summaryrefslogtreecommitdiff
path: root/mm/gup.c
diff options
context:
space:
mode:
authorAndrea Arcangeli <aarcange@redhat.com>2021-06-28 19:36:40 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-06-29 10:53:48 -0700
commita458b76a4171f893efa7657dc079924580a8746a (patch)
treedfeef6225048660a4659fa8a996998d70fd7b714 /mm/gup.c
parent292648ac5cf16ec1fce33e29e0f9e35da7de63f7 (diff)
mm: gup: pack has_pinned in MMF_HAS_PINNED
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. [peterx@redhat.com: pack has_pinned in MMF_HAS_PINNED] Link: https://lkml.kernel.org/r/YJqWESqyxa8OZA+2@t490s [akpm@linux-foundation.org: coding style fixes] [peterx@redhat.com: fix build for task_mmu.c, introduce mm_set_has_pinned_flag, fix comments] Link: https://lkml.kernel.org/r/20210507150553.208763-4-peterx@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Reviewed-by: John Hubbard <jhubbard@nvidia.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: Jann Horn <jannh@google.com> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Kirill Shutemov <kirill@shutemov.name> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/gup.c')
-rw-r--r--mm/gup.c19
1 files changed, 15 insertions, 4 deletions
diff --git a/mm/gup.c b/mm/gup.c
index a6c20a7b3c49..8651309f8ec3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -420,6 +420,17 @@ void unpin_user_pages(struct page **pages, unsigned long npages)
}
EXPORT_SYMBOL(unpin_user_pages);
+/*
+ * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's
+ * lifecycle. Avoid setting the bit unless necessary, or it might cause write
+ * cache bouncing on large SMP machines for concurrent pinned gups.
+ */
+static inline void mm_set_has_pinned_flag(unsigned long *mm_flags)
+{
+ if (!test_bit(MMF_HAS_PINNED, mm_flags))
+ set_bit(MMF_HAS_PINNED, mm_flags);
+}
+
#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
unsigned int flags)
@@ -1320,8 +1331,8 @@ 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)
+ mm_set_has_pinned_flag(&mm->flags);
/*
* FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
@@ -2641,8 +2652,8 @@ 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)
+ mm_set_has_pinned_flag(&current->mm->flags);
if (!(gup_flags & FOLL_FAST_ONLY))
might_lock_read(&current->mm->mmap_lock);