On Fri, Feb 28, 2020 at 02:14:56PM -0800, Suren Baghdasaryan wrote:

< snip >

> > > diff --git a/mm/madvise.c b/mm/madvise.c
> > > index f75c86b6c463..f29155b8185d 100644
> > > --- a/mm/madvise.c
> > > +++ b/mm/madvise.c
> > > @@ -17,6 +17,7 @@
> > >  #include <linux/falloc.h>
> > >  #include <linux/fadvise.h>
> > >  #include <linux/sched.h>
> > > +#include <linux/sched/mm.h>
> > >  #include <linux/ksm.h>
> > >  #include <linux/fs.h>
> > >  #include <linux/file.h>
> > > @@ -986,6 +987,18 @@ madvise_behavior_valid(int behavior)
> > >       }
> > >  }
> > >
> > > +static bool
> > > +process_madvise_behavior_valid(int behavior)
> > > +{
> > > +     switch (behavior) {
> > > +     case MADV_COLD:
> > > +     case MADV_PAGEOUT:
> > > +             return true;
> > > +     default:
> > > +             return false;
> > > +     }
> > > +}
> > > +
> > >  /*/
> > >   * The madvise(2) system call.
> > >   *
> > > @@ -1033,6 +1046,11 @@ madvise_behavior_valid(int behavior)
> > >   *  MADV_DONTDUMP - the application wants to prevent pages in the given range
> > >   *           from being included in its core dump.
> > >   *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
> > > + *  MADV_COLD - the application uses the memory less so the kernel can
> 
> "kernel can" implies that kernel might not deactivate the pages, which
> IIUC is not the case. Maybe rephrase as "MADV_COLD - the application
> is not expected to use this memory soon, deactivate pages in this
> range so that they can be reclaimed easily if memory pressure
> happens.""

That is much better.

> 
> > > + *           deactivate the memory to evict them quickly when the memory
> > > + *           pressure happen.
> > > + *  MADV_PAGEOUT - the application uses the memroy very rarely so kernel can
> 
> s/memroy/memory

Fixed.

> 
> > > + *           page out the memory instantly.
> 
> same nit about the usage of "kernel can". Maybe rephrase as
> "MADV_PAGEOUT - the application is not expected to use this memory
> soon, page out the pages in this range immediately.""

Yub.

> 
> > >   *
> > >   * return values:
> > >   *  zero    - success
> > > @@ -1150,3 +1168,49 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
> > >  {
> > >       return do_madvise(current, current->mm, start, len_in, behavior);
> > >  }
> > > +
> > > +SYSCALL_DEFINE5(process_madvise, int, pidfd, unsigned long, start,
> > > +             size_t, len_in, int, behavior, unsigned long, flags)
> > > +{
> > > +     int ret;
> > > +     struct fd f;
> > > +     struct pid *pid;
> > > +     struct task_struct *task;
> > > +     struct mm_struct *mm;
> > > +
> > > +     if (flags != 0)
> > > +             return -EINVAL;
> > > +
> > > +     if (!process_madvise_behavior_valid(behavior))
> > > +             return -EINVAL;
> > > +
> > > +     f = fdget(pidfd);
> > > +     if (!f.file)
> > > +             return -EBADF;
> > > +
> > > +     pid = pidfd_pid(f.file);
> > > +     if (IS_ERR(pid)) {
> > > +             ret = PTR_ERR(pid);
> > > +             goto fdput;
> > > +     }
> > > +
> > > +     task = get_pid_task(pid, PIDTYPE_PID);
> > > +     if (!task) {
> > > +             ret = -ESRCH;
> > > +             goto fdput;
> > > +     }
> > > +
> > > +     mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
> > > +     if (IS_ERR_OR_NULL(mm)) {
> > > +             ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
> > > +             goto release_task;
> > > +     }
> > > +
> > > +     ret = do_madvise(task, mm, start, len_in, behavior);
> > > +     mmput(mm);
> > > +release_task:
> > > +     put_task_struct(task);
> > > +fdput:
> > > +     fdput(f);
> > > +     return ret;
> > > +}
> > > --
> > > 2.25.0.265.gbab2e86ba0-goog
> > >
> >
> 
> Reviewed-by: Suren Baghdasaryan <surenb@google.com>

Thanks, Suren!