diff options
| author | David Hildenbrand <david@redhat.com> | 2023-12-21 01:44:29 +0300 |
|---|---|---|
| committer | Andrew Morton <akpm@linux-foundation.org> | 2023-12-29 22:58:48 +0300 |
| commit | 0c2ec32bf0b2f0d7ccb98c53ee5d255d68e73595 (patch) | |
| tree | 0c59e12d15cb796b80755874b694e29a2f735d5e /include/linux/rmap.h | |
| parent | ebe2e35ec0f256372c158a18de459fb60070b313 (diff) | |
| download | linux-0c2ec32bf0b2f0d7ccb98c53ee5d255d68e73595.tar.xz | |
mm/rmap: introduce and use hugetlb_try_share_anon_rmap()
hugetlb rmap handling differs quite a lot from "ordinary" rmap code. For
example, hugetlb currently only supports entire mappings, and treats any
mapping as mapped using a single "logical PTE". Let's move it out of the
way so we can overhaul our "ordinary" rmap. implementation/interface.
So let's introduce and use hugetlb_try_dup_anon_rmap() to make all hugetlb
handling use dedicated hugetlb_* rmap functions.
Add sanity checks that we end up with the right folios in the right
functions.
Note that try_to_unmap_one() does not need care. Easy to spot because
among all that nasty hugetlb special-casing in that function, we're not
using set_huge_pte_at() on the anon path -- well, and that code assumes
that we would want to swapout.
Link: https://lkml.kernel.org/r/20231220224504.646757-6-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'include/linux/rmap.h')
| -rw-r--r-- | include/linux/rmap.h | 25 |
1 files changed, 25 insertions, 0 deletions
diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 5f26752de945..d6fefa0f0410 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -227,6 +227,30 @@ static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, return 0; } +/* See page_try_share_anon_rmap() */ +static inline int hugetlb_try_share_anon_rmap(struct folio *folio) +{ + VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); + VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio); + + /* Paired with the memory barrier in try_grab_folio(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb(); + + if (unlikely(folio_maybe_dma_pinned(folio))) + return -EBUSY; + ClearPageAnonExclusive(&folio->page); + + /* + * This is conceptually a smp_wmb() paired with the smp_rmb() in + * gup_must_unshare(). + */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb__after_atomic(); + return 0; +} + static inline void hugetlb_add_file_rmap(struct folio *folio) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); @@ -331,6 +355,7 @@ dup: */ static inline int page_try_share_anon_rmap(struct page *page) { + VM_WARN_ON(folio_test_hugetlb(page_folio(page))); VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); /* device private pages cannot get pinned via GUP. */ |