From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from aserp1040.oracle.com (aserp1040.oracle.com [141.146.126.69]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 1ED4B1A2C9B for ; Mon, 23 Mar 2015 06:27:46 +1100 (AEDT) Date: Sun, 22 Mar 2015 15:27:26 -0400 From: Sowmini Varadhan To: Alexey Kardashevskiy Subject: Re: Generic IOMMU pooled allocator Message-ID: <20150322192726.GB19474@oracle.com> References: <20150318.222517.1444725543017433108.davem@davemloft.net> <1426734106.4770.118.camel@kernel.crashing.org> <550A5E5D.90907@ozlabs.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <550A5E5D.90907@ozlabs.ru> Cc: Alexey Kardashevskiy , Anton Blanchard , paulus@samba.org, sparclinux@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, David Miller List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Turned out that I was able to iterate over it, and remove both the ->cookie_to_index and the ->demap indirection from iommu_tbl_ops. That leaves only the odd iommu_flushall() hook, I'm trying to find the history behind that (needed for sun4u platforms, afaik, and not sure if there are other ways to achieve this). Just sent out a new patch-set, which should reach all the people/lists on this thread. If it's possible, it would also help to share any preliminary code-samples with the iommu_table_ops you folks have in mind. Please take a look at patchv5, and share your thoughts. --Sowmini From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sowmini Varadhan Date: Sun, 22 Mar 2015 19:27:26 +0000 Subject: Re: Generic IOMMU pooled allocator Message-Id: <20150322192726.GB19474@oracle.com> List-Id: References: <20150318.222517.1444725543017433108.davem@davemloft.net> <1426734106.4770.118.camel@kernel.crashing.org> <550A5E5D.90907@ozlabs.ru> In-Reply-To: <550A5E5D.90907@ozlabs.ru> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Alexey Kardashevskiy Cc: Alexey Kardashevskiy , Anton Blanchard , paulus@samba.org, sparclinux@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, David Miller Turned out that I was able to iterate over it, and remove both the ->cookie_to_index and the ->demap indirection from iommu_tbl_ops. That leaves only the odd iommu_flushall() hook, I'm trying to find the history behind that (needed for sun4u platforms, afaik, and not sure if there are other ways to achieve this). Just sent out a new patch-set, which should reach all the people/lists on this thread. If it's possible, it would also help to share any preliminary code-samples with the iommu_table_ops you folks have in mind. Please take a look at patchv5, and share your thoughts. --Sowmini