gldraw

You could as well just modify the PLT/GOT entries for the glDraw… functions to a dumper function and then jmp to the actual glDraw… call.

I only argue that there is no syscall in glDraw* as well as the vast majority of the APIs.

The final command submission itself isn't free of course, but clearly more time is spent processing precisely those glDraw*() calls that you seem to think don't matter.

And what exactly is preventing me from injecting my custom libGL.so that hooks onto the `glDraw…` calls, and downloads the current contents of the bound textures using `glGetTexImage`?

But even if DLL/.so checksumming were applicable, you could still ptrace into the program binary and patch the PLT/GOT entries for the `glDraw…` jumping to a little bit of dumper code (added with ptrace again) that extracts the data and then trampolines into the actual `glDraw…` function called.

> The final command submission itself isn't free of course, but clearly more time is spent processing precisely those glDraw*() calls that you seem to think don't matter.

Just inject a little bit of code into the game process that calls a dumper function just before (or after, it doesn't really matter) calls to `glDraw…` to dump out all the data of the currently bound buffer objects and textures.

Like, am I allowed to call glDraw* multiple times per different objects when the data is already on the gpu, or should I try to push somewhat dissimilar objects into the same buffer and write more complicated shaders differentiating them (without ifs if possible?) or are gpus so performant nowadays that unless I do something stupid I should not worry about it?