forked from Minki/linux
6065a244a0
__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: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: linux-ia64@vger.kernel.org
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
80 lines
2.9 KiB
C
80 lines
2.9 KiB
C
/*
|
|
* Low-level task switching. This is based on information published in
|
|
* the Processor Abstraction Layer and the System Abstraction Layer
|
|
* manual.
|
|
*
|
|
* Copyright (C) 1998-2003 Hewlett-Packard Co
|
|
* David Mosberger-Tang <davidm@hpl.hp.com>
|
|
* Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
|
|
* Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
|
|
*/
|
|
#ifndef _ASM_IA64_SWITCH_TO_H
|
|
#define _ASM_IA64_SWITCH_TO_H
|
|
|
|
#include <linux/percpu.h>
|
|
|
|
struct task_struct;
|
|
|
|
/*
|
|
* Context switch from one thread to another. If the two threads have
|
|
* different address spaces, schedule() has already taken care of
|
|
* switching to the new address space by calling switch_mm().
|
|
*
|
|
* Disabling access to the fph partition and the debug-register
|
|
* context switch MUST be done before calling ia64_switch_to() since a
|
|
* newly created thread returns directly to
|
|
* ia64_ret_from_syscall_clear_r8.
|
|
*/
|
|
extern struct task_struct *ia64_switch_to (void *next_task);
|
|
|
|
extern void ia64_save_extra (struct task_struct *task);
|
|
extern void ia64_load_extra (struct task_struct *task);
|
|
|
|
#ifdef CONFIG_PERFMON
|
|
DECLARE_PER_CPU(unsigned long, pfm_syst_info);
|
|
# define PERFMON_IS_SYSWIDE() (__this_cpu_read(pfm_syst_info) & 0x1)
|
|
#else
|
|
# define PERFMON_IS_SYSWIDE() (0)
|
|
#endif
|
|
|
|
#define IA64_HAS_EXTRA_STATE(t) \
|
|
((t)->thread.flags & (IA64_THREAD_DBG_VALID|IA64_THREAD_PM_VALID) \
|
|
|| PERFMON_IS_SYSWIDE())
|
|
|
|
#define __switch_to(prev,next,last) do { \
|
|
if (IA64_HAS_EXTRA_STATE(prev)) \
|
|
ia64_save_extra(prev); \
|
|
if (IA64_HAS_EXTRA_STATE(next)) \
|
|
ia64_load_extra(next); \
|
|
ia64_psr(task_pt_regs(next))->dfh = !ia64_is_local_fpu_owner(next); \
|
|
(last) = ia64_switch_to((next)); \
|
|
} while (0)
|
|
|
|
#ifdef CONFIG_SMP
|
|
/*
|
|
* In the SMP case, we save the fph state when context-switching away from a thread that
|
|
* modified fph. This way, when the thread gets scheduled on another CPU, the CPU can
|
|
* pick up the state from task->thread.fph, avoiding the complication of having to fetch
|
|
* the latest fph state from another CPU. In other words: eager save, lazy restore.
|
|
*/
|
|
# define switch_to(prev,next,last) do { \
|
|
if (ia64_psr(task_pt_regs(prev))->mfh && ia64_is_local_fpu_owner(prev)) { \
|
|
ia64_psr(task_pt_regs(prev))->mfh = 0; \
|
|
(prev)->thread.flags |= IA64_THREAD_FPH_VALID; \
|
|
__ia64_save_fpu((prev)->thread.fph); \
|
|
} \
|
|
__switch_to(prev, next, last); \
|
|
/* "next" in old context is "current" in new context */ \
|
|
if (unlikely((current->thread.flags & IA64_THREAD_MIGRATION) && \
|
|
(task_cpu(current) != \
|
|
task_thread_info(current)->last_cpu))) { \
|
|
platform_migrate(current); \
|
|
task_thread_info(current)->last_cpu = task_cpu(current); \
|
|
} \
|
|
} while (0)
|
|
#else
|
|
# define switch_to(prev,next,last) __switch_to(prev, next, last)
|
|
#endif
|
|
|
|
#endif /* _ASM_IA64_SWITCH_TO_H */
|