mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-16 03:37:18 +07:00
58c5661f21
Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(), sends an NMI IPI to CPUs which haven't called panic() to stop them, save their register information and do some cleanups for crash dumping. However, if such a CPU is infinitely looping in NMI context, we fail to save its register information into the crash dump. For example, this can happen when unknown NMIs are broadcast to all CPUs as follows: CPU 0 CPU 1 =========================== ========================== receive an unknown NMI unknown_nmi_error() panic() receive an unknown NMI spin_trylock(&panic_lock) unknown_nmi_error() crash_kexec() panic() spin_trylock(&panic_lock) panic_smp_self_stop() infinite loop kdump_nmi_shootdown_cpus() issue NMI IPI -----------> blocked until IRET infinite loop... Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET, so the NMI is not handled and the callback function to save registers is never called. In practice, this can happen on some servers which broadcast NMIs to all CPUs when the NMI button is pushed. To save registers in this case, we need to: a) Return from NMI handler instead of looping infinitely or b) Call the callback function directly from the infinite loop Inherently, a) is risky because NMI is also used to prevent corrupted data from being propagated to devices. So, we chose b). This patch does the following: 1. Move the infinite looping of CPUs which haven't called panic() in NMI context (actually done by panic_smp_self_stop()) outside of panic() to enable us to refer pt_regs. Please note that panic_smp_self_stop() is still used for normal context. 2. Call a callback of kdump_nmi_shootdown_cpus() directly to save registers and do some cleanups after setting waiting_for_crash_ipi which is used for counting down the number of CPUs which handled the callback Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Aaron Tomlin <atomlin@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Dave Young <dyoung@redhat.com> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Javi Merino <javi.merino@arm.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml <linux-kernel@vger.kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Seth Jennings <sjenning@redhat.com> Cc: Stefan Lippers-Hollmann <s.l-h@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov <bp@suse.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
862 lines
28 KiB
C
862 lines
28 KiB
C
#ifndef _LINUX_KERNEL_H
|
|
#define _LINUX_KERNEL_H
|
|
|
|
|
|
#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 <uapi/linux/kernel.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 SIZE_MAX (~(size_t)0)
|
|
|
|
#define U8_MAX ((u8)~0U)
|
|
#define S8_MAX ((s8)(U8_MAX>>1))
|
|
#define S8_MIN ((s8)(-S8_MAX - 1))
|
|
#define U16_MAX ((u16)~0U)
|
|
#define S16_MAX ((s16)(U16_MAX>>1))
|
|
#define S16_MIN ((s16)(-S16_MAX - 1))
|
|
#define U32_MAX ((u32)~0U)
|
|
#define S32_MAX ((s32)(U32_MAX>>1))
|
|
#define S32_MIN ((s32)(-S32_MAX - 1))
|
|
#define U64_MAX ((u64)~0ULL)
|
|
#define S64_MAX ((s64)(U64_MAX>>1))
|
|
#define S64_MIN ((s64)(-S64_MAX - 1))
|
|
|
|
#define STACK_MAGIC 0xdeadbeef
|
|
|
|
#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x))
|
|
|
|
#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))
|
|
#define DIV_ROUND_UP_ULL(ll,d) \
|
|
({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; })
|
|
|
|
#if BITS_PER_LONG == 32
|
|
# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d)
|
|
#else
|
|
# define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP(ll,d)
|
|
#endif
|
|
|
|
/* 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)); \
|
|
} \
|
|
)
|
|
|
|
/*
|
|
* Divide positive or negative dividend by positive divisor and round
|
|
* to closest integer. Result is undefined for negative divisors and
|
|
* for negative dividends if the divisor variable type is unsigned.
|
|
*/
|
|
#define DIV_ROUND_CLOSEST(x, divisor)( \
|
|
{ \
|
|
typeof(x) __x = x; \
|
|
typeof(divisor) __d = divisor; \
|
|
(((typeof(x))-1) > 0 || \
|
|
((typeof(divisor))-1) > 0 || (__x) > 0) ? \
|
|
(((__x) + ((__d) / 2)) / (__d)) : \
|
|
(((__x) - ((__d) / 2)) / (__d)); \
|
|
} \
|
|
)
|
|
/*
|
|
* Same as above but for u64 dividends. divisor must be a 32-bit
|
|
* number.
|
|
*/
|
|
#define DIV_ROUND_CLOSEST_ULL(x, divisor)( \
|
|
{ \
|
|
typeof(divisor) __d = divisor; \
|
|
unsigned long long _tmp = (x) + (__d) / 2; \
|
|
do_div(_tmp, __d); \
|
|
_tmp; \
|
|
} \
|
|
)
|
|
|
|
/*
|
|
* Multiplies an integer by a fraction, while avoiding unnecessary
|
|
* overflow or loss of precision.
|
|
*/
|
|
#define mult_frac(x, numer, denom)( \
|
|
{ \
|
|
typeof(x) quot = (x) / (denom); \
|
|
typeof(x) rem = (x) % (denom); \
|
|
(quot * (numer)) + ((rem * (numer)) / (denom)); \
|
|
} \
|
|
)
|
|
|
|
|
|
#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_ATOMIC_SLEEP
|
|
void ___might_sleep(const char *file, int line, int preempt_offset);
|
|
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)
|
|
# define sched_annotate_sleep() (current->task_state_change = 0)
|
|
#else
|
|
static inline void ___might_sleep(const char *file, int line,
|
|
int preempt_offset) { }
|
|
static inline void __might_sleep(const char *file, int line,
|
|
int preempt_offset) { }
|
|
# define might_sleep() do { might_resched(); } while (0)
|
|
# define sched_annotate_sleep() do { } while (0)
|
|
#endif
|
|
|
|
#define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
|
|
|
|
/**
|
|
* abs - return absolute value of an argument
|
|
* @x: the value. If it is unsigned type, it is converted to signed type first
|
|
* (s64, long or int depending on its size).
|
|
*
|
|
* Return: an absolute value of x. If x is 64-bit, macro's return type is s64,
|
|
* otherwise it is signed long.
|
|
*/
|
|
#define abs(x) __builtin_choose_expr(sizeof(x) == sizeof(s64), ({ \
|
|
s64 __x = (x); \
|
|
(__x < 0) ? -__x : __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; \
|
|
}))
|
|
|
|
/**
|
|
* reciprocal_scale - "scale" a value into range [0, ep_ro)
|
|
* @val: value
|
|
* @ep_ro: right open interval endpoint
|
|
*
|
|
* Perform a "reciprocal multiplication" in order to "scale" a value into
|
|
* range [0, ep_ro), where the upper interval endpoint is right-open.
|
|
* This is useful, e.g. for accessing a index of an array containing
|
|
* ep_ro elements, for example. Think of it as sort of modulus, only that
|
|
* the result isn't that of modulo. ;) Note that if initial input is a
|
|
* small value, then result will return 0.
|
|
*
|
|
* Return: a result based on val in interval [0, ep_ro).
|
|
*/
|
|
static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
|
|
{
|
|
return (u32)(((u64) val * ep_ro) >> 32);
|
|
}
|
|
|
|
#if defined(CONFIG_MMU) && \
|
|
(defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP))
|
|
#define might_fault() __might_fault(__FILE__, __LINE__)
|
|
void __might_fault(const char *file, int line);
|
|
#else
|
|
static inline void might_fault(void) { }
|
|
#endif
|
|
|
|
extern struct atomic_notifier_head panic_notifier_list;
|
|
extern long (*panic_blink)(int state);
|
|
__printf(1, 2)
|
|
void panic(const char *fmt, ...)
|
|
__noreturn __cold;
|
|
void nmi_panic_self_stop(struct pt_regs *);
|
|
extern void oops_enter(void);
|
|
extern void oops_exit(void);
|
|
void print_oops_end_marker(void);
|
|
extern int oops_may_print(void);
|
|
void do_exit(long error_code)
|
|
__noreturn;
|
|
void complete_and_exit(struct completion *, long)
|
|
__noreturn;
|
|
|
|
/* Internal, do not use. */
|
|
int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
|
|
int __must_check _kstrtol(const char *s, unsigned int base, long *res);
|
|
|
|
int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res);
|
|
int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
|
|
|
|
/**
|
|
* kstrtoul - convert a string to an unsigned long
|
|
* @s: The start of the string. The string must be null-terminated, and may also
|
|
* include a single newline before its terminating null. The first character
|
|
* may also be a plus sign, but not a minus sign.
|
|
* @base: The number base to use. The maximum supported base is 16. If base is
|
|
* given as 0, then the base of the string is automatically detected with the
|
|
* conventional semantics - If it begins with 0x the number will be parsed as a
|
|
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
|
|
* parsed as an octal number. Otherwise it will be parsed as a decimal.
|
|
* @res: Where to write the result of the conversion on success.
|
|
*
|
|
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
|
|
* Used as a replacement for the obsolete simple_strtoull. Return code must
|
|
* be checked.
|
|
*/
|
|
static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
|
|
{
|
|
/*
|
|
* We want to shortcut function call, but
|
|
* __builtin_types_compatible_p(unsigned long, unsigned long long) = 0.
|
|
*/
|
|
if (sizeof(unsigned long) == sizeof(unsigned long long) &&
|
|
__alignof__(unsigned long) == __alignof__(unsigned long long))
|
|
return kstrtoull(s, base, (unsigned long long *)res);
|
|
else
|
|
return _kstrtoul(s, base, res);
|
|
}
|
|
|
|
/**
|
|
* kstrtol - convert a string to a long
|
|
* @s: The start of the string. The string must be null-terminated, and may also
|
|
* include a single newline before its terminating null. The first character
|
|
* may also be a plus sign or a minus sign.
|
|
* @base: The number base to use. The maximum supported base is 16. If base is
|
|
* given as 0, then the base of the string is automatically detected with the
|
|
* conventional semantics - If it begins with 0x the number will be parsed as a
|
|
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
|
|
* parsed as an octal number. Otherwise it will be parsed as a decimal.
|
|
* @res: Where to write the result of the conversion on success.
|
|
*
|
|
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
|
|
* Used as a replacement for the obsolete simple_strtoull. Return code must
|
|
* be checked.
|
|
*/
|
|
static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
|
|
{
|
|
/*
|
|
* We want to shortcut function call, but
|
|
* __builtin_types_compatible_p(long, long long) = 0.
|
|
*/
|
|
if (sizeof(long) == sizeof(long long) &&
|
|
__alignof__(long) == __alignof__(long long))
|
|
return kstrtoll(s, base, (long long *)res);
|
|
else
|
|
return _kstrtol(s, base, res);
|
|
}
|
|
|
|
int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res);
|
|
int __must_check kstrtoint(const char *s, unsigned int base, int *res);
|
|
|
|
static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res)
|
|
{
|
|
return kstrtoull(s, base, res);
|
|
}
|
|
|
|
static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res)
|
|
{
|
|
return kstrtoll(s, base, res);
|
|
}
|
|
|
|
static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res)
|
|
{
|
|
return kstrtouint(s, base, res);
|
|
}
|
|
|
|
static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res)
|
|
{
|
|
return kstrtoint(s, base, res);
|
|
}
|
|
|
|
int __must_check kstrtou16(const char *s, unsigned int base, u16 *res);
|
|
int __must_check kstrtos16(const char *s, unsigned int base, s16 *res);
|
|
int __must_check kstrtou8(const char *s, unsigned int base, u8 *res);
|
|
int __must_check kstrtos8(const char *s, unsigned int base, s8 *res);
|
|
|
|
int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res);
|
|
int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res);
|
|
int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res);
|
|
int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res);
|
|
int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res);
|
|
int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res);
|
|
int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res);
|
|
int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res);
|
|
int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res);
|
|
int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res);
|
|
|
|
static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res)
|
|
{
|
|
return kstrtoull_from_user(s, count, base, res);
|
|
}
|
|
|
|
static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res)
|
|
{
|
|
return kstrtoll_from_user(s, count, base, res);
|
|
}
|
|
|
|
static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res)
|
|
{
|
|
return kstrtouint_from_user(s, count, base, res);
|
|
}
|
|
|
|
static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res)
|
|
{
|
|
return kstrtoint_from_user(s, count, base, res);
|
|
}
|
|
|
|
/* Obsolete, do not use. Use kstrto<foo> instead */
|
|
|
|
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 num_to_str(char *buf, int size, unsigned long long num);
|
|
|
|
/* lib/printf utilities */
|
|
|
|
extern __printf(2, 3) int sprintf(char *buf, const char * fmt, ...);
|
|
extern __printf(2, 0) int vsprintf(char *buf, const char *, va_list);
|
|
extern __printf(3, 4)
|
|
int snprintf(char *buf, size_t size, const char *fmt, ...);
|
|
extern __printf(3, 0)
|
|
int vsnprintf(char *buf, size_t size, const char *fmt, va_list args);
|
|
extern __printf(3, 4)
|
|
int scnprintf(char *buf, size_t size, const char *fmt, ...);
|
|
extern __printf(3, 0)
|
|
int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
|
|
extern __printf(2, 3)
|
|
char *kasprintf(gfp_t gfp, const char *fmt, ...);
|
|
extern __printf(2, 0)
|
|
char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
|
|
extern __printf(2, 0)
|
|
const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list args);
|
|
|
|
extern __scanf(2, 3)
|
|
int sscanf(const char *, const char *, ...);
|
|
extern __scanf(2, 0)
|
|
int vsscanf(const char *, const char *, va_list);
|
|
|
|
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 bool parse_option_str(const char *str, const char *option);
|
|
|
|
extern int core_kernel_text(unsigned long addr);
|
|
extern int core_kernel_data(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);
|
|
|
|
unsigned long int_sqrt(unsigned long);
|
|
|
|
extern void bust_spinlocks(int yes);
|
|
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 int panic_on_warn;
|
|
extern int sysctl_panic_on_stackoverflow;
|
|
|
|
extern bool crash_kexec_post_notifiers;
|
|
|
|
/*
|
|
* panic_cpu is used for synchronizing panic() and crash_kexec() execution. It
|
|
* holds a CPU number which is executing panic() currently. A value of
|
|
* PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec().
|
|
*/
|
|
extern atomic_t panic_cpu;
|
|
#define PANIC_CPU_INVALID -1
|
|
|
|
/*
|
|
* A variant of panic() called from NMI context. We return if we've already
|
|
* panicked on this CPU. If another CPU already panicked, loop in
|
|
* nmi_panic_self_stop() which can provide architecture dependent code such
|
|
* as saving register state for crash dump.
|
|
*/
|
|
#define nmi_panic(regs, fmt, ...) \
|
|
do { \
|
|
int old_cpu, cpu; \
|
|
\
|
|
cpu = raw_smp_processor_id(); \
|
|
old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); \
|
|
\
|
|
if (old_cpu == PANIC_CPU_INVALID) \
|
|
panic(fmt, ##__VA_ARGS__); \
|
|
else if (old_cpu != cpu) \
|
|
nmi_panic_self_stop(regs); \
|
|
} while (0)
|
|
|
|
/*
|
|
* Only to be used by arch init code. If the user over-wrote the default
|
|
* CONFIG_PANIC_TIMEOUT, honor it.
|
|
*/
|
|
static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout)
|
|
{
|
|
if (panic_timeout == arch_default_timeout)
|
|
panic_timeout = timeout;
|
|
}
|
|
extern const char *print_tainted(void);
|
|
enum lockdep_ok {
|
|
LOCKDEP_STILL_OK,
|
|
LOCKDEP_NOW_UNRELIABLE
|
|
};
|
|
extern void add_taint(unsigned flag, enum lockdep_ok);
|
|
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_state;
|
|
|
|
#define TAINT_PROPRIETARY_MODULE 0
|
|
#define TAINT_FORCED_MODULE 1
|
|
#define TAINT_CPU_OUT_OF_SPEC 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
|
|
#define TAINT_OOT_MODULE 12
|
|
#define TAINT_UNSIGNED_MODULE 13
|
|
#define TAINT_SOFTLOCKUP 14
|
|
#define TAINT_LIVEPATCH 15
|
|
|
|
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 *hex_byte_pack(char *buf, u8 byte)
|
|
{
|
|
*buf++ = hex_asc_hi(byte);
|
|
*buf++ = hex_asc_lo(byte);
|
|
return buf;
|
|
}
|
|
|
|
extern const char hex_asc_upper[];
|
|
#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)]
|
|
#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4]
|
|
|
|
static inline char *hex_byte_pack_upper(char *buf, u8 byte)
|
|
{
|
|
*buf++ = hex_asc_upper_hi(byte);
|
|
*buf++ = hex_asc_upper_lo(byte);
|
|
return buf;
|
|
}
|
|
|
|
extern int hex_to_bin(char ch);
|
|
extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
|
|
extern char *bin2hex(char *dst, const void *src, size_t count);
|
|
|
|
bool mac_pton(const char *s, u8 *mac);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
|
|
enum ftrace_dump_mode {
|
|
DUMP_NONE,
|
|
DUMP_ALL,
|
|
DUMP_ORIG,
|
|
};
|
|
|
|
#ifdef CONFIG_TRACING
|
|
void tracing_on(void);
|
|
void tracing_off(void);
|
|
int tracing_is_on(void);
|
|
void tracing_snapshot(void);
|
|
void tracing_snapshot_alloc(void);
|
|
|
|
extern void tracing_start(void);
|
|
extern void tracing_stop(void);
|
|
|
|
static inline __printf(1, 2)
|
|
void ____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. (Extra memory is used for special buffers that are
|
|
* allocated when trace_printk() is used)
|
|
*
|
|
* A little optization trick is done here. If there's only one
|
|
* argument, there's no need to scan the string for printf formats.
|
|
* The trace_puts() will suffice. But how can we take advantage of
|
|
* using trace_puts() when trace_printk() has only one argument?
|
|
* By stringifying the args and checking the size we can tell
|
|
* whether or not there are args. __stringify((__VA_ARGS__)) will
|
|
* turn into "()\0" with a size of 3 when there are no args, anything
|
|
* else will be bigger. All we need to do is define a string to this,
|
|
* and then take its size and compare to 3. If it's bigger, use
|
|
* do_trace_printk() otherwise, optimize it to trace_puts(). Then just
|
|
* let gcc optimize the rest.
|
|
*/
|
|
|
|
#define trace_printk(fmt, ...) \
|
|
do { \
|
|
char _______STR[] = __stringify((__VA_ARGS__)); \
|
|
if (sizeof(_______STR) > 3) \
|
|
do_trace_printk(fmt, ##__VA_ARGS__); \
|
|
else \
|
|
trace_puts(fmt); \
|
|
} while (0)
|
|
|
|
#define do_trace_printk(fmt, args...) \
|
|
do { \
|
|
static const char *trace_printk_fmt \
|
|
__attribute__((section("__trace_printk_fmt"))) = \
|
|
__builtin_constant_p(fmt) ? fmt : NULL; \
|
|
\
|
|
__trace_printk_check_format(fmt, ##args); \
|
|
\
|
|
if (__builtin_constant_p(fmt)) \
|
|
__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \
|
|
else \
|
|
__trace_printk(_THIS_IP_, fmt, ##args); \
|
|
} while (0)
|
|
|
|
extern __printf(2, 3)
|
|
int __trace_bprintk(unsigned long ip, const char *fmt, ...);
|
|
|
|
extern __printf(2, 3)
|
|
int __trace_printk(unsigned long ip, const char *fmt, ...);
|
|
|
|
/**
|
|
* trace_puts - write a string into the ftrace buffer
|
|
* @str: the string to record
|
|
*
|
|
* Note: __trace_bputs is an internal function for trace_puts and
|
|
* the @ip is passed in via the trace_puts macro.
|
|
*
|
|
* This is similar to trace_printk() but is made for those really fast
|
|
* paths that a developer wants the least amount of "Heisenbug" affects,
|
|
* where the processing of the print format is still too much.
|
|
*
|
|
* 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_puts scattered around in
|
|
* your code. (Extra memory is used for special buffers that are
|
|
* allocated when trace_puts() is used)
|
|
*
|
|
* Returns: 0 if nothing was written, positive # if string was.
|
|
* (1 when __trace_bputs is used, strlen(str) when __trace_puts is used)
|
|
*/
|
|
|
|
#define trace_puts(str) ({ \
|
|
static const char *trace_printk_fmt \
|
|
__attribute__((section("__trace_printk_fmt"))) = \
|
|
__builtin_constant_p(str) ? str : NULL; \
|
|
\
|
|
if (__builtin_constant_p(str)) \
|
|
__trace_bputs(_THIS_IP_, trace_printk_fmt); \
|
|
else \
|
|
__trace_puts(_THIS_IP_, str, strlen(str)); \
|
|
})
|
|
extern int __trace_bputs(unsigned long ip, const char *str);
|
|
extern int __trace_puts(unsigned long ip, const char *str, int size);
|
|
|
|
extern void trace_dump_stack(int skip);
|
|
|
|
/*
|
|
* 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 __printf(2, 0) int
|
|
__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
|
|
|
|
extern __printf(2, 0) 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 void tracing_start(void) { }
|
|
static inline void tracing_stop(void) { }
|
|
static inline void trace_dump_stack(int skip) { }
|
|
|
|
static inline void tracing_on(void) { }
|
|
static inline void tracing_off(void) { }
|
|
static inline int tracing_is_on(void) { return 0; }
|
|
static inline void tracing_snapshot(void) { }
|
|
static inline void tracing_snapshot_alloc(void) { }
|
|
|
|
static inline __printf(1, 2)
|
|
int trace_printk(const char *fmt, ...)
|
|
{
|
|
return 0;
|
|
}
|
|
static __printf(1, 0) 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) min((typeof(x))min(x, y), z)
|
|
#define max3(x, y, z) max((typeof(x))max(x, y), z)
|
|
|
|
/**
|
|
* 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
|
|
* @lo: lowest allowable value
|
|
* @hi: highest allowable value
|
|
*
|
|
* This macro does strict typechecking of lo/hi to make sure they are of the
|
|
* same type as val. See the unnecessary pointer comparisons.
|
|
*/
|
|
#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
|
|
|
|
/*
|
|
* ..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
|
|
* @lo: minimum allowable value
|
|
* @hi: 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, lo, hi) min_t(type, max_t(type, val, lo), hi)
|
|
|
|
/**
|
|
* clamp_val - return a value clamped to a given range using val's type
|
|
* @val: current value
|
|
* @lo: minimum allowable value
|
|
* @hi: 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, lo, hi) clamp_t(typeof(val), val, lo, hi)
|
|
|
|
|
|
/*
|
|
* 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) );})
|
|
|
|
/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
|
|
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
|
|
# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
|
|
#endif
|
|
|
|
/* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */
|
|
#define VERIFY_OCTAL_PERMISSIONS(perms) \
|
|
(BUILD_BUG_ON_ZERO((perms) < 0) + \
|
|
BUILD_BUG_ON_ZERO((perms) > 0777) + \
|
|
/* USER_READABLE >= GROUP_READABLE >= OTHER_READABLE */ \
|
|
BUILD_BUG_ON_ZERO((((perms) >> 6) & 4) < (((perms) >> 3) & 4)) + \
|
|
BUILD_BUG_ON_ZERO((((perms) >> 3) & 4) < ((perms) & 4)) + \
|
|
/* USER_WRITABLE >= GROUP_WRITABLE */ \
|
|
BUILD_BUG_ON_ZERO((((perms) >> 6) & 2) < (((perms) >> 3) & 2)) + \
|
|
/* OTHER_WRITABLE? Generally considered a bad idea. */ \
|
|
BUILD_BUG_ON_ZERO((perms) & 2) + \
|
|
(perms))
|
|
#endif
|