9b8de7479d
In non-SMP mode, the variable section attribute specified by DECLARE_PER_CPU() does not agree with that specified by DEFINE_PER_CPU(). This means that architectures that have a small data section references relative to a base register may throw up linkage errors due to too great a displacement between where the base register points and the per-CPU variable. On FRV, the .h declaration says that the variable is in the .sdata section, but the .c definition says it's actually in the .data section. The linker throws up the following errors: kernel/built-in.o: In function `release_task': kernel/exit.c:78: relocation truncated to fit: R_FRV_GPREL12 against symbol `per_cpu__process_counts' defined in .data section in kernel/built-in.o kernel/exit.c:78: relocation truncated to fit: R_FRV_GPREL12 against symbol `per_cpu__process_counts' defined in .data section in kernel/built-in.o To fix this, DECLARE_PER_CPU() should simply apply the same section attribute as does DEFINE_PER_CPU(). However, this is made slightly more complex by virtue of the fact that there are several variants on DEFINE, so these need to be matched by variants on DECLARE. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
200 lines
5.6 KiB
C
200 lines
5.6 KiB
C
#ifndef __LINUX_PERCPU_H
|
|
#define __LINUX_PERCPU_H
|
|
|
|
#include <linux/preempt.h>
|
|
#include <linux/slab.h> /* For kmalloc() */
|
|
#include <linux/smp.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/pfn.h>
|
|
|
|
#include <asm/percpu.h>
|
|
|
|
#define DEFINE_PER_CPU_SECTION(type, name, section) \
|
|
__attribute__((__section__(PER_CPU_BASE_SECTION section))) \
|
|
PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
|
|
|
|
#define DEFINE_PER_CPU(type, name) \
|
|
DEFINE_PER_CPU_SECTION(type, name, "")
|
|
|
|
#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \
|
|
DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
|
|
____cacheline_aligned_in_smp
|
|
|
|
#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \
|
|
DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
|
|
|
|
#define DEFINE_PER_CPU_FIRST(type, name) \
|
|
DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
|
|
|
|
#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
|
|
#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
|
|
|
|
/* enough to cover all DEFINE_PER_CPUs in modules */
|
|
#ifdef CONFIG_MODULES
|
|
#define PERCPU_MODULE_RESERVE (8 << 10)
|
|
#else
|
|
#define PERCPU_MODULE_RESERVE 0
|
|
#endif
|
|
|
|
#ifndef PERCPU_ENOUGH_ROOM
|
|
#define PERCPU_ENOUGH_ROOM \
|
|
(ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \
|
|
PERCPU_MODULE_RESERVE)
|
|
#endif
|
|
|
|
/*
|
|
* Must be an lvalue. Since @var must be a simple identifier,
|
|
* we force a syntax error here if it isn't.
|
|
*/
|
|
#define get_cpu_var(var) (*({ \
|
|
extern int simple_identifier_##var(void); \
|
|
preempt_disable(); \
|
|
&__get_cpu_var(var); }))
|
|
#define put_cpu_var(var) preempt_enable()
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
|
|
|
|
/* minimum unit size, also is the maximum supported allocation size */
|
|
#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(64 << 10)
|
|
|
|
/*
|
|
* PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
|
|
* back on the first chunk for dynamic percpu allocation if arch is
|
|
* manually allocating and mapping it for faster access (as a part of
|
|
* large page mapping for example).
|
|
*
|
|
* The following values give between one and two pages of free space
|
|
* after typical minimal boot (2-way SMP, single disk and NIC) with
|
|
* both defconfig and a distro config on x86_64 and 32. More
|
|
* intelligent way to determine this would be nice.
|
|
*/
|
|
#if BITS_PER_LONG > 32
|
|
#define PERCPU_DYNAMIC_RESERVE (20 << 10)
|
|
#else
|
|
#define PERCPU_DYNAMIC_RESERVE (12 << 10)
|
|
#endif
|
|
|
|
extern void *pcpu_base_addr;
|
|
|
|
typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno);
|
|
typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr);
|
|
|
|
extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
|
|
size_t static_size, size_t reserved_size,
|
|
ssize_t dyn_size, ssize_t unit_size,
|
|
void *base_addr,
|
|
pcpu_populate_pte_fn_t populate_pte_fn);
|
|
|
|
extern ssize_t __init pcpu_embed_first_chunk(
|
|
size_t static_size, size_t reserved_size,
|
|
ssize_t dyn_size, ssize_t unit_size);
|
|
|
|
/*
|
|
* Use this to get to a cpu's version of the per-cpu object
|
|
* dynamically allocated. Non-atomic access to the current CPU's
|
|
* version should probably be combined with get_cpu()/put_cpu().
|
|
*/
|
|
#define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
|
|
|
|
extern void *__alloc_reserved_percpu(size_t size, size_t align);
|
|
|
|
#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
|
|
|
|
struct percpu_data {
|
|
void *ptrs[1];
|
|
};
|
|
|
|
#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
|
|
|
|
#define per_cpu_ptr(ptr, cpu) \
|
|
({ \
|
|
struct percpu_data *__p = __percpu_disguise(ptr); \
|
|
(__typeof__(ptr))__p->ptrs[(cpu)]; \
|
|
})
|
|
|
|
#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
|
|
|
|
extern void *__alloc_percpu(size_t size, size_t align);
|
|
extern void free_percpu(void *__pdata);
|
|
|
|
#else /* CONFIG_SMP */
|
|
|
|
#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
|
|
|
|
static inline void *__alloc_percpu(size_t size, size_t align)
|
|
{
|
|
/*
|
|
* Can't easily make larger alignment work with kmalloc. WARN
|
|
* on it. Larger alignment should only be used for module
|
|
* percpu sections on SMP for which this path isn't used.
|
|
*/
|
|
WARN_ON_ONCE(align > SMP_CACHE_BYTES);
|
|
return kzalloc(size, GFP_KERNEL);
|
|
}
|
|
|
|
static inline void free_percpu(void *p)
|
|
{
|
|
kfree(p);
|
|
}
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
#define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type), \
|
|
__alignof__(type))
|
|
|
|
/*
|
|
* Optional methods for optimized non-lvalue per-cpu variable access.
|
|
*
|
|
* @var can be a percpu variable or a field of it and its size should
|
|
* equal char, int or long. percpu_read() evaluates to a lvalue and
|
|
* all others to void.
|
|
*
|
|
* These operations are guaranteed to be atomic w.r.t. preemption.
|
|
* The generic versions use plain get/put_cpu_var(). Archs are
|
|
* encouraged to implement single-instruction alternatives which don't
|
|
* require preemption protection.
|
|
*/
|
|
#ifndef percpu_read
|
|
# define percpu_read(var) \
|
|
({ \
|
|
typeof(per_cpu_var(var)) __tmp_var__; \
|
|
__tmp_var__ = get_cpu_var(var); \
|
|
put_cpu_var(var); \
|
|
__tmp_var__; \
|
|
})
|
|
#endif
|
|
|
|
#define __percpu_generic_to_op(var, val, op) \
|
|
do { \
|
|
get_cpu_var(var) op val; \
|
|
put_cpu_var(var); \
|
|
} while (0)
|
|
|
|
#ifndef percpu_write
|
|
# define percpu_write(var, val) __percpu_generic_to_op(var, (val), =)
|
|
#endif
|
|
|
|
#ifndef percpu_add
|
|
# define percpu_add(var, val) __percpu_generic_to_op(var, (val), +=)
|
|
#endif
|
|
|
|
#ifndef percpu_sub
|
|
# define percpu_sub(var, val) __percpu_generic_to_op(var, (val), -=)
|
|
#endif
|
|
|
|
#ifndef percpu_and
|
|
# define percpu_and(var, val) __percpu_generic_to_op(var, (val), &=)
|
|
#endif
|
|
|
|
#ifndef percpu_or
|
|
# define percpu_or(var, val) __percpu_generic_to_op(var, (val), |=)
|
|
#endif
|
|
|
|
#ifndef percpu_xor
|
|
# define percpu_xor(var, val) __percpu_generic_to_op(var, (val), ^=)
|
|
#endif
|
|
|
|
#endif /* __LINUX_PERCPU_H */
|