http: reduce parser from 72 to 56 bytes on 64-bit

This allows the parser struct to fit in one cache line on
x86-64 systems where cache lines are 64 bytes.

Using 32-bit integer lengths is safe here because these are only for
tracking offsets within the HTTP header buffer.  We can safely limit
HTTP headers and in-memory buffers to be less than 4GB without
anybody complaining.

HTTP bodies continue to use off_t (usually 64-bit, even on 32-bit
systems) sizes and support as much as the OS/hardware can handle.

2 files changed, 15 insertions, 9 deletions

diff --git a/ext/unicorn_http/unicorn_http.rl b/ext/unicorn_http/unicorn_http.rl
index 9372d39..3294357 100644
--- a/ext/unicorn_http/unicorn_http.rl
+++ b/ext/unicorn_http/unicorn_http.rl
@@ -29,27 +29,27 @@ void init_unicorn_httpdate(void);
 /* all of these flags need to be set for keepalive to be supported */
 #define UH_FL_KEEPALIVE (UH_FL_KAVERSION | UH_FL_REQEOF | UH_FL_HASHEADER)
 
-static size_t MAX_HEADER_LEN = 1024 * (80 + 32); /* same as Mongrel */
+static unsigned int MAX_HEADER_LEN = 1024 * (80 + 32); /* same as Mongrel */
 
 /* this is only intended for use with Rainbows! */
 static VALUE set_maxhdrlen(VALUE self, VALUE len)
 {
-  return SIZET2NUM(MAX_HEADER_LEN = NUM2SIZET(len));
+  return UINT2NUM(MAX_HEADER_LEN = NUM2UINT(len));
 }
 
 /* keep this small for Rainbows! since every client has one */
 struct http_parser {
   int cs; /* Ragel internal state */
   unsigned int flags;
-  size_t mark;
-  size_t offset;
+  unsigned int mark;
+  unsigned int offset;
   union { /* these 2 fields don't nest */
-    size_t field;
-    size_t query;
+    unsigned int field;
+    unsigned int query;
   } start;
   union {
-    size_t field_len; /* only used during header processing */
-    size_t dest_offset; /* only used during body processing */
+    unsigned int field_len; /* only used during header processing */
+    unsigned int dest_offset; /* only used during body processing */
   } s;
   VALUE buf;
   VALUE env;
@@ -74,7 +74,7 @@ static void parser_raise(VALUE klass, const char *msg)
 }
 
 #define REMAINING (unsigned long)(pe - p)
-#define LEN(AT, FPC) (FPC - buffer - hp->AT)
+#define LEN(AT, FPC) (FPC - buffer - (unsigned long)hp->AT)
 #define MARK(M,FPC) (hp->M = (FPC) - buffer)
 #define PTR_TO(F) (buffer + hp->F)
 #define STR_NEW(M,FPC) rb_str_new(PTR_TO(M), LEN(M, FPC))
diff --git a/test/unit/test_http_parser_ng.rb b/test/unit/test_http_parser_ng.rb
index 9167845..d5c8d2e 100644
--- a/test/unit/test_http_parser_ng.rb
+++ b/test/unit/test_http_parser_ng.rb
@@ -11,6 +11,12 @@ class HttpParserNgTest < Test::Unit::TestCase
     @parser = HttpParser.new
   end
 
+  def test_parser_max_len
+    assert_raises(RangeError) do
+      HttpParser.max_header_len = 0xffffffff + 1
+    end
+  end
+
   def test_next_clear
     r = "GET / HTTP/1.1\r\nHost: example.com\r\n\r\n"
     @parser.buf << r