Added a new SafeSPrintf() function that implements snprintf() in an async-safe-fashion

base/debug/format.h

+// Copyright (c) 2013 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+//
+// Author: markus@chromium.org
+
+#ifndef BASE_DEBUG_FORMAT_H_
+#define BASE_DEBUG_FORMAT_H_
+
+#include <stddef.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+#if defined(__unix__)
+// For ssize_t
+#include <unistd.h>
+#endif
+
+#include "base/base_export.h"
+#include "base/basictypes.h"
+
+namespace base {
+namespace debug {
+
+#if defined(_MSC_VER)
+// Define ssize_t inside of our namespace.

[jln (very slow on Chromium), 2013/08/01 00:03:15]

The comment is a bit misleading since this won't be scoped to a namespace.

This probably belongs in base/basictypes.h ?

+#if defined(_WIN64)
+typedef __int64 ssize_t;
+#else
+typedef long ssize_t;
+#endif
+#endif
+
+// Format() is a type-safe and async-signal-safe version of snprintf().
+//
+// FormatN() is an alternative function signature that can be used when
+// not dealing with fixed-sized buffers. When possible, Format() should always
+// be used in favor of FormatN()

[jln (very slow on Chromium), 2013/08/01 00:03:15]

s/in favor/instead/ ?

+//
+// These functions allow for formatting complicated messages from contexts that
+// require strict async-signal-safety. In fact, it is safe to call them from
+// any low-level execution context; even from contexts that have stricter
+// requirements than just async-signal-safety.
+//
+// The code currently only supports a subset of format characters:
+//   %c, %d, %x, %X, %p, and %s.
+//
+// Format() aims to be as liberal as reasonably possible. Integer-like values
+// of arbitrary width can be passed to all of the format characters that expect
+// integers. Thus, it is explicitly legal to pass an "int" to "%c", and output
+// will automatically look at the LSB only. It is also explicitly legal to
+// pass either signed or unsigned values, and the format characters will
+// automatically interpret the arguments accordingly.
+//
+// It is still not legal to mix-and-match integer-like values with pointer
+// values. For instance, you cannot pass a pointer to %x, nor can you pass an
+// integer to %p.
+//
+// The one exception is "0" zero being accepted by "%p". This works-around
+// the problem of C++ defining NULL as an integer-like value.
+//
+// All format characters take an optional width parameter. This must be a
+// positive integer. For %d, %x, %X and %p, if the width starts with
+// a leading '0', padding is done with '0' instead of ' ' characters.
+//
+// There are a few features of snprintf-style format strings, that Format()
+// does not support at this time. If an actual user shows up, I would not be

[jln (very slow on Chromium), 2013/08/01 00:03:15]

Could you try to phrase without the first person ?

+// opposed to adding support for these features. But that assumes that the
+// trade-offs between complexity and utility are favorable.
+//
+// For example, adding support for negative padding widths, for %n and for
+// octal numbers are all likely to be viewed positively.
+//
+// On the other hands, adding support for alternate forms, positional
+// arguments, grouping, wide characters, localization or floating point numbers
+// are all unlikely to ever be added.
+//
+// Format() and FormatN() mimicks the behavior of snprintf() and they return
+// the number of bytes needed to store the untruncated output. This does *not*
+// include the terminating NUL byte.
+//
+// They return -1, iff a fatal error happened. This typically can only happen,
+// if the buffer size is a) negative, b) zero (i.e. not even the NUL byte can
+// be written), or c) bigger than SSIZE_MAX.
+//
+// While the code supports type checking and while it is generally very careful
+// to avoid printing incorrect values, it tends to be conservative in printing
+// as much as possible, even when given incorrect parameters. Typically, in
+// case of an error, the format string will not be expanded. (i.e. something
+// like Format(buf, "%p %d", 1, 2) results in "%p 2").
+//
+// The pre-C++11 version cannot handle more than ten arguments.
+//
+// Basic example:
+//   char buf[20];
+//   base::debug::Format(buf, "The answer: %2d", 42);
+//
+// Example with dynamically sized buffer (async-signal-safe); this code won't
+// work on Visual studio, as it requires dynamically allocating arrays on the
+// stack:
+//   const size_t kInitialSize = 128;
+//   size_t sz = kInitialSize;
+//   for (;;) {
+//     char buf[sz];

[jln (very slow on Chromium), 2013/08/01 00:03:15]

I'm a bit uneasy with recommending such a pattern.

Most stack overflows are harmless for security, but it may not always be the
case (at least it allows to DoS). This should at least state that "err" has to
be trusted input.

Recognizing trusted input is much harder than it seems most of the time, so I'm
worried about this pattern.

+//     sz = FormatN(buf, sz, "Error message \"%s\"\n", err) + 1;
+//     if (sz > sizeof(buf))
+//       continue;
+//     write(2, buf, sz-1);
+//     break;
+//   }
+
+namespace internal {
+  // Helpers that use C++ overloading, templates, and specializations to deduce
+  // and record type information from function arguments. This allows us to
+  // later write a type-safe version of snprintf().
+
+  struct Arg {
+    // Any integer-like value.
+    Arg(signed char c)        : i_(c), width_(sizeof(char)),  type_(INT)  { }
+    Arg(unsigned char c)      : i_(c), width_(sizeof(char)),  type_(UINT) { }
+    Arg(signed short i)       : i_(i), width_(sizeof(short)), type_(INT)  { }
+    Arg(unsigned short i)     : i_(i), width_(sizeof(short)), type_(UINT) { }
+    Arg(signed int i)         : i_(i), width_(sizeof(int)),   type_(INT)  { }
+    Arg(unsigned int i)       : i_(i), width_(sizeof(int)),   type_(UINT) { }
+    Arg(signed long i)        : i_(i), width_(sizeof(long)),  type_(INT)  { }
+    Arg(unsigned long i)      : i_(i), width_(sizeof(long)),  type_(UINT) { }
+    Arg(signed long long i)   : i_(i), width_(sizeof(long long)),
+                                                              type_(INT)  { }
+    Arg(unsigned long long i) : i_(i), width_(sizeof(long long)),
+                                                              type_(UINT) { }
+
+    // A C-style text string.
+    Arg(const char* s) : s_(s), type_(STRING) { }
+    Arg(char* s)       : s_(s), type_(STRING) { }
+
+    // Any pointer value that can be cast to a "void*".
+    template<class T> Arg(T* ptr) : ptr_((void*)ptr), type_(POINTER) { }
+
+    union {
+      // An integer-like value.
+      struct {
+        int64_t       i_;
+        unsigned char width_;
+      };
+
+      // A C-style text string.
+      const char* s_;
+
+      // A pointer to an arbitrary object.
+      const void* ptr_;
+    };
+    const enum { INT, UINT, STRING, POINTER } type_;

[jln (very slow on Chromium), 2013/08/01 00:03:15]

Typedefs and enum should be first, please look at the "Declaration order" in the
style guide.

+  };
+
+  // This is the internal function that performs the actual formatting of
+  // an snprintf()-style format string.
+  BASE_EXPORT ssize_t FormatN(char* buf, size_t sz, const char* fmt,
+                              const Arg* args, size_t max_args);
+}  // namespace internal
+
+#if __cplusplus >= 201103  // C++11
+
+template<typename... Args>
+ssize_t FormatN(char* buf, size_t N, const char* fmt, Args... args) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { args... };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N, typename... Args>
+ssize_t Format(char (&buf)[N], const char* fmt, Args... args) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { args... };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+#else  // Pre-C++11
+
+// TODO(markus): C++11 has a much more concise and readable solution for
+//   expressing what we are doing here. Delete the fall-back code for older
+//   compilers as soon as we have fully switched to C++11

[jln (very slow on Chromium), 2013/08/01 00:03:15]

Nit: final dot.

+
+template<class T0, class T1, class T2, class T3, class T4,
+         class T5, class T6, class T7, class T8, class T9>
+ssize_t FormatN(char* buf, size_t N, const char* fmt,
+                T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4,
+                T5 arg5, T6 arg6, T7 arg7, T8 arg8, T9 arg9) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = {
+    arg0, arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8, arg9
+  };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N,
+         class T0, class T1, class T2, class T3, class T4,
+         class T5, class T6, class T7, class T8, class T9>
+ssize_t Format(char (&buf)[N], const char* fmt,
+               T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4,
+               T5 arg5, T6 arg6, T7 arg7, T8 arg8, T9 arg9) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = {
+    arg0, arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8, arg9
+  };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0, class T1, class T2, class T3, class T4,
+         class T5, class T6, class T7, class T8>
+ssize_t FormatN(char* buf, size_t N, const char* fmt,
+                T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4,
+                T5 arg5, T6 arg6, T7 arg7, T8 arg8) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = {
+    arg0, arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8
+  };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N,
+         class T0, class T1, class T2, class T3, class T4, class T5,
+         class T6, class T7, class T8>
+ssize_t Format(char (&buf)[N], const char* fmt,
+               T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4,
+               T5 arg5, T6 arg6, T7 arg7, T8 arg8) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = {
+    arg0, arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8
+  };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0, class T1, class T2, class T3, class T4, class T5,
+         class T6, class T7>
+ssize_t FormatN(char* buf, size_t N, const char* fmt,
+                T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4,
+                T5 arg5, T6 arg6, T7 arg7) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = {
+    arg0, arg1, arg2, arg3, arg4, arg5, arg6, arg7
+  };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N,
+         class T0, class T1, class T2, class T3, class T4, class T5,
+         class T6, class T7>
+ssize_t Format(char (&buf)[N], const char* fmt,
+               T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4,
+               T5 arg5, T6 arg6, T7 arg7) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = {
+    arg0, arg1, arg2, arg3, arg4, arg5, arg6, arg7
+  };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0, class T1, class T2, class T3, class T4, class T5,
+         class T6>
+ssize_t FormatN(char* buf, size_t N, const char* fmt,
+                T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4,
+                T5 arg5, T6 arg6) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = {
+    arg0, arg1, arg2, arg3, arg4, arg5, arg6
+  };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N,
+         class T0, class T1, class T2, class T3, class T4, class T5,
+         class T6>
+ssize_t Format(char (&buf)[N], const char* fmt,
+               T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5, T6 arg6) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = {
+    arg0, arg1, arg2, arg3, arg4, arg5, arg6
+  };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0, class T1, class T2, class T3, class T4, class T5>
+ssize_t FormatN(char* buf, size_t N, const char* fmt,
+                T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1, arg2, arg3, arg4, arg5 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N,
+         class T0, class T1, class T2, class T3, class T4, class T5>
+ssize_t Format(char (&buf)[N], const char* fmt,
+               T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4, T5 arg5) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1, arg2, arg3, arg4, arg5 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0, class T1, class T2, class T3, class T4>
+ssize_t FormatN(char* buf, size_t N, const char* fmt,
+                T0 arg0, T1 arg1, T2 arg2, T3 arg3, T4 arg4) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1, arg2, arg3, arg4 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N, class T0, class T1, class T2, class T3, class T4>
+ssize_t Format(char (&buf)[N], const char* fmt, T0 arg0, T1 arg1,
+               T2 arg2, T3 arg3, T4 arg4) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1, arg2, arg3, arg4 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0, class T1, class T2, class T3>
+ssize_t FormatN(char* buf, size_t N, const char* fmt,
+                T0 arg0, T1 arg1, T2 arg2, T3 arg3) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1, arg2, arg3 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N, class T0, class T1, class T2, class T3>
+ssize_t Format(char (&buf)[N], const char* fmt,
+               T0 arg0, T1 arg1, T2 arg2, T3 arg3) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1, arg2, arg3 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0, class T1, class T2>
+ssize_t FormatN(char* buf, size_t N, const char* fmt,
+                T0 arg0, T1 arg1, T2 arg2) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1, arg2 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N, class T0, class T1, class T2>
+ssize_t Format(char (&buf)[N], const char* fmt, T0 arg0, T1 arg1, T2 arg2) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1, arg2 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0, class T1>
+ssize_t FormatN(char* buf, size_t N, const char* fmt, T0 arg0, T1 arg1) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N, class T0, class T1>
+ssize_t Format(char (&buf)[N], const char* fmt, T0 arg0, T1 arg1) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0, arg1 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<class T0>
+ssize_t FormatN(char* buf, size_t N, const char* fmt, T0 arg0) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+
+template<size_t N, class T0>
+ssize_t Format(char (&buf)[N], const char* fmt, T0 arg0) {
+  // Use Arg() object to record type information and then copy arguments to an
+  // array to make it easier to iterate over them.
+  const internal::Arg arg_array[] = { arg0 };
+  return internal::FormatN(buf, N, fmt, arg_array, arraysize(arg_array));
+}
+#endif
+
+// Fast-path when we don't actually need to substitute any arguments.
+BASE_EXPORT ssize_t FormatN(char* buf, size_t N, const char* fmt);
+template<size_t N>
+inline ssize_t Format(char (&buf)[N], const char* fmt) {
+  return FormatN(buf, N, fmt);
+}
+
+}  // namespace debug
+}  // namespace base
+
+#endif  // BASE_DEBUG_FORMAT_H_