[RFC PATCH 6/7] x86: support dma_map_pfn()

From: Dan Williams
Date: Mon Mar 16 2015 - 16:29:18 EST


Fix up x86 dma_map_ops to allow pfn-only mappings.

As long as a dma_map_sg() implementation uses the generic sg_phys()
helpers it can support scatterlists that use struct pfn instead of
struct page.

Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
arch/x86/Kconfig | 12 ++++++++++++
arch/x86/kernel/amd_gart_64.c | 22 +++++++++++++++++-----
arch/x86/kernel/pci-nommu.c | 22 +++++++++++++++++-----
arch/x86/kernel/pci-swiotlb.c | 4 ++++
arch/x86/pci/sta2x11-fixup.c | 4 ++++
arch/x86/xen/pci-swiotlb-xen.c | 4 ++++
drivers/iommu/amd_iommu.c | 21 ++++++++++++++++-----
drivers/iommu/intel-iommu.c | 22 +++++++++++++++++-----
drivers/xen/swiotlb-xen.c | 29 +++++++++++++++++++----------
include/linux/swiotlb.h | 4 ++++
lib/swiotlb.c | 20 +++++++++++++++-----
11 files changed, 129 insertions(+), 35 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b7d31ca55187..3be1c0ac0025 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -801,6 +801,7 @@ config CALGARY_IOMMU
bool "IBM Calgary IOMMU support"
select SWIOTLB
depends on X86_64 && PCI
+ depends on !HAVE_DMA_PFN
---help---
Support for hardware IOMMUs in IBM's xSeries x366 and x460
systems. Needed to run systems with more than 3GB of memory
@@ -1430,6 +1431,17 @@ config ILLEGAL_POINTER_VALUE

source "mm/Kconfig"

+config PMEM_DMA
+ bool "Support DMA to Persistent Memory"
+ select HAVE_DMA_PFN
+ ---help---
+ Enable drivers that are capable of performing DMA to
+ Persistent Memory. Drivers with this capability are prepared
+ to map memory with either dma_map_pfn() or a dma_map_sg()
+ implementation that is pfn capable. Note, some iommus, like
+ CONFIG_CALGARY_IOMMU are incompatible (disabled by this
+ option).
+
config HIGHPTE
bool "Allocate 3rd-level pagetables from highmem"
depends on HIGHMEM
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 8e3842fc8bea..92c9f8139b08 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -239,13 +239,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
}

/* Map a single area into the IOMMU */
-static dma_addr_t gart_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+static dma_addr_t gart_map_pfn(struct device *dev, __pfn_t pfn,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
unsigned long bus;
- phys_addr_t paddr = page_to_phys(page) + offset;
+ phys_addr_t paddr = pfn_to_phys(pfn) + offset;

if (!dev)
dev = &x86_dma_fallback_dev;
@@ -259,6 +259,14 @@ static dma_addr_t gart_map_page(struct device *dev, struct page *page,
return bus;
}

+static __maybe_unused dma_addr_t gart_map_page(struct device *dev,
+ struct page *page, unsigned long offset, size_t size,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+ return gart_map_pfn(dev, page_to_pfn_typed(page), offset, size, dir,
+ attrs);
+}
+
/*
* Free a DMA mapping.
*/
@@ -699,7 +707,11 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
static struct dma_map_ops gart_dma_ops = {
.map_sg = gart_map_sg,
.unmap_sg = gart_unmap_sg,
+#ifdef CONFIG_HAVE_DMA_PFN
+ .map_pfn = gart_map_pfn,
+#else
.map_page = gart_map_page,
+#endif
.unmap_page = gart_unmap_page,
.alloc = gart_alloc_coherent,
.free = gart_free_coherent,
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index da15918d1c81..dfb66c4b8a73 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -25,12 +25,12 @@ check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
return 1;
}

-static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+static dma_addr_t nommu_map_pfn(struct device *dev, __pfn_t pfn,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
- dma_addr_t bus = page_to_phys(page) + offset;
+ dma_addr_t bus = pfn_to_phys(pfn) + offset;
WARN_ON(size == 0);
if (!check_addr("map_single", dev, bus, size))
return DMA_ERROR_CODE;
@@ -38,6 +38,14 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
return bus;
}

+static __maybe_unused dma_addr_t nommu_map_page(struct device *dev,
+ struct page *page, unsigned long offset, size_t size,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+ return nommu_map_pfn(dev, page_to_pfn_typed(page), offset, size, dir,
+ attrs);
+}
+
/* Map a set of buffers described by scatterlist in streaming
* mode for DMA. This is the scatter-gather version of the
* above pci_map_single interface. Here the scatter gather list
@@ -92,7 +100,11 @@ struct dma_map_ops nommu_dma_ops = {
.alloc = dma_generic_alloc_coherent,
.free = dma_generic_free_coherent,
.map_sg = nommu_map_sg,
+#ifdef CONFIG_HAVE_DMA_PFN
+ .map_pfn = nommu_map_pfn,
+#else
.map_page = nommu_map_page,
+#endif
.sync_single_for_device = nommu_sync_single_for_device,
.sync_sg_for_device = nommu_sync_sg_for_device,
.is_phys = 1,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 77dd0ad58be4..5351eb8c8f7f 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -48,7 +48,11 @@ static struct dma_map_ops swiotlb_dma_ops = {
.sync_sg_for_device = swiotlb_sync_sg_for_device,
.map_sg = swiotlb_map_sg_attrs,
.unmap_sg = swiotlb_unmap_sg_attrs,
+#ifdef CONFIG_HAVE_DMA_PFN
+ .map_pfn = swiotlb_map_pfn,
+#else
.map_page = swiotlb_map_page,
+#endif
.unmap_page = swiotlb_unmap_page,
.dma_supported = NULL,
};
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 5ceda85b8687..d1c6e3808bb5 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -182,7 +182,11 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev,
static struct dma_map_ops sta2x11_dma_ops = {
.alloc = sta2x11_swiotlb_alloc_coherent,
.free = x86_swiotlb_free_coherent,
+#ifdef CONFIG_HAVE_DMA_PFN
+ .map_pfn = swiotlb_map_pfn,
+#else
.map_page = swiotlb_map_page,
+#endif
.unmap_page = swiotlb_unmap_page,
.map_sg = swiotlb_map_sg_attrs,
.unmap_sg = swiotlb_unmap_sg_attrs,
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 0e98e5d241d0..e65ea48d7aed 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -28,7 +28,11 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
.map_sg = xen_swiotlb_map_sg_attrs,
.unmap_sg = xen_swiotlb_unmap_sg_attrs,
+#ifdef CONFIG_HAVE_DMA_PFN
+ .map_pfn = xen_swiotlb_map_pfn,
+#else
.map_page = xen_swiotlb_map_page,
+#endif
.unmap_page = xen_swiotlb_unmap_page,
.dma_supported = xen_swiotlb_dma_supported,
};
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 48882c126245..65fc71985c14 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -2765,16 +2765,15 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
/*
* The exported map_single function for dma_ops.
*/
-static dma_addr_t map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+static dma_addr_t map_pfn(struct device *dev, __pfn_t pfn, unsigned long offset,
+ size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
unsigned long flags;
struct protection_domain *domain;
dma_addr_t addr;
u64 dma_mask;
- phys_addr_t paddr = page_to_phys(page) + offset;
+ phys_addr_t paddr = pfn_to_phys(pfn) + offset;

INC_STATS_COUNTER(cnt_map_single);

@@ -2799,6 +2798,14 @@ out:
spin_unlock_irqrestore(&domain->lock, flags);

return addr;
+
+}
+
+static __maybe_unused dma_addr_t map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ return map_pfn(dev, page_to_pfn_typed(page), offset, size, dir, attrs);
}

/*
@@ -3063,7 +3070,11 @@ static void __init prealloc_protection_domains(void)
static struct dma_map_ops amd_iommu_dma_ops = {
.alloc = alloc_coherent,
.free = free_coherent,
+#ifdef CONFIG_HAVE_DMA_PFN
+ .map_pfn = map_pfn,
+#else
.map_page = map_page,
+#endif
.unmap_page = unmap_page,
.map_sg = map_sg,
.unmap_sg = unmap_sg,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index e10d62f2e61f..e3d304d4c162 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3087,15 +3087,23 @@ error:
return 0;
}

-static dma_addr_t intel_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+static dma_addr_t intel_map_pfn(struct device *dev, __pfn_t pfn,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
- return __intel_map_single(dev, page_to_phys(page) + offset, size,
+ return __intel_map_single(dev, pfn_to_phys(pfn) + offset, size,
dir, *dev->dma_mask);
}

+static __maybe_unused dma_addr_t intel_map_page(struct device *dev,
+ struct page *page, unsigned long offset, size_t size,
+ enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+ return intel_map_pfn(dev, page_to_pfn_typed(page), offset, size, dir,
+ attrs);
+}
+
static void flush_unmaps(void)
{
int i, j;
@@ -3381,7 +3389,11 @@ struct dma_map_ops intel_dma_ops = {
.free = intel_free_coherent,
.map_sg = intel_map_sg,
.unmap_sg = intel_unmap_sg,
+#ifdef CONFIG_HAVE_DMA_PFN
+ .map_pfn = intel_map_pfn,
+#else
.map_page = intel_map_page,
+#endif
.unmap_page = intel_unmap_page,
.mapping_error = intel_mapping_error,
};
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 810ad419e34c..bd29d09bbacc 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -382,10 +382,10 @@ EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
* Once the device is given the dma address, the device owns this memory until
* either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
*/
-dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+dma_addr_t xen_swiotlb_map_pfn(struct device *dev, unsigned long pfn,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
phys_addr_t map, phys = page_to_phys(page) + offset;
dma_addr_t dev_addr = xen_phys_to_bus(phys);
@@ -429,6 +429,16 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
}
return dev_addr;
}
+EXPORT_SYMBOL_GPL(xen_swiotlb_map_pfn);
+
+dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ return xen_swiotlb_map_pfn(dev, page_to_pfn(page), offset, size, dir,
+ attrs);
+}
EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);

/*
@@ -582,15 +592,14 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
attrs);
sg->dma_address = xen_phys_to_bus(map);
} else {
+ __pfn_t pfn = { .pfn = paddr >> PAGE_SHIFT };
+ unsigned long offset = paddr & ~PAGE_MASK;
+
/* we are not interested in the dma_addr returned by
* xen_dma_map_page, only in the potential cache flushes executed
* by the function. */
- xen_dma_map_page(hwdev, pfn_to_page(paddr >> PAGE_SHIFT),
- dev_addr,
- paddr & ~PAGE_MASK,
- sg->length,
- dir,
- attrs);
+ xen_dma_map_pfn(hwdev, pfn, dev_addr, offset,
+ sg->length, attrs);
sg->dma_address = dev_addr;
}
sg_dma_len(sg) = sg->length;
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index dc3a94ce3b45..78b136b0b139 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -67,6 +67,10 @@ extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size,
enum dma_data_direction dir,
struct dma_attrs *attrs);
+extern dma_addr_t swiotlb_map_pfn(struct device *dev, __pfn_t pfn,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs);
extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
size_t size, enum dma_data_direction dir,
struct dma_attrs *attrs);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 4abda074ea45..fc164041ec22 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -727,12 +727,12 @@ swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
* Once the device is given the dma address, the device owns this memory until
* either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
*/
-dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- struct dma_attrs *attrs)
+dma_addr_t swiotlb_map_pfn(struct device *dev, __pfn_t pfn,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
{
- phys_addr_t map, phys = page_to_phys(page) + offset;
+ phys_addr_t map, phys = pfn_to_phys(pfn) + offset;
dma_addr_t dev_addr = phys_to_dma(dev, phys);

BUG_ON(dir == DMA_NONE);
@@ -763,6 +763,16 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,

return dev_addr;
}
+EXPORT_SYMBOL_GPL(swiotlb_map_pfn);
+
+dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ return swiotlb_map_pfn(dev, page_to_pfn_typed(page), offset, size, dir,
+ attrs);
+}
EXPORT_SYMBOL_GPL(swiotlb_map_page);

/*

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/