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>
83 lines
2.2 KiB
C
83 lines
2.2 KiB
C
/*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*
|
|
* Copyright (C) 1992 - 1997, 2000-2005 Silicon Graphics, Inc. All rights reserved.
|
|
*/
|
|
#ifndef _ASM_IA64_SN_NODEPDA_H
|
|
#define _ASM_IA64_SN_NODEPDA_H
|
|
|
|
|
|
#include <asm/irq.h>
|
|
#include <asm/sn/arch.h>
|
|
#include <asm/sn/intr.h>
|
|
#include <asm/sn/bte.h>
|
|
|
|
/*
|
|
* NUMA Node-Specific Data structures are defined in this file.
|
|
* In particular, this is the location of the node PDA.
|
|
* A pointer to the right node PDA is saved in each CPU PDA.
|
|
*/
|
|
|
|
/*
|
|
* Node-specific data structure.
|
|
*
|
|
* One of these structures is allocated on each node of a NUMA system.
|
|
*
|
|
* This structure provides a convenient way of keeping together
|
|
* all per-node data structures.
|
|
*/
|
|
struct phys_cpuid {
|
|
short nasid;
|
|
char subnode;
|
|
char slice;
|
|
};
|
|
|
|
struct nodepda_s {
|
|
void *pdinfo; /* Platform-dependent per-node info */
|
|
|
|
/*
|
|
* The BTEs on this node are shared by the local cpus
|
|
*/
|
|
struct bteinfo_s bte_if[MAX_BTES_PER_NODE]; /* Virtual Interface */
|
|
struct timer_list bte_recovery_timer;
|
|
spinlock_t bte_recovery_lock;
|
|
|
|
/*
|
|
* Array of pointers to the nodepdas for each node.
|
|
*/
|
|
struct nodepda_s *pernode_pdaindr[MAX_COMPACT_NODES];
|
|
|
|
/*
|
|
* Array of physical cpu identifiers. Indexed by cpuid.
|
|
*/
|
|
struct phys_cpuid phys_cpuid[NR_CPUS];
|
|
spinlock_t ptc_lock ____cacheline_aligned_in_smp;
|
|
};
|
|
|
|
typedef struct nodepda_s nodepda_t;
|
|
|
|
/*
|
|
* Access Functions for node PDA.
|
|
* Since there is one nodepda for each node, we need a convenient mechanism
|
|
* to access these nodepdas without cluttering code with #ifdefs.
|
|
* The next set of definitions provides this.
|
|
* Routines are expected to use
|
|
*
|
|
* sn_nodepda - to access node PDA for the node on which code is running
|
|
* NODEPDA(cnodeid) - to access node PDA for cnodeid
|
|
*/
|
|
|
|
DECLARE_PER_CPU(struct nodepda_s *, __sn_nodepda);
|
|
#define sn_nodepda __this_cpu_read(__sn_nodepda)
|
|
#define NODEPDA(cnodeid) (sn_nodepda->pernode_pdaindr[cnodeid])
|
|
|
|
/*
|
|
* Check if given a compact node id the corresponding node has all the
|
|
* cpus disabled.
|
|
*/
|
|
#define is_headless_node(cnodeid) (nr_cpus_node(cnodeid) == 0)
|
|
|
|
#endif /* _ASM_IA64_SN_NODEPDA_H */
|