo: uint, _stack_hi: uint) {
+    record_sp_limit(stack_lo + RED_ZONE);
+}
+
+#[inline(always)]
+pub unsafe fn record_rust_managed_stack_bounds(stack_lo: uint, stack_hi: uint) {
+    // When the old runtime had segmented stacks, it used a calculation that was
+    // "limit + RED_ZONE + FUDGE". The red zone was for things like dynamic
+    // symbol resolution, llvm function calls, etc. In theory this red zone
+    // value is 0, but it matters far less when we have gigantic stacks because
+    // we don't need to be so exact about our stack budget. The "fudge factor"
+    // was because LLVM doesn't emit a stack check for functions < 256 bytes in
+    // size. Again though, we have giant stacks, so we round all these
+    // calculations up to the nice round number of 20k.
+    record_sp_limit(stack_lo + RED_ZONE);
+
+    return target_record_stack_bounds(stack_lo, stack_hi);
+
+    #[cfg(not(windows))] #[inline(always)]
+    unsafe fn target_record_stack_bounds(_stack_lo: uint, _stack_hi: uint) {}
+
+    #[cfg(all(windows, target_arch = "x86"))] #[inline(always)]
+    unsafe fn target_record_stack_bounds(stack_lo: uint, stack_hi: uint) {
+        // stack range is at TIB: %fs:0x04 (top) and %fs:0x08 (bottom)
+        asm!("mov $0, %fs:0x04" :: "r"(stack_hi) :: "volatile");
+        asm!("mov $0, %fs:0x08" :: "r"(stack_lo) :: "volatile");
+    }
+    #[cfg(all(windows, target_arch = "x86_64"))] #[inline(always)]
+    unsafe fn target_record_stack_bounds(stack_lo: uint, stack_hi: uint) {
+        // stack range is at TIB: %gs:0x08 (top) and %gs:0x10 (bottom)
+        asm!("mov $0, %gs:0x08" :: "r"(stack_hi) :: "volatile");
+        asm!("mov $0, %gs:0x10" :: "r"(stack_lo) :: "volatile");
+    }
+}
+
+/// Records the current limit of the stack as specified by `end`.
+///
+/// This is stored in an OS-dependent location, likely inside of the thread
+/// local storage. The location that the limit is stored is a pre-ordained
+/// location because it's where LLVM has emitted code to check.
+///
+/// Note that this cannot be called under normal circumstances. This function is
+/// changing the stack limit, so upon returning any further function calls will
+/// possibly be triggering the morestack logic if you're not careful.
+///
+/// Also note that this and all of the inside functions are all flagged as
+/// "inline(always)" because they're messing around with the stack limits.  This
+/// would be unfortunate for the functions themselves to trigger a morestack
+/// invocation (if they were an actual function call).
+#[inline(always)]
+pub unsafe fn record_sp_limit(limit: uint) {
+    return target_record_sp_limit(limit);
+
+    // x86-64
+    #[cfg(all(target_arch = "x86_64",
+              any(target_os = "macos", target_os = "ios")))]
+    #[inline(always)]
+    unsafe fn target_record_sp_limit(limit: uint) {
+        asm!("movq $$0x60+90*8, %rsi
+              movq $0, %gs:(%rsi)" :: "r"(limit) : "rsi" : "volatile")
+    }
+    #[cfg(all(target_arch = "x86_64", target_os = "linux"))] #[inline(always)]
+    unsafe fn target_record_sp_limit(limit: uint) {
+        asm!("movq $0, %fs:112" :: "r"(limit) :: "volatile")
+    }
+    #[cfg(all(target_arch = "x86_64", target_os = "windows"))] #[inline(always)]
+    unsafe fn target_record_sp_limit(_: uint) {
+    }
+    #[cfg(all(target_arch = "x86_64", target_os = "freebsd"))] #[inline(always)]
+    unsafe fn target_record_sp_limit(limit: uint) {
+        asm!("movq $0, %fs:24" :: "r"(limit) :: "volatile")
+    }
+    #[cfg(all(target_arch = "x86_64", target_os = "dragonfly"))] #[inline(always)]
+    unsafe fn target_record_sp_limit(limit: uint) {
+        asm!("movq $0, %fs:32" :: "r"(limit) :: "volatile")
+    }
+
+    // x86
+    #[cfg(all(target_arch = "x86",
+              any(target_os = "macos", target_os = "ios")))]
+    #[inline(always)]
+    unsafe fn target_record_sp_limit(limit: uint) {
+        asm!("movl $$0x48+90*4, %eax
+              movl $0, %gs:(%eax)" :: "r"(limit) : "eax" : "volatile")
+    }
+    #[cfg(all(target_arch = "x86",
+              any(target_os = "linux", target_os = "freebsd")))]
+    #[inline(always)]
+    unsafe fn target_record_sp_limit(limit: uint) {
+        asm!("movl $0, %gs:48" :: "r"(limit) :: "volatile")
+    }
+    #[cfg(all(target_arch = "x86", target_os = "windows"))] #[inline(always)]
+    unsafe fn target_record_sp_limit(_: uint) {
+    }
+
+    // mips, arm - Some brave soul can port these to inline asm, but it's over
+    //             my head personally
+    #[cfg(any(target_arch = "mips",
+              target_arch = "mipsel",
+              all(target_arch = "arm", not(target_os = "ios"))))]
+    #[inline(always)]
+    unsafe fn target_record_sp_limit(limit: uint) {
+        use libc::c_void;
+        return record_sp_limit(limit as *const c_void);
+        extern {
+            fn record_sp_limit(limit: *const c_void);
+        }
+    }
+
+    // iOS segmented stack is disabled for now, see related notes
+    #[cfg(all(target_arch = "arm", target_os = "ios"))] #[inline(always)]
+    unsafe fn target_record_sp_limit(_: uint) {
+    }
+}
+
+/// The counterpart of the function above, this function will fetch the current
+/// stack limit stored in TLS.
+///
+/// Note that all of these functions are meant to be exact counterparts of their
+/// brethren above, except that the operands are reversed.
+///
+/// As with the setter, this function does not have a __morestack header and can
+/// therefore be called in a "we're out of stack" situation.
+#[inline(always)]
+pub unsafe fn get_sp_limit() -> uint {
+    return target_get_sp_limit();
+
+    // x86-64
+    #[cfg(all(target_arch = "x86_64",
+              any(target_os = "macos", target_os = "ios")))]
+    #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        let limit;
+        asm!("movq $$0x60+90*8, %rsi
+              movq %gs:(%rsi), $0" : "=r"(limit) :: "rsi" : "volatile");
+        return limit;
+    }
+    #[cfg(all(target_arch = "x86_64", target_os = "linux"))] #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        let limit;
+        asm!("movq %fs:112, $0" : "=r"(limit) ::: "volatile");
+        return limit;
+    }
+    #[cfg(all(target_arch = "x86_64", target_os = "windows"))] #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        return 1024;
+    }
+    #[cfg(all(target_arch = "x86_64", target_os = "freebsd"))] #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        let limit;
+        asm!("movq %fs:24, $0" : "=r"(limit) ::: "volatile");
+        return limit;
+    }
+    #[cfg(all(target_arch = "x86_64", target_os = "dragonfly"))] #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        let limit;
+        asm!("movq %fs:32, $0" : "=r"(limit) ::: "volatile");
+        return limit;
+    }
+
+
+    // x86
+    #[cfg(all(target_arch = "x86",
+              any(target_os = "macos", target_os = "ios")))]
+    #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        let limit;
+        asm!("movl $$0x48+90*4, %eax
+              movl %gs:(%eax), $0" : "=r"(limit) :: "eax" : "volatile");
+        return limit;
+    }
+    #[cfg(all(target_arch = "x86",
+              any(target_os = "linux", target_os = "freebsd")))]
+    #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        let limit;
+        asm!("movl %gs:48, $0" : "=r"(limit) ::: "volatile");
+        return limit;
+    }
+    #[cfg(all(target_arch = "x86", target_os = "windows"))] #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        return 1024;
+    }
+
+    // mips, arm - Some brave soul can port these to inline asm, but it's over
+    //             my head personally
+    #[cfg(any(target_arch = "mips",
+              target_arch = "mipsel",
+              all(target_arch = "arm", not(target_os = "ios"))))]
+    #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        use libc::c_void;
+        return get_sp_limit() as uint;
+        extern {
+            fn get_sp_limit() -> *const c_void;
+        }
+    }
+
+    // iOS doesn't support segmented stacks yet. This function might
+    // be called by runtime though so it is unsafe to mark it as
+    // unreachable, let's return a fixed constant.
+    #[cfg(all(target_arch = "arm", target_os = "ios"))] #[inline(always)]
+    unsafe fn target_get_sp_limit() -> uint {
+        1024
+    }
+}
diff --git a/src/libstd/sys/common/thread.rs b/src/libstd/sys/common/thread.rs
new file mode 100644
index 00000000000..048e33399a3
--- /dev/null
+++ b/src/libstd/sys/common/thread.rs
@@ -0,0 +1,35 @@
+// Copyright 2014 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 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+use core::prelude::*;
+
+use boxed::Box;
+use mem;
+use uint;
+use libc;
+use thunk::Thunk;
+use sys_common::stack;
+use sys::{thread, stack_overflow};
+
+// This is the starting point of rust os threads. The first thing we do
+// is make sure that we don't trigger __morestack (also why this has a
+// no_stack_check annotation), and then we extract the main function
+// and invoke it.
+#[no_stack_check]
+pub fn start_thread(main: *mut libc::c_void) -> thread::rust_thread_return {
+    unsafe {
+        stack::record_os_managed_stack_bounds(0, uint::MAX);
+        let handler = stack_overflow::Handler::new();
+        let f: Box<Thunk> = mem::transmute(main);
+        f.invoke(());
+        drop(handler);
+        mem::transmute(0 as thread::rust_thread_return)
+    }
+}
diff --git a/src/libstd/sys/common/thread_info.rs b/src/libstd/sys/common/thread_info.rs
new file mode 100644
index 00000000000..dc21feb17a8
--- /dev/null
+++ b/src/libstd/sys/common/thread_info.rs
@@ -0,0 +1,68 @@
+// Copyright 2014 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 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+use core::prelude::*;
+
+use thread::Thread;
+use cell::RefCell;
+use string::String;
+
+struct ThreadInfo {
+    // This field holds the known bounds of the stack in (lo, hi)
+    // form. Not all threads necessarily know their precise bounds,
+    // hence this is optional.
+    stack_bounds: (uint, uint),
+    stack_guard: uint,
+    thread: Thread,
+}
+
+thread_local! { static THREAD_INFO: RefCell<Option<ThreadInfo>> = RefCell::new(None) }
+
+impl ThreadInfo {
+    fn with<R>(f: |&mut ThreadInfo| -> R) -> R {
+        if THREAD_INFO.destroyed() {
+            panic!("Use of std::thread::Thread::current() is not possible after \
+                    the thread's local data has been destroyed");
+        }
+
+        THREAD_INFO.with(|c| {
+            if c.borrow().is_none() {
+                *c.borrow_mut() = Some(ThreadInfo {
+                    stack_bounds: (0, 0),
+                    stack_guard: 0,
+                    thread: NewThread::new(None),
+                })
+            }
+            f(c.borrow_mut().as_mut().unwrap())
+        })
+    }
+}
+
+pub fn current_thread() -> Thread {
+    ThreadInfo::with(|info| info.thread.clone())
+}
+
+pub fn stack_guard() -> uint {
+    ThreadInfo::with(|info| info.stack_guard)
+}
+
+pub fn set(stack_bounds: (uint, uint), stack_guard: uint, thread: Thread) {
+    THREAD_INFO.with(|c| assert!(c.borrow().is_none()));
+    THREAD_INFO.with(move |c| *c.borrow_mut() = Some(ThreadInfo{
+        stack_bounds: stack_bounds,
+        stack_guard: stack_guard,
+        thread: thread,
+    }));
+}
+
+// a hack to get around privacy restrictions; implemented by `std::thread::Thread`
+pub trait NewThread {
+    fn new(name: Option<String>) -> Self;
+}
diff --git a/src/libstd/sys/common/thread_local.rs b/src/libstd/sys/common/thread_local.rs
index cf56a71d67a..fe7a7d8d037 100644
--- a/src/libstd/sys/common/thread_local.rs
+++ b/src/libstd/sys/common/thread_local.rs
@@ -58,9 +58,8 @@
 
 use prelude::*;
 
-use rustrt::exclusive::Exclusive;
 use sync::atomic::{mod, AtomicUint};
-use sync::{Once, ONCE_INIT};
+use sync::{Mutex, Once, ONCE_INIT};
 
 use sys::thread_local as imp;
 
@@ -142,7 +141,7 @@ pub const INIT_INNER: StaticKeyInner = StaticKeyInner {
 };
 
 static INIT_KEYS: Once = ONCE_INIT;
-static mut KEYS: *mut Exclusive<Vec<imp::Key>> = 0 as *mut _;
+static mut KEYS: *mut Mutex<Vec<imp::Key>> = 0 as *mut _;
 
 impl StaticKey {
     /// Gets the value associated with this TLS key
@@ -283,4 +282,3 @@ mod tests {
         }
     }
 }
-