Re: [External] Re: [RFC] mm: add new syscall pidfd_set_mempolicy()

[Zhongkun He]

> On Mon, Oct 10, 2022 at 05:48:42PM +0800, Zhongkun He wrote:
> > There is usecase that System Management Software(SMS) want to give a
> > memory policy to other processes to make better use of memory.
>
> Better say "There are usecases when system management utilities
> want to apply memory policy to processes to make better use of memory".
>
> > The information about how to use memory is not known to the app.
> > Instead, it is known to the userspace daemon(SMS), and that daemon
> > will decide the memory usage policy based on different factors.
>
> Better say "These utilities doesn't set memory usage policy, but
> rather the job of reporting memory usage and setting the policy is
> offloaded to an userspace daemon."
>
> > To solve the issue, this patch introduces a new syscall
> > pidfd_set_mempolicy(2).  it sets the NUMA memory policy of the thread
> > specified in pidfd.
>
> Better say "To solve the issue above, introduce new syscall
> pidfd_set_mempolicy(2). The syscall sets NUMA memory policy for the
> thread specified in pidfd".
>
> > In current process context there is no locking because only the process
> > accesses its own memory policy, so task_work is used in
> > pidfd_set_mempolicy() to update the mempolicy of the process specified
> > in pidfd, avoid using locks and race conditions.
>
> Better say "In current process context there is no locking because
> only processes access their own memory policy. For this reason, task_work
> is used in pidfd_set_mempolicy() to set or update the mempolicy of process
> specified in pid. Thuse, it avoids into race conditions."
>
> > The API is as follows,
> >
> > 		long pidfd_set_mempolicy(int pidfd, int mode,
> >                                       const unsigned long __user *nmask,
> >                                       unsigned long maxnode,
> >                                       unsigned int flags);
> >
> > Set's the [pidfd] task's "task/process memory policy". The pidfd argument
> > is a PID file descriptor (see pidfd_open(2) man page) that specifies the
> > process to which the mempolicy is to be applied. The flags argument is
> > reserved for future use; currently, this argument must be specified as 0.
> > Please see the set_mempolicy(2) man page for more details about
> > other's arguments.
>
> Why duplicating from the Documentation/ below?
>
> > Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
> > Signed-off-by: Zhongkun He <hezhongkun.hzk@xxxxxxxxxxxxx>
> > ---
> >   .../admin-guide/mm/numa_memory_policy.rst     | 21 ++++-
> >   arch/alpha/kernel/syscalls/syscall.tbl        |  1 +
> >   arch/arm/tools/syscall.tbl                    |  1 +
> >   arch/arm64/include/asm/unistd.h               |  2 +-
> >   arch/arm64/include/asm/unistd32.h             |  3 +-
> >   arch/ia64/kernel/syscalls/syscall.tbl         |  1 +
> >   arch/m68k/kernel/syscalls/syscall.tbl         |  1 +
> >   arch/microblaze/kernel/syscalls/syscall.tbl   |  1 +
> >   arch/mips/kernel/syscalls/syscall_n32.tbl     |  1 +
> >   arch/mips/kernel/syscalls/syscall_n64.tbl     |  1 +
> >   arch/mips/kernel/syscalls/syscall_o32.tbl     |  1 +
> >   arch/parisc/kernel/syscalls/syscall.tbl       |  1 +
> >   arch/powerpc/kernel/syscalls/syscall.tbl      |  1 +
> >   arch/s390/kernel/syscalls/syscall.tbl         |  1 +
> >   arch/sh/kernel/syscalls/syscall.tbl           |  1 +
> >   arch/sparc/kernel/syscalls/syscall.tbl        |  1 +
> >   arch/x86/entry/syscalls/syscall_32.tbl        |  1 +
> >   arch/x86/entry/syscalls/syscall_64.tbl        |  1 +
> >   arch/xtensa/kernel/syscalls/syscall.tbl       |  1 +
> >   include/linux/mempolicy.h                     | 11 +++
> >   include/linux/syscalls.h                      |  4 +
> >   include/uapi/asm-generic/unistd.h             |  5 +-
> >   kernel/sys_ni.c                               |  1 +
> >   mm/mempolicy.c                                | 89 +++++++++++++++++++
> >   24 files changed, 146 insertions(+), 6 deletions(-)
> >
> > diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
> > index 5a6afecbb0d0..b864dd88b2d2 100644
> > --- a/Documentation/admin-guide/mm/numa_memory_policy.rst
> > +++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
> > @@ -408,9 +408,10 @@ follows:
> >   Memory Policy APIs
> >   ==================
> >   
> > -Linux supports 4 system calls for controlling memory policy.  These APIS
> > -always affect only the calling task, the calling task's address space, or
> > -some shared object mapped into the calling task's address space.
> > +Linux supports 5 system calls for controlling memory policy.  The first four
> > +APIS affect only the calling task, the calling task's address space, or some
> > +shared object mapped into the calling task's address space. The last one can
> > +set the mempolicy of task specified in pidfd.
> >   
> >   .. note::
> >      the headers that define these APIs and the parameter data types for
> > @@ -473,6 +474,20 @@ closest to which page allocation will come from. Specifying the home node overri
> >   the default allocation policy to allocate memory close to the local node for an
> >   executing CPU.
> >   
> > +Set [pidfd Task] Memory Policy::
> > +
> > +        long sys_pidfd_set_mempolicy(int pidfd, int mode,
> > +                                     const unsigned long __user *nmask,
> > +                                     unsigned long maxnode,
> > +                                     unsigned int flags);
> > +
> > +Set's the [pidfd] task's "task/process memory policy". The pidfd argument is
> > +a PID file descriptor (see pidfd_open(2) man page) that specifies the process
> > +to which the mempolicy is to be applied. The flags argument is reserved for
> > +future use; currently, this argument must be specified as 0. Please see the
> > +set_mempolicy(2) man page for more details about other's arguments.
> > +
> > +
> >   
> >   Memory Policy Command Line Interface
> >   ====================================
>
> The wording can be improved:
>
> ---- >8 ----
>
> diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
> index b864dd88b2d236..6df35bf4f960bd 100644
> --- a/Documentation/admin-guide/mm/numa_memory_policy.rst
> +++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
> @@ -410,8 +410,8 @@ Memory Policy APIs
>   
>   Linux supports 5 system calls for controlling memory policy.  The first four
>   APIS affect only the calling task, the calling task's address space, or some
> -shared object mapped into the calling task's address space. The last one can
> -set the mempolicy of task specified in pidfd.
> +shared object mapped into the calling task's address space. The last one
> +sets the mempolicy of task specified in the pidfd.
>   
>   .. note::
>      the headers that define these APIs and the parameter data types for
> @@ -481,11 +481,11 @@ Set [pidfd Task] Memory Policy::
>                                        unsigned long maxnode,
>                                        unsigned int flags);
>   
> -Set's the [pidfd] task's "task/process memory policy". The pidfd argument is
> -a PID file descriptor (see pidfd_open(2) man page) that specifies the process
> -to which the mempolicy is to be applied. The flags argument is reserved for
> -future use; currently, this argument must be specified as 0. Please see the
> -set_mempolicy(2) man page for more details about other's arguments.
> +Sets the task/process memory policy for the [pidfd] task. The pidfd argument
> +is a PID file descriptor (see pidfd_open(2) man page for details) that
> +specifies the process for which the mempolicy is applied to. The flags
> +argument is reserved for future use; currently, it must be specified as 0.
> +For the description of all other arguments, see set_mempolicy(2) man page.
>   
>   
>   
>
> Thanks.

Hi Bagas

I got it, thanks for your suggestions.