From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753644AbaI1Pwa (ORCPT ); Sun, 28 Sep 2014 11:52:30 -0400 Received: from mail-pd0-f178.google.com ([209.85.192.178]:39741 "EHLO mail-pd0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750901AbaI1Pw2 (ORCPT ); Sun, 28 Sep 2014 11:52:28 -0400 From: Akinobu Mita To: linux-kernel@vger.kernel.org, akpm@linux-foundation.org Cc: Akinobu Mita , Peter Hurley , Marek Szyprowski , Konrad Rzeszutek Wilk , David Woodhouse , Don Dutile , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , Andi Kleen , Yinghai Lu , x86@kernel.org, iommu@lists.linux-foundation.org Subject: [PATCH 1/2] x86: don't unnecessarily call dma_alloc_from_contiguous() Date: Mon, 29 Sep 2014 00:52:03 +0900 Message-Id: <1411919524-3666-1-git-send-email-akinobu.mita@gmail.com> X-Mailer: git-send-email 1.9.1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org If CONFIG_DMA_CMA is enabled, dma_generic_alloc_coherent() tries to allocate memory region by dma_alloc_from_contiguous() before trying to use alloc_pages(). This wastes CMA region by small DMA-coherent buffers which can be allocated by alloc_pages(). And it also causes performance degradation, as this is trying to drive _all_ dma mapping allocations through a _very_ small window, reported by Peter Hurley. This fixes it by trying to allocate by alloc_pages() first in dma_generic_alloc_coherent() as dma_alloc_from_contiguous should be called only for huge allocation. Signed-off-by: Akinobu Mita Reported-by: Peter Hurley Cc: Peter Hurley Cc: Marek Szyprowski Cc: Konrad Rzeszutek Wilk Cc: David Woodhouse Cc: Don Dutile Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: Yinghai Lu Cc: x86@kernel.org Cc: iommu@lists.linux-foundation.org --- arch/x86/kernel/pci-dma.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index a25e202..0402266 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -99,20 +99,20 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, flag &= ~__GFP_ZERO; again: - page = NULL; + page = alloc_pages_node(dev_to_node(dev), flag | __GFP_NOWARN, + get_order(size)); /* CMA can be used only in the context which permits sleeping */ - if (flag & __GFP_WAIT) { + if (!page && (flag & __GFP_WAIT)) { page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (page && page_to_phys(page) + size > dma_mask) { dma_release_from_contiguous(dev, page, count); page = NULL; } } - /* fallback */ - if (!page) - page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); - if (!page) + if (!page) { + warn_alloc_failed(flag, get_order(size), NULL); return NULL; + } addr = page_to_phys(page); if (addr + size > dma_mask) { -- 1.9.1