docs/dispatch.html

   1 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
   2 <html lang="en">
   3 <head>
   4   <meta http-equiv="content-type" content="text/html; charset=utf-8">
   5   <title>GL Dispatch</title>
   6   <link rel="stylesheet" type="text/css" href="mesa.css">
   7 </head>
   8 <body>
   9
  10 <div class="header">
  11   The Mesa 3D Graphics Library
  12 </div>
  13
  14 <iframe src="contents.html"></iframe>
  15 <div class="content">
  16
  17 <h1>GL Dispatch</h1>
  18
  19 <p>Several factors combine to make efficient dispatch of OpenGL functions
  20 fairly complicated.  This document attempts to explain some of the issues
  21 and introduce the reader to Mesa's implementation.  Readers already familiar
  22 with the issues around GL dispatch can safely skip ahead to the <a
  23 href="#overview">overview of Mesa's implementation</a>.</p>
  24
  25 <h2>1. Complexity of GL Dispatch</h2>
  26
  27 <p>Every GL application has at least one object called a GL <em>context</em>.
  28 This object, which is an implicit parameter to every GL function, stores all
  29 of the GL related state for the application.  Every texture, every buffer
  30 object, every enable, and much, much more is stored in the context.  Since
  31 an application can have more than one context, the context to be used is
  32 selected by a window-system dependent function such as
  33 <code>glXMakeContextCurrent</code>.</p>
  34
  35 <p>In environments that implement OpenGL with X-Windows using GLX, every GL
  36 function, including the pointers returned by <code>glXGetProcAddress</code>, are
  37 <em>context independent</em>.  This means that no matter what context is
  38 currently active, the same <code>glVertex3fv</code> function is used.</p>
  39
  40 <p>This creates the first bit of dispatch complexity.  An application can
  41 have two GL contexts.  One context is a direct rendering context where
  42 function calls are routed directly to a driver loaded within the
  43 application's address space.  The other context is an indirect rendering
  44 context where function calls are converted to GLX protocol and sent to a
  45 server.  The same <code>glVertex3fv</code> has to do the right thing depending
  46 on which context is current.</p>
  47
  48 <p>Highly optimized drivers or GLX protocol implementations may want to
  49 change the behavior of GL functions depending on current state.  For
  50 example, <code>glFogCoordf</code> may operate differently depending on whether
  51 or not fog is enabled.</p>
  52
  53 <p>In multi-threaded environments, it is possible for each thread to have a
  54 different GL context current.  This means that poor old <code>glVertex3fv</code>
  55 has to know which GL context is current in the thread where it is being
  56 called.</p>
  57
  58 <h2 id="overview">2. Overview of Mesa's Implementation</h2>
  59
  60 <p>Mesa uses two per-thread pointers.  The first pointer stores the address
  61 of the context current in the thread, and the second pointer stores the
  62 address of the <em>dispatch table</em> associated with that context.  The
  63 dispatch table stores pointers to functions that actually implement
  64 specific GL functions.  Each time a new context is made current in a thread,
  65 these pointers a updated.</p>
  66
  67 <p>The implementation of functions such as <code>glVertex3fv</code> becomes
  68 conceptually simple:</p>
  69
  70 <ul>
  71 <li>Fetch the current dispatch table pointer.</li>
  72 <li>Fetch the pointer to the real <code>glVertex3fv</code> function from the
  73 table.</li>
  74 <li>Call the real function.</li>
  75 </ul>
  76
  77 <p>This can be implemented in just a few lines of C code.  The file
  78 <code>src/mesa/glapi/glapitemp.h</code> contains code very similar to this.</p>
  79
  80 <figure>
  81 <pre>
  82 void glVertex3f(GLfloat x, GLfloat y, GLfloat z)
  83 {
  84     const struct _glapi_table * const dispatch = GET_DISPATCH();
  85
  86     (*dispatch-&gt;Vertex3f)(x, y, z);
  87 }
  88 </pre>
  89 <figcaption>Sample dispatch function</figcaption>
  90 </figure>
  91
  92 <p>The problem with this simple implementation is the large amount of
  93 overhead that it adds to every GL function call.</p>
  94
  95 <p>In a multithreaded environment, a naive implementation of
  96 <code>GET_DISPATCH</code> involves a call to <code>pthread_getspecific</code> or a
  97 similar function.  Mesa provides a wrapper function called
  98 <code>_glapi_get_dispatch</code> that is used by default.</p>
  99
 100 <h2>3. Optimizations</h2>
 101
 102 <p>A number of optimizations have been made over the years to diminish the
 103 performance hit imposed by GL dispatch.  This section describes these
 104 optimizations.  The benefits of each optimization and the situations where
 105 each can or cannot be used are listed.</p>
 106
 107 <h3>3.1. Dual dispatch table pointers</h3>
 108
 109 <p>The vast majority of OpenGL applications use the API in a single threaded
 110 manner.  That is, the application has only one thread that makes calls into
 111 the GL.  In these cases, not only do the calls to
 112 <code>pthread_getspecific</code> hurt performance, but they are completely
 113 unnecessary!  It is possible to detect this common case and avoid these
 114 calls.</p>
 115
 116 <p>Each time a new dispatch table is set, Mesa examines and records the ID
 117 of the executing thread.  If the same thread ID is always seen, Mesa knows
 118 that the application is, from OpenGL's point of view, single threaded.</p>
 119
 120 <p>As long as an application is single threaded, Mesa stores a pointer to
 121 the dispatch table in a global variable called <code>_glapi_Dispatch</code>.
 122 The pointer is also stored in a per-thread location via
 123 <code>pthread_setspecific</code>.  When Mesa detects that an application has
 124 become multithreaded, <code>NULL</code> is stored in <code>_glapi_Dispatch</code>.</p>
 125
 126 <p>Using this simple mechanism the dispatch functions can detect the
 127 multithreaded case by comparing <code>_glapi_Dispatch</code> to <code>NULL</code>.
 128 The resulting implementation of <code>GET_DISPATCH</code> is slightly more
 129 complex, but it avoids the expensive <code>pthread_getspecific</code> call in
 130 the common case.</p>
 131
 132 <figure>
 133 <pre>
 134 #define GET_DISPATCH() \
 135     (_glapi_Dispatch != NULL) \
 136         ? _glapi_Dispatch : pthread_getspecific(&amp;_glapi_Dispatch_key)
 137 </pre>
 138 <figcaption>Improved <code>GET_DISPATCH</code> Implementation</figcaption>
 139 </figure>
 140
 141 <h3>3.2. ELF TLS</h3>
 142
 143 <p>Starting with the 2.4.20 Linux kernel, each thread is allocated an area
 144 of per-thread, global storage.  Variables can be put in this area using some
 145 extensions to GCC.  By storing the dispatch table pointer in this area, the
 146 expensive call to <code>pthread_getspecific</code> and the test of
 147 <code>_glapi_Dispatch</code> can be avoided.</p>
 148
 149 <p>The dispatch table pointer is stored in a new variable called
 150 <code>_glapi_tls_Dispatch</code>.  A new variable name is used so that a single
 151 libGL can implement both interfaces.  This allows the libGL to operate with
 152 direct rendering drivers that use either interface.  Once the pointer is
 153 properly declared, <code>GET_DISPACH</code> becomes a simple variable
 154 reference.</p>
 155
 156 <figure>
 157 <pre>
 158 extern __thread struct _glapi_table *_glapi_tls_Dispatch
 159     __attribute__((tls_model("initial-exec")));
 160
 161 #define GET_DISPATCH() _glapi_tls_Dispatch
 162 </pre>
 163 <figcaption>TLS <code>GET_DISPATCH</code> Implementation</figcaption>
 164 </figure>
 165
 166 <p>Use of this path is controlled by the preprocessor define
 167 <code>USE_ELF_TLS</code>.  Any platform capable of using ELF TLS should use this
 168 as the default dispatch method.</p>
 169
 170 <h3>3.3. Assembly Language Dispatch Stubs</h3>
 171
 172 <p>Many platforms has difficulty properly optimizing the tail-call in the
 173 dispatch stubs.  Platforms like x86 that pass parameters on the stack seem
 174 to have even more difficulty optimizing these routines.  All of the dispatch
 175 routines are very short, and it is trivial to create optimal assembly
 176 language versions.  The amount of optimization provided by using assembly
 177 stubs varies from platform to platform and application to application.
 178 However, by using the assembly stubs, many platforms can use an additional
 179 space optimization (see <a href="#fixedsize">below</a>).</p>
 180
 181 <p>The biggest hurdle to creating assembly stubs is handling the various
 182 ways that the dispatch table pointer can be accessed.  There are four
 183 different methods that can be used:</p>
 184
 185 <ol>
 186 <li>Using <code>_glapi_Dispatch</code> directly in builds for non-multithreaded
 187 environments.</li>
 188 <li>Using <code>_glapi_Dispatch</code> and <code>_glapi_get_dispatch</code> in
 189 multithreaded environments.</li>
 190 <li>Using <code>_glapi_Dispatch</code> and <code>pthread_getspecific</code> in
 191 multithreaded environments.</li>
 192 <li>Using <code>_glapi_tls_Dispatch</code> directly in TLS enabled
 193 multithreaded environments.</li>
 194 </ol>
 195
 196 <p>People wishing to implement assembly stubs for new platforms should focus
 197 on #4 if the new platform supports TLS.  Otherwise, implement #2 followed by
 198 #3.  Environments that do not support multithreading are uncommon and not
 199 terribly relevant.</p>
 200
 201 <p>Selection of the dispatch table pointer access method is controlled by a
 202 few preprocessor defines.</p>
 203
 204 <ul>
 205 <li>If <code>USE_ELF_TLS</code> is defined, method #3 is used.</li>
 206 <li>If <code>HAVE_PTHREAD</code> is defined, method #2 is used.</li>
 207 <li>If none of the preceding are defined, method #1 is used.</li>
 208 </ul>
 209
 210 <p>Two different techniques are used to handle the various different cases.
 211 On x86 and SPARC, a macro called <code>GL_STUB</code> is used.  In the preamble
 212 of the assembly source file different implementations of the macro are
 213 selected based on the defined preprocessor variables.  The assembly code
 214 then consists of a series of invocations of the macros such as:
 215
 216 <figure>
 217 <pre>
 218 GL_STUB(Color3fv, _gloffset_Color3fv)
 219 </pre>
 220 <figcaption>SPARC Assembly Implementation of <code>glColor3fv</code></figcaption>
 221 </figure>
 222
 223 <p>The benefit of this technique is that changes to the calling pattern
 224 (i.e., addition of a new dispatch table pointer access method) require fewer
 225 changed lines in the assembly code.</p>
 226
 227 <p>However, this technique can only be used on platforms where the function
 228 implementation does not change based on the parameters passed to the
 229 function.  For example, since x86 passes all parameters on the stack, no
 230 additional code is needed to save and restore function parameters around a
 231 call to <code>pthread_getspecific</code>.  Since x86-64 passes parameters in
 232 registers, varying amounts of code needs to be inserted around the call to
 233 <code>pthread_getspecific</code> to save and restore the GL function's
 234 parameters.</p>
 235
 236 <p>The other technique, used by platforms like x86-64 that cannot use the
 237 first technique, is to insert <code>#ifdef</code> within the assembly
 238 implementation of each function.  This makes the assembly file considerably
 239 larger (e.g., 29,332 lines for <code>glapi_x86-64.S</code> versus 1,155 lines for
 240 <code>glapi_x86.S</code>) and causes simple changes to the function
 241 implementation to generate many lines of diffs.  Since the assembly files
 242 are typically generated by scripts (see <a href="#autogen">below</a>), this
 243 isn't a significant problem.</p>
 244
 245 <p>Once a new assembly file is created, it must be inserted in the build
 246 system.  There are two steps to this.  The file must first be added to
 247 <code>src/mesa/sources</code>.  That gets the file built and linked.  The second
 248 step is to add the correct <code>#ifdef</code> magic to
 249 <code>src/mesa/glapi/glapi_dispatch.c</code> to prevent the C version of the
 250 dispatch functions from being built.</p>
 251
 252 <h3 id="fixedsize">3.4. Fixed-Length Dispatch Stubs</h3>
 253
 254 <p>To implement <code>glXGetProcAddress</code>, Mesa stores a table that
 255 associates function names with pointers to those functions.  This table is
 256 stored in <code>src/mesa/glapi/glprocs.h</code>.  For different reasons on
 257 different platforms, storing all of those pointers is inefficient.  On most
 258 platforms, including all known platforms that support TLS, we can avoid this
 259 added overhead.</p>
 260
 261 <p>If the assembly stubs are all the same size, the pointer need not be
 262 stored for every function.  The location of the function can instead be
 263 calculated by multiplying the size of the dispatch stub by the offset of the
 264 function in the table.  This value is then added to the address of the first
 265 dispatch stub.</p>
 266
 267 <p>This path is activated by adding the correct <code>#ifdef</code> magic to
 268 <code>src/mesa/glapi/glapi.c</code> just before <code>glprocs.h</code> is
 269 included.</p>
 270
 271 </div>
 272 </body>
 273 </html>