hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
linux-sg2042/arch/x86/lib/atomic64_cx8_32.S

216 lines
3.1 KiB
ArmAsm
Raw Normal View History

x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
/*
* atomic64_t for 586+
*
* Copyright © 2010 Luca Barbieri
*
* 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.
*/
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
#include <asm/dwarf2.h>
.macro SAVE reg
x86: Use {push,pop}_cfi in more places Cleaning up and shortening code... Signed-off-by: Jan Beulich <jbeulich@novell.com> Cc: Alexander van Heukelum <heukelum@fastmail.fm> LKML-Reference: <4D6BD35002000078000341DA@vpn.id2.novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-28 23:54:40 +08:00
pushl_cfi %\reg
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
CFI_REL_OFFSET \reg, 0
.endm
.macro RESTORE reg
x86: Use {push,pop}_cfi in more places Cleaning up and shortening code... Signed-off-by: Jan Beulich <jbeulich@novell.com> Cc: Alexander van Heukelum <heukelum@fastmail.fm> LKML-Reference: <4D6BD35002000078000341DA@vpn.id2.novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-28 23:54:40 +08:00
popl_cfi %\reg
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
CFI_RESTORE \reg
.endm
.macro read64 reg
movl %ebx, %eax
movl %ecx, %edx
/* we need LOCK_PREFIX since otherwise cmpxchg8b always does the write */
LOCK_PREFIX
cmpxchg8b (\reg)
.endm
ENTRY(atomic64_read_cx8)
CFI_STARTPROC
read64 %ecx
ret
CFI_ENDPROC
ENDPROC(atomic64_read_cx8)
ENTRY(atomic64_set_cx8)
CFI_STARTPROC
1:
/* we don't need LOCK_PREFIX since aligned 64-bit writes
* are atomic on 586 and newer */
cmpxchg8b (%esi)
jne 1b
ret
CFI_ENDPROC
ENDPROC(atomic64_set_cx8)
ENTRY(atomic64_xchg_cx8)
CFI_STARTPROC
1:
LOCK_PREFIX
cmpxchg8b (%esi)
jne 1b
ret
CFI_ENDPROC
ENDPROC(atomic64_xchg_cx8)
.macro addsub_return func ins insc
ENTRY(atomic64_\func\()_return_cx8)
CFI_STARTPROC
SAVE ebp
SAVE ebx
SAVE esi
SAVE edi
movl %eax, %esi
movl %edx, %edi
movl %ecx, %ebp
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
read64 %ecx
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
1:
movl %eax, %ebx
movl %edx, %ecx
\ins\()l %esi, %ebx
\insc\()l %edi, %ecx
LOCK_PREFIX
cmpxchg8b (%ebp)
jne 1b
10:
movl %ebx, %eax
movl %ecx, %edx
RESTORE edi
RESTORE esi
RESTORE ebx
RESTORE ebp
ret
CFI_ENDPROC
ENDPROC(atomic64_\func\()_return_cx8)
.endm
addsub_return add add adc
addsub_return sub sub sbb
.macro incdec_return func ins insc
ENTRY(atomic64_\func\()_return_cx8)
CFI_STARTPROC
SAVE ebx
read64 %esi
1:
movl %eax, %ebx
movl %edx, %ecx
\ins\()l $1, %ebx
\insc\()l $0, %ecx
LOCK_PREFIX
cmpxchg8b (%esi)
jne 1b
10:
movl %ebx, %eax
movl %ecx, %edx
RESTORE ebx
ret
CFI_ENDPROC
ENDPROC(atomic64_\func\()_return_cx8)
.endm
incdec_return inc add adc
incdec_return dec sub sbb
ENTRY(atomic64_dec_if_positive_cx8)
CFI_STARTPROC
SAVE ebx
read64 %esi
1:
movl %eax, %ebx
movl %edx, %ecx
subl $1, %ebx
sbb $0, %ecx
js 2f
LOCK_PREFIX
cmpxchg8b (%esi)
jne 1b
2:
movl %ebx, %eax
movl %ecx, %edx
RESTORE ebx
ret
CFI_ENDPROC
ENDPROC(atomic64_dec_if_positive_cx8)
ENTRY(atomic64_add_unless_cx8)
CFI_STARTPROC
SAVE ebp
SAVE ebx
/* these just push these two parameters on the stack */
SAVE edi
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
SAVE ecx
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
movl %eax, %ebp
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
movl %edx, %edi
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
read64 %esi
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
1:
cmpl %eax, 0(%esp)
je 4f
2:
movl %eax, %ebx
movl %edx, %ecx
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
addl %ebp, %ebx
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
adcl %edi, %ecx
LOCK_PREFIX
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
cmpxchg8b (%esi)
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
jne 1b
x86-32: Fix atomic64_add_unless return value convention atomic64_add_unless must return 1 if it perfomed the add and 0 otherwise. The implementation did the opposite thing. Reported-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267469749-11878-3-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-03-02 02:55:46 +08:00
movl $1, %eax
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
3:
addl $8, %esp
CFI_ADJUST_CFA_OFFSET -8
RESTORE ebx
RESTORE ebp
ret
4:
cmpl %edx, 4(%esp)
jne 2b
x86-32: Fix atomic64_add_unless return value convention atomic64_add_unless must return 1 if it perfomed the add and 0 otherwise. The implementation did the opposite thing. Reported-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267469749-11878-3-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-03-02 02:55:46 +08:00
xorl %eax, %eax
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
jmp 3b
CFI_ENDPROC
ENDPROC(atomic64_add_unless_cx8)
ENTRY(atomic64_inc_not_zero_cx8)
CFI_STARTPROC
SAVE ebx
read64 %esi
1:
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
movl %eax, %ecx
orl %edx, %ecx
jz 3f
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
movl %eax, %ebx
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
xorl %ecx, %ecx
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
addl $1, %ebx
x86: atomic64 assembly improvements In the "xchg" implementation, %ebx and %ecx don't need to be copied into %eax and %edx respectively (this is only necessary when desiring to only read the stored value). In the "add_unless" implementation, swapping the use of %ecx and %esi for passing arguments allows %esi to become an input only (i.e. permitting the register to be re-used to address the same object without reload). In "{add,sub}_return", doing the initial read64 through the passed in %ecx decreases a register dependency. In "inc_not_zero", a branch can be eliminated by or-ing together the two halves of the current (64-bit) value, and code size can be further reduced by adjusting the arithmetic slightly. v2: Undo the folding of "xchg" and "set". Signed-off-by: Jan Beulich <jbeulich@suse.com> Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com Cc: Luca Barbieri <luca@luca-barbieri.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-21 00:22:04 +08:00
adcl %edx, %ecx
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
LOCK_PREFIX
cmpxchg8b (%esi)
jne 1b
x86-32: Fix atomic64_inc_not_zero return value convention atomic64_inc_not_zero must return 1 if it perfomed the add and 0 otherwise. It was doing the opposite thing. Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267469749-11878-6-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-03-02 02:55:49 +08:00
movl $1, %eax
x86-32: Rewrite 32-bit atomic64 functions in assembly This patch replaces atomic64_32.c with two assembly implementations, one for 386/486 machines using pushf/cli/popf and one for 586+ machines using cmpxchg8b. The cmpxchg8b implementation provides the following advantages over the current one: 1. Implements atomic64_add_unless, atomic64_dec_if_positive and atomic64_inc_not_zero 2. Uses the ZF flag changed by cmpxchg8b instead of doing a comparison 3. Uses custom register calling conventions that reduce or eliminate register moves to suit cmpxchg8b 4. Reads the initial value instead of using cmpxchg8b to do that. Currently we use lock xaddl and movl, which seems the fastest. 5. Does not use the lock prefix for atomic64_set 64-bit writes are already atomic, so we don't need that. We still need it for atomic64_read to avoid restoring a value changed in the meantime. 6. Allocates registers as well or better than gcc The 386 implementation provides support for 386 and 486 machines. 386/486 SMP is not supported (we dropped it), but such support can be added easily if desired. A pure assembly implementation is required due to the custom calling conventions, and desire to use %ebp in atomic64_add_return (we need 7 registers...), as well as the ability to use pushf/popf in the 386 code without an intermediate pop/push. The parameter names are changed to match the convention in atomic_64.h Changes in v3 (due to rebasing to tip/x86/asm): - Patches atomic64_32.h instead of atomic_32.h - Uses the CALL alternative mechanism from commit 1b1d9258181bae199dc940f4bd0298126b9a73d9 Changes in v2: - Merged 386 and cx8 support in the same patch - 386 support now done in assembly, C code no longer used at all - cmpxchg64 is used for atomic64_cmpxchg - stop using macros, use one-line inline functions instead - miscellanous changes and improvements Signed-off-by: Luca Barbieri <luca@luca-barbieri.com> LKML-Reference: <1267005265-27958-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-02-24 17:54:25 +08:00
3:
RESTORE ebx
ret
CFI_ENDPROC
ENDPROC(atomic64_inc_not_zero_cx8)