Commit 4418c522 authored by Peter Xu's avatar Peter Xu Committed by Andrew Morton
Browse files

mm/gup: handle huge pmd for follow_pmd_mask() 

Replace pmd_trans_huge() with pmd_leaf() to also cover pmd_huge() as long
as enabled.

FOLL_TOUCH and FOLL_SPLIT_PMD only apply to THP, not yet huge.

Since now follow_trans_huge_pmd() can process hugetlb pages, renaming it
into follow_huge_pmd() to match what it does.  Move it into gup.c so not
depend on CONFIG_THP.

When at it, move the ctx->page_mask setup into follow_huge_pmd(), only set
it when the page is valid.  It was not a bug to set it before even if GUP
failed (page==NULL), because follow_page_mask() callers always ignores
page_mask if so.  But doing so makes the code cleaner.

[peterx@redhat.com: allow follow_pmd_mask() to take hugetlb tail pages]
  Link: https://lkml.kernel.org/r/20240403013249.1418299-3-peterx@redhat.com
Link: https://lkml.kernel.org/r/20240327152332.950956-12-peterx@redhat.com


Signed-off-by: default avatarPeter Xu <peterx@redhat.com>
Reviewed-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Tested-by: default avatarRyan Roberts <ryan.roberts@arm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Jones <andrew.jones@linux.dev>
Cc: Aneesh Kumar K.V (IBM) <aneesh.kumar@kernel.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: James Houghton <jthoughton@google.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Mike Rapoport (IBM)" <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Rik van Riel <riel@surriel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 1b167618

mm/gup.c

+98 −6
Original line number Diff line number Diff line
@@ -580,6 +580,90 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma, 


	return page;

}



/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */

static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,

					struct vm_area_struct *vma,

					unsigned int flags)

{

	/* If the pmd is writable, we can write to the page. */

	if (pmd_write(pmd))

		return true;



	/* Maybe FOLL_FORCE is set to override it? */

	if (!(flags & FOLL_FORCE))

		return false;



	/* But FOLL_FORCE has no effect on shared mappings */

	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))

		return false;



	/* ... or read-only private ones */

	if (!(vma->vm_flags & VM_MAYWRITE))

		return false;



	/* ... or already writable ones that just need to take a write fault */

	if (vma->vm_flags & VM_WRITE)

		return false;



	/*

	 * See can_change_pte_writable(): we broke COW and could map the page

	 * writable if we have an exclusive anonymous page ...

	 */

	if (!page || !PageAnon(page) || !PageAnonExclusive(page))

		return false;



	/* ... and a write-fault isn't required for other reasons. */

	if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd))

		return false;

	return !userfaultfd_huge_pmd_wp(vma, pmd);

}



static struct page *follow_huge_pmd(struct vm_area_struct *vma,

				    unsigned long addr, pmd_t *pmd,

				    unsigned int flags,

				    struct follow_page_context *ctx)

{

	struct mm_struct *mm = vma->vm_mm;

	pmd_t pmdval = *pmd;

	struct page *page;

	int ret;



	assert_spin_locked(pmd_lockptr(mm, pmd));



	page = pmd_page(pmdval);

	if ((flags & FOLL_WRITE) &&

	    !can_follow_write_pmd(pmdval, page, vma, flags))

		return NULL;



	/* Avoid dumping huge zero page */

	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval))

		return ERR_PTR(-EFAULT);



	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags))

		return NULL;



	if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page))

		return ERR_PTR(-EMLINK);



	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&

			!PageAnonExclusive(page), page);



	ret = try_grab_page(page, flags);

	if (ret)

		return ERR_PTR(ret);



#ifdef CONFIG_TRANSPARENT_HUGEPAGE

	if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH))

		touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);

#endif	/* CONFIG_TRANSPARENT_HUGEPAGE */



	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;

	ctx->page_mask = HPAGE_PMD_NR - 1;



	return page;

}



#else  /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */

static struct page *follow_huge_pud(struct vm_area_struct *vma,

				    unsigned long addr, pud_t *pudp,
@@ -587,6 +671,14 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma, 
{

	return NULL;

}



static struct page *follow_huge_pmd(struct vm_area_struct *vma,

				    unsigned long addr, pmd_t *pmd,

				    unsigned int flags,

				    struct follow_page_context *ctx)

{

	return NULL;

}

#endif	/* CONFIG_PGTABLE_HAS_HUGE_LEAVES */



static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
@@ -784,31 +876,31 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, 
			return page;

		return no_page_table(vma, flags, address);

	}

	if (likely(!pmd_trans_huge(pmdval)))

	if (likely(!pmd_leaf(pmdval)))

		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);



	if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags))

		return no_page_table(vma, flags, address);



	ptl = pmd_lock(mm, pmd);

	if (unlikely(!pmd_present(*pmd))) {

	pmdval = *pmd;

	if (unlikely(!pmd_present(pmdval))) {

		spin_unlock(ptl);

		return no_page_table(vma, flags, address);

	}

	if (unlikely(!pmd_trans_huge(*pmd))) {

	if (unlikely(!pmd_leaf(pmdval))) {

		spin_unlock(ptl);

		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);

	}

	if (flags & FOLL_SPLIT_PMD) {

	if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) {

		spin_unlock(ptl);

		split_huge_pmd(vma, pmd, address);

		/* If pmd was left empty, stuff a page table in there quickly */

		return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) :

			follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);

	}

	page = follow_trans_huge_pmd(vma, address, pmd, flags);

	page = follow_huge_pmd(vma, address, pmd, flags, ctx);

	spin_unlock(ptl);

	ctx->page_mask = HPAGE_PMD_NR - 1;

	return page;

}

mm/huge_memory.c

+2 −84
Original line number Diff line number Diff line
@@ -1221,7 +1221,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) 
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);

#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */



static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,

void touch_pmd(struct vm_area_struct *vma, unsigned long addr,

	       pmd_t *pmd, bool write)

{

	pmd_t _pmd;
@@ -1577,88 +1577,6 @@ static inline bool can_change_pmd_writable(struct vm_area_struct *vma, 
	return pmd_dirty(pmd);

}



/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */

static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,

					struct vm_area_struct *vma,

					unsigned int flags)

{

	/* If the pmd is writable, we can write to the page. */

	if (pmd_write(pmd))

		return true;



	/* Maybe FOLL_FORCE is set to override it? */

	if (!(flags & FOLL_FORCE))

		return false;



	/* But FOLL_FORCE has no effect on shared mappings */

	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))

		return false;



	/* ... or read-only private ones */

	if (!(vma->vm_flags & VM_MAYWRITE))

		return false;



	/* ... or already writable ones that just need to take a write fault */

	if (vma->vm_flags & VM_WRITE)

		return false;



	/*

	 * See can_change_pte_writable(): we broke COW and could map the page

	 * writable if we have an exclusive anonymous page ...

	 */

	if (!page || !PageAnon(page) || !PageAnonExclusive(page))

		return false;



	/* ... and a write-fault isn't required for other reasons. */

	if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd))

		return false;

	return !userfaultfd_huge_pmd_wp(vma, pmd);

}



struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,

				   unsigned long addr,

				   pmd_t *pmd,

				   unsigned int flags)

{

	struct mm_struct *mm = vma->vm_mm;

	struct page *page;

	int ret;



	assert_spin_locked(pmd_lockptr(mm, pmd));



	page = pmd_page(*pmd);

	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);



	if ((flags & FOLL_WRITE) &&

	    !can_follow_write_pmd(*pmd, page, vma, flags))

		return NULL;



	/* Avoid dumping huge zero page */

	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))

		return ERR_PTR(-EFAULT);



	if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags))

		return NULL;



	if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page))

		return ERR_PTR(-EMLINK);



	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&

			!PageAnonExclusive(page), page);



	ret = try_grab_page(page, flags);

	if (ret)

		return ERR_PTR(ret);



	if (flags & FOLL_TOUCH)

		touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);



	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;

	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);



	return page;

}



/* NUMA hinting page fault entry point for trans huge pmds */

vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)

{

mm/internal.h

+2 −3
Original line number Diff line number Diff line
@@ -1114,9 +1114,8 @@ int __must_check try_grab_page(struct page *page, unsigned int flags); 
 */

void touch_pud(struct vm_area_struct *vma, unsigned long addr,

	       pud_t *pud, bool write);

struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,

				   unsigned long addr, pmd_t *pmd,

				   unsigned int flags);

void touch_pmd(struct vm_area_struct *vma, unsigned long addr,

	       pmd_t *pmd, bool write);



/*

 * mm/mmap.c