On Mon, 14 May 2018 20:28:01 +0300 Boaz Harrosh <boazh@xxxxxxxxxx> wrote: > On a call to mmap an mmap provider (like an FS) can put > this flag on vma->vm_flags. > > The VM_LOCAL_CPU flag tells the Kernel that the vma will be used > from a single-core only, and therefore invalidation (flush_tlb) of > PTE(s) need not be a wide CPU scheduling. > > The motivation of this flag is the ZUFS project where we want > to optimally map user-application buffers into a user-mode-server > execute the operation and efficiently unmap. > > In this project we utilize a per-core server thread so everything > is kept local. If we use the regular zap_ptes() API All CPU's > are scheduled for the unmap, though in our case we know that we > have only used a single core. The regular zap_ptes adds a very big > latency on every operation and mostly kills the concurrency of the > over all system. Because it imposes a serialization between all cores I'd have thought that in this situation, only the local CPU's bit is set in the vma's mm_cpumask() and the remote invalidations are not performed. Is that a misunderstanding, or is all that stuff not working correctly?
