On Fri, May 31, 2019 at 04:00:50PM +0200, Michal Hocko wrote: > On Fri 31-05-19 22:19:00, Minchan Kim wrote: > > On Fri, May 31, 2019 at 10:37:57AM +0200, Michal Hocko wrote: > > > On Fri 31-05-19 15:43:12, Minchan Kim wrote: > > > > There is some usecase that centralized userspace daemon want to give > > > > a memory hint like MADV_[COLD|PAGEEOUT] to other process. Android's > > > > ActivityManagerService is one of them. > > > > > > > > It's similar in spirit to madvise(MADV_WONTNEED), but the information > > > > required to make the reclaim decision is not known to the app. Instead, > > > > it is known to the centralized userspace daemon(ActivityManagerService), > > > > and that daemon must be able to initiate reclaim on its own without > > > > any app involvement. > > > > > > > > To solve the issue, this patch introduces new syscall process_madvise(2). > > > > It could give a hint to the exeternal process of pidfd. > > > > > > > > int process_madvise(int pidfd, void *addr, size_t length, int advise, > > > > unsigned long cookie, unsigned long flag); > > > > > > > > Since it could affect other process's address range, only privileged > > > > process(CAP_SYS_PTRACE) or something else(e.g., being the same UID) > > > > gives it the right to ptrace the process could use it successfully. > > > > > > > > The syscall has a cookie argument to privode atomicity(i.e., detect > > > > target process's address space change since monitor process has parsed > > > > the address range of target process so the operaion could fail in case > > > > of happening race). Although there is no interface to get a cookie > > > > at this moment, it could be useful to consider it as argument to avoid > > > > introducing another new syscall in future. It could support *atomicity* > > > > for disruptive hint(e.g., MADV_DONTNEED|FREE). > > > > flag argument is reserved for future use if we need to extend the API. > > > > > > Providing an API that is incomplete will not fly. Really. As this really > > > begs for much more discussion and it would be good to move on with the > > > core idea of the pro active memory memory management from userspace > > > usecase. Could you split out the core change so that we can move on and > > > leave the external for a later discussion. I believe this would lead to > > > a smoother integration. > > > > No problem but I need to understand what you want a little bit more because > > I thought this patchset is already step by step so if we reach the agreement > > of part of them like [1-5/6], it could be merged first. > > > > Could you say how you want to split the patchset for forward progress? > > I would start with new madvise modes and once they are in a shape to be > merged then we can start the remote madvise API. I believe that even > local process reclaim modes are interesting and useful. I haven't heard > anybody objecting to them without having a remote API so far. Okay, let's focus on [1-3/6] at this moment. > -- > Michal Hocko > SUSE Labs
