Excessive TLB flush ranges

[Thomas Gleixner]

On Tue, May 16 2023 at 10:26, Baoquan He wrote:
> On 05/15/23 at 08:17pm, Uladzislau Rezki wrote:
>> For systems which lack a full TLB flush and to flush a long range is
>> a problem(it takes time), probably we can flush VA one by one. Because
>> currently we calculate a flush range [min:max] and that range includes
>> the space that might not be mapped at all. Like below:
>
> It's fine if we only calculate a flush range of [min:max] with VA. In
> vm_reset_perms(), it calculates the flush range with the impacted direct
> mapping range, then merge it with VA's range. That looks really strange
> and surprising. If the vm->pages[] are got from a lower part of physical
> memory, the final merged flush will span tremendous range. Wondering why
> we need merge the direct map range with VA range, then do flush. Not
> sure if I misunderstand it.

So what happens on this BPF teardown is:

The vfree(8k) ends up flushing 3 entries. The actual vmalloc part (2) and
one extra which is in the direct map. I haven't verified that yet, but I
assume it's the alias of one of the vmalloc'ed pages.

Thanks,

        tglx