[PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[Hillf Danton]

The DMA buffer allocated is always cleared in DMA core and this is
making DMA_ATTR_NO_KERNEL_MAPPING non-special.

Fixes: d98849aff879 ("dma-direct: handle DMA_ATTR_NO_KERNEL_MAPPING in common code")
Cc: Kees Cook <keescook@chromium.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Hillf Danton <hdanton@sina.com>
---

--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -178,9 +178,17 @@ void *dma_direct_alloc_pages(struct devi
 
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
 	    !force_dma_unencrypted(dev)) {
+		int i;
+
 		/* remove any dirty cache lines on the kernel alias */
 		if (!PageHighMem(page))
 			arch_dma_prep_coherent(page, size);
+
+		for (i = 0; i < size/PAGE_SIZE; i++) {
+			ret = kmap_atomic(page + i);
+			memset(ret, 0, PAGE_SIZE);
+			kunmap_atomic(ret);
+		}
 		/* return the page pointer as the opaque cookie */
 		ret = page;
 		goto done;
--


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[James Bottomley]

On Fri, 2020-09-04 at 23:25 +0800, Hillf Danton wrote:
> The DMA buffer allocated is always cleared in DMA core and this is
> making DMA_ATTR_NO_KERNEL_MAPPING non-special.
> 
> Fixes: d98849aff879 ("dma-direct: handle DMA_ATTR_NO_KERNEL_MAPPING
> in common code")
> Cc: Kees Cook <keescook@chromium.org>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Marek Szyprowski <m.szyprowski@samsung.com>
> Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
> Signed-off-by: Hillf Danton <hdanton@sina.com>
> ---
> 
> --- a/kernel/dma/direct.c
> +++ b/kernel/dma/direct.c
> @@ -178,9 +178,17 @@ void *dma_direct_alloc_pages(struct devi
>  
>  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
>  	    !force_dma_unencrypted(dev)) {
> +		int i;
> +
>  		/* remove any dirty cache lines on the kernel alias
> */
>  		if (!PageHighMem(page))
>  			arch_dma_prep_coherent(page, size);
> +
> +		for (i = 0; i < size/PAGE_SIZE; i++) {
> +			ret = kmap_atomic(page + i);
> +			memset(ret, 0, PAGE_SIZE);
> +			kunmap_atomic(ret);

This is massively expensive on PARISC and likely other VIPT/VIVT
architectures.  What's the reason for clearing it?  This could also be
really inefficient even on PIPT architectures if the memory is device
remote.

If we really have to do this, it should likely be done in the arch or
driver hooks because there are potentially more efficient ways we can
do this knowing how the architecture behaves.

James


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[Hillf Danton]

On Fri, 04 Sep 2020 08:34:39 -0700 James Bottomley wrote:
> On Fri, 2020-09-04 at 23:25 +0800, Hillf Danton wrote:
> > The DMA buffer allocated is always cleared in DMA core and this is
> > making DMA_ATTR_NO_KERNEL_MAPPING non-special.
> > 
> > Fixes: d98849aff879 ("dma-direct: handle DMA_ATTR_NO_KERNEL_MAPPING
> > in common code")
> > Cc: Kees Cook <keescook@chromium.org>
> > Cc: Matthew Wilcox <willy@infradead.org>
> > Cc: Marek Szyprowski <m.szyprowski@samsung.com>
> > Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
> > Signed-off-by: Hillf Danton <hdanton@sina.com>
> > ---
> > 
> > --- a/kernel/dma/direct.c
> > +++ b/kernel/dma/direct.c
> > @@ -178,9 +178,17 @@ void *dma_direct_alloc_pages(struct devi
> >  
> >  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> >  	    !force_dma_unencrypted(dev)) {
> > +		int i;
> > +
> >  		/* remove any dirty cache lines on the kernel alias
> > */
> >  		if (!PageHighMem(page))
> >  			arch_dma_prep_coherent(page, size);
> > +
> > +		for (i = 0; i < size/PAGE_SIZE; i++) {
> > +			ret = kmap_atomic(page + i);
> > +			memset(ret, 0, PAGE_SIZE);
> > +			kunmap_atomic(ret);

Hi James
> 
> This is massively expensive on PARISC and likely other VIPT/VIVT
> architectures.

Correct.

> What's the reason for clearing it?  This could also be

	/* we always manually zero the memory once we are done: */
	gfp &= ~__GFP_ZERO;
	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
					   &phys_limit);

> really inefficient even on PIPT architectures if the memory is device
> remote.
> 
> If we really have to do this, it should likely be done in the arch or
> driver hooks because there are potentially more efficient ways we can
> do this knowing how the architecture behaves.

I'm open to any vintage ideas in your mind wrt clearing dma buf e.g
on platforms like PARISC. Or feel free to offload me the work if it
makes sense to you who are rich of PARISC knowledge.

Hillf


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[James Bottomley]

On Sat, 2020-09-05 at 15:35 +0800, Hillf Danton wrote:
> On Fri, 04 Sep 2020 08:34:39 -0700 James Bottomley wrote:
> > On Fri, 2020-09-04 at 23:25 +0800, Hillf Danton wrote:
> > > The DMA buffer allocated is always cleared in DMA core and this
> > > is making DMA_ATTR_NO_KERNEL_MAPPING non-special.
> > > 
> > > Fixes: d98849aff879 ("dma-direct: handle
> > > DMA_ATTR_NO_KERNEL_MAPPING
> > > in common code")
> > > Cc: Kees Cook <keescook@chromium.org>
> > > Cc: Matthew Wilcox <willy@infradead.org>
> > > Cc: Marek Szyprowski <m.szyprowski@samsung.com>
> > > Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
> > > Signed-off-by: Hillf Danton <hdanton@sina.com>
> > > ---
> > > 
> > > --- a/kernel/dma/direct.c
> > > +++ b/kernel/dma/direct.c
> > > @@ -178,9 +178,17 @@ void *dma_direct_alloc_pages(struct devi
> > >  
> > >  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> > >  	    !force_dma_unencrypted(dev)) {
> > > +		int i;
> > > +
> > >  		/* remove any dirty cache lines on the kernel
> > > alias
> > > */
> > >  		if (!PageHighMem(page))
> > >  			arch_dma_prep_coherent(page, size);
> > > +
> > > +		for (i = 0; i < size/PAGE_SIZE; i++) {
> > > +			ret = kmap_atomic(page + i);
> > > +			memset(ret, 0, PAGE_SIZE);
> > > +			kunmap_atomic(ret);
> 
> Hi James
> > 
> > This is massively expensive on PARISC and likely other VIPT/VIVT
> > architectures.
> 
> Correct.
>
> > What's the reason for clearing it?  This could also be
> 
> 	/* we always manually zero the memory once we are done: */
> 	gfp &= ~__GFP_ZERO;
> 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
> 					   &phys_limit);

That's not a reason ... that comment was put in for coherent mappings. 
What is the reason we should incur all this expense for clearing pages
which aren't unmapped in the kernel, because we can update the comment?
 The usual rationale for kernel mapped pages is security, because they
may leak information but unmapped pages shouldn't have this problem.

> > really inefficient even on PIPT architectures if the memory is
> > device remote.
> > 
> > If we really have to do this, it should likely be done in the arch
> > or driver hooks because there are potentially more efficient ways
> > we can do this knowing how the architecture behaves.
> 
> I'm open to any vintage ideas in your mind wrt clearing dma buf e.g
> on platforms like PARISC. Or feel free to offload me the work if it
> makes sense to you who are rich of PARISC knowledge.

OK, I've cc'd linux-arch because this is a problem for more than just
parisc.  However, not having to do it is the best solution ... sort of
the doctor, doctor it hurts when I do this answer.

James


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[James Bottomley]

[resend with correct linux-arch address]
On Sat, 2020-09-05 at 15:35 +0800, Hillf Danton wrote:
> On Fri, 04 Sep 2020 08:34:39 -0700 James Bottomley wrote:
> > On Fri, 2020-09-04 at 23:25 +0800, Hillf Danton wrote:
> > > The DMA buffer allocated is always cleared in DMA core and this
> > > is making DMA_ATTR_NO_KERNEL_MAPPING non-special.
> > > 
> > > Fixes: d98849aff879 ("dma-direct: handle
> > > DMA_ATTR_NO_KERNEL_MAPPING
> > > in common code")
> > > Cc: Kees Cook <keescook@chromium.org>
> > > Cc: Matthew Wilcox <willy@infradead.org>
> > > Cc: Marek Szyprowski <m.szyprowski@samsung.com>
> > > Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
> > > Signed-off-by: Hillf Danton <hdanton@sina.com>
> > > ---
> > > 
> > > --- a/kernel/dma/direct.c
> > > +++ b/kernel/dma/direct.c
> > > @@ -178,9 +178,17 @@ void *dma_direct_alloc_pages(struct devi
> > >  
> > >  	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
> > >  	    !force_dma_unencrypted(dev)) {
> > > +		int i;
> > > +
> > >  		/* remove any dirty cache lines on the kernel
> > > alias
> > > */
> > >  		if (!PageHighMem(page))
> > >  			arch_dma_prep_coherent(page, size);
> > > +
> > > +		for (i = 0; i < size/PAGE_SIZE; i++) {
> > > +			ret = kmap_atomic(page + i);
> > > +			memset(ret, 0, PAGE_SIZE);
> > > +			kunmap_atomic(ret);
> 
> Hi James
> > 
> > This is massively expensive on PARISC and likely other VIPT/VIVT
> > architectures.
> 
> Correct.
> 
> > What's the reason for clearing it?  This could also be
> 
> 	/* we always manually zero the memory once we are done: */
> 	gfp &= ~__GFP_ZERO;
> 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
> 					   &phys_limit);

That's not a reason ... that comment was put in for coherent mappings. 
What is the reason we should incur all this expense for clearing pages
which aren't unmapped in the kernel, because we can update the comment?
 The usual rationale for kernel mapped pages is security, because they
may leak information but unmapped pages shouldn't have this problem.

> > really inefficient even on PIPT architectures if the memory is
> > device remote.
> > 
> > If we really have to do this, it should likely be done in the arch
> > or driver hooks because there are potentially more efficient ways
> > we can do this knowing how the architecture behaves.
> 
> I'm open to any vintage ideas in your mind wrt clearing dma buf e.g
> on platforms like PARISC. Or feel free to offload me the work if it
> makes sense to you who are rich of PARISC knowledge.

OK, I've cc'd linux-arch because this is a problem for more than just
parisc.  However, not having to do it is the best solution ... sort of
the doctor, doctor it hurts when I do this answer.

James


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[Hillf Danton]

On Sat, 05 Sep 2020 08:50:42 -0700 James Bottomley wrote:
> [resend with correct linux-arch address]
> On Sat, 2020-09-05 at 15:35 +0800, Hillf Danton wrote:
> > On Fri, 04 Sep 2020 08:34:39 -0700 James Bottomley wrote:
[...]
> > Hi James
> > > 
> > > This is massively expensive on PARISC and likely other VIPT/VIVT
> > > architectures.
> > 
> > Correct.
> > 
> > > What's the reason for clearing it?  This could also be
> > 
> > 	/* we always manually zero the memory once we are done: */
> > 	gfp &= ~__GFP_ZERO;
> > 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
> > 					   &phys_limit);
> 
> That's not a reason ... that comment was put in for coherent mappings. 

It's quite likely that I misread it.

> What is the reason we should incur all this expense for clearing pages
> which aren't unmapped in the kernel, because we can update the comment?

A tough question.

> The usual rationale for kernel mapped pages is security, because they
> may leak information but unmapped pages shouldn't have this problem.

We can turn to Marek for some more light on the concerns you have
about security, particularly linked to DMA_ATTR_NO_KERNEL_MAPPING,
after the patch [1] fails to answer your question.

[1] Subject: [PATCH 1/3] common: DMA-mapping: add DMA_ATTR_NO_KERNEL_MAPPING attribute
https://lore.kernel.org/lkml/1337273586-11089-2-git-send-email-m.szyprowski@samsung.com/

> 
> > > really inefficient even on PIPT architectures if the memory is
> > > device remote.
> > > 
> > > If we really have to do this, it should likely be done in the arch
> > > or driver hooks because there are potentially more efficient ways
> > > we can do this knowing how the architecture behaves.
> > 
> > I'm open to any vintage ideas in your mind wrt clearing dma buf e.g
> > on platforms like PARISC. Or feel free to offload me the work if it
> > makes sense to you who are rich of PARISC knowledge.
> 
> OK, I've cc'd linux-arch because this is a problem for more than just
> parisc.  However, not having to do it is the best solution ... sort of
> the doctor, doctor it hurts when I do this answer.
> 
> James


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[Marek Szyprowski]

Hi James,

On 05.09.2020 17:50, James Bottomley wrote:
> [resend with correct linux-arch address]
> On Sat, 2020-09-05 at 15:35 +0800, Hillf Danton wrote:
>> On Fri, 04 Sep 2020 08:34:39 -0700 James Bottomley wrote:
>>> On Fri, 2020-09-04 at 23:25 +0800, Hillf Danton wrote:
>>>> The DMA buffer allocated is always cleared in DMA core and this
>>>> is making DMA_ATTR_NO_KERNEL_MAPPING non-special.
>>>>
>>>> Fixes: d98849aff879 ("dma-direct: handle
>>>> DMA_ATTR_NO_KERNEL_MAPPING
>>>> in common code")
>>>> Cc: Kees Cook <keescook@chromium.org>
>>>> Cc: Matthew Wilcox <willy@infradead.org>
>>>> Cc: Marek Szyprowski <m.szyprowski@samsung.com>
>>>> Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
>>>> Signed-off-by: Hillf Danton <hdanton@sina.com>
>>>> ---
>>>>
>>>> --- a/kernel/dma/direct.c
>>>> +++ b/kernel/dma/direct.c
>>>> @@ -178,9 +178,17 @@ void *dma_direct_alloc_pages(struct devi
>>>>   
>>>>   	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
>>>>   	    !force_dma_unencrypted(dev)) {
>>>> +		int i;
>>>> +
>>>>   		/* remove any dirty cache lines on the kernel
>>>> alias
>>>> */
>>>>   		if (!PageHighMem(page))
>>>>   			arch_dma_prep_coherent(page, size);
>>>> +
>>>> +		for (i = 0; i < size/PAGE_SIZE; i++) {
>>>> +			ret = kmap_atomic(page + i);
>>>> +			memset(ret, 0, PAGE_SIZE);
>>>> +			kunmap_atomic(ret);
>> Hi James
>>> This is massively expensive on PARISC and likely other VIPT/VIVT
>>> architectures.
>> Correct.
>>
>>> What's the reason for clearing it?  This could also be
>> 	/* we always manually zero the memory once we are done: */
>> 	gfp &= ~__GFP_ZERO;
>> 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
>> 					   &phys_limit);
> That's not a reason ... that comment was put in for coherent mappings.
> What is the reason we should incur all this expense for clearing pages
> which aren't unmapped in the kernel, because we can update the comment?
>   The usual rationale for kernel mapped pages is security, because they
> may leak information but unmapped pages shouldn't have this problem.

Any dma_alloc_attrs() buffer might be mmaped to userspace, so the 
security reason is still valid. Possible lack if kernel mapping was only 
a hint that driver doesn't need it, so it might be skipped on some 
architectures, where creating it requires significant resources (i.e. 
vmalloc area).

>>> really inefficient even on PIPT architectures if the memory is
>>> device remote.
>>>
>>> If we really have to do this, it should likely be done in the arch
>>> or driver hooks because there are potentially more efficient ways
>>> we can do this knowing how the architecture behaves.
>> I'm open to any vintage ideas in your mind wrt clearing dma buf e.g
>> on platforms like PARISC. Or feel free to offload me the work if it
>> makes sense to you who are rich of PARISC knowledge.
> OK, I've cc'd linux-arch because this is a problem for more than just
> parisc.  However, not having to do it is the best solution ... sort of
> the doctor, doctor it hurts when I do this answer.

Best regards
-- 
Marek Szyprowski, PhD
Samsung R&D Institute Poland


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

Re: [PATCH] dma-direct: zero out DMA_ATTR_NO_KERNEL_MAPPING buf

[Christoph Hellwig]

On Mon, Sep 07, 2020 at 09:02:34AM +0200, Marek Szyprowski wrote:
> > That's not a reason ... that comment was put in for coherent mappings.
> > What is the reason we should incur all this expense for clearing pages
> > which aren't unmapped in the kernel, because we can update the comment?
> >   The usual rationale for kernel mapped pages is security, because they
> > may leak information but unmapped pages shouldn't have this problem.
> 
> Any dma_alloc_attrs() buffer might be mmaped to userspace, so the 
> security reason is still valid. Possible lack if kernel mapping was only 
> a hint that driver doesn't need it, so it might be skipped on some 
> architectures, where creating it requires significant resources (i.e. 
> vmalloc area).

Yes.  It seems actually mapping it to userspace in media/drm drivers
seems to be one of the big use cases.  There other one is memory not
used by the host at all and just as an extra buffer for hardware so
that the PCIe device can cut down on DRAM cost.  For that could
potentially skip the zeroing, but then again you'd need to trust the
device, which with thunderbolt might not always be a good idea.

_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme