int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, get_block_t get_block, dax_iodone_t complete_unwritten) { struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct buffer_head bh; unsigned blkbits = inode->i_blkbits; unsigned long pmd_addr = address & PMD_MASK; bool write = flags & FAULT_FLAG_WRITE; struct block_device *bdev; pgoff_t size, pgoff; sector_t block; int error, result = 0; bool alloc = false; /* dax pmd mappings require pfn_t_devmap() */ if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) return VM_FAULT_FALLBACK; /* Fall back to PTEs if we're going to COW */ if (write && !(vma->vm_flags & VM_SHARED)) { split_huge_pmd(vma, pmd, address); dax_pmd_dbg(NULL, address, "cow write"); return VM_FAULT_FALLBACK; } /* If the PMD would extend outside the VMA */ if (pmd_addr < vma->vm_start) { dax_pmd_dbg(NULL, address, "vma start unaligned"); return VM_FAULT_FALLBACK; } if ((pmd_addr + PMD_SIZE) > vma->vm_end) { dax_pmd_dbg(NULL, address, "vma end unaligned"); return VM_FAULT_FALLBACK; } pgoff = linear_page_index(vma, pmd_addr); size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (pgoff >= size) return VM_FAULT_SIGBUS; /* If the PMD would cover blocks out of the file */ if ((pgoff | PG_PMD_COLOUR) >= size) { dax_pmd_dbg(NULL, address, "offset + huge page size > file size"); return VM_FAULT_FALLBACK; } memset(&bh, 0, sizeof(bh)); bh.b_bdev = inode->i_sb->s_bdev; block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; if (get_block(inode, block, &bh, 0) != 0) return VM_FAULT_SIGBUS; if (!buffer_mapped(&bh) && write) { if (get_block(inode, block, &bh, 1) != 0) return VM_FAULT_SIGBUS; alloc = true; } bdev = bh.b_bdev; /* * If the filesystem isn't willing to tell us the length of a hole, * just fall back to PTEs. Calling get_block 512 times in a loop * would be silly. */ if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) { dax_pmd_dbg(&bh, address, "allocated block too small"); return VM_FAULT_FALLBACK; } /* * If we allocated new storage, make sure no process has any * zero pages covering this hole */ if (alloc) { loff_t lstart = pgoff << PAGE_SHIFT; loff_t lend = lstart + PMD_SIZE - 1; /* inclusive */ truncate_pagecache_range(inode, lstart, lend); } i_mmap_lock_read(mapping); /* * If a truncate happened while we were allocating blocks, we may * leave blocks allocated to the file that are beyond EOF. We can't * take i_mutex here, so just leave them hanging; they'll be freed * when the file is deleted. */ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (pgoff >= size) { result = VM_FAULT_SIGBUS; goto out; } if ((pgoff | PG_PMD_COLOUR) >= size) { dax_pmd_dbg(&bh, address, "offset + huge page size > file size"); goto fallback; } if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) { spinlock_t *ptl; pmd_t entry; struct page *zero_page = get_huge_zero_page(); if (unlikely(!zero_page)) { dax_pmd_dbg(&bh, address, "no zero page"); goto fallback; } ptl = pmd_lock(vma->vm_mm, pmd); if (!pmd_none(*pmd)) { spin_unlock(ptl); dax_pmd_dbg(&bh, address, "pmd already present"); goto fallback; } dev_dbg(part_to_dev(bdev->bd_part), "%s: %s addr: %lx pfn: <zero> sect: %llx\n", __func__, current->comm, address, (unsigned long long) to_sector(&bh, inode)); entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry); result = VM_FAULT_NOPAGE; spin_unlock(ptl); } else { struct blk_dax_ctl dax = { .sector = to_sector(&bh, inode), .size = PMD_SIZE, }; long length = dax_map_atomic(bdev, &dax); if (length < 0) { result = VM_FAULT_SIGBUS; goto out; } if (length < PMD_SIZE) { dax_pmd_dbg(&bh, address, "dax-length too small"); dax_unmap_atomic(bdev, &dax); goto fallback; } if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) { dax_pmd_dbg(&bh, address, "pfn unaligned"); dax_unmap_atomic(bdev, &dax); goto fallback; } if (!pfn_t_devmap(dax.pfn)) { dax_unmap_atomic(bdev, &dax); dax_pmd_dbg(&bh, address, "pfn not in memmap"); goto fallback; } if (buffer_unwritten(&bh) || buffer_new(&bh)) { clear_pmem(dax.addr, PMD_SIZE); wmb_pmem(); count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); result |= VM_FAULT_MAJOR; } dax_unmap_atomic(bdev, &dax); /* * For PTE faults we insert a radix tree entry for reads, and * leave it clean. Then on the first write we dirty the radix * tree entry via the dax_pfn_mkwrite() path. This sequence * allows the dax_pfn_mkwrite() call to be simpler and avoid a * call into get_block() to translate the pgoff to a sector in * order to be able to create a new radix tree entry. * * The PMD path doesn't have an equivalent to * dax_pfn_mkwrite(), though, so for a read followed by a * write we traverse all the way through __dax_pmd_fault() * twice. This means we can just skip inserting a radix tree * entry completely on the initial read and just wait until * the write to insert a dirty entry. */ if (write) { error = dax_radix_entry(mapping, pgoff, dax.sector, true, true); if (error) { dax_pmd_dbg(&bh, address, "PMD radix insertion failed"); goto fallback; } } dev_dbg(part_to_dev(bdev->bd_part), "%s: %s addr: %lx pfn: %lx sect: %llx\n", __func__, current->comm, address, pfn_t_to_pfn(dax.pfn), (unsigned long long) dax.sector); result |= vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write); } out: i_mmap_unlock_read(mapping); if (buffer_unwritten(&bh)) complete_unwritten(&bh, !(result & VM_FAULT_ERROR)); return result; fallback: count_vm_event(THP_FAULT_FALLBACK); result = VM_FAULT_FALLBACK; goto out; } EXPORT_SYMBOL_GPL(__dax_pmd_fault); /** * dax_pmd_fault - handle a PMD fault on a DAX file * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault * @get_block: The filesystem method used to translate file offsets to blocks * * When a page fault occurs, filesystems may call this helper in their * pmd_fault handler for DAX files. */ int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, get_block_t get_block, dax_iodone_t complete_unwritten) { int result; struct super_block *sb = file_inode(vma->vm_file)->i_sb; if (flags & FAULT_FLAG_WRITE) { sb_start_pagefault(sb); file_update_time(vma->vm_file); } result = __dax_pmd_fault(vma, address, pmd, flags, get_block, complete_unwritten); if (flags & FAULT_FLAG_WRITE) sb_end_pagefault(sb); return result; }
/** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @page_mask: on output, *page_mask is set according to the size of the page * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * Returns the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned int *page_mask) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; *page_mask = 0; page = follow_huge_addr(mm, address, flags & FOLL_WRITE); if (!IS_ERR(page)) { BUG_ON(flags & FOLL_GET); return page; } pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) return no_page_table(vma, flags); p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return no_page_table(vma, flags); BUILD_BUG_ON(p4d_huge(*p4d)); if (unlikely(p4d_bad(*p4d))) return no_page_table(vma, flags); pud = pud_offset(p4d, address); if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { page = follow_huge_pud(mm, address, pud, flags); if (page) return page; return no_page_table(vma, flags); } if (pud_devmap(*pud)) { ptl = pud_lock(mm, pud); page = follow_devmap_pud(vma, address, pud, flags); spin_unlock(ptl); if (page) return page; } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) return no_page_table(vma, flags); if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { page = follow_huge_pmd(mm, address, pmd, flags); if (page) return page; return no_page_table(vma, flags); } if (pmd_devmap(*pmd)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags); spin_unlock(ptl); if (page) return page; } if (likely(!pmd_trans_huge(*pmd))) return follow_page_pte(vma, address, pmd, flags); if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) return no_page_table(vma, flags); ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags); } if (flags & FOLL_SPLIT) { int ret; page = pmd_page(*pmd); if (is_huge_zero_page(page)) { spin_unlock(ptl); ret = 0; split_huge_pmd(vma, pmd, address); if (pmd_trans_unstable(pmd)) ret = -EBUSY; } else { get_page(page); spin_unlock(ptl); lock_page(page); ret = split_huge_page(page); unlock_page(page); put_page(page); if (pmd_none(*pmd)) return no_page_table(vma, flags); } return ret ? ERR_PTR(ret) : follow_page_pte(vma, address, pmd, flags); } page = follow_trans_huge_pmd(vma, address, pmd, flags); spin_unlock(ptl); *page_mask = HPAGE_PMD_NR - 1; return page; }
/** * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at * @pvmw->address * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags * must be set. pmd, pte and ptl must be NULL. * * Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point * to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is * adjusted if needed (for PTE-mapped THPs). * * If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page * (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in * a loop to find all PTEs that map the THP. * * For HugeTLB pages, @pvmw->pte is set to the relevant page table entry * regardless of which page table level the page is mapped at. @pvmw->pmd is * NULL. * * Retruns false if there are no more page table entries for the page in * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped. * * If you need to stop the walk before page_vma_mapped_walk() returned false, * use page_vma_mapped_walk_done(). It will do the housekeeping. */ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t pmde; /* The only possible pmd mapping has been handled on last iteration */ if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); if (pvmw->pte) goto next_pte; if (unlikely(PageHuge(pvmw->page))) { /* when pud is not present, pte will be NULL */ pvmw->pte = huge_pte_offset(mm, pvmw->address, PAGE_SIZE << compound_order(page)); if (!pvmw->pte) return false; pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte); spin_lock(pvmw->ptl); if (!check_pte(pvmw)) return not_found(pvmw); return true; } restart: pgd = pgd_offset(mm, pvmw->address); if (!pgd_present(*pgd)) return false; p4d = p4d_offset(pgd, pvmw->address); if (!p4d_present(*p4d)) return false; pud = pud_offset(p4d, pvmw->address); if (!pud_present(*pud)) return false; pvmw->pmd = pmd_offset(pud, pvmw->address); /* * Make sure the pmd value isn't cached in a register by the * compiler and used as a stale value after we've observed a * subsequent update. */ pmde = READ_ONCE(*pvmw->pmd); if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); if (likely(pmd_trans_huge(*pvmw->pmd))) { if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); if (pmd_page(*pvmw->pmd) != page) return not_found(pvmw); return true; } else if (!pmd_present(*pvmw->pmd)) { if (thp_migration_supported()) { if (!(pvmw->flags & PVMW_MIGRATION)) return not_found(pvmw); if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) { swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd); if (migration_entry_to_page(entry) != page) return not_found(pvmw); return true; } } return not_found(pvmw); } else { /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } } else if (!pmd_present(pmde)) { return false; } if (!map_pte(pvmw)) goto next_pte; while (1) { if (check_pte(pvmw)) return true; next_pte: /* Seek to next pte only makes sense for THP */ if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) return not_found(pvmw); do { pvmw->address += PAGE_SIZE; if (pvmw->address >= pvmw->vma->vm_end || pvmw->address >= __vma_address(pvmw->page, pvmw->vma) + hpage_nr_pages(pvmw->page) * PAGE_SIZE) return not_found(pvmw); /* Did we cross page table boundary? */ if (pvmw->address % PMD_SIZE == 0) { pte_unmap(pvmw->pte); if (pvmw->ptl) { spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } goto restart; } else { pvmw->pte++; } } while (pte_none(*pvmw->pte)); if (!pvmw->ptl) { pvmw->ptl = pte_lockptr(mm, pvmw->pmd); spin_lock(pvmw->ptl); } } }
/** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @page_mask: on output, *page_mask is set according to the size of the page * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * Returns the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned int *page_mask) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; *page_mask = 0; page = follow_huge_addr(mm, address, flags & FOLL_WRITE); if (!IS_ERR(page)) { BUG_ON(flags & FOLL_GET); return page; } pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) return no_page_table(vma, flags); pud = pud_offset(pgd, address); if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { if (flags & FOLL_GET) return NULL; page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); return page; } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) return no_page_table(vma, flags); if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); if (flags & FOLL_GET) { /* * Refcount on tail pages are not well-defined and * shouldn't be taken. The caller should handle a NULL * return when trying to follow tail pages. */ if (PageHead(page)) get_page(page); else page = NULL; } return page; } if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) return no_page_table(vma, flags); if (pmd_trans_huge(*pmd)) { if (flags & FOLL_SPLIT) { split_huge_page_pmd(vma, address, pmd); return follow_page_pte(vma, address, pmd, flags); } ptl = pmd_lock(mm, pmd); if (likely(pmd_trans_huge(*pmd))) { if (unlikely(pmd_trans_splitting(*pmd))) { spin_unlock(ptl); wait_split_huge_page(vma->anon_vma, pmd); } else { page = follow_trans_huge_pmd(vma, address, pmd, flags); spin_unlock(ptl); *page_mask = HPAGE_PMD_NR - 1; return page; } } else spin_unlock(ptl); } return follow_page_pte(vma, address, pmd, flags); }
/** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @page_mask: on output, *page_mask is set according to the size of the page * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * Returns the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned int *page_mask) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; *page_mask = 0; page = follow_huge_addr(mm, address, flags & FOLL_WRITE); if (!IS_ERR(page)) { BUG_ON(flags & FOLL_GET); return page; } pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) return no_page_table(vma, flags); pud = pud_offset(pgd, address); if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { page = follow_huge_pud(mm, address, pud, flags); if (page) return page; return no_page_table(vma, flags); } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); pmd = pmd_offset(pud, address); if (pmd_none(*pmd)) return no_page_table(vma, flags); if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { page = follow_huge_pmd(mm, address, pmd, flags); if (page) return page; return no_page_table(vma, flags); } if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) return no_page_table(vma, flags); if (pmd_trans_huge(*pmd)) { if (flags & FOLL_SPLIT) { split_huge_page_pmd(vma, address, pmd); return follow_page_pte(vma, address, pmd, flags); } ptl = pmd_lock(mm, pmd); if (likely(pmd_trans_huge(*pmd))) { if (unlikely(pmd_trans_splitting(*pmd))) { spin_unlock(ptl); wait_split_huge_page(vma->anon_vma, pmd); } else { page = follow_trans_huge_pmd(vma, address, pmd, flags); spin_unlock(ptl); *page_mask = HPAGE_PMD_NR - 1; return page; } } else spin_unlock(ptl); } return follow_page_pte(vma, address, pmd, flags); }