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

base/debug/format.cc

+// 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.
+
+#include <limits>
+
+#include "base/debug/format.h"
+
+
+namespace base {
+namespace debug {
+
+// The code in this file is extremely careful to be async-signal-safe.
+//
+// Most obviously, we avoid calling any code that could dynamically allocate
+// memory. Doing so would almost certainly result in bugs and dead-locks.
+// We also avoid calling any other STL functions that could have unintended
+// side-effects involving memory allocation or access to other shared
+// resources.
+//
+// But on top of that, we also avoid calling other library functions, as many
+// of them have the side-effect of calling getenv() (in order to deal with
+// localization) or accessing errno. The latter sounds benign, but there are
+// several execution contexts where it isn't even possible to safely read let
+// alone write errno.
+//
+// The stated design goal of the Format() function is that it can be called
+// from any context that can safely call C or C++ code (i.e. anything that
+// doesn't require assembly code).
+//
+// For a brief overview of some but not all of the issues with async-signal-
+// safety, refer to:
+// http://pubs.opengroup.org/onlinepubs/009695399/functions/xsh_chap02_04.html
+
+namespace {
+
+inline bool IncrementCount(size_t* count, size_t inc = 1) {
+  if (*count > std::numeric_limits<ssize_t>::max() - inc) {

[Jeffrey Yasskin, 2013/07/30 23:13:53]

I think this will give the wrong answer if
inc>std::numeric_limits<ssize_t>::max().

+    *count = std::numeric_limits<ssize_t>::max();
+    return false;
+  } else {
+    *count += inc;
+    return true;
+  }
+}
+
+inline bool Out(char* buf, size_t sz, size_t* count, char ch) {
+  if (*count + 1 < sz) {
+    buf[*count] = ch;
+    IncrementCount(count);
+    return true;
+  }
+  IncrementCount(count);
+  return false;
+}
+
+inline void Pad(char* buf, size_t sz, size_t* count, char pad, size_t padding,
+                size_t len, char** ptr) {
+  char *dst = *ptr;
+  for (; padding > len; --padding)
+    if (Out(buf, sz, count, pad))
+      ++dst;
+    else {
+      if (--padding)
+        IncrementCount(count, padding-len);
+      break;
+    }
+  *ptr = dst;
+}
+
+// POSIX doesn't define any async-signal safe function for converting
+// an integer to ASCII. Define our own version.
+//
+// This also gives us the ability to make the function a little more powerful
+// and have it deal with padding, with truncation, and with predicting the
+// length of the untruncated output.
+//
+// IToASCII() converts an (optionally signed) integer to ASCII.  It never
+// writes more than "sz" bytes. Output will be truncated as needed, and a NUL
+// character is appended, unless "sz" is zero. It returns the number of non-NUL
+// bytes that would be output if no truncation had happened.
+//
+// It supports bases 2 through 16. Padding can be done with either '0' zeros
+// or ' ' spaces.
+size_t IToASCII(bool sign, bool upcase, int64_t i, char* buf, size_t sz,
+                int base, size_t padding, char pad) {
+  // Sanity check for the "base".
+  if (base < 2 || base > 16 || (sign && base != 10)) {
+    if (static_cast<ssize_t>(sz) >= 1)
+      buf[0] = '\000';
+    return 0;
+  }
+
+  // Handle negative numbers, if requested by caller.
+  size_t count = 0;
+  size_t n = 1;
+  char* start = buf;
+  int minint = 0;
+  bool needs_minus = false;
+  uint64_t num;
+  if (sign && i < 0) {
+    // If we aren't inserting padding, or if we are padding with '0' zeros,
+    // we should insert the minus character now. It makes it easier to
+    // correctly deal with truncated padded numbers.
+    // On the other hand, if we are padding with ' ' spaces, we have to
+    // delay outputting the minus character until later.
+    if (padding <= 2 || pad == '0') {
+      ++count;
+
+      // Make sure we can write the '-' character.
+      if (++n > sz) {
+        if (sz > 0)
+          *start = '\000';
+      } else
+        *start++ = '-';
+
+      // Adjust padding, since we just output one character already.
+      if (padding)
+        --padding;
+    } else
+      needs_minus = true;
+
+    // Turn our number positive.
+    if (i == -i) {

[Jeffrey Yasskin, 2013/07/30 23:13:53]

That's undefined behavior for signed numbers (sorry); compute the negation as
unsigned instead or use numeric_limits<int64_t>::min().

+      // The lowest-most negative integer needs special treatment.
+      minint = 1;
+      num = -(i + 1);
+    } else {
+      // "Normal" negative numbers are easy.
+      num = -i;
+    }
+  } else
+    num = i;
+
+  // Loop until we have converted the entire number. Output at least one
+  // character (i.e. '0').
+  char* ptr = start;
+  bool started = false;
+  do {
+    // Sanity check. If padding is used to fill the entire address space,
+    // don't allow more than MAXINT bytes.

[Jeffrey Yasskin, 2013/07/30 23:13:53]

MAXINT != numeric_limits<ssize_t>::max(). SSIZE_MAX instead? (Here and in the
header comment.)

+    if (++count == static_cast<size_t>(std::numeric_limits<ssize_t>::max())) {
+      break;
+    }
+
+    // Make sure there is still enough space left in our output buffer.
+    if (n == sz) {
+      if (ptr > start) {
+        // It is rare that we need to output a partial number. But if asked
+        // to do so, we will still make sure we output the correct number of
+        // leading digits.
+        // memmove(start, start+1, --ptr - start)

[Jeffrey Yasskin, 2013/07/30 23:13:53]

This is weird. Why do you need to erase the first digit you printed?

+        --ptr;
+        for (char* move = start; move < ptr; ++move)
+          *move = move[1];
+      } else
+        goto cannot_write_anything_but_nul;
+    } else
+      ++n;
+
+    // Output the next digit and (if necessary) compensate for the lowest-

[Jeffrey Yasskin, 2013/07/30 23:13:53]

"lowest-most negative integer" should probably be "lowest integer" or
"most-negative integer".

+    // most negative integer needing special treatment. This works because,
+    // no matter the bit width of the integer, the lowest-most decimal
+    // integer always ends in 2, 4, 6, or 8.
+    if (n <= sz) {
+      if (!num && started)
+        if (needs_minus) {
+          *ptr++ = '-';
+          needs_minus = false;
+        } else
+          *ptr++ = pad;
+      else {
+        started = true;
+        *ptr++ = (upcase ? "0123456789ABCDEF" : "0123456789abcdef")
+                 [num%base+minint];
+      }
+    }
+
+  cannot_write_anything_but_nul:
+    minint = 0;
+    num /= base;
+
+    // Add padding, if requested.
+    if (padding > 0) {
+      --padding;
+
+      // Performance optimization for when we are asked to output
+      // excessive padding, but our output buffer is limited in size.
+      // Even if we output a 128bit number in binary, we would never
+      // write more than 130 characters. So, anything beyond this limit
+      // and we can compute the result arithmetically.
+      if (count > n && count - n > 130) {
+        IncrementCount(&count, padding);
+        padding = 0;
+      }
+    }
+  } while (num || padding || needs_minus);
+
+  // Terminate the output with a NUL character.
+  if (sz > 0)
+    *ptr = '\000';
+
+  // Conversion to ASCII actually resulted in the digits being in reverse
+  // order. We can't easily generate them in forward order, as we can't tell
+  // the number of characters needed until we are done converting.
+  // So, now, we reverse the string (except for the possible '-' sign).
+  while (--ptr > start) {
+    char ch = *ptr;
+    *ptr = *start;
+    *start++ = ch;
+  }
+  return count;
+}
+
+}  // anonymous namespace
+
+ssize_t internal::FormatN(char* buf, size_t sz, const char* fmt,
+                          const Arg* args, const size_t max_args) {
+  // Make sure we can write at least one NUL byte.
+  if (static_cast<ssize_t>(sz) < 1)
+    return -1;
+
+  // Iterate over format string and interpret '%' arguments as they are
+  // encountered.
+  char* ptr = buf;
+  size_t padding;
+  char pad;
+  size_t count = 0;
+  for (unsigned int cur_arg = 0;
+       *fmt &&
+       count != static_cast<size_t>(std::numeric_limits<ssize_t>::max()); ) {
+    if (*fmt++ == '%') {
+      padding = 0;
+      pad = ' ';
+      char ch = *fmt++;
+    format_character_found:
+      switch (ch) {
+      case '0': case '1': case '2': case '3': case '4':
+      case '5': case '6': case '7': case '8': case '9':
+        // Found a width parameter. Convert to an integer value and store in
+        // "padding". If the leading digit is a zero, change the padding
+        // character from a space ' ' to a zero '0'.
+        pad = ch == '0' ? '0' : ' ';
+        for (;;) {
+          const size_t max_padding = std::numeric_limits<ssize_t>::max();
+          if (padding > max_padding/10 ||
+              10*padding > max_padding - (ch - '0')) {
+            // Integer overflow detected. Skip the rest of the width until
+            // we find the format character, then do the normal error handling.
+            while ((ch = *fmt++) >= '0' && ch <= '9') {
+            }
+            goto fail_to_expand;
+          }
+          padding = 10*padding + ch - '0';
+          ch = *fmt++;
+          if (ch < '0' || ch > '9') {
+            // Reached the end of the width parameter. This is where the format
+            // character is found.
+            goto format_character_found;
+          }
+        }
+        break;
+      case 'c': {  // Output an ASCII character.
+        // Check that there are arguments left to be inserted.
+        if (cur_arg >= max_args)
+          goto fail_to_expand;
+
+        // Check that the argument has the expected type.
+        const Arg& arg = args[cur_arg++];
+        if (arg.type_ != Arg::INT &&
+            arg.type_ != Arg::UINT)
+          goto fail_to_expand;
+
+        // Apply padding, if needed.
+        Pad(buf, sz, &count, ' ', padding, 1, &ptr);
+
+        // Convert the argument to an ASCII character and output it.
+        char ch = static_cast<char>(arg.i_);
+        if (!ch)
+          goto end_of_output_buffer;
+        if (Out(buf, sz, &count, ch))
+          ++ptr;
+        break; }
+      case 'd': {  // Output a signed or unsigned integer-like value.
+        // Check that there are arguments left to be inserted.
+        if (cur_arg >= max_args)
+          goto fail_to_expand;
+
+        // Check that the argument has the expected type.
+        const Arg& arg = args[cur_arg++];
+        if (arg.type_ != Arg::INT &&
+            arg.type_ != Arg::UINT)
+          goto fail_to_expand;
+
+        // Our implementation of IToASCII() can handle all widths of data types
+        // and can print both signed and unsigned values.
+        IncrementCount(&count,
+                       IToASCII(arg.type_ == Arg::INT, false, arg.i_,
+                                ptr, sz - (ptr - buf), 10, padding, pad));
+
+        // Advance "ptr" to the end of the string that was just emitted.
+        if (sz - (ptr - buf))
+          while (*ptr)
+            ++ptr;
+        break; }
+      case 'x':    // Output an unsigned hexadecimal value.
+      case 'X':
+      case 'p': {  // Output a pointer value.
+        // Check that there are arguments left to be inserted.
+        if (cur_arg >= max_args)
+          goto fail_to_expand;
+
+        const Arg& arg = args[cur_arg++];
+        int64_t i;
+        switch (ch) {
+        case 'x':  // Hexadecimal values are available for integer-like args.
+        case 'X':
+          // Check that the argument has the expected type.
+          if (arg.type_ != Arg::INT &&
+              arg.type_ != Arg::UINT)
+            goto fail_to_expand;
+          i = arg.i_;
+
+          // The Arg() constructor automatically performed sign expansion on
+          // signed parameters. This is great when outputting a %d decimal
+          // number, but can result in unexpected leading 0xFF bytes when
+          // outputting a %c hexadecimal number. Mask bits, if necessary.
+          if (arg.type_ == Arg::INT && arg.width_ < 8)
+            i &= ~(static_cast<int64_t>(-1) << (8*arg.width_));

[Jeffrey Yasskin, 2013/07/30 23:13:53]

Heh, alternately, "i &= (1LL << 8*arg.width_) - 1".

You could handle this in the Arg() constructor by converting unsigned arguments
to uint64_t before storing them in the int64_t.

+          break;
+        default:
+          // Pointer values require an actual pointer or a string.
+          if (arg.type_ == Arg::POINTER)
+            i = reinterpret_cast<uintptr_t>(arg.ptr_);
+          else if (arg.type_ == Arg::STRING)
+            i = reinterpret_cast<uintptr_t>(arg.s_);
+          else
+            goto fail_to_expand;
+
+          // Pointers always include the "0x" prefix. This affects padding.
+          if (padding) {
+            if (pad == ' ') {
+              // Predict the number of hex digits (including "0x" prefix) that
+              // will be output for this address when it is converted to ASCII.
+              size_t chars = 2;
+              uint64_t j = i;
+              do {
+                ++chars;
+                j >>= 4;
+              } while (j);
+
+              // Output the necessary number of space characters to perform
+              // padding. We can't rely on IToASCII() to do that for us, as it
+              // would incorrectly add padding _after_ the "0x" prefix.
+              Pad(buf, sz, &count, pad, padding, chars, &ptr);
+
+              // Inform itoa_r() that it no longer needs to handle the padding.
+              padding = 0;
+            } else {
+              // Adjust for the two-character "0x" prefix.
+              padding = padding >= 2 ? padding - 2 : 0;
+            }
+          }
+
+          // Insert "0x" prefix, if there is still sufficient space in the
+          // output buffer.
+          if (Out(buf, sz, &count, '0'))
+            ++ptr;
+          if (Out(buf, sz, &count, 'x'))
+            ++ptr;
+          break;
+        }
+
+        // No matter what data type this value originated from, print it as
+        // a regular hexadecimal number.
+        IncrementCount(&count,
+                       IToASCII(false, ch != 'x', i, ptr, sz - (ptr - buf),
+                                16, padding, pad));
+
+        // Advance "ptr" to the end of the string that was just emitted.
+        if (sz - (ptr - buf))
+          while (*ptr)
+            ++ptr;
+        break; }
+      case 's': {
+        // Check that there are arguments left to be inserted.
+        if (cur_arg >= max_args)
+          goto fail_to_expand;
+
+        // Check that the argument has the expected type.
+        const Arg& arg = args[cur_arg++];
+        if (arg.type_ != Arg::STRING)
+          goto fail_to_expand;
+
+        // Apply padding, if needed. This requires us to first check the
+        // length of the string that we are outputting.
+        if (padding) {
+          size_t len = 0;
+          for (const char* src = arg.s_ ? arg.s_ : "<NULL>"; *src++; )
+            ++len;
+          Pad(buf, sz, &count, ' ', padding, len, &ptr);
+        }
+
+        // Printing a string involves nothing more than copying it into the
+        // output buffer and making sure we don't output more bytes than
+        // available space.
+        for (const char* src = arg.s_ ? arg.s_ : "<NULL>"; *src; )
+          if (Out(buf, sz, &count, *src++))
+            ++ptr;
+        break; }
+      case '%':
+        // Quoted percent '%' character.
+        goto copy_verbatim;
+      fail_to_expand:
+        // C++ gives us tools to do type checking -- something that snprintf()
+        // could never really do. So, whenever we see arguments that don't
+        // match up with the format string, we refuse to output them. But
+        // since we have to be extremely conservative about being async-
+        // signal-safe, we are limited in the type of error handling that we

[Jeffrey Yasskin, 2013/07/30 23:13:53]

Is abort() or "*(volatile char*)0 = 0" ok for debug mode?

+        // can do. So, all we do is pass the format string unchanged. That
+        // should eventually get the user's attention.
+      default:
+        // Unknown or unsupported format character. Just copy verbatim to
+        // output.
+        if (Out(buf, sz, &count, '%'))
+          ++ptr;
+        if (!ch)
+          goto end_of_format_string;
+        if (Out(buf, sz, &count, ch))
+          ++ptr;
+        break;
+      }
+    } else {
+  copy_verbatim:
+    if (Out(buf, sz, &count, fmt[-1]))
+      ++ptr;
+    }
+  }
+ end_of_format_string:
+ end_of_output_buffer:
+  *ptr = '\000';
+  IncrementCount(&count);
+  return static_cast<ssize_t>(count)-1;
+}
+
+ssize_t FormatN(char* buf, size_t N, const char* fmt) {
+  // Make sure we can write at least one NUL byte.
+  ssize_t n = static_cast<ssize_t>(N);
+  if (n < 1)
+    return -1;
+  size_t count = 0;
+
+  // In the slow-path, we deal with errors by copying the contents of
+  // "fmt" unexpanded. This means, if there are no arguments passed, the
+  // Format() function always degenerates to version of strncpy() that
+  // de-duplicates '%' characters.
+  char* dst = buf;
+  const char* src = fmt;
+  for (; *src; ++src) {
+    char ch = *src;
+    if (!IncrementCount(&count) && n > 1) {
+      --dst;
+      break;
+    }
+    if (n > 1) {
+      --n;
+      *dst++ = ch;
+    }
+    if (ch == '%' && src[1] == '%')
+      ++src;
+  }
+  IncrementCount(&count);
+  *dst = '\000';
+  return static_cast<ssize_t>(count)-1;
+}
+
+}  // namespace debug
+}  // namespace base