5fb7dc37dc
per cpu data section contains two types of data. One set which is exclusively accessed by the local cpu and the other set which is per cpu, but also shared by remote cpus. In the current kernel, these two sets are not clearely separated out. This can potentially cause the same data cacheline shared between the two sets of data, which will result in unnecessary bouncing of the cacheline between cpus. One way to fix the problem is to cacheline align the remotely accessed per cpu data, both at the beginning and at the end. Because of the padding at both ends, this will likely cause some memory wastage and also the interface to achieve this is not clean. This patch: Moves the remotely accessed per cpu data (which is currently marked as ____cacheline_aligned_in_smp) into a different section, where all the data elements are cacheline aligned. And as such, this differentiates the local only data and remotely accessed data cleanly. Signed-off-by: Fenghua Yu <fenghua.yu@intel.com> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Christoph Lameter <clameter@sgi.com> Cc: <linux-arch@vger.kernel.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Andi Kleen <ak@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
68 lines
2.2 KiB
C
68 lines
2.2 KiB
C
#ifndef _ASM_X8664_PERCPU_H_
|
|
#define _ASM_X8664_PERCPU_H_
|
|
#include <linux/compiler.h>
|
|
|
|
/* Same as asm-generic/percpu.h, except that we store the per cpu offset
|
|
in the PDA. Longer term the PDA and every per cpu variable
|
|
should be just put into a single section and referenced directly
|
|
from %gs */
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
#include <asm/pda.h>
|
|
|
|
#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
|
|
#define __my_cpu_offset() read_pda(data_offset)
|
|
|
|
#define per_cpu_offset(x) (__per_cpu_offset(x))
|
|
|
|
/* Separate out the type, so (int[3], foo) works. */
|
|
#define DEFINE_PER_CPU(type, name) \
|
|
__attribute__((__section__(".data.percpu"))) __typeof__(type) per_cpu__##name
|
|
|
|
#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \
|
|
__attribute__((__section__(".data.percpu.shared_aligned"))) \
|
|
__typeof__(type) per_cpu__##name \
|
|
____cacheline_internodealigned_in_smp
|
|
|
|
/* var is in discarded region: offset to particular copy we want */
|
|
#define per_cpu(var, cpu) (*({ \
|
|
extern int simple_identifier_##var(void); \
|
|
RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)); }))
|
|
#define __get_cpu_var(var) (*({ \
|
|
extern int simple_identifier_##var(void); \
|
|
RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()); }))
|
|
#define __raw_get_cpu_var(var) (*({ \
|
|
extern int simple_identifier_##var(void); \
|
|
RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()); }))
|
|
|
|
/* A macro to avoid #include hell... */
|
|
#define percpu_modcopy(pcpudst, src, size) \
|
|
do { \
|
|
unsigned int __i; \
|
|
for_each_possible_cpu(__i) \
|
|
memcpy((pcpudst)+__per_cpu_offset(__i), \
|
|
(src), (size)); \
|
|
} while (0)
|
|
|
|
extern void setup_per_cpu_areas(void);
|
|
|
|
#else /* ! SMP */
|
|
|
|
#define DEFINE_PER_CPU(type, name) \
|
|
__typeof__(type) per_cpu__##name
|
|
#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \
|
|
DEFINE_PER_CPU(type, name)
|
|
|
|
#define per_cpu(var, cpu) (*((void)(cpu), &per_cpu__##var))
|
|
#define __get_cpu_var(var) per_cpu__##var
|
|
#define __raw_get_cpu_var(var) per_cpu__##var
|
|
|
|
#endif /* SMP */
|
|
|
|
#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
|
|
|
|
#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
|
|
#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
|
|
|
|
#endif /* _ASM_X8664_PERCPU_H_ */
|