mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 09:56:40 +07:00
e041c68341
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>
337 lines
9.7 KiB
C
337 lines
9.7 KiB
C
#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 <asm/byteorder.h>
|
|
#include <asm/bug.h>
|
|
|
|
extern const char linux_banner[];
|
|
|
|
#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 STACK_MAGIC 0xdeadbeef
|
|
|
|
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
|
|
#define ALIGN(x,a) (((x)+(a)-1)&~((a)-1))
|
|
|
|
#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 */
|
|
|
|
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;
|
|
|
|
/**
|
|
* 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 biten later when the calling function happens to sleep when it is not
|
|
* supposed to.
|
|
*/
|
|
#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);
|
|
# 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 (unlikely(cond)) might_sleep(); } while (0)
|
|
|
|
#define abs(x) ({ \
|
|
int __x = (x); \
|
|
(__x < 0) ? -__x : __x; \
|
|
})
|
|
|
|
#define labs(x) ({ \
|
|
long __x = (x); \
|
|
(__x < 0) ? -__x : __x; \
|
|
})
|
|
|
|
extern struct atomic_notifier_head panic_notifier_list;
|
|
extern long (*panic_blink)(long time);
|
|
NORET_TYPE void panic(const char * fmt, ...)
|
|
__attribute__ ((NORET_AND format (printf, 1, 2)));
|
|
extern void oops_enter(void);
|
|
extern void oops_exit(void);
|
|
extern int oops_may_print(void);
|
|
fastcall 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 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 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(char *ptr, char **retptr);
|
|
|
|
extern int __kernel_text_address(unsigned long addr);
|
|
extern int kernel_text_address(unsigned long addr);
|
|
extern int session_of_pgrp(int pgrp);
|
|
|
|
extern void dump_thread(struct pt_regs *regs, struct user *dump);
|
|
|
|
#ifdef CONFIG_PRINTK
|
|
asmlinkage int vprintk(const char *fmt, va_list args)
|
|
__attribute__ ((format (printf, 1, 0)));
|
|
asmlinkage int printk(const char * fmt, ...)
|
|
__attribute__ ((format (printf, 1, 2)));
|
|
#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)));
|
|
static inline int printk(const char *s, ...) { return 0; }
|
|
#endif
|
|
|
|
unsigned long int_sqrt(unsigned long);
|
|
|
|
static inline int __attribute_pure__ long_log2(unsigned long x)
|
|
{
|
|
int r = 0;
|
|
for (x >>= 1; x > 0; x >>= 1)
|
|
r++;
|
|
return r;
|
|
}
|
|
|
|
static inline unsigned long
|
|
__attribute_const__ roundup_pow_of_two(unsigned long x)
|
|
{
|
|
return 1UL << fls_long(x - 1);
|
|
}
|
|
|
|
extern int printk_ratelimit(void);
|
|
extern int __printk_ratelimit(int ratelimit_jiffies, int ratelimit_burst);
|
|
|
|
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 int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */
|
|
extern __deprecated_for_modules int panic_timeout;
|
|
extern int panic_on_oops;
|
|
extern int tainted;
|
|
extern const char *print_tainted(void);
|
|
extern void add_taint(unsigned);
|
|
|
|
/* 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 (1<<0)
|
|
#define TAINT_FORCED_MODULE (1<<1)
|
|
#define TAINT_UNSAFE_SMP (1<<2)
|
|
#define TAINT_FORCED_RMMOD (1<<3)
|
|
#define TAINT_MACHINE_CHECK (1<<4)
|
|
#define TAINT_BAD_PAGE (1<<5)
|
|
|
|
extern void dump_stack(void);
|
|
|
|
#ifdef DEBUG
|
|
#define pr_debug(fmt,arg...) \
|
|
printk(KERN_DEBUG fmt,##arg)
|
|
#else
|
|
#define pr_debug(fmt,arg...) \
|
|
do { } while (0)
|
|
#endif
|
|
|
|
#define pr_info(fmt,arg...) \
|
|
printk(KERN_INFO fmt,##arg)
|
|
|
|
/*
|
|
* 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"
|
|
|
|
#define NIP6(addr) \
|
|
ntohs((addr).s6_addr16[0]), \
|
|
ntohs((addr).s6_addr16[1]), \
|
|
ntohs((addr).s6_addr16[2]), \
|
|
ntohs((addr).s6_addr16[3]), \
|
|
ntohs((addr).s6_addr16[4]), \
|
|
ntohs((addr).s6_addr16[5]), \
|
|
ntohs((addr).s6_addr16[6]), \
|
|
ntohs((addr).s6_addr16[7])
|
|
#define NIP6_FMT "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x"
|
|
#define NIP6_SEQFMT "%04x%04x%04x%04x%04x%04x%04x%04x"
|
|
|
|
#if defined(__LITTLE_ENDIAN)
|
|
#define HIPQUAD(addr) \
|
|
((unsigned char *)&addr)[3], \
|
|
((unsigned char *)&addr)[2], \
|
|
((unsigned char *)&addr)[1], \
|
|
((unsigned char *)&addr)[0]
|
|
#elif defined(__BIG_ENDIAN)
|
|
#define HIPQUAD NIPQUAD
|
|
#else
|
|
#error "Please fix asm/byteorder.h"
|
|
#endif /* __LITTLE_ENDIAN */
|
|
|
|
/*
|
|
* min()/max() macros that also do
|
|
* strict type-checking.. See the
|
|
* "unnecessary" pointer comparison.
|
|
*/
|
|
#define min(x,y) ({ \
|
|
typeof(x) _x = (x); \
|
|
typeof(y) _y = (y); \
|
|
(void) (&_x == &_y); \
|
|
_x < _y ? _x : _y; })
|
|
|
|
#define max(x,y) ({ \
|
|
typeof(x) _x = (x); \
|
|
typeof(y) _y = (y); \
|
|
(void) (&_x == &_y); \
|
|
_x > _y ? _x : _y; })
|
|
|
|
/*
|
|
* ..and if you can't take the strict
|
|
* types, you can specify one yourself.
|
|
*
|
|
* Or not use min/max at all, of course.
|
|
*/
|
|
#define min_t(type,x,y) \
|
|
({ type __x = (x); type __y = (y); __x < __y ? __x: __y; })
|
|
#define max_t(type,x,y) \
|
|
({ type __x = (x); type __y = (y); __x > __y ? __x: __y; })
|
|
|
|
|
|
/**
|
|
* 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) );})
|
|
|
|
/*
|
|
* Check at compile time that something is of a particular type.
|
|
* Always evaluates to 1 so you may use it easily in comparisons.
|
|
*/
|
|
#define typecheck(type,x) \
|
|
({ type __dummy; \
|
|
typeof(x) __dummy2; \
|
|
(void)(&__dummy == &__dummy2); \
|
|
1; \
|
|
})
|
|
|
|
/*
|
|
* Check at compile time that 'function' is a certain type, or is a pointer
|
|
* to that type (needs to use typedef for the function type.)
|
|
*/
|
|
#define typecheck_fn(type,function) \
|
|
({ typeof(type) __tmp = function; \
|
|
(void)__tmp; \
|
|
})
|
|
|
|
#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)]))
|
|
|
|
/* Trap pasters of __FUNCTION__ at compile-time */
|
|
#define __FUNCTION__ (__func__)
|
|
|
|
#endif
|