X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Ffremap.c;h=414b5bcd0e442298953e0c6371602a159e66d8c8;hb=34a75f0025b9cf803b6a88db032e6ad6950c9313;hp=2c8abe6d1f5a383c5ebb6b8ecea19eded27cd5cc;hpb=5273a3df6485dc2ad6aa7ddd441b9a21970f003b;p=linux-2.6.git diff --git a/mm/fremap.c b/mm/fremap.c index 2c8abe6d1..414b5bcd0 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -14,90 +14,88 @@ #include #include #include +#include +#include #include #include #include -static inline void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, +static int zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; + struct page *page = NULL; - if (pte_none(pte)) - return; if (pte_present(pte)) { - unsigned long pfn = pte_pfn(pte); - - flush_cache_page(vma, addr); + flush_cache_page(vma, addr, pte_pfn(pte)); pte = ptep_clear_flush(vma, addr, ptep); - if (pfn_valid(pfn)) { - struct page *page = pfn_to_page(pfn); - if (!PageReserved(page)) { - if (pte_dirty(pte)) - set_page_dirty(page); - page_remove_rmap(page, ptep); - page_cache_release(page); - mm->rss--; - } + page = vm_normal_page(vma, addr, pte); + if (page) { + if (pte_dirty(pte)) + set_page_dirty(page); + page_remove_rmap(page); + page_cache_release(page); } } else { if (!pte_file(pte)) free_swap_and_cache(pte_to_swp_entry(pte)); - pte_clear(ptep); + pte_clear(mm, addr, ptep); } + return !!page; } /* - * Install a page to a given virtual memory address, release any + * Install a file page to a given virtual memory address, release any * previously existing mapping. */ int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { + struct inode *inode; + pgoff_t size; int err = -ENOMEM; pte_t *pte; - pgd_t *pgd; - pmd_t *pmd; pte_t pte_val; - struct pte_chain *pte_chain; - - pte_chain = pte_chain_alloc(GFP_KERNEL); - if (!pte_chain) - goto err; - pgd = pgd_offset(mm, addr); - spin_lock(&mm->page_table_lock); + spinlock_t *ptl; - pmd = pmd_alloc(mm, pgd, addr); - if (!pmd) - goto err_unlock; - - pte = pte_alloc_map(mm, pmd, addr); + pte = get_locked_pte(mm, addr, &ptl); if (!pte) - goto err_unlock; + goto out; + + /* + * This page may have been truncated. Tell the + * caller about it. + */ + err = -EINVAL; + if (vma->vm_file) { + inode = vma->vm_file->f_mapping->host; + size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + if (!page->mapping || page->index >= size) + goto unlock; + err = -ENOMEM; + if (page_mapcount(page) > INT_MAX/2) + goto unlock; + if (!vx_rsspages_avail(mm, 1)) + goto unlock; + } - zap_pte(mm, vma, addr, pte); + if (pte_none(*pte) || !zap_pte(mm, vma, addr, pte)) + inc_mm_counter(mm, file_rss); - mm->rss++; flush_icache_page(vma, page); - set_pte(pte, mk_pte(page, prot)); - pte_chain = page_add_rmap(page, pte, pte_chain); + set_pte_at(mm, addr, pte, mk_pte(page, prot)); + page_add_file_rmap(page); pte_val = *pte; - pte_unmap(pte); update_mmu_cache(vma, addr, pte_val); - spin_unlock(&mm->page_table_lock); - pte_chain_free(pte_chain); - return 0; - -err_unlock: - spin_unlock(&mm->page_table_lock); - pte_chain_free(pte_chain); -err: + err = 0; +unlock: + pte_unmap_unlock(pte, ptl); +out: return err; } EXPORT_SYMBOL(install_page); - /* * Install a file pte to a given virtual memory address, release any * previously existing mapping. @@ -107,36 +105,27 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, { int err = -ENOMEM; pte_t *pte; - pgd_t *pgd; - pmd_t *pmd; pte_t pte_val; + spinlock_t *ptl; - pgd = pgd_offset(mm, addr); - spin_lock(&mm->page_table_lock); - - pmd = pmd_alloc(mm, pgd, addr); - if (!pmd) - goto err_unlock; - - pte = pte_alloc_map(mm, pmd, addr); + pte = get_locked_pte(mm, addr, &ptl); if (!pte) - goto err_unlock; + goto out; - zap_pte(mm, vma, addr, pte); + if (!pte_none(*pte) && zap_pte(mm, vma, addr, pte)) { + update_hiwater_rss(mm); + dec_mm_counter(mm, file_rss); + } - set_pte(pte, pgoff_to_pte(pgoff)); + set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff)); pte_val = *pte; - pte_unmap(pte); update_mmu_cache(vma, addr, pte_val); - spin_unlock(&mm->page_table_lock); - return 0; - -err_unlock: - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(pte, ptl); + err = 0; +out: return err; } - /*** * sys_remap_file_pages - remap arbitrary pages of a shared backing store * file within an existing vma. @@ -159,9 +148,11 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long __prot, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; + struct address_space *mapping; unsigned long end = start + size; struct vm_area_struct *vma; int err = -EINVAL; + int has_write_lock = 0; if (__prot) return err; @@ -182,25 +173,41 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, #endif /* We need down_write() to change vma->vm_flags. */ - down_write(&mm->mmap_sem); + down_read(&mm->mmap_sem); + retry: vma = find_vma(mm, start); /* * Make sure the vma is shared, that it supports prefaulting, * and that the remapped range is valid and fully within - * the single existing vma: + * the single existing vma. vm_private_data is used as a + * swapout cursor in a VM_NONLINEAR vma. */ if (vma && (vma->vm_flags & VM_SHARED) && + (!vma->vm_private_data || (vma->vm_flags & VM_NONLINEAR)) && vma->vm_ops && vma->vm_ops->populate && end > start && start >= vma->vm_start && end <= vma->vm_end) { /* Must set VM_NONLINEAR before any pages are populated. */ - if (pgoff != ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff) + if (pgoff != linear_page_index(vma, start) && + !(vma->vm_flags & VM_NONLINEAR)) { + if (!has_write_lock) { + up_read(&mm->mmap_sem); + down_write(&mm->mmap_sem); + has_write_lock = 1; + goto retry; + } + mapping = vma->vm_file->f_mapping; + spin_lock(&mapping->i_mmap_lock); + flush_dcache_mmap_lock(mapping); vma->vm_flags |= VM_NONLINEAR; + vma_prio_tree_remove(vma, &mapping->i_mmap); + vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); + flush_dcache_mmap_unlock(mapping); + spin_unlock(&mapping->i_mmap_lock); + } - /* ->populate can take a long time, so downgrade the lock. */ - downgrade_write(&mm->mmap_sem); err = vma->vm_ops->populate(vma, start, size, vma->vm_page_prot, pgoff, flags & MAP_NONBLOCK); @@ -210,10 +217,11 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, * it after ->populate completes, and that would prevent * downgrading the lock. (Locks can't be upgraded). */ + } + if (likely(!has_write_lock)) up_read(&mm->mmap_sem); - } else { + else up_write(&mm->mmap_sem); - } return err; }