ensure dma_alloc_coherent always returns zeroed memory

ensure dma_alloc_coherent always returns zeroed memory

[Vineet Gupta]

On 12/28/18 9:58 AM, hch@lst.de wrote:
> On Fri, Dec 28, 2018@05:46:32PM +0000, Eugeniy Paltsev wrote:
>> What happens:
>>
>> First coherent allocation (PAL#1):
>> 1) allocate page via alloc_pages(__GFP_ZERO), got page vith paddr 0xbf2d6000
>> 2) zero it via memset [deep inside alloc_pages()]
>> 3) remap it as uncached via ioremap_nocache(), got vaddr 0x70004000
>> 4) flush and invalidate L1 and L2 lines which belongs to allocated page.
>> Everything is OK for now.
>>
>> Second coherent allocation (PAL#2):
>> 1) allocate page via alloc_pages(__GFP_ZERO), got page vith paddr 0xbf2d4000
>> 2) zero it via memset [deep inside alloc_pages()].
>> -> Ooops: ARC memset implementation (due to SW bug) calls 'prefetchw' instruction
>> for address which lies outside of memset area (it will be 0xbf2d6000 in this case)
>> So we got one modified (dirty) cache line in the beginning of previous coherent
>> buffer which has been already flushed and invalidated (in PAL#1).
>>
>> So if we put some real data in this buffer [via virtual (uncached) address)]
>> before this line is flushed - we will got corrupted data.
> We could instead do the memset on the remapped address, which would
> work around this prefetching issue:

Right, it probably would, but that would still be too fragile, there are other bad
things in non-dma scenarios which happen due to this.
This needed fixing and Eugeniy's fix is in upstream/master now

    2019-01-14 e6a72b7daeeb ARCv2: lib: memeset: fix doing prefetchw outside of
buffer 


>
> diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
> index 1525ac00fd02..7c3b47019079 100644
> --- a/arch/arc/mm/dma.c
> +++ b/arch/arc/mm/dma.c
> @@ -33,7 +33,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
>  	 */
>  	BUG_ON(gfp & __GFP_HIGHMEM);
>  
> -	page = alloc_pages(gfp | __GFP_ZERO, order);
> +	page = alloc_pages(gfp, order);
>  	if (!page)
>  		return NULL;
>  
> @@ -69,6 +69,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
>  	if (need_coh)
>  		dma_cache_wback_inv(paddr, size);
>  
> +	memset(kvaddr, 0, size);
>  	return kvaddr;
>  }

ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

For security reasons we already returned zeroed memory from
dma_alloc_coherent on most common platforms, but some implementation
missed out.  Make sure we provide a consistent behavior.

ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

For security reasons we already returned zeroed memory from
dma_alloc_coherent on most common platforms, but some implementation
missed out.  Make sure we provide a consistent behavior.

ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

For security reasons we already returned zeroed memory from
dma_alloc_coherent on most common platforms, but some implementation
missed out.  Make sure we provide a consistent behavior.

ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

For security reasons we already returned zeroed memory from
dma_alloc_coherent on most common platforms, but some implementation
missed out.  Make sure we provide a consistent behavior.

Re: ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

And in various places this used GFP_ZERO instead of __GFP_ZERO,
so won't compile.

The fixed version is available here:

http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/dma-alloc-always-zero

ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

And in various places this used GFP_ZERO instead of __GFP_ZERO,
so won't compile.

The fixed version is available here:

http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/dma-alloc-always-zero

Re: ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

And in various places this used GFP_ZERO instead of __GFP_ZERO,
so won't compile.

The fixed version is available here:

http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/dma-alloc-always-zero

Re: ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

FYI, I've picked this up for dma-mapping for-next now.

ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

FYI, I've picked this up for dma-mapping for-next now.

Re: ensure dma_alloc_coherent always returns zeroed memory

[Christoph Hellwig]

FYI, I've picked this up for dma-mapping for-next now.

Re: ensure dma_alloc_coherent always returns zeroed memory

[Eugeniy Paltsev]

Hi Christoph,

I test kernel from your 'dma-alloc-always-zero' branch, and as
I can see we have DMA peripherals (like USB) broken.

There are the errors example I got during USB initializing:
------------------------------>8--------------------------------
usb 1-1: device descriptor read/64, error -110
usb usb1-port1: attempt power cycle
usb 1-1: new high-speed USB device number 4 using ehci-platform
usb 1-1: device descriptor read/64, error -110
usb 1-1: device descriptor read/64, error -110
usb 1-1: new high-speed USB device number 5 using ehci-platform
usb 1-1: device descriptor read/64, error -110
usb 1-1: device descriptor read/64, error -110
usb usb1-port1: unable to enumerate USB device
usb 2-1: new full-speed USB device number 2 using ohci-platform
usb 2-1: device descriptor read/all, error -84
usb 2-1: new full-speed USB device number 3 using ohci-platform
usb 2-1: device descriptor read/all, error -84
usb usb2-port1: attempt power cycle
usb 2-1: new full-speed USB device number 4 using ohci-platform
usb 2-1: device descriptor read/8, error -62
usb 2-1: device descriptor read/8, error -62
usb 2-1: new full-speed USB device number 5 using ohci-platform
usb 2-1: device descriptor read/8, error -84
usb 2-1: device descriptor read/8, error -84
usb usb2-port1: unable to enumerate USB device
 [snip]
------------------------------8<--------------------------------


On Wed, 2018-12-19 at 17:59 +0100, Christoph Hellwig wrote:
> FYI, I've picked this up for dma-mapping for-next now.
> 
> _______________________________________________
> linux-snps-arc mailing list
> linux-snps-arc@lists.infradead.org
> https://urldefense.proofpoint.com/v2/url?u=http-3A__lists.infradead.org_mailman_listinfo_linux-2Dsnps-2Darc&d=DwICAg&c=DPL6_X_6JkXFx7AXWqB0tg&r=ZlJN
> 1MriPUTkBKCrPSx67GmaplEUGcAEk9yPtCLdUXI&m=naBCT96A4RSQJLzBWzuCcmptFGiQDfFTOWJpprqDIVk&s=cHF84va89ofP6VlrV683ewENUXdaLW7opamLZSkZBgk&e=
-- 
 Eugeniy Paltsev

ensure dma_alloc_coherent always returns zeroed memory

[Eugeniy Paltsev]

Hi Christoph,

I test kernel from your 'dma-alloc-always-zero' branch, and as
I can see we have DMA peripherals (like USB) broken.

There are the errors example I got during USB initializing:
------------------------------>8--------------------------------
usb 1-1: device descriptor read/64, error -110
usb usb1-port1: attempt power cycle
usb 1-1: new high-speed USB device number 4 using ehci-platform
usb 1-1: device descriptor read/64, error -110
usb 1-1: device descriptor read/64, error -110
usb 1-1: new high-speed USB device number 5 using ehci-platform
usb 1-1: device descriptor read/64, error -110
usb 1-1: device descriptor read/64, error -110
usb usb1-port1: unable to enumerate USB device
usb 2-1: new full-speed USB device number 2 using ohci-platform
usb 2-1: device descriptor read/all, error -84
usb 2-1: new full-speed USB device number 3 using ohci-platform
usb 2-1: device descriptor read/all, error -84
usb usb2-port1: attempt power cycle
usb 2-1: new full-speed USB device number 4 using ohci-platform
usb 2-1: device descriptor read/8, error -62
usb 2-1: device descriptor read/8, error -62
usb 2-1: new full-speed USB device number 5 using ohci-platform
usb 2-1: device descriptor read/8, error -84
usb 2-1: device descriptor read/8, error -84
usb usb2-port1: unable to enumerate USB device
 [snip]
------------------------------8<--------------------------------


On Wed, 2018-12-19@17:59 +0100, Christoph Hellwig wrote:
> FYI, I've picked this up for dma-mapping for-next now.
> 
> _______________________________________________
> linux-snps-arc mailing list
> linux-snps-arc at lists.infradead.org
> https://urldefense.proofpoint.com/v2/url?u=http-3A__lists.infradead.org_mailman_listinfo_linux-2Dsnps-2Darc&d=DwICAg&c=DPL6_X_6JkXFx7AXWqB0tg&r=ZlJN
> 1MriPUTkBKCrPSx67GmaplEUGcAEk9yPtCLdUXI&m=naBCT96A4RSQJLzBWzuCcmptFGiQDfFTOWJpprqDIVk&s=cHF84va89ofP6VlrV683ewENUXdaLW7opamLZSkZBgk&e=
-- 
 Eugeniy Paltsev

Re: ensure dma_alloc_coherent always returns zeroed memory

[Eugeniy Paltsev]

SGkgQ2hyaXN0b3BoLA0KDQpJIHRlc3Qga2VybmVsIGZyb20geW91ciAnZG1hLWFsbG9jLWFsd2F5
cy16ZXJvJyBicmFuY2gsIGFuZCBhcw0KSSBjYW4gc2VlIHdlIGhhdmUgRE1BIHBlcmlwaGVyYWxz
IChsaWtlIFVTQikgYnJva2VuLg0KDQpUaGVyZSBhcmUgdGhlIGVycm9ycyBleGFtcGxlIEkgZ290
IGR1cmluZyBVU0IgaW5pdGlhbGl6aW5nOg0KLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0t
PjgtLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLQ0KdXNiIDEtMTogZGV2aWNlIGRlc2Ny
aXB0b3IgcmVhZC82NCwgZXJyb3IgLTExMA0KdXNiIHVzYjEtcG9ydDE6IGF0dGVtcHQgcG93ZXIg
Y3ljbGUNCnVzYiAxLTE6IG5ldyBoaWdoLXNwZWVkIFVTQiBkZXZpY2UgbnVtYmVyIDQgdXNpbmcg
ZWhjaS1wbGF0Zm9ybQ0KdXNiIDEtMTogZGV2aWNlIGRlc2NyaXB0b3IgcmVhZC82NCwgZXJyb3Ig
LTExMA0KdXNiIDEtMTogZGV2aWNlIGRlc2NyaXB0b3IgcmVhZC82NCwgZXJyb3IgLTExMA0KdXNi
IDEtMTogbmV3IGhpZ2gtc3BlZWQgVVNCIGRldmljZSBudW1iZXIgNSB1c2luZyBlaGNpLXBsYXRm
b3JtDQp1c2IgMS0xOiBkZXZpY2UgZGVzY3JpcHRvciByZWFkLzY0LCBlcnJvciAtMTEwDQp1c2Ig
MS0xOiBkZXZpY2UgZGVzY3JpcHRvciByZWFkLzY0LCBlcnJvciAtMTEwDQp1c2IgdXNiMS1wb3J0
MTogdW5hYmxlIHRvIGVudW1lcmF0ZSBVU0IgZGV2aWNlDQp1c2IgMi0xOiBuZXcgZnVsbC1zcGVl
ZCBVU0IgZGV2aWNlIG51bWJlciAyIHVzaW5nIG9oY2ktcGxhdGZvcm0NCnVzYiAyLTE6IGRldmlj
ZSBkZXNjcmlwdG9yIHJlYWQvYWxsLCBlcnJvciAtODQNCnVzYiAyLTE6IG5ldyBmdWxsLXNwZWVk
IFVTQiBkZXZpY2UgbnVtYmVyIDMgdXNpbmcgb2hjaS1wbGF0Zm9ybQ0KdXNiIDItMTogZGV2aWNl
IGRlc2NyaXB0b3IgcmVhZC9hbGwsIGVycm9yIC04NA0KdXNiIHVzYjItcG9ydDE6IGF0dGVtcHQg
cG93ZXIgY3ljbGUNCnVzYiAyLTE6IG5ldyBmdWxsLXNwZWVkIFVTQiBkZXZpY2UgbnVtYmVyIDQg
dXNpbmcgb2hjaS1wbGF0Zm9ybQ0KdXNiIDItMTogZGV2aWNlIGRlc2NyaXB0b3IgcmVhZC84LCBl
cnJvciAtNjINCnVzYiAyLTE6IGRldmljZSBkZXNjcmlwdG9yIHJlYWQvOCwgZXJyb3IgLTYyDQp1
c2IgMi0xOiBuZXcgZnVsbC1zcGVlZCBVU0IgZGV2aWNlIG51bWJlciA1IHVzaW5nIG9oY2ktcGxh
dGZvcm0NCnVzYiAyLTE6IGRldmljZSBkZXNjcmlwdG9yIHJlYWQvOCwgZXJyb3IgLTg0DQp1c2Ig
Mi0xOiBkZXZpY2UgZGVzY3JpcHRvciByZWFkLzgsIGVycm9yIC04NA0KdXNiIHVzYjItcG9ydDE6
IHVuYWJsZSB0byBlbnVtZXJhdGUgVVNCIGRldmljZQ0KIFtzbmlwXQ0KLS0tLS0tLS0tLS0tLS0t
LS0tLS0tLS0tLS0tLS0tODwtLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLS0tLQ0KDQoNCk9u
IFdlZCwgMjAxOC0xMi0xOSBhdCAxNzo1OSArMDEwMCwgQ2hyaXN0b3BoIEhlbGx3aWcgd3JvdGU6
DQo+IEZZSSwgSSd2ZSBwaWNrZWQgdGhpcyB1cCBmb3IgZG1hLW1hcHBpbmcgZm9yLW5leHQgbm93
Lg0KPiANCj4gX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18N
Cj4gbGludXgtc25wcy1hcmMgbWFpbGluZyBsaXN0DQo+IGxpbnV4LXNucHMtYXJjQGxpc3RzLmlu
ZnJhZGVhZC5vcmcNCj4gaHR0cHM6Ly91cmxkZWZlbnNlLnByb29mcG9pbnQuY29tL3YyL3VybD91
PWh0dHAtM0FfX2xpc3RzLmluZnJhZGVhZC5vcmdfbWFpbG1hbl9saXN0aW5mb19saW51eC0yRHNu
cHMtMkRhcmMmZD1Ed0lDQWcmYz1EUEw2X1hfNkprWEZ4N0FYV3FCMHRnJnI9WmxKTg0KPiAxTXJp
UFVUa0JLQ3JQU3g2N0dtYXBsRVVHY0FFazl5UHRDTGRVWEkmbT1uYUJDVDk2QTRSU1FKTHpCV3p1
Q2NtcHRGR2lRRGZGVE9XSnBwcnFESVZrJnM9Y0hGODR2YTg5b2ZQNlZsclY2ODNld0VOVVhkYUxX
N29wYW1MWlNrWkJnayZlPQ0KLS0gDQogRXVnZW5peSBQYWx0c2V2

Re: ensure dma_alloc_coherent always returns zeroed memory

[Eugeniy Paltsev]

Hi Christoph,

I test kernel from your 'dma-alloc-always-zero' branch, and as
I can see we have DMA peripherals (like USB) broken.

There are the errors example I got during USB initializing:
------------------------------>8--------------------------------
usb 1-1: device descriptor read/64, error -110
usb usb1-port1: attempt power cycle
usb 1-1: new high-speed USB device number 4 using ehci-platform
usb 1-1: device descriptor read/64, error -110
usb 1-1: device descriptor read/64, error -110
usb 1-1: new high-speed USB device number 5 using ehci-platform
usb 1-1: device descriptor read/64, error -110
usb 1-1: device descriptor read/64, error -110
usb usb1-port1: unable to enumerate USB device
usb 2-1: new full-speed USB device number 2 using ohci-platform
usb 2-1: device descriptor read/all, error -84
usb 2-1: new full-speed USB device number 3 using ohci-platform
usb 2-1: device descriptor read/all, error -84
usb usb2-port1: attempt power cycle
usb 2-1: new full-speed USB device number 4 using ohci-platform
usb 2-1: device descriptor read/8, error -62
usb 2-1: device descriptor read/8, error -62
usb 2-1: new full-speed USB device number 5 using ohci-platform
usb 2-1: device descriptor read/8, error -84
usb 2-1: device descriptor read/8, error -84
usb usb2-port1: unable to enumerate USB device
 [snip]
------------------------------8<--------------------------------


On Wed, 2018-12-19 at 17:59 +0100, Christoph Hellwig wrote:
> FYI, I've picked this up for dma-mapping for-next now.
> 
> _______________________________________________
> linux-snps-arc mailing list
> linux-snps-arc@lists.infradead.org
> https://urldefense.proofpoint.com/v2/url?u=http-3A__lists.infradead.org_mailman_listinfo_linux-2Dsnps-2Darc&d=DwICAg&c=DPL6_X_6JkXFx7AXWqB0tg&r=ZlJN
> 1MriPUTkBKCrPSx67GmaplEUGcAEk9yPtCLdUXI&m=naBCT96A4RSQJLzBWzuCcmptFGiQDfFTOWJpprqDIVk&s=cHF84va89ofP6VlrV683ewENUXdaLW7opamLZSkZBgk&e=
-- 
 Eugeniy Paltsev

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

On Thu, Dec 20, 2018 at 02:32:52PM +0000, Eugeniy Paltsev wrote:
> Hi Christoph,
> 
> I test kernel from your 'dma-alloc-always-zero' branch, and as
> I can see we have DMA peripherals (like USB) broken.

I would be really surprised if that is caused by the patch to add
the zeroing.  Can you check which commit caused the issue by bisecting
from a known good baseline?

ensure dma_alloc_coherent always returns zeroed memory

[hch]

On Thu, Dec 20, 2018@02:32:52PM +0000, Eugeniy Paltsev wrote:
> Hi Christoph,
> 
> I test kernel from your 'dma-alloc-always-zero' branch, and as
> I can see we have DMA peripherals (like USB) broken.

I would be really surprised if that is caused by the patch to add
the zeroing.  Can you check which commit caused the issue by bisecting
from a known good baseline?

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

On Thu, Dec 20, 2018 at 02:32:52PM +0000, Eugeniy Paltsev wrote:
> Hi Christoph,
> 
> I test kernel from your 'dma-alloc-always-zero' branch, and as
> I can see we have DMA peripherals (like USB) broken.

I would be really surprised if that is caused by the patch to add
the zeroing.  Can you check which commit caused the issue by bisecting
from a known good baseline?

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

On Thu, Dec 20, 2018 at 02:32:52PM +0000, Eugeniy Paltsev wrote:
> Hi Christoph,
> 
> I test kernel from your 'dma-alloc-always-zero' branch, and as
> I can see we have DMA peripherals (like USB) broken.

I would be really surprised if that is caused by the patch to add
the zeroing.  Can you check which commit caused the issue by bisecting
from a known good baseline?

Re: ensure dma_alloc_coherent always returns zeroed memory

[Eugeniy Paltsev]

On Thu, 2018-12-20 at 15:34 +0100, hch@lst.de wrote:
> On Thu, Dec 20, 2018 at 02:32:52PM +0000, Eugeniy Paltsev wrote:
> > Hi Christoph,
> > 
> > I test kernel from your 'dma-alloc-always-zero' branch, and as
> > I can see we have DMA peripherals (like USB) broken.
> 
> I would be really surprised if that is caused by the patch to add
> the zeroing. 
Me too :)

>  Can you check which commit caused the issue by bisecting
> from a known good baseline?

Yep. At least kernel build from v4.20-rc4 (which is base for your branch)
seems to work fine.

-- 
 Eugeniy Paltsev

ensure dma_alloc_coherent always returns zeroed memory

[Eugeniy Paltsev]

On Thu, 2018-12-20@15:34 +0100, hch@lst.de wrote:
> On Thu, Dec 20, 2018@02:32:52PM +0000, Eugeniy Paltsev wrote:
> > Hi Christoph,
> > 
> > I test kernel from your 'dma-alloc-always-zero' branch, and as
> > I can see we have DMA peripherals (like USB) broken.
> 
> I would be really surprised if that is caused by the patch to add
> the zeroing. 
Me too :)

>  Can you check which commit caused the issue by bisecting
> from a known good baseline?

Yep. At least kernel build from v4.20-rc4 (which is base for your branch)
seems to work fine.

-- 
 Eugeniy Paltsev

Re: ensure dma_alloc_coherent always returns zeroed memory

[Eugeniy Paltsev]
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Re: ensure dma_alloc_coherent always returns zeroed memory

[Eugeniy Paltsev]

On Thu, 2018-12-20 at 15:34 +0100, hch@lst.de wrote:
> On Thu, Dec 20, 2018 at 02:32:52PM +0000, Eugeniy Paltsev wrote:
> > Hi Christoph,
> > 
> > I test kernel from your 'dma-alloc-always-zero' branch, and as
> > I can see we have DMA peripherals (like USB) broken.
> 
> I would be really surprised if that is caused by the patch to add
> the zeroing. 
Me too :)

>  Can you check which commit caused the issue by bisecting
> from a known good baseline?

Yep. At least kernel build from v4.20-rc4 (which is base for your branch)
seems to work fine.

-- 
 Eugeniy Paltsev

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

On Thu, Dec 20, 2018 at 02:39:20PM +0000, Eugeniy Paltsev wrote:
> > I would be really surprised if that is caused by the patch to add
> > the zeroing. 
> Me too :)
> 
> >  Can you check which commit caused the issue by bisecting
> > from a known good baseline?
> 
> Yep. At least kernel build from v4.20-rc4 (which is base for your branch)
> seems to work fine.

Well, the branch has quite a few commits.  Can you check the commit
just before the zeroing to start, and if that is already broken (which
I suspect) bisect the offending commit?

ensure dma_alloc_coherent always returns zeroed memory

[hch]

On Thu, Dec 20, 2018@02:39:20PM +0000, Eugeniy Paltsev wrote:
> > I would be really surprised if that is caused by the patch to add
> > the zeroing. 
> Me too :)
> 
> >  Can you check which commit caused the issue by bisecting
> > from a known good baseline?
> 
> Yep. At least kernel build from v4.20-rc4 (which is base for your branch)
> seems to work fine.

Well, the branch has quite a few commits.  Can you check the commit
just before the zeroing to start, and if that is already broken (which
I suspect) bisect the offending commit?

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

On Thu, Dec 20, 2018 at 02:39:20PM +0000, Eugeniy Paltsev wrote:
> > I would be really surprised if that is caused by the patch to add
> > the zeroing. 
> Me too :)
> 
> >  Can you check which commit caused the issue by bisecting
> > from a known good baseline?
> 
> Yep. At least kernel build from v4.20-rc4 (which is base for your branch)
> seems to work fine.

Well, the branch has quite a few commits.  Can you check the commit
just before the zeroing to start, and if that is already broken (which
I suspect) bisect the offending commit?

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

On Thu, Dec 20, 2018 at 02:39:20PM +0000, Eugeniy Paltsev wrote:
> > I would be really surprised if that is caused by the patch to add
> > the zeroing. 
> Me too :)
> 
> >  Can you check which commit caused the issue by bisecting
> > from a known good baseline?
> 
> Yep. At least kernel build from v4.20-rc4 (which is base for your branch)
> seems to work fine.

Well, the branch has quite a few commits.  Can you check the commit
just before the zeroing to start, and if that is already broken (which
I suspect) bisect the offending commit?

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

Btw, can you try wit the very latests dma-mapping-for-next tree
which has a new fix from Thierry Reding that might be related.

ensure dma_alloc_coherent always returns zeroed memory

[hch]

Btw, can you try wit the very latests dma-mapping-for-next tree
which has a new fix from Thierry Reding that might be related.

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

Btw, can you try wit the very latests dma-mapping-for-next tree
which has a new fix from Thierry Reding that might be related.

Re: ensure dma_alloc_coherent always returns zeroed memory

[hch]

Btw, can you try wit the very latests dma-mapping-for-next tree
which has a new fix from Thierry Reding that might be related.