From mboxrd@z Thu Jan 1 00:00:00 1970 Return-path: Date: Wed, 11 Aug 2021 06:52:57 +0100 From: Christoph Hellwig Subject: Re: [PATCH RFC 0/2] dma-pool: allow user to disable atomic pool Message-ID: References: <20210624052010.5676-1-bhe@redhat.com> <20210624092930.GA802261@MiWiFi-R3L-srv> <8b3d4e02-6e94-ad59-a480-fed8e55c009a@arm.com> <20210805065410.GA2051@MiWiFi-R3L-srv> <5df93c4e-ffdd-88c5-db4a-1a09826d047a@amd.com> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <5df93c4e-ffdd-88c5-db4a-1a09826d047a@amd.com> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "kexec" Errors-To: kexec-bounces+dwmw2=infradead.org@lists.infradead.org To: Tom Lendacky Cc: Baoquan He , Robin Murphy , Christoph Hellwig , brijesh.singh@amd.com, x86@kernel.org, kexec@lists.infradead.org, linux-kernel@vger.kernel.org, rppt@linux.ibm.com, linux-mm@kvack.org, iommu@lists.linux-foundation.org, rientjes@google.com On Tue, Aug 10, 2021 at 03:52:25PM -0500, Tom Lendacky via iommu wrote: > I think the atomic pool is used by the NVMe driver. My understanding is > that driver will do a dma_alloc_coherent() from interrupt context, so it > needs to use GFP_ATOMIC. The pool was created because dma_alloc_coherent() > would perform a set_memory_decrypted() call, which can sleep. The pool > eliminates that issue (David can correct me if I got that wrong). Not just the NVMe driver. We have plenty of drivers doing that, just do a quick grep for dma_alloc_* dma_poll_alloc, dma_pool_zalloc with GFP_ATOMIC (and that won't even find multi-line strings). _______________________________________________ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec