2005-04-17 06:20:36 +08:00
|
|
|
#ifndef __ARCH_S390_PERCPU__
|
|
|
|
|
#define __ARCH_S390_PERCPU__
|
|
|
|
|
|
2011-05-23 16:24:32 +08:00
|
|
|
#include <linux/preempt.h>
|
|
|
|
|
#include <asm/cmpxchg.h>
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
|
* s390 uses its own implementation for per cpu data, the offset of
|
|
|
|
|
* the cpu local data area is cached in the cpu's lowcore memory.
|
|
|
|
|
*/
|
2009-06-24 14:13:53 +08:00
|
|
|
#define __my_cpu_offset S390_lowcore.percpu_offset
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-06-24 14:13:53 +08:00
|
|
|
/*
|
|
|
|
|
* For 64 bit module code, the module may be more than 4G above the
|
|
|
|
|
* per cpu area, use weak definitions to force the compiler to
|
|
|
|
|
* generate external references.
|
|
|
|
|
*/
|
2013-10-21 13:44:08 +08:00
|
|
|
#if defined(CONFIG_SMP) && defined(MODULE)
|
2009-06-24 14:13:53 +08:00
|
|
|
#define ARCH_NEEDS_WEAK_PER_CPU
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
2013-10-21 13:57:41 +08:00
|
|
|
/*
|
|
|
|
|
* We use a compare-and-swap loop since that uses less cpu cycles than
|
|
|
|
|
* disabling and enabling interrupts like the generic variant would do.
|
|
|
|
|
*/
|
|
|
|
|
#define arch_this_cpu_to_op_simple(pcp, val, op) \
|
2012-09-17 12:46:55 +08:00
|
|
|
({ \
|
2011-05-23 16:24:32 +08:00
|
|
|
typedef typeof(pcp) pcp_op_T__; \
|
|
|
|
|
pcp_op_T__ old__, new__, prev__; \
|
|
|
|
|
pcp_op_T__ *ptr__; \
|
|
|
|
|
preempt_disable(); \
|
s390: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e. using a global
register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
this_cpu_inc(y)
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
CC: linux390@de.ibm.com
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:45 +08:00
|
|
|
ptr__ = raw_cpu_ptr(&(pcp)); \
|
2011-05-23 16:24:32 +08:00
|
|
|
prev__ = *ptr__; \
|
|
|
|
|
do { \
|
|
|
|
|
old__ = prev__; \
|
|
|
|
|
new__ = old__ op (val); \
|
2013-10-21 13:44:08 +08:00
|
|
|
prev__ = cmpxchg(ptr__, old__, new__); \
|
2011-05-23 16:24:32 +08:00
|
|
|
} while (prev__ != old__); \
|
|
|
|
|
preempt_enable(); \
|
2012-09-17 12:46:55 +08:00
|
|
|
new__; \
|
|
|
|
|
})
|
2011-05-23 16:24:32 +08:00
|
|
|
|
2013-10-21 13:57:41 +08:00
|
|
|
#define this_cpu_add_1(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +)
|
|
|
|
|
#define this_cpu_add_2(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +)
|
|
|
|
|
#define this_cpu_add_return_1(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +)
|
|
|
|
|
#define this_cpu_add_return_2(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +)
|
|
|
|
|
#define this_cpu_and_1(pcp, val) arch_this_cpu_to_op_simple(pcp, val, &)
|
|
|
|
|
#define this_cpu_and_2(pcp, val) arch_this_cpu_to_op_simple(pcp, val, &)
|
|
|
|
|
#define this_cpu_or_1(pcp, val) arch_this_cpu_to_op_simple(pcp, val, |)
|
|
|
|
|
#define this_cpu_or_2(pcp, val) arch_this_cpu_to_op_simple(pcp, val, |)
|
|
|
|
|
|
|
|
|
|
#ifndef CONFIG_HAVE_MARCH_Z196_FEATURES
|
|
|
|
|
|
|
|
|
|
#define this_cpu_add_4(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +)
|
|
|
|
|
#define this_cpu_add_8(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +)
|
|
|
|
|
#define this_cpu_add_return_4(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +)
|
|
|
|
|
#define this_cpu_add_return_8(pcp, val) arch_this_cpu_to_op_simple(pcp, val, +)
|
|
|
|
|
#define this_cpu_and_4(pcp, val) arch_this_cpu_to_op_simple(pcp, val, &)
|
|
|
|
|
#define this_cpu_and_8(pcp, val) arch_this_cpu_to_op_simple(pcp, val, &)
|
|
|
|
|
#define this_cpu_or_4(pcp, val) arch_this_cpu_to_op_simple(pcp, val, |)
|
|
|
|
|
#define this_cpu_or_8(pcp, val) arch_this_cpu_to_op_simple(pcp, val, |)
|
|
|
|
|
|
|
|
|
|
#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
|
|
|
|
|
|
|
|
|
|
#define arch_this_cpu_add(pcp, val, op1, op2, szcast) \
|
|
|
|
|
{ \
|
|
|
|
|
typedef typeof(pcp) pcp_op_T__; \
|
|
|
|
|
pcp_op_T__ val__ = (val); \
|
|
|
|
|
pcp_op_T__ old__, *ptr__; \
|
|
|
|
|
preempt_disable(); \
|
s390: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e. using a global
register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
this_cpu_inc(y)
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
CC: linux390@de.ibm.com
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:45 +08:00
|
|
|
ptr__ = raw_cpu_ptr(&(pcp)); \
|
2013-10-21 13:57:41 +08:00
|
|
|
if (__builtin_constant_p(val__) && \
|
|
|
|
|
((szcast)val__ > -129) && ((szcast)val__ < 128)) { \
|
|
|
|
|
asm volatile( \
|
|
|
|
|
op2 " %[ptr__],%[val__]\n" \
|
|
|
|
|
: [ptr__] "+Q" (*ptr__) \
|
|
|
|
|
: [val__] "i" ((szcast)val__) \
|
|
|
|
|
: "cc"); \
|
|
|
|
|
} else { \
|
|
|
|
|
asm volatile( \
|
|
|
|
|
op1 " %[old__],%[val__],%[ptr__]\n" \
|
|
|
|
|
: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \
|
|
|
|
|
: [val__] "d" (val__) \
|
|
|
|
|
: "cc"); \
|
|
|
|
|
} \
|
|
|
|
|
preempt_enable(); \
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int)
|
|
|
|
|
#define this_cpu_add_8(pcp, val) arch_this_cpu_add(pcp, val, "laag", "agsi", long)
|
|
|
|
|
|
|
|
|
|
#define arch_this_cpu_add_return(pcp, val, op) \
|
|
|
|
|
({ \
|
|
|
|
|
typedef typeof(pcp) pcp_op_T__; \
|
|
|
|
|
pcp_op_T__ val__ = (val); \
|
|
|
|
|
pcp_op_T__ old__, *ptr__; \
|
|
|
|
|
preempt_disable(); \
|
s390: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e. using a global
register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
this_cpu_inc(y)
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
CC: linux390@de.ibm.com
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:45 +08:00
|
|
|
ptr__ = raw_cpu_ptr(&(pcp)); \
|
2013-10-21 13:57:41 +08:00
|
|
|
asm volatile( \
|
|
|
|
|
op " %[old__],%[val__],%[ptr__]\n" \
|
|
|
|
|
: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \
|
|
|
|
|
: [val__] "d" (val__) \
|
|
|
|
|
: "cc"); \
|
|
|
|
|
preempt_enable(); \
|
|
|
|
|
old__ + val__; \
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
#define this_cpu_add_return_4(pcp, val) arch_this_cpu_add_return(pcp, val, "laa")
|
|
|
|
|
#define this_cpu_add_return_8(pcp, val) arch_this_cpu_add_return(pcp, val, "laag")
|
|
|
|
|
|
|
|
|
|
#define arch_this_cpu_to_op(pcp, val, op) \
|
|
|
|
|
{ \
|
|
|
|
|
typedef typeof(pcp) pcp_op_T__; \
|
|
|
|
|
pcp_op_T__ val__ = (val); \
|
|
|
|
|
pcp_op_T__ old__, *ptr__; \
|
|
|
|
|
preempt_disable(); \
|
s390: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e. using a global
register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
this_cpu_inc(y)
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
CC: linux390@de.ibm.com
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:45 +08:00
|
|
|
ptr__ = raw_cpu_ptr(&(pcp)); \
|
2013-10-21 13:57:41 +08:00
|
|
|
asm volatile( \
|
|
|
|
|
op " %[old__],%[val__],%[ptr__]\n" \
|
|
|
|
|
: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \
|
|
|
|
|
: [val__] "d" (val__) \
|
|
|
|
|
: "cc"); \
|
|
|
|
|
preempt_enable(); \
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lan")
|
|
|
|
|
#define this_cpu_and_8(pcp, val) arch_this_cpu_to_op(pcp, val, "lang")
|
|
|
|
|
#define this_cpu_or_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lao")
|
|
|
|
|
#define this_cpu_or_8(pcp, val) arch_this_cpu_to_op(pcp, val, "laog")
|
|
|
|
|
|
|
|
|
|
#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
|
2011-05-23 16:24:32 +08:00
|
|
|
|
2012-09-17 13:37:13 +08:00
|
|
|
#define arch_this_cpu_cmpxchg(pcp, oval, nval) \
|
2011-05-23 16:24:32 +08:00
|
|
|
({ \
|
|
|
|
|
typedef typeof(pcp) pcp_op_T__; \
|
|
|
|
|
pcp_op_T__ ret__; \
|
|
|
|
|
pcp_op_T__ *ptr__; \
|
|
|
|
|
preempt_disable(); \
|
s390: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e. using a global
register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
this_cpu_inc(y)
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
CC: linux390@de.ibm.com
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:45 +08:00
|
|
|
ptr__ = raw_cpu_ptr(&(pcp)); \
|
2013-10-21 13:44:08 +08:00
|
|
|
ret__ = cmpxchg(ptr__, oval, nval); \
|
2011-05-23 16:24:32 +08:00
|
|
|
preempt_enable(); \
|
|
|
|
|
ret__; \
|
|
|
|
|
})
|
|
|
|
|
|
2011-12-23 01:58:51 +08:00
|
|
|
#define this_cpu_cmpxchg_1(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
|
|
|
|
|
#define this_cpu_cmpxchg_2(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
|
|
|
|
|
#define this_cpu_cmpxchg_4(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
|
|
|
|
|
#define this_cpu_cmpxchg_8(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
|
2011-05-23 16:24:32 +08:00
|
|
|
|
2012-09-17 12:38:22 +08:00
|
|
|
#define arch_this_cpu_xchg(pcp, nval) \
|
|
|
|
|
({ \
|
|
|
|
|
typeof(pcp) *ptr__; \
|
|
|
|
|
typeof(pcp) ret__; \
|
|
|
|
|
preempt_disable(); \
|
s390: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e. using a global
register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
this_cpu_inc(y)
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
CC: linux390@de.ibm.com
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:45 +08:00
|
|
|
ptr__ = raw_cpu_ptr(&(pcp)); \
|
2012-09-17 12:38:22 +08:00
|
|
|
ret__ = xchg(ptr__, nval); \
|
|
|
|
|
preempt_enable(); \
|
|
|
|
|
ret__; \
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
#define this_cpu_xchg_1(pcp, nval) arch_this_cpu_xchg(pcp, nval)
|
|
|
|
|
#define this_cpu_xchg_2(pcp, nval) arch_this_cpu_xchg(pcp, nval)
|
|
|
|
|
#define this_cpu_xchg_4(pcp, nval) arch_this_cpu_xchg(pcp, nval)
|
|
|
|
|
#define this_cpu_xchg_8(pcp, nval) arch_this_cpu_xchg(pcp, nval)
|
|
|
|
|
|
2012-09-17 13:37:13 +08:00
|
|
|
#define arch_this_cpu_cmpxchg_double(pcp1, pcp2, o1, o2, n1, n2) \
|
|
|
|
|
({ \
|
|
|
|
|
typeof(pcp1) o1__ = (o1), n1__ = (n1); \
|
|
|
|
|
typeof(pcp2) o2__ = (o2), n2__ = (n2); \
|
|
|
|
|
typeof(pcp1) *p1__; \
|
|
|
|
|
typeof(pcp2) *p2__; \
|
|
|
|
|
int ret__; \
|
|
|
|
|
preempt_disable(); \
|
s390: Replace __get_cpu_var uses
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e. using a global
register that may be set to the per cpu base.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
this_cpu_inc(y)
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
CC: linux390@de.ibm.com
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
2014-08-18 01:30:45 +08:00
|
|
|
p1__ = raw_cpu_ptr(&(pcp1)); \
|
|
|
|
|
p2__ = raw_cpu_ptr(&(pcp2)); \
|
2012-09-17 13:37:13 +08:00
|
|
|
ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__); \
|
|
|
|
|
preempt_enable(); \
|
|
|
|
|
ret__; \
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
#define this_cpu_cmpxchg_double_8 arch_this_cpu_cmpxchg_double
|
2013-10-21 13:44:08 +08:00
|
|
|
|
2008-01-31 06:27:58 +08:00
|
|
|
#include <asm-generic/percpu.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
|
#endif /* __ARCH_S390_PERCPU__ */
|