On Sun, Apr 26, 2026 at 10:42:24AM -0300, Jason Gunthorpe wrote: > On Sun, Apr 26, 2026 at 01:39:57PM +0300, Leon Romanovsky wrote: > > On Fri, Apr 24, 2026 at 11:19:21AM -0300, Jason Gunthorpe wrote: > > > On Thu, Apr 23, 2026 at 05:09:50PM +0300, Leon Romanovsky wrote: > > > > > > > > > Leon mentioned that different firmware revisions would have > > > > > > different > > > > > > parameters for a given opcode, and that one would need to inspect > > > > > > those parameters to properly filter the command. Is that not true, > > > > > > or > > > > > > am I misreading or misunderstanding Leon's comments? > > > > > > > > > > They are ABI stable, so there will be rules about future changes that > > > > > old software can follow to ignore or reject future things it doesn't > > > > > understand. > > > > > > > > It is wishful thinking and applicable only to mlx5 devices. No one > > > > promises that other devices follow same ABI rules. > > > > > > Well, I will definately kick them out of fwctl if they don't. > > > > It is easy to say but harder to follow. The kernel includes many devices > > that > > exist only in specific hyperscale environments, where the update cycle is > > tightly controlled. They easily can break FW backward compatibility. > > Well Linus's rule applies here, if it doesn't bother anyone it didn't > break..
Great, that means they can load any BPF program they want and access whatever firmware fields they choose. Your earlier claim about 'not breaking FW compatibility' is only partially correct. Thanks > > Jason >
