kernel-ark/include/linux/kernel.h

534 lines
16 KiB
C
Raw Normal View History

#ifndef _LINUX_KERNEL_H
#define _LINUX_KERNEL_H
/*
* 'kernel.h' contains some often-used function prototypes etc
*/
#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/ratelimit.h>
#include <linux/dynamic_debug.h>
#include <asm/byteorder.h>
#include <asm/bug.h>
extern const char linux_banner[];
extern const char linux_proc_banner[];
#define USHORT_MAX ((u16)(~0U))
#define SHORT_MAX ((s16)(USHORT_MAX>>1))
#define SHORT_MIN (-SHORT_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 09:03:26 +00:00
#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_MASK(x,(typeof(x))(a)-1)
#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(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))
#define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
#define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (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_LBD
# 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))
#define KERN_EMERG "<0>" /* system is unusable */
#define KERN_ALERT "<1>" /* action must be taken immediately */
#define KERN_CRIT "<2>" /* critical conditions */
#define KERN_ERR "<3>" /* error conditions */
#define KERN_WARNING "<4>" /* warning conditions */
#define KERN_NOTICE "<5>" /* normal but significant condition */
#define KERN_INFO "<6>" /* informational */
#define KERN_DEBUG "<7>" /* debug-level messages */
/*
* Annotation for a "continued" line of log printout (only done after a
* line that had no enclosing \n). Only to be used by core/arch code
* during early bootup (a continued line is not SMP-safe otherwise).
*/
#define KERN_CONT ""
extern int console_printk[];
#define console_loglevel (console_printk[0])
#define default_message_loglevel (console_printk[1])
#define minimum_console_loglevel (console_printk[2])
#define default_console_loglevel (console_printk[3])
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(char *file, int line);
/**
* 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__); might_resched(); } while (0)
#else
# define might_sleep() do { might_resched(); } while (0)
#endif
#define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
#define abs(x) ({ \
int __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 09:16:30 +00:00
extern struct atomic_notifier_head panic_notifier_list;
extern long (*panic_blink)(long time);
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 15:10:00 +00:00
__attribute__ ((NORET_AND format (printf, 1, 2))) __cold;
extern void oops_enter(void);
extern void oops_exit(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);
Add new string functions strict_strto* and convert kernel params to use them Currently, for every sysfs node, the callers will be responsible for implementing store operation, so many many callers are doing duplicate things to validate input, they have the same mistakes because they are calling simple_strtol/ul/ll/uul, especially for module params, they are just numeric, but you can echo such values as 0x1234xxx, 07777888 and 1234aaa, for these cases, module params store operation just ignores succesive invalid char and converts prefix part to a numeric although input is acctually invalid. This patch tries to fix the aforementioned issues and implements strict_strtox serial functions, kernel/params.c uses them to strictly validate input, so module params will reject such values as 0x1234xxxx and returns an error: write error: Invalid argument Any modules which export numeric sysfs node can use strict_strtox instead of simple_strtox to reject any invalid input. Here are some test results: Before applying this patch: [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000g > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000gggggggg > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 010000 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0100008 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 010000aaaaa > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# After applying this patch: [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000g > /sys/module/e1000/parameters/copybreak -bash: echo: write error: Invalid argument [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000gggggggg > /sys/module/e1000/parameters/copybreak -bash: echo: write error: Invalid argument [root@yangyi-dev /]# echo 010000 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# echo 0100008 > /sys/module/e1000/parameters/copybreak -bash: echo: write error: Invalid argument [root@yangyi-dev /]# echo 010000aaaaa > /sys/module/e1000/parameters/copybreak -bash: echo: write error: Invalid argument [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo -n 4096 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# [akpm@linux-foundation.org: fix compiler warnings] [akpm@linux-foundation.org: fix off-by-one found by tiwai@suse.de] Signed-off-by: Yi Yang <yi.y.yang@intel.com> Cc: Greg KH <greg@kroah.com> Cc: "Randy.Dunlap" <rdunlap@xenotime.net> Cc: Takashi Iwai <tiwai@suse.de> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:57 +00:00
extern int strict_strtoul(const char *, unsigned int, unsigned long *);
extern int strict_strtol(const char *, unsigned int, long *);
extern int strict_strtoull(const char *, unsigned int, unsigned long long *);
extern int 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);
Introduce FW_BUG, FW_WARN and FW_INFO to consistenly tell users about BIOS bugs The idea is to add this to printk after the severity: printk(KERN_ERR FW_BUG "This is not our fault, BIOS developer: fix it by simply add ...\n"); If a Firmware issue should be hidden, because it is work-arounded, but you still want to see something popping up e.g. for info only: printk(KERN_INFO FW_INFO "This is done stupid, we can handle it, but it should better be avoided in future\n"); or on the Linuxfirmwarekit to tell vendors that they did something stupid or wrong without bothering the user: printk(KERN_INFO FW_BUG "This is done stupid, we can handle it, but it should better be avoided in future\n"); Some use cases: - If a user sees a [Firmware Bug] message in the kernel he should first update the BIOS before wasting time with debugging and submiting on old firmware code to mailing lists. - The linuxfirmwarekit (http://www.linuxfirmwarekit.org) tries to detect firmware bugs. It currently is doing that in userspace which results in: - Huge test scripts that could be a one liner in the kernel - A lot of BIOS bugs are already absorbed by the kernel What do we need such a stupid linuxfirmwarekit for? - Vendors: Can test their BIOSes for Linux compatibility. There will be the time when vendors realize that the test utils on Linux are more strict and using them increases the qualitity and stability of their products. - Vendors: Can easily fix up their BIOSes and be more Linux compatible by: dmesg |grep "Firmware Bug" and send the result to their BIOS developer colleagues who should know what the messages are about and how to fix them, without the need of studying kernel code. - Distributions: can do a first automated HW/BIOS checks. This can then be done without the need of asking kernel developers who need to dig down the code and explain the details. Certification can/will just be rejected until dmesg |grep "Firmware Bug" is empty. - Thus this can be used as an instrument to enforce cleaner BIOS code. Currently every stupid Windows ACPI bug is re-implemented in Linux which is a rather unfortunate situation. We already have the power to avoid this in e.g. memory or cpu hot-plug ACPI implementations, because Linux certification is a must for most vendors in the server area. Working towards being able to do that in the laptop area (vendors are starting to look at Linux here also and will use this tool) is the goal. At least provide them a tool to make it as easy for this guys (e.g. not needing to browse kernel code) as possible. - The ordinary Linux user: can go into the next shop, boots the firmwarekit on his most preferred machines. He chooses one without BIOS bugs. Unsupported HW is ok, he likes to try out latest projects which might support them or likes to dig on it on his own, but he hates to workaround broken BIOSes like hell. I double checked with the firmwarekit. There they have: So the mapping generally is (also depending on how likely the BIOS is to blame, this could sometimes be difficult): FW_INFO = INFO FW_WARN = WARN FW_BUG = FAIL For more info about the linuxfirmwarekit and why this is needed can be found here: http://www.linuxfirmwarekit.org While severity matches with the firmwarekit, it might be tricky to hide messages from the user. E.g. we recently found out that on HP BIOSes negative temperatures are returned, which seem to indicate that the thermal zone is invalid. We can work around that gracefully by ignoring the thermal zone and we do not want to bother the ordinary user with a frightening message: Firmware Bug: thermal management absolutely broken but want to hide it from the user. But in the linuxfirmwarekit this should be shown as a real show stopper (the temperatures could really be wrong, broken thermal management is one of the worst things that can happen and the BIOS guys of the machine must implement this properly). It is intended to do that (hide it from the user with KERN_INFO msg, but still print it as a BIOS bug) by: printk(KERN_INFO FW_BUG "Negativ temperature values detected. Try to workarounded, BIOS must get fixed\n"); Hope that works out..., no idea how to better hide it as printk is the only way to easily provide this functionality. Signed-off-by: Thomas Renninger <trenn@suse.de> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
2008-09-01 12:27:02 +00:00
/*
* FW_BUG
* Add this to a message where you are sure the firmware is buggy or behaves
* really stupid or out of spec. Be aware that the responsible BIOS developer
* should be able to fix this issue or at least get a concrete idea of the
* problem by reading your message without the need of looking at the kernel
* code.
*
* Use it for definite and high priority BIOS bugs.
*
* FW_WARN
* Use it for not that clear (e.g. could the kernel messed up things already?)
* and medium priority BIOS bugs.
*
* FW_INFO
* Use this one if you want to tell the user or vendor about something
* suspicious, but generally harmless related to the firmware.
*
* Use it for information or very low priority BIOS bugs.
*/
#define FW_BUG "[Firmware Bug]: "
#define FW_WARN "[Firmware Warn]: "
#define FW_INFO "[Firmware Info]: "
#ifdef CONFIG_PRINTK
asmlinkage int vprintk(const char *fmt, va_list args)
__attribute__ ((format (printf, 1, 0)));
asmlinkage int printk(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 15:10:00 +00:00
__attribute__ ((format (printf, 1, 2))) __cold;
extern struct ratelimit_state printk_ratelimit_state;
extern int printk_ratelimit(void);
extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msec);
#else
static inline int vprintk(const char *s, va_list args)
__attribute__ ((format (printf, 1, 0)));
static inline int vprintk(const char *s, va_list args) { return 0; }
static inline int printk(const char *s, ...)
__attribute__ ((format (printf, 1, 2)));
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 15:10:00 +00:00
static inline int __cold printk(const char *s, ...) { return 0; }
static inline int printk_ratelimit(void) { return 0; }
static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \
unsigned int interval_msec) \
{ return false; }
#endif
extern int printk_needs_cpu(int cpu);
extern void printk_tick(void);
extern void asmlinkage __attribute__((format(printf, 1, 2)))
early_printk(const char *fmt, ...);
unsigned long int_sqrt(unsigned long);
static inline void console_silent(void)
{
console_loglevel = 0;
}
static inline void console_verbose(void)
{
if (console_loglevel)
console_loglevel = 15;
}
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 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
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 15:10:00 +00:00
extern void dump_stack(void) __cold;
enum {
DUMP_PREFIX_NONE,
DUMP_PREFIX_ADDRESS,
DUMP_PREFIX_OFFSET
};
extern void hex_dump_to_buffer(const void *buf, size_t len,
int rowsize, int groupsize,
char *linebuf, size_t linebuflen, bool ascii);
extern void print_hex_dump(const char *level, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
const void *buf, size_t len, bool ascii);
extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type,
const void *buf, size_t len);
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;
}
#ifndef pr_fmt
#define pr_fmt(fmt) fmt
#endif
#define pr_emerg(fmt, ...) \
printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
#define pr_alert(fmt, ...) \
printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_crit(fmt, ...) \
printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_err(fmt, ...) \
printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
#define pr_warning(fmt, ...) \
printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
#define pr_notice(fmt, ...) \
printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
#define pr_info(fmt, ...) \
printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
/* If you are writing a driver, please use dev_dbg instead */
#if defined(DEBUG)
#define pr_debug(fmt, ...) \
printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#elif defined(CONFIG_DYNAMIC_DEBUG)
/* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */
driver core: basic infrastructure for per-module dynamic debug messages Base infrastructure to enable per-module debug messages. I've introduced CONFIG_DYNAMIC_PRINTK_DEBUG, which when enabled centralizes control of debugging statements on a per-module basis in one /proc file, currently, <debugfs>/dynamic_printk/modules. When, CONFIG_DYNAMIC_PRINTK_DEBUG, is not set, debugging statements can still be enabled as before, often by defining 'DEBUG' for the proper compilation unit. Thus, this patch set has no affect when CONFIG_DYNAMIC_PRINTK_DEBUG is not set. The infrastructure currently ties into all pr_debug() and dev_dbg() calls. That is, if CONFIG_DYNAMIC_PRINTK_DEBUG is set, all pr_debug() and dev_dbg() calls can be dynamically enabled/disabled on a per-module basis. Future plans include extending this functionality to subsystems, that define their own debug levels and flags. Usage: Dynamic debugging is controlled by the debugfs file, <debugfs>/dynamic_printk/modules. This file contains a list of the modules that can be enabled. The format of the file is as follows: <module_name> <enabled=0/1> . . . <module_name> : Name of the module in which the debug call resides <enabled=0/1> : whether the messages are enabled or not For example: snd_hda_intel enabled=0 fixup enabled=1 driver enabled=0 Enable a module: $echo "set enabled=1 <module_name>" > dynamic_printk/modules Disable a module: $echo "set enabled=0 <module_name>" > dynamic_printk/modules Enable all modules: $echo "set enabled=1 all" > dynamic_printk/modules Disable all modules: $echo "set enabled=0 all" > dynamic_printk/modules Finally, passing "dynamic_printk" at the command line enables debugging for all modules. This mode can be turned off via the above disable command. [gkh: minor cleanups and tweaks to make the build work quietly] Signed-off-by: Jason Baron <jbaron@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-08-12 20:46:19 +00:00
#define pr_debug(fmt, ...) do { \
dynamic_pr_debug(fmt, ##__VA_ARGS__); \
driver core: basic infrastructure for per-module dynamic debug messages Base infrastructure to enable per-module debug messages. I've introduced CONFIG_DYNAMIC_PRINTK_DEBUG, which when enabled centralizes control of debugging statements on a per-module basis in one /proc file, currently, <debugfs>/dynamic_printk/modules. When, CONFIG_DYNAMIC_PRINTK_DEBUG, is not set, debugging statements can still be enabled as before, often by defining 'DEBUG' for the proper compilation unit. Thus, this patch set has no affect when CONFIG_DYNAMIC_PRINTK_DEBUG is not set. The infrastructure currently ties into all pr_debug() and dev_dbg() calls. That is, if CONFIG_DYNAMIC_PRINTK_DEBUG is set, all pr_debug() and dev_dbg() calls can be dynamically enabled/disabled on a per-module basis. Future plans include extending this functionality to subsystems, that define their own debug levels and flags. Usage: Dynamic debugging is controlled by the debugfs file, <debugfs>/dynamic_printk/modules. This file contains a list of the modules that can be enabled. The format of the file is as follows: <module_name> <enabled=0/1> . . . <module_name> : Name of the module in which the debug call resides <enabled=0/1> : whether the messages are enabled or not For example: snd_hda_intel enabled=0 fixup enabled=1 driver enabled=0 Enable a module: $echo "set enabled=1 <module_name>" > dynamic_printk/modules Disable a module: $echo "set enabled=0 <module_name>" > dynamic_printk/modules Enable all modules: $echo "set enabled=1 all" > dynamic_printk/modules Disable all modules: $echo "set enabled=0 all" > dynamic_printk/modules Finally, passing "dynamic_printk" at the command line enables debugging for all modules. This mode can be turned off via the above disable command. [gkh: minor cleanups and tweaks to make the build work quietly] Signed-off-by: Jason Baron <jbaron@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-08-12 20:46:19 +00:00
} while (0)
#else
#define pr_debug(fmt, ...) \
({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; })
#endif
/*
* Display an IP address in readable format.
*/
#define NIPQUAD(addr) \
((unsigned char *)&addr)[0], \
((unsigned char *)&addr)[1], \
((unsigned char *)&addr)[2], \
((unsigned char *)&addr)[3]
#define NIPQUAD_FMT "%u.%u.%u.%u"
/*
* 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; })
/**
* 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)sizeof(char[1 - 2*!!(condition)]))
/* 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(char[1 - 2 * !!(e)]) - 1)
/* 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
/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
#endif
#endif