[PATCH] x86: adjust GFP mask handling for coherent allocations (take 2)

[PATCH] x86: adjust GFP mask handling for coherent allocations (take 2)

[Jan Beulich]

Rather than forcing GFP flags and DMA mask to be inconsistent, GFP
flags should be determined even for the fallback device through
dma_alloc_coherent_mask()/dma_alloc_coherent_gfp_flags(). This
restores 64-bit behavior as it was prior to commits
8965eb19386fdf5ccd0ef8b02593eb8560aa3416 and
4a367f3a9dbf2e7ffcee4702203479809236ee6e (not sure why there are two of
them), where GFP_DMA was forced on for 32-bit, but not for 64-bit, with
the slight adjustment that afaict even 32-bit doesn't need this without
CONFIG_ISA.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>

---
 arch/x86/include/asm/dma-mapping.h |   10 +++++++---
 arch/x86/kernel/pci-dma.c          |    6 ++----
 2 files changed, 9 insertions(+), 7 deletions(-)

--- linux-2.6.32-rc6/arch/x86/include/asm/dma-mapping.h	2009-11-04 13:23:36.000000000 +0100
+++ 2.6.32-rc6-x86-dma-mask-gfp/arch/x86/include/asm/dma-mapping.h	2009-10-27 11:10:28.000000000 +0100
@@ -14,6 +14,12 @@
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
 
+#ifdef CONFIG_ISA
+#define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
+#else
+#define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
+#endif
+
 extern dma_addr_t bad_dma_address;
 extern int iommu_merge;
 extern struct device x86_dma_fallback_dev;
@@ -124,10 +130,8 @@ dma_alloc_coherent(struct device *dev, s
 	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
 		return memory;
 
-	if (!dev) {
+	if (!dev)
 		dev = &x86_dma_fallback_dev;
-		gfp |= GFP_DMA;
-	}
 
 	if (!is_device_dma_capable(dev))
 		return NULL;
--- linux-2.6.32-rc6/arch/x86/kernel/pci-dma.c	2009-11-04 13:23:36.000000000 +0100
+++ 2.6.32-rc6-x86-dma-mask-gfp/arch/x86/kernel/pci-dma.c	2009-10-27 11:14:11.000000000 +0100
@@ -45,12 +45,10 @@ int iommu_pass_through __read_mostly;
 dma_addr_t bad_dma_address __read_mostly = 0;
 EXPORT_SYMBOL(bad_dma_address);
 
-/* Dummy device used for NULL arguments (normally ISA). Better would
-   be probably a smaller DMA mask, but this is bug-to-bug compatible
-   to older i386. */
+/* Dummy device used for NULL arguments (normally ISA). */
 struct device x86_dma_fallback_dev = {
 	.init_name = "fallback device",
-	.coherent_dma_mask = DMA_BIT_MASK(32),
+	.coherent_dma_mask = ISA_DMA_BIT_MASK,
 	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
 };
 EXPORT_SYMBOL(x86_dma_fallback_dev);

Re: [PATCH] x86: adjust GFP mask handling for coherent allocations (take 2)

[Takashi Iwai]

At Wed, 04 Nov 2009 12:28:39 +0000,
Jan Beulich wrote:
> 
> Rather than forcing GFP flags and DMA mask to be inconsistent, GFP
> flags should be determined even for the fallback device through
> dma_alloc_coherent_mask()/dma_alloc_coherent_gfp_flags(). This
> restores 64-bit behavior as it was prior to commits
> 8965eb19386fdf5ccd0ef8b02593eb8560aa3416 and
> 4a367f3a9dbf2e7ffcee4702203479809236ee6e (not sure why there are two of
> them), where GFP_DMA was forced on for 32-bit, but not for 64-bit, with
> the slight adjustment that afaict even 32-bit doesn't need this without
> CONFIG_ISA.
> 
> Signed-off-by: Jan Beulich <jbeulich@novell.com>
> Cc: Takashi Iwai <tiwai@suse.de>

Acked-by: Takashi Iwai <tiwai@suse.de>


thanks,

Takashi


> Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
> 
> ---
>  arch/x86/include/asm/dma-mapping.h |   10 +++++++---
>  arch/x86/kernel/pci-dma.c          |    6 ++----
>  2 files changed, 9 insertions(+), 7 deletions(-)
> 
> --- linux-2.6.32-rc6/arch/x86/include/asm/dma-mapping.h	2009-11-04 13:23:36.000000000 +0100
> +++ 2.6.32-rc6-x86-dma-mask-gfp/arch/x86/include/asm/dma-mapping.h	2009-10-27 11:10:28.000000000 +0100
> @@ -14,6 +14,12 @@
>  #include <asm/swiotlb.h>
>  #include <asm-generic/dma-coherent.h>
>  
> +#ifdef CONFIG_ISA
> +#define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
> +#else
> +#define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
> +#endif
> +
>  extern dma_addr_t bad_dma_address;
>  extern int iommu_merge;
>  extern struct device x86_dma_fallback_dev;
> @@ -124,10 +130,8 @@ dma_alloc_coherent(struct device *dev, s
>  	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
>  		return memory;
>  
> -	if (!dev) {
> +	if (!dev)
>  		dev = &x86_dma_fallback_dev;
> -		gfp |= GFP_DMA;
> -	}
>  
>  	if (!is_device_dma_capable(dev))
>  		return NULL;
> --- linux-2.6.32-rc6/arch/x86/kernel/pci-dma.c	2009-11-04 13:23:36.000000000 +0100
> +++ 2.6.32-rc6-x86-dma-mask-gfp/arch/x86/kernel/pci-dma.c	2009-10-27 11:14:11.000000000 +0100
> @@ -45,12 +45,10 @@ int iommu_pass_through __read_mostly;
>  dma_addr_t bad_dma_address __read_mostly = 0;
>  EXPORT_SYMBOL(bad_dma_address);
>  
> -/* Dummy device used for NULL arguments (normally ISA). Better would
> -   be probably a smaller DMA mask, but this is bug-to-bug compatible
> -   to older i386. */
> +/* Dummy device used for NULL arguments (normally ISA). */
>  struct device x86_dma_fallback_dev = {
>  	.init_name = "fallback device",
> -	.coherent_dma_mask = DMA_BIT_MASK(32),
> +	.coherent_dma_mask = ISA_DMA_BIT_MASK,
>  	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
>  };
>  EXPORT_SYMBOL(x86_dma_fallback_dev);
> 
> 
> 

[PATCH, v3] x86: Adjust GFP mask handling for coherent allocations

[Ingo Molnar]

* Takashi Iwai <tiwai@suse.de> wrote:

> At Wed, 04 Nov 2009 12:28:39 +0000,
> Jan Beulich wrote:
> > 
> > Rather than forcing GFP flags and DMA mask to be inconsistent, GFP
> > flags should be determined even for the fallback device through
> > dma_alloc_coherent_mask()/dma_alloc_coherent_gfp_flags(). This
> > restores 64-bit behavior as it was prior to commits
> > 8965eb19386fdf5ccd0ef8b02593eb8560aa3416 and
> > 4a367f3a9dbf2e7ffcee4702203479809236ee6e (not sure why there are two of
> > them), where GFP_DMA was forced on for 32-bit, but not for 64-bit, with
> > the slight adjustment that afaict even 32-bit doesn't need this without
> > CONFIG_ISA.
> > 
> > Signed-off-by: Jan Beulich <jbeulich@novell.com>
> > Cc: Takashi Iwai <tiwai@suse.de>
> 
> Acked-by: Takashi Iwai <tiwai@suse.de>

Jesse, mind picking this up for .32?

I've attached below a slightly cleaned up version of the patch, with 
Takashi's ack added.

Thanks,

	Ingo

------------------>
Subject: x86: Adjust GFP mask handling for coherent allocations
From: "Jan Beulich" <JBeulich@novell.com>
Date: Wed, 04 Nov 2009 12:28:39 +0000

Rather than forcing GFP flags and DMA mask to be inconsistent,
GFP flags should be determined even for the fallback device
through dma_alloc_coherent_mask()/dma_alloc_coherent_gfp_flags().

This restores 64-bit behavior as it was prior to commits
8965eb19386fdf5ccd0ef8b02593eb8560aa3416 and
4a367f3a9dbf2e7ffcee4702203479809236ee6e (not sure why there are
two of them), where GFP_DMA was forced on for 32-bit, but not
for 64-bit, with the slight adjustment that afaict even 32-bit
doesn't need this without CONFIG_ISA.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Acked-by: Takashi Iwai <tiwai@suse.de>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
LKML-Reference: <4AF18187020000780001D8AA@vpn.id2.novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/dma-mapping.h |   10 +++++++---
 arch/x86/kernel/pci-dma.c          |    6 ++----
 2 files changed, 9 insertions(+), 7 deletions(-)

Index: tip/arch/x86/include/asm/dma-mapping.h
===================================================================
--- tip.orig/arch/x86/include/asm/dma-mapping.h
+++ tip/arch/x86/include/asm/dma-mapping.h
@@ -14,6 +14,12 @@
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
 
+#ifdef CONFIG_ISA
+# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
+#else
+# define ISA_DMA_BIT_MASK DMA_BIT_MASK(32)
+#endif
+
 extern dma_addr_t bad_dma_address;
 extern int iommu_merge;
 extern struct device x86_dma_fallback_dev;
@@ -124,10 +130,8 @@ dma_alloc_coherent(struct device *dev, s
 	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
 		return memory;
 
-	if (!dev) {
+	if (!dev)
 		dev = &x86_dma_fallback_dev;
-		gfp |= GFP_DMA;
-	}
 
 	if (!is_device_dma_capable(dev))
 		return NULL;
Index: tip/arch/x86/kernel/pci-dma.c
===================================================================
--- tip.orig/arch/x86/kernel/pci-dma.c
+++ tip/arch/x86/kernel/pci-dma.c
@@ -45,12 +45,10 @@ int iommu_pass_through __read_mostly;
 dma_addr_t bad_dma_address __read_mostly = 0;
 EXPORT_SYMBOL(bad_dma_address);
 
-/* Dummy device used for NULL arguments (normally ISA). Better would
-   be probably a smaller DMA mask, but this is bug-to-bug compatible
-   to older i386. */
+/* Dummy device used for NULL arguments (normally ISA). */
 struct device x86_dma_fallback_dev = {
 	.init_name = "fallback device",
-	.coherent_dma_mask = DMA_BIT_MASK(32),
+	.coherent_dma_mask = ISA_DMA_BIT_MASK,
 	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
 };
 EXPORT_SYMBOL(x86_dma_fallback_dev);

Re: [PATCH, v3] x86: Adjust GFP mask handling for coherent allocations

[Jesse Barnes]

On Sun, 8 Nov 2009 12:12:14 +0100
Ingo Molnar <mingo@elte.hu> wrote:

> 
> * Takashi Iwai <tiwai@suse.de> wrote:
> 
> > At Wed, 04 Nov 2009 12:28:39 +0000,
> > Jan Beulich wrote:
> > > 
> > > Rather than forcing GFP flags and DMA mask to be inconsistent, GFP
> > > flags should be determined even for the fallback device through
> > > dma_alloc_coherent_mask()/dma_alloc_coherent_gfp_flags(). This
> > > restores 64-bit behavior as it was prior to commits
> > > 8965eb19386fdf5ccd0ef8b02593eb8560aa3416 and
> > > 4a367f3a9dbf2e7ffcee4702203479809236ee6e (not sure why there are
> > > two of them), where GFP_DMA was forced on for 32-bit, but not for
> > > 64-bit, with the slight adjustment that afaict even 32-bit
> > > doesn't need this without CONFIG_ISA.
> > > 
> > > Signed-off-by: Jan Beulich <jbeulich@novell.com>
> > > Cc: Takashi Iwai <tiwai@suse.de>
> > 
> > Acked-by: Takashi Iwai <tiwai@suse.de>
> 
> Jesse, mind picking this up for .32?
> 
> I've attached below a slightly cleaned up version of the patch, with 
> Takashi's ack added.

Sure, I just stuffed it into my for-linus tree, I'll send a pull req on
Monday or Tuesday.

Thanks,
-- 
Jesse Barnes, Intel Open Source Technology Center