Re: [RFC 1/8] memory: Allow eventfd add/del without starting a transaction

2021-03-30 Thread Stefan Hajnoczi
On Tue, Mar 30, 2021 at 09:47:49AM +0200, Greg Kurz wrote: > On Mon, 29 Mar 2021 18:03:49 +0100 > Stefan Hajnoczi wrote: > > > On Thu, Mar 25, 2021 at 04:07:28PM +0100, Greg Kurz wrote: > > > diff --git a/include/exec/memory.h b/include/exec/memory.h > > > index 5728a681b27d..98ed552e001c 100644

Re: [RFC 1/8] memory: Allow eventfd add/del without starting a transaction

2021-03-30 Thread Greg Kurz
On Mon, 29 Mar 2021 18:03:49 +0100 Stefan Hajnoczi wrote: > On Thu, Mar 25, 2021 at 04:07:28PM +0100, Greg Kurz wrote: > > diff --git a/include/exec/memory.h b/include/exec/memory.h > > index 5728a681b27d..98ed552e001c 100644 > > --- a/include/exec/memory.h > > +++ b/include/exec/memory.h > > @@

Re: [RFC 1/8] memory: Allow eventfd add/del without starting a transaction

2021-03-29 Thread Stefan Hajnoczi
On Thu, Mar 25, 2021 at 04:07:28PM +0100, Greg Kurz wrote: > diff --git a/include/exec/memory.h b/include/exec/memory.h > index 5728a681b27d..98ed552e001c 100644 > --- a/include/exec/memory.h > +++ b/include/exec/memory.h > @@ -1848,13 +1848,25 @@ void memory_region_clear_flush_coalesced(MemoryRegi

[RFC 1/8] memory: Allow eventfd add/del without starting a transaction

2021-03-25 Thread Greg Kurz
Each addition or deletion of an eventfd happens in its own MR transaction. This doesn't scale well with multiqueue devices that do 1:1 queue:vCPU mapping (e.g. virtio-scsi-pci or virtio-blk-pci) : these devices typically create at least one eventfd per queue and memory_region_transaction_commit(),