Re: [PATCH] iommu/arm-smmu-v3: Fix L1 stream table index calculation for AmpereOne

[Yang Shi]

On 10/1/24 12:18 PM, Jason Gunthorpe wrote:
> On Tue, Oct 01, 2024 at 12:09:03PM -0700, Yang Shi wrote:
> > > Also, there are other places doing "1 << smmu->sid_bits", e.g.
> > > arm_smmu_init_strtab_linear().
> > The disassembly shows it uses "sbfiz x21, x20, 6, 32" instead of lsl. 1UL
> > should be used if we want to take extra caution and don't prefer rely on
> > compiler.
> Still, we should be fixing them all if sid_bits == 32, all those
> shifts should be throwing a UBSAN error. It would be crazy to have a

OK, will cover this is v2.

> 32 bit linear table but I guess it is allowed?

I'm not smmu expert, but if sid_bits is 32, it looks like the linear 
table will consume 256GB IIUC? That is crazy.

> Jason