rustc: Attempt to handle super long linker invocations

alexcrichton · alexcrichton · commit ed938f08a949 · 2017-09-05T21:07:02.000-07:00
This commit adds logic to the compiler to attempt to handle super long linker invocations by falling back to the `@`-file syntax if the invoked command is too large. Each OS has a limit on how many arguments and how large the arguments can be when spawning a new process, and linkers tend to be one of those programs that can hit the limit! The logic implemented here is to unconditionally attempt to spawn a linker and then if it fails to spawn with an error from the OS that indicates the command line is too big we attempt a fallback. The fallback is roughly the same for all linkers where an argument pointing to a file, prepended with `@`, is passed. This file then contains all the various arguments that we want to pass to the linker. Closes #41190
diff --git a/src/librustc_trans/back/command.rs b/src/librustc_trans/back/command.rs
@@ -0,0 +1,114 @@
+// 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 <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.
+
+//! A thin wrapper around `Command` in the standard library which allows us to
+//! read the arguments that are built up.
+
+use std::ffi::{OsStr, OsString};
+use std::fmt;
+use std::io;
+use std::process::{self, Output, Child};
+
+pub struct Command {
+    program: OsString,
+    args: Vec<OsString>,
+    env: Vec<(OsString, OsString)>,
+}
+
+impl Command {
+    pub fn new<P: AsRef<OsStr>>(program: P) -> Command {
+        Command::_new(program.as_ref())
+    }
+
+    fn _new(program: &OsStr) -> Command {
+        Command {
+            program: program.to_owned(),
+            args: Vec::new(),
+            env: Vec::new(),
+        }
+    }
+
+    pub fn arg<P: AsRef<OsStr>>(&mut self, arg: P) -> &mut Command {
+        self._arg(arg.as_ref());
+        self
+    }
+
+    pub fn args<I>(&mut self, args: I) -> &mut Command
+        where I: IntoIterator,
+              I::Item: AsRef<OsStr>,
+    {
+        for arg in args {
+            self._arg(arg.as_ref());
+        }
+        self
+    }
+
+    fn _arg(&mut self, arg: &OsStr) {
+        self.args.push(arg.to_owned());
+    }
+
+    pub fn env<K, V>(&mut self, key: K, value: V) -> &mut Command
+        where K: AsRef<OsStr>,
+              V: AsRef<OsStr>
+    {
+        self._env(key.as_ref(), value.as_ref());
+        self
+    }
+
+    pub fn envs<I, K, V>(&mut self, envs: I) -> &mut Command
+        where I: IntoIterator<Item=(K, V)>,
+              K: AsRef<OsStr>,
+              V: AsRef<OsStr>
+    {
+        for (key, value) in envs {
+            self._env(key.as_ref(), value.as_ref());
+        }
+        self
+    }
+
+    fn _env(&mut self, key: &OsStr, value: &OsStr) {
+        self.env.push((key.to_owned(), value.to_owned()));
+    }
+
+    pub fn output(&mut self) -> io::Result<Output> {
+        self.command().output()
+    }
+
+    pub fn spawn(&mut self) -> io::Result<Child> {
+        self.command().spawn()
+    }
+
+    pub fn command(&self) -> process::Command {
+        let mut ret = process::Command::new(&self.program);
+        ret.args(&self.args);
+        ret.envs(self.env.clone());
+        return ret
+    }
+
+    // extensions
+
+    pub fn get_program(&self) -> &OsStr {
+        &self.program
+    }
+
+    pub fn get_args(&self) -> &[OsString] {
+        &self.args
+    }
+
+    pub fn get_env(&self) -> &[(OsString, OsString)] {
+        &self.env
+    }
+}
+
+impl fmt::Debug for Command {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        self.command().fmt(f)
+    }
+}
diff --git a/src/librustc_trans/back/link.rs b/src/librustc_trans/back/link.rs
@@ -12,6 +12,7 @@ extern crate rustc_trans_utils;
 
 use super::archive::{ArchiveBuilder, ArchiveConfig};
 use super::linker::Linker;
+use super::command::Command;
 use super::rpath::RPathConfig;
 use super::rpath;
 use metadata::METADATA_FILENAME;
@@ -38,11 +39,12 @@ use std::ascii;
 use std::char;
 use std::env;
 use std::ffi::OsString;
-use std::fs;
-use std::io::{self, Read, Write};
+use std::fmt;
+use std::fs::{self, File};
+use std::io::{self, Read, Write, BufWriter};
 use std::mem;
 use std::path::{Path, PathBuf};
-use std::process::Command;
+use std::process::{Output, Stdio};
 use std::str;
 use flate2::Compression;
 use flate2::write::DeflateEncoder;
@@ -125,8 +127,13 @@ pub fn msvc_link_exe_cmd(sess: &Session) -> (Command, Vec<(OsString, OsString)>)
     let tool = windows_registry::find_tool(target, "link.exe");
 
     if let Some(tool) = tool {
+        let mut cmd = Command::new(tool.path());
+        cmd.args(tool.args());
+        for &(ref k, ref v) in tool.env() {
+            cmd.env(k, v);
+        }
         let envs = tool.env().to_vec();
-        (tool.to_command(), envs)
+        (cmd, envs)
     } else {
         debug!("Failed to locate linker.");
         (Command::new("link.exe"), vec![])
@@ -797,7 +804,9 @@ fn link_natively(sess: &Session,
     let mut i = 0;
     loop {
         i += 1;
-        prog = time(sess.time_passes(), "running linker", || cmd.output());
+        prog = time(sess.time_passes(), "running linker", || {
+            exec_linker(sess, &mut cmd, tmpdir)
+        });
         if !retry_on_segfault || i > 3 {
             break
         }
@@ -875,6 +884,98 @@ fn link_natively(sess: &Session,
     }
 }
 
+fn exec_linker(sess: &Session, cmd: &mut Command, tmpdir: &Path)
+    -> io::Result<Output>
+{
+    // When attempting to spawn the linker we run a risk of blowing out the
+    // size limits for spawning a new process with respect to the arguments
+    // we pass on the command line.
+    //
+    // Here we attempt to handle errors from the OS saying "your list of
+    // arguments is too big" by reinvoking the linker again with an `@`-file
+    // that contains all the arguments. The theory is that this is then
+    // accepted on all linkers and the linker will read all its options out of
+    // there instead of looking at the command line.
+    match cmd.command().stdout(Stdio::piped()).stderr(Stdio::piped()).spawn() {
+        Ok(child) => return child.wait_with_output(),
+        Err(ref e) if command_line_too_big(e) => {}
+        Err(e) => return Err(e)
+    }
+
+    let file = tmpdir.join("linker-arguments");
+    let mut cmd2 = Command::new(cmd.get_program());
+    cmd2.arg(format!("@{}", file.display()));
+    for &(ref k, ref v) in cmd.get_env() {
+        cmd2.env(k, v);
+    }
+    let mut f = BufWriter::new(File::create(&file)?);
+    for arg in cmd.get_args() {
+        writeln!(f, "{}", Escape {
+            arg: arg.to_str().unwrap(),
+            is_like_msvc: sess.target.target.options.is_like_msvc,
+        })?;
+    }
+    f.into_inner()?;
+    return cmd2.output();
+
+    #[cfg(unix)]
+    fn command_line_too_big(err: &io::Error) -> bool {
+        err.raw_os_error() == Some(::libc::E2BIG)
+    }
+
+    #[cfg(windows)]
+    fn command_line_too_big(err: &io::Error) -> bool {
+        const ERROR_FILENAME_EXCED_RANGE: i32 = 206;
+        err.raw_os_error() == Some(ERROR_FILENAME_EXCED_RANGE)
+    }
+
+    struct Escape<'a> {
+        arg: &'a str,
+        is_like_msvc: bool,
+    }
+
+    impl<'a> fmt::Display for Escape<'a> {
+        fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+            if self.is_like_msvc {
+                // This is "documented" at
+                // https://msdn.microsoft.com/en-us/library/4xdcbak7.aspx
+                //
+                // Unfortunately there's not a great specification of the
+                // syntax I could find online (at least) but some local
+                // testing showed that this seemed sufficient-ish to catch
+                // at least a few edge cases.
+                write!(f, "\"")?;
+                for c in self.arg.chars() {
+                    match c {
+                        '"' => write!(f, "\\{}", c)?,
+                        c => write!(f, "{}", c)?,
+                    }
+                }
+                write!(f, "\"")?;
+            } else {
+                // This is documented at https://linux.die.net/man/1/ld, namely:
+                //
+                // > Options in file are separated by whitespace. A whitespace
+                // > character may be included in an option by surrounding the
+                // > entire option in either single or double quotes. Any
+                // > character (including a backslash) may be included by
+                // > prefixing the character to be included with a backslash.
+                //
+                // We put an argument on each line, so all we need to do is
+                // ensure the line is interpreted as one whole argument.
+                for c in self.arg.chars() {
+                    match c {
+                        '\\' |
+                        ' ' => write!(f, "\\{}", c)?,
+                        c => write!(f, "{}", c)?,
+                    }
+                }
+            }
+            Ok(())
+        }
+    }
+}
+
 fn link_args(cmd: &mut Linker,
              sess: &Session,
              crate_type: config::CrateType,
diff --git a/src/librustc_trans/back/linker.rs b/src/librustc_trans/back/linker.rs
@@ -14,11 +14,11 @@ use std::fs::{self, File};
 use std::io::prelude::*;
 use std::io::{self, BufWriter};
 use std::path::{Path, PathBuf};
-use std::process::Command;
 
 use context::SharedCrateContext;
 
 use back::archive;
+use back::command::Command;
 use back::symbol_export::ExportedSymbols;
 use rustc::middle::dependency_format::Linkage;
 use rustc::hir::def_id::{LOCAL_CRATE, CrateNum};
diff --git a/src/librustc_trans/lib.rs b/src/librustc_trans/lib.rs
@@ -68,6 +68,7 @@ pub use llvm_util::{init, target_features, print_version, print_passes, print, e
 
 pub mod back {
     mod archive;
+    mod command;
     pub(crate) mod linker;
     pub mod link;
     mod lto;
diff --git a/src/test/run-make/long-linker-command-lines/Makefile b/src/test/run-make/long-linker-command-lines/Makefile
@@ -0,0 +1,5 @@
+-include ../tools.mk
+
+all:
+	$(RUSTC) foo.rs -g
+	RUSTC="$(RUSTC_ORIGINAL)" $(call RUN,foo)
diff --git a/src/test/run-make/long-linker-command-lines/foo.rs b/src/test/run-make/long-linker-command-lines/foo.rs
@@ -0,0 +1,88 @@
+// 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 <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.
+
+// This is a test which attempts to blow out the system limit with how many
+// arguments can be passed to a process. This'll successively call rustc with
+// larger and larger argument lists in an attempt to find one that's way too
+// big for the system at hand. This file itself is then used as a "linker" to
+// detect when the process creation succeeds.
+//
+// Eventually we should see an argument that looks like `@` as we switch from
+// passing literal arguments to passing everything in the file.
+
+use std::env;
+use std::fs::{self, File};
+use std::io::{BufWriter, Write, Read};
+use std::path::PathBuf;
+use std::process::Command;
+
+fn main() {
+    let tmpdir = PathBuf::from(env::var_os("TMPDIR").unwrap());
+    let ok = tmpdir.join("ok");
+    if env::var("YOU_ARE_A_LINKER").is_ok() {
+        if let Some(file) = env::args().find(|a| a.contains("@")) {
+            fs::copy(&file[1..], &ok).unwrap();
+        }
+        return
+    }
+
+    let rustc = env::var_os("RUSTC").unwrap_or("rustc".into());
+    let me_as_linker = format!("linker={}", env::current_exe().unwrap().display());
+    for i in (1..).map(|i| i * 100) {
+        println!("attempt: {}", i);
+        let file = tmpdir.join("bar.rs");
+        let mut f = BufWriter::new(File::create(&file).unwrap());
+        let mut lib_name = String::new();
+        for _ in 0..i {
+            lib_name.push_str("foo");
+        }
+        for j in 0..i {
+            writeln!(f, "#[link(name = \"{}{}\")]", lib_name, j).unwrap();
+        }
+        writeln!(f, "extern {{}}\nfn main() {{}}").unwrap();
+        f.into_inner().unwrap();
+
+        drop(fs::remove_file(&ok));
+        let output = Command::new(&rustc)
+            .arg(&file)
+            .arg("-C").arg(&me_as_linker)
+            .arg("--out-dir").arg(&tmpdir)
+            .env("YOU_ARE_A_LINKER", "1")
+            .output()
+            .unwrap();
+
+        if !output.status.success() {
+            let stderr = String::from_utf8_lossy(&output.stderr);
+            panic!("status: {}\nstdout:\n{}\nstderr:\n{}",
+                   output.status,
+                   String::from_utf8_lossy(&output.stdout),
+                   stderr.lines().map(|l| {
+                       if l.len() > 200 {
+                           format!("{}...\n", &l[..200])
+                       } else {
+                           format!("{}\n", l)
+                       }
+                   }).collect::<String>());
+        }
+
+        if !ok.exists() {
+            continue
+        }
+
+        let mut contents = String::new();
+        File::open(&ok).unwrap().read_to_string(&mut contents).unwrap();
+
+        for j in 0..i {
+            assert!(contents.contains(&format!("{}{}", lib_name, j)));
+        }
+
+        break
+    }
+}
diff --git a/src/test/run-make/tools.mk b/src/test/run-make/tools.mk
@@ -5,6 +5,7 @@ HOST_RPATH_ENV = \
 TARGET_RPATH_ENV = \
     $(LD_LIB_PATH_ENVVAR)="$(TMPDIR):$(TARGET_RPATH_DIR):$($(LD_LIB_PATH_ENVVAR))"
 
+RUSTC_ORIGINAL := $(RUSTC)
 BARE_RUSTC := $(HOST_RPATH_ENV) '$(RUSTC)'
 RUSTC := $(BARE_RUSTC) --out-dir $(TMPDIR) -L $(TMPDIR) $(RUSTFLAGS)
 #CC := $(CC) -L $(TMPDIR)
