Re: [PATCH 3/3] mm: gup: pack has_pinned in MMF_HAS_PINNED

[John Hubbard <jhubbard@nvidia.com>]

On 5/6/21 4:25 PM, Peter Xu wrote:
> From: Andrea Arcangeli <aarcange@redhat.com>
> 
> has_pinned 32bit can be packed in the MMF_HAS_PINNED bit as a noop
> cleanup.
> 
> Any atomic_inc/dec to the mm cacheline shared by all threads in
> pin-fast would reintroduce a loss of SMP scalability to pin-fast, so
> there's no future potential usefulness to keep an atomic in the mm for
> this.
> 
> set_bit(MMF_HAS_PINNED) will be theoretically a bit slower than
> WRITE_ONCE (atomic_set is equivalent to WRITE_ONCE), but the set_bit
> (just like atomic_set after this commit) has to be still issued only
> once per "mm", so the difference between the two will be lost in the
> noise.
> 
> will-it-scale "mmap2" shows no change in performance with enterprise
> config as expected.
> 
> will-it-scale "pin_fast" retains the > 4000% SMP scalability
> performance improvement against upstream as expected.
> 
> This is a noop as far as overall performance and SMP scalability are
> concerned.

It's nice that you spelled that out. I don't see any technical problems
with the diffs. There are a couple of tiny suggestions, below.

> 
> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
> [peterx: Fix build for task_mmu.c]
> Signed-off-by: Peter Xu <peterx@redhat.com>
> ---
>   fs/proc/task_mmu.c             |  2 +-
>   include/linux/mm.h             |  2 +-
>   include/linux/mm_types.h       | 10 ----------
>   include/linux/sched/coredump.h |  1 +
>   kernel/fork.c                  |  1 -
>   mm/gup.c                       |  9 +++++----
>   6 files changed, 8 insertions(+), 17 deletions(-)
> 
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 4c95cc57a66a8..6144571942db9 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -1049,7 +1049,7 @@ static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr,
>   		return false;
>   	if (!is_cow_mapping(vma->vm_flags))
>   		return false;
> -	if (likely(!atomic_read(&vma->vm_mm->has_pinned)))
> +	if (likely(!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)))
>   		return false;
>   	page = vm_normal_page(vma, addr, pte);
>   	if (!page)
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index d6790ab0cf575..94dc84f6d8658 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1331,7 +1331,7 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
>   	if (!is_cow_mapping(vma->vm_flags))
>   		return false;
>   
> -	if (!atomic_read(&vma->vm_mm->has_pinned))
> +	if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
>   		return false;
>   
>   	return page_maybe_dma_pinned(page);
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 6613b26a88946..15d79858fadbd 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -435,16 +435,6 @@ struct mm_struct {
>   		 */
>   		atomic_t mm_count;
>   
> -		/**
> -		 * @has_pinned: Whether this mm has pinned any pages.  This can
> -		 * be either replaced in the future by @pinned_vm when it
> -		 * becomes stable, or grow into a counter on its own. We're
> -		 * aggresive on this bit now - even if the pinned pages were
> -		 * unpinned later on, we'll still keep this bit set for the
> -		 * lifecycle of this mm just for simplicity.
> -		 */
> -		atomic_t has_pinned;
> -
>   		/**
>   		 * @write_protect_seq: Locked when any thread is write
>   		 * protecting pages mapped by this mm to enforce a later COW,
> diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
> index dfd82eab29025..bf45badd63e6d 100644
> --- a/include/linux/sched/coredump.h
> +++ b/include/linux/sched/coredump.h
> @@ -73,6 +73,7 @@ static inline int get_dumpable(struct mm_struct *mm)
>   #define MMF_OOM_VICTIM		25	/* mm is the oom victim */
>   #define MMF_OOM_REAP_QUEUED	26	/* mm was queued for oom_reaper */
>   #define MMF_MULTIPROCESS	27	/* mm is shared between processes */
> +#define MMF_HAS_PINNED		28	/* FOLL_PIN has run, never cleared */

How about this instead, so that we effectively retain the comment block
that is otherwise being deleted from mm.h:

/*
  * MMF_HAS_PINNED: Whether this mm has pinned any pages.  This can be either
  * replaced in the future by mm.pinned_vm when it becomes stable, or grow into a
  * counter on its own. We're aggresive on this bit for now: even if the pinned
  * pages were unpinned later on, we'll still keep this bit set for the lifecycle
  * of this mm, just for simplicity.
  */
#define MMF_HAS_PINNED		28	/* FOLL_PIN ran. Never cleared. */


>   #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
>   
>   #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
> diff --git a/kernel/fork.c b/kernel/fork.c
> index 502dc046fbc62..a71e73707ef59 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -1026,7 +1026,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
>   	mm_pgtables_bytes_init(mm);
>   	mm->map_count = 0;
>   	mm->locked_vm = 0;
> -	atomic_set(&mm->has_pinned, 0);
>   	atomic64_set(&mm->pinned_vm, 0);
>   	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
>   	spin_lock_init(&mm->page_table_lock);
> diff --git a/mm/gup.c b/mm/gup.c
> index 8b513e1723b45..78416b0909873 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -1292,8 +1292,8 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
>   		BUG_ON(*locked != 1);
>   	}
>   
> -	if (flags & FOLL_PIN && !atomic_read(&mm->has_pinned))
> -		atomic_set(&mm->has_pinned, 1);
> +	if (flags & FOLL_PIN && !test_bit(MMF_HAS_PINNED, &mm->flags))
> +		set_bit(MMF_HAS_PINNED, &mm->flags);

I expect this suggestion to be controversial, but I'm going to float it
anyway. The above is a little less clear than it used to be, *and* it is
in two places so far, so how about factoring out a tiny subroutine, like this:

diff --git a/mm/gup.c b/mm/gup.c
index 036ab0de9457..2dc001a7c850 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1270,6 +1270,16 @@ int fixup_user_fault(struct mm_struct *mm,
}
EXPORT_SYMBOL_GPL(fixup_user_fault);

+static void set_mm_has_pinned_flag(unsigned long *mm_flags)
+{
+       /*
+        * Avoid setting the bit unless necessary. This matters a lot with
+        * large SMP machines.
+        */
+       if (!test_bit(MMF_HAS_PINNED, mm_flags))
+               set_bit(MMF_HAS_PINNED, mm_flags);
+}
+
/*
* Please note that this function, unlike __get_user_pages will not
* return 0 for nr_pages > 0 without FOLL_NOWAIT
@@ -1292,8 +1302,8 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
BUG_ON(*locked != 1);
}

-       if (flags & FOLL_PIN && !test_bit(MMF_HAS_PINNED, &mm->flags))
-               set_bit(MMF_HAS_PINNED, &mm->flags);
+       if (flags & FOLL_PIN)
+               set_mm_has_pinned_flag(&mm->flags);

...which is now very readable, once again.

>   
>   	/*
>   	 * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
> @@ -2617,8 +2617,9 @@ static int internal_get_user_pages_fast(unsigned long start,
>   				       FOLL_FAST_ONLY)))
>   		return -EINVAL;
>   
> -	if (gup_flags & FOLL_PIN && !atomic_read(&current->mm->has_pinned))
> -		atomic_set(&current->mm->has_pinned, 1);
> +	if (gup_flags & FOLL_PIN &&
> +	    !test_bit(MMF_HAS_PINNED, &current->mm->flags))
> +		set_bit(MMF_HAS_PINNED, &current->mm->flags);
>   
>   	if (!(gup_flags & FOLL_FAST_ONLY))
>   		might_lock_read(&current->mm->mmap_lock);
> 

thanks,
-- 
John Hubbard
NVIDIA