[PATCHv3 0/4]: dma, x86, xen: reduce SWIOTLB usage in Xen guests

[PATCHv3 0/4]: dma, x86, xen: reduce SWIOTLB usage in Xen guests

[David Vrabel]

On systems where DMA addresses and physical addresses are not 1:1
(such as Xen PV guests), the generic dma_get_required_mask() will not
return the correct mask (since it uses max_pfn).

Some device drivers (such as mptsas, mpt2sas) use
dma_get_required_mask() to set the device's DMA mask to allow them to use
only 32-bit DMA addresses in hardware structures.  This results in
unnecessary use of the SWIOTLB if DMA addresses are more than 32-bits,
impacting performance significantly.

This series allows Xen PV guests to override the default
dma_get_required_mask() with one that calculates the DMA mask from the
maximum MFN (and not the PFN).

Changes in v3:
- fix off-by-one in xen_dma_get_required_mask()
- split ia64 changes into separate patch.

Changes in v2:
- split x86 and xen changes into separate patches

David

[PATCH 1/4] dma: add dma_get_required_mask_from_max_pfn()

[David Vrabel]

A generic dma_get_required_mask() is useful even for architectures (such
as ia64) that define ARCH_HAS_GET_REQUIRED_MASK.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 drivers/base/platform.c     |   10 ++++++++--
 include/linux/dma-mapping.h |    1 +
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index b2afc29..f9f3930 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1009,8 +1009,7 @@ int __init platform_bus_init(void)
 	return error;
 }
 
-#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK
-u64 dma_get_required_mask(struct device *dev)
+u64 dma_get_required_mask_from_max_pfn(struct device *dev)
 {
 	u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT);
 	u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT));
@@ -1028,6 +1027,13 @@ u64 dma_get_required_mask(struct device *dev)
 	}
 	return mask;
 }
+EXPORT_SYMBOL_GPL(dma_get_required_mask_from_max_pfn);
+
+#ifndef ARCH_HAS_DMA_GET_REQUIRED_MASK
+u64 dma_get_required_mask(struct device *dev)
+{
+	return dma_get_required_mask_from_max_pfn(dev);
+}
 EXPORT_SYMBOL_GPL(dma_get_required_mask);
 #endif
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index d5d3881..6e2fdfc 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -127,6 +127,7 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
 	return dma_set_mask_and_coherent(dev, mask);
 }
 
+extern u64 dma_get_required_mask_from_max_pfn(struct device *dev);
 extern u64 dma_get_required_mask(struct device *dev);
 
 #ifndef set_arch_dma_coherent_ops
-- 
1.7.10.4

[PATCH 2/4] ia64: use common dma_get_required_mask_from_pfn()

[David Vrabel]

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: linux-ia64@vger.kernel.org
---
 arch/ia64/include/asm/machvec.h      |    2 +-
 arch/ia64/include/asm/machvec_init.h |    1 -
 arch/ia64/pci/pci.c                  |   20 --------------------
 3 files changed, 1 insertion(+), 22 deletions(-)

diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
index 9c39bdf..beaa47d 100644
--- a/arch/ia64/include/asm/machvec.h
+++ b/arch/ia64/include/asm/machvec.h
@@ -287,7 +287,7 @@ extern struct dma_map_ops *dma_get_ops(struct device *);
 # define platform_dma_get_ops		dma_get_ops
 #endif
 #ifndef platform_dma_get_required_mask
-# define  platform_dma_get_required_mask	ia64_dma_get_required_mask
+# define  platform_dma_get_required_mask	dma_get_required_mask_from_max_pfn
 #endif
 #ifndef platform_irq_to_vector
 # define platform_irq_to_vector		__ia64_irq_to_vector
diff --git a/arch/ia64/include/asm/machvec_init.h b/arch/ia64/include/asm/machvec_init.h
index 37a4698..ef964b2 100644
--- a/arch/ia64/include/asm/machvec_init.h
+++ b/arch/ia64/include/asm/machvec_init.h
@@ -3,7 +3,6 @@
 
 extern ia64_mv_send_ipi_t ia64_send_ipi;
 extern ia64_mv_global_tlb_purge_t ia64_global_tlb_purge;
-extern ia64_mv_dma_get_required_mask ia64_dma_get_required_mask;
 extern ia64_mv_irq_to_vector __ia64_irq_to_vector;
 extern ia64_mv_local_vector_to_irq __ia64_local_vector_to_irq;
 extern ia64_mv_pci_get_legacy_mem_t ia64_pci_get_legacy_mem;
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 291a582..79da21b 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -791,26 +791,6 @@ static void __init set_pci_dfl_cacheline_size(void)
 	pci_dfl_cache_line_size = (1 << cci.pcci_line_size) / 4;
 }
 
-u64 ia64_dma_get_required_mask(struct device *dev)
-{
-	u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT);
-	u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT));
-	u64 mask;
-
-	if (!high_totalram) {
-		/* convert to mask just covering totalram */
-		low_totalram = (1 << (fls(low_totalram) - 1));
-		low_totalram += low_totalram - 1;
-		mask = low_totalram;
-	} else {
-		high_totalram = (1 << (fls(high_totalram) - 1));
-		high_totalram += high_totalram - 1;
-		mask = (((u64)high_totalram) << 32) + 0xffffffff;
-	}
-	return mask;
-}
-EXPORT_SYMBOL_GPL(ia64_dma_get_required_mask);
-
 u64 dma_get_required_mask(struct device *dev)
 {
 	return platform_dma_get_required_mask(dev);
-- 
1.7.10.4

Re: [PATCH 2/4] ia64: use common dma_get_required_mask_from_pfn()

[Stefano Stabellini]

On Wed, 19 Nov 2014, David Vrabel wrote:
> Signed-off-by: David Vrabel <david.vrabel@citrix.com>
> Cc: Tony Luck <tony.luck@intel.com>
> Cc: Fenghua Yu <fenghua.yu@intel.com>
> Cc: linux-ia64@vger.kernel.org

Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>


>  arch/ia64/include/asm/machvec.h      |    2 +-
>  arch/ia64/include/asm/machvec_init.h |    1 -
>  arch/ia64/pci/pci.c                  |   20 --------------------
>  3 files changed, 1 insertion(+), 22 deletions(-)
> 
> diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
> index 9c39bdf..beaa47d 100644
> --- a/arch/ia64/include/asm/machvec.h
> +++ b/arch/ia64/include/asm/machvec.h
> @@ -287,7 +287,7 @@ extern struct dma_map_ops *dma_get_ops(struct device *);
>  # define platform_dma_get_ops		dma_get_ops
>  #endif
>  #ifndef platform_dma_get_required_mask
> -# define  platform_dma_get_required_mask	ia64_dma_get_required_mask
> +# define  platform_dma_get_required_mask	dma_get_required_mask_from_max_pfn
>  #endif
>  #ifndef platform_irq_to_vector
>  # define platform_irq_to_vector		__ia64_irq_to_vector
> diff --git a/arch/ia64/include/asm/machvec_init.h b/arch/ia64/include/asm/machvec_init.h
> index 37a4698..ef964b2 100644
> --- a/arch/ia64/include/asm/machvec_init.h
> +++ b/arch/ia64/include/asm/machvec_init.h
> @@ -3,7 +3,6 @@
>  
>  extern ia64_mv_send_ipi_t ia64_send_ipi;
>  extern ia64_mv_global_tlb_purge_t ia64_global_tlb_purge;
> -extern ia64_mv_dma_get_required_mask ia64_dma_get_required_mask;
>  extern ia64_mv_irq_to_vector __ia64_irq_to_vector;
>  extern ia64_mv_local_vector_to_irq __ia64_local_vector_to_irq;
>  extern ia64_mv_pci_get_legacy_mem_t ia64_pci_get_legacy_mem;
> diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
> index 291a582..79da21b 100644
> --- a/arch/ia64/pci/pci.c
> +++ b/arch/ia64/pci/pci.c
> @@ -791,26 +791,6 @@ static void __init set_pci_dfl_cacheline_size(void)
>  	pci_dfl_cache_line_size = (1 << cci.pcci_line_size) / 4;
>  }
>  
> -u64 ia64_dma_get_required_mask(struct device *dev)
> -{
> -	u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT);
> -	u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT));
> -	u64 mask;
> -
> -	if (!high_totalram) {
> -		/* convert to mask just covering totalram */
> -		low_totalram = (1 << (fls(low_totalram) - 1));
> -		low_totalram += low_totalram - 1;
> -		mask = low_totalram;
> -	} else {
> -		high_totalram = (1 << (fls(high_totalram) - 1));
> -		high_totalram += high_totalram - 1;
> -		mask = (((u64)high_totalram) << 32) + 0xffffffff;
> -	}
> -	return mask;
> -}
> -EXPORT_SYMBOL_GPL(ia64_dma_get_required_mask);
> -
>  u64 dma_get_required_mask(struct device *dev)
>  {
>  	return platform_dma_get_required_mask(dev);
> -- 
> 1.7.10.4
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://secure-web.cisco.com/1uzdEOuzPh9ddYCppJ7edARD7taQXur82_EMioIJqXcGS1lEgfETQB2j546iHGLqo8mraFv4u9YxUpICa6DurqoTbYGXFrH14KuGQfFFzn4DHYx5HIksjcOqO2hiw74xfemY9frjnyDwhuBoBc3quJ5I8zLhf8kRz1AJGBKOKY_o/http%3A%2F%2Fwww.tux.org%2Flkml%2F
> 

[PATCH 3/4] x86: allow dma_get_required_mask() to be overridden

[David Vrabel]

Use dma_ops->get_required_mask() if provided, defaulting to
dma_get_requried_mask_from_max_pfn().

This is needed on systems (such as Xen PV guests) where the DMA
address and the physical address are not equal.

ARCH_HAS_DMA_GET_REQUIRED_MASK is defined in asm/device.h instead of
asm/dma-mapping.h because linux/dma-mapping.h uses the define before
including asm/dma-mapping.h

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 arch/x86/include/asm/device.h |    2 ++
 arch/x86/kernel/pci-dma.c     |    8 ++++++++
 2 files changed, 10 insertions(+)

diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 03dd729..10bc628 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -13,4 +13,6 @@ struct dev_archdata {
 struct pdev_archdata {
 };
 
+#define ARCH_HAS_DMA_GET_REQUIRED_MASK
+
 #endif /* _ASM_X86_DEVICE_H */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index a25e202..5154400 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -140,6 +140,14 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
 		free_pages((unsigned long)vaddr, get_order(size));
 }
 
+u64 dma_get_required_mask(struct device *dev)
+{
+	if (dma_ops->get_required_mask)
+		return dma_ops->get_required_mask(dev);
+	return dma_get_required_mask_from_max_pfn(dev);
+}
+EXPORT_SYMBOL_GPL(dma_get_required_mask);
+
 /*
  * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
  * parameter documentation.
-- 
1.7.10.4

[PATCH 4/4] x86/xen: use the maximum MFN to calculate the required DMA mask

[David Vrabel]

On a Xen PV guest the DMA addresses and physical addresses are not 1:1
(such as Xen PV guests) and the generic dma_get_required_mask() does
not return the correct mask (since it uses max_pfn).

Some device drivers (such as mptsas, mpt2sas) use
dma_get_required_mask() to set the device's DMA mask to allow them to
use only 32-bit DMA addresses in hardware structures.  This results in
unnecessary use of the SWIOTLB if DMA addresses are more than 32-bits,
impacting performance significantly.

Provide a get_required_mask op that uses the maximum MFN to calculate
the DMA mask.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 arch/x86/xen/pci-swiotlb-xen.c |    1 +
 drivers/xen/swiotlb-xen.c      |   13 +++++++++++++
 include/xen/swiotlb-xen.h      |    4 ++++
 3 files changed, 18 insertions(+)

diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 0e98e5d..a5d180a 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -31,6 +31,7 @@ static 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,
+	.get_required_mask = xen_swiotlb_get_required_mask,
 };
 
 /*
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index ebd8f21..654587d 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -42,9 +42,11 @@
 #include <xen/page.h>
 #include <xen/xen-ops.h>
 #include <xen/hvc-console.h>
+#include <xen/interface/memory.h>
 
 #include <asm/dma-mapping.h>
 #include <asm/xen/page-coherent.h>
+#include <asm/xen/hypercall.h>
 
 #include <trace/events/swiotlb.h>
 /*
@@ -683,3 +685,14 @@ xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
+
+u64
+xen_swiotlb_get_required_mask(struct device *dev)
+{
+	unsigned long max_mfn;
+
+	max_mfn = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL);
+
+	return DMA_BIT_MASK(fls_long(max_mfn - 1) + PAGE_SHIFT);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_get_required_mask);
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index 8b2eb93..6408888 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -58,4 +58,8 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
 
 extern int
 xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
+
+extern u64
+xen_swiotlb_get_required_mask(struct device *dev);
+
 #endif /* __LINUX_SWIOTLB_XEN_H */
-- 
1.7.10.4

Re: [Xen-devel] [PATCH 4/4] x86/xen: use the maximum MFN to calculate the required DMA mask

[Stefano Stabellini]

On Wed, 19 Nov 2014, David Vrabel wrote:
> On a Xen PV guest the DMA addresses and physical addresses are not 1:1
> (such as Xen PV guests) and the generic dma_get_required_mask() does
> not return the correct mask (since it uses max_pfn).
> 
> Some device drivers (such as mptsas, mpt2sas) use
> dma_get_required_mask() to set the device's DMA mask to allow them to
> use only 32-bit DMA addresses in hardware structures.  This results in
> unnecessary use of the SWIOTLB if DMA addresses are more than 32-bits,
> impacting performance significantly.
> 
> Provide a get_required_mask op that uses the maximum MFN to calculate
> the DMA mask.
> 
> Signed-off-by: David Vrabel <david.vrabel@citrix.com>
> ---
>  arch/x86/xen/pci-swiotlb-xen.c |    1 +
>  drivers/xen/swiotlb-xen.c      |   13 +++++++++++++
>  include/xen/swiotlb-xen.h      |    4 ++++
>  3 files changed, 18 insertions(+)
> 
> diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
> index 0e98e5d..a5d180a 100644
> --- a/arch/x86/xen/pci-swiotlb-xen.c
> +++ b/arch/x86/xen/pci-swiotlb-xen.c
> @@ -31,6 +31,7 @@ static 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,
> +	.get_required_mask = xen_swiotlb_get_required_mask,
>  };
>  
>  /*
> diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
> index ebd8f21..654587d 100644
> --- a/drivers/xen/swiotlb-xen.c
> +++ b/drivers/xen/swiotlb-xen.c
> @@ -42,9 +42,11 @@
>  #include <xen/page.h>
>  #include <xen/xen-ops.h>
>  #include <xen/hvc-console.h>
> +#include <xen/interface/memory.h>
>  
>  #include <asm/dma-mapping.h>
>  #include <asm/xen/page-coherent.h>
> +#include <asm/xen/hypercall.h>
>  
>  #include <trace/events/swiotlb.h>
>  /*
> @@ -683,3 +685,14 @@ xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
>  	return 0;
>  }
>  EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
> +
> +u64
> +xen_swiotlb_get_required_mask(struct device *dev)
> +{
> +	unsigned long max_mfn;
> +
> +	max_mfn = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL);

As Jan pointed out, I think you need to change the prototype of
HYPERVISOR_memory_op to return long. Please do consistently across all
relevant archs.


> +	return DMA_BIT_MASK(fls_long(max_mfn - 1) + PAGE_SHIFT);
> +}
> +EXPORT_SYMBOL_GPL(xen_swiotlb_get_required_mask);
> diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
> index 8b2eb93..6408888 100644
> --- a/include/xen/swiotlb-xen.h
> +++ b/include/xen/swiotlb-xen.h
> @@ -58,4 +58,8 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
>  
>  extern int
>  xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
> +
> +extern u64
> +xen_swiotlb_get_required_mask(struct device *dev);
> +
>  #endif /* __LINUX_SWIOTLB_XEN_H */
> -- 
> 1.7.10.4
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> http://lists.xen.org/xen-devel
> 

Re: [Xen-devel] [PATCH 4/4] x86/xen: use the maximum MFN to calculate the required DMA mask

[David Vrabel]

On 19/11/14 17:51, Stefano Stabellini wrote:
> On Wed, 19 Nov 2014, David Vrabel wrote:
>> 
>> +u64
>> +xen_swiotlb_get_required_mask(struct device *dev)
>> +{
>> +	unsigned long max_mfn;
>> +
>> +	max_mfn = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL);
> 
> As Jan pointed out, I think you need to change the prototype of
> HYPERVISOR_memory_op to return long. Please do consistently across all
> relevant archs.

This doesn't help since 32-bit guests will still truncate.  A new
hypercall op that returns the result in a uint64_t parameter is required.

There is another reason why max_mfn isn't suitable -- IOMMU usage so I
think we should assume a 64-bit DMA mask is required (this is actually
the change I put into XenServer's kernel).

David

Re: [Xen-devel] [PATCH 4/4] x86/xen: use the maximum MFN to calculate the required DMA mask

[Jan Beulich]

>>> On 19.11.14 at 17:02, <david.vrabel@citrix.com> wrote:
> On a Xen PV guest the DMA addresses and physical addresses are not 1:1
> (such as Xen PV guests) and the generic dma_get_required_mask() does
> not return the correct mask (since it uses max_pfn).
> 
> Some device drivers (such as mptsas, mpt2sas) use
> dma_get_required_mask() to set the device's DMA mask to allow them to
> use only 32-bit DMA addresses in hardware structures.  This results in
> unnecessary use of the SWIOTLB if DMA addresses are more than 32-bits,
> impacting performance significantly.
> 
> Provide a get_required_mask op that uses the maximum MFN to calculate
> the DMA mask.
> 
> Signed-off-by: David Vrabel <david.vrabel@citrix.com>

Reviewed-by: Jan Beulich <jbeulich@suse.com>