LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
* [PATCH 0/3] Sync unmappings in vmalloc/ioremap areas
@ 2019-07-15 11:02 Joerg Roedel
  2019-07-15 11:02 ` [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one() Joerg Roedel
                   ` (2 more replies)
  0 siblings, 3 replies; 8+ messages in thread
From: Joerg Roedel @ 2019-07-15 11:02 UTC (permalink / raw)
  To: Dave Hansen, Andy Lutomirski, Peter Zijlstra, Thomas Gleixner,
	Ingo Molnar, Borislav Petkov
  Cc: Andrew Morton, linux-kernel, linux-mm, Joerg Roedel

Hi,

here is a small patch-set to sync unmappings in the
vmalloc/ioremap areas between page-tables in the system.

This is only needed x86-32 with !SHARED_KERNEL_PMD, which is
the case on a PAE kernel with PTI enabled.

On affected systems the missing sync causes old mappings to
persist in some page-tables, causing data corruption and
other undefined behavior.

Please review.

Thanks,

	Joerg

Joerg Roedel (3):
  x86/mm: Check for pfn instead of page in vmalloc_sync_one()
  x86/mm: Sync also unmappings in vmalloc_sync_one()
  mm/vmalloc: Sync unmappings in vunmap_page_range()

 arch/x86/mm/fault.c | 9 +++++----
 mm/vmalloc.c        | 2 ++
 2 files changed, 7 insertions(+), 4 deletions(-)

-- 
2.17.1


^ permalink raw reply	[flat|nested] 8+ messages in thread

* [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one()
  2019-07-15 11:02 [PATCH 0/3] Sync unmappings in vmalloc/ioremap areas Joerg Roedel
@ 2019-07-15 11:02 ` Joerg Roedel
  2019-07-15 13:08   ` Thomas Gleixner
  2019-07-15 11:02 ` [PATCH 2/3] x86/mm: Sync also unmappings " Joerg Roedel
  2019-07-15 11:02 ` [PATCH 3/3] mm/vmalloc: Sync unmappings in vunmap_page_range() Joerg Roedel
  2 siblings, 1 reply; 8+ messages in thread
From: Joerg Roedel @ 2019-07-15 11:02 UTC (permalink / raw)
  To: Dave Hansen, Andy Lutomirski, Peter Zijlstra, Thomas Gleixner,
	Ingo Molnar, Borislav Petkov
  Cc: Andrew Morton, linux-kernel, linux-mm, Joerg Roedel

From: Joerg Roedel <jroedel@suse.de>

Do not require a struct page for the mapped memory location
because it might not exist. This can happen when an
ioremapped region is mapped with 2MB pages.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/x86/mm/fault.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 794f364cb882..4a4049f6d458 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -200,7 +200,7 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	if (!pmd_present(*pmd))
 		set_pmd(pmd, *pmd_k);
 	else
-		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
+		BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k));
 
 	return pmd_k;
 }
-- 
2.17.1


^ permalink raw reply	[flat|nested] 8+ messages in thread

* [PATCH 2/3] x86/mm: Sync also unmappings in vmalloc_sync_one()
  2019-07-15 11:02 [PATCH 0/3] Sync unmappings in vmalloc/ioremap areas Joerg Roedel
  2019-07-15 11:02 ` [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one() Joerg Roedel
@ 2019-07-15 11:02 ` Joerg Roedel
  2019-07-15 13:08   ` Thomas Gleixner
  2019-07-15 11:02 ` [PATCH 3/3] mm/vmalloc: Sync unmappings in vunmap_page_range() Joerg Roedel
  2 siblings, 1 reply; 8+ messages in thread
From: Joerg Roedel @ 2019-07-15 11:02 UTC (permalink / raw)
  To: Dave Hansen, Andy Lutomirski, Peter Zijlstra, Thomas Gleixner,
	Ingo Molnar, Borislav Petkov
  Cc: Andrew Morton, linux-kernel, linux-mm, Joerg Roedel

From: Joerg Roedel <jroedel@suse.de>

With huge-page ioremap areas the unmappings also need to be
synced between all page-tables. Otherwise it can cause data
corruption when a region is unmapped and later re-used.

Make the vmalloc_sync_one() function ready to sync
unmappings.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/x86/mm/fault.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 4a4049f6d458..d71e167662c3 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -194,11 +194,12 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 
 	pmd = pmd_offset(pud, address);
 	pmd_k = pmd_offset(pud_k, address);
-	if (!pmd_present(*pmd_k))
-		return NULL;
 
-	if (!pmd_present(*pmd))
+	if (pmd_present(*pmd) ^ pmd_present(*pmd_k))
 		set_pmd(pmd, *pmd_k);
+
+	if (!pmd_present(*pmd_k))
+		return NULL;
 	else
 		BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k));
 
-- 
2.17.1


^ permalink raw reply	[flat|nested] 8+ messages in thread

* [PATCH 3/3] mm/vmalloc: Sync unmappings in vunmap_page_range()
  2019-07-15 11:02 [PATCH 0/3] Sync unmappings in vmalloc/ioremap areas Joerg Roedel
  2019-07-15 11:02 ` [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one() Joerg Roedel
  2019-07-15 11:02 ` [PATCH 2/3] x86/mm: Sync also unmappings " Joerg Roedel
@ 2019-07-15 11:02 ` Joerg Roedel
  2 siblings, 0 replies; 8+ messages in thread
From: Joerg Roedel @ 2019-07-15 11:02 UTC (permalink / raw)
  To: Dave Hansen, Andy Lutomirski, Peter Zijlstra, Thomas Gleixner,
	Ingo Molnar, Borislav Petkov
  Cc: Andrew Morton, linux-kernel, linux-mm, Joerg Roedel

From: Joerg Roedel <jroedel@suse.de>

On x86-32 with PTI enabled, parts of the kernel page-tables
are not shared between processes. This can cause mappings in
the vmalloc/ioremap area to persist in some page-tables
after the regions is unmapped and released.

When the region is re-used the processes with the old
mappings do not fault in the new mappings but still access
the old ones.

This causes undefined behavior, in reality often data
corruption, kernel oopses and panics and even spontaneous
reboots.

Fix this problem by activly syncing unmaps in the
vmalloc/ioremap area to all page-tables in the system.

References: https://bugzilla.suse.com/show_bug.cgi?id=1118689
Fixes: 7757d607c6b3 ('x86/pti: Allow CONFIG_PAGE_TABLE_ISOLATION for x86_32')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 mm/vmalloc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4fa8d84599b0..322b11a374fd 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -132,6 +132,8 @@ static void vunmap_page_range(unsigned long addr, unsigned long end)
 			continue;
 		vunmap_p4d_range(pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
+
+	vmalloc_sync_all();
 }
 
 static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
-- 
2.17.1


^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH 2/3] x86/mm: Sync also unmappings in vmalloc_sync_one()
  2019-07-15 11:02 ` [PATCH 2/3] x86/mm: Sync also unmappings " Joerg Roedel
@ 2019-07-15 13:08   ` Thomas Gleixner
  0 siblings, 0 replies; 8+ messages in thread
From: Thomas Gleixner @ 2019-07-15 13:08 UTC (permalink / raw)
  To: Joerg Roedel
  Cc: Dave Hansen, Andy Lutomirski, Peter Zijlstra, Ingo Molnar,
	Borislav Petkov, Andrew Morton, linux-kernel, linux-mm,
	Joerg Roedel

On Mon, 15 Jul 2019, Joerg Roedel wrote:

> From: Joerg Roedel <jroedel@suse.de>
> 
> With huge-page ioremap areas the unmappings also need to be
> synced between all page-tables. Otherwise it can cause data
> corruption when a region is unmapped and later re-used.
> 
> Make the vmalloc_sync_one() function ready to sync
> unmappings.
> 
> Signed-off-by: Joerg Roedel <jroedel@suse.de>

Lacks a Fixes tag methinks.

> ---
>  arch/x86/mm/fault.c | 7 ++++---
>  1 file changed, 4 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
> index 4a4049f6d458..d71e167662c3 100644
> --- a/arch/x86/mm/fault.c
> +++ b/arch/x86/mm/fault.c
> @@ -194,11 +194,12 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
>  
>  	pmd = pmd_offset(pud, address);
>  	pmd_k = pmd_offset(pud_k, address);
> -	if (!pmd_present(*pmd_k))
> -		return NULL;
>  
> -	if (!pmd_present(*pmd))
> +	if (pmd_present(*pmd) ^ pmd_present(*pmd_k))
>  		set_pmd(pmd, *pmd_k);

It took me a while to understand what this is doing. Can we please have a
comment here?

> +
> +	if (!pmd_present(*pmd_k))
> +		return NULL;

Thanks,

	tglx

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one()
  2019-07-15 11:02 ` [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one() Joerg Roedel
@ 2019-07-15 13:08   ` Thomas Gleixner
  2019-07-15 15:44     ` Joerg Roedel
  0 siblings, 1 reply; 8+ messages in thread
From: Thomas Gleixner @ 2019-07-15 13:08 UTC (permalink / raw)
  To: Joerg Roedel
  Cc: Dave Hansen, Andy Lutomirski, Peter Zijlstra, Ingo Molnar,
	Borislav Petkov, Andrew Morton, linux-kernel, linux-mm,
	Joerg Roedel

On Mon, 15 Jul 2019, Joerg Roedel wrote:

> From: Joerg Roedel <jroedel@suse.de>
> 
> Do not require a struct page for the mapped memory location
> because it might not exist. This can happen when an
> ioremapped region is mapped with 2MB pages.
> 
> Signed-off-by: Joerg Roedel <jroedel@suse.de>

Lacks a Fixes tag, hmm?


^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one()
  2019-07-15 13:08   ` Thomas Gleixner
@ 2019-07-15 15:44     ` Joerg Roedel
  2019-07-15 18:48       ` Thomas Gleixner
  0 siblings, 1 reply; 8+ messages in thread
From: Joerg Roedel @ 2019-07-15 15:44 UTC (permalink / raw)
  To: Thomas Gleixner
  Cc: Joerg Roedel, Dave Hansen, Andy Lutomirski, Peter Zijlstra,
	Ingo Molnar, Borislav Petkov, Andrew Morton, linux-kernel,
	linux-mm

On Mon, Jul 15, 2019 at 03:08:42PM +0200, Thomas Gleixner wrote:
> On Mon, 15 Jul 2019, Joerg Roedel wrote:
> 
> > From: Joerg Roedel <jroedel@suse.de>
> > 
> > Do not require a struct page for the mapped memory location
> > because it might not exist. This can happen when an
> > ioremapped region is mapped with 2MB pages.
> > 
> > Signed-off-by: Joerg Roedel <jroedel@suse.de>
> 
> Lacks a Fixes tag, hmm?

Yeah, right, the question is, which commit to put in there. The problem
results from two changes:

	1) Introduction of !SHARED_KERNEL_PMD path in x86-32. In itself
	   this is not a problem, and the path was only enabled for
	   Xen-PV.

	2) Huge IORemapings which use the PMD level. Also not a problem
	   by itself, but together with !SHARED_KERNEL_PMD problematic
	   because it requires to sync the PMD entries between all
	   page-tables, and that was not implemented.

Before PTI-x32 was merged this problem did not show up, maybe because
the 32-bit Xen-PV users did not trigger it. But with PTI-x32 all PAE
users run with !SHARED_KERNEL_PMD and the problem popped up.

For the last patch I put the PTI-x32 enablement commit in the fixes tag,
because that was the one that showed up during bisection. But more
correct would probably be

	5d72b4fba40e ('x86, mm: support huge I/O mapping capability I/F')

Or do I miss something?

Regards,

	Joerg



^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one()
  2019-07-15 15:44     ` Joerg Roedel
@ 2019-07-15 18:48       ` Thomas Gleixner
  0 siblings, 0 replies; 8+ messages in thread
From: Thomas Gleixner @ 2019-07-15 18:48 UTC (permalink / raw)
  To: Joerg Roedel
  Cc: Joerg Roedel, Dave Hansen, Andy Lutomirski, Peter Zijlstra,
	Ingo Molnar, Borislav Petkov, Andrew Morton, linux-kernel,
	linux-mm

On Mon, 15 Jul 2019, Joerg Roedel wrote:
> On Mon, Jul 15, 2019 at 03:08:42PM +0200, Thomas Gleixner wrote:
> > On Mon, 15 Jul 2019, Joerg Roedel wrote:
> > 
> > > From: Joerg Roedel <jroedel@suse.de>
> > > 
> > > Do not require a struct page for the mapped memory location
> > > because it might not exist. This can happen when an
> > > ioremapped region is mapped with 2MB pages.
> > > 
> > > Signed-off-by: Joerg Roedel <jroedel@suse.de>
> > 
> > Lacks a Fixes tag, hmm?
> 
> Yeah, right, the question is, which commit to put in there. The problem
> results from two changes:
> 
> 	1) Introduction of !SHARED_KERNEL_PMD path in x86-32. In itself
> 	   this is not a problem, and the path was only enabled for
> 	   Xen-PV.
> 
> 	2) Huge IORemapings which use the PMD level. Also not a problem
> 	   by itself, but together with !SHARED_KERNEL_PMD problematic
> 	   because it requires to sync the PMD entries between all
> 	   page-tables, and that was not implemented.
> 
> Before PTI-x32 was merged this problem did not show up, maybe because
> the 32-bit Xen-PV users did not trigger it. But with PTI-x32 all PAE
> users run with !SHARED_KERNEL_PMD and the problem popped up.
> 
> For the last patch I put the PTI-x32 enablement commit in the fixes tag,
> because that was the one that showed up during bisection. But more
> correct would probably be
> 
> 	5d72b4fba40e ('x86, mm: support huge I/O mapping capability I/F')

Looks about right.

Thanks,

	tglx

^ permalink raw reply	[flat|nested] 8+ messages in thread

end of thread, other threads:[~2019-07-15 18:48 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-07-15 11:02 [PATCH 0/3] Sync unmappings in vmalloc/ioremap areas Joerg Roedel
2019-07-15 11:02 ` [PATCH 1/3] x86/mm: Check for pfn instead of page in vmalloc_sync_one() Joerg Roedel
2019-07-15 13:08   ` Thomas Gleixner
2019-07-15 15:44     ` Joerg Roedel
2019-07-15 18:48       ` Thomas Gleixner
2019-07-15 11:02 ` [PATCH 2/3] x86/mm: Sync also unmappings " Joerg Roedel
2019-07-15 13:08   ` Thomas Gleixner
2019-07-15 11:02 ` [PATCH 3/3] mm/vmalloc: Sync unmappings in vunmap_page_range() Joerg Roedel

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).