syscall: support POSIX semantics for Linux syscalls

This change adds two new methods for invoking system calls
under Linux: syscall.AllThreadsSyscall() and
syscall.AllThreadsSyscall6().

These system call wrappers ensure that all OSThreads mirror
a common system call. The wrappers serialize execution of the
runtime to ensure no race conditions where any Go code observes
a non-atomic OS state change. As such, the syscalls have
higher runtime overhead than regular system calls, and only
need to be used where such thread (or 'm' in the parlance
of the runtime sources) consistency is required.

The new support is used to enable these functions under Linux:

  syscall.Setegid(), syscall.Seteuid(), syscall.Setgroups(),
  syscall.Setgid(), syscall.Setregid(), syscall.Setreuid(),
  syscall.Setresgid(), syscall.Setresuid() and syscall.Setuid().

They work identically to their glibc counterparts.

Extensive discussion of the background issue addressed in this
patch can be found here:

   https://github.com/golang/go/issues/1435

In the case where cgo is used, the C runtime can launch pthreads that
are not managed by the Go runtime. As such, the added
syscall.AllThreadsSyscall*() return ENOTSUP when cgo is enabled.
However, for the 9 syscall.Set*() functions listed above, when cgo is
active, these functions redirect to invoke their C.set*() equivalents
in glibc, which wraps the raw system calls with a nptl:setxid fixup
mechanism. This achieves POSIX semantics for these functions in the
combined Go and C runtime.

As a side note, the glibc/nptl:setxid support (2019-11-30) does not
extend to all security related system calls under Linux so using
native Go (CGO_ENABLED=0) and these AllThreadsSyscall*()s, where
needed, will yield more well defined/consistent behavior over all
threads of a Go program. That is, using the
syscall.AllThreadsSyscall*() wrappers for things like setting state
through SYS_PRCTL and SYS_CAPSET etc.

Fixes #1435

Change-Id: Ib1a3e16b9180f64223196a32fc0f9dce14d9105c
Reviewed-on: https://go-review.googlesource.com/c/go/+/210639
Trust: Emmanuel Odeke <emm.odeke@gmail.com>
Trust: Ian Lance Taylor <iant@golang.org>
Trust: Michael Pratt <mpratt@google.com>
Run-TryBot: Emmanuel Odeke <emm.odeke@gmail.com>
Reviewed-by: Michael Pratt <mpratt@google.com>
Reviewed-by: Austin Clements <austin@google.com>

2 files changed, 153 insertions, 0 deletions

diff --git a/misc/cgo/test/cgo_linux_test.go b/misc/cgo/test/cgo_linux_test.go
index 7b56e11a27..a9746b552e 100644
--- a/misc/cgo/test/cgo_linux_test.go
+++ b/misc/cgo/test/cgo_linux_test.go
@@ -15,5 +15,6 @@ func TestSetgid(t *testing.T) {
 	}
 	testSetgid(t)
 }
+func Test1435(t *testing.T)    { test1435(t) }
 func Test6997(t *testing.T)    { test6997(t) }
 func TestBuildID(t *testing.T) { testBuildID(t) }
diff --git a/misc/cgo/test/issue1435.go b/misc/cgo/test/issue1435.go
new file mode 100644
index 0000000000..155d33baff
--- /dev/null
+++ b/misc/cgo/test/issue1435.go
@@ -0,0 +1,152 @@
+// Copyright 2019 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// +build linux,cgo
+
+package cgotest
+
+import (
+	"fmt"
+	"io/ioutil"
+	"strings"
+	"syscall"
+	"testing"
+)
+
+// #include <stdio.h>
+// #include <stdlib.h>
+// #include <pthread.h>
+// #include <unistd.h>
+// #include <sys/types.h>
+//
+// pthread_t *t = NULL;
+// pthread_mutex_t mu;
+// int nts = 0;
+// int all_done = 0;
+//
+// static void *aFn(void *vargp) {
+//   int done = 0;
+//   while (!done) {
+//     usleep(100);
+//     pthread_mutex_lock(&mu);
+//     done = all_done;
+//     pthread_mutex_unlock(&mu);
+//   }
+//   return NULL;
+// }
+//
+// void trial(int argc) {
+//   int i;
+//   nts = argc;
+//   t = calloc(nts, sizeof(pthread_t));
+//   pthread_mutex_init(&mu, NULL);
+//   for (i = 0; i < nts; i++) {
+//     pthread_create(&t[i], NULL, aFn, NULL);
+//   }
+// }
+//
+// void cleanup(void) {
+//   int i;
+//   pthread_mutex_lock(&mu);
+//   all_done = 1;
+//   pthread_mutex_unlock(&mu);
+//   for (i = 0; i < nts; i++) {
+//     pthread_join(t[i], NULL);
+//   }
+//   pthread_mutex_destroy(&mu);
+//   free(t);
+// }
+import "C"
+
+// compareStatus is used to confirm the contents of the thread
+// specific status files match expectations.
+func compareStatus(filter, expect string) error {
+	expected := filter + "\t" + expect
+	pid := syscall.Getpid()
+	fs, err := ioutil.ReadDir(fmt.Sprintf("/proc/%d/task", pid))
+	if err != nil {
+		return fmt.Errorf("unable to find %d tasks: %v", pid, err)
+	}
+	for _, f := range fs {
+		tf := fmt.Sprintf("/proc/%s/status", f.Name())
+		d, err := ioutil.ReadFile(tf)
+		if err != nil {
+			return fmt.Errorf("unable to read %q: %v", tf, err)
+		}
+		lines := strings.Split(string(d), "\n")
+		for _, line := range lines {
+			if strings.HasPrefix(line, filter) {
+				if line != expected {
+					return fmt.Errorf("%s %s (bad)\n", tf, line)
+				}
+				break
+			}
+		}
+	}
+	return nil
+}
+
+// test1435 test 9 glibc implemented setuid/gid syscall functions are
+// mapped.  This test is a slightly more expansive test than that of
+// src/syscall/syscall_linux_test.go:TestSetuidEtc() insofar as it
+// launches concurrent threads from C code via CGo and validates that
+// they are subject to the system calls being tested. For the actual
+// Go functionality being tested here, the syscall_linux_test version
+// is considered authoritative, but non-trivial improvements to that
+// should be mirrored here.
+func test1435(t *testing.T) {
+	if syscall.Getuid() != 0 {
+		t.Skip("skipping root only test")
+	}
+
+	// Launch some threads in C.
+	const cts = 5
+	C.trial(cts)
+	defer C.cleanup()
+
+	vs := []struct {
+		call           string
+		fn             func() error
+		filter, expect string
+	}{
+		{call: "Setegid(1)", fn: func() error { return syscall.Setegid(1) }, filter: "Gid:", expect: "0\t1\t0\t1"},
+		{call: "Setegid(0)", fn: func() error { return syscall.Setegid(0) }, filter: "Gid:", expect: "0\t0\t0\t0"},
+
+		{call: "Seteuid(1)", fn: func() error { return syscall.Seteuid(1) }, filter: "Uid:", expect: "0\t1\t0\t1"},
+		{call: "Setuid(0)", fn: func() error { return syscall.Setuid(0) }, filter: "Uid:", expect: "0\t0\t0\t0"},
+
+		{call: "Setgid(1)", fn: func() error { return syscall.Setgid(1) }, filter: "Gid:", expect: "1\t1\t1\t1"},
+		{call: "Setgid(0)", fn: func() error { return syscall.Setgid(0) }, filter: "Gid:", expect: "0\t0\t0\t0"},
+
+		{call: "Setgroups([]int{0,1,2,3})", fn: func() error { return syscall.Setgroups([]int{0, 1, 2, 3}) }, filter: "Groups:", expect: "0 1 2 3 "},
+		{call: "Setgroups(nil)", fn: func() error { return syscall.Setgroups(nil) }, filter: "Groups:", expect: " "},
+		{call: "Setgroups([]int{0})", fn: func() error { return syscall.Setgroups([]int{0}) }, filter: "Groups:", expect: "0 "},
+
+		{call: "Setregid(101,0)", fn: func() error { return syscall.Setregid(101, 0) }, filter: "Gid:", expect: "101\t0\t0\t0"},
+		{call: "Setregid(0,102)", fn: func() error { return syscall.Setregid(0, 102) }, filter: "Gid:", expect: "0\t102\t102\t102"},
+		{call: "Setregid(0,0)", fn: func() error { return syscall.Setregid(0, 0) }, filter: "Gid:", expect: "0\t0\t0\t0"},
+
+		{call: "Setreuid(1,0)", fn: func() error { return syscall.Setreuid(1, 0) }, filter: "Uid:", expect: "1\t0\t0\t0"},
+		{call: "Setreuid(0,2)", fn: func() error { return syscall.Setreuid(0, 2) }, filter: "Uid:", expect: "0\t2\t2\t2"},
+		{call: "Setreuid(0,0)", fn: func() error { return syscall.Setreuid(0, 0) }, filter: "Uid:", expect: "0\t0\t0\t0"},
+
+		{call: "Setresgid(101,0,102)", fn: func() error { return syscall.Setresgid(101, 0, 102) }, filter: "Gid:", expect: "101\t0\t102\t0"},
+		{call: "Setresgid(0,102,101)", fn: func() error { return syscall.Setresgid(0, 102, 101) }, filter: "Gid:", expect: "0\t102\t101\t102"},
+		{call: "Setresgid(0,0,0)", fn: func() error { return syscall.Setresgid(0, 0, 0) }, filter: "Gid:", expect: "0\t0\t0\t0"},
+
+		{call: "Setresuid(1,0,2)", fn: func() error { return syscall.Setresuid(1, 0, 2) }, filter: "Uid:", expect: "1\t0\t2\t0"},
+		{call: "Setresuid(0,2,1)", fn: func() error { return syscall.Setresuid(0, 2, 1) }, filter: "Uid:", expect: "0\t2\t1\t2"},
+		{call: "Setresuid(0,0,0)", fn: func() error { return syscall.Setresuid(0, 0, 0) }, filter: "Uid:", expect: "0\t0\t0\t0"},
+	}
+
+	for i, v := range vs {
+		if err := v.fn(); err != nil {
+			t.Errorf("[%d] %q failed: %v", i, v.call, err)
+			continue
+		}
+		if err := compareStatus(v.filter, v.expect); err != nil {
+			t.Errorf("[%d] %q comparison: %v", i, v.call, err)
+		}
+	}
+}