Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
大约 1 年 前同步成功

通知 158
Star 36
Fork 7
cloud-kernel
cloud-kernel

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 15 10月, 2015 13 次提交
  3. 12 10月, 2015 2 次提交
  5. 09 10月, 2015 2 次提交
  7. 06 10月, 2015 2 次提交
  9. 05 10月, 2015 6 次提交
  11. 02 10月, 2015 3 次提交
  13. 01 10月, 2015 8 次提交
    • M
      powerpc: Add ppc64le_defconfig · 2adc48a6
      由 Michael Ellerman 提交于 
      Based directly on ppc64_defconfig using merge_config.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      2adc48a6
    • M
      scripts/kconfig/Makefile: Allow KBUILD_DEFCONFIG to be a target · d2036f30
      由 Michael Ellerman 提交于 
      Arch Makefiles can set KBUILD_DEFCONFIG to tell kbuild the name of the
defconfig that should be built by default.

However currently there is an assumption that KBUILD_DEFCONFIG points to
a file at arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG).

We would like to use a target, using merge_config, as our defconfig, so
adapt the logic in scripts/kconfig/Makefile to allow that.

To minimise the chance of breaking anything, we first check if
KBUILD_DEFCONFIG is a file, and if so we do the old logic. If it's not a
file, then we call the top-level Makefile with KBUILD_DEFCONFIG as the
target.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
Acked-by: NMichal Marek <mmarek@suse.com>
      d2036f30
    • A
      powerpc/mm: Add virt_to_pfn and use this instead of opencoding · 65d3223a
      由 Aneesh Kumar K.V 提交于 
      This add helper virt_to_pfn and remove the opencoded usage of the
same.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      65d3223a
    • M
      powerpc/vdso: Avoid link stack corruption in __get_datapage() · c974809a
      由 Michael Neuling 提交于 
      powerpc has a link register (lr) used for calling functions. We "bl
<func>" to call a function, and "blr" to return back to the call site.

The lr is only a single register, so if we call another function from
inside this function (ie. nested calls), software must save away the
lr on the software stack before calling the new function. Before
returning (ie. before the "blr"), the lr is restored by software from
the software stack.

This makes branch prediction quite difficult for the processor as it
will only know the branch target just before the "blr".

To help with this, modern powerpc processors keep a (non-architected)
hardware stack of lr called a "link stack". When a "bl <func>" is
run, the lr is pushed onto this stack. When a "blr" is called, the
branch predictor pops the lr value from the top of the link stack, and
uses it to predict the branch target. Hence the processor pipeline
knows a lot earlier the branch target.

This works great but there are some cases where you call "bl" but
without a matching "blr". Once such case is when trying to determine
the program counter (which can't be read directly). Here you "bl+4;
mflr" to get the program counter. If you do this, the link stack will
get out of sync with reality, causing the branch predictor to
mis-predict subsequent function returns.

To avoid this, modern micro-architectures have a special case of bl.
Using the form "bcl 20,31,+4", ensures the processor doesn't push to
the link stack.

The 32 and 64 bit variants of __get_datapage() use a "bl; mflr" to
determine the loaded address of the VDSO. The current versions of
these attempt to use this special bl variant.

Unfortunately they use +8 rather than the required +4. Hence the
current code results in the link stack getting out of sync with
reality and hence the resulting performance degradation.

This patch moves it to bcl+4 by moving __kernel_datapage_offset out of
__get_datapage().

With this patch, running a gettimeofday() (which uses
__get_datapage()) microbenchmark we get a decent bump in performance
on POWER7/8.

For the benchmark in tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
  POWER8:
    64bit gets ~4% improvement
    32bit gets ~9% improvement
  POWER7:
    64bit gets ~7% improvement
Signed-off-by: NMichael Neuling <mikey@neuling.org>
Reported-by: NAaron Sawdey <sawdey@us.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      c974809a
    • M
      powerpc/selftest: Add gettimeofday() benchmark · d17475d9
      由 Michael Neuling 提交于 
      This adds a benchmark directory to the powerpc selftests and adds a
gettimeofday() benchmark to it.
Suggested-by: NMichael Ellerman <mpe@ellerman.id.au>
Signed-off-by: NMichael Neuling <mikey@neuling.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      d17475d9
    • M
      powerpc/slb: Use a local to avoid multiple calls to get_slb_shadow() · 26cd835e
      由 Michael Ellerman 提交于 
      For no reason other than it looks ugly.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      26cd835e
    • A
      powerpc/slb: Define an enum for the bolted indexes · 1d15010c
      由 Anshuman Khandual 提交于 
      This patch defines macros for the three bolted SLB indexes we use.
Switch the functions that take the indexes as an argument to use the
enum.
Signed-off-by: NAnshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      1d15010c
    • M
      powerpc/vdso: Emit GNU & SysV hashes · 787b393c
      由 Michael Ellerman 提交于 
      Andy Lutomirski says:

  Some dynamic loaders may be slightly faster if a GNU hash is
  available.

  This is unlikely to have any measurable effect on the time it takes
  to resolve vdso symbols (since there are so few of them).  In some
  contexts, it can be a win for a different reason: if every DSO has a
  GNU hash section, then libc can avoid calculating SysV hashes at
  all. Both musl and glibc appear to have this optimization.
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>
      787b393c
  15. 29 9月, 2015 4 次提交