Re: [ 10/65] ARM: 7467/1: mutex: use generic xchg-based implementation for ARMv6+

[Will Deacon]

Hi Ben,

On Wed, Aug 15, 2012 at 05:29:26AM +0100, Ben Hutchings wrote:
> On Mon, 2012-08-13 at 15:13 -0700, Greg Kroah-Hartman wrote:
> > From: Greg KH 
> > 
> > 3.4-stable review patch.  If anyone has any objections, please let me know.
> > 
> > --
> > 
> > From: Will Deacon 
> > 
> > commit a76d7bd96d65fa5119adba97e1b58d95f2e78829 upstream.
> > 
> > The open-coded mutex implementation for ARMv6+ cores suffers from a
> > severe lack of barriers, so in the uncontended case we don't actually
> > protect any accesses performed during the critical section.
> > 
> > Furthermore, the code is largely a duplication of the ARMv6+ atomic_dec
> > code but optimised to remove a branch instruction, as the mutex fastpath
> > was previously inlined. Now that this is executed out-of-line, we can
> > reuse the atomic access code for the locking (in fact, we use the xchg
> > code as this produces shorter critical sections).
> > 
> > This patch uses the generic xchg based implementation for mutexes on
> > ARMv6+, which introduces barriers to the lock/unlock operations and also
> > has the benefit of removing a fair amount of inline assembly code.
> [...]
> 
> I understand that a further fix is needed on top of this
>  but it's
> not in Linus's tree yet.  Is it better to apply this on its own or to
> wait for the complete fix?

The additional patch should also be CC'd to stable and is sitting in -tip
somewhere I believe, so it shouldn't be long before it does hit mainline.

Without this patch there's a memory-ordering bug (which we seem to have hit
once in > 5 years). With the patch there's a mutex lockup issue on SMP systems
that I can provoke with enough hackbenching, so you may want to hold off for
now.

Will
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [ 10/65] ARM: 7467/1: mutex: use generic xchg-based implementation for ARMv6+

[Will Deacon]

Hi Ben,

On Wed, Aug 15, 2012 at 05:29:26AM +0100, Ben Hutchings wrote:
 On Mon, 2012-08-13 at 15:13 -0700, Greg Kroah-Hartman wrote:
  From: Greg KH gre...@linuxfoundation.org
  
  3.4-stable review patch.  If anyone has any objections, please let me know.
  
  --
  
  From: Will Deacon will.dea...@arm.com
  
  commit a76d7bd96d65fa5119adba97e1b58d95f2e78829 upstream.
  
  The open-coded mutex implementation for ARMv6+ cores suffers from a
  severe lack of barriers, so in the uncontended case we don't actually
  protect any accesses performed during the critical section.
  
  Furthermore, the code is largely a duplication of the ARMv6+ atomic_dec
  code but optimised to remove a branch instruction, as the mutex fastpath
  was previously inlined. Now that this is executed out-of-line, we can
  reuse the atomic access code for the locking (in fact, we use the xchg
  code as this produces shorter critical sections).
  
  This patch uses the generic xchg based implementation for mutexes on
  ARMv6+, which introduces barriers to the lock/unlock operations and also
  has the benefit of removing a fair amount of inline assembly code.
 [...]
 
 I understand that a further fix is needed on top of this
 http://article.gmane.org/gmane.linux.ports.arm.kernel/181693 but it's
 not in Linus's tree yet.  Is it better to apply this on its own or to
 wait for the complete fix?

The additional patch should also be CC'd to stable and is sitting in -tip
somewhere I believe, so it shouldn't be long before it does hit mainline.

Without this patch there's a memory-ordering bug (which we seem to have hit
once in  5 years). With the patch there's a mutex lockup issue on SMP systems
that I can provoke with enough hackbenching, so you may want to hold off for
now.

Will
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [ 10/65] ARM: 7467/1: mutex: use generic xchg-based implementation for ARMv6+

[Ben Hutchings]

On Mon, 2012-08-13 at 15:13 -0700, Greg Kroah-Hartman wrote:
> From: Greg KH 
> 
> 3.4-stable review patch.  If anyone has any objections, please let me know.
> 
> --
> 
> From: Will Deacon 
> 
> commit a76d7bd96d65fa5119adba97e1b58d95f2e78829 upstream.
> 
> The open-coded mutex implementation for ARMv6+ cores suffers from a
> severe lack of barriers, so in the uncontended case we don't actually
> protect any accesses performed during the critical section.
> 
> Furthermore, the code is largely a duplication of the ARMv6+ atomic_dec
> code but optimised to remove a branch instruction, as the mutex fastpath
> was previously inlined. Now that this is executed out-of-line, we can
> reuse the atomic access code for the locking (in fact, we use the xchg
> code as this produces shorter critical sections).
> 
> This patch uses the generic xchg based implementation for mutexes on
> ARMv6+, which introduces barriers to the lock/unlock operations and also
> has the benefit of removing a fair amount of inline assembly code.
[...]

I understand that a further fix is needed on top of this
 but it's
not in Linus's tree yet.  Is it better to apply this on its own or to
wait for the complete fix?

Ben.

-- 
Ben Hutchings
I say we take off; nuke the site from orbit.  It's the only way to be sure.


signature.asc
Description: This is a digitally signed message part

Re: [ 10/65] ARM: 7467/1: mutex: use generic xchg-based implementation for ARMv6+

[Ben Hutchings]

On Mon, 2012-08-13 at 15:13 -0700, Greg Kroah-Hartman wrote:
 From: Greg KH gre...@linuxfoundation.org
 
 3.4-stable review patch.  If anyone has any objections, please let me know.
 
 --
 
 From: Will Deacon will.dea...@arm.com
 
 commit a76d7bd96d65fa5119adba97e1b58d95f2e78829 upstream.
 
 The open-coded mutex implementation for ARMv6+ cores suffers from a
 severe lack of barriers, so in the uncontended case we don't actually
 protect any accesses performed during the critical section.
 
 Furthermore, the code is largely a duplication of the ARMv6+ atomic_dec
 code but optimised to remove a branch instruction, as the mutex fastpath
 was previously inlined. Now that this is executed out-of-line, we can
 reuse the atomic access code for the locking (in fact, we use the xchg
 code as this produces shorter critical sections).
 
 This patch uses the generic xchg based implementation for mutexes on
 ARMv6+, which introduces barriers to the lock/unlock operations and also
 has the benefit of removing a fair amount of inline assembly code.
[...]

I understand that a further fix is needed on top of this
http://article.gmane.org/gmane.linux.ports.arm.kernel/181693 but it's
not in Linus's tree yet.  Is it better to apply this on its own or to
wait for the complete fix?

Ben.

-- 
Ben Hutchings
I say we take off; nuke the site from orbit.  It's the only way to be sure.


signature.asc
Description: This is a digitally signed message part