From: Robin Murphy <robin.murphy@arm.com> To: hch@lst.de, m.szyprowski@samsung.com Cc: lorenzo.pieralisi@arm.com, gregkh@linuxfoundation.org, joro@8bytes.org, x86@kernel.org, linux-acpi@vger.kernel.org, iommu@lists.linux-foundation.org, robh+dt@kernel.org, hanjun.guo@linaro.org, sudeep.holla@arm.com, frowand.list@gmail.com, linux-arm-kernel@lists.infradead.org Subject: [PATCH v2 5/7] iommu/dma: Respect bus DMA limit for IOVAs Date: Mon, 23 Jul 2018 23:16:10 +0100 [thread overview] Message-ID: <d370670edae9c9c537a5280c5e7c96bf3ec7ed8f.1532382222.git.robin.murphy@arm.com> (raw) In-Reply-To: <cover.1532382222.git.robin.murphy@arm.com> Take the new bus limit into account (when present) for IOVA allocations, to accommodate those SoCs which integrate off-the-shelf IP blocks with narrower interconnects such that the link between a device output and an IOMMU input can truncate DMA addresses to even fewer bits than the native size of either block's interface would imply. Eventually it might make sense for the DMA core to apply this constraint up-front in dma_set_mask() and friends, but for now this seems like the least risky approach. CC: Joerg Roedel <joro@8bytes.org> Signed-off-by: Robin Murphy <robin.murphy@arm.com> --- Bonus question: Now that we're collecing DMA API code in kernel/dma/ do we want to reevaluate dma-iommu? On the one hand it's the bulk of a dma_ops implementation so should perhaps move, but on the other it's entirely IOMMU-specific code so should perhaps stay where it is... :/ drivers/iommu/dma-iommu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index ddcbbdb5d658..511ff9a1d6d9 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -367,6 +367,9 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain, if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1))) iova_len = roundup_pow_of_two(iova_len); + if (dev->bus_dma_mask) + dma_limit &= dev->bus_dma_mask; + if (domain->geometry.force_aperture) dma_limit = min(dma_limit, domain->geometry.aperture_end); -- 2.17.1.dirty
WARNING: multiple messages have this Message-ID (diff)
From: robin.murphy@arm.com (Robin Murphy) To: linux-arm-kernel@lists.infradead.org Subject: [PATCH v2 5/7] iommu/dma: Respect bus DMA limit for IOVAs Date: Mon, 23 Jul 2018 23:16:10 +0100 [thread overview] Message-ID: <d370670edae9c9c537a5280c5e7c96bf3ec7ed8f.1532382222.git.robin.murphy@arm.com> (raw) In-Reply-To: <cover.1532382222.git.robin.murphy@arm.com> Take the new bus limit into account (when present) for IOVA allocations, to accommodate those SoCs which integrate off-the-shelf IP blocks with narrower interconnects such that the link between a device output and an IOMMU input can truncate DMA addresses to even fewer bits than the native size of either block's interface would imply. Eventually it might make sense for the DMA core to apply this constraint up-front in dma_set_mask() and friends, but for now this seems like the least risky approach. CC: Joerg Roedel <joro@8bytes.org> Signed-off-by: Robin Murphy <robin.murphy@arm.com> --- Bonus question: Now that we're collecing DMA API code in kernel/dma/ do we want to reevaluate dma-iommu? On the one hand it's the bulk of a dma_ops implementation so should perhaps move, but on the other it's entirely IOMMU-specific code so should perhaps stay where it is... :/ drivers/iommu/dma-iommu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index ddcbbdb5d658..511ff9a1d6d9 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -367,6 +367,9 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain, if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1))) iova_len = roundup_pow_of_two(iova_len); + if (dev->bus_dma_mask) + dma_limit &= dev->bus_dma_mask; + if (domain->geometry.force_aperture) dma_limit = min(dma_limit, domain->geometry.aperture_end); -- 2.17.1.dirty
next prev parent reply other threads:[~2018-07-23 22:16 UTC|newest] Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-07-23 22:16 [PATCH v2 0/7] Stop losing firmware-set DMA masks Robin Murphy 2018-07-23 22:16 ` Robin Murphy 2018-07-23 22:16 ` [PATCH v2 1/7] ACPI/IORT: Support address size limit for root complexes Robin Murphy 2018-07-23 22:16 ` Robin Murphy 2018-07-23 22:16 ` [PATCH v2 2/7] dma-mapping: Generalise dma_32bit_limit flag Robin Murphy 2018-07-23 22:16 ` Robin Murphy [not found] ` <c1720f0181b66f711e4097d85149757b16a7b0a7.1532382222.git.robin.murphy-5wv7dgnIgG8@public.gmane.org> 2018-07-25 11:29 ` Christoph Hellwig 2018-07-25 11:29 ` Christoph Hellwig 2018-07-27 17:45 ` Grygorii Strashko via iommu 2018-07-27 17:45 ` Grygorii Strashko [not found] ` <7872d914-8ea7-06e4-4a0c-489023e098d6-l0cyMroinI0@public.gmane.org> 2018-07-27 20:11 ` Robin Murphy 2018-07-27 20:11 ` Robin Murphy [not found] ` <5354ef69-c54e-170b-62d4-5110dc60aa8f-5wv7dgnIgG8@public.gmane.org> 2018-07-27 20:41 ` Grygorii Strashko via iommu 2018-07-27 20:41 ` Grygorii Strashko 2018-07-23 22:16 ` [PATCH v2 3/7] ACPI/IORT: Set bus DMA mask as appropriate Robin Murphy 2018-07-23 22:16 ` Robin Murphy [not found] ` <07cbf8f77fac552dca9b4c85a9d3bd8ed5a4cd29.1532382222.git.robin.murphy-5wv7dgnIgG8@public.gmane.org> 2018-07-25 11:29 ` Christoph Hellwig 2018-07-25 11:29 ` Christoph Hellwig 2018-07-25 13:16 ` Lorenzo Pieralisi 2018-07-25 13:16 ` Lorenzo Pieralisi 2018-07-23 22:16 ` [PATCH v2 4/7] of/device: " Robin Murphy 2018-07-23 22:16 ` Robin Murphy [not found] ` <cc56f074b8da7e03a187b2363b1f2c2955d62c1c.1532382222.git.robin.murphy-5wv7dgnIgG8@public.gmane.org> 2018-07-25 11:30 ` Christoph Hellwig 2018-07-25 11:30 ` Christoph Hellwig 2018-07-23 22:16 ` Robin Murphy [this message] 2018-07-23 22:16 ` [PATCH v2 5/7] iommu/dma: Respect bus DMA limit for IOVAs Robin Murphy [not found] ` <d370670edae9c9c537a5280c5e7c96bf3ec7ed8f.1532382222.git.robin.murphy-5wv7dgnIgG8@public.gmane.org> 2018-07-26 8:58 ` Christoph Hellwig 2018-07-26 8:58 ` Christoph Hellwig 2018-07-23 22:16 ` [PATCH v2 6/7] ACPI/IORT: Don't set default coherent DMA mask Robin Murphy 2018-07-23 22:16 ` Robin Murphy [not found] ` <3525869e8e7530128bf9718ae8af7d7564b3c684.1532382222.git.robin.murphy-5wv7dgnIgG8@public.gmane.org> 2018-07-25 15:27 ` Lorenzo Pieralisi 2018-07-25 15:27 ` Lorenzo Pieralisi 2018-07-25 15:43 ` Robin Murphy 2018-07-25 15:43 ` Robin Murphy 2018-07-23 22:16 ` [PATCH v2 7/7] OF: " Robin Murphy 2018-07-23 22:16 ` Robin Murphy [not found] ` <66c08e4df2032fde82a2f97544f41fd3a2f24a94.1532382222.git.robin.murphy-5wv7dgnIgG8@public.gmane.org> 2018-07-26 23:52 ` Grygorii Strashko via iommu 2018-07-26 23:52 ` Grygorii Strashko 2018-07-27 0:22 ` Grygorii Strashko 2018-07-27 0:22 ` Grygorii Strashko [not found] ` <92d6b010-b5c0-fc59-0668-5b455e26c912-l0cyMroinI0@public.gmane.org> 2018-07-27 11:36 ` Robin Murphy 2018-07-27 11:36 ` Robin Murphy 2018-07-27 17:34 ` Grygorii Strashko 2018-07-27 17:34 ` Grygorii Strashko [not found] ` <108a6254-1257-5daf-deaa-69bc4db2ec77-l0cyMroinI0@public.gmane.org> 2018-07-27 19:46 ` Robin Murphy 2018-07-27 19:46 ` Robin Murphy [not found] ` <c7a9c7ae-1f4a-af9d-df78-1f48bb5c28a5-5wv7dgnIgG8@public.gmane.org> 2018-07-27 18:13 ` Russell King - ARM Linux 2018-07-27 18:13 ` Russell King - ARM Linux [not found] ` <20180727181302.GC17271-l+eeeJia6m9URfEZ8mYm6t73F7V6hmMc@public.gmane.org> 2018-07-27 18:45 ` Grygorii Strashko via iommu 2018-07-27 18:45 ` Grygorii Strashko [not found] ` <affa2718-5f3a-7439-db25-ce171a99414a-l0cyMroinI0@public.gmane.org> 2018-07-27 20:42 ` Robin Murphy 2018-07-27 20:42 ` Robin Murphy 2018-07-27 19:29 ` Robin Murphy 2018-07-27 19:29 ` Robin Murphy 2018-07-26 23:45 ` [PATCH v2 0/7] Stop losing firmware-set DMA masks Grygorii Strashko 2018-07-26 23:45 ` Grygorii Strashko [not found] ` <c73bc8d2-b745-ff31-1949-7a59ab04ede6-l0cyMroinI0@public.gmane.org> 2018-07-27 10:55 ` Robin Murphy 2018-07-27 10:55 ` Robin Murphy [not found] ` <8b8ac841-5c4c-ae27-21d5-d7aaaf4c277c-5wv7dgnIgG8@public.gmane.org> 2018-07-27 17:22 ` Grygorii Strashko via iommu 2018-07-27 17:22 ` Grygorii Strashko [not found] ` <cover.1532382222.git.robin.murphy-5wv7dgnIgG8@public.gmane.org> 2018-07-25 11:31 ` Christoph Hellwig 2018-07-25 11:31 ` Christoph Hellwig [not found] ` <20180725113122.GD24736-jcswGhMUV9g@public.gmane.org> 2018-07-25 12:11 ` Joerg Roedel 2018-07-25 12:11 ` Joerg Roedel 2018-07-25 12:12 ` Robin Murphy 2018-07-25 12:12 ` Robin Murphy [not found] ` <5e036ade-db0b-f628-a4a0-6d014d1d76c8-5wv7dgnIgG8@public.gmane.org> 2018-07-25 12:17 ` Will Deacon 2018-07-25 12:17 ` Will Deacon 2018-07-25 13:58 ` Ard Biesheuvel 2018-07-25 13:58 ` Ard Biesheuvel 2018-07-26 9:00 ` Christoph Hellwig 2018-07-26 9:00 ` Christoph Hellwig 2018-07-29 12:32 ` Arnd Bergmann 2018-07-29 12:32 ` Arnd Bergmann [not found] ` <CAK8P3a3HDJ6svNN_cwvegxu20yNv8+tvc0D1A6Ooeq8agawbFg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org> 2018-07-31 11:24 ` Robin Murphy 2018-07-31 11:24 ` Robin Murphy [not found] ` <1ccccc4b-7d4c-a3ee-23a2-f108916705e9-5wv7dgnIgG8@public.gmane.org> 2018-08-06 10:01 ` Arnd Bergmann 2018-08-06 10:01 ` Arnd Bergmann [not found] ` <CAK8P3a3ZcOeHMR_qFnsBdXED+2X8_AEMKoS5MeAQhbapbGmm9w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org> 2018-08-06 12:13 ` Christoph Hellwig 2018-08-06 12:13 ` Christoph Hellwig [not found] ` <20180806121334.GA5340-jcswGhMUV9g@public.gmane.org> 2018-08-06 12:13 ` Arnd Bergmann 2018-08-06 12:13 ` Arnd Bergmann
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=d370670edae9c9c537a5280c5e7c96bf3ec7ed8f.1532382222.git.robin.murphy@arm.com \ --to=robin.murphy@arm.com \ --cc=frowand.list@gmail.com \ --cc=gregkh@linuxfoundation.org \ --cc=hanjun.guo@linaro.org \ --cc=hch@lst.de \ --cc=iommu@lists.linux-foundation.org \ --cc=joro@8bytes.org \ --cc=linux-acpi@vger.kernel.org \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=lorenzo.pieralisi@arm.com \ --cc=m.szyprowski@samsung.com \ --cc=robh+dt@kernel.org \ --cc=sudeep.holla@arm.com \ --cc=x86@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.