Re: [PATCH 1/8] posix clocks: introduce a syscall for clock tuning.

[Benjamin Herrenschmidt <benh-XVmvHMARGAS8U2dJNN8I7kB+6BGkLq7r@public.gmane.org>]

On Thu, 2010-09-23 at 19:31 +0200, Richard Cochran wrote:
> A new syscall is introduced that allows tuning of a POSIX clock. The
> syscall is implemented for four architectures: arm, blackfin, powerpc,
> and x86.
> 
> The new syscall, clock_adjtime, takes two parameters, the clock ID,
> and a pointer to a struct timex. The semantics of the timex struct
> have been expanded by one additional mode flag, which allows an
> absolute offset correction. When specificied, the clock offset is
> immediately corrected by adding the given time value to the current
> time value.

Any reason why you CC'ed device-tree discuss ?

This list is getting way too much unrelated stuff, which I find
annoying, it would be nice if we were all a bit more careful here with
our CC lists.

Cheers,
Ben.

> Signed-off-by: Richard Cochran <richard.cochran-3mrvs1K0uXizZXS1Dc/lvw@public.gmane.org>
> ---
>  arch/arm/include/asm/unistd.h      |    1 +
>  arch/arm/kernel/calls.S            |    1 +
>  arch/blackfin/include/asm/unistd.h |    3 +-
>  arch/blackfin/mach-common/entry.S  |    1 +
>  arch/powerpc/include/asm/systbl.h  |    1 +
>  arch/powerpc/include/asm/unistd.h  |    3 +-
>  arch/x86/ia32/ia32entry.S          |    1 +
>  arch/x86/include/asm/unistd_32.h   |    3 +-
>  arch/x86/include/asm/unistd_64.h   |    2 +
>  arch/x86/kernel/syscall_table_32.S |    1 +
>  include/linux/posix-timers.h       |    3 +
>  include/linux/syscalls.h           |    2 +
>  include/linux/timex.h              |    3 +-
>  kernel/compat.c                    |  136 +++++++++++++++++++++++-------------
>  kernel/posix-cpu-timers.c          |    4 +
>  kernel/posix-timers.c              |   17 +++++
>  16 files changed, 130 insertions(+), 52 deletions(-)
> 
> diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
> index c891eb7..f58d881 100644
> --- a/arch/arm/include/asm/unistd.h
> +++ b/arch/arm/include/asm/unistd.h
> @@ -396,6 +396,7 @@
>  #define __NR_fanotify_init		(__NR_SYSCALL_BASE+367)
>  #define __NR_fanotify_mark		(__NR_SYSCALL_BASE+368)
>  #define __NR_prlimit64			(__NR_SYSCALL_BASE+369)
> +#define __NR_clock_adjtime		(__NR_SYSCALL_BASE+370)
>  
>  /*
>   * The following SWIs are ARM private.
> diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
> index 5c26ecc..430de4c 100644
> --- a/arch/arm/kernel/calls.S
> +++ b/arch/arm/kernel/calls.S
> @@ -379,6 +379,7 @@
>  		CALL(sys_fanotify_init)
>  		CALL(sys_fanotify_mark)
>  		CALL(sys_prlimit64)
> +/* 370 */	CALL(sys_clock_adjtime)
>  #ifndef syscalls_counted
>  .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
>  #define syscalls_counted
> diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h
> index 14fcd25..79ad99b 100644
> --- a/arch/blackfin/include/asm/unistd.h
> +++ b/arch/blackfin/include/asm/unistd.h
> @@ -392,8 +392,9 @@
>  #define __NR_fanotify_init	371
>  #define __NR_fanotify_mark	372
>  #define __NR_prlimit64		373
> +#define __NR_clock_adjtime	374
>  
> -#define __NR_syscall		374
> +#define __NR_syscall		375
>  #define NR_syscalls		__NR_syscall
>  
>  /* Old optional stuff no one actually uses */
> diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S
> index af1bffa..ee68730 100644
> --- a/arch/blackfin/mach-common/entry.S
> +++ b/arch/blackfin/mach-common/entry.S
> @@ -1631,6 +1631,7 @@ ENTRY(_sys_call_table)
>  	.long _sys_fanotify_init
>  	.long _sys_fanotify_mark
>  	.long _sys_prlimit64
> +	.long _sys_clock_adjtime
>  
>  	.rept NR_syscalls-(.-_sys_call_table)/4
>  	.long _sys_ni_syscall
> diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
> index 3d21266..2485d8f 100644
> --- a/arch/powerpc/include/asm/systbl.h
> +++ b/arch/powerpc/include/asm/systbl.h
> @@ -329,3 +329,4 @@ COMPAT_SYS(rt_tgsigqueueinfo)
>  SYSCALL(fanotify_init)
>  COMPAT_SYS(fanotify_mark)
>  SYSCALL_SPU(prlimit64)
> +COMPAT_SYS_SPU(clock_adjtime)
> diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
> index 597e6f9..85d5067 100644
> --- a/arch/powerpc/include/asm/unistd.h
> +++ b/arch/powerpc/include/asm/unistd.h
> @@ -348,10 +348,11 @@
>  #define __NR_fanotify_init	323
>  #define __NR_fanotify_mark	324
>  #define __NR_prlimit64		325
> +#define __NR_clock_adjtime	326
>  
>  #ifdef __KERNEL__
>  
> -#define __NR_syscalls		326
> +#define __NR_syscalls		327
>  
>  #define __NR__exit __NR_exit
>  #define NR_syscalls	__NR_syscalls
> diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
> index 518bb99..0ed7896 100644
> --- a/arch/x86/ia32/ia32entry.S
> +++ b/arch/x86/ia32/ia32entry.S
> @@ -851,4 +851,5 @@ ia32_sys_call_table:
>  	.quad sys_fanotify_init
>  	.quad sys32_fanotify_mark
>  	.quad sys_prlimit64		/* 340 */
> +	.quad compat_sys_clock_adjtime
>  ia32_syscall_end:
> diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
> index b766a5e..b6f73f1 100644
> --- a/arch/x86/include/asm/unistd_32.h
> +++ b/arch/x86/include/asm/unistd_32.h
> @@ -346,10 +346,11 @@
>  #define __NR_fanotify_init	338
>  #define __NR_fanotify_mark	339
>  #define __NR_prlimit64		340
> +#define __NR_clock_adjtime	341
>  
>  #ifdef __KERNEL__
>  
> -#define NR_syscalls 341
> +#define NR_syscalls 342
>  
>  #define __ARCH_WANT_IPC_PARSE_VERSION
>  #define __ARCH_WANT_OLD_READDIR
> diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
> index 363e9b8..5ee3085 100644
> --- a/arch/x86/include/asm/unistd_64.h
> +++ b/arch/x86/include/asm/unistd_64.h
> @@ -669,6 +669,8 @@ __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
>  __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
>  #define __NR_prlimit64				302
>  __SYSCALL(__NR_prlimit64, sys_prlimit64)
> +#define __NR_clock_adjtime			303
> +__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
>  
>  #ifndef __NO_STUBS
>  #define __ARCH_WANT_OLD_READDIR
> diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
> index b35786d..68c7b9a 100644
> --- a/arch/x86/kernel/syscall_table_32.S
> +++ b/arch/x86/kernel/syscall_table_32.S
> @@ -340,3 +340,4 @@ ENTRY(sys_call_table)
>  	.long sys_fanotify_init
>  	.long sys_fanotify_mark
>  	.long sys_prlimit64		/* 340 */
> +	.long sys_clock_adjtime
> diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
> index 3e23844..abf61cc 100644
> --- a/include/linux/posix-timers.h
> +++ b/include/linux/posix-timers.h
> @@ -4,6 +4,7 @@
>  #include <linux/spinlock.h>
>  #include <linux/list.h>
>  #include <linux/sched.h>
> +#include <linux/timex.h>
>  
>  union cpu_time_count {
>  	cputime_t cpu;
> @@ -71,6 +72,7 @@ struct k_clock {
>  	int (*clock_getres) (const clockid_t which_clock, struct timespec *tp);
>  	int (*clock_set) (const clockid_t which_clock, struct timespec * tp);
>  	int (*clock_get) (const clockid_t which_clock, struct timespec * tp);
> +	int (*clock_adj) (const clockid_t which_clock, struct timex *tx);
>  	int (*timer_create) (struct k_itimer *timer);
>  	int (*nsleep) (const clockid_t which_clock, int flags,
>  		       struct timespec *, struct timespec __user *);
> @@ -97,6 +99,7 @@ int posix_timer_event(struct k_itimer *timr, int si_private);
>  int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *ts);
>  int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *ts);
>  int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *ts);
> +int posix_cpu_clock_adj(const clockid_t which_clock, struct timex *tx);
>  int posix_cpu_timer_create(struct k_itimer *timer);
>  int posix_cpu_nsleep(const clockid_t which_clock, int flags,
>  		     struct timespec *rqtp, struct timespec __user *rmtp);
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index e6319d1..0b24775 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -313,6 +313,8 @@ asmlinkage long sys_clock_settime(clockid_t which_clock,
>  				const struct timespec __user *tp);
>  asmlinkage long sys_clock_gettime(clockid_t which_clock,
>  				struct timespec __user *tp);
> +asmlinkage long sys_clock_adjtime(clockid_t which_clock,
> +				struct timex __user *tx);
>  asmlinkage long sys_clock_getres(clockid_t which_clock,
>  				struct timespec __user *tp);
>  asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags,
> diff --git a/include/linux/timex.h b/include/linux/timex.h
> index 32d852f..82d4b24 100644
> --- a/include/linux/timex.h
> +++ b/include/linux/timex.h
> @@ -73,7 +73,7 @@ struct timex {
>  	long tolerance;		/* clock frequency tolerance (ppm)
>  				 * (read only)
>  				 */
> -	struct timeval time;	/* (read only) */
> +	struct timeval time;	/* (read only, except for ADJ_SETOFFSET) */
>  	long tick;		/* (modified) usecs between clock ticks */
>  
>  	long ppsfreq;           /* pps frequency (scaled ppm) (ro) */
> @@ -101,6 +101,7 @@ struct timex {
>  #define ADJ_ESTERROR		0x0008	/* estimated time error */
>  #define ADJ_STATUS		0x0010	/* clock status */
>  #define ADJ_TIMECONST		0x0020	/* pll time constant */
> +#define ADJ_SETOFFSET		0x0040  /* add 'time' to current time */
>  #define ADJ_TAI			0x0080	/* set TAI offset */
>  #define ADJ_MICRO		0x1000	/* select microsecond resolution */
>  #define ADJ_NANO		0x2000	/* select nanosecond resolution */
> diff --git a/kernel/compat.c b/kernel/compat.c
> index c9e2ec0..38b1d2c 100644
> --- a/kernel/compat.c
> +++ b/kernel/compat.c
> @@ -52,6 +52,64 @@ static int compat_put_timeval(struct compat_timeval __user *o,
>  		put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
>  }
>  
> +static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp)
> +{
> +	memset(txc, 0, sizeof(struct timex));
> +
> +	if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) ||
> +			__get_user(txc->modes, &utp->modes) ||
> +			__get_user(txc->offset, &utp->offset) ||
> +			__get_user(txc->freq, &utp->freq) ||
> +			__get_user(txc->maxerror, &utp->maxerror) ||
> +			__get_user(txc->esterror, &utp->esterror) ||
> +			__get_user(txc->status, &utp->status) ||
> +			__get_user(txc->constant, &utp->constant) ||
> +			__get_user(txc->precision, &utp->precision) ||
> +			__get_user(txc->tolerance, &utp->tolerance) ||
> +			__get_user(txc->time.tv_sec, &utp->time.tv_sec) ||
> +			__get_user(txc->time.tv_usec, &utp->time.tv_usec) ||
> +			__get_user(txc->tick, &utp->tick) ||
> +			__get_user(txc->ppsfreq, &utp->ppsfreq) ||
> +			__get_user(txc->jitter, &utp->jitter) ||
> +			__get_user(txc->shift, &utp->shift) ||
> +			__get_user(txc->stabil, &utp->stabil) ||
> +			__get_user(txc->jitcnt, &utp->jitcnt) ||
> +			__get_user(txc->calcnt, &utp->calcnt) ||
> +			__get_user(txc->errcnt, &utp->errcnt) ||
> +			__get_user(txc->stbcnt, &utp->stbcnt))
> +		return -EFAULT;
> +
> +	return 0;
> +}
> +
> +static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc)
> +{
> +	if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) ||
> +			__put_user(txc->modes, &utp->modes) ||
> +			__put_user(txc->offset, &utp->offset) ||
> +			__put_user(txc->freq, &utp->freq) ||
> +			__put_user(txc->maxerror, &utp->maxerror) ||
> +			__put_user(txc->esterror, &utp->esterror) ||
> +			__put_user(txc->status, &utp->status) ||
> +			__put_user(txc->constant, &utp->constant) ||
> +			__put_user(txc->precision, &utp->precision) ||
> +			__put_user(txc->tolerance, &utp->tolerance) ||
> +			__put_user(txc->time.tv_sec, &utp->time.tv_sec) ||
> +			__put_user(txc->time.tv_usec, &utp->time.tv_usec) ||
> +			__put_user(txc->tick, &utp->tick) ||
> +			__put_user(txc->ppsfreq, &utp->ppsfreq) ||
> +			__put_user(txc->jitter, &utp->jitter) ||
> +			__put_user(txc->shift, &utp->shift) ||
> +			__put_user(txc->stabil, &utp->stabil) ||
> +			__put_user(txc->jitcnt, &utp->jitcnt) ||
> +			__put_user(txc->calcnt, &utp->calcnt) ||
> +			__put_user(txc->errcnt, &utp->errcnt) ||
> +			__put_user(txc->stbcnt, &utp->stbcnt) ||
> +			__put_user(txc->tai, &utp->tai))
> +		return -EFAULT;
> +	return 0;
> +}
> +
>  asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
>  		struct timezone __user *tz)
>  {
> @@ -617,6 +675,29 @@ long compat_sys_clock_gettime(clockid_t which_clock,
>  	return err;
>  }
>  
> +long compat_sys_clock_adjtime(clockid_t which_clock,
> +		struct compat_timex __user *utp)
> +{
> +	struct timex txc;
> +	mm_segment_t oldfs;
> +	int err, ret;
> +
> +	err = compat_get_timex(&txc, utp);
> +	if (err)
> +		return err;
> +
> +	oldfs = get_fs();
> +	set_fs(KERNEL_DS);
> +	ret = sys_clock_adjtime(which_clock, (struct timex __user *) &txc);
> +	set_fs(oldfs);
> +
> +	err = compat_put_timex(utp, &txc);
> +	if (err)
> +		return err;
> +
> +	return ret;
> +}
> +
>  long compat_sys_clock_getres(clockid_t which_clock,
>  		struct compat_timespec __user *tp)
>  {
> @@ -951,58 +1032,17 @@ asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat
>  asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp)
>  {
>  	struct timex txc;
> -	int ret;
> -
> -	memset(&txc, 0, sizeof(struct timex));
> +	int err, ret;
>  
> -	if (!access_ok(VERIFY_READ, utp, sizeof(struct compat_timex)) ||
> -			__get_user(txc.modes, &utp->modes) ||
> -			__get_user(txc.offset, &utp->offset) ||
> -			__get_user(txc.freq, &utp->freq) ||
> -			__get_user(txc.maxerror, &utp->maxerror) ||
> -			__get_user(txc.esterror, &utp->esterror) ||
> -			__get_user(txc.status, &utp->status) ||
> -			__get_user(txc.constant, &utp->constant) ||
> -			__get_user(txc.precision, &utp->precision) ||
> -			__get_user(txc.tolerance, &utp->tolerance) ||
> -			__get_user(txc.time.tv_sec, &utp->time.tv_sec) ||
> -			__get_user(txc.time.tv_usec, &utp->time.tv_usec) ||
> -			__get_user(txc.tick, &utp->tick) ||
> -			__get_user(txc.ppsfreq, &utp->ppsfreq) ||
> -			__get_user(txc.jitter, &utp->jitter) ||
> -			__get_user(txc.shift, &utp->shift) ||
> -			__get_user(txc.stabil, &utp->stabil) ||
> -			__get_user(txc.jitcnt, &utp->jitcnt) ||
> -			__get_user(txc.calcnt, &utp->calcnt) ||
> -			__get_user(txc.errcnt, &utp->errcnt) ||
> -			__get_user(txc.stbcnt, &utp->stbcnt))
> -		return -EFAULT;
> +	err = compat_get_timex(&txc, utp);
> +	if (err)
> +		return err;
>  
>  	ret = do_adjtimex(&txc);
>  
> -	if (!access_ok(VERIFY_WRITE, utp, sizeof(struct compat_timex)) ||
> -			__put_user(txc.modes, &utp->modes) ||
> -			__put_user(txc.offset, &utp->offset) ||
> -			__put_user(txc.freq, &utp->freq) ||
> -			__put_user(txc.maxerror, &utp->maxerror) ||
> -			__put_user(txc.esterror, &utp->esterror) ||
> -			__put_user(txc.status, &utp->status) ||
> -			__put_user(txc.constant, &utp->constant) ||
> -			__put_user(txc.precision, &utp->precision) ||
> -			__put_user(txc.tolerance, &utp->tolerance) ||
> -			__put_user(txc.time.tv_sec, &utp->time.tv_sec) ||
> -			__put_user(txc.time.tv_usec, &utp->time.tv_usec) ||
> -			__put_user(txc.tick, &utp->tick) ||
> -			__put_user(txc.ppsfreq, &utp->ppsfreq) ||
> -			__put_user(txc.jitter, &utp->jitter) ||
> -			__put_user(txc.shift, &utp->shift) ||
> -			__put_user(txc.stabil, &utp->stabil) ||
> -			__put_user(txc.jitcnt, &utp->jitcnt) ||
> -			__put_user(txc.calcnt, &utp->calcnt) ||
> -			__put_user(txc.errcnt, &utp->errcnt) ||
> -			__put_user(txc.stbcnt, &utp->stbcnt) ||
> -			__put_user(txc.tai, &utp->tai))
> -		ret = -EFAULT;
> +	err = compat_put_timex(utp, &txc);
> +	if (err)
> +		return err;
>  
>  	return ret;
>  }
> diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
> index 6842eeb..e1c2e7b 100644
> --- a/kernel/posix-cpu-timers.c
> +++ b/kernel/posix-cpu-timers.c
> @@ -207,6 +207,10 @@ int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
>  	return error;
>  }
>  
> +int posix_cpu_clock_adj(const clockid_t which_clock, struct timex *tx)
> +{
> +	return -EOPNOTSUPP;
> +}
>  
>  /*
>   * Sample a per-thread clock for the given task.
> diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
> index 9ca4973..446b566 100644
> --- a/kernel/posix-timers.c
> +++ b/kernel/posix-timers.c
> @@ -197,6 +197,14 @@ static int common_timer_create(struct k_itimer *new_timer)
>  	return 0;
>  }
>  
> +static inline int common_clock_adj(const clockid_t which_clock, struct timex *t)
> +{
> +	if (CLOCK_REALTIME == which_clock)
> +		return do_adjtimex(t);
> +	else
> +		return -EOPNOTSUPP;
> +}
> +
>  static int no_timer_create(struct k_itimer *new_timer)
>  {
>  	return -EOPNOTSUPP;
> @@ -969,6 +977,15 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
>  
>  }
>  
> +SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
> +		struct timex __user *, tx)
> +{
> +	if (invalid_clockid(which_clock))
> +		return -EINVAL;
> +
> +	return CLOCK_DISPATCH(which_clock, clock_adj, (which_clock, tx));
> +}
> +
>  SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
>  		struct timespec __user *, tp)
>  {