diff options
author | Peter Xu <peterx@redhat.com> | 2024-03-27 11:23:30 -0400 |
---|---|---|
committer | Andrew Morton <akpm@linux-foundation.org> | 2024-04-25 20:56:23 -0700 |
commit | 4418c522f683f2d73e9573847e98904c2b777654 (patch) | |
tree | 465be73473362d58fc8c605942997cf1c0991d87 /mm/gup.c | |
parent | 1b1676180246232308885c4f37fee01cf898fdb2 (diff) |
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: Peter Xu <peterx@redhat.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Ryan 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: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/gup.c')
-rw-r--r-- | mm/gup.c | 104 |
1 files changed, 98 insertions, 6 deletions
@@ -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; } |