[PATCH 0/2] Refactor dummy DMA ops

[PATCH 0/2] Refactor dummy DMA ops

[Robin Murphy]

Hi all,

Tangential to Christoph's RFC for mitigating indirect call overhead in
common DMA mapping scenarios[1], this is a little reshuffle to prevent the
CONFIG_ACPI_CCA_REQUIRED case from getting in the way. This would best go
via the dma-mapping tree, so reviews and acks welcome.

Robin.

[1] https://lore.kernel.org/lkml/20181206153720.10702-1-hch@lst.de/

Robin Murphy (2):
  dma-mapping: Factor out dummy DMA ops
  ACPI / scan: Refactor _CCA enforcement

 arch/arm64/include/asm/dma-mapping.h |  4 +-
 arch/arm64/mm/dma-mapping.c          | 92 ----------------------------
 drivers/acpi/scan.c                  |  5 ++
 drivers/base/platform.c              |  3 +-
 drivers/pci/pci-driver.c             |  3 +-
 include/linux/dma-mapping.h          |  1 +
 kernel/dma/mapping.c                 | 54 ++++++++++++++++
 7 files changed, 63 insertions(+), 99 deletions(-)

-- 
2.19.1.dirty

[PATCH 1/2] dma-mapping: Factor out dummy DMA ops

[Robin Murphy]

The dummy DMA ops are currently used by arm64 for any device which has
an invalid ACPI description and is thus barred from using DMA due to not
knowing whether is is cache-coherent or not. Factor these out into
general dma-mapping code so that they can be referenced from other
common code paths. In the process, we can prune all the optional
callbacks which just do the same thing as the default behaviour, and
fill in .map_resource for completeness.

CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/arm64/include/asm/dma-mapping.h |  4 +-
 arch/arm64/mm/dma-mapping.c          | 92 ----------------------------
 include/linux/dma-mapping.h          |  1 +
 kernel/dma/mapping.c                 | 54 ++++++++++++++++
 4 files changed, 56 insertions(+), 95 deletions(-)

diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index c41f3fb1446c..273e778f7de2 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -24,15 +24,13 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-extern const struct dma_map_ops dummy_dma_ops;
-
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
 	/*
 	 * We expect no ISA devices, and all other DMA masters are expected to
 	 * have someone call arch_setup_dma_ops at device creation time.
 	 */
-	return &dummy_dma_ops;
+	return &dma_dummy_ops;
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index a3ac26284845..f3af6cc52fad 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -252,98 +252,6 @@ static int __init atomic_pool_init(void)
 	return -ENOMEM;
 }
 
-/********************************************
- * The following APIs are for dummy DMA ops *
- ********************************************/
-
-static void *__dummy_alloc(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flags,
-			   unsigned long attrs)
-{
-	return NULL;
-}
-
-static void __dummy_free(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle,
-			 unsigned long attrs)
-{
-}
-
-static int __dummy_mmap(struct device *dev,
-			struct vm_area_struct *vma,
-			void *cpu_addr, dma_addr_t dma_addr, size_t size,
-			unsigned long attrs)
-{
-	return -ENXIO;
-}
-
-static dma_addr_t __dummy_map_page(struct device *dev, struct page *page,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	return 0;
-}
-
-static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-}
-
-static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl,
-			  int nelems, enum dma_data_direction dir,
-			  unsigned long attrs)
-{
-	return 0;
-}
-
-static void __dummy_unmap_sg(struct device *dev,
-			     struct scatterlist *sgl, int nelems,
-			     enum dma_data_direction dir,
-			     unsigned long attrs)
-{
-}
-
-static void __dummy_sync_single(struct device *dev,
-				dma_addr_t dev_addr, size_t size,
-				enum dma_data_direction dir)
-{
-}
-
-static void __dummy_sync_sg(struct device *dev,
-			    struct scatterlist *sgl, int nelems,
-			    enum dma_data_direction dir)
-{
-}
-
-static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
-{
-	return 1;
-}
-
-static int __dummy_dma_supported(struct device *hwdev, u64 mask)
-{
-	return 0;
-}
-
-const struct dma_map_ops dummy_dma_ops = {
-	.alloc                  = __dummy_alloc,
-	.free                   = __dummy_free,
-	.mmap                   = __dummy_mmap,
-	.map_page               = __dummy_map_page,
-	.unmap_page             = __dummy_unmap_page,
-	.map_sg                 = __dummy_map_sg,
-	.unmap_sg               = __dummy_unmap_sg,
-	.sync_single_for_cpu    = __dummy_sync_single,
-	.sync_single_for_device = __dummy_sync_single,
-	.sync_sg_for_cpu        = __dummy_sync_sg,
-	.sync_sg_for_device     = __dummy_sync_sg,
-	.mapping_error          = __dummy_mapping_error,
-	.dma_supported          = __dummy_dma_supported,
-};
-EXPORT_SYMBOL(dummy_dma_ops);
-
 static int __init arm64_dma_init(void)
 {
 	WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(),
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 15bd41447025..3a1928ea23c9 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -134,6 +134,7 @@ struct dma_map_ops {
 };
 
 extern const struct dma_map_ops dma_direct_ops;
+extern const struct dma_map_ops dma_dummy_ops;
 extern const struct dma_map_ops dma_virt_ops;
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 58dec7a92b7b..957a42ebabcf 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -346,3 +346,57 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
 	vunmap(cpu_addr);
 }
 #endif
+
+/*
+ * Dummy DMA ops always fail
+ */
+
+static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma,
+			  void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			  unsigned long attrs)
+{
+	return -ENXIO;
+}
+
+static dma_addr_t dma_dummy_map_page(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir,
+				     unsigned long attrs)
+{
+	return 0;
+}
+
+static int dma_dummy_map_sg(struct device *dev, struct scatterlist *sgl,
+			    int nelems, enum dma_data_direction dir,
+			    unsigned long attrs)
+{
+	return 0;
+}
+
+static dma_addr_t dma_dummy_map_resource(struct device *dev,
+					 phys_addr_t phys_addr, size_t size,
+					 enum dma_data_direction dir,
+					 unsigned long attrs)
+{
+	return 0;
+}
+
+static int dma_dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+	return 1;
+}
+
+static int dma_dummy_supported(struct device *hwdev, u64 mask)
+{
+	return 0;
+}
+
+const struct dma_map_ops dma_dummy_ops = {
+	.mmap		= dma_dummy_mmap,
+	.map_page	= dma_dummy_map_page,
+	.map_sg		= dma_dummy_map_sg,
+	.map_resource	= dma_dummy_map_resource,
+	.mapping_error	= dma_dummy_mapping_error,
+	.dma_supported	= dma_dummy_supported,
+};
+EXPORT_SYMBOL(dma_dummy_ops);
-- 
2.19.1.dirty

[PATCH 2/2] ACPI / scan: Refactor _CCA enforcement

[Robin Murphy]

Rather than checking the DMA attribute at each callsite, just pass it
through for acpi_dma_configure() to handle directly. That can then deal
with the relatively exceptional DEV_DMA_NOT_SUPPORTED case by explicitly
installing dummy DMA ops instead of just skipping setup entirely. This
will then free up the dev->dma_ops == NULL case for some valuable
fastpath optimisations.

CC: Rafael J. Wysocki <rjw@rjwysocki.net>
CC: Len Brown <lenb@kernel.org>
CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
CC: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
 drivers/acpi/scan.c      | 5 +++++
 drivers/base/platform.c  | 3 +--
 drivers/pci/pci-driver.c | 3 +--
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index bd1c59fb0e17..b75ae34ed188 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1456,6 +1456,11 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
 	const struct iommu_ops *iommu;
 	u64 dma_addr = 0, size = 0;
 
+	if (attr == DEV_DMA_NOT_SUPPORTED) {
+		set_dma_ops(dev, &dma_dummy_ops);
+		return 0;
+	}
+
 	iort_dma_setup(dev, &dma_addr, &size);
 
 	iommu = iort_iommu_configure(dev);
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 41b91af95afb..c6daca875c17 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1138,8 +1138,7 @@ int platform_dma_configure(struct device *dev)
 		ret = of_dma_configure(dev, dev->of_node, true);
 	} else if (has_acpi_companion(dev)) {
 		attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode));
-		if (attr != DEV_DMA_NOT_SUPPORTED)
-			ret = acpi_dma_configure(dev, attr);
+		ret = acpi_dma_configure(dev, attr);
 	}
 
 	return ret;
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index bef17c3fca67..f899a28b90f8 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1602,8 +1602,7 @@ static int pci_dma_configure(struct device *dev)
 		struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
 		enum dev_dma_attr attr = acpi_get_dma_attr(adev);
 
-		if (attr != DEV_DMA_NOT_SUPPORTED)
-			ret = acpi_dma_configure(dev, attr);
+		ret = acpi_dma_configure(dev, attr);
 	}
 
 	pci_put_host_bridge_device(bridge);
-- 
2.19.1.dirty

Re: [PATCH 0/2] Refactor dummy DMA ops

[Christoph Hellwig]

So I'd really prefer if we had a separate dummy.c file, like in
my take on your previous patch here:

http://git.infradead.org/users/hch/misc.git/commitdiff/e01adddc1733fa414dc16cd22e8f58be9b64a025

http://git.infradead.org/users/hch/misc.git/commitdiff/596bde76e5944a3f4beb8c2769067ca88dda127a

Otherwise this looks fine.  If you don't minde I'll take your patches,
apply the move to a separate file and merge it into the above tree.

Re: [PATCH 0/2] Refactor dummy DMA ops

[Robin Murphy]

On 07/12/2018 17:05, Christoph Hellwig wrote:
> So I'd really prefer if we had a separate dummy.c file, like in
> my take on your previous patch here:
> 
> http://git.infradead.org/users/hch/misc.git/commitdiff/e01adddc1733fa414dc16cd22e8f58be9b64a025
> 
> http://git.infradead.org/users/hch/misc.git/commitdiff/596bde76e5944a3f4beb8c2769067ca88dda127a
> 
> Otherwise this looks fine.  If you don't minde I'll take your patches,
> apply the move to a separate file and merge it into the above tree.

Sure - TBH I did consider creating a separate file, but then didn't for 
mysterious reasons that don't stand up to scrutiny. If you're happy to 
do the fixup on top that's fine by me (if culling .map_resource was 
intentional, please scrub the last bit of the commit message to match).

I'll make the equivalent change locally anyway just in case there's any 
other cause to resend.

Robin.

Re: [PATCH 2/2] ACPI / scan: Refactor _CCA enforcement

[Rafael J. Wysocki]

On Fri, Dec 7, 2018 at 5:31 PM Robin Murphy <robin.murphy@arm.com> wrote:
>
> Rather than checking the DMA attribute at each callsite, just pass it
> through for acpi_dma_configure() to handle directly. That can then deal
> with the relatively exceptional DEV_DMA_NOT_SUPPORTED case by explicitly
> installing dummy DMA ops instead of just skipping setup entirely. This
> will then free up the dev->dma_ops == NULL case for some valuable
> fastpath optimisations.
>
> CC: Rafael J. Wysocki <rjw@rjwysocki.net>
> CC: Len Brown <lenb@kernel.org>
> CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> CC: Bjorn Helgaas <bhelgaas@google.com>
> Signed-off-by: Robin Murphy <robin.murphy@arm.com>

The changes in this patch are fine by me:

Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

> ---
>  drivers/acpi/scan.c      | 5 +++++
>  drivers/base/platform.c  | 3 +--
>  drivers/pci/pci-driver.c | 3 +--
>  3 files changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
> index bd1c59fb0e17..b75ae34ed188 100644
> --- a/drivers/acpi/scan.c
> +++ b/drivers/acpi/scan.c
> @@ -1456,6 +1456,11 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
>         const struct iommu_ops *iommu;
>         u64 dma_addr = 0, size = 0;
>
> +       if (attr == DEV_DMA_NOT_SUPPORTED) {
> +               set_dma_ops(dev, &dma_dummy_ops);
> +               return 0;
> +       }
> +
>         iort_dma_setup(dev, &dma_addr, &size);
>
>         iommu = iort_iommu_configure(dev);
> diff --git a/drivers/base/platform.c b/drivers/base/platform.c
> index 41b91af95afb..c6daca875c17 100644
> --- a/drivers/base/platform.c
> +++ b/drivers/base/platform.c
> @@ -1138,8 +1138,7 @@ int platform_dma_configure(struct device *dev)
>                 ret = of_dma_configure(dev, dev->of_node, true);
>         } else if (has_acpi_companion(dev)) {
>                 attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode));
> -               if (attr != DEV_DMA_NOT_SUPPORTED)
> -                       ret = acpi_dma_configure(dev, attr);
> +               ret = acpi_dma_configure(dev, attr);
>         }
>
>         return ret;
> diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
> index bef17c3fca67..f899a28b90f8 100644
> --- a/drivers/pci/pci-driver.c
> +++ b/drivers/pci/pci-driver.c
> @@ -1602,8 +1602,7 @@ static int pci_dma_configure(struct device *dev)
>                 struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
>                 enum dev_dma_attr attr = acpi_get_dma_attr(adev);
>
> -               if (attr != DEV_DMA_NOT_SUPPORTED)
> -                       ret = acpi_dma_configure(dev, attr);
> +               ret = acpi_dma_configure(dev, attr);
>         }
>
>         pci_put_host_bridge_device(bridge);
> --
> 2.19.1.dirty
>

Re: [PATCH 2/2] ACPI / scan: Refactor _CCA enforcement

[Bjorn Helgaas]

On Fri, Dec 07, 2018 at 04:31:35PM +0000, Robin Murphy wrote:
> Rather than checking the DMA attribute at each callsite, just pass it
> through for acpi_dma_configure() to handle directly. That can then deal
> with the relatively exceptional DEV_DMA_NOT_SUPPORTED case by explicitly
> installing dummy DMA ops instead of just skipping setup entirely. This
> will then free up the dev->dma_ops == NULL case for some valuable
> fastpath optimisations.
> 
> CC: Rafael J. Wysocki <rjw@rjwysocki.net>
> CC: Len Brown <lenb@kernel.org>
> CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
> CC: Bjorn Helgaas <bhelgaas@google.com>
> Signed-off-by: Robin Murphy <robin.murphy@arm.com>

FWIW, if this hasn't been applied already (I think you targeted a DMA
tree):

Acked-by: Bjorn Helgaas <bhelgaas@google.com>

> ---
>  drivers/acpi/scan.c      | 5 +++++
>  drivers/base/platform.c  | 3 +--
>  drivers/pci/pci-driver.c | 3 +--
>  3 files changed, 7 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
> index bd1c59fb0e17..b75ae34ed188 100644
> --- a/drivers/acpi/scan.c
> +++ b/drivers/acpi/scan.c
> @@ -1456,6 +1456,11 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
>  	const struct iommu_ops *iommu;
>  	u64 dma_addr = 0, size = 0;
>  
> +	if (attr == DEV_DMA_NOT_SUPPORTED) {
> +		set_dma_ops(dev, &dma_dummy_ops);
> +		return 0;
> +	}
> +
>  	iort_dma_setup(dev, &dma_addr, &size);
>  
>  	iommu = iort_iommu_configure(dev);
> diff --git a/drivers/base/platform.c b/drivers/base/platform.c
> index 41b91af95afb..c6daca875c17 100644
> --- a/drivers/base/platform.c
> +++ b/drivers/base/platform.c
> @@ -1138,8 +1138,7 @@ int platform_dma_configure(struct device *dev)
>  		ret = of_dma_configure(dev, dev->of_node, true);
>  	} else if (has_acpi_companion(dev)) {
>  		attr = acpi_get_dma_attr(to_acpi_device_node(dev->fwnode));
> -		if (attr != DEV_DMA_NOT_SUPPORTED)
> -			ret = acpi_dma_configure(dev, attr);
> +		ret = acpi_dma_configure(dev, attr);
>  	}
>  
>  	return ret;
> diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
> index bef17c3fca67..f899a28b90f8 100644
> --- a/drivers/pci/pci-driver.c
> +++ b/drivers/pci/pci-driver.c
> @@ -1602,8 +1602,7 @@ static int pci_dma_configure(struct device *dev)
>  		struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
>  		enum dev_dma_attr attr = acpi_get_dma_attr(adev);
>  
> -		if (attr != DEV_DMA_NOT_SUPPORTED)
> -			ret = acpi_dma_configure(dev, attr);
> +		ret = acpi_dma_configure(dev, attr);
>  	}
>  
>  	pci_put_host_bridge_device(bridge);
> -- 
> 2.19.1.dirty
> 
> 
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel