One more comment:
On Sun 23-03-14 15:08:33, Matthew Wilcox wrote:
> +static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
> + get_block_t get_block)
> +{
> + struct file *file = vma->vm_file;
> + struct inode *inode = file_inode(file);
> + struct address_space *mapping = file->f_mapping;
> + struct page *page;
> + struct buffer_head bh;
> + unsigned long vaddr = (unsigned long)vmf->virtual_address;
> + sector_t block;
> + pgoff_t size;
> + unsigned long pfn;
> + int error;
> + int major = 0;
> +
> + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
> + if (vmf->pgoff >= size)
> + return VM_FAULT_SIGBUS;
> +
> + memset(&bh, 0, sizeof(bh));
> + block = (sector_t)vmf->pgoff << (PAGE_SHIFT - inode->i_blkbits);
> + bh.b_size = PAGE_SIZE;
> +
> + repeat:
> + page = find_get_page(mapping, vmf->pgoff);
> + if (page) {
> + if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
> + page_cache_release(page);
> + return VM_FAULT_RETRY;
> + }
> + if (unlikely(page->mapping != mapping)) {
> + unlock_page(page);
> + page_cache_release(page);
> + goto repeat;
> + }
> + }
> +
> + error = get_block(inode, block, &bh, 0);
> + if (error || bh.b_size < PAGE_SIZE)
> + goto sigbus;
> +
> + if (!buffer_written(&bh) && !vmf->cow_page) {
> + if (vmf->flags & FAULT_FLAG_WRITE) {
> + error = get_block(inode, block, &bh, 1);
> + count_vm_event(PGMAJFAULT);
> + mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
> + major = VM_FAULT_MAJOR;
> + if (error || bh.b_size < PAGE_SIZE)
> + goto sigbus;
> + } else {
> + return dax_load_hole(mapping, page, vmf);
> + }
> + }
> +
> + /* Recheck i_size under i_mmap_mutex */
> + mutex_lock(&mapping->i_mmap_mutex);
> + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
> + if (unlikely(vmf->pgoff >= size)) {
> + mutex_unlock(&mapping->i_mmap_mutex);
> + goto sigbus;
You need to release the block you've got from the filesystem in case of
error here an below.
Honza
> + }
> + if (vmf->cow_page) {
> + if (buffer_written(&bh))
> + copy_user_bh(vmf->cow_page, inode, &bh, vaddr);
> + else
> + clear_user_highpage(vmf->cow_page, vaddr);
> + if (page) {
> + unlock_page(page);
> + page_cache_release(page);
> + }
> + /* do_cow_fault() will release the i_mmap_mutex */
> + return VM_FAULT_COWED;
> + }
> +
> + if (buffer_unwritten(&bh) || buffer_new(&bh))
> + dax_clear_blocks(inode, bh.b_blocknr, bh.b_size);
> +
> + error = dax_get_pfn(inode, &bh, &pfn);
> + if (error > 0)
> + error = vm_insert_mixed(vma, vaddr, pfn);
> + mutex_unlock(&mapping->i_mmap_mutex);
> +
> + if (page) {
> + delete_from_page_cache(page);
> + unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
> + PAGE_CACHE_SIZE, 0);
> + unlock_page(page);
> + page_cache_release(page);
> + }
> +
> + if (error == -ENOMEM)
> + return VM_FAULT_OOM;
> + /* -EBUSY is fine, somebody else faulted on the same PTE */
> + if (error != -EBUSY)
> + BUG_ON(error);
> + return VM_FAULT_NOPAGE | major;
> +
> + sigbus:
> + if (page) {
> + unlock_page(page);
> + page_cache_release(page);
> + }
> + return VM_FAULT_SIGBUS;
> +}
--
Jan Kara <[email protected]>
SUSE Labs, CR
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
