From a585042f7b933539a0b6bc63650c2d49ffb2e55d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 21 Nov 2011 12:32:23 -0800 Subject: freezer: remove racy clear_freeze_flag() and set PF_NOFREEZE on dead tasks clear_freeze_flag() in exit_mm() is racy. Freezing can start afterwards. Remove it. Skipping freezer for exiting task will be properly implemented later. Also, freezable() was testing exit_state directly to make system freezer ignore dead tasks. Let the exiting task set PF_NOFREEZE after entering TASK_DEAD instead. Signed-off-by: Tejun Heo Cc: Oleg Nesterov --- kernel/exit.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index d0b7d988f87..95a4141d07e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -679,8 +679,6 @@ static void exit_mm(struct task_struct * tsk) tsk->mm = NULL; up_read(&mm->mmap_sem); enter_lazy_tlb(mm, current); - /* We don't want this task to be frozen prematurely */ - clear_freeze_flag(tsk); task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); @@ -1040,6 +1038,7 @@ NORET_TYPE void do_exit(long code) exit_rcu(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; + tsk->flags |= PF_NOFREEZE; /* tell freezer to ignore us */ schedule(); BUG(); /* Avoid "noreturn function does return". */ -- cgit v1.2.3-70-g09d2 From 648616343cdbe904c585a6c12e323d3b3c72e46f Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 15 Dec 2011 14:56:09 +0100 Subject: [S390] cputime: add sparse checking and cleanup Make cputime_t and cputime64_t nocast to enable sparse checking to detect incorrect use of cputime. Drop the cputime macros for simple scalar operations. The conversion macros are still needed. Signed-off-by: Martin Schwidefsky --- arch/ia64/include/asm/cputime.h | 69 ++++++++-------- arch/powerpc/include/asm/cputime.h | 70 +++++++---------- arch/s390/include/asm/cputime.h | 140 +++++++++++++++------------------ drivers/cpufreq/cpufreq_conservative.c | 29 ++++--- drivers/cpufreq/cpufreq_ondemand.c | 33 ++++---- drivers/cpufreq/cpufreq_stats.c | 5 +- drivers/macintosh/rack-meter.c | 11 +-- fs/proc/array.c | 8 +- fs/proc/stat.c | 27 +++---- fs/proc/uptime.c | 4 +- include/asm-generic/cputime.h | 62 +++++++-------- include/linux/sched.h | 4 +- kernel/acct.c | 4 +- kernel/cpu.c | 3 +- kernel/exit.c | 22 ++---- kernel/fork.c | 14 ++-- kernel/itimer.c | 15 ++-- kernel/posix-cpu-timers.c | 132 ++++++++++++------------------- kernel/sched.c | 80 +++++++++---------- kernel/sched_stats.h | 6 +- kernel/signal.c | 6 +- kernel/sys.c | 6 +- kernel/tsacct.c | 2 +- 23 files changed, 323 insertions(+), 429 deletions(-) (limited to 'kernel/exit.c') diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h index 6073b187528..461e52f0277 100644 --- a/arch/ia64/include/asm/cputime.h +++ b/arch/ia64/include/asm/cputime.h @@ -26,59 +26,51 @@ #include #include -typedef u64 cputime_t; -typedef u64 cputime64_t; +typedef u64 __nocast cputime_t; +typedef u64 __nocast cputime64_t; -#define cputime_zero ((cputime_t)0) #define cputime_one_jiffy jiffies_to_cputime(1) -#define cputime_max ((~((cputime_t)0) >> 1) - 1) -#define cputime_add(__a, __b) ((__a) + (__b)) -#define cputime_sub(__a, __b) ((__a) - (__b)) -#define cputime_div(__a, __n) ((__a) / (__n)) -#define cputime_halve(__a) ((__a) >> 1) -#define cputime_eq(__a, __b) ((__a) == (__b)) -#define cputime_gt(__a, __b) ((__a) > (__b)) -#define cputime_ge(__a, __b) ((__a) >= (__b)) -#define cputime_lt(__a, __b) ((__a) < (__b)) -#define cputime_le(__a, __b) ((__a) <= (__b)) - -#define cputime64_zero ((cputime64_t)0) -#define cputime64_add(__a, __b) ((__a) + (__b)) -#define cputime64_sub(__a, __b) ((__a) - (__b)) -#define cputime_to_cputime64(__ct) (__ct) /* * Convert cputime <-> jiffies (HZ) */ -#define cputime_to_jiffies(__ct) ((__ct) / (NSEC_PER_SEC / HZ)) -#define jiffies_to_cputime(__jif) ((__jif) * (NSEC_PER_SEC / HZ)) -#define cputime64_to_jiffies64(__ct) ((__ct) / (NSEC_PER_SEC / HZ)) -#define jiffies64_to_cputime64(__jif) ((__jif) * (NSEC_PER_SEC / HZ)) +#define cputime_to_jiffies(__ct) \ + ((__force u64)(__ct) / (NSEC_PER_SEC / HZ)) +#define jiffies_to_cputime(__jif) \ + (__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ)) +#define cputime64_to_jiffies64(__ct) \ + ((__force u64)(__ct) / (NSEC_PER_SEC / HZ)) +#define jiffies64_to_cputime64(__jif) \ + (__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ)) /* * Convert cputime <-> microseconds */ -#define cputime_to_usecs(__ct) ((__ct) / NSEC_PER_USEC) -#define usecs_to_cputime(__usecs) ((__usecs) * NSEC_PER_USEC) +#define cputime_to_usecs(__ct) \ + ((__force u64)(__ct) / NSEC_PER_USEC) +#define usecs_to_cputime(__usecs) \ + (__force cputime_t)((__usecs) * NSEC_PER_USEC) /* * Convert cputime <-> seconds */ -#define cputime_to_secs(__ct) ((__ct) / NSEC_PER_SEC) -#define secs_to_cputime(__secs) ((__secs) * NSEC_PER_SEC) +#define cputime_to_secs(__ct) \ + ((__force u64)(__ct) / NSEC_PER_SEC) +#define secs_to_cputime(__secs) \ + (__force cputime_t)((__secs) * NSEC_PER_SEC) /* * Convert cputime <-> timespec (nsec) */ static inline cputime_t timespec_to_cputime(const struct timespec *val) { - cputime_t ret = val->tv_sec * NSEC_PER_SEC; - return (ret + val->tv_nsec); + u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec; + return (__force cputime_t) ret; } static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) { - val->tv_sec = ct / NSEC_PER_SEC; - val->tv_nsec = ct % NSEC_PER_SEC; + val->tv_sec = (__force u64) ct / NSEC_PER_SEC; + val->tv_nsec = (__force u64) ct % NSEC_PER_SEC; } /* @@ -86,25 +78,28 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) */ static inline cputime_t timeval_to_cputime(struct timeval *val) { - cputime_t ret = val->tv_sec * NSEC_PER_SEC; - return (ret + val->tv_usec * NSEC_PER_USEC); + u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC; + return (__force cputime_t) ret; } static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val) { - val->tv_sec = ct / NSEC_PER_SEC; - val->tv_usec = (ct % NSEC_PER_SEC) / NSEC_PER_USEC; + val->tv_sec = (__force u64) ct / NSEC_PER_SEC; + val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC; } /* * Convert cputime <-> clock (USER_HZ) */ -#define cputime_to_clock_t(__ct) ((__ct) / (NSEC_PER_SEC / USER_HZ)) -#define clock_t_to_cputime(__x) ((__x) * (NSEC_PER_SEC / USER_HZ)) +#define cputime_to_clock_t(__ct) \ + ((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ)) +#define clock_t_to_cputime(__x) \ + (__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ)) /* * Convert cputime64 to clock. */ -#define cputime64_to_clock_t(__ct) cputime_to_clock_t((cputime_t)__ct) +#define cputime64_to_clock_t(__ct) \ + cputime_to_clock_t((__force cputime_t)__ct) #endif /* CONFIG_VIRT_CPU_ACCOUNTING */ #endif /* __IA64_CPUTIME_H */ diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 1cf20bdfbec..e94935c5201 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -29,25 +29,8 @@ static inline void setup_cputime_one_jiffy(void) { } #include #include -typedef u64 cputime_t; -typedef u64 cputime64_t; - -#define cputime_zero ((cputime_t)0) -#define cputime_max ((~((cputime_t)0) >> 1) - 1) -#define cputime_add(__a, __b) ((__a) + (__b)) -#define cputime_sub(__a, __b) ((__a) - (__b)) -#define cputime_div(__a, __n) ((__a) / (__n)) -#define cputime_halve(__a) ((__a) >> 1) -#define cputime_eq(__a, __b) ((__a) == (__b)) -#define cputime_gt(__a, __b) ((__a) > (__b)) -#define cputime_ge(__a, __b) ((__a) >= (__b)) -#define cputime_lt(__a, __b) ((__a) < (__b)) -#define cputime_le(__a, __b) ((__a) <= (__b)) - -#define cputime64_zero ((cputime64_t)0) -#define cputime64_add(__a, __b) ((__a) + (__b)) -#define cputime64_sub(__a, __b) ((__a) - (__b)) -#define cputime_to_cputime64(__ct) (__ct) +typedef u64 __nocast cputime_t; +typedef u64 __nocast cputime64_t; #ifdef __KERNEL__ @@ -65,7 +48,7 @@ DECLARE_PER_CPU(unsigned long, cputime_scaled_last_delta); static inline unsigned long cputime_to_jiffies(const cputime_t ct) { - return mulhdu(ct, __cputime_jiffies_factor); + return mulhdu((__force u64) ct, __cputime_jiffies_factor); } /* Estimate the scaled cputime by scaling the real cputime based on @@ -74,14 +57,15 @@ static inline cputime_t cputime_to_scaled(const cputime_t ct) { if (cpu_has_feature(CPU_FTR_SPURR) && __get_cpu_var(cputime_last_delta)) - return ct * __get_cpu_var(cputime_scaled_last_delta) / - __get_cpu_var(cputime_last_delta); + return (__force u64) ct * + __get_cpu_var(cputime_scaled_last_delta) / + __get_cpu_var(cputime_last_delta); return ct; } static inline cputime_t jiffies_to_cputime(const unsigned long jif) { - cputime_t ct; + u64 ct; unsigned long sec; /* have to be a little careful about overflow */ @@ -93,7 +77,7 @@ static inline cputime_t jiffies_to_cputime(const unsigned long jif) } if (sec) ct += (cputime_t) sec * tb_ticks_per_sec; - return ct; + return (__force cputime_t) ct; } static inline void setup_cputime_one_jiffy(void) @@ -103,7 +87,7 @@ static inline void setup_cputime_one_jiffy(void) static inline cputime64_t jiffies64_to_cputime64(const u64 jif) { - cputime_t ct; + u64 ct; u64 sec; /* have to be a little careful about overflow */ @@ -114,13 +98,13 @@ static inline cputime64_t jiffies64_to_cputime64(const u64 jif) do_div(ct, HZ); } if (sec) - ct += (cputime_t) sec * tb_ticks_per_sec; - return ct; + ct += (u64) sec * tb_ticks_per_sec; + return (__force cputime64_t) ct; } static inline u64 cputime64_to_jiffies64(const cputime_t ct) { - return mulhdu(ct, __cputime_jiffies_factor); + return mulhdu((__force u64) ct, __cputime_jiffies_factor); } /* @@ -130,12 +114,12 @@ extern u64 __cputime_msec_factor; static inline unsigned long cputime_to_usecs(const cputime_t ct) { - return mulhdu(ct, __cputime_msec_factor) * USEC_PER_MSEC; + return mulhdu((__force u64) ct, __cputime_msec_factor) * USEC_PER_MSEC; } static inline cputime_t usecs_to_cputime(const unsigned long us) { - cputime_t ct; + u64 ct; unsigned long sec; /* have to be a little careful about overflow */ @@ -147,7 +131,7 @@ static inline cputime_t usecs_to_cputime(const unsigned long us) } if (sec) ct += (cputime_t) sec * tb_ticks_per_sec; - return ct; + return (__force cputime_t) ct; } /* @@ -157,12 +141,12 @@ extern u64 __cputime_sec_factor; static inline unsigned long cputime_to_secs(const cputime_t ct) { - return mulhdu(ct, __cputime_sec_factor); + return mulhdu((__force u64) ct, __cputime_sec_factor); } static inline cputime_t secs_to_cputime(const unsigned long sec) { - return (cputime_t) sec * tb_ticks_per_sec; + return (__force cputime_t)((u64) sec * tb_ticks_per_sec); } /* @@ -170,7 +154,7 @@ static inline cputime_t secs_to_cputime(const unsigned long sec) */ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p) { - u64 x = ct; + u64 x = (__force u64) ct; unsigned int frac; frac = do_div(x, tb_ticks_per_sec); @@ -182,11 +166,11 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p) static inline cputime_t timespec_to_cputime(const struct timespec *p) { - cputime_t ct; + u64 ct; ct = (u64) p->tv_nsec * tb_ticks_per_sec; do_div(ct, 1000000000); - return ct + (u64) p->tv_sec * tb_ticks_per_sec; + return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec); } /* @@ -194,7 +178,7 @@ static inline cputime_t timespec_to_cputime(const struct timespec *p) */ static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p) { - u64 x = ct; + u64 x = (__force u64) ct; unsigned int frac; frac = do_div(x, tb_ticks_per_sec); @@ -206,11 +190,11 @@ static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p) static inline cputime_t timeval_to_cputime(const struct timeval *p) { - cputime_t ct; + u64 ct; ct = (u64) p->tv_usec * tb_ticks_per_sec; do_div(ct, 1000000); - return ct + (u64) p->tv_sec * tb_ticks_per_sec; + return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec); } /* @@ -220,12 +204,12 @@ extern u64 __cputime_clockt_factor; static inline unsigned long cputime_to_clock_t(const cputime_t ct) { - return mulhdu(ct, __cputime_clockt_factor); + return mulhdu((__force u64) ct, __cputime_clockt_factor); } static inline cputime_t clock_t_to_cputime(const unsigned long clk) { - cputime_t ct; + u64 ct; unsigned long sec; /* have to be a little careful about overflow */ @@ -236,8 +220,8 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk) do_div(ct, USER_HZ); } if (sec) - ct += (cputime_t) sec * tb_ticks_per_sec; - return ct; + ct += (u64) sec * tb_ticks_per_sec; + return (__force cputime_t) ct; } #define cputime64_to_clock_t(ct) cputime_to_clock_t((cputime_t)(ct)) diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 08143487829..0887a0463e3 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -16,114 +16,98 @@ /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ -typedef unsigned long long cputime_t; -typedef unsigned long long cputime64_t; +typedef unsigned long long __nocast cputime_t; +typedef unsigned long long __nocast cputime64_t; -#ifndef __s390x__ - -static inline unsigned int -__div(unsigned long long n, unsigned int base) +static inline unsigned long __div(unsigned long long n, unsigned long base) { +#ifndef __s390x__ register_pair rp; rp.pair = n >> 1; asm ("dr %0,%1" : "+d" (rp) : "d" (base >> 1)); return rp.subreg.odd; +#else /* __s390x__ */ + return n / base; +#endif /* __s390x__ */ } -#else /* __s390x__ */ +#define cputime_one_jiffy jiffies_to_cputime(1) -static inline unsigned int -__div(unsigned long long n, unsigned int base) +/* + * Convert cputime to jiffies and back. + */ +static inline unsigned long cputime_to_jiffies(const cputime_t cputime) { - return n / base; + return __div((__force unsigned long long) cputime, 4096000000ULL / HZ); } -#endif /* __s390x__ */ +static inline cputime_t jiffies_to_cputime(const unsigned int jif) +{ + return (__force cputime_t)(jif * (4096000000ULL / HZ)); +} -#define cputime_zero (0ULL) -#define cputime_one_jiffy jiffies_to_cputime(1) -#define cputime_max ((~0UL >> 1) - 1) -#define cputime_add(__a, __b) ((__a) + (__b)) -#define cputime_sub(__a, __b) ((__a) - (__b)) -#define cputime_div(__a, __n) ({ \ - unsigned long long __div = (__a); \ - do_div(__div,__n); \ - __div; \ -}) -#define cputime_halve(__a) ((__a) >> 1) -#define cputime_eq(__a, __b) ((__a) == (__b)) -#define cputime_gt(__a, __b) ((__a) > (__b)) -#define cputime_ge(__a, __b) ((__a) >= (__b)) -#define cputime_lt(__a, __b) ((__a) < (__b)) -#define cputime_le(__a, __b) ((__a) <= (__b)) -#define cputime_to_jiffies(__ct) (__div((__ct), 4096000000ULL / HZ)) -#define cputime_to_scaled(__ct) (__ct) -#define jiffies_to_cputime(__hz) ((cputime_t)(__hz) * (4096000000ULL / HZ)) - -#define cputime64_zero (0ULL) -#define cputime64_add(__a, __b) ((__a) + (__b)) -#define cputime_to_cputime64(__ct) (__ct) - -static inline u64 -cputime64_to_jiffies64(cputime64_t cputime) -{ - do_div(cputime, 4096000000ULL / HZ); - return cputime; +static inline u64 cputime64_to_jiffies64(cputime64_t cputime) +{ + unsigned long long jif = (__force unsigned long long) cputime; + do_div(jif, 4096000000ULL / HZ); + return jif; +} + +static inline cputime64_t jiffies64_to_cputime64(const u64 jif) +{ + return (__force cputime64_t)(jif * (4096000000ULL / HZ)); } /* * Convert cputime to microseconds and back. */ -static inline unsigned int -cputime_to_usecs(const cputime_t cputime) +static inline unsigned int cputime_to_usecs(const cputime_t cputime) { - return cputime_div(cputime, 4096); + return (__force unsigned long long) cputime >> 12; } -static inline cputime_t -usecs_to_cputime(const unsigned int m) +static inline cputime_t usecs_to_cputime(const unsigned int m) { - return (cputime_t) m * 4096; + return (__force cputime_t)(m * 4096ULL); } /* * Convert cputime to milliseconds and back. */ -static inline unsigned int -cputime_to_secs(const cputime_t cputime) +static inline unsigned int cputime_to_secs(const cputime_t cputime) { - return __div(cputime, 2048000000) >> 1; + return __div((__force unsigned long long) cputime, 2048000000) >> 1; } -static inline cputime_t -secs_to_cputime(const unsigned int s) +static inline cputime_t secs_to_cputime(const unsigned int s) { - return (cputime_t) s * 4096000000ULL; + return (__force cputime_t)(s * 4096000000ULL); } /* * Convert cputime to timespec and back. */ -static inline cputime_t -timespec_to_cputime(const struct timespec *value) +static inline cputime_t timespec_to_cputime(const struct timespec *value) { - return value->tv_nsec * 4096 / 1000 + (u64) value->tv_sec * 4096000000ULL; + unsigned long long ret = value->tv_sec * 4096000000ULL; + return (__force cputime_t)(ret + value->tv_nsec * 4096 / 1000); } -static inline void -cputime_to_timespec(const cputime_t cputime, struct timespec *value) +static inline void cputime_to_timespec(const cputime_t cputime, + struct timespec *value) { + unsigned long long __cputime = (__force unsigned long long) cputime; #ifndef __s390x__ register_pair rp; - rp.pair = cputime >> 1; + rp.pair = __cputime >> 1; asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL)); value->tv_nsec = rp.subreg.even * 1000 / 4096; value->tv_sec = rp.subreg.odd; #else - value->tv_nsec = (cputime % 4096000000ULL) * 1000 / 4096; - value->tv_sec = cputime / 4096000000ULL; + value->tv_nsec = (__cputime % 4096000000ULL) * 1000 / 4096; + value->tv_sec = __cputime / 4096000000ULL; #endif } @@ -132,50 +116,52 @@ cputime_to_timespec(const cputime_t cputime, struct timespec *value) * Since cputime and timeval have the same resolution (microseconds) * this is easy. */ -static inline cputime_t -timeval_to_cputime(const struct timeval *value) +static inline cputime_t timeval_to_cputime(const struct timeval *value) { - return value->tv_usec * 4096 + (u64) value->tv_sec * 4096000000ULL; + unsigned long long ret = value->tv_sec * 4096000000ULL; + return (__force cputime_t)(ret + value->tv_usec * 4096ULL); } -static inline void -cputime_to_timeval(const cputime_t cputime, struct timeval *value) +static inline void cputime_to_timeval(const cputime_t cputime, + struct timeval *value) { + unsigned long long __cputime = (__force unsigned long long) cputime; #ifndef __s390x__ register_pair rp; - rp.pair = cputime >> 1; + rp.pair = __cputime >> 1; asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL)); value->tv_usec = rp.subreg.even / 4096; value->tv_sec = rp.subreg.odd; #else - value->tv_usec = (cputime % 4096000000ULL) / 4096; - value->tv_sec = cputime / 4096000000ULL; + value->tv_usec = (__cputime % 4096000000ULL) / 4096; + value->tv_sec = __cputime / 4096000000ULL; #endif } /* * Convert cputime to clock and back. */ -static inline clock_t -cputime_to_clock_t(cputime_t cputime) +static inline clock_t cputime_to_clock_t(cputime_t cputime) { - return cputime_div(cputime, 4096000000ULL / USER_HZ); + unsigned long long clock = (__force unsigned long long) cputime; + do_div(clock, 4096000000ULL / USER_HZ); + return clock; } -static inline cputime_t -clock_t_to_cputime(unsigned long x) +static inline cputime_t clock_t_to_cputime(unsigned long x) { - return (cputime_t) x * (4096000000ULL / USER_HZ); + return (__force cputime_t)(x * (4096000000ULL / USER_HZ)); } /* * Convert cputime64 to clock. */ -static inline clock_t -cputime64_to_clock_t(cputime64_t cputime) +static inline clock_t cputime64_to_clock_t(cputime64_t cputime) { - return cputime_div(cputime, 4096000000ULL / USER_HZ); + unsigned long long clock = (__force unsigned long long) cputime; + do_div(clock, 4096000000ULL / USER_HZ); + return clock; } struct s390_idle_data { diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index c97b468ee9f..7f31a031c0b 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -103,15 +103,14 @@ static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu, cputime64_t busy_time; cur_wall_time = jiffies64_to_cputime64(get_jiffies_64()); - busy_time = cputime64_add(kstat_cpu(cpu).cpustat.user, - kstat_cpu(cpu).cpustat.system); - - busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.irq); - busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.softirq); - busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.steal); - busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.nice); - - idle_time = cputime64_sub(cur_wall_time, busy_time); + busy_time = kstat_cpu(cpu).cpustat.user; + busy_time += kstat_cpu(cpu).cpustat.system; + busy_time += kstat_cpu(cpu).cpustat.irq; + busy_time += kstat_cpu(cpu).cpustat.softirq; + busy_time += kstat_cpu(cpu).cpustat.steal; + busy_time += kstat_cpu(cpu).cpustat.nice; + + idle_time = cur_wall_time - busy_time; if (wall) *wall = (cputime64_t)jiffies_to_usecs(cur_wall_time); @@ -353,20 +352,20 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info) cur_idle_time = get_cpu_idle_time(j, &cur_wall_time); - wall_time = (unsigned int) cputime64_sub(cur_wall_time, - j_dbs_info->prev_cpu_wall); + wall_time = (unsigned int) + (cur_wall_time - j_dbs_info->prev_cpu_wall); j_dbs_info->prev_cpu_wall = cur_wall_time; - idle_time = (unsigned int) cputime64_sub(cur_idle_time, - j_dbs_info->prev_cpu_idle); + idle_time = (unsigned int) + (cur_idle_time - j_dbs_info->prev_cpu_idle); j_dbs_info->prev_cpu_idle = cur_idle_time; if (dbs_tuners_ins.ignore_nice) { cputime64_t cur_nice; unsigned long cur_nice_jiffies; - cur_nice = cputime64_sub(kstat_cpu(j).cpustat.nice, - j_dbs_info->prev_cpu_nice); + cur_nice = kstat_cpu(j).cpustat.nice - + j_dbs_info->prev_cpu_nice; /* * Assumption: nice time between sampling periods will * be less than 2^32 jiffies for 32 bit sys diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index fa8af4ebb1d..07cffe2f6cf 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -127,15 +127,14 @@ static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu, cputime64_t busy_time; cur_wall_time = jiffies64_to_cputime64(get_jiffies_64()); - busy_time = cputime64_add(kstat_cpu(cpu).cpustat.user, - kstat_cpu(cpu).cpustat.system); - - busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.irq); - busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.softirq); - busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.steal); - busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.nice); - - idle_time = cputime64_sub(cur_wall_time, busy_time); + busy_time = kstat_cpu(cpu).cpustat.user; + busy_time += kstat_cpu(cpu).cpustat.system; + busy_time += kstat_cpu(cpu).cpustat.irq; + busy_time += kstat_cpu(cpu).cpustat.softirq; + busy_time += kstat_cpu(cpu).cpustat.steal; + busy_time += kstat_cpu(cpu).cpustat.nice; + + idle_time = cur_wall_time - busy_time; if (wall) *wall = (cputime64_t)jiffies_to_usecs(cur_wall_time); @@ -442,24 +441,24 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info) cur_idle_time = get_cpu_idle_time(j, &cur_wall_time); cur_iowait_time = get_cpu_iowait_time(j, &cur_wall_time); - wall_time = (unsigned int) cputime64_sub(cur_wall_time, - j_dbs_info->prev_cpu_wall); + wall_time = (unsigned int) + (cur_wall_time - j_dbs_info->prev_cpu_wall); j_dbs_info->prev_cpu_wall = cur_wall_time; - idle_time = (unsigned int) cputime64_sub(cur_idle_time, - j_dbs_info->prev_cpu_idle); + idle_time = (unsigned int) + (cur_idle_time - j_dbs_info->prev_cpu_idle); j_dbs_info->prev_cpu_idle = cur_idle_time; - iowait_time = (unsigned int) cputime64_sub(cur_iowait_time, - j_dbs_info->prev_cpu_iowait); + iowait_time = (unsigned int) + (cur_iowait_time - j_dbs_info->prev_cpu_iowait); j_dbs_info->prev_cpu_iowait = cur_iowait_time; if (dbs_tuners_ins.ignore_nice) { cputime64_t cur_nice; unsigned long cur_nice_jiffies; - cur_nice = cputime64_sub(kstat_cpu(j).cpustat.nice, - j_dbs_info->prev_cpu_nice); + cur_nice = kstat_cpu(j).cpustat.nice - + j_dbs_info->prev_cpu_nice; /* * Assumption: nice time between sampling periods will * be less than 2^32 jiffies for 32 bit sys diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index c5072a91e84..2a508edd768 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -61,9 +61,8 @@ static int cpufreq_stats_update(unsigned int cpu) spin_lock(&cpufreq_stats_lock); stat = per_cpu(cpufreq_stats_table, cpu); if (stat->time_in_state) - stat->time_in_state[stat->last_index] = - cputime64_add(stat->time_in_state[stat->last_index], - cputime_sub(cur_time, stat->last_time)); + stat->time_in_state[stat->last_index] += + cur_time - stat->last_time; stat->last_time = cur_time; spin_unlock(&cpufreq_stats_lock); return 0; diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c index 2637c139777..909908ebf16 100644 --- a/drivers/macintosh/rack-meter.c +++ b/drivers/macintosh/rack-meter.c @@ -83,11 +83,10 @@ static inline cputime64_t get_cpu_idle_time(unsigned int cpu) { cputime64_t retval; - retval = cputime64_add(kstat_cpu(cpu).cpustat.idle, - kstat_cpu(cpu).cpustat.iowait); + retval = kstat_cpu(cpu).cpustat.idle + kstat_cpu(cpu).cpustat.iowait; if (rackmeter_ignore_nice) - retval = cputime64_add(retval, kstat_cpu(cpu).cpustat.nice); + retval += kstat_cpu(cpu).cpustat.nice; return retval; } @@ -220,13 +219,11 @@ static void rackmeter_do_timer(struct work_struct *work) int i, offset, load, cumm, pause; cur_jiffies = jiffies64_to_cputime64(get_jiffies_64()); - total_ticks = (unsigned int)cputime64_sub(cur_jiffies, - rcpu->prev_wall); + total_ticks = (unsigned int) (cur_jiffies - rcpu->prev_wall); rcpu->prev_wall = cur_jiffies; total_idle_ticks = get_cpu_idle_time(cpu); - idle_ticks = (unsigned int) cputime64_sub(total_idle_ticks, - rcpu->prev_idle); + idle_ticks = (unsigned int) (total_idle_ticks - rcpu->prev_idle); rcpu->prev_idle = total_idle_ticks; /* We do a very dumb calculation to update the LEDs for now, diff --git a/fs/proc/array.c b/fs/proc/array.c index 3a1dafd228d..8c344f037bd 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -394,8 +394,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = cputime_zero; - cgtime = gtime = cputime_zero; + cutime = cstime = utime = stime = 0; + cgtime = gtime = 0; if (lock_task_sighand(task, &flags)) { struct signal_struct *sig = task->signal; @@ -423,14 +423,14 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, do { min_flt += t->min_flt; maj_flt += t->maj_flt; - gtime = cputime_add(gtime, t->gtime); + gtime += t->gtime; t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; thread_group_times(task, &utime, &stime); - gtime = cputime_add(gtime, sig->gtime); + gtime += sig->gtime; } sid = task_session_nr_ns(task, ns); diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 2a30d67dd6b..714d5d131e7 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -30,7 +30,7 @@ static cputime64_t get_idle_time(int cpu) if (idle_time == -1ULL) { /* !NO_HZ so we can rely on cpustat.idle */ idle = kstat_cpu(cpu).cpustat.idle; - idle = cputime64_add(idle, arch_idle_time(cpu)); + idle += arch_idle_time(cpu); } else idle = nsecs_to_jiffies64(1000 * idle_time); @@ -63,23 +63,22 @@ static int show_stat(struct seq_file *p, void *v) struct timespec boottime; user = nice = system = idle = iowait = - irq = softirq = steal = cputime64_zero; - guest = guest_nice = cputime64_zero; + irq = softirq = steal = 0; + guest = guest_nice = 0; getboottime(&boottime); jif = boottime.tv_sec; for_each_possible_cpu(i) { - user = cputime64_add(user, kstat_cpu(i).cpustat.user); - nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice); - system = cputime64_add(system, kstat_cpu(i).cpustat.system); - idle = cputime64_add(idle, get_idle_time(i)); - iowait = cputime64_add(iowait, get_iowait_time(i)); - irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq); - softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); - steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); - guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); - guest_nice = cputime64_add(guest_nice, - kstat_cpu(i).cpustat.guest_nice); + user += kstat_cpu(i).cpustat.user; + nice += kstat_cpu(i).cpustat.nice; + system += kstat_cpu(i).cpustat.system; + idle += get_idle_time(i); + iowait += get_iowait_time(i); + irq += kstat_cpu(i).cpustat.irq; + softirq += kstat_cpu(i).cpustat.softirq; + steal += kstat_cpu(i).cpustat.steal; + guest += kstat_cpu(i).cpustat.guest; + guest_nice += kstat_cpu(i).cpustat.guest_nice; sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 766b1d45605..ac5243657da 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -12,10 +12,10 @@ static int uptime_proc_show(struct seq_file *m, void *v) struct timespec uptime; struct timespec idle; int i; - cputime_t idletime = cputime_zero; + cputime_t idletime = 0; for_each_possible_cpu(i) - idletime = cputime64_add(idletime, kstat_cpu(i).cpustat.idle); + idletime += kstat_cpu(i).cpustat.idle; do_posix_clock_monotonic_gettime(&uptime); monotonic_to_bootbased(&uptime); diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h index 62ce6823c0f..77202e2c9fc 100644 --- a/include/asm-generic/cputime.h +++ b/include/asm-generic/cputime.h @@ -4,70 +4,64 @@ #include #include -typedef unsigned long cputime_t; +typedef unsigned long __nocast cputime_t; -#define cputime_zero (0UL) #define cputime_one_jiffy jiffies_to_cputime(1) -#define cputime_max ((~0UL >> 1) - 1) -#define cputime_add(__a, __b) ((__a) + (__b)) -#define cputime_sub(__a, __b) ((__a) - (__b)) -#define cputime_div(__a, __n) ((__a) / (__n)) -#define cputime_halve(__a) ((__a) >> 1) -#define cputime_eq(__a, __b) ((__a) == (__b)) -#define cputime_gt(__a, __b) ((__a) > (__b)) -#define cputime_ge(__a, __b) ((__a) >= (__b)) -#define cputime_lt(__a, __b) ((__a) < (__b)) -#define cputime_le(__a, __b) ((__a) <= (__b)) -#define cputime_to_jiffies(__ct) (__ct) +#define cputime_to_jiffies(__ct) (__force unsigned long)(__ct) #define cputime_to_scaled(__ct) (__ct) -#define jiffies_to_cputime(__hz) (__hz) +#define jiffies_to_cputime(__hz) (__force cputime_t)(__hz) -typedef u64 cputime64_t; +typedef u64 __nocast cputime64_t; -#define cputime64_zero (0ULL) -#define cputime64_add(__a, __b) ((__a) + (__b)) -#define cputime64_sub(__a, __b) ((__a) - (__b)) -#define cputime64_to_jiffies64(__ct) (__ct) -#define jiffies64_to_cputime64(__jif) (__jif) -#define cputime_to_cputime64(__ct) ((u64) __ct) -#define cputime64_gt(__a, __b) ((__a) > (__b)) +#define cputime64_to_jiffies64(__ct) (__force u64)(__ct) +#define jiffies64_to_cputime64(__jif) (__force cputime64_t)(__jif) -#define nsecs_to_cputime64(__ct) nsecs_to_jiffies64(__ct) +#define nsecs_to_cputime64(__ct) \ + jiffies64_to_cputime64(nsecs_to_jiffies64(__ct)) /* * Convert cputime to microseconds and back. */ -#define cputime_to_usecs(__ct) jiffies_to_usecs(__ct) -#define usecs_to_cputime(__msecs) usecs_to_jiffies(__msecs) +#define cputime_to_usecs(__ct) \ + jiffies_to_usecs(cputime_to_jiffies(__ct)); +#define usecs_to_cputime(__msecs) \ + jiffies_to_cputime(usecs_to_jiffies(__msecs)); /* * Convert cputime to seconds and back. */ -#define cputime_to_secs(jif) ((jif) / HZ) -#define secs_to_cputime(sec) ((sec) * HZ) +#define cputime_to_secs(jif) (cputime_to_jiffies(jif) / HZ) +#define secs_to_cputime(sec) jiffies_to_cputime((sec) * HZ) /* * Convert cputime to timespec and back. */ -#define timespec_to_cputime(__val) timespec_to_jiffies(__val) -#define cputime_to_timespec(__ct,__val) jiffies_to_timespec(__ct,__val) +#define timespec_to_cputime(__val) \ + jiffies_to_cputime(timespec_to_jiffies(__val)) +#define cputime_to_timespec(__ct,__val) \ + jiffies_to_timespec(cputime_to_jiffies(__ct),__val) /* * Convert cputime to timeval and back. */ -#define timeval_to_cputime(__val) timeval_to_jiffies(__val) -#define cputime_to_timeval(__ct,__val) jiffies_to_timeval(__ct,__val) +#define timeval_to_cputime(__val) \ + jiffies_to_cputime(timeval_to_jiffies(__val)) +#define cputime_to_timeval(__ct,__val) \ + jiffies_to_timeval(cputime_to_jiffies(__ct),__val) /* * Convert cputime to clock and back. */ -#define cputime_to_clock_t(__ct) jiffies_to_clock_t(__ct) -#define clock_t_to_cputime(__x) clock_t_to_jiffies(__x) +#define cputime_to_clock_t(__ct) \ + jiffies_to_clock_t(cputime_to_jiffies(__ct)) +#define clock_t_to_cputime(__x) \ + jiffies_to_cputime(clock_t_to_jiffies(__x)) /* * Convert cputime64 to clock. */ -#define cputime64_to_clock_t(__ct) jiffies_64_to_clock_t(__ct) +#define cputime64_to_clock_t(__ct) \ + jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct)) #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c4f3e9b9bc..5649032d73f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -483,8 +483,8 @@ struct task_cputime { #define INIT_CPUTIME \ (struct task_cputime) { \ - .utime = cputime_zero, \ - .stime = cputime_zero, \ + .utime = 0, \ + .stime = 0, \ .sum_exec_runtime = 0, \ } diff --git a/kernel/acct.c b/kernel/acct.c index fa7eb3de2dd..203dfead2e0 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -613,8 +613,8 @@ void acct_collect(long exitcode, int group_dead) pacct->ac_flag |= ACORE; if (current->flags & PF_SIGNALED) pacct->ac_flag |= AXSIG; - pacct->ac_utime = cputime_add(pacct->ac_utime, current->utime); - pacct->ac_stime = cputime_add(pacct->ac_stime, current->stime); + pacct->ac_utime += current->utime; + pacct->ac_stime += current->stime; pacct->ac_minflt += current->min_flt; pacct->ac_majflt += current->maj_flt; spin_unlock_irq(¤t->sighand->siglock); diff --git a/kernel/cpu.c b/kernel/cpu.c index 563f1360947..3f8ee8a138c 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -178,8 +178,7 @@ static inline void check_for_tasks(int cpu) write_lock_irq(&tasklist_lock); for_each_process(p) { if (task_cpu(p) == cpu && p->state == TASK_RUNNING && - (!cputime_eq(p->utime, cputime_zero) || - !cputime_eq(p->stime, cputime_zero))) + (p->utime || p->stime)) printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d " "(state = %ld, flags = %x)\n", p->comm, task_pid_nr(p), cpu, diff --git a/kernel/exit.c b/kernel/exit.c index d0b7d988f87..5e0d1f4c696 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -121,9 +121,9 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, tsk->utime); - sig->stime = cputime_add(sig->stime, tsk->stime); - sig->gtime = cputime_add(sig->gtime, tsk->gtime); + sig->utime += tsk->utime; + sig->stime += tsk->stime; + sig->gtime += tsk->gtime; sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; @@ -1255,19 +1255,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) spin_lock_irq(&p->real_parent->sighand->siglock); psig = p->real_parent->signal; sig = p->signal; - psig->cutime = - cputime_add(psig->cutime, - cputime_add(tgutime, - sig->cutime)); - psig->cstime = - cputime_add(psig->cstime, - cputime_add(tgstime, - sig->cstime)); - psig->cgtime = - cputime_add(psig->cgtime, - cputime_add(p->gtime, - cputime_add(sig->gtime, - sig->cgtime))); + psig->cutime += tgutime + sig->cutime; + psig->cstime += tgstime + sig->cstime; + psig->cgtime += p->gtime + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += diff --git a/kernel/fork.c b/kernel/fork.c index da4a6a10d08..b058c5820ec 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1023,8 +1023,8 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p) */ static void posix_cpu_timers_init(struct task_struct *tsk) { - tsk->cputime_expires.prof_exp = cputime_zero; - tsk->cputime_expires.virt_exp = cputime_zero; + tsk->cputime_expires.prof_exp = 0; + tsk->cputime_expires.virt_exp = 0; tsk->cputime_expires.sched_exp = 0; INIT_LIST_HEAD(&tsk->cpu_timers[0]); INIT_LIST_HEAD(&tsk->cpu_timers[1]); @@ -1132,14 +1132,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, init_sigpending(&p->pending); - p->utime = cputime_zero; - p->stime = cputime_zero; - p->gtime = cputime_zero; - p->utimescaled = cputime_zero; - p->stimescaled = cputime_zero; + p->utime = p->stime = p->gtime = 0; + p->utimescaled = p->stimescaled = 0; #ifndef CONFIG_VIRT_CPU_ACCOUNTING - p->prev_utime = cputime_zero; - p->prev_stime = cputime_zero; + p->prev_utime = p->prev_stime = 0; #endif #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); diff --git a/kernel/itimer.c b/kernel/itimer.c index d802883153d..22000c3db0d 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -52,22 +52,22 @@ static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, cval = it->expires; cinterval = it->incr; - if (!cputime_eq(cval, cputime_zero)) { + if (cval) { struct task_cputime cputime; cputime_t t; thread_group_cputimer(tsk, &cputime); if (clock_id == CPUCLOCK_PROF) - t = cputime_add(cputime.utime, cputime.stime); + t = cputime.utime + cputime.stime; else /* CPUCLOCK_VIRT */ t = cputime.utime; - if (cputime_le(cval, t)) + if (cval < t) /* about to fire */ cval = cputime_one_jiffy; else - cval = cputime_sub(cval, t); + cval = cval - t; } spin_unlock_irq(&tsk->sighand->siglock); @@ -161,10 +161,9 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, cval = it->expires; cinterval = it->incr; - if (!cputime_eq(cval, cputime_zero) || - !cputime_eq(nval, cputime_zero)) { - if (cputime_gt(nval, cputime_zero)) - nval = cputime_add(nval, cputime_one_jiffy); + if (cval || nval) { + if (nval > 0) + nval += cputime_one_jiffy; set_process_cpu_timer(tsk, clock_id, &nval, &cval); } it->expires = nval; diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index e7cb76dc18f..125cb67daa2 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -78,7 +78,7 @@ static inline int cpu_time_before(const clockid_t which_clock, if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { return now.sched < then.sched; } else { - return cputime_lt(now.cpu, then.cpu); + return now.cpu < then.cpu; } } static inline void cpu_time_add(const clockid_t which_clock, @@ -88,7 +88,7 @@ static inline void cpu_time_add(const clockid_t which_clock, if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { acc->sched += val.sched; } else { - acc->cpu = cputime_add(acc->cpu, val.cpu); + acc->cpu += val.cpu; } } static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock, @@ -98,24 +98,11 @@ static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock, if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { a.sched -= b.sched; } else { - a.cpu = cputime_sub(a.cpu, b.cpu); + a.cpu -= b.cpu; } return a; } -/* - * Divide and limit the result to res >= 1 - * - * This is necessary to prevent signal delivery starvation, when the result of - * the division would be rounded down to 0. - */ -static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div) -{ - cputime_t res = cputime_div(time, div); - - return max_t(cputime_t, res, 1); -} - /* * Update expiry time from increment, and increase overrun count, * given the current clock sample. @@ -148,28 +135,26 @@ static void bump_cpu_timer(struct k_itimer *timer, } else { cputime_t delta, incr; - if (cputime_lt(now.cpu, timer->it.cpu.expires.cpu)) + if (now.cpu < timer->it.cpu.expires.cpu) return; incr = timer->it.cpu.incr.cpu; - delta = cputime_sub(cputime_add(now.cpu, incr), - timer->it.cpu.expires.cpu); + delta = now.cpu + incr - timer->it.cpu.expires.cpu; /* Don't use (incr*2 < delta), incr*2 might overflow. */ - for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++) - incr = cputime_add(incr, incr); - for (; i >= 0; incr = cputime_halve(incr), i--) { - if (cputime_lt(delta, incr)) + for (i = 0; incr < delta - incr; i++) + incr += incr; + for (; i >= 0; incr = incr >> 1, i--) { + if (delta < incr) continue; - timer->it.cpu.expires.cpu = - cputime_add(timer->it.cpu.expires.cpu, incr); + timer->it.cpu.expires.cpu += incr; timer->it_overrun += 1 << i; - delta = cputime_sub(delta, incr); + delta -= incr; } } } static inline cputime_t prof_ticks(struct task_struct *p) { - return cputime_add(p->utime, p->stime); + return p->utime + p->stime; } static inline cputime_t virt_ticks(struct task_struct *p) { @@ -248,8 +233,8 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) t = tsk; do { - times->utime = cputime_add(times->utime, t->utime); - times->stime = cputime_add(times->stime, t->stime); + times->utime += t->utime; + times->stime += t->stime; times->sum_exec_runtime += task_sched_runtime(t); } while_each_thread(tsk, t); out: @@ -258,10 +243,10 @@ out: static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b) { - if (cputime_gt(b->utime, a->utime)) + if (b->utime > a->utime) a->utime = b->utime; - if (cputime_gt(b->stime, a->stime)) + if (b->stime > a->stime) a->stime = b->stime; if (b->sum_exec_runtime > a->sum_exec_runtime) @@ -306,7 +291,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock, return -EINVAL; case CPUCLOCK_PROF: thread_group_cputime(p, &cputime); - cpu->cpu = cputime_add(cputime.utime, cputime.stime); + cpu->cpu = cputime.utime + cputime.stime; break; case CPUCLOCK_VIRT: thread_group_cputime(p, &cputime); @@ -470,26 +455,24 @@ static void cleanup_timers(struct list_head *head, unsigned long long sum_exec_runtime) { struct cpu_timer_list *timer, *next; - cputime_t ptime = cputime_add(utime, stime); + cputime_t ptime = utime + stime; list_for_each_entry_safe(timer, next, head, entry) { list_del_init(&timer->entry); - if (cputime_lt(timer->expires.cpu, ptime)) { - timer->expires.cpu = cputime_zero; + if (timer->expires.cpu < ptime) { + timer->expires.cpu = 0; } else { - timer->expires.cpu = cputime_sub(timer->expires.cpu, - ptime); + timer->expires.cpu -= ptime; } } ++head; list_for_each_entry_safe(timer, next, head, entry) { list_del_init(&timer->entry); - if (cputime_lt(timer->expires.cpu, utime)) { - timer->expires.cpu = cputime_zero; + if (timer->expires.cpu < utime) { + timer->expires.cpu = 0; } else { - timer->expires.cpu = cputime_sub(timer->expires.cpu, - utime); + timer->expires.cpu -= utime; } } @@ -520,8 +503,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk) struct signal_struct *const sig = tsk->signal; cleanup_timers(tsk->signal->cpu_timers, - cputime_add(tsk->utime, sig->utime), - cputime_add(tsk->stime, sig->stime), + tsk->utime + sig->utime, tsk->stime + sig->stime, tsk->se.sum_exec_runtime + sig->sum_sched_runtime); } @@ -540,8 +522,7 @@ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) static inline int expires_gt(cputime_t expires, cputime_t new_exp) { - return cputime_eq(expires, cputime_zero) || - cputime_gt(expires, new_exp); + return expires == 0 || expires > new_exp; } /* @@ -651,7 +632,7 @@ static int cpu_timer_sample_group(const clockid_t which_clock, default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = cputime_add(cputime.utime, cputime.stime); + cpu->cpu = cputime.utime + cputime.stime; break; case CPUCLOCK_VIRT: cpu->cpu = cputime.utime; @@ -918,12 +899,12 @@ static void check_thread_timers(struct task_struct *tsk, unsigned long soft; maxfire = 20; - tsk->cputime_expires.prof_exp = cputime_zero; + tsk->cputime_expires.prof_exp = 0; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); - if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) { + if (!--maxfire || prof_ticks(tsk) < t->expires.cpu) { tsk->cputime_expires.prof_exp = t->expires.cpu; break; } @@ -933,12 +914,12 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->cputime_expires.virt_exp = cputime_zero; + tsk->cputime_expires.virt_exp = 0; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); - if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) { + if (!--maxfire || virt_ticks(tsk) < t->expires.cpu) { tsk->cputime_expires.virt_exp = t->expires.cpu; break; } @@ -1009,20 +990,19 @@ static u32 onecputick; static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, cputime_t *expires, cputime_t cur_time, int signo) { - if (cputime_eq(it->expires, cputime_zero)) + if (!it->expires) return; - if (cputime_ge(cur_time, it->expires)) { - if (!cputime_eq(it->incr, cputime_zero)) { - it->expires = cputime_add(it->expires, it->incr); + if (cur_time >= it->expires) { + if (it->incr) { + it->expires += it->incr; it->error += it->incr_error; if (it->error >= onecputick) { - it->expires = cputime_sub(it->expires, - cputime_one_jiffy); + it->expires -= cputime_one_jiffy; it->error -= onecputick; } } else { - it->expires = cputime_zero; + it->expires = 0; } trace_itimer_expire(signo == SIGPROF ? @@ -1031,9 +1011,7 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, __group_send_sig_info(signo, SEND_SIG_PRIV, tsk); } - if (!cputime_eq(it->expires, cputime_zero) && - (cputime_eq(*expires, cputime_zero) || - cputime_lt(it->expires, *expires))) { + if (it->expires && (!*expires || it->expires < *expires)) { *expires = it->expires; } } @@ -1048,9 +1026,7 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, */ static inline int task_cputime_zero(const struct task_cputime *cputime) { - if (cputime_eq(cputime->utime, cputime_zero) && - cputime_eq(cputime->stime, cputime_zero) && - cputime->sum_exec_runtime == 0) + if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime) return 1; return 0; } @@ -1076,15 +1052,15 @@ static void check_process_timers(struct task_struct *tsk, */ thread_group_cputimer(tsk, &cputime); utime = cputime.utime; - ptime = cputime_add(utime, cputime.stime); + ptime = utime + cputime.stime; sum_sched_runtime = cputime.sum_exec_runtime; maxfire = 20; - prof_expires = cputime_zero; + prof_expires = 0; while (!list_empty(timers)) { struct cpu_timer_list *tl = list_first_entry(timers, struct cpu_timer_list, entry); - if (!--maxfire || cputime_lt(ptime, tl->expires.cpu)) { + if (!--maxfire || ptime < tl->expires.cpu) { prof_expires = tl->expires.cpu; break; } @@ -1094,12 +1070,12 @@ static void check_process_timers(struct task_struct *tsk, ++timers; maxfire = 20; - virt_expires = cputime_zero; + virt_expires = 0; while (!list_empty(timers)) { struct cpu_timer_list *tl = list_first_entry(timers, struct cpu_timer_list, entry); - if (!--maxfire || cputime_lt(utime, tl->expires.cpu)) { + if (!--maxfire || utime < tl->expires.cpu) { virt_expires = tl->expires.cpu; break; } @@ -1154,8 +1130,7 @@ static void check_process_timers(struct task_struct *tsk, } } x = secs_to_cputime(soft); - if (cputime_eq(prof_expires, cputime_zero) || - cputime_lt(x, prof_expires)) { + if (!prof_expires || x < prof_expires) { prof_expires = x; } } @@ -1249,12 +1224,9 @@ out: static inline int task_cputime_expired(const struct task_cputime *sample, const struct task_cputime *expires) { - if (!cputime_eq(expires->utime, cputime_zero) && - cputime_ge(sample->utime, expires->utime)) + if (expires->utime && sample->utime >= expires->utime) return 1; - if (!cputime_eq(expires->stime, cputime_zero) && - cputime_ge(cputime_add(sample->utime, sample->stime), - expires->stime)) + if (expires->stime && sample->utime + sample->stime >= expires->stime) return 1; if (expires->sum_exec_runtime != 0 && sample->sum_exec_runtime >= expires->sum_exec_runtime) @@ -1389,18 +1361,18 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, * it to be relative, *newval argument is relative and we update * it to be absolute. */ - if (!cputime_eq(*oldval, cputime_zero)) { - if (cputime_le(*oldval, now.cpu)) { + if (*oldval) { + if (*oldval <= now.cpu) { /* Just about to fire. */ *oldval = cputime_one_jiffy; } else { - *oldval = cputime_sub(*oldval, now.cpu); + *oldval -= now.cpu; } } - if (cputime_eq(*newval, cputime_zero)) + if (!*newval) return; - *newval = cputime_add(*newval, now.cpu); + *newval += now.cpu; } /* diff --git a/kernel/sched.c b/kernel/sched.c index d6b149ccf92..18cad4467e6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2166,7 +2166,7 @@ static int irqtime_account_hi_update(void) local_irq_save(flags); latest_ns = this_cpu_read(cpu_hardirq_time); - if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq)) + if (nsecs_to_cputime64(latest_ns) > cpustat->irq) ret = 1; local_irq_restore(flags); return ret; @@ -2181,7 +2181,7 @@ static int irqtime_account_si_update(void) local_irq_save(flags); latest_ns = this_cpu_read(cpu_softirq_time); - if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq)) + if (nsecs_to_cputime64(latest_ns) > cpustat->softirq) ret = 1; local_irq_restore(flags); return ret; @@ -3868,19 +3868,17 @@ void account_user_time(struct task_struct *p, cputime_t cputime, cputime_t cputime_scaled) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t tmp; /* Add user time to process. */ - p->utime = cputime_add(p->utime, cputime); - p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); + p->utime += cputime; + p->utimescaled += cputime_scaled; account_group_user_time(p, cputime); /* Add user time to cpustat. */ - tmp = cputime_to_cputime64(cputime); if (TASK_NICE(p) > 0) - cpustat->nice = cputime64_add(cpustat->nice, tmp); + cpustat->nice += (__force cputime64_t) cputime; else - cpustat->user = cputime64_add(cpustat->user, tmp); + cpustat->user += (__force cputime64_t) cputime; cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime); /* Account for user time used */ @@ -3896,24 +3894,21 @@ void account_user_time(struct task_struct *p, cputime_t cputime, static void account_guest_time(struct task_struct *p, cputime_t cputime, cputime_t cputime_scaled) { - cputime64_t tmp; struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - tmp = cputime_to_cputime64(cputime); - /* Add guest time to process. */ - p->utime = cputime_add(p->utime, cputime); - p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); + p->utime += cputime; + p->utimescaled += cputime_scaled; account_group_user_time(p, cputime); - p->gtime = cputime_add(p->gtime, cputime); + p->gtime += cputime; /* Add guest time to cpustat. */ if (TASK_NICE(p) > 0) { - cpustat->nice = cputime64_add(cpustat->nice, tmp); - cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp); + cpustat->nice += (__force cputime64_t) cputime; + cpustat->guest_nice += (__force cputime64_t) cputime; } else { - cpustat->user = cputime64_add(cpustat->user, tmp); - cpustat->guest = cputime64_add(cpustat->guest, tmp); + cpustat->user += (__force cputime64_t) cputime; + cpustat->guest += (__force cputime64_t) cputime; } } @@ -3928,15 +3923,13 @@ static inline void __account_system_time(struct task_struct *p, cputime_t cputime, cputime_t cputime_scaled, cputime64_t *target_cputime64) { - cputime64_t tmp = cputime_to_cputime64(cputime); - /* Add system time to process. */ - p->stime = cputime_add(p->stime, cputime); - p->stimescaled = cputime_add(p->stimescaled, cputime_scaled); + p->stime += cputime; + p->stimescaled += cputime_scaled; account_group_system_time(p, cputime); /* Add system time to cpustat. */ - *target_cputime64 = cputime64_add(*target_cputime64, tmp); + *target_cputime64 += (__force cputime64_t) cputime; cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime); /* Account for system time used */ @@ -3978,9 +3971,8 @@ void account_system_time(struct task_struct *p, int hardirq_offset, void account_steal_time(cputime_t cputime) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t cputime64 = cputime_to_cputime64(cputime); - cpustat->steal = cputime64_add(cpustat->steal, cputime64); + cpustat->steal += (__force cputime64_t) cputime; } /* @@ -3990,13 +3982,12 @@ void account_steal_time(cputime_t cputime) void account_idle_time(cputime_t cputime) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t cputime64 = cputime_to_cputime64(cputime); struct rq *rq = this_rq(); if (atomic_read(&rq->nr_iowait) > 0) - cpustat->iowait = cputime64_add(cpustat->iowait, cputime64); + cpustat->iowait += (__force cputime64_t) cputime; else - cpustat->idle = cputime64_add(cpustat->idle, cputime64); + cpustat->idle += (__force cputime64_t) cputime; } static __always_inline bool steal_account_process_tick(void) @@ -4046,16 +4037,15 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, struct rq *rq) { cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); - cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; if (steal_account_process_tick()) return; if (irqtime_account_hi_update()) { - cpustat->irq = cputime64_add(cpustat->irq, tmp); + cpustat->irq += (__force cputime64_t) cputime_one_jiffy; } else if (irqtime_account_si_update()) { - cpustat->softirq = cputime64_add(cpustat->softirq, tmp); + cpustat->softirq += (__force cputime64_t) cputime_one_jiffy; } else if (this_cpu_ksoftirqd() == p) { /* * ksoftirqd time do not get accounted in cpu_softirq_time. @@ -4171,7 +4161,7 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); + cputime_t rtime, utime = p->utime, total = utime + p->stime; /* * Use CFS's precise accounting: @@ -4179,11 +4169,11 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) rtime = nsecs_to_cputime(p->se.sum_exec_runtime); if (total) { - u64 temp = rtime; + u64 temp = (__force u64) rtime; - temp *= utime; - do_div(temp, total); - utime = (cputime_t)temp; + temp *= (__force u64) utime; + do_div(temp, (__force u32) total); + utime = (__force cputime_t) temp; } else utime = rtime; @@ -4191,7 +4181,7 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) * Compare with previous values, to keep monotonicity: */ p->prev_utime = max(p->prev_utime, utime); - p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime)); + p->prev_stime = max(p->prev_stime, rtime - p->prev_utime); *ut = p->prev_utime; *st = p->prev_stime; @@ -4208,21 +4198,20 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) thread_group_cputime(p, &cputime); - total = cputime_add(cputime.utime, cputime.stime); + total = cputime.utime + cputime.stime; rtime = nsecs_to_cputime(cputime.sum_exec_runtime); if (total) { - u64 temp = rtime; + u64 temp = (__force u64) rtime; - temp *= cputime.utime; - do_div(temp, total); - utime = (cputime_t)temp; + temp *= (__force u64) cputime.utime; + do_div(temp, (__force u32) total); + utime = (__force cputime_t) temp; } else utime = rtime; sig->prev_utime = max(sig->prev_utime, utime); - sig->prev_stime = max(sig->prev_stime, - cputime_sub(rtime, sig->prev_utime)); + sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime); *ut = sig->prev_utime; *st = sig->prev_stime; @@ -9769,7 +9758,8 @@ static void cpuacct_update_stats(struct task_struct *tsk, ca = task_ca(tsk); do { - __percpu_counter_add(&ca->cpustat[idx], val, batch); + __percpu_counter_add(&ca->cpustat[idx], + (__force s64) val, batch); ca = ca->parent; } while (ca); rcu_read_unlock(); diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 87f9e36ea56..4b71dbef271 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -283,8 +283,7 @@ static inline void account_group_user_time(struct task_struct *tsk, return; raw_spin_lock(&cputimer->lock); - cputimer->cputime.utime = - cputime_add(cputimer->cputime.utime, cputime); + cputimer->cputime.utime += cputime; raw_spin_unlock(&cputimer->lock); } @@ -307,8 +306,7 @@ static inline void account_group_system_time(struct task_struct *tsk, return; raw_spin_lock(&cputimer->lock); - cputimer->cputime.stime = - cputime_add(cputimer->cputime.stime, cputime); + cputimer->cputime.stime += cputime; raw_spin_unlock(&cputimer->lock); } diff --git a/kernel/signal.c b/kernel/signal.c index b3f78d09a10..739ef2bf105 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1629,10 +1629,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig) info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); - info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime, - tsk->signal->utime)); - info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime, - tsk->signal->stime)); + info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime); + info.si_stime = cputime_to_clock_t(tsk->stime + tsk->signal->stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) diff --git a/kernel/sys.c b/kernel/sys.c index 481611fbd07..ddf8155bf3f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1605,7 +1605,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) unsigned long maxrss = 0; memset((char *) r, 0, sizeof *r); - utime = stime = cputime_zero; + utime = stime = 0; if (who == RUSAGE_THREAD) { task_times(current, &utime, &stime); @@ -1635,8 +1635,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) case RUSAGE_SELF: thread_group_times(p, &tgutime, &tgstime); - utime = cputime_add(utime, tgutime); - stime = cputime_add(stime, tgstime); + utime += tgutime; + stime += tgstime; r->ru_nvcsw += p->signal->nvcsw; r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 5bbfac85866..23b4d784ebd 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -127,7 +127,7 @@ void acct_update_integrals(struct task_struct *tsk) local_irq_save(flags); time = tsk->stime + tsk->utime; - dtime = cputime_sub(time, tsk->acct_timexpd); + dtime = time - tsk->acct_timexpd; jiffies_to_timeval(cputime_to_jiffies(dtime), &value); delta = value.tv_sec; delta = delta * USEC_PER_SEC + value.tv_usec; -- cgit v1.2.3-70-g09d2 From 54848d73f9f254631303d6eab9b976855988b266 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Tue, 5 Apr 2011 13:21:19 -0600 Subject: writeback: charge leaked page dirties to active tasks It's a years long problem that a large number of short-lived dirtiers (eg. gcc instances in a fast kernel build) may starve long-run dirtiers (eg. dd) as well as pushing the dirty pages to the global hard limit. The solution is to charge the pages dirtied by the exited gcc to the other random dirtying tasks. It sounds not perfect, however should behave good enough in practice, seeing as that throttled tasks aren't actually running so those that are running are more likely to pick it up and get throttled, therefore promoting an equal spread. Randy: fix compile error: 'dirty_throttle_leaks' undeclared in exit.c Acked-by: Jan Kara Acked-by: Peter Zijlstra Signed-off-by: Randy Dunlap Signed-off-by: Wu Fengguang --- include/linux/writeback.h | 2 ++ kernel/exit.c | 3 +++ mm/page-writeback.c | 27 +++++++++++++++++++++++++++ 3 files changed, 32 insertions(+) (limited to 'kernel/exit.c') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a378c295851..05eaf5e3aad 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -7,6 +7,8 @@ #include #include +DECLARE_PER_CPU(int, dirty_throttle_leaks); + /* * The 1/4 region under the global dirty thresh is for smooth dirty throttling: * diff --git a/kernel/exit.c b/kernel/exit.c index d0b7d988f87..d4aac24cc46 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include @@ -1037,6 +1038,8 @@ NORET_TYPE void do_exit(long code) validate_creds_for_do_exit(tsk); preempt_disable(); + if (tsk->nr_dirtied) + __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 50f08241f98..619c445fc03 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1214,6 +1214,22 @@ void set_page_dirty_balance(struct page *page, int page_mkwrite) static DEFINE_PER_CPU(int, bdp_ratelimits); +/* + * Normal tasks are throttled by + * loop { + * dirty tsk->nr_dirtied_pause pages; + * take a snap in balance_dirty_pages(); + * } + * However there is a worst case. If every task exit immediately when dirtied + * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be + * called to throttle the page dirties. The solution is to save the not yet + * throttled page dirties in dirty_throttle_leaks on task exit and charge them + * randomly into the running tasks. This works well for the above worst case, + * as the new task will pick up and accumulate the old task's leaked dirty + * count and eventually get throttled. + */ +DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; + /** * balance_dirty_pages_ratelimited_nr - balance dirty memory state * @mapping: address_space which was dirtied @@ -1261,6 +1277,17 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, ratelimit = 0; } } + /* + * Pick up the dirtied pages by the exited tasks. This avoids lots of + * short-lived tasks (eg. gcc invocations in a kernel build) escaping + * the dirty throttling and livelock other long-run dirtiers. + */ + p = &__get_cpu_var(dirty_throttle_leaks); + if (*p > 0 && current->nr_dirtied < ratelimit) { + nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); + *p -= nr_pages_dirtied; + current->nr_dirtied += nr_pages_dirtied; + } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) -- cgit v1.2.3-70-g09d2 From 50b8d257486a45cba7b65ca978986ed216bbcc10 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 4 Jan 2012 17:29:02 +0100 Subject: ptrace: partially fix the do_wait(WEXITED) vs EXIT_DEAD->EXIT_ZOMBIE race Test-case: int main(void) { int pid, status; pid = fork(); if (!pid) { for (;;) { if (!fork()) return 0; if (waitpid(-1, &status, 0) < 0) { printf("ERR!! wait: %m\n"); return 0; } } } assert(ptrace(PTRACE_ATTACH, pid, 0,0) == 0); assert(waitpid(-1, NULL, 0) == pid); assert(ptrace(PTRACE_SETOPTIONS, pid, 0, PTRACE_O_TRACEFORK) == 0); do { ptrace(PTRACE_CONT, pid, 0, 0); pid = waitpid(-1, NULL, 0); } while (pid > 0); return 1; } It fails because ->real_parent sees its child in EXIT_DEAD state while the tracer is going to change the state back to EXIT_ZOMBIE in wait_task_zombie(). The offending commit is 823b018e which moved the EXIT_DEAD check, but in fact we should not blame it. The original code was not correct as well because it didn't take ptrace_reparented() into account and because we can't really trust ->ptrace. This patch adds the additional check to close this particular race but it doesn't solve the whole problem. We simply can't rely on ->ptrace in this case, it can be cleared if the tracer is multithreaded by the exiting ->parent. I think we should kill EXIT_DEAD altogether, we should always remove the soon-to-be-reaped child from ->children or at least we should never do the DEAD->ZOMBIE transition. But this is too complex for 3.2. Reported-and-tested-by: Denys Vlasenko Tested-by: Lukasz Michalik Acked-by: Tejun Heo Cc: [3.0+] Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- kernel/exit.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index d0b7d988f87..e6e01b959a0 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1540,8 +1540,15 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, } /* dead body doesn't have much to contribute */ - if (p->exit_state == EXIT_DEAD) + if (unlikely(p->exit_state == EXIT_DEAD)) { + /* + * But do not ignore this task until the tracer does + * wait_task_zombie()->do_notify_parent(). + */ + if (likely(!ptrace) && unlikely(ptrace_reparented(p))) + wo->notask_error = 0; return 0; + } /* slay zombie? */ if (p->exit_state == EXIT_ZOMBIE) { -- cgit v1.2.3-70-g09d2 From 9402c95f34a66e81eba473a2f7267bbae5a1dee2 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 12 Jan 2012 17:17:17 -0800 Subject: treewide: remove useless NORET_TYPE macro and uses It's a very old and now unused prototype marking so just delete it. Neaten panic pointer argument style to keep checkpatch quiet. Signed-off-by: Joe Perches Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Tony Luck Cc: Fenghua Yu Acked-by: Geert Uytterhoeven Acked-by: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Chris Metcalf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/avr32/include/asm/system.h | 2 +- arch/avr32/kernel/traps.c | 2 +- arch/ia64/kernel/machine_kexec.c | 2 +- arch/m68k/amiga/config.c | 2 +- arch/mips/include/asm/ptrace.h | 2 +- arch/mips/kernel/traps.c | 2 +- arch/powerpc/kernel/machine_kexec_32.c | 2 +- arch/powerpc/kernel/machine_kexec_64.c | 6 +++--- arch/s390/kernel/nmi.c | 2 +- arch/tile/kernel/machine_kexec.c | 4 ++-- include/linux/kernel.h | 6 +++--- include/linux/linkage.h | 1 - include/linux/sched.h | 2 +- kernel/exit.c | 6 +++--- kernel/panic.c | 2 +- 15 files changed, 21 insertions(+), 22 deletions(-) (limited to 'kernel/exit.c') diff --git a/arch/avr32/include/asm/system.h b/arch/avr32/include/asm/system.h index 9702c2213e1..62d9ded0163 100644 --- a/arch/avr32/include/asm/system.h +++ b/arch/avr32/include/asm/system.h @@ -169,7 +169,7 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr, #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n)) struct pt_regs; -void NORET_TYPE die(const char *str, struct pt_regs *regs, long err); +void die(const char *str, struct pt_regs *regs, long err); void _exception(long signr, struct pt_regs *regs, int code, unsigned long addr); diff --git a/arch/avr32/kernel/traps.c b/arch/avr32/kernel/traps.c index 7aa25756412..3d760c06f02 100644 --- a/arch/avr32/kernel/traps.c +++ b/arch/avr32/kernel/traps.c @@ -24,7 +24,7 @@ static DEFINE_SPINLOCK(die_lock); -void NORET_TYPE die(const char *str, struct pt_regs *regs, long err) +void die(const char *str, struct pt_regs *regs, long err) { static int die_counter; diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c index 3d3aeef4694..581a16d5e85 100644 --- a/arch/ia64/kernel/machine_kexec.c +++ b/arch/ia64/kernel/machine_kexec.c @@ -27,7 +27,7 @@ #include #include -typedef NORET_TYPE void (*relocate_new_kernel_t)( +typedef void (*relocate_new_kernel_t)( unsigned long indirection_page, unsigned long start_address, struct ia64_boot_param *boot_param, diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c index 82a4bb51d5d..a3b0558328b 100644 --- a/arch/m68k/amiga/config.c +++ b/arch/m68k/amiga/config.c @@ -511,7 +511,7 @@ static unsigned long amiga_gettimeoffset(void) return ticks + offset; } -static NORET_TYPE void amiga_reset(void) +static void amiga_reset(void) ATTRIB_NORET; static void amiga_reset(void) diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index de39b1f343e..3d913259e50 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -144,7 +144,7 @@ extern int ptrace_set_watch_regs(struct task_struct *child, extern asmlinkage void syscall_trace_enter(struct pt_regs *regs); extern asmlinkage void syscall_trace_leave(struct pt_regs *regs); -extern NORET_TYPE void die(const char *, struct pt_regs *) ATTRIB_NORET; +extern void die(const char *, struct pt_regs *) ATTRIB_NORET; static inline void die_if_kernel(const char *str, struct pt_regs *regs) { diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 5c8a49d5505..725e9a5ca96 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -1340,7 +1340,7 @@ void ejtag_exception_handler(struct pt_regs *regs) /* * NMI exception handler. */ -NORET_TYPE void ATTRIB_NORET nmi_exception_handler(struct pt_regs *regs) +void ATTRIB_NORET nmi_exception_handler(struct pt_regs *regs) { bust_spinlocks(1); printk("NMI taken!!!!\n"); diff --git a/arch/powerpc/kernel/machine_kexec_32.c b/arch/powerpc/kernel/machine_kexec_32.c index e63f2e7d2ef..026e7f15394 100644 --- a/arch/powerpc/kernel/machine_kexec_32.c +++ b/arch/powerpc/kernel/machine_kexec_32.c @@ -16,7 +16,7 @@ #include #include -typedef NORET_TYPE void (*relocate_new_kernel_t)( +typedef void (*relocate_new_kernel_t)( unsigned long indirection_page, unsigned long reboot_code_buffer, unsigned long start_address) ATTRIB_NORET; diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 26ccbf77dd4..5fbbf814923 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -307,9 +307,9 @@ static union thread_union kexec_stack __init_task_data = struct paca_struct kexec_paca; /* Our assembly helper, in kexec_stub.S */ -extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start, - void *image, void *control, - void (*clear_all)(void)) ATTRIB_NORET; +extern void kexec_sequence(void *newstack, unsigned long start, + void *image, void *control, + void (*clear_all)(void)) ATTRIB_NORET; /* too late to fail here */ void default_machine_kexec(struct kimage *image) diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index fab88431a06..0fd2e863e11 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -30,7 +30,7 @@ struct mcck_struct { static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck); -static NORET_TYPE void s390_handle_damage(char *msg) +static void s390_handle_damage(char *msg) { smp_send_stop(); disabled_wait((unsigned long) __builtin_return_address(0)); diff --git a/arch/tile/kernel/machine_kexec.c b/arch/tile/kernel/machine_kexec.c index e00d7179989..b0c90705906 100644 --- a/arch/tile/kernel/machine_kexec.c +++ b/arch/tile/kernel/machine_kexec.c @@ -248,10 +248,10 @@ static void setup_quasi_va_is_pa(void) } -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { void *reboot_code_buffer; - NORET_TYPE void (*rnk)(unsigned long, void *, unsigned long) + void (*rnk)(unsigned long, void *, unsigned long) ATTRIB_NORET; /* Mask all interrupts before starting to reboot. */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 60934395e36..aaf1753dd2b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -185,16 +185,16 @@ static inline void might_fault(void) extern struct atomic_notifier_head panic_notifier_list; extern long (*panic_blink)(int state); -NORET_TYPE __printf(1, 2) +__printf(1, 2) void panic(const char *fmt, ...) ATTRIB_NORET __cold; extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); extern int oops_may_print(void); -NORET_TYPE void do_exit(long error_code) +void do_exit(long error_code) ATTRIB_NORET; -NORET_TYPE void complete_and_exit(struct completion *, long) +void complete_and_exit(struct completion *, long) ATTRIB_NORET; /* Internal, do not use. */ diff --git a/include/linux/linkage.h b/include/linux/linkage.h index c75074cb8ad..6a8f252e49e 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -88,7 +88,6 @@ #endif -#define NORET_TYPE /**/ #define ATTRIB_NORET __attribute__((noreturn)) #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 21cd0303af5..4032ec1cf83 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2275,7 +2275,7 @@ extern void __cleanup_sighand(struct sighand_struct *); extern void exit_itimers(struct signal_struct *); extern void flush_itimer_signals(void); -extern NORET_TYPE void do_group_exit(int); +extern void do_group_exit(int); extern void daemonize(const char *, ...); extern int allow_signal(int); diff --git a/kernel/exit.c b/kernel/exit.c index 94ed6e20bb5..c44738267be 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -887,7 +887,7 @@ static void check_stack_usage(void) static inline void check_stack_usage(void) {} #endif -NORET_TYPE void do_exit(long code) +void do_exit(long code) { struct task_struct *tsk = current; int group_dead; @@ -1051,7 +1051,7 @@ NORET_TYPE void do_exit(long code) EXPORT_SYMBOL_GPL(do_exit); -NORET_TYPE void complete_and_exit(struct completion *comp, long code) +void complete_and_exit(struct completion *comp, long code) { if (comp) complete(comp); @@ -1070,7 +1070,7 @@ SYSCALL_DEFINE1(exit, int, error_code) * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ -NORET_TYPE void +void do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; diff --git a/kernel/panic.c b/kernel/panic.c index 3458469eb7c..6fd09ed6fd9 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -57,7 +57,7 @@ EXPORT_SYMBOL(panic_blink); * * This function never returns. */ -NORET_TYPE void panic(const char * fmt, ...) +void panic(const char *fmt, ...) { static char buf[1024]; va_list args; -- cgit v1.2.3-70-g09d2 From a4ff8dba7d8ce5ceb43fb27df66292251cc73bdc Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 3 Jan 2012 14:23:07 -0500 Subject: audit: inline audit_free to simplify the look of generic code make the conditional a static inline instead of doing it in generic code. Signed-off-by: Eric Paris --- include/linux/audit.h | 7 ++++++- kernel/auditsc.c | 2 +- kernel/exit.c | 3 +-- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'kernel/exit.c') diff --git a/include/linux/audit.h b/include/linux/audit.h index 4f1efe3e861..8eb8bda749b 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -417,7 +417,7 @@ extern int audit_classify_arch(int arch); /* Public API */ extern void audit_finish_fork(struct task_struct *child); extern int audit_alloc(struct task_struct *task); -extern void audit_free(struct task_struct *task); +extern void __audit_free(struct task_struct *task); extern void __audit_syscall_entry(int arch, int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); @@ -435,6 +435,11 @@ static inline int audit_dummy_context(void) void *p = current->audit_context; return !p || *(int *)p; } +static inline void audit_free(struct task_struct *task) +{ + if (unlikely(task->audit_context)) + __audit_free(task); +} static inline void audit_syscall_entry(int arch, int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index e1062f66b01..7aaeb38b262 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1594,7 +1594,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts * * Called from copy_process and do_exit */ -void audit_free(struct task_struct *tsk) +void __audit_free(struct task_struct *tsk) { struct audit_context *context; diff --git a/kernel/exit.c b/kernel/exit.c index 94ed6e20bb5..88dcbbc446f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -964,8 +964,7 @@ NORET_TYPE void do_exit(long code) acct_collect(code, group_dead); if (group_dead) tty_audit_exit(); - if (unlikely(tsk->audit_context)) - audit_free(tsk); + audit_free(tsk); tsk->exit_code = code; taskstats_exit(tsk, group_dead); -- cgit v1.2.3-70-g09d2 From b5740f4b2cb3503b436925eb2242bc3d75cd3dfe Mon Sep 17 00:00:00 2001 From: Yasunori Goto Date: Tue, 17 Jan 2012 17:40:31 +0900 Subject: sched: Fix ancient race in do_exit() try_to_wake_up() has a problem which may change status from TASK_DEAD to TASK_RUNNING in race condition with SMI or guest environment of virtual machine. As a result, exited task is scheduled() again and panic occurs. Here is the sequence how it occurs: ----------------------------------+----------------------------- | CPU A | CPU B ----------------------------------+----------------------------- TASK A calls exit().... do_exit() exit_mm() down_read(mm->mmap_sem); rwsem_down_failed_common() set TASK_UNINTERRUPTIBLE set waiter.task <= task A list_add to sem->wait_list : raw_spin_unlock_irq() (I/O interruption occured) __rwsem_do_wake(mmap_sem) list_del(&waiter->list); waiter->task = NULL wake_up_process(task A) try_to_wake_up() (task is still TASK_UNINTERRUPTIBLE) p->on_rq is still 1.) ttwu_do_wakeup() (*A) : (I/O interruption handler finished) if (!waiter.task) schedule() is not called due to waiter.task is NULL. tsk->state = TASK_RUNNING : check_preempt_curr(); : task->state = TASK_DEAD (*B) <--- set TASK_RUNNING (*C) schedule() (exit task is running again) BUG_ON() is called! -------------------------------------------------------- The execution time between (*A) and (*B) is usually very short, because the interruption is disabled, and setting TASK_RUNNING at (*C) must be executed before setting TASK_DEAD. HOWEVER, if SMI is interrupted between (*A) and (*B), (*C) is able to execute AFTER setting TASK_DEAD! Then, exited task is scheduled again, and BUG_ON() is called.... If the system works on guest system of virtual machine, the time between (*A) and (*B) may be also long due to scheduling of hypervisor, and same phenomenon can occur. By this patch, do_exit() waits for releasing task->pi_lock which is used in try_to_wake_up(). It guarantees the task becomes TASK_DEAD after waking up. Signed-off-by: Yasunori Goto Acked-by: Oleg Nesterov Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20120117174031.3118.E1E9C6FF@jp.fujitsu.com Signed-off-by: Ingo Molnar --- kernel/exit.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'kernel/exit.c') diff --git a/kernel/exit.c b/kernel/exit.c index 294b1709170..4b4042f9bc6 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1038,6 +1038,22 @@ void do_exit(long code) if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); + + /* + * The setting of TASK_RUNNING by try_to_wake_up() may be delayed + * when the following two conditions become true. + * - There is race condition of mmap_sem (It is acquired by + * exit_mm()), and + * - SMI occurs before setting TASK_RUNINNG. + * (or hypervisor of virtual machine switches to other guest) + * As a result, we may become TASK_RUNNING after becoming TASK_DEAD + * + * To avoid it, we have to wait for releasing tsk->pi_lock which + * is held by try_to_wake_up() + */ + smp_mb(); + raw_spin_unlock_wait(&tsk->pi_lock); + /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; tsk->flags |= PF_NOFREEZE; /* tell freezer to ignore us */ -- cgit v1.2.3-70-g09d2