[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
/*
|
|
|
|
* PowerPC atomic bit operations.
|
|
|
|
*
|
|
|
|
* Merged version by David Gibson <david@gibson.dropbear.id.au>.
|
|
|
|
* Based on ppc64 versions by: Dave Engebretsen, Todd Inglett, Don
|
|
|
|
* Reed, Pat McCarthy, Peter Bergner, Anton Blanchard. They
|
|
|
|
* originally took it from the ppc32 code.
|
|
|
|
*
|
|
|
|
* Within a word, bits are numbered LSB first. Lot's of places make
|
|
|
|
* this assumption by directly testing bits with (val & (1<<nr)).
|
|
|
|
* This can cause confusion for large (> 1 word) bitmaps on a
|
|
|
|
* big-endian system because, unlike little endian, the number of each
|
|
|
|
* bit depends on the word size.
|
|
|
|
*
|
|
|
|
* The bitop functions are defined to work on unsigned longs, so for a
|
|
|
|
* ppc64 system the bits end up numbered:
|
2014-11-11 12:50:22 +08:00
|
|
|
* |63..............0|127............64|191...........128|255...........192|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
* and on ppc32:
|
2014-11-11 12:50:22 +08:00
|
|
|
* |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
*
|
|
|
|
* There are a few little-endian macros used mostly for filesystem
|
|
|
|
* bitmaps, these work on similar bit arrays layouts, but
|
|
|
|
* byte-oriented:
|
|
|
|
* |7...0|15...8|23...16|31...24|39...32|47...40|55...48|63...56|
|
|
|
|
*
|
|
|
|
* The main difference is that bit 3-5 (64b) or 3-4 (32b) in the bit
|
|
|
|
* number field needs to be reversed compared to the big-endian bit
|
|
|
|
* fields. This can be achieved by XOR with 0x38 (64b) or 0x18 (32b).
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _ASM_POWERPC_BITOPS_H
|
|
|
|
#define _ASM_POWERPC_BITOPS_H
|
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
|
2007-10-19 14:40:26 +08:00
|
|
|
#ifndef _LINUX_BITOPS_H
|
|
|
|
#error only <linux/bitops.h> can be included directly
|
|
|
|
#endif
|
|
|
|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
#include <linux/compiler.h>
|
[PATCH] powerpc: Consolidate asm compatibility macros
This patch consolidates macros used to generate assembly for
compatibility across different CPUs or configs. A new header,
asm-powerpc/asm-compat.h contains the main compatibility macros. It
uses some preprocessor magic to make the macros suitable both for use
in .S files, and in inline asm in .c files. Headers (bitops.h,
uaccess.h, atomic.h, bug.h) which had their own such compatibility
macros are changed to use asm-compat.h.
ppc_asm.h is now for use in .S files *only*, and a #error enforces
that. As such, we're a lot more careless about namespace pollution
here than in asm-compat.h.
While we're at it, this patch adds a call to the PPC405_ERR77 macro in
futex.h which should have had it already, but didn't.
Built and booted on pSeries, Maple and iSeries (ARCH=powerpc). Built
for 32-bit powermac (ARCH=powerpc) and Walnut (ARCH=ppc).
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-10 09:56:55 +08:00
|
|
|
#include <asm/asm-compat.h>
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
#include <asm/synch.h>
|
|
|
|
|
2013-10-30 22:35:11 +08:00
|
|
|
/* PPC bit number conversion */
|
|
|
|
#define PPC_BITLSHIFT(be) (BITS_PER_LONG - 1 - (be))
|
|
|
|
#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit))
|
|
|
|
#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
|
|
|
|
|
2017-02-28 10:00:48 +08:00
|
|
|
/* Put a PPC bit into a "normal" bit position */
|
|
|
|
#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit) \
|
|
|
|
((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
|
|
|
|
|
2014-03-14 02:00:35 +08:00
|
|
|
#include <asm/barrier.h>
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
|
2009-07-07 23:23:56 +08:00
|
|
|
/* Macro for generating the ***_bits() functions */
|
2013-02-22 01:25:41 +08:00
|
|
|
#define DEFINE_BITOP(fn, op, prefix) \
|
2009-07-07 23:23:56 +08:00
|
|
|
static __inline__ void fn(unsigned long mask, \
|
|
|
|
volatile unsigned long *_p) \
|
|
|
|
{ \
|
|
|
|
unsigned long old; \
|
|
|
|
unsigned long *p = (unsigned long *)_p; \
|
|
|
|
__asm__ __volatile__ ( \
|
|
|
|
prefix \
|
2010-02-10 09:02:36 +08:00
|
|
|
"1:" PPC_LLARX(%0,0,%3,0) "\n" \
|
2009-07-07 23:23:56 +08:00
|
|
|
stringify_in_c(op) "%0,%0,%2\n" \
|
|
|
|
PPC405_ERR77(0,%3) \
|
|
|
|
PPC_STLCX "%0,0,%3\n" \
|
|
|
|
"bne- 1b\n" \
|
|
|
|
: "=&r" (old), "+m" (*p) \
|
|
|
|
: "r" (mask), "r" (p) \
|
|
|
|
: "cc", "memory"); \
|
|
|
|
}
|
|
|
|
|
2013-02-22 01:25:41 +08:00
|
|
|
DEFINE_BITOP(set_bits, or, "")
|
|
|
|
DEFINE_BITOP(clear_bits, andc, "")
|
|
|
|
DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER)
|
|
|
|
DEFINE_BITOP(change_bits, xor, "")
|
2009-07-07 23:23:56 +08:00
|
|
|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
static __inline__ void set_bit(int nr, volatile unsigned long *addr)
|
|
|
|
{
|
2012-11-04 10:03:44 +08:00
|
|
|
set_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static __inline__ void clear_bit(int nr, volatile unsigned long *addr)
|
|
|
|
{
|
2012-11-04 10:03:44 +08:00
|
|
|
clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
}
|
|
|
|
|
2007-10-18 18:06:53 +08:00
|
|
|
static __inline__ void clear_bit_unlock(int nr, volatile unsigned long *addr)
|
|
|
|
{
|
2012-11-04 10:03:44 +08:00
|
|
|
clear_bits_unlock(BIT_MASK(nr), addr + BIT_WORD(nr));
|
2007-10-18 18:06:53 +08:00
|
|
|
}
|
|
|
|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
static __inline__ void change_bit(int nr, volatile unsigned long *addr)
|
|
|
|
{
|
2012-11-04 10:03:44 +08:00
|
|
|
change_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
|
2009-07-07 23:23:56 +08:00
|
|
|
}
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
|
2009-07-07 23:23:56 +08:00
|
|
|
/* Like DEFINE_BITOP(), with changes to the arguments to 'op' and the output
|
|
|
|
* operands. */
|
2010-02-10 09:02:36 +08:00
|
|
|
#define DEFINE_TESTOP(fn, op, prefix, postfix, eh) \
|
|
|
|
static __inline__ unsigned long fn( \
|
|
|
|
unsigned long mask, \
|
|
|
|
volatile unsigned long *_p) \
|
|
|
|
{ \
|
|
|
|
unsigned long old, t; \
|
|
|
|
unsigned long *p = (unsigned long *)_p; \
|
|
|
|
__asm__ __volatile__ ( \
|
|
|
|
prefix \
|
|
|
|
"1:" PPC_LLARX(%0,0,%3,eh) "\n" \
|
|
|
|
stringify_in_c(op) "%1,%0,%2\n" \
|
|
|
|
PPC405_ERR77(0,%3) \
|
|
|
|
PPC_STLCX "%1,0,%3\n" \
|
|
|
|
"bne- 1b\n" \
|
|
|
|
postfix \
|
|
|
|
: "=&r" (old), "=&r" (t) \
|
|
|
|
: "r" (mask), "r" (p) \
|
|
|
|
: "cc", "memory"); \
|
|
|
|
return (old & mask); \
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
}
|
|
|
|
|
2011-11-16 01:11:27 +08:00
|
|
|
DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER,
|
|
|
|
PPC_ATOMIC_EXIT_BARRIER, 0)
|
2010-02-10 09:04:06 +08:00
|
|
|
DEFINE_TESTOP(test_and_set_bits_lock, or, "",
|
|
|
|
PPC_ACQUIRE_BARRIER, 1)
|
2011-11-16 01:11:27 +08:00
|
|
|
DEFINE_TESTOP(test_and_clear_bits, andc, PPC_ATOMIC_ENTRY_BARRIER,
|
|
|
|
PPC_ATOMIC_EXIT_BARRIER, 0)
|
|
|
|
DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER,
|
|
|
|
PPC_ATOMIC_EXIT_BARRIER, 0)
|
2009-07-07 23:23:56 +08:00
|
|
|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
static __inline__ int test_and_set_bit(unsigned long nr,
|
|
|
|
volatile unsigned long *addr)
|
|
|
|
{
|
2012-11-04 10:03:44 +08:00
|
|
|
return test_and_set_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
}
|
|
|
|
|
2007-10-18 18:06:53 +08:00
|
|
|
static __inline__ int test_and_set_bit_lock(unsigned long nr,
|
|
|
|
volatile unsigned long *addr)
|
|
|
|
{
|
2012-11-04 10:03:44 +08:00
|
|
|
return test_and_set_bits_lock(BIT_MASK(nr),
|
|
|
|
addr + BIT_WORD(nr)) != 0;
|
2007-10-18 18:06:53 +08:00
|
|
|
}
|
|
|
|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
static __inline__ int test_and_clear_bit(unsigned long nr,
|
|
|
|
volatile unsigned long *addr)
|
|
|
|
{
|
2012-11-04 10:03:44 +08:00
|
|
|
return test_and_clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static __inline__ int test_and_change_bit(unsigned long nr,
|
|
|
|
volatile unsigned long *addr)
|
|
|
|
{
|
2012-11-04 10:03:44 +08:00
|
|
|
return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
}
|
|
|
|
|
powerpc/64: Implement clear_bit_unlock_is_negative_byte()
Commit b91e1302ad9b8 ("mm: optimize PageWaiters bit use for
unlock_page()") added a special bitop function to speed up
unlock_page(). Implement this for 64-bit powerpc.
This improves the unlock_page() core code from this:
li 9,1
lwsync
1: ldarx 10,0,3,0
andc 10,10,9
stdcx. 10,0,3
bne- 1b
ori 2,2,0
ld 9,0(3)
andi. 10,9,0x80
beqlr
li 4,0
b wake_up_page_bit
To this:
li 10,1
lwsync
1: ldarx 9,0,3,0
andc 9,9,10
stdcx. 9,0,3
bne- 1b
andi. 10,9,0x80
beqlr
li 4,0
b wake_up_page_bit
In a test of elapsed time for dd writing into 16GB of already-dirty
pagecache on a POWER8 with 4K pages, which has one unlock_page per 4kB
this patch reduced overhead by 1.1%:
N Min Max Median Avg Stddev
x 19 2.578 2.619 2.594 2.595 0.011
+ 19 2.552 2.592 2.564 2.565 0.008
Difference at 95.0% confidence
-0.030 +/- 0.006
-1.142% +/- 0.243%
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Made 64-bit only until I can test it properly on 32-bit]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-01-04 02:58:28 +08:00
|
|
|
#ifdef CONFIG_PPC64
|
|
|
|
static __inline__ unsigned long clear_bit_unlock_return_word(int nr,
|
|
|
|
volatile unsigned long *addr)
|
|
|
|
{
|
|
|
|
unsigned long old, t;
|
|
|
|
unsigned long *p = (unsigned long *)addr + BIT_WORD(nr);
|
|
|
|
unsigned long mask = BIT_MASK(nr);
|
|
|
|
|
|
|
|
__asm__ __volatile__ (
|
|
|
|
PPC_RELEASE_BARRIER
|
|
|
|
"1:" PPC_LLARX(%0,0,%3,0) "\n"
|
|
|
|
"andc %1,%0,%2\n"
|
|
|
|
PPC405_ERR77(0,%3)
|
|
|
|
PPC_STLCX "%1,0,%3\n"
|
|
|
|
"bne- 1b\n"
|
|
|
|
: "=&r" (old), "=&r" (t)
|
|
|
|
: "r" (mask), "r" (p)
|
|
|
|
: "cc", "memory");
|
|
|
|
|
|
|
|
return old;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* This is a special function for mm/filemap.c */
|
|
|
|
#define clear_bit_unlock_is_negative_byte(nr, addr) \
|
|
|
|
(clear_bit_unlock_return_word(nr, addr) & BIT_MASK(PG_waiters))
|
|
|
|
|
|
|
|
#endif /* CONFIG_PPC64 */
|
|
|
|
|
2006-03-26 17:39:33 +08:00
|
|
|
#include <asm-generic/bitops/non-atomic.h>
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
|
2007-10-18 18:06:53 +08:00
|
|
|
static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr)
|
|
|
|
{
|
2010-02-10 09:04:06 +08:00
|
|
|
__asm__ __volatile__(PPC_RELEASE_BARRIER "" ::: "memory");
|
2007-10-18 18:06:53 +08:00
|
|
|
__clear_bit(nr, addr);
|
|
|
|
}
|
|
|
|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
/*
|
|
|
|
* Return the zero-based bit position (LE, not IBM bit numbering) of
|
|
|
|
* the most significant 1-bit in a double word.
|
|
|
|
*/
|
2006-12-08 18:37:53 +08:00
|
|
|
static __inline__ __attribute__((const))
|
|
|
|
int __ilog2(unsigned long x)
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
{
|
|
|
|
int lz;
|
|
|
|
|
[PATCH] powerpc: Consolidate asm compatibility macros
This patch consolidates macros used to generate assembly for
compatibility across different CPUs or configs. A new header,
asm-powerpc/asm-compat.h contains the main compatibility macros. It
uses some preprocessor magic to make the macros suitable both for use
in .S files, and in inline asm in .c files. Headers (bitops.h,
uaccess.h, atomic.h, bug.h) which had their own such compatibility
macros are changed to use asm-compat.h.
ppc_asm.h is now for use in .S files *only*, and a #error enforces
that. As such, we're a lot more careless about namespace pollution
here than in asm-compat.h.
While we're at it, this patch adds a call to the PPC405_ERR77 macro in
futex.h which should have had it already, but didn't.
Built and booted on pSeries, Maple and iSeries (ARCH=powerpc). Built
for 32-bit powermac (ARCH=powerpc) and Walnut (ARCH=ppc).
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-10 09:56:55 +08:00
|
|
|
asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (x));
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
return BITS_PER_LONG - 1 - lz;
|
|
|
|
}
|
|
|
|
|
2006-12-08 18:37:53 +08:00
|
|
|
static inline __attribute__((const))
|
|
|
|
int __ilog2_u32(u32 n)
|
|
|
|
{
|
|
|
|
int bit;
|
|
|
|
asm ("cntlzw %0,%1" : "=r" (bit) : "r" (n));
|
|
|
|
return 31 - bit;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef __powerpc64__
|
|
|
|
static inline __attribute__((const))
|
2006-12-11 21:16:05 +08:00
|
|
|
int __ilog2_u64(u64 n)
|
2006-12-08 18:37:53 +08:00
|
|
|
{
|
|
|
|
int bit;
|
|
|
|
asm ("cntlzd %0,%1" : "=r" (bit) : "r" (n));
|
|
|
|
return 63 - bit;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
/*
|
|
|
|
* Determines the bit position of the least significant 0 bit in the
|
|
|
|
* specified double word. The returned bit position will be
|
|
|
|
* zero-based, starting from the right side (63/31 - 0).
|
|
|
|
*/
|
|
|
|
static __inline__ unsigned long ffz(unsigned long x)
|
|
|
|
{
|
|
|
|
/* no zero exists anywhere in the 8 byte area. */
|
|
|
|
if ((x = ~x) == 0)
|
|
|
|
return BITS_PER_LONG;
|
|
|
|
|
|
|
|
/*
|
2011-03-31 09:57:33 +08:00
|
|
|
* Calculate the bit position of the least significant '1' bit in x
|
|
|
|
* (since x has been changed this will actually be the least significant
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
* '0' bit in * the original x). Note: (x & -x) gives us a mask that
|
|
|
|
* is the least significant * (RIGHT-most) 1-bit of the value in x.
|
|
|
|
*/
|
|
|
|
return __ilog2(x & -x);
|
|
|
|
}
|
|
|
|
|
2014-09-17 20:15:37 +08:00
|
|
|
static __inline__ unsigned long __ffs(unsigned long x)
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
{
|
|
|
|
return __ilog2(x & -x);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ffs: find first bit set. This is defined the same way as
|
|
|
|
* the libc and compiler builtin ffs routines, therefore
|
|
|
|
* differs in spirit from the above ffz (man ffs).
|
|
|
|
*/
|
|
|
|
static __inline__ int ffs(int x)
|
|
|
|
{
|
|
|
|
unsigned long i = (unsigned long)x;
|
|
|
|
return __ilog2(i & -i) + 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* fls: find last (most-significant) bit set.
|
|
|
|
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
|
|
|
|
*/
|
|
|
|
static __inline__ int fls(unsigned int x)
|
|
|
|
{
|
|
|
|
int lz;
|
|
|
|
|
|
|
|
asm ("cntlzw %0,%1" : "=r" (lz) : "r" (x));
|
|
|
|
return 32 - lz;
|
|
|
|
}
|
2008-04-18 12:26:08 +08:00
|
|
|
|
2008-03-16 01:31:49 +08:00
|
|
|
static __inline__ unsigned long __fls(unsigned long x)
|
|
|
|
{
|
|
|
|
return __ilog2(x);
|
|
|
|
}
|
|
|
|
|
2008-04-18 12:26:08 +08:00
|
|
|
/*
|
|
|
|
* 64-bit can do this using one cntlzd (count leading zeroes doubleword)
|
|
|
|
* instruction; for 32-bit we use the generic version, which does two
|
|
|
|
* 32-bit fls calls.
|
|
|
|
*/
|
|
|
|
#ifdef __powerpc64__
|
|
|
|
static __inline__ int fls64(__u64 x)
|
|
|
|
{
|
|
|
|
int lz;
|
|
|
|
|
|
|
|
asm ("cntlzd %0,%1" : "=r" (lz) : "r" (x));
|
|
|
|
return 64 - lz;
|
|
|
|
}
|
|
|
|
#else
|
2006-03-26 17:39:33 +08:00
|
|
|
#include <asm-generic/bitops/fls64.h>
|
2008-04-18 12:26:08 +08:00
|
|
|
#endif /* __powerpc64__ */
|
|
|
|
|
2010-08-13 00:28:09 +08:00
|
|
|
#ifdef CONFIG_PPC64
|
|
|
|
unsigned int __arch_hweight8(unsigned int w);
|
|
|
|
unsigned int __arch_hweight16(unsigned int w);
|
|
|
|
unsigned int __arch_hweight32(unsigned int w);
|
|
|
|
unsigned long __arch_hweight64(__u64 w);
|
|
|
|
#include <asm-generic/bitops/const_hweight.h>
|
|
|
|
#else
|
2006-03-26 17:39:33 +08:00
|
|
|
#include <asm-generic/bitops/hweight.h>
|
2010-08-13 00:28:09 +08:00
|
|
|
#endif
|
|
|
|
|
2008-04-16 21:55:08 +08:00
|
|
|
#include <asm-generic/bitops/find.h>
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
|
|
|
|
/* Little-endian versions */
|
2012-11-04 10:03:45 +08:00
|
|
|
#include <asm-generic/bitops/le.h>
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
|
|
|
|
/* Bitmap functions for the ext2 filesystem */
|
|
|
|
|
2011-07-27 07:09:04 +08:00
|
|
|
#include <asm-generic/bitops/ext2-atomic-setbit.h>
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
|
2006-03-26 17:39:33 +08:00
|
|
|
#include <asm-generic/bitops/sched.h>
|
[PATCH] powerpc: Merge bitops.h
Here's a revised version. This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch). In fact it is used in the powermac interrupt code
(but not on pSeries).
- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S
- ppc32 previously used a full "sync" barrier at the end of
test_and_*_bit(), whereas ppc64 used an "isync". The merged version
uses "isync", since I believe that's sufficient.
- The ppc64 versions of then minix_*() bitmap functions have changed
semantics. Previously on ppc64, these functions were big-endian
(that is bit 0 was the LSB in the first 64-bit, big-endian word).
On ppc32 (and x86, for that matter, they were little-endian. As far
as I can tell, the big-endian usage was simply wrong - I guess
no-one ever tried to use minixfs on ppc64.
- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
inline (they were already out-of-line on ppc64).
- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
the merged bitops. What it was doing in mmu_context.h in the first
place, I have no idea.
- The fls() function is now implemented using the cntlzw instruction
on ppc64, instead of generic_fls(), as it already was on ppc32.
- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
arch/ppc/Makefile. This in turn requires some changes to
arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.
Built and running on G5.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-01 14:28:10 +08:00
|
|
|
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
|
|
|
|
#endif /* _ASM_POWERPC_BITOPS_H */
|