Message ID | 20231204142146.91437-5-david@redhat.com (mailing list archive) |
---|---|
State | New |
Headers | show |
Series | mm/rmap: interface overhaul | expand |
On 12/4/23 22:21, David Hildenbrand wrote: > 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. > > Note that is_device_private_page() does not apply to hugetlb. > > Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Yin Fengwei <fengwei.yin@intel.com> > --- > include/linux/mm.h | 12 +++++++++--- > include/linux/rmap.h | 15 +++++++++++++++ > mm/hugetlb.c | 3 +-- > 3 files changed, 25 insertions(+), 5 deletions(-) > > diff --git a/include/linux/mm.h b/include/linux/mm.h > index 418d26608ece7..24c1c7c5a99c0 100644 > --- a/include/linux/mm.h > +++ b/include/linux/mm.h > @@ -1953,15 +1953,21 @@ static inline bool page_maybe_dma_pinned(struct page *page) > * > * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. > */ > -static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, > - struct page *page) > +static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, > + struct folio *folio) > { > VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); > > if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) > return false; > > - return page_maybe_dma_pinned(page); > + return folio_maybe_dma_pinned(folio); > +} > + > +static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, > + struct page *page) > +{ > + return folio_needs_cow_for_dma(vma, page_folio(page)); > } > > /** > diff --git a/include/linux/rmap.h b/include/linux/rmap.h > index 0a81e8420a961..8068c332e2ce5 100644 > --- a/include/linux/rmap.h > +++ b/include/linux/rmap.h > @@ -208,6 +208,21 @@ void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *, > void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *, > unsigned long address); > > +/* See page_try_dup_anon_rmap() */ > +static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, > + struct vm_area_struct *vma) > +{ > + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); > + > + if (PageAnonExclusive(&folio->page)) { > + if (unlikely(folio_needs_cow_for_dma(vma, folio))) > + return -EBUSY; > + ClearPageAnonExclusive(&folio->page); > + } > + atomic_inc(&folio->_entire_mapcount); > + return 0; > +} > + > static inline void hugetlb_add_file_rmap(struct folio *folio) > { > VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); > diff --git a/mm/hugetlb.c b/mm/hugetlb.c > index 541a8f38cfdc7..d927f8b2893c0 100644 > --- a/mm/hugetlb.c > +++ b/mm/hugetlb.c > @@ -5402,8 +5402,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, > */ > if (!folio_test_anon(pte_folio)) { > hugetlb_add_file_rmap(pte_folio); > - } else if (page_try_dup_anon_rmap(&pte_folio->page, > - true, src_vma)) { > + } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { > pte_t src_pte_old = entry; > struct folio *new_folio; >
diff --git a/include/linux/mm.h b/include/linux/mm.h index 418d26608ece7..24c1c7c5a99c0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1953,15 +1953,21 @@ static inline bool page_maybe_dma_pinned(struct page *page) * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ -static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, - struct page *page) +static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma, + struct folio *folio) { VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; - return page_maybe_dma_pinned(page); + return folio_maybe_dma_pinned(folio); +} + +static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, + struct page *page) +{ + return folio_needs_cow_for_dma(vma, page_folio(page)); } /** diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 0a81e8420a961..8068c332e2ce5 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -208,6 +208,21 @@ void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *, void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address); +/* See page_try_dup_anon_rmap() */ +static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, + struct vm_area_struct *vma) +{ + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); + + if (PageAnonExclusive(&folio->page)) { + if (unlikely(folio_needs_cow_for_dma(vma, folio))) + return -EBUSY; + ClearPageAnonExclusive(&folio->page); + } + atomic_inc(&folio->_entire_mapcount); + return 0; +} + static inline void hugetlb_add_file_rmap(struct folio *folio) { VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 541a8f38cfdc7..d927f8b2893c0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5402,8 +5402,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, */ if (!folio_test_anon(pte_folio)) { hugetlb_add_file_rmap(pte_folio); - } else if (page_try_dup_anon_rmap(&pte_folio->page, - true, src_vma)) { + } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { pte_t src_pte_old = entry; struct folio *new_folio;
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. Note that is_device_private_page() does not apply to hugetlb. Signed-off-by: David Hildenbrand <david@redhat.com> --- include/linux/mm.h | 12 +++++++++--- include/linux/rmap.h | 15 +++++++++++++++ mm/hugetlb.c | 3 +-- 3 files changed, 25 insertions(+), 5 deletions(-)