Skip to content

L
linux
An error occurred fetching the project authors.
Switch branch/tag
  1. 02 May, 2011 2 commits
    • Tejun Heo's avatar
      x86-32, NUMA: Replace srat_32.c with srat.c · 5acd91ab
      Tejun Heo authored 
      SRAT support implementation in srat_32.c and srat.c are generally
similar; however, there are some differences.

First of all, 64bit implementation supports more types of SRAT
entries.  64bit supports x2apic, affinity, memory and SLIT.  32bit
only supports processor and memory.

Most other differences stem from different initialization protocols
employed by 64bit and 32bit NUMA init paths.

On 64bit,

* Mappings among PXM, node and apicid are directly done in each SRAT
  entry callback.

* Memory affinity information is passed to numa_add_memblk() which
  takes care of all interfacing with NUMA init.

* Doesn't directly initialize NUMA configurations.  All the
  information is recorded in numa_nodes_parsed and memblks.

On 32bit,

* Checks numa_off.

* Things go through one more level of indirection via private tables
  but eventually end up initializing the same mappings.

* node_start/end_pfn[] are initialized and
  memblock_x86_register_active_regions() is called for each memory
  chunk.

* node_set_online() is called for each online node.

* sort_node_map() is called.

There are also other minor differences in sanity checking and messages
but taking 64bit version should be good enough.

This patch drops the 32bit specific implementation and makes the 64bit
implementation common for both 32 and 64bit.

The init protocol differences are dealt with in two places - the
numa_add_memblk() shim added in the previous patch and new temporary
numa_32.c:get_memcfg_from_srat() which wraps invocation of
x86_acpi_numa_init().

The shim numa_add_memblk() handles the folowings.

* node_start/end_pfn[] initialization.

* node_set_online() for memory nodes.

* Invocation of memblock_x86_register_active_regions().

The shim get_memcfg_from_srat() handles the followings.

* numa_off check.

* node_set_online() for CPU nodes.

* sort_node_map() invocation.

* Clearing of numa_nodes_parsed and active_ranges on failure.

The shims are temporary and will be removed as the generic NUMA init
path in 32bit is replaced with 64bit one.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
      5acd91ab
    • Tejun Heo's avatar
      x86, NUMA: rename srat_64.c to srat.c · 7b2600f8
      Tejun Heo authored 
      Rename srat_64.c to srat.c.  This is to prepare for unification of
NUMA init paths between 32 and 64bit.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
      7b2600f8
  3. 22 Feb, 2011 1 commit
    • Tejun Heo's avatar
      x86-64, NUMA: Move NUMA emulation into numa_emulation.c · b8ef9172
      Tejun Heo authored 
      Create numa_emulation.c and move all NUMA emulation code there.  The
definitions of struct numa_memblk and numa_meminfo are moved to
numa_64.h.  Also, numa_remove_memblk_from(), numa_cleanup_meminfo(),
numa_reset_distance() along with numa_emulation() are made global.

- v2: Internal declarations moved to numa_internal.h as suggested by
      Yinghai.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Acked-by: default avatarYinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
      b8ef9172
  5. 18 Nov, 2010 1 commit
  7. 27 Aug, 2010 1 commit
  9. 18 Feb, 2010 1 commit
  11. 21 Sep, 2009 2 commits
  13. 10 Sep, 2009 1 commit
  15. 09 Sep, 2009 1 commit
    • Jeremy Fitzhardinge's avatar
      xen: make -fstack-protector work under Xen · 577eebea
      Jeremy Fitzhardinge authored 
      -fstack-protector uses a special per-cpu "stack canary" value.
gcc generates special code in each function to test the canary to make
sure that the function's stack hasn't been overrun.

On x86-64, this is simply an offset of %gs, which is the usual per-cpu
base segment register, so setting it up simply requires loading %gs's
base as normal.

On i386, the stack protector segment is %gs (rather than the usual kernel
percpu %fs segment register).  This requires setting up the full kernel
GDT and then loading %gs accordingly.  We also need to make sure %gs is
initialized when bringing up secondary cpus too.

To keep things consistent, we do the full GDT/segment register setup on
both architectures.

Because we need to avoid -fstack-protected code before setting up the GDT
and because there's no way to disable it on a per-function basis, several
files need to have stack-protector inhibited.

[ Impact: allow Xen booting with stack-protector enabled ]
Signed-off-by: default avatarJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
      577eebea
  17. 13 Jun, 2009 1 commit
  19. 13 Mar, 2009 1 commit
  21. 03 Mar, 2009 1 commit
  23. 29 Jan, 2009 1 commit
    • Ingo Molnar's avatar
      x86: replace CONFIG_X86_SMP with CONFIG_SMP · 3e5095d1
      Ingo Molnar authored 
      The x86/Voyager subarch used to have this distinction between
 'x86 SMP support' and 'Voyager SMP support':

 config X86_SMP
	bool
	depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64)

This is a pointless distinction - Voyager can (and already does) use
smp_ops to implement various SMP quirks it has - and it can be extended
more to cover all the specialities of Voyager.

So remove this complication in the Kconfig space.
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      3e5095d1
  25. 21 Jan, 2009 1 commit
  27. 31 Oct, 2008 1 commit
  29. 27 Oct, 2008 1 commit
  31. 13 Oct, 2008 1 commit
  33. 12 Aug, 2008 1 commit
  35. 26 Jul, 2008 1 commit
    • Nick Piggin's avatar
      x86: lockless get_user_pages_fast() · 8174c430
      Nick Piggin authored 
      Implement get_user_pages_fast without locking in the fastpath on x86.

Do an optimistic lockless pagetable walk, without taking mmap_sem or any
page table locks or even mmap_sem.  Page table existence is guaranteed by
turning interrupts off (combined with the fact that we're always looking
up the current mm, means we can do the lockless page table walk within the
constraints of the TLB shootdown design).  Basically we can do this
lockless pagetable walk in a similar manner to the way the CPU's pagetable
walker does not have to take any locks to find present ptes.

This patch (combined with the subsequent ones to convert direct IO to use
it) was found to give about 10% performance improvement on a 2 socket 8
core Intel Xeon system running an OLTP workload on DB2 v9.5

 "To test the effects of the patch, an OLTP workload was run on an IBM
  x3850 M2 server with 2 processors (quad-core Intel Xeon processors at
  2.93 GHz) using IBM DB2 v9.5 running Linux 2.6.24rc7 kernel.  Comparing
  runs with and without the patch resulted in an overall performance
  benefit of ~9.8%.  Correspondingly, oprofiles showed that samples from
  __up_read and __down_read routines that is seen during thread contention
  for system resources was reduced from 2.8% down to .05%.  Monitoring the
  /proc/vmstat output from the patched run showed that the counter for
  fast_gup contained a very high number while the fast_gup_slow value was
  zero."

(fast_gup is the old name for get_user_pages_fast, fast_gup_slow is a
counter we had for the number of times the slowpath was invoked).

The main reason for the improvement is that DB2 has multiple threads each
issuing direct-IO.  Direct-IO uses get_user_pages, and thus the threads
contend the mmap_sem cacheline, and can also contend on page table locks.

I would anticipate larger performance gains on larger systems, however I
think DB2 uses an adaptive mix of threads and processes, so it could be
that thread contention remains pretty constant as machine size increases.
In which case, we stuck with "only" a 10% gain.

The downside of using get_user_pages_fast is that if there is not a pte
with the correct permissions for the access, we end up falling back to
get_user_pages and so the get_user_pages_fast is a bit of extra work.
However this should not be the common case in most performance critical
code.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: Kconfig fix]
[akpm@linux-foundation.org: Makefile fix/cleanup]
[akpm@linux-foundation.org: warning fix]
Signed-off-by: default avatarNick Piggin <npiggin@suse.de>
Cc: Dave Kleikamp <shaggy@austin.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Dave Kleikamp <shaggy@austin.ibm.com>
Cc: Badari Pulavarty <pbadari@us.ibm.com>
Cc: Zach Brown <zach.brown@oracle.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Reviewed-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      8174c430
  37. 18 Jul, 2008 1 commit
  39. 08 Jul, 2008 1 commit
  41. 24 May, 2008 1 commit
  43. 24 Apr, 2008 1 commit
  45. 17 Apr, 2008 4 commits
  47. 11 Oct, 2007 12 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7