linux/include/linux/percpu.h

223 lines
6.1 KiB
C
Raw Normal View History

#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>
/* 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
/* 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;
extern const unsigned long *pcpu_unit_offsets;
percpu: introduce pcpu_alloc_info and pcpu_group_info Till now, non-linear cpu->unit map was expressed using an integer array which maps each cpu to a unit and used only by lpage allocator. Although how many units have been placed in a single contiguos area (group) is known while building unit_map, the information is lost when the result is recorded into the unit_map array. For lpage allocator, as all allocations are done by lpages and whether two adjacent lpages are in the same group or not is irrelevant, this didn't cause any problem. Non-linear cpu->unit mapping will be used for sparse embedding and this grouping information is necessary for that. This patch introduces pcpu_alloc_info which contains all the information necessary for initializing percpu allocator. pcpu_alloc_info contains array of pcpu_group_info which describes how units are grouped and mapped to cpus. pcpu_group_info also has base_offset field to specify its offset from the chunk's base address. pcpu_build_alloc_info() initializes this field as if all groups are allocated back-to-back as is currently done but this will be used to sparsely place groups. pcpu_alloc_info is a rather complex data structure which contains a flexible array which in turn points to nested cpu_map arrays. * pcpu_alloc_alloc_info() and pcpu_free_alloc_info() are provided to help dealing with pcpu_alloc_info. * pcpu_lpage_build_unit_map() is updated to build pcpu_alloc_info, generalized and renamed to pcpu_build_alloc_info(). @cpu_distance_fn may be NULL indicating that all cpus are of LOCAL_DISTANCE. * pcpul_lpage_dump_cfg() is updated to process pcpu_alloc_info, generalized and renamed to pcpu_dump_alloc_info(). It now also prints which group each alloc unit belongs to. * pcpu_setup_first_chunk() now takes pcpu_alloc_info instead of the separate parameters. All first chunk allocators are updated to use pcpu_build_alloc_info() to build alloc_info and call pcpu_setup_first_chunk() with it. This has the side effect of packing units for sparse possible cpus. ie. if cpus 0, 2 and 4 are possible, they'll be assigned unit 0, 1 and 2 instead of 0, 2 and 4. * x86 setup_pcpu_lpage() is updated to deal with alloc_info. * sparc64 setup_per_cpu_areas() is updated to build alloc_info. Although the changes made by this patch are pretty pervasive, it doesn't cause any behavior difference other than packing of sparse cpus. It mostly changes how information is passed among initialization functions and makes room for more flexibility. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: David Miller <davem@davemloft.net>
2009-08-14 08:00:51 +02:00
struct pcpu_group_info {
int nr_units; /* aligned # of units */
unsigned long base_offset; /* base address offset */
unsigned int *cpu_map; /* unit->cpu map, empty
* entries contain NR_CPUS */
};
struct pcpu_alloc_info {
size_t static_size;
size_t reserved_size;
size_t dyn_size;
size_t unit_size;
size_t atom_size;
size_t alloc_size;
size_t __ai_size; /* internal, don't use */
int nr_groups; /* 0 if grouping unnecessary */
struct pcpu_group_info groups[];
};
enum pcpu_fc {
PCPU_FC_AUTO,
PCPU_FC_EMBED,
PCPU_FC_PAGE,
PCPU_FC_NR,
};
extern const char *pcpu_fc_names[PCPU_FC_NR];
extern enum pcpu_fc pcpu_chosen_fc;
typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size,
size_t align);
typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size);
typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr);
typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to);
percpu: introduce pcpu_alloc_info and pcpu_group_info Till now, non-linear cpu->unit map was expressed using an integer array which maps each cpu to a unit and used only by lpage allocator. Although how many units have been placed in a single contiguos area (group) is known while building unit_map, the information is lost when the result is recorded into the unit_map array. For lpage allocator, as all allocations are done by lpages and whether two adjacent lpages are in the same group or not is irrelevant, this didn't cause any problem. Non-linear cpu->unit mapping will be used for sparse embedding and this grouping information is necessary for that. This patch introduces pcpu_alloc_info which contains all the information necessary for initializing percpu allocator. pcpu_alloc_info contains array of pcpu_group_info which describes how units are grouped and mapped to cpus. pcpu_group_info also has base_offset field to specify its offset from the chunk's base address. pcpu_build_alloc_info() initializes this field as if all groups are allocated back-to-back as is currently done but this will be used to sparsely place groups. pcpu_alloc_info is a rather complex data structure which contains a flexible array which in turn points to nested cpu_map arrays. * pcpu_alloc_alloc_info() and pcpu_free_alloc_info() are provided to help dealing with pcpu_alloc_info. * pcpu_lpage_build_unit_map() is updated to build pcpu_alloc_info, generalized and renamed to pcpu_build_alloc_info(). @cpu_distance_fn may be NULL indicating that all cpus are of LOCAL_DISTANCE. * pcpul_lpage_dump_cfg() is updated to process pcpu_alloc_info, generalized and renamed to pcpu_dump_alloc_info(). It now also prints which group each alloc unit belongs to. * pcpu_setup_first_chunk() now takes pcpu_alloc_info instead of the separate parameters. All first chunk allocators are updated to use pcpu_build_alloc_info() to build alloc_info and call pcpu_setup_first_chunk() with it. This has the side effect of packing units for sparse possible cpus. ie. if cpus 0, 2 and 4 are possible, they'll be assigned unit 0, 1 and 2 instead of 0, 2 and 4. * x86 setup_pcpu_lpage() is updated to deal with alloc_info. * sparc64 setup_per_cpu_areas() is updated to build alloc_info. Although the changes made by this patch are pretty pervasive, it doesn't cause any behavior difference other than packing of sparse cpus. It mostly changes how information is passed among initialization functions and makes room for more flexibility. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: David Miller <davem@davemloft.net>
2009-08-14 08:00:51 +02:00
extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
int nr_units);
extern void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai);
extern struct pcpu_alloc_info * __init pcpu_build_alloc_info(
size_t reserved_size, ssize_t dyn_size,
size_t atom_size,
pcpu_fc_cpu_distance_fn_t cpu_distance_fn);
extern int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
void *base_addr);
#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
extern int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
size_t atom_size,
pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
pcpu_fc_alloc_fn_t alloc_fn,
pcpu_fc_free_fn_t free_fn);
#endif
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
extern int __init pcpu_page_first_chunk(size_t reserved_size,
pcpu_fc_alloc_fn_t alloc_fn,
pcpu_fc_free_fn_t free_fn,
pcpu_fc_populate_pte_fn_t populate_pte_fn);
#endif
/*
* 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);
extern void *__alloc_percpu(size_t size, size_t align);
extern void free_percpu(void *__pdata);
percpu: use dynamic percpu allocator as the default percpu allocator This patch makes most !CONFIG_HAVE_SETUP_PER_CPU_AREA archs use dynamic percpu allocator. The first chunk is allocated using embedding helper and 8k is reserved for modules. This ensures that the new allocator behaves almost identically to the original allocator as long as static percpu variables are concerned, so it shouldn't introduce much breakage. s390 and alpha use custom SHIFT_PERCPU_PTR() to work around addressing range limit the addressing model imposes. Unfortunately, this breaks if the address is specified using a variable, so for now, the two archs aren't converted. The following architectures are affected by this change. * sh * arm * cris * mips * sparc(32) * blackfin * avr32 * parisc (broken, under investigation) * m32r * powerpc(32) As this change makes the dynamic allocator the default one, CONFIG_HAVE_DYNAMIC_PER_CPU_AREA is replaced with its invert - CONFIG_HAVE_LEGACY_PER_CPU_AREA, which is added to yet-to-be converted archs. These archs implement their own setup_per_cpu_areas() and the conversion is not trivial. * powerpc(64) * sparc(64) * ia64 * alpha * s390 Boot and batch alloc/free tests on x86_32 with debug code (x86_32 doesn't use default first chunk initialization). Compile tested on sparc(32), powerpc(32), arm and alpha. Kyle McMartin reported that this change breaks parisc. The problem is still under investigation and he is okay with pushing this patch forward and fixing parisc later. [ Impact: use dynamic allocator for most archs w/o custom percpu setup ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Reviewed-by: Christoph Lameter <cl@linux.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Mikael Starvik <starvik@axis.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Bryan Wu <cooloney@kernel.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Grant Grundler <grundler@parisc-linux.org> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu>
2009-03-30 12:07:44 +02:00
#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
extern void __init setup_per_cpu_areas(void);
#endif
#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);
}
percpu: use dynamic percpu allocator as the default percpu allocator This patch makes most !CONFIG_HAVE_SETUP_PER_CPU_AREA archs use dynamic percpu allocator. The first chunk is allocated using embedding helper and 8k is reserved for modules. This ensures that the new allocator behaves almost identically to the original allocator as long as static percpu variables are concerned, so it shouldn't introduce much breakage. s390 and alpha use custom SHIFT_PERCPU_PTR() to work around addressing range limit the addressing model imposes. Unfortunately, this breaks if the address is specified using a variable, so for now, the two archs aren't converted. The following architectures are affected by this change. * sh * arm * cris * mips * sparc(32) * blackfin * avr32 * parisc (broken, under investigation) * m32r * powerpc(32) As this change makes the dynamic allocator the default one, CONFIG_HAVE_DYNAMIC_PER_CPU_AREA is replaced with its invert - CONFIG_HAVE_LEGACY_PER_CPU_AREA, which is added to yet-to-be converted archs. These archs implement their own setup_per_cpu_areas() and the conversion is not trivial. * powerpc(64) * sparc(64) * ia64 * alpha * s390 Boot and batch alloc/free tests on x86_32 with debug code (x86_32 doesn't use default first chunk initialization). Compile tested on sparc(32), powerpc(32), arm and alpha. Kyle McMartin reported that this change breaks parisc. The problem is still under investigation and he is okay with pushing this patch forward and fixing parisc later. [ Impact: use dynamic allocator for most archs w/o custom percpu setup ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Reviewed-by: Christoph Lameter <cl@linux.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Mikael Starvik <starvik@axis.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Bryan Wu <cooloney@kernel.org> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Grant Grundler <grundler@parisc-linux.org> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ingo Molnar <mingo@elte.hu>
2009-03-30 12:07:44 +02:00
static inline void __init setup_per_cpu_areas(void) { }
static inline void *pcpu_lpage_remapped(void *kaddr)
{
return NULL;
}
#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 */