buffer: proper safety checks for unbounded memory

The previous work for unbounded memory usage and overflows on the buffer
API had several shortcomings:

1. The total size of the buffer was limited by arbitrarily small
precision on the storage type for buffer indexes (typedef'd as
`bufsize_t`). This is not a good design pattern in secure applications,
particualarly since it requires the addition of helper functions to cast
to/from the native `size` types and the custom type for the buffer, and
check for overflows.

2. The library was calling `abort` on overflow and memory allocation
failures. This is not a good practice for production libraries, since it
turns a potential RCE into a trivial, guaranteed DoS to the whole
application that is linked against the library. It defeats the whole
point of performing overflow or allocation checks when the checks will
crash the library and the enclosing program anyway.

3. The default size limits for buffers were essentially unbounded
(capped to the precision of the storage type) and could lead to DoS
attacks by simple memory exhaustion (particularly critical in 32-bit
platforms). This is not a good practice for a library that handles
arbitrary user input.

Hence, this patchset provides slight (but in my opinion critical)
improvements on this area, copying some of the patterns we've used in
the past for high throughput, security sensitive Markdown parsers:

1. The storage type for buffer sizes is now platform native (`ssize_t`).
Ideally, this would be a `size_t`, but several parts of the code expect
buffer indexes to be possibly negative. Either way, switching to a
`size` type is an strict improvement, particularly in 64-bit platforms.
All the helpers that assured that values cannot escape the `size` range
have been removed, since they are superfluous.

2. The overflow checks have been removed. Instead, the maximum size for
a buffer has been set to a safe value for production usage (32mb) that
can be proven not to overflow in practice. Users that need to parse
particularly large Markdown documents can increase this value. A static,
compile-time check has been added to ensure that the maximum buffer size
cannot overflow on any growth operations.

3. The library no longer aborts on buffer overflow.  The CMark library
now follows the convention of other Markdown implementations (such as
Hoedown and Sundown) and silently handles buffer overflows and
allocation failures by dropping data from the buffer. The result is
that pathological Markdown documents that try to exploit the library
will instead generate truncated (but valid, and safe) outputs.

All tests after these small refactorings have been verified to pass.

---

NOTE: Regarding 32 bit overflows, generating test cases that crash the
library is trivial (any input document larger than 2gb will crash
CMark), but most Python implementations have issues with large strings
to begin with, so a test case cannot be added to the pathological tests
suite, since it's written in Python.

1 files changed, 37 insertions, 56 deletions

diff --git a/src/buffer.c b/src/buffer.c
index 4efa97b..80ca49a 100644
--- a/src/buffer.c
+++ b/src/buffer.c
@@ -5,6 +5,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <stdint.h>
+#include <limits.h>
 
 #include "config.h"
 #include "cmark_ctype.h"
@@ -28,68 +29,48 @@ void cmark_strbuf_init(cmark_strbuf *buf, bufsize_t initial_size) {
     cmark_strbuf_grow(buf, initial_size);
 }
 
-void cmark_strbuf_overflow_err() {
-  fprintf(stderr, "String buffer overflow");
-  abort();
+static CMARK_INLINE bool S_strbuf_grow_by(cmark_strbuf *buf, bufsize_t add) {
+  return cmark_strbuf_grow(buf, buf->size + add);
 }
 
-static CMARK_INLINE void S_strbuf_grow_by(cmark_strbuf *buf, size_t add) {
-  size_t target_size = (size_t)buf->size + add;
-
-  if (target_size < add            /* Integer overflow. */
-      || target_size > BUFSIZE_MAX /* Truncation overflow. */
-      ) {
-    cmark_strbuf_overflow_err();
-    return; /* unreachable */
-  }
-
-  if ((bufsize_t)target_size >= buf->asize)
-    cmark_strbuf_grow(buf, (bufsize_t)target_size);
-}
+#if BUFSIZE_MAX > (SIZE_MAX / 4)
+#  error "unsafe value for BUFSIZE_MAX"
+#endif
 
-void cmark_strbuf_grow(cmark_strbuf *buf, bufsize_t target_size) {
-  unsigned char *new_ptr;
+bool cmark_strbuf_grow(cmark_strbuf *buf, bufsize_t target_size) {
+  assert(target_size > 0);
 
   if (target_size < buf->asize)
-    return;
-
-  if (buf->asize == 0) {
-    new_ptr = NULL;
-  } else {
-    new_ptr = buf->ptr;
-  }
+    return true;
+
+  /*
+   * Do not allow string buffers to grow past this "safe" value.
+   *
+   * Note that this is a soft cap to prevent unbounded memory growth:
+   * in practice, the buffer can get larger than this value because we
+   * overgrow it by 50%
+   *
+   * Note that there are no overflow checks for the realloc because
+   * the value of BUFSIZE_MAX is always assured to be impossible
+   * to overflow on both 32 and 64 bit systems, since it will never
+   * be larger than 1/4th of our address space.
+   */
+  if (target_size > BUFSIZE_MAX)
+    return false;
 
   /* Oversize the buffer by 50% to guarantee amortized linear time
    * complexity on append operations. */
-  size_t new_size = (size_t)target_size + (size_t)target_size / 2;
-
-  /* Account for terminating null byte. */
+  bufsize_t new_size = target_size + target_size / 2;
   new_size += 1;
-
-  /* round allocation up to multiple of 8 */
   new_size = (new_size + 7) & ~7;
 
-  if (new_size < (size_t)target_size /* Integer overflow. */
-      || new_size > BUFSIZE_MAX      /* Truncation overflow. */
-      ) {
-    if (target_size >= BUFSIZE_MAX) {
-      /* No space for terminating null byte. */
-      cmark_strbuf_overflow_err();
-      return; /* unreachable */
-    }
-    /* Oversize by the maximum possible amount. */
-    new_size = BUFSIZE_MAX;
-  }
+  unsigned char *new_ptr = realloc(buf->asize ? buf->ptr : NULL, new_size);
+  if (!new_ptr)
+    return false;
 
-  new_ptr = (unsigned char *)realloc(new_ptr, new_size);
-
-  if (!new_ptr) {
-    perror("realloc in cmark_strbuf_grow");
-    abort();
-  }
-
-  buf->asize = (bufsize_t)new_size;
+  buf->asize = new_size;
   buf->ptr = new_ptr;
+  return true;
 }
 
 bufsize_t cmark_strbuf_len(const cmark_strbuf *buf) { return buf->size; }
@@ -117,8 +98,8 @@ void cmark_strbuf_set(cmark_strbuf *buf, const unsigned char *data,
     cmark_strbuf_clear(buf);
   } else {
     if (data != buf->ptr) {
-      if (len >= buf->asize)
-        cmark_strbuf_grow(buf, len);
+      if (len >= buf->asize && !cmark_strbuf_grow(buf, len))
+        return;
       memmove(buf->ptr, data, len);
     }
     buf->size = len;
@@ -128,21 +109,21 @@ void cmark_strbuf_set(cmark_strbuf *buf, const unsigned char *data,
 
 void cmark_strbuf_sets(cmark_strbuf *buf, const char *string) {
   cmark_strbuf_set(buf, (const unsigned char *)string,
-                   string ? cmark_strbuf_safe_strlen(string) : 0);
+                   string ? strlen(string) : 0);
 }
 
 void cmark_strbuf_putc(cmark_strbuf *buf, int c) {
-  S_strbuf_grow_by(buf, 1);
+  if (!S_strbuf_grow_by(buf, 1))
+    return;
   buf->ptr[buf->size++] = (unsigned char)(c & 0xFF);
   buf->ptr[buf->size] = '\0';
 }
 
 void cmark_strbuf_put(cmark_strbuf *buf, const unsigned char *data,
                       bufsize_t len) {
-  if (len <= 0)
+  if (len <= 0 || !S_strbuf_grow_by(buf, len))
     return;
 
-  S_strbuf_grow_by(buf, len);
   memmove(buf->ptr + buf->size, data, len);
   buf->size += len;
   buf->ptr[buf->size] = '\0';
@@ -150,7 +131,7 @@ void cmark_strbuf_put(cmark_strbuf *buf, const unsigned char *data,
 
 void cmark_strbuf_puts(cmark_strbuf *buf, const char *string) {
   cmark_strbuf_put(buf, (const unsigned char *)string,
-                   cmark_strbuf_safe_strlen(string));
+                   strlen(string));
 }
 
 void cmark_strbuf_copy_cstr(char *data, bufsize_t datasize,