remarkable-linux/include/linux/kernel.h
Mel Gorman 3e7d344970 mm: vmscan: reclaim order-0 and use compaction instead of lumpy reclaim
Lumpy reclaim is disruptive.  It reclaims a large number of pages and
ignores the age of the pages it reclaims.  This can incur significant
stalls and potentially increase the number of major faults.

Compaction has reached the point where it is considered reasonably stable
(meaning it has passed a lot of testing) and is a potential candidate for
displacing lumpy reclaim.  This patch introduces an alternative to lumpy
reclaim whe compaction is available called reclaim/compaction.  The basic
operation is very simple - instead of selecting a contiguous range of
pages to reclaim, a number of order-0 pages are reclaimed and then
compaction is later by either kswapd (compact_zone_order()) or direct
compaction (__alloc_pages_direct_compact()).

[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: use conventional task_struct naming]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-13 17:32:33 -08:00

616 lines
19 KiB
C

#ifndef _LINUX_KERNEL_H
#define _LINUX_KERNEL_H
/*
* 'kernel.h' contains some often-used function prototypes etc
*/
#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
#ifdef __KERNEL__
#include <stdarg.h>
#include <linux/linkage.h>
#include <linux/stddef.h>
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/bitops.h>
#include <linux/log2.h>
#include <linux/typecheck.h>
#include <linux/printk.h>
#include <linux/dynamic_debug.h>
#include <asm/byteorder.h>
#include <asm/bug.h>
#define USHRT_MAX ((u16)(~0U))
#define SHRT_MAX ((s16)(USHRT_MAX>>1))
#define SHRT_MIN ((s16)(-SHRT_MAX - 1))
#define INT_MAX ((int)(~0U>>1))
#define INT_MIN (-INT_MAX - 1)
#define UINT_MAX (~0U)
#define LONG_MAX ((long)(~0UL>>1))
#define LONG_MIN (-LONG_MAX - 1)
#define ULONG_MAX (~0UL)
#define LLONG_MAX ((long long)(~0ULL>>1))
#define LLONG_MIN (-LLONG_MAX - 1)
#define ULLONG_MAX (~0ULL)
#define STACK_MAGIC 0xdeadbeef
#define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
#define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask))
#define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a)))
#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0)
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
/*
* This looks more complex than it should be. But we need to
* get the type for the ~ right in round_down (it needs to be
* as wide as the result!), and we want to evaluate the macro
* arguments just once each.
*/
#define __round_mask(x, y) ((__typeof__(x))((y)-1))
#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
#define round_down(x, y) ((x) & ~__round_mask(x, y))
#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
/* The `const' in roundup() prevents gcc-3.3 from calling __divdi3 */
#define roundup(x, y) ( \
{ \
const typeof(y) __y = y; \
(((x) + (__y - 1)) / __y) * __y; \
} \
)
#define rounddown(x, y) ( \
{ \
typeof(x) __x = (x); \
__x - (__x % (y)); \
} \
)
#define DIV_ROUND_CLOSEST(x, divisor)( \
{ \
typeof(divisor) __divisor = divisor; \
(((x) + ((__divisor) / 2)) / (__divisor)); \
} \
)
#define _RET_IP_ (unsigned long)__builtin_return_address(0)
#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
#ifdef CONFIG_LBDAF
# include <asm/div64.h>
# define sector_div(a, b) do_div(a, b)
#else
# define sector_div(n, b)( \
{ \
int _res; \
_res = (n) % (b); \
(n) /= (b); \
_res; \
} \
)
#endif
/**
* upper_32_bits - return bits 32-63 of a number
* @n: the number we're accessing
*
* A basic shift-right of a 64- or 32-bit quantity. Use this to suppress
* the "right shift count >= width of type" warning when that quantity is
* 32-bits.
*/
#define upper_32_bits(n) ((u32)(((n) >> 16) >> 16))
/**
* lower_32_bits - return bits 0-31 of a number
* @n: the number we're accessing
*/
#define lower_32_bits(n) ((u32)(n))
struct completion;
struct pt_regs;
struct user;
#ifdef CONFIG_PREEMPT_VOLUNTARY
extern int _cond_resched(void);
# define might_resched() _cond_resched()
#else
# define might_resched() do { } while (0)
#endif
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
void __might_sleep(const char *file, int line, int preempt_offset);
/**
* might_sleep - annotation for functions that can sleep
*
* this macro will print a stack trace if it is executed in an atomic
* context (spinlock, irq-handler, ...).
*
* This is a useful debugging help to be able to catch problems early and not
* be bitten later when the calling function happens to sleep when it is not
* supposed to.
*/
# define might_sleep() \
do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
#else
static inline void __might_sleep(const char *file, int line,
int preempt_offset) { }
# define might_sleep() do { might_resched(); } while (0)
#endif
#define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
/*
* abs() handles unsigned and signed longs, ints, shorts and chars. For all
* input types abs() returns a signed long.
* abs() should not be used for 64-bit types (s64, u64, long long) - use abs64()
* for those.
*/
#define abs(x) ({ \
long ret; \
if (sizeof(x) == sizeof(long)) { \
long __x = (x); \
ret = (__x < 0) ? -__x : __x; \
} else { \
int __x = (x); \
ret = (__x < 0) ? -__x : __x; \
} \
ret; \
})
#define abs64(x) ({ \
s64 __x = (x); \
(__x < 0) ? -__x : __x; \
})
#ifdef CONFIG_PROVE_LOCKING
void might_fault(void);
#else
static inline void might_fault(void)
{
might_sleep();
}
#endif
extern struct atomic_notifier_head panic_notifier_list;
extern long (*panic_blink)(int state);
NORET_TYPE void panic(const char * fmt, ...)
__attribute__ ((NORET_AND format (printf, 1, 2))) __cold;
extern void oops_enter(void);
extern void oops_exit(void);
void print_oops_end_marker(void);
extern int oops_may_print(void);
NORET_TYPE void do_exit(long error_code)
ATTRIB_NORET;
NORET_TYPE void complete_and_exit(struct completion *, long)
ATTRIB_NORET;
extern unsigned long simple_strtoul(const char *,char **,unsigned int);
extern long simple_strtol(const char *,char **,unsigned int);
extern unsigned long long simple_strtoull(const char *,char **,unsigned int);
extern long long simple_strtoll(const char *,char **,unsigned int);
extern int __must_check strict_strtoul(const char *, unsigned int, unsigned long *);
extern int __must_check strict_strtol(const char *, unsigned int, long *);
extern int __must_check strict_strtoull(const char *, unsigned int, unsigned long long *);
extern int __must_check strict_strtoll(const char *, unsigned int, long long *);
extern int sprintf(char * buf, const char * fmt, ...)
__attribute__ ((format (printf, 2, 3)));
extern int vsprintf(char *buf, const char *, va_list)
__attribute__ ((format (printf, 2, 0)));
extern int snprintf(char * buf, size_t size, const char * fmt, ...)
__attribute__ ((format (printf, 3, 4)));
extern int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
__attribute__ ((format (printf, 3, 0)));
extern int scnprintf(char * buf, size_t size, const char * fmt, ...)
__attribute__ ((format (printf, 3, 4)));
extern int vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
__attribute__ ((format (printf, 3, 0)));
extern char *kasprintf(gfp_t gfp, const char *fmt, ...)
__attribute__ ((format (printf, 2, 3)));
extern char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
extern int sscanf(const char *, const char *, ...)
__attribute__ ((format (scanf, 2, 3)));
extern int vsscanf(const char *, const char *, va_list)
__attribute__ ((format (scanf, 2, 0)));
extern int get_option(char **str, int *pint);
extern char *get_options(const char *str, int nints, int *ints);
extern unsigned long long memparse(const char *ptr, char **retptr);
extern int core_kernel_text(unsigned long addr);
extern int __kernel_text_address(unsigned long addr);
extern int kernel_text_address(unsigned long addr);
extern int func_ptr_is_kernel_text(void *ptr);
struct pid;
extern struct pid *session_of_pgrp(struct pid *pgrp);
unsigned long int_sqrt(unsigned long);
extern void bust_spinlocks(int yes);
extern void wake_up_klogd(void);
extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */
extern int panic_timeout;
extern int panic_on_oops;
extern int panic_on_unrecovered_nmi;
extern int panic_on_io_nmi;
extern const char *print_tainted(void);
extern void add_taint(unsigned flag);
extern int test_taint(unsigned flag);
extern unsigned long get_taint(void);
extern int root_mountflags;
/* Values used for system_state */
extern enum system_states {
SYSTEM_BOOTING,
SYSTEM_RUNNING,
SYSTEM_HALT,
SYSTEM_POWER_OFF,
SYSTEM_RESTART,
SYSTEM_SUSPEND_DISK,
} system_state;
#define TAINT_PROPRIETARY_MODULE 0
#define TAINT_FORCED_MODULE 1
#define TAINT_UNSAFE_SMP 2
#define TAINT_FORCED_RMMOD 3
#define TAINT_MACHINE_CHECK 4
#define TAINT_BAD_PAGE 5
#define TAINT_USER 6
#define TAINT_DIE 7
#define TAINT_OVERRIDDEN_ACPI_TABLE 8
#define TAINT_WARN 9
#define TAINT_CRAP 10
#define TAINT_FIRMWARE_WORKAROUND 11
extern const char hex_asc[];
#define hex_asc_lo(x) hex_asc[((x) & 0x0f)]
#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4]
static inline char *pack_hex_byte(char *buf, u8 byte)
{
*buf++ = hex_asc_hi(byte);
*buf++ = hex_asc_lo(byte);
return buf;
}
extern int hex_to_bin(char ch);
extern void hex2bin(u8 *dst, const char *src, size_t count);
/*
* General tracing related utility functions - trace_printk(),
* tracing_on/tracing_off and tracing_start()/tracing_stop
*
* Use tracing_on/tracing_off when you want to quickly turn on or off
* tracing. It simply enables or disables the recording of the trace events.
* This also corresponds to the user space /sys/kernel/debug/tracing/tracing_on
* file, which gives a means for the kernel and userspace to interact.
* Place a tracing_off() in the kernel where you want tracing to end.
* From user space, examine the trace, and then echo 1 > tracing_on
* to continue tracing.
*
* tracing_stop/tracing_start has slightly more overhead. It is used
* by things like suspend to ram where disabling the recording of the
* trace is not enough, but tracing must actually stop because things
* like calling smp_processor_id() may crash the system.
*
* Most likely, you want to use tracing_on/tracing_off.
*/
#ifdef CONFIG_RING_BUFFER
void tracing_on(void);
void tracing_off(void);
/* trace_off_permanent stops recording with no way to bring it back */
void tracing_off_permanent(void);
int tracing_is_on(void);
#else
static inline void tracing_on(void) { }
static inline void tracing_off(void) { }
static inline void tracing_off_permanent(void) { }
static inline int tracing_is_on(void) { return 0; }
#endif
enum ftrace_dump_mode {
DUMP_NONE,
DUMP_ALL,
DUMP_ORIG,
};
#ifdef CONFIG_TRACING
extern void tracing_start(void);
extern void tracing_stop(void);
extern void ftrace_off_permanent(void);
static inline void __attribute__ ((format (printf, 1, 2)))
____trace_printk_check_format(const char *fmt, ...)
{
}
#define __trace_printk_check_format(fmt, args...) \
do { \
if (0) \
____trace_printk_check_format(fmt, ##args); \
} while (0)
/**
* trace_printk - printf formatting in the ftrace buffer
* @fmt: the printf format for printing
*
* Note: __trace_printk is an internal function for trace_printk and
* the @ip is passed in via the trace_printk macro.
*
* This function allows a kernel developer to debug fast path sections
* that printk is not appropriate for. By scattering in various
* printk like tracing in the code, a developer can quickly see
* where problems are occurring.
*
* This is intended as a debugging tool for the developer only.
* Please refrain from leaving trace_printks scattered around in
* your code.
*/
#define trace_printk(fmt, args...) \
do { \
__trace_printk_check_format(fmt, ##args); \
if (__builtin_constant_p(fmt)) { \
static const char *trace_printk_fmt \
__attribute__((section("__trace_printk_fmt"))) = \
__builtin_constant_p(fmt) ? fmt : NULL; \
\
__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \
} else \
__trace_printk(_THIS_IP_, fmt, ##args); \
} while (0)
extern int
__trace_bprintk(unsigned long ip, const char *fmt, ...)
__attribute__ ((format (printf, 2, 3)));
extern int
__trace_printk(unsigned long ip, const char *fmt, ...)
__attribute__ ((format (printf, 2, 3)));
extern void trace_dump_stack(void);
/*
* The double __builtin_constant_p is because gcc will give us an error
* if we try to allocate the static variable to fmt if it is not a
* constant. Even with the outer if statement.
*/
#define ftrace_vprintk(fmt, vargs) \
do { \
if (__builtin_constant_p(fmt)) { \
static const char *trace_printk_fmt \
__attribute__((section("__trace_printk_fmt"))) = \
__builtin_constant_p(fmt) ? fmt : NULL; \
\
__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \
} else \
__ftrace_vprintk(_THIS_IP_, fmt, vargs); \
} while (0)
extern int
__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
extern int
__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
#else
static inline int
trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
static inline void tracing_start(void) { }
static inline void tracing_stop(void) { }
static inline void ftrace_off_permanent(void) { }
static inline void trace_dump_stack(void) { }
static inline int
trace_printk(const char *fmt, ...)
{
return 0;
}
static inline int
ftrace_vprintk(const char *fmt, va_list ap)
{
return 0;
}
static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
#endif /* CONFIG_TRACING */
/*
* min()/max()/clamp() macros that also do
* strict type-checking.. See the
* "unnecessary" pointer comparison.
*/
#define min(x, y) ({ \
typeof(x) _min1 = (x); \
typeof(y) _min2 = (y); \
(void) (&_min1 == &_min2); \
_min1 < _min2 ? _min1 : _min2; })
#define max(x, y) ({ \
typeof(x) _max1 = (x); \
typeof(y) _max2 = (y); \
(void) (&_max1 == &_max2); \
_max1 > _max2 ? _max1 : _max2; })
#define min3(x, y, z) ({ \
typeof(x) _min1 = (x); \
typeof(y) _min2 = (y); \
typeof(z) _min3 = (z); \
(void) (&_min1 == &_min2); \
(void) (&_min1 == &_min3); \
_min1 < _min2 ? (_min1 < _min3 ? _min1 : _min3) : \
(_min2 < _min3 ? _min2 : _min3); })
#define max3(x, y, z) ({ \
typeof(x) _max1 = (x); \
typeof(y) _max2 = (y); \
typeof(z) _max3 = (z); \
(void) (&_max1 == &_max2); \
(void) (&_max1 == &_max3); \
_max1 > _max2 ? (_max1 > _max3 ? _max1 : _max3) : \
(_max2 > _max3 ? _max2 : _max3); })
/**
* min_not_zero - return the minimum that is _not_ zero, unless both are zero
* @x: value1
* @y: value2
*/
#define min_not_zero(x, y) ({ \
typeof(x) __x = (x); \
typeof(y) __y = (y); \
__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
/**
* clamp - return a value clamped to a given range with strict typechecking
* @val: current value
* @min: minimum allowable value
* @max: maximum allowable value
*
* This macro does strict typechecking of min/max to make sure they are of the
* same type as val. See the unnecessary pointer comparisons.
*/
#define clamp(val, min, max) ({ \
typeof(val) __val = (val); \
typeof(min) __min = (min); \
typeof(max) __max = (max); \
(void) (&__val == &__min); \
(void) (&__val == &__max); \
__val = __val < __min ? __min: __val; \
__val > __max ? __max: __val; })
/*
* ..and if you can't take the strict
* types, you can specify one yourself.
*
* Or not use min/max/clamp at all, of course.
*/
#define min_t(type, x, y) ({ \
type __min1 = (x); \
type __min2 = (y); \
__min1 < __min2 ? __min1: __min2; })
#define max_t(type, x, y) ({ \
type __max1 = (x); \
type __max2 = (y); \
__max1 > __max2 ? __max1: __max2; })
/**
* clamp_t - return a value clamped to a given range using a given type
* @type: the type of variable to use
* @val: current value
* @min: minimum allowable value
* @max: maximum allowable value
*
* This macro does no typechecking and uses temporary variables of type
* 'type' to make all the comparisons.
*/
#define clamp_t(type, val, min, max) ({ \
type __val = (val); \
type __min = (min); \
type __max = (max); \
__val = __val < __min ? __min: __val; \
__val > __max ? __max: __val; })
/**
* clamp_val - return a value clamped to a given range using val's type
* @val: current value
* @min: minimum allowable value
* @max: maximum allowable value
*
* This macro does no typechecking and uses temporary variables of whatever
* type the input argument 'val' is. This is useful when val is an unsigned
* type and min and max are literals that will otherwise be assigned a signed
* integer type.
*/
#define clamp_val(val, min, max) ({ \
typeof(val) __val = (val); \
typeof(val) __min = (min); \
typeof(val) __max = (max); \
__val = __val < __min ? __min: __val; \
__val > __max ? __max: __val; })
/*
* swap - swap value of @a and @b
*/
#define swap(a, b) \
do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
/**
* container_of - cast a member of a structure out to the containing structure
* @ptr: the pointer to the member.
* @type: the type of the container struct this is embedded in.
* @member: the name of the member within the struct.
*
*/
#define container_of(ptr, type, member) ({ \
const typeof( ((type *)0)->member ) *__mptr = (ptr); \
(type *)( (char *)__mptr - offsetof(type,member) );})
struct sysinfo;
extern int do_sysinfo(struct sysinfo *info);
#endif /* __KERNEL__ */
#define SI_LOAD_SHIFT 16
struct sysinfo {
long uptime; /* Seconds since boot */
unsigned long loads[3]; /* 1, 5, and 15 minute load averages */
unsigned long totalram; /* Total usable main memory size */
unsigned long freeram; /* Available memory size */
unsigned long sharedram; /* Amount of shared memory */
unsigned long bufferram; /* Memory used by buffers */
unsigned long totalswap; /* Total swap space size */
unsigned long freeswap; /* swap space still available */
unsigned short procs; /* Number of current processes */
unsigned short pad; /* explicit padding for m68k */
unsigned long totalhigh; /* Total high memory size */
unsigned long freehigh; /* Available high memory size */
unsigned int mem_unit; /* Memory unit size in bytes */
char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */
};
/* Force a compilation error if condition is true */
#define BUILD_BUG_ON(condition) ((void)BUILD_BUG_ON_ZERO(condition))
/* Force a compilation error if condition is constant and true */
#define MAYBE_BUILD_BUG_ON(cond) ((void)sizeof(char[1 - 2 * !!(cond)]))
/* Force a compilation error if a constant expression is not a power of 2 */
#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \
BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
/* Force a compilation error if condition is true, but also produce a
result (of value 0 and type size_t), so the expression can be used
e.g. in a structure initializer (or where-ever else comma expressions
aren't permitted). */
#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))
/* Trap pasters of __FUNCTION__ at compile-time */
#define __FUNCTION__ (__func__)
/* This helps us to avoid #ifdef CONFIG_NUMA */
#ifdef CONFIG_NUMA
#define NUMA_BUILD 1
#else
#define NUMA_BUILD 0
#endif
/* This helps us avoid #ifdef CONFIG_COMPACTION */
#ifdef CONFIG_COMPACTION
#define COMPACTION_BUILD 1
#else
#define COMPACTION_BUILD 0
#endif
/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
#endif
#endif