From: Alistair Popple Date: Fri, 28 Feb 2025 03:31:11 +0000 (+1100) Subject: mm/huge_memory: add vmf_insert_folio_pmd() X-Git-Tag: v6.15-rc1~81^2~140 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=6c88f72691f88fd1fc493a3c2eed97f91b82b3f0;p=thirdparty%2Flinux.git mm/huge_memory: add vmf_insert_folio_pmd() Currently DAX folio/page reference counts are managed differently to normal pages. To allow these to be managed the same as normal pages introduce vmf_insert_folio_pmd. This will map the entire PMD-sized folio and take references as it would for a normally mapped page. This is distinct from the current mechanism, vmf_insert_pfn_pmd, which simply inserts a special devmap PMD entry into the page table without holding a reference to the page for the mapping. It is not currently useful to implement a more generic vmf_insert_folio() which selects the correct behaviour based on folio_order(). This is because PTE faults require only a subpage of the folio to be PTE mapped rather than the entire folio. It would be possible to add this context somewhere but callers already need to handle PTE faults and PMD faults separately so a more generic function is not useful. Link: https://lkml.kernel.org/r/7bf92a2e68225d13ea368d53bbfee327314d1c40.1740713401.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Acked-by: David Hildenbrand Tested-by: Alison Schofield Cc: Alexander Gordeev Cc: Asahi Lina Cc: Balbir Singh Cc: Bjorn Helgaas Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christoph Hellwig Cc: Chunyan Zhang Cc: Dan Wiliams Cc: "Darrick J. Wong" Cc: Dave Chinner Cc: Dave Hansen Cc: Dave Jiang Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Huacai Chen Cc: Ira Weiny Cc: Jan Kara Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: John Hubbard Cc: linmiaohe Cc: Logan Gunthorpe Cc: Matthew Wilcow (Oracle) Cc: Michael "Camp Drill Sergeant" Ellerman Cc: Nicholas Piggin Cc: Peter Xu Cc: Sven Schnelle Cc: Ted Ts'o Cc: Vasily Gorbik Cc: Vishal Verma Cc: Vivek Goyal Cc: WANG Xuerui Cc: Will Deacon Signed-off-by: Andrew Morton --- diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 4eeb54b506216..e57e811cfd3cc 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -39,6 +39,8 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); +vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, + bool write); vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio, bool write); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4cd79784f841e..e6f4189c1c947 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1375,20 +1375,20 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) return __do_huge_pmd_anonymous_page(vmf); } -static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, +static int insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write, pgtable_t pgtable) { struct mm_struct *mm = vma->vm_mm; pmd_t entry; - spinlock_t *ptl; - ptl = pmd_lock(mm, pmd); + lockdep_assert_held(pmd_lockptr(mm, pmd)); + if (!pmd_none(*pmd)) { if (write) { if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); - goto out_unlock; + return -EEXIST; } entry = pmd_mkyoung(*pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); @@ -1396,7 +1396,7 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, update_mmu_cache_pmd(vma, addr, pmd); } - goto out_unlock; + return -EEXIST; } entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); @@ -1412,16 +1412,11 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, if (pgtable) { pgtable_trans_huge_deposit(mm, pmd, pgtable); mm_inc_nr_ptes(mm); - pgtable = NULL; } set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); - -out_unlock: - spin_unlock(ptl); - if (pgtable) - pte_free(mm, pgtable); + return 0; } /** @@ -1440,6 +1435,8 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) struct vm_area_struct *vma = vmf->vma; pgprot_t pgprot = vma->vm_page_prot; pgtable_t pgtable = NULL; + spinlock_t *ptl; + int error; /* * If we had pmd_special, we could avoid all these restrictions, @@ -1462,12 +1459,56 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) } track_pfn_insert(vma, &pgprot, pfn); + ptl = pmd_lock(vma->vm_mm, vmf->pmd); + error = insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, + pgtable); + spin_unlock(ptl); + if (error && pgtable) + pte_free(vma->vm_mm, pgtable); - insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); +vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio, + bool write) +{ + struct vm_area_struct *vma = vmf->vma; + unsigned long addr = vmf->address & PMD_MASK; + struct mm_struct *mm = vma->vm_mm; + spinlock_t *ptl; + pgtable_t pgtable = NULL; + int error; + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + if (WARN_ON_ONCE(folio_order(folio) != PMD_ORDER)) + return VM_FAULT_SIGBUS; + + if (arch_needs_pgtable_deposit()) { + pgtable = pte_alloc_one(vma->vm_mm); + if (!pgtable) + return VM_FAULT_OOM; + } + + ptl = pmd_lock(mm, vmf->pmd); + if (pmd_none(*vmf->pmd)) { + folio_get(folio); + folio_add_file_rmap_pmd(folio, &folio->page, vma); + add_mm_counter(mm, mm_counter_file(folio), HPAGE_PMD_NR); + } + error = insert_pfn_pmd(vma, addr, vmf->pmd, + pfn_to_pfn_t(folio_pfn(folio)), vma->vm_page_prot, + write, pgtable); + spin_unlock(ptl); + if (error && pgtable) + pte_free(mm, pgtable); + + return VM_FAULT_NOPAGE; +} +EXPORT_SYMBOL_GPL(vmf_insert_folio_pmd); + #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) {