OpenCloudOS-Kernel/include/linux/kernel.h

618 lines
19 KiB
C
Raw Normal View History

#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)
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:26 +08:00
#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)
include/linux/kernel.h: abs(): fix handling of 32-bit unsigneds on 64-bit Michal reports: In the framebuffer subsystem the abs() macro is often used as a part of the calculation of a Manhattan metric, which in turn is used as a measure of similarity between video modes. The arguments of abs() are sometimes unsigned numbers. This worked fine until commit a49c59c0 ("Make sure the value in abs() does not get truncated if it is greater than 2^32:) , which changed the definition of abs() to prevent truncation. As a result of this change, in the following piece of code: u32 a = 0, b = 1; u32 c = abs(a - b); 'c' will end up with a value of 0xffffffff instead of the expected 0x1. A problem caused by this change and visible by the end user is that framebuffer drivers relying on functions from modedb.c will fail to find high resolution video modes similar to that explicitly requested by the user if an exact match cannot be found (see e.g. Fix this by special-casing `long' types within abs(). This patch reduces x86_64 code size a bit - drivers/video/uvesafb.o shrunk by 15 bytes, presumably because it is doing abs() on 4-byte quantities, and expanding those to 8-byte longs adds code. testcase: #define oldabs(x) ({ \ long __x = (x); \ (__x < 0) ? -__x : __x; \ }) #define newabs(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; \ }) typedef unsigned int u32; main() { u32 a = 0; u32 b = 1; u32 oldc = oldabs(a - b); u32 newc = newabs(a - b); printf("%u %u\n", oldc, newc); } akpm:/home/akpm> gcc t.c akpm:/home/akpm> ./a.out 4294967295 1 Reported-by: Michal Januszewski <michalj@gmail.com> Cc: Rolf Eike Beer <eike-kernel@sf-tec.de Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-13 08:59:35 +08:00
/*
* 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
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
extern struct atomic_notifier_head panic_notifier_list;
extern long (*panic_blink)(int state);
NORET_TYPE void panic(const char * fmt, ...)
x86: Support __attribute__((__cold__)) in gcc 4.3 gcc 4.3 supports a new __attribute__((__cold__)) to mark functions cold. Any path directly leading to a call of this function will be unlikely. And gcc will try to generate smaller code for the function itself. Please use with care. The code generation advantage isn't large and in most cases it is not worth uglifying code with this. This patch marks some common error functions like panic(), printk() as cold. This will longer term make many unlikely()s unnecessary, although we can keep them for now for older compilers. BUG is not marked cold because there is currently no way to tell gcc to mark a inline function told. Also all __init and __exit functions are marked cold. With a non -Os build this will tell the compiler to generate slightly smaller code for them. I think it currently only uses less alignments for labels, but that might change in the future. One disadvantage over *likely() is that they cannot be easily instrumented to verify them. Another drawback is that only the latest gcc 4.3 snapshots support this. Unfortunately we cannot detect this using the preprocessor. This means older snapshots will fail now. I don't think that's a problem because they are unreleased compilers that nobody should be using. gcc also has a __hot__ attribute, but I don't see any sense in using this in the kernel right now. But someday I hope gcc will be able to use more aggressive optimizing for hot functions even in -Os, if that happens it should be added. Includes compile fix from Thomas Gleixner. Cc: Jan Hubicka <jh@suse.cz> Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-21 23:10:00 +08:00
__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;
extern bool early_boot_irqs_disabled;
/* 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: add tracing_on/tracing_off to kernel.h Impact: cleanup The functions tracing_start/tracing_stop have been moved to kernel.h. These are not the functions a developer most likely wants to use when they want to insert a place to stop tracing and restart it from user space. tracing_start/tracing_stop was created to work with things like suspend to ram, where even calling smp_processor_id() can crash the system. The tracing_start/tracing_stop was used to stop the tracer from doing anything. These are still light weight functions, but add a bit more overhead to be able to stop the tracers. They also have no interface back to userland. That is, if the kernel calls tracing_stop, userland can not start tracing. What a developer most likely wants to use is tracing_on/tracing_off. These are very light weight functions (simply sets or clears a bit). These functions just stop recording into the ring buffer. The tracers don't even know that this happens except that they would receive NULL from the ring_buffer_lock_reserve function. Also, there's a way for the user land to enable or disable this bit. In debugfs/tracing/tracing_on, a user may echo "0" (same as tracing_off()) or echo "1" (same as tracing_on()) into this file. This becomes handy when a kernel developer is debugging and wants tracing to turn off when it hits an anomaly. Then the developer can examine the trace, and restart tracing if they want to try again (echo 1 > tracing_on). This patch moves the prototypes for tracing_on/tracing_off to kernel.h and comments their use, so that a kernel developer will know how to use them. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-03-05 23:35:56 +08:00
* 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
tracing: add tracing_on/tracing_off to kernel.h Impact: cleanup The functions tracing_start/tracing_stop have been moved to kernel.h. These are not the functions a developer most likely wants to use when they want to insert a place to stop tracing and restart it from user space. tracing_start/tracing_stop was created to work with things like suspend to ram, where even calling smp_processor_id() can crash the system. The tracing_start/tracing_stop was used to stop the tracer from doing anything. These are still light weight functions, but add a bit more overhead to be able to stop the tracers. They also have no interface back to userland. That is, if the kernel calls tracing_stop, userland can not start tracing. What a developer most likely wants to use is tracing_on/tracing_off. These are very light weight functions (simply sets or clears a bit). These functions just stop recording into the ring buffer. The tracers don't even know that this happens except that they would receive NULL from the ring_buffer_lock_reserve function. Also, there's a way for the user land to enable or disable this bit. In debugfs/tracing/tracing_on, a user may echo "0" (same as tracing_off()) or echo "1" (same as tracing_on()) into this file. This becomes handy when a kernel developer is debugging and wants tracing to turn off when it hits an anomaly. Then the developer can examine the trace, and restart tracing if they want to try again (echo 1 > tracing_on). This patch moves the prototypes for tracing_on/tracing_off to kernel.h and comments their use, so that a kernel developer will know how to use them. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-03-05 23:35:56 +08:00
* 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.
*/
tracing: add tracing_on/tracing_off to kernel.h Impact: cleanup The functions tracing_start/tracing_stop have been moved to kernel.h. These are not the functions a developer most likely wants to use when they want to insert a place to stop tracing and restart it from user space. tracing_start/tracing_stop was created to work with things like suspend to ram, where even calling smp_processor_id() can crash the system. The tracing_start/tracing_stop was used to stop the tracer from doing anything. These are still light weight functions, but add a bit more overhead to be able to stop the tracers. They also have no interface back to userland. That is, if the kernel calls tracing_stop, userland can not start tracing. What a developer most likely wants to use is tracing_on/tracing_off. These are very light weight functions (simply sets or clears a bit). These functions just stop recording into the ring buffer. The tracers don't even know that this happens except that they would receive NULL from the ring_buffer_lock_reserve function. Also, there's a way for the user land to enable or disable this bit. In debugfs/tracing/tracing_on, a user may echo "0" (same as tracing_off()) or echo "1" (same as tracing_on()) into this file. This becomes handy when a kernel developer is debugging and wants tracing to turn off when it hits an anomaly. Then the developer can examine the trace, and restart tracing if they want to try again (echo 1 > tracing_on). This patch moves the prototypes for tracing_on/tracing_off to kernel.h and comments their use, so that a kernel developer will know how to use them. Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-03-05 23:35:56 +08:00
#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);
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
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.
*/
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
#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); \
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
} 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)));
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
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.
*/
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
#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); \
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
} 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);
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
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) { }
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
#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