[GIT] Sparc

I've been auditing the THP support on sparc64 and found several bugs,
hopefully most of which are fixed completely here.

Also an RT kernel locking fix from Kirill Tkhai.

Please pull, thanks a lot!

The following changes since commit b7270cce7db770602510043b212992d839fd25a6:

  Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband (2014-05-01 17:52:42 -0700)

are available in the git repository at:


  git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc.git master

for you to fetch changes up to fe866433f843b080246ce729b5e6b27b5f5d9a58:

  sparc64: Give more detailed information in {pgd,pmd}_ERROR() and kill pte_ERROR(). (2014-05-03 22:56:25 -0700)

----------------------------------------------------------------
David S. Miller (13):
      sparc64: Fix argument sign extension for compat_sys_futex().
      sparc64: Normalize NMI watchdog logging and behavior.
      sparc64: Fix executable bit testing in set_pmd_at() paths.
      sparc64: Fix huge PMD invalidation.
      sparc64: Fix bugs in get_user_pages_fast() wrt. THP.
      sparc64: Fix hex values in comment above pte_modify().
      sparc64: Don't use _PAGE_PRESENT in pte_modify() mask.
      sparc64: Handle 32-bit tasks properly in compute_effective_address().
      sparc64: Fix top-level fault handling bugs.
      sparc64: Fix range check in kern_addr_valid().
      sparc64: Use 'ILOG2_4MB' instead of constant '22'.
      sparc64: Add basic validations to {pud,pmd}_bad().
      sparc64: Give more detailed information in {pgd,pmd}_ERROR() and kill pte_ERROR().

Kirill Tkhai (1):
      sparc64: Make itc_sync_lock raw

 arch/sparc/include/asm/pgtable_64.h | 83 ++++++++++++++++++++++++++++++++++++++------------------------------
 arch/sparc/include/asm/tsb.h        |  3 ++-
 arch/sparc/kernel/head_64.S         |  4 ++--
 arch/sparc/kernel/ktlb.S            |  2 +-
 arch/sparc/kernel/nmi.c             | 21 +++++------------
 arch/sparc/kernel/smp_64.c          |  6 ++---
 arch/sparc/kernel/sys32.S           |  2 +-
 arch/sparc/kernel/unaligned_64.c    | 12 +++++++---
 arch/sparc/mm/fault_64.c            | 82 ++++++++++++++++++++++++++++++++++++++++++-------------------------
 arch/sparc/mm/gup.c                 |  2 +-
 arch/sparc/mm/init_64.c             | 12 +++++-----
 arch/sparc/mm/tlb.c                 | 26 ++++++++++++++++-----
 12 files changed, 148 insertions(+), 107 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

On Tue, May 06, 2014 at 11:30:31AM -0400, David Miller wrote:
 > 
 > I've been auditing the THP support on sparc64 and found several bugs,
 > hopefully most of which are fixed completely here.
 
Hi Dave,

It seems like forever you go you sent me patches to trinity to make it
work on sparc. I'm curious if you've tried running it again more
recently ?   Given the work I've done it to do more creative things with
VM related syscalls, I wouldn't be surprised if it also found some sparc
specific bugs in thp.

It should now also scale up to run a lot more child processes than the older
version, with the -c option, which could be interesting on some of the
bigger sparc machines.

(It's entirely possible I've broken the compile on non-x86 in
 current git, but it shouldn't be much work to fix up).

git://github.com/kernelslacker/trinity is where it lives now.

	Dave

--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

From: Dave Jones <davej@redhat.com>
Date: Tue, 6 May 2014 12:29:46 -0400

> It seems like forever you go you sent me patches to trinity to make it
> work on sparc. I'm curious if you've tried running it again more
> recently ?   Given the work I've done it to do more creative things with
> VM related syscalls, I wouldn't be surprised if it also found some sparc
> specific bugs in thp.
> 
> It should now also scale up to run a lot more child processes than the older
> version, with the -c option, which could be interesting on some of the
> bigger sparc machines.
> 
> (It's entirely possible I've broken the compile on non-x86 in
>  current git, but it shouldn't be much work to fix up).
> 
> git://github.com/kernelslacker/trinity is where it lives now.

Thanks Dave, I'll take a look and get back to you.
--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html