From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934250AbXCWAvT (ORCPT ); Thu, 22 Mar 2007 20:51:19 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S934251AbXCWAvT (ORCPT ); Thu, 22 Mar 2007 20:51:19 -0400 Received: from smtp-out.google.com ([216.239.45.13]:22645 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934250AbXCWAvS (ORCPT ); Thu, 22 Mar 2007 20:51:18 -0400 DomainKey-Signature: a=rsa-sha1; s=beta; d=google.com; c=nofws; q=dns; h=received:message-id:date:from:to:subject:mime-version: content-type:content-transfer-encoding:content-disposition; b=WHAVnSjL72zMU3qYdPPUp0bqKGTze61ERXbuTI7ZALnuEyLZnu5VNoSj8ZQBBM0H2 2S4SCSW2SpX74/X7SyZuQ== Message-ID: Date: Thu, 22 Mar 2007 17:51:11 -0700 From: "Ken Chen" To: "Andrew Morton" , linux-kernel@vger.kernel.org Subject: [patch] cache pipe buf page address for non-highmem arch MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org It is really sad that we always call kmap and friends for every pipe buffer page on 64-bit arch that doesn't use HIGHMEM, or on configuration that doesn't turn on HIGHMEM. The effect of calling kmap* is visible in the execution profile when pipe code is being stressed. It is especially true on amd's x86-64 platform where kmap() has to traverse through numa node index calculation in order to convert struct page * to kernel virtual address. It is fairly pointless to perform that calculation repeatly on system with no highmem (i.e., 64-bit arch like x86-64). This patch caches kernel pipe buffer page's kernel vaddr to speed up pipe buffer mapping functions. There is another suboptimal block in pipe_read() where wake_up is called twice. I think it was an oversight since in pipe_write(), it looks like it is doing the right thing. Signed-off-by: Ken Chen --- linus-2.6.git/fs/pipe.c.orig 2007-03-01 12:41:06.000000000 -0800 +++ linus-2.6.git/fs/pipe.c 2007-03-22 16:28:03.000000000 -0700 @@ -20,6 +20,22 @@ #include #include +#include + +#ifdef CONFIG_HIGHMEM +#define pipe_kmap kmap +#define pipe_kmap_atomic kmap_atomic +#else /* CONFIG_HIGHMEM */ +static inline void *pipe_kmap(struct page *page) +{ + return (void *) page->private; +} +static inline void *pipe_kmap_atomic(struct page *page, enum km_type type) +{ + pagefault_disable(); + return pipe_kmap(page); +} +#endif /* * We use a start+len construction, which provides full use of the @@ -169,10 +185,10 @@ void *generic_pipe_buf_map(struct pipe_i { if (atomic) { buf->flags |= PIPE_BUF_FLAG_ATOMIC; - return kmap_atomic(buf->page, KM_USER0); + return pipe_kmap_atomic(buf->page, KM_USER0); } - return kmap(buf->page); + return pipe_kmap(buf->page); } void generic_pipe_buf_unmap(struct pipe_inode_info *pipe, @@ -316,6 +332,7 @@ redo: if (do_wakeup) { wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); + do_wakeup = 0; } pipe_wait(pipe); } @@ -423,6 +440,8 @@ redo1: ret = ret ? : -ENOMEM; break; } + page->private = (unsigned long) + page_address(page); pipe->tmp_page = page; } /* Always wake up, even if the copy fails. Otherwise @@ -438,9 +457,9 @@ redo1: iov_fault_in_pages_read(iov, chars); redo2: if (atomic) - src = kmap_atomic(page, KM_USER0); + src = pipe_kmap_atomic(page, KM_USER0); else - src = kmap(page); + src = pipe_kmap(page); error = pipe_iov_copy_from_user(src, iov, chars, atomic);