NVIDIA Talks Of Optimus Possibilities For Linux

[sunny0]

NVidia's binary blobs have been around for more than a decade, offer good performance, and still they didn't propell Linux to 90% desktop share. And now it's Alan Cox' fault?

Why do you think it is exactly THIS license change which will bring all gaming to Linux and make it THE desktop for all (tm)?

Overlooking everything else, yes he is not responsible.

On the other hand, I buy NVIDIA products and I expect the manufacture to do everything possible to make their product work better under LINUX. That engineer is doing his job. You are just tossing around meaningless attacks.

[patrik]

With such an attitude Linux will always have 1-1,5% market share. And don't even get me started on Stable API nonsense and lack of real backward libraries compatibility (it's just not there).

Take a second and think about what you're saying here...

You're arguing that higher FPS in games is more important than your freedom!!! And if Alan has written code that you can use free of charge, don't you think you owe it to him to let him decide how it is to be licensed?

[Silverwing]

Take a second and think about what you're saying here...

You're arguing that higher FPS in games is more important than your freedom!!! And if Alan has written code that you can use free of charge, don't you think you owe it to him to let him decide how it is to be licensed?

Well.. I agree on that statement. I don't give a single fuck if I have to use closed source drivers. If Nvidia doesn't want to release open source drivers, so be it. They are responsible for their drivers and they are doing quite well except for the optimus functionality. Furthermore, I use Linux because it offers me freedom. Limiting me to not use close source drivers will limit my freedom. It limits me on playing games on Linux.

I strongly support open source software, but I don't hate closed source software because it's closed source.

[FireBurn]

The whole point of Symbol GPL was to prevent non-GPL code using it as a derived work - the reason Nvidia's binary blob works is it's LGPL wrapper on symbols that don't have symbol GPL exported

They've gotten away with this because Linus, quite rightly, points out that the Nvidia binary isn't using the interfaces as a derived work (they've already got it working on so many platforms that it can't be Linux Kernel secret sauce)

This wouldn't be the case with dma-buf they would be clearly deriving something new and something they didn't help develop

Perhaps if they were willing to create a binary Intel driver similar to AMD's work that could bypass all the open source work including dma-buf it would keep them in a safer place from a legal perspective

As much as I'd like to see them adopt a standard Symbol GPL was added specifically for this reason

[TheBlackCat]

And if Alan has written code that you can use free of charge, don't you think you owe it to him to let him decide how it is to be licensed?

Yes, but as best as I can tell, it isn't his code he is trying to control, it is code written by other people. He seems to be saying that since he contributed code to the Linux kernel, he is opposed to other parts of the Linux kernel he did not write being able to interact with closed-source software in this manner. Whether this is a valid position or not is another debate.

[spykes]

Their driver stack is different. They could either rewrite it to use the DRI, or continue to use the mechanism that they presumably share with their windows driver. Rewriting is more work for dubious benefit, so...

I don't expect them to use the existing DRI code, but I suppose they have something that does the same job.
Why do they can't split their code and present their own DRI driver for kernel inclusion ?
I fail to see what can prevent them to do that.

[Silverthorn]

Nvidia is a big company. Why not put some money behind their offer. Just because something is licensed under GPL does not mean it is not possible to pay the licence holder for the privilege to include and use the protected code in a closed source project.

[patrik]

Yes, but as best as I can tell, it isn't his code he is trying to control, it is code written by other people. He seems to be saying that since he contributed code to the Linux kernel, he is opposed to other parts of the Linux kernel he did not write being able to interact with closed-source software in this manner. Whether this is a valid position or not is another debate.

True, but I think he should be granted that right. At the end of the day, it is our freedom he is protecting. The goal of nvidia is to make money (nothing wrong with that), but that is not the goal of Linux. If nvidia wants to make money on the Linux market, they need to understand that.

[agd5f]

I don't expect them to use the existing DRI code, but I suppose they have something that does the same job.
Why do they can't split their code and present their own DRI driver for kernel inclusion ?
I fail to see what can prevent them to do that.

They would likely have to rewrite and sanitize large amounts of code to be accepted upstream into the kernel. Plus, if they still have a closed source 3D driver, their kernel driver is not likely to be accepted upstream. Once again, lots of work, little benefit for anyone.

[birdie]

Take a second and think about what you're saying here...

You're arguing that higher FPS in games is more important than your freedom!!! And if Alan has written code that you can use free of charge, don't you think you owe it to him to let him decide how it is to be licensed?

Freedom not to successfully use for any real life work? I.e. freedom to work in text console?

Linux is meant to be run on modern hardware. It looks to me Alan Cox and you have a different opinion.