From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: swiotlb detection should be memory hotplug aware ? Date: Wed, 28 Jul 2010 13:09:57 +0200 Message-ID: <8739v3kgl6.fsf@basil.nowhere.org> References: <4C49A83C.8070203@linux.intel.com> <20100723145945.GA31857@phenom.dumpdata.com> <4C49B3F5.3030904@linux.intel.com> <20100728190939D.fujita.tomonori@lab.ntt.co.jp> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: In-Reply-To: <20100728190939D.fujita.tomonori@lab.ntt.co.jp> (FUJITA Tomonori's message of "Wed, 28 Jul 2010 19:10:19 +0900") Sender: linux-kernel-owner@vger.kernel.org To: FUJITA Tomonori Cc: ak@linux.intel.com, konrad.wilk@oracle.com, akataria@vmware.com, lenb@kernel.org, x86@kernel.org, linux-acpi@vger.kernel.org, linux-kernel@vger.kernel.org, petr@vmware.com List-Id: linux-acpi@vger.kernel.org FUJITA Tomonori writes: > >> The other problem is that using only two bits for the needed address >> space is also extremly >> inefficient (4GB and 16MB on x86). Really want masks everywhere and >> optimize for the >> actual requirements. > > swiotlb doesn't allocate GFP_DMA memory. It handles only GFP_DMA32. I was lumping GFP_DMA and swiotlb together here. The pci_alloc_consistent() function uses both interchangedly. They really effectively are the same thing these days and just separated by historical accident. > I have a half-baked patch for it. I'll send it later. The problem are still the *_map users which usually cannot sleep, and then it's difficult to grow. For *_alloc it's relatively easy and to some extend already implemented. -Andi -- ak@linux.intel.com -- Speaking for myself only.