From mboxrd@z Thu Jan 1 00:00:00 1970 From: npiggin@suse.de Subject: [patch 13/41] mm: restore KERNEL_DS optimisations Date: Mon, 14 May 2007 16:06:32 +1000 Message-ID: <20070514060651.948656000@wotan.suse.de> References: <20070514060619.689648000@wotan.suse.de> Cc: linux-fsdevel@vger.kernel.org, Linux Memory Management To: Andrew Morton Return-path: Received: from cantor2.suse.de ([195.135.220.15]:51803 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1761079AbXENIXz (ORCPT ); Mon, 14 May 2007 04:23:55 -0400 Content-Disposition: inline; filename=fs-kernel_ds-opt.patch Sender: linux-fsdevel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org Restore the KERNEL_DS optimisation, especially helpful to the 2copy write path. This may be a pretty questionable gain in most cases, especially after the legacy 2copy write path is removed, but it doesn't cost much. Cc: Linux Memory Management Cc: Linux Filesystems Signed-off-by: Nick Piggin mm/filemap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) Index: linux-2.6/mm/filemap.c =================================================================== --- linux-2.6.orig/mm/filemap.c +++ linux-2.6/mm/filemap.c @@ -2113,7 +2113,7 @@ static ssize_t generic_perform_write_2co * cannot take a pagefault with the destination page locked. * So pin the source page to copy it. */ - if (!PageUptodate(page)) { + if (!PageUptodate(page) && !segment_eq(get_fs(), KERNEL_DS)) { unlock_page(page); src_page = alloc_page(GFP_KERNEL); @@ -2238,6 +2238,13 @@ static ssize_t generic_perform_write(str const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; + unsigned int flags = 0; + + /* + * Copies from kernel address space cannot fail (NFSD is a big user). + */ + if (segment_eq(get_fs(), KERNEL_DS)) + flags |= AOP_FLAG_UNINTERRUPTIBLE; do { struct page *page; @@ -2269,7 +2276,7 @@ again: break; } - status = a_ops->write_begin(file, mapping, pos, bytes, 0, + status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status)) break; --