diff options
Diffstat (limited to 'mm/memory.c')
-rw-r--r-- | mm/memory.c | 204 |
1 files changed, 130 insertions, 74 deletions
diff --git a/mm/memory.c b/mm/memory.c index 098f00d05461..15322b73636b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -63,6 +63,7 @@ #include <linux/dma-debug.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> +#include <linux/dax.h> #include <asm/io.h> #include <asm/mmu_context.h> @@ -789,6 +790,46 @@ out: return pfn_to_page(pfn); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + /* + * There is no pmd_special() but there may be special pmds, e.g. + * in a direct-access (dax) mapping, so let's just replicate the + * !HAVE_PTE_SPECIAL case from vm_normal_page() here. + */ + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + if (is_zero_pfn(pfn)) + return NULL; + if (unlikely(pfn > highest_memmap_pfn)) + return NULL; + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} +#endif + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range @@ -1182,15 +1223,8 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { -#ifdef CONFIG_DEBUG_VM - if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { - pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n", - __func__, addr, end, - vma->vm_start, - vma->vm_end); - BUG(); - } -#endif + VM_BUG_ON_VMA(vma_is_anonymous(vma) && + !rwsem_is_locked(&tlb->mm->mmap_sem), vma); split_huge_pmd(vma, pmd, addr); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; @@ -1711,6 +1745,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; + unsigned long remap_pfn = pfn; int err; /* @@ -1737,7 +1772,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, vma->vm_pgoff = pfn; } - err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); + err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; @@ -1756,7 +1791,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, } while (pgd++, addr = next, addr != end); if (err) - untrack_pfn(vma, pfn, PAGE_ALIGN(size)); + untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size)); return err; } @@ -2054,7 +2089,7 @@ static inline int wp_page_reuse(struct mm_struct *mm, VM_BUG_ON_PAGE(PageAnon(page), page); mapping = page->mapping; unlock_page(page); - page_cache_release(page); + put_page(page); if ((dirtied || page_mkwrite) && mapping) { /* @@ -2188,7 +2223,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, } if (new_page) - page_cache_release(new_page); + put_page(new_page); pte_unmap_unlock(page_table, ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); @@ -2203,14 +2238,14 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, munlock_vma_page(old_page); unlock_page(old_page); } - page_cache_release(old_page); + put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: - page_cache_release(new_page); + put_page(new_page); oom: if (old_page) - page_cache_release(old_page); + put_page(old_page); return VM_FAULT_OOM; } @@ -2258,7 +2293,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, { int page_mkwrite = 0; - page_cache_get(old_page); + get_page(old_page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; @@ -2267,7 +2302,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, tmp = do_page_mkwrite(vma, old_page, address); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { - page_cache_release(old_page); + put_page(old_page); return tmp; } /* @@ -2281,7 +2316,7 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); pte_unmap_unlock(page_table, ptl); - page_cache_release(old_page); + put_page(old_page); return 0; } page_mkwrite = 1; @@ -2340,8 +2375,9 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * not dirty accountable. */ if (PageAnon(old_page) && !PageKsm(old_page)) { + int total_mapcount; if (!trylock_page(old_page)) { - page_cache_get(old_page); + get_page(old_page); pte_unmap_unlock(page_table, ptl); lock_page(old_page); page_table = pte_offset_map_lock(mm, pmd, address, @@ -2349,18 +2385,23 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); pte_unmap_unlock(page_table, ptl); - page_cache_release(old_page); + put_page(old_page); return 0; } - page_cache_release(old_page); + put_page(old_page); } - if (reuse_swap_page(old_page)) { - /* - * The page is all ours. Move it to our anon_vma so - * the rmap code will not search our parent or siblings. - * Protected against the rmap code by the page lock. - */ - page_move_anon_rmap(old_page, vma, address); + if (reuse_swap_page(old_page, &total_mapcount)) { + if (total_mapcount == 1) { + /* + * The page is all ours. Move it to + * our anon_vma so the rmap code will + * not search our parent or siblings. + * Protected against the rmap code by + * the page lock. + */ + page_move_anon_rmap(compound_head(old_page), + vma, address); + } unlock_page(old_page); return wp_page_reuse(mm, vma, address, page_table, ptl, orig_pte, old_page, 0, 0); @@ -2375,7 +2416,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, /* * Ok, we need to copy. Oh, well.. */ - page_cache_get(old_page); + get_page(old_page); pte_unmap_unlock(page_table, ptl); return wp_page_copy(mm, vma, address, page_table, pmd, @@ -2400,7 +2441,6 @@ static inline void unmap_mapping_range_tree(struct rb_root *root, vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; - /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */ zba = details->first_index; if (zba < vba) zba = vba; @@ -2453,8 +2493,6 @@ void unmap_mapping_range(struct address_space *mapping, if (details.last_index < details.first_index) details.last_index = ULONG_MAX; - - /* DAX uses i_mmap_lock to serialise file truncate vs page fault */ i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); @@ -2585,7 +2623,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, inc_mm_counter_fast(mm, MM_ANONPAGES); dec_mm_counter_fast(mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); - if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { + if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; @@ -2619,7 +2657,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, * parallel locked swapcache. */ unlock_page(swapcache); - page_cache_release(swapcache); + put_page(swapcache); } if (flags & FAULT_FLAG_WRITE) { @@ -2641,10 +2679,10 @@ out_nomap: out_page: unlock_page(page); out_release: - page_cache_release(page); + put_page(page); if (page != swapcache) { unlock_page(swapcache); - page_cache_release(swapcache); + put_page(swapcache); } return ret; } @@ -2752,7 +2790,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (userfaultfd_missing(vma)) { pte_unmap_unlock(page_table, ptl); mem_cgroup_cancel_charge(page, memcg, false); - page_cache_release(page); + put_page(page); return handle_userfault(vma, address, flags, VM_UFFD_MISSING); } @@ -2771,10 +2809,10 @@ unlock: return 0; release: mem_cgroup_cancel_charge(page, memcg, false); - page_cache_release(page); + put_page(page); goto unlock; oom_free_page: - page_cache_release(page); + put_page(page); oom: return VM_FAULT_OOM; } @@ -2786,7 +2824,8 @@ oom: */ static int __do_fault(struct vm_area_struct *vma, unsigned long address, pgoff_t pgoff, unsigned int flags, - struct page *cow_page, struct page **page) + struct page *cow_page, struct page **page, + void **entry) { struct vm_fault vmf; int ret; @@ -2801,13 +2840,15 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, ret = vma->vm_ops->fault(vma, &vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; - if (!vmf.page) - goto out; + if (ret & VM_FAULT_DAX_LOCKED) { + *entry = vmf.entry; + return ret; + } if (unlikely(PageHWPoison(vmf.page))) { if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); - page_cache_release(vmf.page); + put_page(vmf.page); return VM_FAULT_HWPOISON; } @@ -2816,7 +2857,6 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, else VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page); - out: *page = vmf.page; return ret; } @@ -2837,7 +2877,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, * vm_ops->map_pages. */ void do_set_pte(struct vm_area_struct *vma, unsigned long address, - struct page *page, pte_t *pte, bool write, bool anon) + struct page *page, pte_t *pte, bool write, bool anon, bool old) { pte_t entry; @@ -2845,6 +2885,8 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, entry = mk_pte(page, vma->vm_page_prot); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (old) + entry = pte_mkold(entry); if (anon) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address, false); @@ -2858,8 +2900,16 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, update_mmu_cache(vma, address, pte); } +/* + * If architecture emulates "accessed" or "young" bit without HW support, + * there is no much gain with fault_around. + */ static unsigned long fault_around_bytes __read_mostly = +#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS + PAGE_SIZE; +#else rounddown_pow_of_two(65536); +#endif #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) @@ -2982,13 +3032,24 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { pte = pte_offset_map_lock(mm, pmd, address, &ptl); - do_fault_around(vma, address, pte, pgoff, flags); if (!pte_same(*pte, orig_pte)) goto unlock_out; + do_fault_around(vma, address, pte, pgoff, flags); + /* Check if the fault is handled by faultaround */ + if (!pte_same(*pte, orig_pte)) { + /* + * Faultaround produce old pte, but the pte we've + * handler fault for should be young. + */ + pte_t entry = pte_mkyoung(*pte); + if (ptep_set_access_flags(vma, address, pte, entry, 0)) + update_mmu_cache(vma, address, pte); + goto unlock_out; + } pte_unmap_unlock(pte, ptl); } - ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page, NULL); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; @@ -2996,10 +3057,10 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(!pte_same(*pte, orig_pte))) { pte_unmap_unlock(pte, ptl); unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); return ret; } - do_set_pte(vma, address, fault_page, pte, false, false); + do_set_pte(vma, address, fault_page, pte, false, false, false); unlock_page(fault_page); unlock_out: pte_unmap_unlock(pte, ptl); @@ -3011,6 +3072,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, pgoff_t pgoff, unsigned int flags, pte_t orig_pte) { struct page *fault_page, *new_page; + void *fault_entry; struct mem_cgroup *memcg; spinlock_t *ptl; pte_t *pte; @@ -3024,51 +3086,45 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_OOM; if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) { - page_cache_release(new_page); + put_page(new_page); return VM_FAULT_OOM; } - ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page, + &fault_entry); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; - if (fault_page) + if (!(ret & VM_FAULT_DAX_LOCKED)) copy_user_highpage(new_page, fault_page, address, vma); __SetPageUptodate(new_page); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (unlikely(!pte_same(*pte, orig_pte))) { pte_unmap_unlock(pte, ptl); - if (fault_page) { + if (!(ret & VM_FAULT_DAX_LOCKED)) { unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); } else { - /* - * The fault handler has no page to lock, so it holds - * i_mmap_lock for read to protect against truncate. - */ - i_mmap_unlock_read(vma->vm_file->f_mapping); + dax_unlock_mapping_entry(vma->vm_file->f_mapping, + pgoff); } goto uncharge_out; } - do_set_pte(vma, address, new_page, pte, true, true); + do_set_pte(vma, address, new_page, pte, true, true, false); mem_cgroup_commit_charge(new_page, memcg, false, false); lru_cache_add_active_or_unevictable(new_page, vma); pte_unmap_unlock(pte, ptl); - if (fault_page) { + if (!(ret & VM_FAULT_DAX_LOCKED)) { unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); } else { - /* - * The fault handler has no page to lock, so it holds - * i_mmap_lock for read to protect against truncate. - */ - i_mmap_unlock_read(vma->vm_file->f_mapping); + dax_unlock_mapping_entry(vma->vm_file->f_mapping, pgoff); } return ret; uncharge_out: mem_cgroup_cancel_charge(new_page, memcg, false); - page_cache_release(new_page); + put_page(new_page); return ret; } @@ -3083,7 +3139,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, int dirtied = 0; int ret, tmp; - ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page, NULL); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; @@ -3096,7 +3152,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, tmp = do_page_mkwrite(vma, fault_page, address); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { - page_cache_release(fault_page); + put_page(fault_page); return tmp; } } @@ -3105,10 +3161,10 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(!pte_same(*pte, orig_pte))) { pte_unmap_unlock(pte, ptl); unlock_page(fault_page); - page_cache_release(fault_page); + put_page(fault_page); return ret; } - do_set_pte(vma, address, fault_page, pte, true, false); + do_set_pte(vma, address, fault_page, pte, true, false, false); pte_unmap_unlock(pte, ptl); if (set_page_dirty(fault_page)) @@ -3736,7 +3792,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, buf, maddr + offset, bytes); } kunmap(page); - page_cache_release(page); + put_page(page); } len -= bytes; buf += bytes; |