1. 29 Apr, 2008 1 commit
    • Thomas Gleixner's avatar
      bitops: remove "optimizations" · fee4b19f
      Thomas Gleixner authored
      The mapsize optimizations which were moved from x86 to the generic
      code in commit 64970b68 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: default avatarThomas Gleixner <[email protected]>
      Signed-off-by: default avatarLinus Torvalds <[email protected]>
      fee4b19f
  2. 26 Apr, 2008 3 commits
    • Alexander van Heukelum's avatar
      x86: generic versions of find_first_(zero_)bit, convert i386 · 77b9bd9c
      Alexander van Heukelum authored
      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: default avatarAlexander van Heukelum <[email protected]>
      Signed-off-by: default avatarIngo Molnar <[email protected]>
      77b9bd9c
    • Alexander van Heukelum's avatar
      x86, generic: optimize find_next_(zero_)bit for small constant-size bitmaps · 64970b68
      Alexander van Heukelum authored
      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
      
      [ [email protected]: build fixes ]
      Signed-off-by: default avatarIngo Molnar <[email protected]>
      64970b68
    • Alexander van Heukelum's avatar
      x86: change x86 to use generic find_next_bit · 6fd92b63
      Alexander van Heukelum authored
      The versions with inline assembly are in fact slower on the machines I
      tested them on (in userspace) (Athlon XP 2800+, p4-like Xeon 2.8GHz, AMD
      Opteron 270). The i386-version needed a fix similar to 06024f21 to avoid
      crashing the benchmark.
      
      Benchmark using: gcc -fomit-frame-pointer -Os. For each bitmap size
      1...512, for each possible bitmap with one bit set, for each possible
      offset: find the position of the first bit starting at offset. If you
      follow ;). Times include setup of the bitmap and checking of the
      results.
      
      		Athlon		Xeon		Opteron 32/64bit
      x86-specific:	0m3.692s	0m2.820s	0m3.196s / 0m2.480s
      generic:	0m2.622s	0m1.662s	0m2.100s / 0m1.572s
      
      If the bitmap size is not a multiple of BITS_PER_LONG, and no set
      (cleared) bit is found, find_next_bit (find_next_zero_bit) returns a
      value outside of the range [0, size]. The generic version always returns
      exactly size. The generic version also uses unsigned long everywhere,
      while the x86 versions use a mishmash of int, unsigned (int), long and
      unsigned long.
      
      Using the generic version does give a slightly bigger kernel, though.
      
      defconfig:	   text    data     bss     dec     hex filename
      x86-specific:	4738555  481232  626688 5846475  5935cb vmlinux (32 bit)
      generic:	4738621  481232  626688 5846541  59360d vmlinux (32 bit)
      x86-specific:	5392395  846568  724424 6963387  6a40bb vmlinux (64 bit)
      generic:	5392458  846568  724424 6963450  6a40fa vmlinux (64 bit)
      Signed-off-by: default avatarAlexander van Heukelum <[email protected]>
      Signed-off-by: default avatarIngo Molnar <[email protected]>
      6fd92b63
  3. 29 Jan, 2008 1 commit
  4. 26 Mar, 2006 2 commits
  5. 09 Jan, 2006 1 commit
  6. 16 Apr, 2005 1 commit
    • Linus Torvalds's avatar
      Linux-2.6.12-rc2 · 1da177e4
      Linus Torvalds authored
      Initial git repository build. I'm not bothering with the full history,
      even though we have it. We can create a separate "historical" git
      archive of that later if we want to, and in the meantime it's about
      3.2GB when imported into git - space that would just make the early
      git days unnecessarily complicated, when we don't have a lot of good
      infrastructure for it.
      
      Let it rip!
      1da177e4