Skip to content

L
linux
Switch branch/tag
  1. 21 Jan, 2009 3 commits
  3. 20 Jan, 2009 9 commits
  5. 19 Jan, 2009 2 commits
  7. 18 Jan, 2009 14 commits
  9. 17 Jan, 2009 2 commits
  11. 16 Jan, 2009 10 commits
    • Tejun Heo's avatar
      x86_64: initialize this_cpu_off to __per_cpu_load · cd3adf52
      Tejun Heo authored 
      On x86_64, if get_per_cpu_var() is used before per cpu area is setup
(if lockdep is turned on, it happens), it needs this_cpu_off to point
to __per_cpu_load.  Initialize accordingly.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      cd3adf52
    • Tejun Heo's avatar
      x86: fix build bug introduced during merge · a338af2c
      Tejun Heo authored 
      EXPORT_PER_CPU_SYMBOL() got misplaced during merge leading to build
failure.  Fix it.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      a338af2c
    • Ingo Molnar's avatar
      percpu: add optimized generic percpu accessors · 6dbde353
      Ingo Molnar authored 
      It is an optimization and a cleanup, and adds the following new
generic percpu methods:

  percpu_read()
  percpu_write()
  percpu_add()
  percpu_sub()
  percpu_and()
  percpu_or()
  percpu_xor()

and implements support for them on x86. (other architectures will fall
back to a default implementation)

The advantage is that for example to read a local percpu variable,
instead of this sequence:

 return __get_cpu_var(var);

 ffffffff8102ca2b:	48 8b 14 fd 80 09 74 	mov    -0x7e8bf680(,%rdi,8),%rdx
 ffffffff8102ca32:	81
 ffffffff8102ca33:	48 c7 c0 d8 59 00 00 	mov    $0x59d8,%rax
 ffffffff8102ca3a:	48 8b 04 10          	mov    (%rax,%rdx,1),%rax

We can get a single instruction by using the optimized variants:

 return percpu_read(var);

 ffffffff8102ca3f:	65 48 8b 05 91 8f fd 	mov    %gs:0x7efd8f91(%rip),%rax

I also cleaned up the x86-specific APIs and made the x86 code use
these new generic percpu primitives.

tj: * fixed generic percpu_sub() definition as Roel Kluin pointed out
    * added percpu_and() for completeness's sake
    * made generic percpu ops atomic against preemption
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      6dbde353
    • Tejun Heo's avatar
      x86: misc clean up after the percpu update · 004aa322
      Tejun Heo authored 
      Do the following cleanups:

* kill x86_64_init_pda() which now is equivalent to pda_init()

* use per_cpu_offset() instead of cpu_pda() when initializing
  initial_gs
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      004aa322
    • Tejun Heo's avatar
      x86: convert pda ops to wrappers around x86 percpu accessors · 49357d19
      Tejun Heo authored 
      pda is now a percpu variable and there's no reason it can't use plain
x86 percpu accessors.  Add x86_test_and_clear_bit_percpu() and replace
pda op implementations with wrappers around x86 percpu accessors.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      49357d19
    • Tejun Heo's avatar
      x86: make pda a percpu variable · b12d8db8
      Tejun Heo authored 
      [ Based on original patch from Christoph Lameter and Mike Travis. ]

As pda is now allocated in percpu area, it can easily be made a proper
percpu variable.  Make it so by defining per cpu symbol from linker
script and declaring it in C code for SMP and simply defining it for
UP.  This change cleans up code and brings SMP and UP closer a bit.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      b12d8db8
    • Tejun Heo's avatar
      x86: merge 64 and 32 SMP percpu handling · 9939ddaf
      Tejun Heo authored 
      Now that pda is allocated as part of percpu, percpu doesn't need to be
accessed through pda.  Unify x86_64 SMP percpu access with x86_32 SMP
one.  Other than the segment register, operand size and the base of
percpu symbols, they behave identical now.

This patch replaces now unnecessary pda->data_offset with a dummy
field which is necessary to keep stack_canary at its place.  This
patch also moves per_cpu_offset initialization out of init_gdt() into
setup_per_cpu_areas().  Note that this change also necessitates
explicit per_cpu_offset initializations in voyager_smp.c.

With this change, x86_OP_percpu()'s are as efficient on x86_64 as on
x86_32 and also x86_64 can use assembly PER_CPU macros.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      9939ddaf
    • Tejun Heo's avatar
      x86: fold pda into percpu area on SMP · 1a51e3a0
      Tejun Heo authored 
      [ Based on original patch from Christoph Lameter and Mike Travis. ]

Currently pdas and percpu areas are allocated separately.  %gs points
to local pda and percpu area can be reached using pda->data_offset.
This patch folds pda into percpu area.

Due to strange gcc requirement, pda needs to be at the beginning of
the percpu area so that pda->stack_canary is at %gs:40.  To achieve
this, a new percpu output section macro - PERCPU_VADDR_PREALLOC() - is
added and used to reserve pda sized chunk at the start of the percpu
area.

After this change, for boot cpu, %gs first points to pda in the
data.init area and later during setup_per_cpu_areas() gets updated to
point to the actual pda.  This means that setup_per_cpu_areas() need
to reload %gs for CPU0 while clearing pda area for other cpus as cpu0
already has modified it when control reaches setup_per_cpu_areas().

This patch also removes now unnecessary get_local_pda() and its call
sites.

A lot of this patch is taken from Mike Travis' "x86_64: Fold pda into
per cpu area" patch.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      1a51e3a0
    • Tejun Heo's avatar
      x86: use static _cpu_pda array · c8f3329a
      Tejun Heo authored 
      _cpu_pda array first uses statically allocated storage in data.init
and then switches to allocated bootmem to conserve space.  However,
after folding pda area into percpu area, _cpu_pda array will be
removed completely.  Drop the reallocation part to simplify the code
for soon-to-follow changes.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      c8f3329a
    • Tejun Heo's avatar
      x86: load pointer to pda into %gs while brining up a CPU · f32ff538
      Tejun Heo authored 
      [ Based on original patch from Christoph Lameter and Mike Travis. ]

CPU startup code in head_64.S loaded address of a zero page into %gs
for temporary use till pda is loaded but address to the actual pda is
available at the point.  Load the real address directly instead.

This will help unifying percpu and pda handling later on.

This patch is mostly taken from Mike Travis' "x86_64: Fold pda into
per cpu area" patch.
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      f32ff538
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7