linux-toradex.git/include/linux/bitops.h, branch v2.6.26-rc5

bitops: remove "optimizations"

2008-04-29T15:11:16+00:00

The mapsize optimizations which were moved from x86 to the generic
code in commit 64970b68d2b3ed32b964b0b30b1b98518fde388e increased the
binary size on non x86 architectures.

Looking into the real effects of the "optimizations" it turned out
that they are not used in find_next_bit() and find_next_zero_bit().

The ones in find_first_bit() and find_first_zero_bit() are used in a
couple of places but none of them is a real hot path.

Remove the "optimizations" all together and call the library functions
unconditionally.

Boot-tested on x86 and compile tested on every cross compiler I have.

Signed-off-by: Thomas Gleixner 
Signed-off-by: Linus Torvalds

Avoid divides in BITS_TO_LONGS

2008-04-29T15:05:59+00:00

BITS_PER_LONG is a signed value (32 or 64)

DIV_ROUND_UP(nr, BITS_PER_LONG) performs signed arithmetic if "nr" is signed too.

Converting BITS_TO_LONGS(nr) to DIV_ROUND_UP(nr, BITS_PER_BYTE *
sizeof(long)) makes sure compiler can perform a right shift, even if "nr"
is a signed value, instead of an expensive integer divide.

Applying this patch saves 141 bytes on x86 when CONFIG_CC_OPTIMIZE_FOR_SIZE=y
and speedup bitmap operations.

Signed-off-by: Eric Dumazet 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

x86: optimize find_first_bit for small bitmaps

2008-04-26T17:21:17+00:00

Avoid a call to find_first_bit if the bitmap size is know at
compile time and small enough to fit in a single long integer.
Modeled after an optimization in the original x86_64-specific
code.

Signed-off-by: Alexander van Heukelum 
Signed-off-by: Ingo Molnar

x86: generic versions of find_first_(zero_)bit, convert i386

2008-04-26T17:21:16+00:00

Generic versions of __find_first_bit and __find_first_zero_bit
are introduced as simplified versions of __find_next_bit and
__find_next_zero_bit. Their compilation and use are guarded by
a new config variable GENERIC_FIND_FIRST_BIT.

The generic versions of find_first_bit and find_first_zero_bit
are implemented in terms of the newly introduced __find_first_bit
and __find_first_zero_bit.

This patch does not remove the i386-specific implementation,
but it does switch i386 to use the generic functions by setting
GENERIC_FIND_FIRST_BIT=y for X86_32.

Signed-off-by: Alexander van Heukelum 
Signed-off-by: Ingo Molnar

x86, generic: optimize find_next_(zero_)bit for small constant-size bitmaps

2008-04-26T17:21:16+00:00

This moves an optimization for searching constant-sized small
bitmaps form x86_64-specific to generic code.

On an i386 defconfig (the x86#testing one), the size of vmlinux hardly
changes with this applied. I have observed only four places where this
optimization avoids a call into find_next_bit:

In the functions return_unused_surplus_pages, alloc_fresh_huge_page,
and adjust_pool_surplus, this patch avoids a call for a 1-bit bitmap.
In __next_cpu a call is avoided for a 32-bit bitmap. That's it.

On x86_64, 52 locations are optimized with a minimal increase in
code size:

Current #testing defconfig:
	146 x bsf, 27 x find_next_*bit
   text    data     bss     dec     hex filename
   5392637  846592  724424 6963653  6a41c5 vmlinux

After removing the x86_64 specific optimization for find_next_*bit:
	94 x bsf, 79 x find_next_*bit
   text    data     bss     dec     hex filename
   5392358  846592  724424 6963374  6a40ae vmlinux

After this patch (making the optimization generic):
	146 x bsf, 27 x find_next_*bit
   text    data     bss     dec     hex filename
   5392396  846592  724424 6963412  6a40d4 vmlinux

[ tglx@linutronix.de: build fixes ]

Signed-off-by: Ingo Molnar

kernel: add bit rotation helpers for 16 and 8 bit

2008-03-28T21:45:22+00:00

Will replace open-coded variants elsewhere.  Done in the same
style as the 32-bit versions.

Signed-off-by: Harvey Harrison 
Acked-by: Randy Dunlap 
Cc: Johannes Berg 
Cc: John W. Linville 
Cc: Joe Perches 
Cc: Jiri Benc 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

remove BITS_TO_TYPE macro

2007-10-19T18:53:42+00:00

remove BITS_TO_TYPE macro

I realized, that it is actually the same as DIV_ROUND_UP, use it instead.

[akpm@linux-foundation.org: build fix]
Signed-off-by: Jiri Slaby 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

define global BIT macro

2007-10-19T18:53:42+00:00

define global BIT macro

move all local BIT defines to the new globally define macro.

Signed-off-by: Jiri Slaby 
Cc: Paul Mackerras 
Cc: Benjamin Herrenschmidt 
Cc: Kumar Gala 
Cc: Dmitry Torokhov 
Cc: Jeff Garzik 
Cc: James Bottomley 
Cc: "Antonino A. Daplas" 
Cc: Russell King 
Acked-by: Ralf Baechle 
Cc: "John W. Linville" 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

define first set of BIT* macros

2007-10-19T18:53:42+00:00

define first set of BIT* macros

- move BITOP_MASK and BITOP_WORD from asm-generic/bitops/atomic.h to
  include/linux/bitops.h and rename it to BIT_MASK and BIT_WORD
- move BITS_TO_LONGS and BITS_PER_BYTE to bitops.h too and allow easily
  define another BITS_TO_something (e.g. in event.c) by BITS_TO_TYPE macro
Remaining (and common) BIT macro will be defined after all occurences and
conflicts will be sorted out in the patches.

Signed-off-by: Jiri Slaby 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

I/OAT: Add support for MSI and MSI-X

2007-10-16T16:43:09+00:00

Add support for MSI and MSI-X interrupt handling, including the ability
to choose the desired interrupt method.

Signed-off-by: Shannon Nelson 
Acked-by: David S. Miller 
[bunk@kernel.org: drivers/dma/ioat_dma.c: make 3 functions static]
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds