linux-toradex.git/arch/powerpc/include/asm/bitops.h, branch v4.3-rc2

powerpc: Fix comment typos in arch/powerpc/include/asm/bitops.h

2014-11-12T05:31:46+00:00

In arch/powerpc/include/asm/bitops.h, the comments about bit numbers in
large (> 1 word) bitmaps have two typos:
- On ppc64 system, the LSB of the 4th word should be bit 192 rather than
  196, because if it's bit 196, bit 192-195 will be missing in the
  bitmap.
- On ppc32 system, the LSB of the second word should be bit 32 rather
  than 31, because bit 31 is already in the first word.

This patch fixes these typos.

Signed-off-by: Boqun Feng 
Signed-off-by: Michael Ellerman

powerpc: make __ffs return unsigned long

2014-11-09T22:59:27+00:00

I'm seeing a build warning in mm/nobootmem.c after removing
bootmem:

mm/nobootmem.c: In function '__free_pages_memory':
include/linux/kernel.h:713:17: warning: comparison of distinct pointer types lacks a cast [enabled by default]
  (void) (&_min1 == &_min2);  \
                 ^
mm/nobootmem.c:90:11: note: in expansion of macro 'min'
   order = min(MAX_ORDER - 1UL, __ffs(start));
           ^

The rest of the worlds seems to define __ffs as returning unsigned long,
so lets do that.

Signed-off-by: Anton Blanchard 
Tested-by: Emil Medve 
Signed-off-by: Michael Ellerman

arch,powerpc: Convert smp_mb__*()

2014-04-18T12:20:41+00:00

Powerpc allows reordering over its ll/sc implementation. Implement the
two new barriers as appropriate.

Signed-off-by: Peter Zijlstra 
Acked-by: Paul E. McKenney 
Link: http://lkml.kernel.org/n/tip-gg2ffgq32sjgy9b8lj6m3hsc@git.kernel.org
Cc: Benjamin Herrenschmidt 
Cc: Linus Torvalds 
Cc: Mahesh Salgaonkar 
Cc: Paul Gortmaker 
Cc: Paul Mackerras 
Cc: Will Deacon 
Cc: linux-kernel@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Ingo Molnar

powerpc/book3s: Flush SLB/TLBs if we get SLB/TLB machine check errors on power7.

2013-12-05T05:04:39+00:00

If we get a machine check exception due to SLB or TLB errors, then flush
SLBs/TLBs and reload SLBs to recover. We do this in real mode before turning
on MMU. Otherwise we would run into nested machine checks.

If we get a machine check when we are in guest, then just flush the
SLBs and continue. This patch handles errors for power7. The next
patch will handle errors for power8

Signed-off-by: Mahesh Salgaonkar 
Signed-off-by: Paul Mackerras 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Remove unused postfix parameter to DEFINE_BITOP()

2013-04-18T01:53:04+00:00

None of the users of DEFINE_BITOP pass a postfix, and as far as I can
tell none ever did, so drop it.

Signed-off-by: Michael Ellerman

powerpc: Remove unused BITOP_LE_SWIZZLE macro

2013-03-05T05:56:28+00:00

The BITOP_LE_SWIZZLE macro was used in the little-endian bitops functions
for powerpc.  But these functions were converted to generic bitops and
the BITOP_LE_SWIZZLE is not used anymore.

Signed-off-by: Akinobu Mita 
Cc: Benjamin Herrenschmidt 
Cc: Paul Mackerras 
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Benjamin Herrenschmidt

powerpc: Use asm-generic/bitops/le.h

2012-11-15T02:01:10+00:00

The only difference between powerpc and asm-generic le-bitops is
test_bit_le().  Usually all bitops require a long aligned bitmap.
But powerpc test_bit_le() can take an unaligned address.

There is no special callsite of test_bit_le() that needs unaligned
access in powerpc as far as I can see.  So convert to use
asm-generic/bitops/le.h for powerpc.

Signed-off-by: Akinobu Mita 
Cc: Benjamin Herrenschmidt 
Cc: Paul Mackerras 
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Benjamin Herrenschmidt

powerpc: Remove BITOP_MASK and BITOP_WORD from asm/bitops.h

2012-11-15T02:01:07+00:00

Replace BITOP_MASK and BITOP_WORD with BIT_MASK and BIT_WORD defined
in linux/bitops.h and remove BITOP_* which are not used anymore.

Signed-off-by: Akinobu Mita 
Cc: Benjamin Herrenschmidt 
Cc: Paul Mackerras 
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Benjamin Herrenschmidt

powerpc: bitops: introduce {clear,set}_bit_le()

2012-10-05T18:04:55+00:00

Needed to replace test_and_set_bit_le() in virt/kvm/kvm_main.c which is
being used for this missing function.

Signed-off-by: Takuya Yoshikawa 
Acked-by: Benjamin Herrenschmidt 
Cc: Avi Kivity 
Cc: Marcelo Tosatti 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

powerpc: Fix atomic_xxx_return barrier semantics

2011-11-17T05:26:07+00:00

The Documentation/memory-barriers.txt document requires that atomic
operations that return a value act as a memory barrier both before
and after the actual atomic operation.

Our current implementation doesn't guarantee this. More specifically,
while a load following the isync can not be issued before stwcx. has
completed, that completion doesn't architecturally means that the
result of stwcx. is visible to other processors (or any previous stores
for that matter) (typically, the other processors L1 caches can still
hold the old value).

This has caused an actual crash in RCU torture testing on Power 7

This fixes it by changing those atomic ops to use new macros instead
of RELEASE/ACQUIRE barriers, called ATOMIC_ENTRY and ATMOIC_EXIT barriers,
which are then defined respectively to lwsync and sync.

I haven't had a chance to measure the performance impact (or rather
what I measured with kernel compiles is in the noise, I yet have to
find a more precise benchmark)

Signed-off-by: Benjamin Herrenschmidt 
Acked-by: Paul E. McKenney