swiotlb-xen cleanups

swiotlb-xen cleanups

[Christoph Hellwig]

Hi Xen maintainers and friends,

please take a look at this series that cleans up the parts of swiotlb-xen
that deal with non-coherent caches.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 01/11] xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance

[Christoph Hellwig]

Reuse the arm64 code that uses the dma-direct/swiotlb helpers for DMA
non-coherent devices.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/Kconfig                           |  4 +
 arch/arm/include/asm/device.h              |  3 -
 arch/arm/include/asm/xen/page-coherent.h   | 93 ----------------------
 arch/arm/mm/Kconfig                        |  4 -
 arch/arm/mm/dma-mapping.c                  |  8 +-
 arch/arm64/include/asm/xen/page-coherent.h | 75 -----------------
 drivers/xen/swiotlb-xen.c                  | 49 +-----------
 include/xen/arm/page-coherent.h            | 71 +++++++++++++++++
 8 files changed, 78 insertions(+), 229 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 33b00579beff..24360211534a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -7,6 +7,8 @@ config ARM
 	select ARCH_HAS_BINFMT_FLAT
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_DMA_COHERENT_TO_PFN if SWIOTLB
+	select ARCH_HAS_DMA_MMAP_PGPROT if SWIOTLB
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_KEEPINITRD
@@ -18,6 +20,8 @@ config ARM
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if SWIOTLB
+	select ARCH_HAS_SYNC_DMA_FOR_CPU if SWIOTLB
 	select ARCH_HAS_TEARDOWN_DMA_OPS if MMU
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
index f6955b55c544..c675bc0d5aa8 100644
--- a/arch/arm/include/asm/device.h
+++ b/arch/arm/include/asm/device.h
@@ -14,9 +14,6 @@ struct dev_archdata {
 #endif
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 	struct dma_iommu_mapping	*mapping;
-#endif
-#ifdef CONFIG_XEN
-	const struct dma_map_ops *dev_dma_ops;
 #endif
 	unsigned int dma_coherent:1;
 	unsigned int dma_ops_setup:1;
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index 2c403e7c782d..27e984977402 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/arch/arm/include/asm/xen/page-coherent.h
@@ -1,95 +1,2 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
-#define _ASM_ARM_XEN_PAGE_COHERENT_H
-
-#include <linux/dma-mapping.h>
-#include <asm/page.h>
 #include <xen/arm/page-coherent.h>
-
-static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
-{
-	if (dev && dev->archdata.dev_dma_ops)
-		return dev->archdata.dev_dma_ops;
-	return get_arch_dma_ops(NULL);
-}
-
-static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
-{
-	return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
-}
-
-static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
-{
-	xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
-}
-
-static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
-	     dma_addr_t dev_addr, unsigned long offset, size_t size,
-	     enum dma_data_direction dir, unsigned long attrs)
-{
-	unsigned long page_pfn = page_to_xen_pfn(page);
-	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
-	unsigned long compound_pages =
-		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
-	bool local = (page_pfn <= dev_pfn) &&
-		(dev_pfn - page_pfn < compound_pages);
-
-	/*
-	 * Dom0 is mapped 1:1, while the Linux page can span across
-	 * multiple Xen pages, it's not possible for it to contain a
-	 * mix of local and foreign Xen pages. So if the first xen_pfn
-	 * == mfn the page is local otherwise it's a foreign page
-	 * grant-mapped in dom0. If the page is local we can safely
-	 * call the native dma_ops function, otherwise we call the xen
-	 * specific function.
-	 */
-	if (local)
-		xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
-	else
-		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
-}
-
-static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-	/*
-	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * multiple Xen page, it's not possible to have a mix of local and
-	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
-	 * foreign mfn will always return false. If the page is local we can
-	 * safely call the native dma_ops function, otherwise we call the xen
-	 * specific function.
-	 */
-	if (pfn_valid(pfn)) {
-		if (xen_get_dma_ops(hwdev)->unmap_page)
-			xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
-	} else
-		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
-}
-
-static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-	if (pfn_valid(pfn)) {
-		if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
-			xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
-	} else
-		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
-}
-
-static inline void xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-	if (pfn_valid(pfn)) {
-		if (xen_get_dma_ops(hwdev)->sync_single_for_device)
-			xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
-	} else
-		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
-}
-
-#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index c54cd7ed90ba..c1222c0e9fd3 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -664,10 +664,6 @@ config ARM_LPAE
 		!CPU_32v4 && !CPU_32v3
 	select PHYS_ADDR_T_64BIT
 	select SWIOTLB
-	select ARCH_HAS_DMA_COHERENT_TO_PFN
-	select ARCH_HAS_DMA_MMAP_PGPROT
-	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	help
 	  Say Y if you have an ARMv7 processor supporting the LPAE page
 	  table format and you would like to access memory beyond the
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index d42557ee69c2..738097396445 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1132,10 +1132,6 @@ static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
 	 * 32-bit DMA.
 	 * Use the generic dma-direct / swiotlb ops code in that case, as that
 	 * handles bounce buffering for us.
-	 *
-	 * Note: this checks CONFIG_ARM_LPAE instead of CONFIG_SWIOTLB as the
-	 * latter is also selected by the Xen code, but that code for now relies
-	 * on non-NULL dev_dma_ops.  To be cleaned up later.
 	 */
 	if (IS_ENABLED(CONFIG_ARM_LPAE))
 		return NULL;
@@ -2363,10 +2359,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	set_dma_ops(dev, dma_ops);
 
 #ifdef CONFIG_XEN
-	if (xen_initial_domain()) {
-		dev->archdata.dev_dma_ops = dev->dma_ops;
+	if (xen_initial_domain())
 		dev->dma_ops = xen_dma_ops;
-	}
 #endif
 	dev->archdata.dma_ops_setup = true;
 }
diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
index d88e56b90b93..27e984977402 100644
--- a/arch/arm64/include/asm/xen/page-coherent.h
+++ b/arch/arm64/include/asm/xen/page-coherent.h
@@ -1,77 +1,2 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H
-#define _ASM_ARM64_XEN_PAGE_COHERENT_H
-
-#include <linux/dma-mapping.h>
-#include <asm/page.h>
 #include <xen/arm/page-coherent.h>
-
-static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
-{
-	return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
-}
-
-static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
-{
-	dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
-}
-
-static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-
-	if (pfn_valid(pfn))
-		dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
-	else
-		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
-}
-
-static inline void xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-	if (pfn_valid(pfn))
-		dma_direct_sync_single_for_device(hwdev, handle, size, dir);
-	else
-		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
-}
-
-static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
-	     dma_addr_t dev_addr, unsigned long offset, size_t size,
-	     enum dma_data_direction dir, unsigned long attrs)
-{
-	unsigned long page_pfn = page_to_xen_pfn(page);
-	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
-	unsigned long compound_pages =
-		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
-	bool local = (page_pfn <= dev_pfn) &&
-		(dev_pfn - page_pfn < compound_pages);
-
-	if (local)
-		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
-	else
-		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
-}
-
-static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-	/*
-	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * multiple Xen page, it's not possible to have a mix of local and
-	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
-	 * foreign mfn will always return false. If the page is local we can
-	 * safely call the native dma_ops function, otherwise we call the xen
-	 * specific function.
-	 */
-	if (pfn_valid(pfn))
-		dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
-	else
-		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
-}
-
-#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index ae1df496bf38..b8808677ae1d 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -547,51 +547,6 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
 	return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
 }
 
-/*
- * Create userspace mapping for the DMA-coherent memory.
- * This function should be called with the pages from the current domain only,
- * passing pages mapped from other domains would lead to memory corruption.
- */
-static int
-xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		     unsigned long attrs)
-{
-#ifdef CONFIG_ARM
-	if (xen_get_dma_ops(dev)->mmap)
-		return xen_get_dma_ops(dev)->mmap(dev, vma, cpu_addr,
-						    dma_addr, size, attrs);
-#endif
-	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
-
-/*
- * This function should be called with the pages from the current domain only,
- * passing pages mapped from other domains would lead to memory corruption.
- */
-static int
-xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
-			void *cpu_addr, dma_addr_t handle, size_t size,
-			unsigned long attrs)
-{
-#ifdef CONFIG_ARM
-	if (xen_get_dma_ops(dev)->get_sgtable) {
-#if 0
-	/*
-	 * This check verifies that the page belongs to the current domain and
-	 * is not one mapped from another domain.
-	 * This check is for debug only, and should not go to production build
-	 */
-		unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle));
-		BUG_ON (!page_is_ram(bfn));
-#endif
-		return xen_get_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
-							   handle, size, attrs);
-	}
-#endif
-	return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size, attrs);
-}
-
 const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.alloc = xen_swiotlb_alloc_coherent,
 	.free = xen_swiotlb_free_coherent,
@@ -604,6 +559,6 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.map_page = xen_swiotlb_map_page,
 	.unmap_page = xen_swiotlb_unmap_page,
 	.dma_supported = xen_swiotlb_dma_supported,
-	.mmap = xen_swiotlb_dma_mmap,
-	.get_sgtable = xen_swiotlb_get_sgtable,
+	.mmap = dma_common_mmap,
+	.get_sgtable = dma_common_get_sgtable,
 };
diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h
index 2ca9164a79bf..da2cc09c8eda 100644
--- a/include/xen/arm/page-coherent.h
+++ b/include/xen/arm/page-coherent.h
@@ -2,6 +2,9 @@
 #ifndef _XEN_ARM_PAGE_COHERENT_H
 #define _XEN_ARM_PAGE_COHERENT_H
 
+#include <linux/dma-mapping.h>
+#include <asm/page.h>
+
 void __xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, unsigned long attrs);
@@ -13,4 +16,72 @@ void __xen_dma_sync_single_for_cpu(struct device *hwdev,
 void __xen_dma_sync_single_for_device(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir);
 
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
+{
+	return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
+{
+	dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+
+	if (pfn_valid(pfn))
+		dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
+	else
+		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn))
+		dma_direct_sync_single_for_device(hwdev, handle, size, dir);
+	else
+		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
+	if (local)
+		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
+	else
+		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+	 * multiple Xen page, it's not possible to have a mix of local and
+	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+	 * foreign mfn will always return false. If the page is local we can
+	 * safely call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
+	if (pfn_valid(pfn))
+		dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
+	else
+		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
+
 #endif /* _XEN_ARM_PAGE_COHERENT_H */
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [Xen-devel] [PATCH 01/11] xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance

[Julien Grall]

Hi Christoph,

On 8/16/19 2:00 PM, Christoph Hellwig wrote:
> +static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
> +	     dma_addr_t dev_addr, unsigned long offset, size_t size,
> +	     enum dma_data_direction dir, unsigned long attrs)
> +{
> +	unsigned long page_pfn = page_to_xen_pfn(page);
> +	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
> +	unsigned long compound_pages =
> +		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
> +	bool local = (page_pfn <= dev_pfn) &&
> +		(dev_pfn - page_pfn < compound_pages);
> +

The Arm version as a comment here. Could we retain it?

> +	if (local)
> +		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
> +	else
> +		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
> +}
> +

Cheers,

-- 
Julien Grall
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [Xen-devel] [PATCH 01/11] xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance

[Christoph Hellwig]

On Mon, Aug 19, 2019 at 12:45:17PM +0100, Julien Grall wrote:
> On 8/16/19 2:00 PM, Christoph Hellwig wrote:
>> +static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
>> +	     dma_addr_t dev_addr, unsigned long offset, size_t size,
>> +	     enum dma_data_direction dir, unsigned long attrs)
>> +{
>> +	unsigned long page_pfn = page_to_xen_pfn(page);
>> +	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
>> +	unsigned long compound_pages =
>> +		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
>> +	bool local = (page_pfn <= dev_pfn) &&
>> +		(dev_pfn - page_pfn < compound_pages);
>> +
>
> The Arm version as a comment here. Could we retain it?

I've added it in this patch, altough the rewrites later on mean it will
go away in favour of a new comment elsewhere anyway.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 02/11] xen/arm: use dev_is_dma_coherent

[Christoph Hellwig]

Use the dma-noncoherent dev_is_dma_coherent helper instead of the home
grown variant.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/include/asm/dma-mapping.h   |  6 ------
 arch/arm/xen/mm.c                    | 12 ++++++------
 arch/arm64/include/asm/dma-mapping.h |  9 ---------
 3 files changed, 6 insertions(+), 21 deletions(-)

diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index dba9355e2484..bdd80ddbca34 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -91,12 +91,6 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 }
 #endif
 
-/* do not use this function in a driver */
-static inline bool is_device_dma_coherent(struct device *dev)
-{
-	return dev->archdata.dma_coherent;
-}
-
 /**
  * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index d33b77e9add3..90574d89d0d4 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/cpu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
@@ -99,7 +99,7 @@ void __xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, unsigned long attrs)
 {
-	if (is_device_dma_coherent(hwdev))
+	if (dev_is_dma_coherent(hwdev))
 		return;
 	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
 		return;
@@ -112,7 +112,7 @@ void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 		unsigned long attrs)
 
 {
-	if (is_device_dma_coherent(hwdev))
+	if (dev_is_dma_coherent(hwdev))
 		return;
 	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
 		return;
@@ -123,7 +123,7 @@ void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 void __xen_dma_sync_single_for_cpu(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	if (is_device_dma_coherent(hwdev))
+	if (dev_is_dma_coherent(hwdev))
 		return;
 	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
 }
@@ -131,7 +131,7 @@ void __xen_dma_sync_single_for_cpu(struct device *hwdev,
 void __xen_dma_sync_single_for_device(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	if (is_device_dma_coherent(hwdev))
+	if (dev_is_dma_coherent(hwdev))
 		return;
 	__xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
 }
@@ -159,7 +159,7 @@ bool xen_arch_need_swiotlb(struct device *dev,
 	 * memory and we are not able to flush the cache.
 	 */
 	return (!hypercall_cflush && (xen_pfn != bfn) &&
-		!is_device_dma_coherent(dev));
+		!dev_is_dma_coherent(dev));
 }
 
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index bdcb0922a40c..67243255a858 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -18,14 +18,5 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return NULL;
 }
 
-/*
- * Do not use this function in a driver, it is only provided for
- * arch/arm/mm/xen.c, which is used by arm64 as well.
- */
-static inline bool is_device_dma_coherent(struct device *dev)
-{
-	return dev->dma_coherent;
-}
-
 #endif	/* __KERNEL__ */
 #endif	/* __ASM_DMA_MAPPING_H */
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [Xen-devel] [PATCH 02/11] xen/arm: use dev_is_dma_coherent

[Julien Grall]

Hi Christoph,

On 8/16/19 2:00 PM, Christoph Hellwig wrote:
> Use the dma-noncoherent dev_is_dma_coherent helper instead of the home
> grown variant.

It took me a bit of time to understand that dev->archdata.dma_coherent 
and dev->dma_coherent will always contain the same value.

Would you mind it mention it in the commit message?

Other than that:

Reviewed-by: Julien Grall <julien.grall@arm.com>

> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Cheers,

-- 
Julien Grall
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 03/11] xen/arm: pass one less argument to dma_cache_maint

[Christoph Hellwig]

Instead of taking apart the dma address in both callers do it inside
dma_cache_maint itself.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/xen/mm.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 90574d89d0d4..d9da24fda2f7 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -43,13 +43,15 @@ static bool hypercall_cflush = false;
 
 /* functions called by SWIOTLB */
 
-static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
-	size_t size, enum dma_data_direction dir, enum dma_cache_op op)
+static void dma_cache_maint(dma_addr_t handle, size_t size,
+		enum dma_data_direction dir, enum dma_cache_op op)
 {
 	struct gnttab_cache_flush cflush;
 	unsigned long xen_pfn;
+	unsigned long offset = handle & ~PAGE_MASK;
 	size_t left = size;
 
+	offset &= PAGE_MASK;
 	xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
 	offset %= XEN_PAGE_SIZE;
 
@@ -86,13 +88,13 @@ static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
 static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
+	dma_cache_maint(handle, size, dir, DMA_UNMAP);
 }
 
 static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
+	dma_cache_maint(handle, size, dir, DMA_MAP);
 }
 
 void __xen_dma_map_page(struct device *hwdev, struct page *page,
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [PATCH 03/11] xen/arm: pass one less argument to dma_cache_maint

[Robin Murphy]

On 16/08/2019 14:00, Christoph Hellwig wrote:
> Instead of taking apart the dma address in both callers do it inside
> dma_cache_maint itself.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>   arch/arm/xen/mm.c | 10 ++++++----
>   1 file changed, 6 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
> index 90574d89d0d4..d9da24fda2f7 100644
> --- a/arch/arm/xen/mm.c
> +++ b/arch/arm/xen/mm.c
> @@ -43,13 +43,15 @@ static bool hypercall_cflush = false;
>   
>   /* functions called by SWIOTLB */
>   
> -static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
> -	size_t size, enum dma_data_direction dir, enum dma_cache_op op)
> +static void dma_cache_maint(dma_addr_t handle, size_t size,
> +		enum dma_data_direction dir, enum dma_cache_op op)
>   {
>   	struct gnttab_cache_flush cflush;
>   	unsigned long xen_pfn;
> +	unsigned long offset = handle & ~PAGE_MASK;
>   	size_t left = size;
>   
> +	offset &= PAGE_MASK;

Ahem... presumably that should be handle, not offset.

Robin.

>   	xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
>   	offset %= XEN_PAGE_SIZE;
>   
> @@ -86,13 +88,13 @@ static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
>   static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
>   		size_t size, enum dma_data_direction dir)
>   {
> -	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
> +	dma_cache_maint(handle, size, dir, DMA_UNMAP);
>   }
>   
>   static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
>   		size_t size, enum dma_data_direction dir)
>   {
> -	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
> +	dma_cache_maint(handle, size, dir, DMA_MAP);
>   }
>   
>   void __xen_dma_map_page(struct device *hwdev, struct page *page,
> 
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [PATCH 03/11] xen/arm: pass one less argument to dma_cache_maint

[Christoph Hellwig]

On Fri, Aug 16, 2019 at 02:37:58PM +0100, Robin Murphy wrote:
> On 16/08/2019 14:00, Christoph Hellwig wrote:
>> Instead of taking apart the dma address in both callers do it inside
>> dma_cache_maint itself.
>>
>> Signed-off-by: Christoph Hellwig <hch@lst.de>
>> ---
>>   arch/arm/xen/mm.c | 10 ++++++----
>>   1 file changed, 6 insertions(+), 4 deletions(-)
>>
>> diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
>> index 90574d89d0d4..d9da24fda2f7 100644
>> --- a/arch/arm/xen/mm.c
>> +++ b/arch/arm/xen/mm.c
>> @@ -43,13 +43,15 @@ static bool hypercall_cflush = false;
>>     /* functions called by SWIOTLB */
>>   -static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
>> -	size_t size, enum dma_data_direction dir, enum dma_cache_op op)
>> +static void dma_cache_maint(dma_addr_t handle, size_t size,
>> +		enum dma_data_direction dir, enum dma_cache_op op)
>>   {
>>   	struct gnttab_cache_flush cflush;
>>   	unsigned long xen_pfn;
>> +	unsigned long offset = handle & ~PAGE_MASK;
>>   	size_t left = size;
>>   +	offset &= PAGE_MASK;
>
> Ahem... presumably that should be handle, not offset.

Ooops, yes.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 04/11] xen/arm: remove xen_dma_ops

[Christoph Hellwig]

arm and arm64 can just use xen_swiotlb_dma_ops directly like x86, no
need for a pointer indirection.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/mm/dma-mapping.c    | 3 ++-
 arch/arm/xen/mm.c            | 4 ----
 arch/arm64/mm/dma-mapping.c  | 3 ++-
 include/xen/arm/hypervisor.h | 2 --
 4 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 738097396445..2661cad36359 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -35,6 +35,7 @@
 #include <asm/mach/map.h>
 #include <asm/system_info.h>
 #include <asm/dma-contiguous.h>
+#include <xen/swiotlb-xen.h>
 
 #include "dma.h"
 #include "mm.h"
@@ -2360,7 +2361,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 
 #ifdef CONFIG_XEN
 	if (xen_initial_domain())
-		dev->dma_ops = xen_dma_ops;
+		dev->dma_ops = &xen_swiotlb_dma_ops;
 #endif
 	dev->archdata.dma_ops_setup = true;
 }
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index d9da24fda2f7..388a45002bad 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -183,16 +183,12 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 }
 EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
 
-const struct dma_map_ops *xen_dma_ops;
-EXPORT_SYMBOL(xen_dma_ops);
-
 int __init xen_mm_init(void)
 {
 	struct gnttab_cache_flush cflush;
 	if (!xen_initial_domain())
 		return 0;
 	xen_swiotlb_init(1, false);
-	xen_dma_ops = &xen_swiotlb_dma_ops;
 
 	cflush.op = 0;
 	cflush.a.dev_bus_addr = 0;
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index bd2b039f43a6..4b244a037349 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -8,6 +8,7 @@
 #include <linux/cache.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-iommu.h>
+#include <xen/swiotlb-xen.h>
 
 #include <asm/cacheflush.h>
 
@@ -64,6 +65,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 
 #ifdef CONFIG_XEN
 	if (xen_initial_domain())
-		dev->dma_ops = xen_dma_ops;
+		dev->dma_ops = &xen_swiotlb_dma_ops;
 #endif
 }
diff --git a/include/xen/arm/hypervisor.h b/include/xen/arm/hypervisor.h
index 2982571f7cc1..43ef24dd030e 100644
--- a/include/xen/arm/hypervisor.h
+++ b/include/xen/arm/hypervisor.h
@@ -19,8 +19,6 @@ static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return PARAVIRT_LAZY_NONE;
 }
 
-extern const struct dma_map_ops *xen_dma_ops;
-
 #ifdef CONFIG_XEN
 void __init xen_early_init(void);
 #else
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [Xen-devel] [PATCH 04/11] xen/arm: remove xen_dma_ops

[Julien Grall]

Hi Christoph,

On 8/16/19 2:00 PM, Christoph Hellwig wrote:
> arm and arm64 can just use xen_swiotlb_dma_ops directly like x86, no
> need for a pointer indirection.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Reviewed-by: Julien Grall <julien.grall@arm.com>

Cheers,

-- 
Julien Grall
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 05/11] xen: remove the exports for xen_{create, destroy}_contiguous_region

[Christoph Hellwig]

These routines are only used by swiotlb-xen, which cannot be modular.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/xen/mm.c     | 2 --
 arch/x86/xen/mmu_pv.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 388a45002bad..a59980f1aa54 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -175,13 +175,11 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 	*dma_handle = pstart;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
 
 void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 {
 	return;
 }
-EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
 
 int __init xen_mm_init(void)
 {
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 26e8b326966d..c8dbee62ec2a 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2625,7 +2625,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 	*dma_handle = virt_to_machine(vstart).maddr;
 	return success ? 0 : -ENOMEM;
 }
-EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
 
 void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 {
@@ -2660,7 +2659,6 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 
 	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 }
-EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);
 
 static noinline void xen_flush_tlb_all(void)
 {
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 06/11] swiotlb-xen: always use dma-direct helpers to alloc coherent pages

[Christoph Hellwig]

x86 currently calls alloc_pages, but using dma-direct works as well
there, with the added benefit of using the CMA pool if available.
The biggest advantage is of course to remove a pointless bit of
architecture specific code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/x86/include/asm/xen/page-coherent.h | 16 ----------------
 drivers/xen/swiotlb-xen.c                |  7 +++----
 include/xen/arm/page-coherent.h          | 12 ------------
 3 files changed, 3 insertions(+), 32 deletions(-)

diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h
index 116777e7f387..8ee33c5edded 100644
--- a/arch/x86/include/asm/xen/page-coherent.h
+++ b/arch/x86/include/asm/xen/page-coherent.h
@@ -5,22 +5,6 @@
 #include <asm/page.h>
 #include <linux/dma-mapping.h>
 
-static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flags,
-		unsigned long attrs)
-{
-	void *vstart = (void*)__get_free_pages(flags, get_order(size));
-	*dma_handle = virt_to_phys(vstart);
-	return vstart;
-}
-
-static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle,
-		unsigned long attrs)
-{
-	free_pages((unsigned long) cpu_addr, get_order(size));
-}
-
 static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, unsigned long attrs) { }
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index b8808677ae1d..f9dd4cb6e4b3 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -299,8 +299,7 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	 * address. In fact on ARM virt_to_phys only works for kernel direct
 	 * mapped RAM memory. Also see comment below.
 	 */
-	ret = xen_alloc_coherent_pages(hwdev, size, dma_handle, flags, attrs);
-
+	ret = dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
 	if (!ret)
 		return ret;
 
@@ -319,7 +318,7 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	else {
 		if (xen_create_contiguous_region(phys, order,
 						 fls64(dma_mask), dma_handle) != 0) {
-			xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
+			dma_direct_free(hwdev, size, ret, (dma_addr_t)phys, attrs);
 			return NULL;
 		}
 		SetPageXenRemapped(virt_to_page(ret));
@@ -351,7 +350,7 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	    TestClearPageXenRemapped(virt_to_page(vaddr)))
 		xen_destroy_contiguous_region(phys, order);
 
-	xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
+	dma_direct_free(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
 }
 
 /*
diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h
index da2cc09c8eda..4294a31305ca 100644
--- a/include/xen/arm/page-coherent.h
+++ b/include/xen/arm/page-coherent.h
@@ -16,18 +16,6 @@ void __xen_dma_sync_single_for_cpu(struct device *hwdev,
 void __xen_dma_sync_single_for_device(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir);
 
-static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
-{
-	return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
-}
-
-static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
-{
-	dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
-}
-
 static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 07/11] swiotlb-xen: provide a single page-coherent.h header

[Christoph Hellwig]

Merge the various page-coherent.h files into a single one that either
provides prototypes or stubs depending on the need for cache
maintainance.

For extra benefits alo include <xen/page-coherent.h> in the file
actually implementing the interfaces provided.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/include/asm/xen/page-coherent.h   |  2 --
 arch/arm/xen/mm.c                          |  1 +
 arch/arm64/include/asm/xen/page-coherent.h |  2 --
 arch/x86/include/asm/xen/page-coherent.h   | 22 ------------------
 drivers/xen/swiotlb-xen.c                  |  4 +---
 include/Kbuild                             |  2 +-
 include/xen/{arm => }/page-coherent.h      | 27 +++++++++++++++++++---
 7 files changed, 27 insertions(+), 33 deletions(-)
 delete mode 100644 arch/arm/include/asm/xen/page-coherent.h
 delete mode 100644 arch/arm64/include/asm/xen/page-coherent.h
 delete mode 100644 arch/x86/include/asm/xen/page-coherent.h
 rename include/xen/{arm => }/page-coherent.h (76%)

diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
deleted file mode 100644
index 27e984977402..000000000000
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <xen/arm/page-coherent.h>
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index a59980f1aa54..85482cdda1e5 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -15,6 +15,7 @@
 #include <xen/interface/grant_table.h>
 #include <xen/interface/memory.h>
 #include <xen/page.h>
+#include <xen/page-coherent.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
deleted file mode 100644
index 27e984977402..000000000000
--- a/arch/arm64/include/asm/xen/page-coherent.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <xen/arm/page-coherent.h>
diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h
deleted file mode 100644
index 8ee33c5edded..000000000000
--- a/arch/x86/include/asm/xen/page-coherent.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_XEN_PAGE_COHERENT_H
-#define _ASM_X86_XEN_PAGE_COHERENT_H
-
-#include <asm/page.h>
-#include <linux/dma-mapping.h>
-
-static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
-	     dma_addr_t dev_addr, unsigned long offset, size_t size,
-	     enum dma_data_direction dir, unsigned long attrs) { }
-
-static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs) { }
-
-static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
-
-static inline void xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
-
-#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index f9dd4cb6e4b3..7b23929854e7 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -31,12 +31,10 @@
 #include <linux/export.h>
 #include <xen/swiotlb-xen.h>
 #include <xen/page.h>
+#include <xen/page-coherent.h>
 #include <xen/xen-ops.h>
 #include <xen/hvc-console.h>
 
-#include <asm/dma-mapping.h>
-#include <asm/xen/page-coherent.h>
-
 #include <trace/events/swiotlb.h>
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
diff --git a/include/Kbuild b/include/Kbuild
index c38f0d46b267..e2ae52ef9e1e 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -1189,7 +1189,6 @@ header-test-			+= video/vga.h
 header-test-			+= video/w100fb.h
 header-test-			+= xen/acpi.h
 header-test-			+= xen/arm/hypercall.h
-header-test-			+= xen/arm/page-coherent.h
 header-test-			+= xen/arm/page.h
 header-test-			+= xen/balloon.h
 header-test-			+= xen/events.h
@@ -1231,6 +1230,7 @@ header-test-			+= xen/interface/xen.h
 header-test-			+= xen/interface/xenpmu.h
 header-test-			+= xen/mem-reservation.h
 header-test-			+= xen/page.h
+header-test-			+= xen/page-coherent.h
 header-test-			+= xen/platform_pci.h
 header-test-			+= xen/swiotlb-xen.h
 header-test-			+= xen/xen-front-pgdir-shbuf.h
diff --git a/include/xen/arm/page-coherent.h b/include/xen/page-coherent.h
similarity index 76%
rename from include/xen/arm/page-coherent.h
rename to include/xen/page-coherent.h
index 4294a31305ca..7c32944de051 100644
--- a/include/xen/arm/page-coherent.h
+++ b/include/xen/page-coherent.h
@@ -1,10 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XEN_ARM_PAGE_COHERENT_H
-#define _XEN_ARM_PAGE_COHERENT_H
+#ifndef _XEN_PAGE_COHERENT_H
+#define _XEN_PAGE_COHERENT_H
 
 #include <linux/dma-mapping.h>
 #include <asm/page.h>
 
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU)
 void __xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, unsigned long attrs);
@@ -71,5 +73,24 @@ static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 	else
 		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
 }
+#else
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, unsigned long attrs)
+{
+}
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+}
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+}
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+}
+#endif
 
-#endif /* _XEN_ARM_PAGE_COHERENT_H */
+#endif /* _XEN_PAGE_COHERENT_H */
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [Xen-devel] [PATCH 07/11] swiotlb-xen: provide a single page-coherent.h header

[Julien Grall]

Hi,

On 8/16/19 2:00 PM, Christoph Hellwig wrote:
> Merge the various page-coherent.h files into a single one that either
> provides prototypes or stubs depending on the need for cache
> maintainance.
> 
> For extra benefits alo include <xen/page-coherent.h> in the file
> actually implementing the interfaces provided.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>   arch/arm/include/asm/xen/page-coherent.h   |  2 --
>   arch/arm/xen/mm.c                          |  1 +
>   arch/arm64/include/asm/xen/page-coherent.h |  2 --
>   arch/x86/include/asm/xen/page-coherent.h   | 22 ------------------
>   drivers/xen/swiotlb-xen.c                  |  4 +---
>   include/Kbuild                             |  2 +-
>   include/xen/{arm => }/page-coherent.h      | 27 +++++++++++++++++++---

I am not sure I agree with this rename. The implementation of the 
helpers are very Arm specific as this is assuming Dom0 is 1:1 mapped.

This was necessary due to the lack of IOMMU on Arm platforms back then.
But this is now a pain to get rid of it on newer platform...

Cheers,

-- 
Julien Grall
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [Xen-devel] [PATCH 07/11] swiotlb-xen: provide a single page-coherent.h header

[Christoph Hellwig]

On Fri, Aug 16, 2019 at 11:40:43PM +0100, Julien Grall wrote:
> I am not sure I agree with this rename. The implementation of the helpers 
> are very Arm specific as this is assuming Dom0 is 1:1 mapped.
>
> This was necessary due to the lack of IOMMU on Arm platforms back then.
> But this is now a pain to get rid of it on newer platform...

So if you look at the final version of the header after the whole
series, what assumes a 1:1 mapping?  It all just is

	if (pfn_valid())
		local cache sync;
	else
		call into the arch code;

are you concerned that the local cache sync might have to be split
up more for a non-1:1 map in that case?  We could just move
the xen_dma_* routines into the arch instead of __xen_dma, but it
really helps to have a common interface header.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [Xen-devel] [PATCH 07/11] swiotlb-xen: provide a single page-coherent.h header

[Julien Grall]

Hi Christoph,

On 8/17/19 7:50 AM, Christoph Hellwig wrote:
> On Fri, Aug 16, 2019 at 11:40:43PM +0100, Julien Grall wrote:
>> I am not sure I agree with this rename. The implementation of the helpers
>> are very Arm specific as this is assuming Dom0 is 1:1 mapped.
>>
>> This was necessary due to the lack of IOMMU on Arm platforms back then.
>> But this is now a pain to get rid of it on newer platform...
> 
> So if you look at the final version of the header after the whole
> series, what assumes a 1:1 mapping?  It all just is
> 
> 	if (pfn_valid())
> 		local cache sync;
> 	else
> 		call into the arch code;

In the context of Xen Arm, the dev_addr is a host physical address. From 
my understanding pfn_valid() is dealing with a guest physical frame.

Therefore by passing PFN_DOWN(dev_addr) in argument you assume that the 
host and guest address spaces are the same.

> 
> are you concerned that the local cache sync might have to be split
> up more for a non-1:1 map in that case?  We could just movea
> the xen_dma_* routines into the arch instead of __xen_dma, but it
> really helps to have a common interface header.
Moving xen_dma_* routines into the arch would be a good option. 
Although, I would still consider a stub version for arch not requiring 
specific DMA.

Cheers,

-- 
Julien Grall

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 08/11] swiotlb-xen: use the same foreign page check everywhere

[Christoph Hellwig]

xen_dma_map_page uses a different and more complicated check for
foreign pages than the other three cache maintainance helpers.
Switch it to the simpler pfn_vali method a well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/xen/page-coherent.h | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/include/xen/page-coherent.h b/include/xen/page-coherent.h
index 7c32944de051..0f4d468e7a89 100644
--- a/include/xen/page-coherent.h
+++ b/include/xen/page-coherent.h
@@ -43,14 +43,9 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, unsigned long attrs)
 {
-	unsigned long page_pfn = page_to_xen_pfn(page);
-	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
-	unsigned long compound_pages =
-		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
-	bool local = (page_pfn <= dev_pfn) &&
-		(dev_pfn - page_pfn < compound_pages);
+	unsigned long pfn = PFN_DOWN(dev_addr);
 
-	if (local)
+	if (pfn_valid(pfn))
 		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
 	else
 		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [Xen-devel] [PATCH 08/11] swiotlb-xen: use the same foreign page check everywhere

[Julien Grall]

Hi Christoph,

On 8/16/19 2:00 PM, Christoph Hellwig wrote:
> xen_dma_map_page uses a different and more complicated check for
> foreign pages than the other three cache maintainance helpers.
> Switch it to the simpler pfn_vali method a well.

NIT: s/pfn_vali/pfn_valid/

> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Reviewed-by: Julien Grall <julien.grall@arm.com>

Cheers,

-- 
Julien Grall
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 09/11] swiotlb-xen: simplify cache maintainance

[Christoph Hellwig]

Now that we know we always have the dma-noncoherent.h helpers available
if we are on an architecture with support for non-coherent devices,
we can just call them directly, and remove the calls to the dma-direct
routines, including the fact that we call the dma_direct_map_page
routines but ignore the value returned from it.  Instead we now have
Xen wrappers for the arch_sync_dma_for_{device,cpu} helpers that call
the special Xen versions of those routines for foreign pages.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/xen/mm.c           |  47 ++---------------
 drivers/xen/swiotlb-xen.c   |  19 ++++---
 include/xen/page-coherent.h | 100 +++++++++++-------------------------
 3 files changed, 42 insertions(+), 124 deletions(-)

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 85482cdda1e5..0eb88f1355c2 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -86,59 +86,18 @@ static void dma_cache_maint(dma_addr_t handle, size_t size,
 	} while (left);
 }
 
-static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
+void __xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, size_t size,
+		enum dma_data_direction dir)
 {
 	dma_cache_maint(handle, size, dir, DMA_UNMAP);
 }
 
-static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
+void __xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir)
 {
 	dma_cache_maint(handle, size, dir, DMA_MAP);
 }
 
-void __xen_dma_map_page(struct device *hwdev, struct page *page,
-	     dma_addr_t dev_addr, unsigned long offset, size_t size,
-	     enum dma_data_direction dir, unsigned long attrs)
-{
-	if (dev_is_dma_coherent(hwdev))
-		return;
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	__xen_dma_page_cpu_to_dev(hwdev, dev_addr, size, dir);
-}
-
-void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-
-{
-	if (dev_is_dma_coherent(hwdev))
-		return;
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
-}
-
-void __xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	if (dev_is_dma_coherent(hwdev))
-		return;
-	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
-}
-
-void __xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	if (dev_is_dma_coherent(hwdev))
-		return;
-	__xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
-}
-
 bool xen_arch_need_swiotlb(struct device *dev,
 			   phys_addr_t phys,
 			   dma_addr_t dev_addr)
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 7b23929854e7..c3c383033ae4 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -388,6 +388,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
+	phys = map;
 	dev_addr = xen_phys_to_bus(map);
 
 	/*
@@ -399,14 +400,9 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 		return DMA_MAPPING_ERROR;
 	}
 
-	page = pfn_to_page(map >> PAGE_SHIFT);
-	offset = map & ~PAGE_MASK;
 done:
-	/*
-	 * 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(dev, page, dev_addr, offset, size, dir, attrs);
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		xen_dma_sync_for_device(dev, dev_addr, phys, size, dir);
 	return dev_addr;
 }
 
@@ -426,7 +422,8 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs);
+	if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		xen_dma_sync_for_cpu(hwdev, dev_addr, paddr, size, dir);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr))
@@ -446,7 +443,8 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
 {
 	phys_addr_t paddr = xen_bus_to_phys(dma_addr);
 
-	xen_dma_sync_single_for_cpu(dev, dma_addr, size, dir);
+	if (!dev_is_dma_coherent(dev))
+		xen_dma_sync_for_cpu(dev, dma_addr, paddr, size, dir);
 
 	if (is_xen_swiotlb_buffer(dma_addr))
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
@@ -461,7 +459,8 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
 	if (is_xen_swiotlb_buffer(dma_addr))
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
 
-	xen_dma_sync_single_for_device(dev, dma_addr, size, dir);
+	if (!dev_is_dma_coherent(dev))
+		xen_dma_sync_for_device(dev, dma_addr, paddr, size, dir);
 }
 
 /*
diff --git a/include/xen/page-coherent.h b/include/xen/page-coherent.h
index 0f4d468e7a89..38b572ed0879 100644
--- a/include/xen/page-coherent.h
+++ b/include/xen/page-coherent.h
@@ -2,88 +2,48 @@
 #ifndef _XEN_PAGE_COHERENT_H
 #define _XEN_PAGE_COHERENT_H
 
-#include <linux/dma-mapping.h>
-#include <asm/page.h>
+#include <linux/dma-noncoherent.h>
 
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU)
-void __xen_dma_map_page(struct device *hwdev, struct page *page,
-	     dma_addr_t dev_addr, unsigned long offset, size_t size,
-	     enum dma_data_direction dir, unsigned long attrs);
-void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs);
-void __xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir);
-void __xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir);
-
-static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-
-	if (pfn_valid(pfn))
-		dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
-	else
-		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
-}
-
-static inline void xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-	if (pfn_valid(pfn))
-		dma_direct_sync_single_for_device(hwdev, handle, size, dir);
-	else
-		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
-}
-
-static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
-	     dma_addr_t dev_addr, unsigned long offset, size_t size,
-	     enum dma_data_direction dir, unsigned long attrs)
-{
-	unsigned long pfn = PFN_DOWN(dev_addr);
-
-	if (pfn_valid(pfn))
-		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
+/*
+ * Dom0 is mapped 1:1, while the Linux page can be spanned accross multiple Xen
+ * pages, it's not possible to have a mix of local and foreign Xen page.  Dom0
+ * is mapped 1:1, so calling pfn_valid on a foreign mfn will always return
+ * false.  If the page is local we can safely use the native routines for cache
+ * maintainance, otherwise we call the Xen specific function.
+ */
+void __xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, size_t size,
+		enum dma_data_direction dir);
+void __xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir);
+
+static inline void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
+		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+{
+	if (pfn_valid(PFN_DOWN(handle)))
+		arch_sync_dma_for_cpu(dev, paddr, size, dir);
 	else
-		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+		__xen_dma_sync_for_cpu(dev, handle, size, dir);
 }
 
-static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
+static inline void xen_dma_sync_for_device(struct device *dev,
+		dma_addr_t handle, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	unsigned long pfn = PFN_DOWN(handle);
-	/*
-	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * multiple Xen page, it's not possible to have a mix of local and
-	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
-	 * foreign mfn will always return false. If the page is local we can
-	 * safely call the native dma_ops function, otherwise we call the xen
-	 * specific function.
-	 */
-	if (pfn_valid(pfn))
-		dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
+	if (pfn_valid(PFN_DOWN(handle)))
+		arch_sync_dma_for_device(dev, paddr, size, dir);
 	else
-		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+		__xen_dma_sync_for_device(dev, handle, size, dir);
 }
 #else
-static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
-	     dma_addr_t dev_addr, unsigned long offset, size_t size,
-	     enum dma_data_direction dir, unsigned long attrs)
-{
-}
-static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-}
-static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+static inline void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
+		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
 {
 }
-static inline void xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+static inline void xen_dma_sync_for_device(struct device *dev,
+		dma_addr_t handle, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 }
 #endif
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 10/11] swiotlb-xen: merge xen_unmap_single into xen_swiotlb_unmap_page

[Christoph Hellwig]

No need for a no-op wrapper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/xen/swiotlb-xen.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index c3c383033ae4..b6b9c4c1b397 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -414,9 +414,8 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
  * After this call, reads by the cpu to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
-static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
-			     size_t size, enum dma_data_direction dir,
-			     unsigned long attrs)
+static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	phys_addr_t paddr = xen_bus_to_phys(dev_addr);
 
@@ -430,13 +429,6 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
 }
 
-static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
-			    size_t size, enum dma_data_direction dir,
-			    unsigned long attrs)
-{
-	xen_unmap_single(hwdev, dev_addr, size, dir, attrs);
-}
-
 static void
 xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
 		size_t size, enum dma_data_direction dir)
@@ -477,7 +469,8 @@ xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i)
-		xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs);
+		xen_swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg),
+				dir, attrs);
 
 }
 
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 11/11] arm64: use asm-generic/dma-mapping.h

[Christoph Hellwig]

Now that the Xen special cases are gone nothing worth mentioning is
left in the arm64 <asm/dma-mapping.h> file, so switch to use the
asm-generic version instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm64/include/asm/Kbuild        |  1 +
 arch/arm64/include/asm/dma-mapping.h | 22 ----------------------
 arch/arm64/mm/dma-mapping.c          |  1 +
 3 files changed, 2 insertions(+), 22 deletions(-)
 delete mode 100644 arch/arm64/include/asm/dma-mapping.h

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index c52e151afab0..98a5405c8558 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -4,6 +4,7 @@ generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
 generic-y += dma-contiguous.h
+generic-y += dma-mapping.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += hw_irq.h
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
deleted file mode 100644
index 67243255a858..000000000000
--- a/arch/arm64/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2012 ARM Ltd.
- */
-#ifndef __ASM_DMA_MAPPING_H
-#define __ASM_DMA_MAPPING_H
-
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-#include <linux/vmalloc.h>
-
-#include <xen/xen.h>
-#include <asm/xen/hypervisor.h>
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return NULL;
-}
-
-#endif	/* __KERNEL__ */
-#endif	/* __ASM_DMA_MAPPING_H */
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 4b244a037349..6578abcfbbc7 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -8,6 +8,7 @@
 #include <linux/cache.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-iommu.h>
+#include <xen/xen.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/cacheflush.h>
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [PATCH 11/11] arm64: use asm-generic/dma-mapping.h

[Will Deacon]

On Fri, Aug 16, 2019 at 03:00:13PM +0200, Christoph Hellwig wrote:
> Now that the Xen special cases are gone nothing worth mentioning is
> left in the arm64 <asm/dma-mapping.h> file, so switch to use the
> asm-generic version instead.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  arch/arm64/include/asm/Kbuild        |  1 +
>  arch/arm64/include/asm/dma-mapping.h | 22 ----------------------
>  arch/arm64/mm/dma-mapping.c          |  1 +
>  3 files changed, 2 insertions(+), 22 deletions(-)
>  delete mode 100644 arch/arm64/include/asm/dma-mapping.h

Acked-by: Will Deacon <will@kernel.org>

Thanks for cleaning this up.

Will
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: swiotlb-xen cleanups

[Stefano Stabellini]

On Fri, 16 Aug 2019, Christoph Hellwig wrote:
> Hi Xen maintainers and friends,
> 
> please take a look at this series that cleans up the parts of swiotlb-xen
> that deal with non-coherent caches.

Hi Christoph,

I just wanted to let you know that your series is on my radar, but I
have been swamped the last few days. I hope to get to it by the end of
the week.

Cheers,

Stefano
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: swiotlb-xen cleanups

[Christoph Hellwig]

On Mon, Aug 26, 2019 at 07:00:44PM -0700, Stefano Stabellini wrote:
> On Fri, 16 Aug 2019, Christoph Hellwig wrote:
> > Hi Xen maintainers and friends,
> > 
> > please take a look at this series that cleans up the parts of swiotlb-xen
> > that deal with non-coherent caches.
> 
> Hi Christoph,
> 
> I just wanted to let you know that your series is on my radar, but I
> have been swamped the last few days. I hope to get to it by the end of
> the week.

Thanks, and no rush.  Note that I posted a v2 with a few significant
changes yesterday.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

swiotlb-xen cleanups v4

[Christoph Hellwig]

Hi Xen maintainers and friends,

please take a look at this series that cleans up the parts of swiotlb-xen
that deal with non-coherent caches.


Changes since v3:
 - don't use dma_direct_alloc on x86

Changes since v2:
 - further dma_cache_maint improvements
 - split the previous patch 1 into 3 patches

Changes since v1:
 - rewrite dma_cache_maint to be much simpler
 - improve various comments and commit logs
 - remove page-coherent.h entirely
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 08/11] swiotlb-xen: use the same foreign page check everywhere

[Christoph Hellwig]

xen_dma_map_page uses a different and more complicated check for foreign
pages than the other three cache maintainance helpers.  Switch it to the
simpler pfn_valid method a well, and document the scheme with a single
improved comment in xen_dma_map_page.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
---
 include/xen/arm/page-coherent.h | 31 +++++++++----------------------
 1 file changed, 9 insertions(+), 22 deletions(-)

diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h
index a840d6949a87..a8d9c0678c27 100644
--- a/include/xen/arm/page-coherent.h
+++ b/include/xen/arm/page-coherent.h
@@ -53,23 +53,17 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, unsigned long attrs)
 {
-	unsigned long page_pfn = page_to_xen_pfn(page);
-	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
-	unsigned long compound_pages =
-		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
-	bool local = (page_pfn <= dev_pfn) &&
-		(dev_pfn - page_pfn < compound_pages);
+	unsigned long pfn = PFN_DOWN(dev_addr);
 
 	/*
-	 * Dom0 is mapped 1:1, while the Linux page can span across
-	 * multiple Xen pages, it's not possible for it to contain a
-	 * mix of local and foreign Xen pages. So if the first xen_pfn
-	 * == mfn the page is local otherwise it's a foreign page
-	 * grant-mapped in dom0. If the page is local we can safely
-	 * call the native dma_ops function, otherwise we call the xen
-	 * specific function.
+	 * Dom0 is mapped 1:1, and while the Linux page can span across multiple
+	 * Xen pages, it is not possible for it to contain a mix of local and
+	 * foreign Xen pages.  Calling pfn_valid on a foreign mfn will always
+	 * return false, so if pfn_valid returns true the pages is local and we
+	 * can use the native dma-direct functions, otherwise we call the Xen
+	 * specific version.
 	 */
-	if (local)
+	if (pfn_valid(pfn))
 		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
 	else
 		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
@@ -79,14 +73,7 @@ static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	unsigned long pfn = PFN_DOWN(handle);
-	/*
-	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * multiple Xen page, it's not possible to have a mix of local and
-	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
-	 * foreign mfn will always return false. If the page is local we can
-	 * safely call the native dma_ops function, otherwise we call the xen
-	 * specific function.
-	 */
+
 	if (pfn_valid(pfn))
 		dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
 	else
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu