From: Christoph Hellwig <hch@lst.de>
To: Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Paul Mackerras <paulus@samba.org>,
Michael Ellerman <mpe@ellerman.id.au>,
Olof Johansson <olof@lixom.net>
Cc: iommu@lists.linux-foundation.org, linuxppc-dev@lists.ozlabs.org,
linux-kernel@vger.kernel.org
Subject: [PATCH 10/32] powerpc/dart: use the generic iommu bypass code
Date: Wed, 13 Feb 2019 08:01:11 +0100 [thread overview]
Message-ID: <20190213070133.11259-11-hch@lst.de> (raw)
In-Reply-To: <20190213070133.11259-1-hch@lst.de>
Use the generic iommu bypass code instead of overriding set_dma_mask.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/powerpc/sysdev/dart_iommu.c | 47 ++++++++++++--------------------
1 file changed, 17 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 283ce04c5844..d42ba645d51d 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -360,13 +360,6 @@ static void iommu_table_dart_setup(void)
set_bit(iommu_table_dart.it_size - 1, iommu_table_dart.it_map);
}
-static void pci_dma_dev_setup_dart(struct pci_dev *dev)
-{
- if (dart_is_u4)
- set_dma_offset(&dev->dev, DART_U4_BYPASS_BASE);
- set_iommu_table_base(&dev->dev, &iommu_table_dart);
-}
-
static void pci_dma_bus_setup_dart(struct pci_bus *bus)
{
if (!iommu_table_dart_inited) {
@@ -390,27 +383,18 @@ static bool dart_device_on_pcie(struct device *dev)
return false;
}
-static int dart_dma_set_mask(struct device *dev, u64 dma_mask)
+static void pci_dma_dev_setup_dart(struct pci_dev *dev)
{
- if (!dev->dma_mask || !dma_supported(dev, dma_mask))
- return -EIO;
-
- /* U4 supports a DART bypass, we use it for 64-bit capable
- * devices to improve performances. However, that only works
- * for devices connected to U4 own PCIe interface, not bridged
- * through hypertransport. We need the device to support at
- * least 40 bits of addresses.
- */
- if (dart_device_on_pcie(dev) && dma_mask >= DMA_BIT_MASK(40)) {
- dev_info(dev, "Using 64-bit DMA iommu bypass\n");
- set_dma_ops(dev, &dma_nommu_ops);
- } else {
- dev_info(dev, "Using 32-bit DMA via iommu\n");
- set_dma_ops(dev, &dma_iommu_ops);
- }
+ if (dart_is_u4 && dart_device_on_pcie(&dev->dev))
+ set_dma_offset(&dev->dev, DART_U4_BYPASS_BASE);
+ set_iommu_table_base(&dev->dev, &iommu_table_dart);
+}
- *dev->dma_mask = dma_mask;
- return 0;
+static bool iommu_bypass_supported_dart(struct pci_dev *dev, u64 mask)
+{
+ return dart_is_u4 &&
+ dart_device_on_pcie(&dev->dev) &&
+ mask >= DMA_BIT_MASK(40);
}
void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
@@ -430,12 +414,15 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
if (dart_init(dn) != 0)
return;
- /* Setup bypass if supported */
- if (dart_is_u4)
- ppc_md.dma_set_mask = dart_dma_set_mask;
-
+ /*
+ * U4 supports a DART bypass, we use it for 64-bit capable devices to
+ * improve performance. However, that only works for devices connected
+ * to the U4 own PCIe interface, not bridged through hypertransport.
+ * We need the device to support at least 40 bits of addresses.
+ */
controller_ops->dma_dev_setup = pci_dma_dev_setup_dart;
controller_ops->dma_bus_setup = pci_dma_bus_setup_dart;
+ controller_ops->iommu_bypass_supported = iommu_bypass_supported_dart;
/* Setup pci_dma ops */
set_pci_dma_ops(&dma_iommu_ops);
--
2.20.1
next prev parent reply other threads:[~2019-02-13 7:24 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-13 7:01 use generic DMA mapping code in powerpc V7 Christoph Hellwig
2019-02-13 7:01 ` [PATCH 01/32] net: pasemi: set a 64-bit DMA mask on the DMA device Christoph Hellwig
2019-02-22 9:47 ` [01/32] " Michael Ellerman
2019-02-13 7:01 ` [PATCH 02/32] dma-direct: we might need GFP_DMA for 32-bit dma masks Christoph Hellwig
2019-02-13 7:01 ` [PATCH 03/32] powerpc/dma: untangle vio_dma_mapping_ops from dma_iommu_ops Christoph Hellwig
2019-02-13 7:01 ` [PATCH 04/32] powerpc/dma: handle iommu bypass in dma_iommu_ops Christoph Hellwig
2019-02-13 7:01 ` [PATCH 05/32] powerpc/pseries: unwind dma_get_required_mask_pSeriesLP a bit Christoph Hellwig
2019-02-13 7:01 ` [PATCH 06/32] powerpc/pseries: use the generic iommu bypass code Christoph Hellwig
2019-02-13 7:01 ` [PATCH 07/32] powerpc/cell: move dma direct window setup out of dma_configure Christoph Hellwig
2019-02-13 7:01 ` [PATCH 08/32] powerpc/cell: use the generic iommu bypass code Christoph Hellwig
2019-02-13 7:01 ` [PATCH 09/32] powerpc/dart: remove dead cleanup code in iommu_init_early_dart Christoph Hellwig
2019-02-13 7:01 ` Christoph Hellwig [this message]
2019-02-13 7:01 ` [PATCH 11/32] powerpc/powernv: remove pnv_pci_ioda_pe_single_vendor Christoph Hellwig
2019-02-13 7:01 ` [PATCH 12/32] powerpc/powernv: remove pnv_npu_dma_set_mask Christoph Hellwig
2019-02-13 7:01 ` [PATCH 13/32] powerpc/powernv: use the generic iommu bypass code Christoph Hellwig
2019-02-13 7:01 ` [PATCH 14/32] powerpc/dma: stop overriding dma_get_required_mask Christoph Hellwig
2019-02-13 7:01 ` [PATCH 15/32] powerpc/pci: remove the dma_set_mask pci_controller ops methods Christoph Hellwig
2019-02-13 7:01 ` [PATCH 16/32] powerpc/dma: remove the iommu fallback for coherent allocations Christoph Hellwig
2019-02-13 7:01 ` [PATCH 17/32] powerpc/dma: remove get_pci_dma_ops Christoph Hellwig
2019-02-13 7:01 ` [PATCH 18/32] powerpc/dma: move pci_dma_dev_setup_swiotlb to fsl_pci.c Christoph Hellwig
2019-02-13 7:01 ` [PATCH 19/32] powerpc/dma: remove max_direct_dma_addr Christoph Hellwig
2019-02-13 7:01 ` [PATCH 20/32] powerpc/dma: fix an off-by-one in dma_capable Christoph Hellwig
2019-02-13 7:01 ` [PATCH 21/32] dma-mapping, powerpc: simplify the arch dma_set_mask override Christoph Hellwig
2019-02-13 7:01 ` [PATCH 22/32] powerpc/dma: use phys_to_dma instead of get_dma_offset Christoph Hellwig
2019-02-13 7:01 ` [PATCH 23/32] powerpc/dma: remove dma_nommu_mmap_coherent Christoph Hellwig
2019-02-13 7:01 ` [PATCH 24/32] powerpc/dma: remove dma_nommu_get_required_mask Christoph Hellwig
2019-02-13 7:01 ` [PATCH 25/32] powerpc/dma: remove dma_nommu_dma_supported Christoph Hellwig
2019-02-13 7:01 ` [PATCH 26/32] swiotlb: remove swiotlb_dma_supported Christoph Hellwig
2019-02-13 7:01 ` [PATCH 27/32] powerpc/dma: use the dma-direct allocator for coherent platforms Christoph Hellwig
2019-02-13 7:01 ` [PATCH 28/32] powerpc/dma: use the dma_direct mapping routines Christoph Hellwig
2019-02-13 7:01 ` [PATCH 29/32] powerpc/dma: use the generic direct mapping bypass Christoph Hellwig
2019-02-13 7:01 ` [PATCH 30/32] powerpc/dma: remove get_dma_offset Christoph Hellwig
2019-02-13 7:01 ` [PATCH 31/32] powerpc/dma: remove set_dma_offset Christoph Hellwig
2019-02-13 7:01 ` [PATCH 32/32] powerpc/dma: trim the fat from <asm/dma-mapping.h> Christoph Hellwig
2019-02-20 14:23 ` use generic DMA mapping code in powerpc V7 Christoph Hellwig
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=20190213070133.11259-11-hch@lst.de \
--to=hch@lst.de \
--cc=benh@kernel.crashing.org \
--cc=iommu@lists.linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mpe@ellerman.id.au \
--cc=olof@lixom.net \
--cc=paulus@samba.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).