All of lore.kernel.org
 help / color / mirror / Atom feed
From: Marcelo Tosatti <mtosatti-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: Alex Williamson
	<alex.williamson-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
	dwmw2-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH] intel-iommu: Fix off-by-one in pagetable freeing
Date: Thu, 23 Jan 2014 14:47:28 -0200	[thread overview]
Message-ID: <20140123164728.GA23854@amt.cnet> (raw)
In-Reply-To: <20131220193250.17903.48255.stgit-xdHQ/5r00wBBDLzU/O5InQ@public.gmane.org>

On Fri, Dec 20, 2013 at 12:33:43PM -0700, Alex Williamson wrote:
> dma_pte_free_level() has an off-by-one error when checking whether a
> pte is completely covered by a range.  Take for example the case of
> attempting to free pfn 0x0 - 0x1ff, ie. 512 entries covering the first
> 2M superpage.  The level_size() is 0x200 and we test:
> 
> static void dma_pte_free_level(...
> 	...
> 
> 	if (!(0 > 0 || 0x1ff < 0 + 0x200)) {
> 		...
> 	}
> 
> Clearly the 2nd test is true, which means we fail to take the branch
> to clear and free the pagetable entry.  As a result, we're leaking
> pagetables and failing to install new pages over the range.
> 
> This was found with a PCI device assigned to a QEMU guest using
> vfio-pci without a VGA device present.  The first 1M of guest
> address space is mapped with various combinations of 4K pages, but
> eventually the range is entirely freed and replaced with a 2M
> contiguous mapping.  intel-iommu errors out with something like:
> 
> ERROR: DMA PTE for vPFN 0x0 already set (to 5c2b8003 not 849c00083)
> 
> In this case 5c2b8003 is the pointer to the previous leaf page that
> was neither freed nor cleared and 849c00083 is the superpage entry
> that we're trying to replace it with.
> 
> Cc: stable-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> Signed-off-by: Alex Williamson <alex.williamson-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
> ---
>  drivers/iommu/intel-iommu.c |    2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index 43b9bfe..59779e1 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -917,7 +917,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
>  
>  		/* If range covers entire pagetable, free it */
>  		if (!(start_pfn > level_pfn ||
> -		      last_pfn < level_pfn + level_size(level))) {
> +		      last_pfn < level_pfn + level_size(level) - 1)) {
>  			dma_clear_pte(pte);
>  			domain_flush_cache(domain, pte, sizeof(*pte));
>  			free_pgtable_page(level_pte);

Reviewed-by: Marcelo Tosatti <mtosatti-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>

WARNING: multiple messages have this Message-ID (diff)
From: Marcelo Tosatti <mtosatti@redhat.com>
To: Alex Williamson <alex.williamson@redhat.com>
Cc: iommu@lists.linux-foundation.org, dwmw2@infradead.org,
	ddutile@redhat.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] intel-iommu: Fix off-by-one in pagetable freeing
Date: Thu, 23 Jan 2014 14:47:28 -0200	[thread overview]
Message-ID: <20140123164728.GA23854@amt.cnet> (raw)
In-Reply-To: <20131220193250.17903.48255.stgit@bling.home>

On Fri, Dec 20, 2013 at 12:33:43PM -0700, Alex Williamson wrote:
> dma_pte_free_level() has an off-by-one error when checking whether a
> pte is completely covered by a range.  Take for example the case of
> attempting to free pfn 0x0 - 0x1ff, ie. 512 entries covering the first
> 2M superpage.  The level_size() is 0x200 and we test:
> 
> static void dma_pte_free_level(...
> 	...
> 
> 	if (!(0 > 0 || 0x1ff < 0 + 0x200)) {
> 		...
> 	}
> 
> Clearly the 2nd test is true, which means we fail to take the branch
> to clear and free the pagetable entry.  As a result, we're leaking
> pagetables and failing to install new pages over the range.
> 
> This was found with a PCI device assigned to a QEMU guest using
> vfio-pci without a VGA device present.  The first 1M of guest
> address space is mapped with various combinations of 4K pages, but
> eventually the range is entirely freed and replaced with a 2M
> contiguous mapping.  intel-iommu errors out with something like:
> 
> ERROR: DMA PTE for vPFN 0x0 already set (to 5c2b8003 not 849c00083)
> 
> In this case 5c2b8003 is the pointer to the previous leaf page that
> was neither freed nor cleared and 849c00083 is the superpage entry
> that we're trying to replace it with.
> 
> Cc: stable@vger.kernel.org
> Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
> ---
>  drivers/iommu/intel-iommu.c |    2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index 43b9bfe..59779e1 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -917,7 +917,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
>  
>  		/* If range covers entire pagetable, free it */
>  		if (!(start_pfn > level_pfn ||
> -		      last_pfn < level_pfn + level_size(level))) {
> +		      last_pfn < level_pfn + level_size(level) - 1)) {
>  			dma_clear_pte(pte);
>  			domain_flush_cache(domain, pte, sizeof(*pte));
>  			free_pgtable_page(level_pte);

Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>


  parent reply	other threads:[~2014-01-23 16:47 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-12-20 19:33 [PATCH] intel-iommu: Fix off-by-one in pagetable freeing Alex Williamson
2013-12-20 19:33 ` Alex Williamson
     [not found] ` <20131220193250.17903.48255.stgit-xdHQ/5r00wBBDLzU/O5InQ@public.gmane.org>
2014-01-23 16:47   ` Marcelo Tosatti [this message]
2014-01-23 16:47     ` Marcelo Tosatti

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140123164728.GA23854@amt.cnet \
    --to=mtosatti-h+wxahxf7alqt0dzr+alfa@public.gmane.org \
    --cc=alex.williamson-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=dwmw2-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org \
    --cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
    --cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.