From cddd02489f52ccf635ed65931214729a23b93cd6 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Sun, 22 Jun 2014 01:29:15 +0200 Subject: hrtimer: Store cpu-number in struct hrtimer_cpu_base In lowres mode, hrtimers are serviced by the tick instead of a clock event. Now it works well as long as the tick stays periodic but we must also make sure that the hrtimers are serviced in dynticks mode. Part of that job consist in kicking a dynticks hrtimer target in order to make it reconsider the next tick to schedule to correctly handle the hrtimer's expiring time. And that part isn't handled by the hrtimers subsystem. To prepare for fixing this, we need __hrtimer_start_range_ns() to be able to resolve the CPU target associated to a hrtimer's object 'cpu_base' so that the kick can be centralized there. So lets store it in the 'struct hrtimer_cpu_base' to resolve the CPU without overhead. It is set once at CPU's online notification. Signed-off-by: Viresh Kumar Signed-off-by: Frederic Weisbecker Link: http://lkml.kernel.org/r/1403393357-2070-4-git-send-email-fweisbec@gmail.com Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index e7a8d3fa91d5..bb4ffff31c69 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -165,6 +165,7 @@ enum hrtimer_base_type { * struct hrtimer_cpu_base - the per cpu clock bases * @lock: lock protecting the base and associated clock bases * and timers + * @cpu: cpu number * @active_bases: Bitfield to mark bases with active timers * @clock_was_set: Indicates that clock was set from irq context. * @expires_next: absolute time of the next event which was scheduled @@ -179,6 +180,7 @@ enum hrtimer_base_type { */ struct hrtimer_cpu_base { raw_spinlock_t lock; + unsigned int cpu; unsigned int active_bases; unsigned int clock_was_set; #ifdef CONFIG_HIGH_RES_TIMERS -- cgit v1.2.3 From 628627bfd943c077c65489acd8b23c7bb14eb0e2 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 4 Mar 2014 18:50:53 +0100 Subject: clocksource: shmobile: Remove unused sh_timer_config members The name, channel_offset, timer_bit, clockevent_rating and clocksource_rating members are unused. Remove them. Signed-off-by: Laurent Pinchart Tested-by: Simon Horman --- include/linux/sh_timer.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sh_timer.h b/include/linux/sh_timer.h index 8e1e036d6d45..64638b058076 100644 --- a/include/linux/sh_timer.h +++ b/include/linux/sh_timer.h @@ -2,11 +2,6 @@ #define __SH_TIMER_H__ struct sh_timer_config { - char *name; - long channel_offset; - int timer_bit; - unsigned long clockevent_rating; - unsigned long clocksource_rating; unsigned int channels_mask; }; -- cgit v1.2.3 From 5442e9fbd7c23172a1c9bc736629cd123a9923f0 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 16 Jul 2014 01:54:54 +0400 Subject: timerfd: Implement timerfd_ioctl method to restore timerfd_ctx::ticks, v3 The read() of timerfd files allows to fetch the number of timer ticks while there is no way to set it back from userspace. To restore the timer's state as it was at checkpoint moment we need a path to bring @ticks back. Initially I thought about writing ticks back via write() interface but it seems such API is somehow obscure. Instead implement timerfd_ioctl() method with TFD_IOC_SET_TICKS command which allows to adjust @ticks into non-zero value waking up the waiters. I wrapped code with CONFIG_CHECKPOINT_RESTORE which can be dropped off if there users except c/r camp appear. v2 (by akpm@): - Use define timerfd_ioctl NULL for non c/r config v3: - Use copy_from_user for @ticks fetching since not all arch support get_user for 8 byte argument Signed-off-by: Cyrill Gorcunov Cc: Andrew Morton Cc: Michael Kerrisk Cc: Andrey Vagin Cc: Arnd Bergmann Cc: Christopher Covington Cc: Pavel Emelyanov Cc: Vladimir Davydov Link: http://lkml.kernel.org/r/20140715215703.285617923@openvz.org Signed-off-by: Thomas Gleixner --- fs/timerfd.c | 37 +++++++++++++++++++++++++++++++++++++ include/linux/timerfd.h | 5 +++++ 2 files changed, 42 insertions(+) (limited to 'include/linux') diff --git a/fs/timerfd.c b/fs/timerfd.c index 77183f047f65..709603cac9e6 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -315,12 +315,49 @@ static int timerfd_show(struct seq_file *m, struct file *file) #define timerfd_show NULL #endif +#ifdef CONFIG_CHECKPOINT_RESTORE +static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct timerfd_ctx *ctx = file->private_data; + int ret = 0; + + switch (cmd) { + case TFD_IOC_SET_TICKS: { + u64 ticks; + + if (copy_from_user(&ticks, (u64 __user *)arg, sizeof(ticks))) + return -EFAULT; + if (!ticks) + return -EINVAL; + + spin_lock_irq(&ctx->wqh.lock); + if (!timerfd_canceled(ctx)) { + ctx->ticks = ticks; + if (ticks) + wake_up_locked(&ctx->wqh); + } else + ret = -ECANCELED; + spin_unlock_irq(&ctx->wqh.lock); + break; + } + default: + ret = -ENOTTY; + break; + } + + return ret; +} +#else +#define timerfd_ioctl NULL +#endif + static const struct file_operations timerfd_fops = { .release = timerfd_release, .poll = timerfd_poll, .read = timerfd_read, .llseek = noop_llseek, .show_fdinfo = timerfd_show, + .unlocked_ioctl = timerfd_ioctl, }; static int timerfd_fget(int fd, struct fd *p) diff --git a/include/linux/timerfd.h b/include/linux/timerfd.h index d3b57fa12225..bd36ce431e32 100644 --- a/include/linux/timerfd.h +++ b/include/linux/timerfd.h @@ -11,6 +11,9 @@ /* For O_CLOEXEC and O_NONBLOCK */ #include +/* For _IO helpers */ +#include + /* * CAREFUL: Check include/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want @@ -29,4 +32,6 @@ /* Flags for timerfd_settime. */ #define TFD_SETTIME_FLAGS (TFD_TIMER_ABSTIME | TFD_TIMER_CANCEL_ON_SET) +#define TFD_IOC_SET_TICKS _IOW('T', 0, u64) + #endif /* _LINUX_TIMERFD_H */ -- cgit v1.2.3 From efd342fb0031a17758571dce42e3f373d94e2fec Mon Sep 17 00:00:00 2001 From: Matthias Brugger Date: Fri, 18 Jul 2014 11:36:39 +0200 Subject: of: Provide a function to request and map memory A call to of_iomap does not request the memory region. This patch adds the function of_io_request_and_map which requests the memory region before mapping it. Signed-off-by: Matthias Brugger Suggested-by: Thomas Gleixner Suggested-by: Rob Herring Acked-by: Rob Herring Signed-off-by: Daniel Lezcano --- drivers/of/address.c | 36 ++++++++++++++++++++++++++++++++++++ include/linux/io.h | 2 ++ include/linux/of_address.h | 11 +++++++++++ lib/devres.c | 2 -- 4 files changed, 49 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/address.c b/drivers/of/address.c index 5edfcb0da37d..e3718250d66e 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -702,6 +702,42 @@ void __iomem *of_iomap(struct device_node *np, int index) } EXPORT_SYMBOL(of_iomap); +/* + * of_io_request_and_map - Requests a resource and maps the memory mapped IO + * for a given device_node + * @device: the device whose io range will be mapped + * @index: index of the io range + * @name: name of the resource + * + * Returns a pointer to the requested and mapped memory or an ERR_PTR() encoded + * error code on failure. Usage example: + * + * base = of_io_request_and_map(node, 0, "foo"); + * if (IS_ERR(base)) + * return PTR_ERR(base); + */ +void __iomem *of_io_request_and_map(struct device_node *np, int index, + char *name) +{ + struct resource res; + void __iomem *mem; + + if (of_address_to_resource(np, index, &res)) + return IOMEM_ERR_PTR(-EINVAL); + + if (!request_mem_region(res.start, resource_size(&res), name)) + return IOMEM_ERR_PTR(-EBUSY); + + mem = ioremap(res.start, resource_size(&res)); + if (!mem) { + release_mem_region(res.start, resource_size(&res)); + return IOMEM_ERR_PTR(-ENOMEM); + } + + return mem; +} +EXPORT_SYMBOL(of_io_request_and_map); + /** * of_dma_get_range - Get DMA range info * @np: device node to get DMA range info diff --git a/include/linux/io.h b/include/linux/io.h index b76e6e545806..d5fc9b8d8b03 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -58,6 +58,8 @@ static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr) } #endif +#define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err) + void __iomem *devm_ioremap(struct device *dev, resource_size_t offset, unsigned long size); void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset, diff --git a/include/linux/of_address.h b/include/linux/of_address.h index c13b8782a4eb..fb7b7221e063 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -109,7 +109,12 @@ static inline bool of_dma_is_coherent(struct device_node *np) extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); void __iomem *of_iomap(struct device_node *node, int index); +void __iomem *of_io_request_and_map(struct device_node *device, + int index, char *name); #else + +#include + static inline int of_address_to_resource(struct device_node *dev, int index, struct resource *r) { @@ -120,6 +125,12 @@ static inline void __iomem *of_iomap(struct device_node *device, int index) { return NULL; } + +static inline void __iomem *of_io_request_and_map(struct device_node *device, + int index, char *name) +{ + return IOMEM_ERR_PTR(-EINVAL); +} #endif #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI) diff --git a/lib/devres.c b/lib/devres.c index f562bf6ff71d..bb632484a860 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -86,8 +86,6 @@ void devm_iounmap(struct device *dev, void __iomem *addr) } EXPORT_SYMBOL(devm_iounmap); -#define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err) - /** * devm_ioremap_resource() - check, request region, and ioremap resource * @dev: generic device to handle the resource for -- cgit v1.2.3 From 76f4108892d9a9e3408bba839914f97a54086a6f Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 16 Jul 2014 21:03:52 +0000 Subject: hrtimer: Cleanup hrtimer accessors to the timekepeing state Rather then having two similar but totally different implementations that provide timekeeping state to the hrtimer code, try to unify the two implementations to be more simliar. Thus this clarifies ktime_get_update_offsets to ktime_get_update_offsets_now and changes get_xtime... to ktime_get_update_offsets_tick. Signed-off-by: John Stultz Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/hrtimer.h | 9 ++++++--- include/linux/time.h | 2 -- kernel/time/hrtimer.c | 19 ++++++++----------- kernel/time/timekeeping.c | 36 +++++++++++++++++++++++------------- 4 files changed, 37 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index bb4ffff31c69..e84eb4f228cd 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -331,9 +331,12 @@ extern ktime_t ktime_get_real(void); extern ktime_t ktime_get_boottime(void); extern ktime_t ktime_get_monotonic_offset(void); extern ktime_t ktime_get_clocktai(void); -extern ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot, - ktime_t *offs_tai); - +extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); +extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); DECLARE_PER_CPU(struct tick_device, tick_cpu_device); diff --git a/include/linux/time.h b/include/linux/time.h index d5d229b2e5af..f6d990d1c79a 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -133,8 +133,6 @@ unsigned long get_seconds(void); struct timespec current_kernel_time(void); struct timespec __current_kernel_time(void); /* does not take xtime_lock */ struct timespec get_monotonic_coarse(void); -void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, - struct timespec *wtom, struct timespec *sleep); void timekeeping_inject_sleeptime(struct timespec *delta); #define CURRENT_TIME (current_kernel_time()) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 66a6dc1075ad..2f4ef8a1e5ff 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -114,21 +114,18 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id) */ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) { - ktime_t xtim, mono, boot; - struct timespec xts, tom, slp; - s32 tai_offset; + ktime_t xtim, mono, boot, tai; + ktime_t off_real, off_boot, off_tai; - get_xtime_and_monotonic_and_sleep_offset(&xts, &tom, &slp); - tai_offset = timekeeping_get_tai_offset(); + mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai); + boot = ktime_add(mono, off_boot); + xtim = ktime_add(mono, off_real); + tai = ktime_add(xtim, off_tai); - xtim = timespec_to_ktime(xts); - mono = ktime_add(xtim, timespec_to_ktime(tom)); - boot = ktime_add(mono, timespec_to_ktime(slp)); base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim; base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono; base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot; - base->clock_base[HRTIMER_BASE_TAI].softirq_time = - ktime_add(xtim, ktime_set(tai_offset, 0)); + base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai; } /* @@ -673,7 +670,7 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; - return ktime_get_update_offsets(offs_real, offs_boot, offs_tai); + return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai); } /* diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 908861c58e62..b94fa3652aaa 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1581,29 +1581,39 @@ void do_timer(unsigned long ticks) } /** - * get_xtime_and_monotonic_and_sleep_offset() - get xtime, wall_to_monotonic, - * and sleep offsets. - * @xtim: pointer to timespec to be set with xtime - * @wtom: pointer to timespec to be set with wall_to_monotonic - * @sleep: pointer to timespec to be set with time in suspend + * ktime_get_update_offsets_tick - hrtimer helper + * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset + * @offs_tai: pointer to storage for monotonic -> clock tai offset + * + * Returns monotonic time at last tick and various offsets */ -void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, - struct timespec *wtom, struct timespec *sleep) +ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, + ktime_t *offs_tai) { struct timekeeper *tk = &timekeeper; - unsigned long seq; + struct timespec ts; + ktime_t now; + unsigned int seq; do { seq = read_seqcount_begin(&timekeeper_seq); - *xtim = tk_xtime(tk); - *wtom = tk->wall_to_monotonic; - *sleep = tk->total_sleep_time; + + ts = tk_xtime(tk); + + *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; + *offs_tai = tk->offs_tai; } while (read_seqcount_retry(&timekeeper_seq, seq)); + + now = ktime_set(ts.tv_sec, ts.tv_nsec); + now = ktime_sub(now, *offs_real); + return now; } #ifdef CONFIG_HIGH_RES_TIMERS /** - * ktime_get_update_offsets - hrtimer helper + * ktime_get_update_offsets_now - hrtimer helper * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset @@ -1611,7 +1621,7 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, * Returns current monotonic time and updates the offsets * Called from hrtimer_interrupt() or retrigger_next_event() */ -ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot, +ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &timekeeper; -- cgit v1.2.3 From 24e4a8c3e8868874835b0f1ad6dd417341e99822 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 16 Jul 2014 21:03:53 +0000 Subject: ktime: Kill non-scalar ktime_t implementation for 2038 The non-scalar ktime_t implementation is basically a timespec which has to be changed to support dates past 2038 on 32bit systems. This patch removes the non-scalar ktime_t implementation, forcing the scalar s64 nanosecond version on all architectures. This may have additional performance overhead on some 32bit systems when converting between ktime_t and timespec structures, however the majority of 32bit systems (arm and i386) were already using scalar ktime_t, so no performance regressions will be seen on those platforms. On affected platforms, I'm open to finding optimizations, including avoiding converting to timespecs where possible. [ tglx: We can now cleanup the ktime_t.tv64 mess, but thats a different issue and we can throw a coccinelle script at it ] Signed-off-by: John Stultz Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- arch/arm/Kconfig | 1 - arch/hexagon/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/x86/Kconfig | 1 - include/linux/ktime.h | 173 +--------------------------------------------- include/linux/time.h | 11 ++- kernel/time/Kconfig | 4 -- kernel/time/hrtimer.c | 54 --------------- kernel/time/timekeeping.c | 7 +- 9 files changed, 7 insertions(+), 246 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 05a71511ab3c..b9f6728331c8 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -64,7 +64,6 @@ config ARM select HAVE_UID16 select HAVE_VIRT_CPU_ACCOUNTING_GEN select IRQ_FORCED_THREADING - select KTIME_SCALAR select MODULES_USE_ELF_REL select NO_BOOTMEM select OLD_SIGACTION diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 0fd6138f6203..4dc89d1f9c48 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -23,7 +23,6 @@ config HEXAGON select GENERIC_IOMAP select GENERIC_SMP_IDLE_THREAD select STACKTRACE_SUPPORT - select KTIME_SCALAR select GENERIC_CLOCKEVENTS select GENERIC_CLOCKEVENTS_BROADCAST select MODULES_USE_ELF_RELA diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bb63499fc5d3..1afc7a686702 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -137,7 +137,6 @@ config S390 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 if 32BIT select HAVE_VIRT_CPU_ACCOUNTING - select KTIME_SCALAR if 32BIT select MODULES_USE_ELF_RELA select NO_BOOTMEM select OLD_SIGACTION diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a8f749ef0fdc..7fa17b5ce668 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -111,7 +111,6 @@ config X86 select ARCH_CLOCKSOURCE_DATA select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) select GENERIC_TIME_VSYSCALL - select KTIME_SCALAR if X86_32 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_CONTEXT_TRACKING if X86_64 diff --git a/include/linux/ktime.h b/include/linux/ktime.h index de9e46e6bcc9..fbc64f8481b7 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -27,43 +27,19 @@ /* * ktime_t: * - * On 64-bit CPUs a single 64-bit variable is used to store the hrtimers + * A single 64-bit variable is used to store the hrtimers * internal representation of time values in scalar nanoseconds. The * design plays out best on 64-bit CPUs, where most conversions are * NOPs and most arithmetic ktime_t operations are plain arithmetic * operations. * - * On 32-bit CPUs an optimized representation of the timespec structure - * is used to avoid expensive conversions from and to timespecs. The - * endian-aware order of the tv struct members is chosen to allow - * mathematical operations on the tv64 member of the union too, which - * for certain operations produces better code. - * - * For architectures with efficient support for 64/32-bit conversions the - * plain scalar nanosecond based representation can be selected by the - * config switch CONFIG_KTIME_SCALAR. */ union ktime { s64 tv64; -#if BITS_PER_LONG != 64 && !defined(CONFIG_KTIME_SCALAR) - struct { -# ifdef __BIG_ENDIAN - s32 sec, nsec; -# else - s32 nsec, sec; -# endif - } tv; -#endif }; typedef union ktime ktime_t; /* Kill this */ -/* - * ktime_t definitions when using the 64-bit scalar representation: - */ - -#if (BITS_PER_LONG == 64) || defined(CONFIG_KTIME_SCALAR) - /** * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value * @secs: seconds to set @@ -123,153 +99,6 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) /* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */ #define ktime_to_ns(kt) ((kt).tv64) -#else /* !((BITS_PER_LONG == 64) || defined(CONFIG_KTIME_SCALAR)) */ - -/* - * Helper macros/inlines to get the ktime_t math right in the timespec - * representation. The macros are sometimes ugly - their actual use is - * pretty okay-ish, given the circumstances. We do all this for - * performance reasons. The pure scalar nsec_t based code was nice and - * simple, but created too many 64-bit / 32-bit conversions and divisions. - * - * Be especially aware that negative values are represented in a way - * that the tv.sec field is negative and the tv.nsec field is greater - * or equal to zero but less than nanoseconds per second. This is the - * same representation which is used by timespecs. - * - * tv.sec < 0 and 0 >= tv.nsec < NSEC_PER_SEC - */ - -/* Set a ktime_t variable to a value in sec/nsec representation: */ -static inline ktime_t ktime_set(const long secs, const unsigned long nsecs) -{ - return (ktime_t) { .tv = { .sec = secs, .nsec = nsecs } }; -} - -/** - * ktime_sub - subtract two ktime_t variables - * @lhs: minuend - * @rhs: subtrahend - * - * Return: The remainder of the subtraction. - */ -static inline ktime_t ktime_sub(const ktime_t lhs, const ktime_t rhs) -{ - ktime_t res; - - res.tv64 = lhs.tv64 - rhs.tv64; - if (res.tv.nsec < 0) - res.tv.nsec += NSEC_PER_SEC; - - return res; -} - -/** - * ktime_add - add two ktime_t variables - * @add1: addend1 - * @add2: addend2 - * - * Return: The sum of @add1 and @add2. - */ -static inline ktime_t ktime_add(const ktime_t add1, const ktime_t add2) -{ - ktime_t res; - - res.tv64 = add1.tv64 + add2.tv64; - /* - * performance trick: the (u32) -NSEC gives 0x00000000Fxxxxxxx - * so we subtract NSEC_PER_SEC and add 1 to the upper 32 bit. - * - * it's equivalent to: - * tv.nsec -= NSEC_PER_SEC - * tv.sec ++; - */ - if (res.tv.nsec >= NSEC_PER_SEC) - res.tv64 += (u32)-NSEC_PER_SEC; - - return res; -} - -/** - * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable - * @kt: addend - * @nsec: the scalar nsec value to add - * - * Return: The sum of @kt and @nsec in ktime_t format. - */ -extern ktime_t ktime_add_ns(const ktime_t kt, u64 nsec); - -/** - * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable - * @kt: minuend - * @nsec: the scalar nsec value to subtract - * - * Return: The subtraction of @nsec from @kt in ktime_t format. - */ -extern ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec); - -/** - * timespec_to_ktime - convert a timespec to ktime_t format - * @ts: the timespec variable to convert - * - * Return: A ktime_t variable with the converted timespec value. - */ -static inline ktime_t timespec_to_ktime(const struct timespec ts) -{ - return (ktime_t) { .tv = { .sec = (s32)ts.tv_sec, - .nsec = (s32)ts.tv_nsec } }; -} - -/** - * timeval_to_ktime - convert a timeval to ktime_t format - * @tv: the timeval variable to convert - * - * Return: A ktime_t variable with the converted timeval value. - */ -static inline ktime_t timeval_to_ktime(const struct timeval tv) -{ - return (ktime_t) { .tv = { .sec = (s32)tv.tv_sec, - .nsec = (s32)(tv.tv_usec * - NSEC_PER_USEC) } }; -} - -/** - * ktime_to_timespec - convert a ktime_t variable to timespec format - * @kt: the ktime_t variable to convert - * - * Return: The timespec representation of the ktime value. - */ -static inline struct timespec ktime_to_timespec(const ktime_t kt) -{ - return (struct timespec) { .tv_sec = (time_t) kt.tv.sec, - .tv_nsec = (long) kt.tv.nsec }; -} - -/** - * ktime_to_timeval - convert a ktime_t variable to timeval format - * @kt: the ktime_t variable to convert - * - * Return: The timeval representation of the ktime value. - */ -static inline struct timeval ktime_to_timeval(const ktime_t kt) -{ - return (struct timeval) { - .tv_sec = (time_t) kt.tv.sec, - .tv_usec = (suseconds_t) (kt.tv.nsec / NSEC_PER_USEC) }; -} - -/** - * ktime_to_ns - convert a ktime_t variable to scalar nanoseconds - * @kt: the ktime_t variable to convert - * - * Return: The scalar nanoseconds representation of @kt. - */ -static inline s64 ktime_to_ns(const ktime_t kt) -{ - return (s64) kt.tv.sec * NSEC_PER_SEC + kt.tv.nsec; -} - -#endif /* !((BITS_PER_LONG == 64) || defined(CONFIG_KTIME_SCALAR)) */ /** * ktime_equal - Compares two ktime_t variables to see if they are equal diff --git a/include/linux/time.h b/include/linux/time.h index f6d990d1c79a..129f0bd36a8d 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -19,6 +19,10 @@ extern struct timezone sys_tz; #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) +/* Located here for timespec_valid_strict */ +#define KTIME_MAX ((s64)~((u64)1 << 63)) +#define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) + static inline int timespec_equal(const struct timespec *a, const struct timespec *b) { @@ -84,13 +88,6 @@ static inline struct timespec timespec_sub(struct timespec lhs, return ts_delta; } -#define KTIME_MAX ((s64)~((u64)1 << 63)) -#if (BITS_PER_LONG == 64) -# define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) -#else -# define KTIME_SEC_MAX LONG_MAX -#endif - /* * Returns true if the timespec is norm, false if denorm: */ diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index f448513a45ed..feccfd888732 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -20,10 +20,6 @@ config GENERIC_TIME_VSYSCALL config GENERIC_TIME_VSYSCALL_OLD bool -# ktime_t scalar 64bit nsec representation -config KTIME_SCALAR - bool - # Old style timekeeping config ARCH_USES_GETTIMEOFFSET bool diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 2f4ef8a1e5ff..19f211051c35 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -261,60 +261,6 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) * too large for inlining: */ #if BITS_PER_LONG < 64 -# ifndef CONFIG_KTIME_SCALAR -/** - * ktime_add_ns - Add a scalar nanoseconds value to a ktime_t variable - * @kt: addend - * @nsec: the scalar nsec value to add - * - * Returns the sum of kt and nsec in ktime_t format - */ -ktime_t ktime_add_ns(const ktime_t kt, u64 nsec) -{ - ktime_t tmp; - - if (likely(nsec < NSEC_PER_SEC)) { - tmp.tv64 = nsec; - } else { - unsigned long rem = do_div(nsec, NSEC_PER_SEC); - - /* Make sure nsec fits into long */ - if (unlikely(nsec > KTIME_SEC_MAX)) - return (ktime_t){ .tv64 = KTIME_MAX }; - - tmp = ktime_set((long)nsec, rem); - } - - return ktime_add(kt, tmp); -} - -EXPORT_SYMBOL_GPL(ktime_add_ns); - -/** - * ktime_sub_ns - Subtract a scalar nanoseconds value from a ktime_t variable - * @kt: minuend - * @nsec: the scalar nsec value to subtract - * - * Returns the subtraction of @nsec from @kt in ktime_t format - */ -ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec) -{ - ktime_t tmp; - - if (likely(nsec < NSEC_PER_SEC)) { - tmp.tv64 = nsec; - } else { - unsigned long rem = do_div(nsec, NSEC_PER_SEC); - - tmp = ktime_set((long)nsec, rem); - } - - return ktime_sub(kt, tmp); -} - -EXPORT_SYMBOL_GPL(ktime_sub_ns); -# endif /* !CONFIG_KTIME_SCALAR */ - /* * Divide a ktime value by a nanosecond value */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b94fa3652aaa..cafef242d8f9 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -344,11 +344,8 @@ ktime_t ktime_get(void) nsecs = timekeeping_get_ns(tk) + tk->wall_to_monotonic.tv_nsec; } while (read_seqcount_retry(&timekeeper_seq, seq)); - /* - * Use ktime_set/ktime_add_ns to create a proper ktime on - * 32-bit architectures without CONFIG_KTIME_SCALAR. - */ - return ktime_add_ns(ktime_set(secs, 0), nsecs); + + return ktime_set(secs, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); -- cgit v1.2.3 From 166afb64511eef08e13331b970c44fe91cea45ef Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:03:55 +0000 Subject: ktime: Sanitize ktime_to_us/ms conversion With the plain nanoseconds based ktime_t we can simply use ktime_divns() instead of going through loops and hoops of timespec/timeval conversion. Reported-by: John Stultz Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/hrtimer.h | 6 ------ include/linux/ktime.h | 12 ++++++++---- kernel/time/hrtimer.c | 1 + 3 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index e84eb4f228cd..adf5056bd7b3 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -457,12 +457,6 @@ extern void hrtimer_run_pending(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); -#if BITS_PER_LONG < 64 -extern u64 ktime_divns(const ktime_t kt, s64 div); -#else /* BITS_PER_LONG < 64 */ -# define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) -#endif - /* Show pending timers: */ extern void sysrq_timer_list_show(void); diff --git a/include/linux/ktime.h b/include/linux/ktime.h index fbc64f8481b7..74eaba9b3569 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -157,16 +157,20 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) return ktime_compare(cmp1, cmp2) < 0; } +#if BITS_PER_LONG < 64 +extern u64 ktime_divns(const ktime_t kt, s64 div); +#else /* BITS_PER_LONG < 64 */ +# define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) +#endif + static inline s64 ktime_to_us(const ktime_t kt) { - struct timeval tv = ktime_to_timeval(kt); - return (s64) tv.tv_sec * USEC_PER_SEC + tv.tv_usec; + return ktime_divns(kt, NSEC_PER_USEC); } static inline s64 ktime_to_ms(const ktime_t kt) { - struct timeval tv = ktime_to_timeval(kt); - return (s64) tv.tv_sec * MSEC_PER_SEC + tv.tv_usec / USEC_PER_MSEC; + return ktime_divns(kt, NSEC_PER_MSEC); } static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 19f211051c35..64843a836637 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -280,6 +280,7 @@ u64 ktime_divns(const ktime_t kt, s64 div) return dclc; } +EXPORT_SYMBOL_GPL(ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* -- cgit v1.2.3 From b17b20d70dcbe48dd1aa6aba073a60ddfce5d7db Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 16 Jul 2014 21:03:56 +0000 Subject: ktime: Change ktime_set() to take 64bit seconds value In order to support dates past 2038 on 32bit systems, ktime_set() needs to handle 64bit second values. [ tglx: Removed the BITS_PER_LONG check ] Signed-off-by: John Stultz Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/ktime.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 74eaba9b3569..538c283714e1 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -47,13 +47,12 @@ typedef union ktime ktime_t; /* Kill this */ * * Return: The ktime_t representation of the value. */ -static inline ktime_t ktime_set(const long secs, const unsigned long nsecs) +static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) { -#if (BITS_PER_LONG == 64) if (unlikely(secs >= KTIME_SEC_MAX)) return (ktime_t){ .tv64 = KTIME_MAX }; -#endif - return (ktime_t) { .tv64 = (s64)secs * NSEC_PER_SEC + (s64)nsecs }; + + return (ktime_t) { .tv64 = secs * NSEC_PER_SEC + (s64)nsecs }; } /* Subtract two ktime_t variables. rem = lhs -rhs: */ -- cgit v1.2.3 From 361a3bf00582469877f8d18ff20f1efa6b781274 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 16 Jul 2014 21:03:58 +0000 Subject: time64: Add time64.h header and define struct timespec64 Define the timespec64 structure and standard helper functions. [ tglx: Make it 32bit only. 64bit really can map timespec to timespec64 ] Signed-off-by: John Stultz Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/time.h | 15 +---- include/linux/time64.h | 162 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 163 insertions(+), 14 deletions(-) create mode 100644 include/linux/time64.h (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 129f0bd36a8d..234feac7f1c3 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -4,25 +4,12 @@ # include # include # include -#include +# include extern struct timezone sys_tz; -/* Parameters used to convert the timespec values: */ -#define MSEC_PER_SEC 1000L -#define USEC_PER_MSEC 1000L -#define NSEC_PER_USEC 1000L -#define NSEC_PER_MSEC 1000000L -#define USEC_PER_SEC 1000000L -#define NSEC_PER_SEC 1000000000L -#define FSEC_PER_SEC 1000000000000000LL - #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) -/* Located here for timespec_valid_strict */ -#define KTIME_MAX ((s64)~((u64)1 << 63)) -#define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) - static inline int timespec_equal(const struct timespec *a, const struct timespec *b) { diff --git a/include/linux/time64.h b/include/linux/time64.h new file mode 100644 index 000000000000..e7b499e1cd79 --- /dev/null +++ b/include/linux/time64.h @@ -0,0 +1,162 @@ +#ifndef _LINUX_TIME64_H +#define _LINUX_TIME64_H + +#include + +typedef __s64 time64_t; + +/* + * This wants to go into uapi/linux/time.h once we agreed about the + * userspace interfaces. + */ +#if __BITS_PER_LONG == 64 +# define timespec64 timespec +#else +struct timespec64 { + time64_t tv_sec; /* seconds */ + long tv_nsec; /* nanoseconds */ +}; +#endif + +/* Parameters used to convert the timespec values: */ +#define MSEC_PER_SEC 1000L +#define USEC_PER_MSEC 1000L +#define NSEC_PER_USEC 1000L +#define NSEC_PER_MSEC 1000000L +#define USEC_PER_SEC 1000000L +#define NSEC_PER_SEC 1000000000L +#define FSEC_PER_SEC 1000000000000000LL + +/* Located here for timespec[64]_valid_strict */ +#define KTIME_MAX ((s64)~((u64)1 << 63)) +#define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) + +#if __BITS_PER_LONG == 64 + +# define timespec64_equal timespec_equal +# define timespec64_compare timespec_compare +# define set_normalized_timespec64 set_normalized_timespec +# define timespec64_add_safe timespec_add_safe +# define timespec64_add timespec_add +# define timespec64_sub timespec_sub +# define timespec64_valid timespec_valid +# define timespec64_valid_strict timespec_valid_strict +# define timespec64_to_ns timespec_to_ns +# define ns_to_timespec64 ns_to_timespec +# define timespec64_add_ns timespec_add_ns + +#else + +static inline int timespec64_equal(const struct timespec64 *a, + const struct timespec64 *b) +{ + return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); +} + +/* + * lhs < rhs: return <0 + * lhs == rhs: return 0 + * lhs > rhs: return >0 + */ +static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) +{ + if (lhs->tv_sec < rhs->tv_sec) + return -1; + if (lhs->tv_sec > rhs->tv_sec) + return 1; + return lhs->tv_nsec - rhs->tv_nsec; +} + +extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); + +/* + * timespec64_add_safe assumes both values are positive and checks for + * overflow. It will return TIME_T_MAX if the returned value would be + * smaller then either of the arguments. + */ +extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, + const struct timespec64 rhs); + + +static inline struct timespec64 timespec64_add(struct timespec64 lhs, + struct timespec64 rhs) +{ + struct timespec64 ts_delta; + set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, + lhs.tv_nsec + rhs.tv_nsec); + return ts_delta; +} + +/* + * sub = lhs - rhs, in normalized form + */ +static inline struct timespec64 timespec64_sub(struct timespec64 lhs, + struct timespec64 rhs) +{ + struct timespec64 ts_delta; + set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, + lhs.tv_nsec - rhs.tv_nsec); + return ts_delta; +} + +/* + * Returns true if the timespec64 is norm, false if denorm: + */ +static inline bool timespec64_valid(const struct timespec64 *ts) +{ + /* Dates before 1970 are bogus */ + if (ts->tv_sec < 0) + return false; + /* Can't have more nanoseconds then a second */ + if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) + return false; + return true; +} + +static inline bool timespec64_valid_strict(const struct timespec64 *ts) +{ + if (!timespec64_valid(ts)) + return false; + /* Disallow values that could overflow ktime_t */ + if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) + return false; + return true; +} + +/** + * timespec64_to_ns - Convert timespec64 to nanoseconds + * @ts: pointer to the timespec64 variable to be converted + * + * Returns the scalar nanosecond representation of the timespec64 + * parameter. + */ +static inline s64 timespec64_to_ns(const struct timespec64 *ts) +{ + return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; +} + +/** + * ns_to_timespec64 - Convert nanoseconds to timespec64 + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec64 representation of the nsec parameter. + */ +extern struct timespec64 ns_to_timespec64(const s64 nsec); + +/** + * timespec64_add_ns - Adds nanoseconds to a timespec64 + * @a: pointer to timespec64 to be incremented + * @ns: unsigned nanoseconds value to be added + * + * This must always be inlined because its used from the x86-64 vdso, + * which cannot call other kernel functions. + */ +static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) +{ + a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); + a->tv_nsec = ns; +} + +#endif + +#endif /* _LINUX_TIME64_H */ -- cgit v1.2.3 From 49cd6f869984692547c57621bf42697aaa7f5622 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 16 Jul 2014 21:03:59 +0000 Subject: time: More core infrastructure for timespec64 Helper and conversion functions for timespec64. Signed-off-by: John Stultz Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/ktime.h | 28 +++++++++++++++++++++++ include/linux/time64.h | 28 +++++++++++++++++++++++ kernel/time/time.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 118 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 538c283714e1..da6b680c252b 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -83,6 +83,12 @@ static inline ktime_t timespec_to_ktime(struct timespec ts) return ktime_set(ts.tv_sec, ts.tv_nsec); } +/* convert a timespec64 to ktime_t format: */ +static inline ktime_t timespec64_to_ktime(struct timespec64 ts) +{ + return ktime_set(ts.tv_sec, ts.tv_nsec); +} + /* convert a timeval to ktime_t format: */ static inline ktime_t timeval_to_ktime(struct timeval tv) { @@ -92,6 +98,9 @@ static inline ktime_t timeval_to_ktime(struct timeval tv) /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec(kt) ns_to_timespec((kt).tv64) +/* Map the ktime_t to timespec conversion to ns_to_timespec function */ +#define ktime_to_timespec64(kt) ns_to_timespec64((kt).tv64) + /* Map the ktime_t to timeval conversion to ns_to_timeval function */ #define ktime_to_timeval(kt) ns_to_timeval((kt).tv64) @@ -213,6 +222,25 @@ static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt, } } +/** + * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64 + * format only if the variable contains data + * @kt: the ktime_t variable to convert + * @ts: the timespec variable to store the result in + * + * Return: %true if there was a successful conversion, %false if kt was 0. + */ +static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt, + struct timespec64 *ts) +{ + if (kt.tv64) { + *ts = ktime_to_timespec64(kt); + return true; + } else { + return false; + } +} + /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an diff --git a/include/linux/time64.h b/include/linux/time64.h index e7b499e1cd79..a3831478d9cf 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -33,6 +33,16 @@ struct timespec64 { #if __BITS_PER_LONG == 64 +static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) +{ + return ts64; +} + +static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) +{ + return ts; +} + # define timespec64_equal timespec_equal # define timespec64_compare timespec_compare # define set_normalized_timespec64 set_normalized_timespec @@ -47,6 +57,24 @@ struct timespec64 { #else +static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) +{ + struct timespec ret; + + ret.tv_sec = (time_t)ts64.tv_sec; + ret.tv_nsec = ts64.tv_nsec; + return ret; +} + +static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) +{ + struct timespec64 ret; + + ret.tv_sec = ts.tv_sec; + ret.tv_nsec = ts.tv_nsec; + return ret; +} + static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { diff --git a/kernel/time/time.c b/kernel/time/time.c index 7c7964c33ae7..e8121a67fd74 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -420,6 +420,68 @@ struct timeval ns_to_timeval(const s64 nsec) } EXPORT_SYMBOL(ns_to_timeval); +#if BITS_PER_LONG == 32 +/** + * set_normalized_timespec - set timespec sec and nsec parts and normalize + * + * @ts: pointer to timespec variable to be set + * @sec: seconds to set + * @nsec: nanoseconds to set + * + * Set seconds and nanoseconds field of a timespec variable and + * normalize to the timespec storage format + * + * Note: The tv_nsec part is always in the range of + * 0 <= tv_nsec < NSEC_PER_SEC + * For negative values only the tv_sec field is negative ! + */ +void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) +{ + while (nsec >= NSEC_PER_SEC) { + /* + * The following asm() prevents the compiler from + * optimising this loop into a modulo operation. See + * also __iter_div_u64_rem() in include/linux/time.h + */ + asm("" : "+rm"(nsec)); + nsec -= NSEC_PER_SEC; + ++sec; + } + while (nsec < 0) { + asm("" : "+rm"(nsec)); + nsec += NSEC_PER_SEC; + --sec; + } + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} +EXPORT_SYMBOL(set_normalized_timespec64); + +/** + * ns_to_timespec64 - Convert nanoseconds to timespec64 + * @nsec: the nanoseconds value to be converted + * + * Returns the timespec64 representation of the nsec parameter. + */ +struct timespec64 ns_to_timespec64(const s64 nsec) +{ + struct timespec64 ts; + s32 rem; + + if (!nsec) + return (struct timespec64) {0, 0}; + + ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); + if (unlikely(rem < 0)) { + ts.tv_sec--; + rem += NSEC_PER_SEC; + } + ts.tv_nsec = rem; + + return ts; +} +EXPORT_SYMBOL(ns_to_timespec64); +#endif /* * When we convert to jiffies then we interpret incoming values * the following way: -- cgit v1.2.3 From 7d489d15ce4be5310ca60e5896df833f9b3b4088 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 16 Jul 2014 21:04:01 +0000 Subject: timekeeping: Convert timekeeping core to use timespec64s Convert the core timekeeping logic to use timespec64s. This moves the 2038 issues out of the core logic and into all of the accessor functions. Future changes will need to push the timespec64s out to all timekeeping users, but that can be done interface by interface. Signed-off-by: John Stultz Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 10 +-- kernel/time/ntp.c | 8 +- kernel/time/ntp_internal.h | 2 +- kernel/time/timekeeping.c | 172 ++++++++++++++++++++---------------- kernel/time/timekeeping_debug.c | 2 +- kernel/time/timekeeping_internal.h | 2 +- 6 files changed, 109 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index c1825eb436ed..1b05491e10f9 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -55,15 +55,15 @@ struct timekeeper { * - wall_to_monotonic is no longer the boot time, getboottime must be * used instead. */ - struct timespec wall_to_monotonic; + struct timespec64 wall_to_monotonic; /* Offset clock monotonic -> clock realtime */ ktime_t offs_real; /* time spent in suspend */ - struct timespec total_sleep_time; + struct timespec64 total_sleep_time; /* Offset clock monotonic -> clock boottime */ ktime_t offs_boot; /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ - struct timespec raw_time; + struct timespec64 raw_time; /* The current UTC to TAI offset in seconds */ s32 tai_offset; /* Offset clock monotonic -> clock tai */ @@ -71,9 +71,9 @@ struct timekeeper { }; -static inline struct timespec tk_xtime(struct timekeeper *tk) +static inline struct timespec64 tk_xtime(struct timekeeper *tk) { - struct timespec ts; + struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 33db43a39515..6e87df94122f 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -531,7 +531,7 @@ void ntp_notify_cmos_timer(void) { } /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(struct timex *txc, struct timespec *ts) +static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -554,7 +554,7 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts) static inline void process_adjtimex_modes(struct timex *txc, - struct timespec *ts, + struct timespec64 *ts, s32 *time_tai) { if (txc->modes & ADJ_STATUS) @@ -640,7 +640,7 @@ int ntp_validate_timex(struct timex *txc) * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai) +int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) { int result; @@ -684,7 +684,7 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai) /* fill PPS status fields */ pps_fill_timex(txc); - txc->time.tv_sec = ts->tv_sec; + txc->time.tv_sec = (time_t)ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; if (!(time_status & STA_NANO)) txc->time.tv_usec /= NSEC_PER_USEC; diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 1950cb4ca2a4..bbd102ad9df7 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -7,6 +7,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern int second_overflow(unsigned long secs); extern int ntp_validate_timex(struct timex *); -extern int __do_adjtimex(struct timex *, struct timespec *, s32 *); +extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); extern void __hardpps(const struct timespec *, const struct timespec *); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index cafef242d8f9..84a2075c3eb4 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -51,43 +51,43 @@ static inline void tk_normalize_xtime(struct timekeeper *tk) } } -static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts) +static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->xtime_nsec = (u64)ts->tv_nsec << tk->shift; } -static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts) +static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift; tk_normalize_xtime(tk); } -static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm) +static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { - struct timespec tmp; + struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ - set_normalized_timespec(&tmp, -tk->wall_to_monotonic.tv_sec, + set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); - WARN_ON_ONCE(tk->offs_real.tv64 != timespec_to_ktime(tmp).tv64); + WARN_ON_ONCE(tk->offs_real.tv64 != timespec64_to_ktime(tmp).tv64); tk->wall_to_monotonic = wtm; - set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec); - tk->offs_real = timespec_to_ktime(tmp); + set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); + tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } -static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t) +static void tk_set_sleep_time(struct timekeeper *tk, struct timespec64 t) { /* Verify consistency before modifying */ - WARN_ON_ONCE(tk->offs_boot.tv64 != timespec_to_ktime(tk->total_sleep_time).tv64); + WARN_ON_ONCE(tk->offs_boot.tv64 != timespec64_to_ktime(tk->total_sleep_time).tv64); tk->total_sleep_time = t; - tk->offs_boot = timespec_to_ktime(t); + tk->offs_boot = timespec64_to_ktime(t); } /** @@ -281,7 +281,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) tk_normalize_xtime(tk); nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); - timespec_add_ns(&tk->raw_time, nsec); + timespec64_add_ns(&tk->raw_time, nsec); } /** @@ -360,7 +360,7 @@ EXPORT_SYMBOL_GPL(ktime_get); void ktime_get_ts(struct timespec *ts) { struct timekeeper *tk = &timekeeper; - struct timespec tomono; + struct timespec64 ts64, tomono; s64 nsec; unsigned int seq; @@ -368,15 +368,16 @@ void ktime_get_ts(struct timespec *ts) do { seq = read_seqcount_begin(&timekeeper_seq); - ts->tv_sec = tk->xtime_sec; + ts64.tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(tk); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&timekeeper_seq, seq)); - ts->tv_sec += tomono.tv_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, nsec + tomono.tv_nsec); + ts64.tv_sec += tomono.tv_sec; + ts64.tv_nsec = 0; + timespec64_add_ns(&ts64, nsec + tomono.tv_nsec); + *ts = timespec64_to_timespec(ts64); } EXPORT_SYMBOL_GPL(ktime_get_ts); @@ -390,6 +391,7 @@ EXPORT_SYMBOL_GPL(ktime_get_ts); void timekeeping_clocktai(struct timespec *ts) { struct timekeeper *tk = &timekeeper; + struct timespec64 ts64; unsigned long seq; u64 nsecs; @@ -398,13 +400,14 @@ void timekeeping_clocktai(struct timespec *ts) do { seq = read_seqcount_begin(&timekeeper_seq); - ts->tv_sec = tk->xtime_sec + tk->tai_offset; + ts64.tv_sec = tk->xtime_sec + tk->tai_offset; nsecs = timekeeping_get_ns(tk); } while (read_seqcount_retry(&timekeeper_seq, seq)); - ts->tv_nsec = 0; - timespec_add_ns(ts, nsecs); + ts64.tv_nsec = 0; + timespec64_add_ns(&ts64, nsecs); + *ts = timespec64_to_timespec(ts64); } EXPORT_SYMBOL(timekeeping_clocktai); @@ -446,7 +449,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) do { seq = read_seqcount_begin(&timekeeper_seq); - *ts_raw = tk->raw_time; + *ts_raw = timespec64_to_timespec(tk->raw_time); ts_real->tv_sec = tk->xtime_sec; ts_real->tv_nsec = 0; @@ -487,7 +490,7 @@ EXPORT_SYMBOL(do_gettimeofday); int do_settimeofday(const struct timespec *tv) { struct timekeeper *tk = &timekeeper; - struct timespec ts_delta, xt; + struct timespec64 ts_delta, xt, tmp; unsigned long flags; if (!timespec_valid_strict(tv)) @@ -502,9 +505,10 @@ int do_settimeofday(const struct timespec *tv) ts_delta.tv_sec = tv->tv_sec - xt.tv_sec; ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec; - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, ts_delta)); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); - tk_set_xtime(tk, tv); + tmp = timespec_to_timespec64(*tv); + tk_set_xtime(tk, &tmp); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); @@ -528,26 +532,28 @@ int timekeeping_inject_offset(struct timespec *ts) { struct timekeeper *tk = &timekeeper; unsigned long flags; - struct timespec tmp; + struct timespec64 ts64, tmp; int ret = 0; if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; + ts64 = timespec_to_timespec64(*ts); + raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&timekeeper_seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ - tmp = timespec_add(tk_xtime(tk), *ts); - if (!timespec_valid_strict(&tmp)) { + tmp = timespec64_add(tk_xtime(tk), ts64); + if (!timespec64_valid_strict(&tmp)) { ret = -EINVAL; goto error; } - tk_xtime_add(tk, ts); - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); + tk_xtime_add(tk, &ts64); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts64)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); @@ -691,17 +697,19 @@ EXPORT_SYMBOL_GPL(ktime_get_real); void getrawmonotonic(struct timespec *ts) { struct timekeeper *tk = &timekeeper; + struct timespec64 ts64; unsigned long seq; s64 nsecs; do { seq = read_seqcount_begin(&timekeeper_seq); nsecs = timekeeping_get_ns_raw(tk); - *ts = tk->raw_time; + ts64 = tk->raw_time; } while (read_seqcount_retry(&timekeeper_seq, seq)); - timespec_add_ns(ts, nsecs); + timespec64_add_ns(&ts64, nsecs); + *ts = timespec64_to_timespec(ts64); } EXPORT_SYMBOL(getrawmonotonic); @@ -781,11 +789,12 @@ void __init timekeeping_init(void) struct timekeeper *tk = &timekeeper; struct clocksource *clock; unsigned long flags; - struct timespec now, boot, tmp; - - read_persistent_clock(&now); + struct timespec64 now, boot, tmp; + struct timespec ts; - if (!timespec_valid_strict(&now)) { + read_persistent_clock(&ts); + now = timespec_to_timespec64(ts); + if (!timespec64_valid_strict(&now)) { pr_warn("WARNING: Persistent clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); now.tv_sec = 0; @@ -793,8 +802,9 @@ void __init timekeeping_init(void) } else if (now.tv_sec || now.tv_nsec) persistent_clock_exist = true; - read_boot_clock(&boot); - if (!timespec_valid_strict(&boot)) { + read_boot_clock(&ts); + boot = timespec_to_timespec64(ts); + if (!timespec64_valid_strict(&boot)) { pr_warn("WARNING: Boot clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); boot.tv_sec = 0; @@ -816,7 +826,7 @@ void __init timekeeping_init(void) if (boot.tv_sec == 0 && boot.tv_nsec == 0) boot = tk_xtime(tk); - set_normalized_timespec(&tmp, -boot.tv_sec, -boot.tv_nsec); + set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); tk_set_wall_to_mono(tk, tmp); tmp.tv_sec = 0; @@ -830,7 +840,7 @@ void __init timekeeping_init(void) } /* time in seconds when suspend began */ -static struct timespec timekeeping_suspend_time; +static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval @@ -840,17 +850,17 @@ static struct timespec timekeeping_suspend_time; * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, - struct timespec *delta) + struct timespec64 *delta) { - if (!timespec_valid_strict(delta)) { + if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); - tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta)); - tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta)); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); + tk_set_sleep_time(tk, timespec64_add(tk->total_sleep_time, *delta)); tk_debug_account_sleep_time(delta); } @@ -867,6 +877,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, void timekeeping_inject_sleeptime(struct timespec *delta) { struct timekeeper *tk = &timekeeper; + struct timespec64 tmp; unsigned long flags; /* @@ -881,7 +892,8 @@ void timekeeping_inject_sleeptime(struct timespec *delta) timekeeping_forward_now(tk); - __timekeeping_inject_sleeptime(tk, delta); + tmp = timespec_to_timespec64(*delta); + __timekeeping_inject_sleeptime(tk, &tmp); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); @@ -904,11 +916,13 @@ static void timekeeping_resume(void) struct timekeeper *tk = &timekeeper; struct clocksource *clock = tk->clock; unsigned long flags; - struct timespec ts_new, ts_delta; + struct timespec64 ts_new, ts_delta; + struct timespec tmp; cycle_t cycle_now, cycle_delta; bool suspendtime_found = false; - read_persistent_clock(&ts_new); + read_persistent_clock(&tmp); + ts_new = timespec_to_timespec64(tmp); clockevents_resume(); clocksource_resume(); @@ -951,10 +965,10 @@ static void timekeeping_resume(void) } nsec += ((u64) cycle_delta * mult) >> shift; - ts_delta = ns_to_timespec(nsec); + ts_delta = ns_to_timespec64(nsec); suspendtime_found = true; - } else if (timespec_compare(&ts_new, &timekeeping_suspend_time) > 0) { - ts_delta = timespec_sub(ts_new, timekeeping_suspend_time); + } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { + ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); suspendtime_found = true; } @@ -981,10 +995,12 @@ static int timekeeping_suspend(void) { struct timekeeper *tk = &timekeeper; unsigned long flags; - struct timespec delta, delta_delta; - static struct timespec old_delta; + struct timespec64 delta, delta_delta; + static struct timespec64 old_delta; + struct timespec tmp; - read_persistent_clock(&timekeeping_suspend_time); + read_persistent_clock(&tmp); + timekeeping_suspend_time = timespec_to_timespec64(tmp); /* * On some systems the persistent_clock can not be detected at @@ -1005,8 +1021,8 @@ static int timekeeping_suspend(void) * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ - delta = timespec_sub(tk_xtime(tk), timekeeping_suspend_time); - delta_delta = timespec_sub(delta, old_delta); + delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); + delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction @@ -1016,7 +1032,7 @@ static int timekeeping_suspend(void) } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = - timespec_add(timekeeping_suspend_time, delta_delta); + timespec64_add(timekeeping_suspend_time, delta_delta); } timekeeping_update(tk, TK_MIRROR); @@ -1253,14 +1269,14 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { - struct timespec ts; + struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, - timespec_sub(tk->wall_to_monotonic, ts)); + timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); @@ -1469,7 +1485,7 @@ EXPORT_SYMBOL_GPL(getboottime); void get_monotonic_boottime(struct timespec *ts) { struct timekeeper *tk = &timekeeper; - struct timespec tomono, sleep; + struct timespec64 tomono, sleep, ret; s64 nsec; unsigned int seq; @@ -1477,16 +1493,17 @@ void get_monotonic_boottime(struct timespec *ts) do { seq = read_seqcount_begin(&timekeeper_seq); - ts->tv_sec = tk->xtime_sec; + ret.tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(tk); tomono = tk->wall_to_monotonic; sleep = tk->total_sleep_time; } while (read_seqcount_retry(&timekeeper_seq, seq)); - ts->tv_sec += tomono.tv_sec + sleep.tv_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, nsec + tomono.tv_nsec + sleep.tv_nsec); + ret.tv_sec += tomono.tv_sec + sleep.tv_sec; + ret.tv_nsec = 0; + timespec64_add_ns(&ret, nsec + tomono.tv_nsec + sleep.tv_nsec); + *ts = timespec64_to_timespec(ret); } EXPORT_SYMBOL_GPL(get_monotonic_boottime); @@ -1514,8 +1531,11 @@ EXPORT_SYMBOL_GPL(ktime_get_boottime); void monotonic_to_bootbased(struct timespec *ts) { struct timekeeper *tk = &timekeeper; + struct timespec64 ts64; - *ts = timespec_add(*ts, tk->total_sleep_time); + ts64 = timespec_to_timespec64(*ts); + ts64 = timespec64_add(ts64, tk->total_sleep_time); + *ts = timespec64_to_timespec(ts64); } EXPORT_SYMBOL_GPL(monotonic_to_bootbased); @@ -1531,13 +1551,13 @@ struct timespec __current_kernel_time(void) { struct timekeeper *tk = &timekeeper; - return tk_xtime(tk); + return timespec64_to_timespec(tk_xtime(tk)); } struct timespec current_kernel_time(void) { struct timekeeper *tk = &timekeeper; - struct timespec now; + struct timespec64 now; unsigned long seq; do { @@ -1546,14 +1566,14 @@ struct timespec current_kernel_time(void) now = tk_xtime(tk); } while (read_seqcount_retry(&timekeeper_seq, seq)); - return now; + return timespec64_to_timespec(now); } EXPORT_SYMBOL(current_kernel_time); struct timespec get_monotonic_coarse(void) { struct timekeeper *tk = &timekeeper; - struct timespec now, mono; + struct timespec64 now, mono; unsigned long seq; do { @@ -1563,9 +1583,10 @@ struct timespec get_monotonic_coarse(void) mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&timekeeper_seq, seq)); - set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, + set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); - return now; + + return timespec64_to_timespec(now); } /* @@ -1589,7 +1610,7 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &timekeeper; - struct timespec ts; + struct timespec64 ts; ktime_t now; unsigned int seq; @@ -1597,7 +1618,6 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, seq = read_seqcount_begin(&timekeeper_seq); ts = tk_xtime(tk); - *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; @@ -1650,14 +1670,14 @@ ktime_t ktime_get_monotonic_offset(void) { struct timekeeper *tk = &timekeeper; unsigned long seq; - struct timespec wtom; + struct timespec64 wtom; do { seq = read_seqcount_begin(&timekeeper_seq); wtom = tk->wall_to_monotonic; } while (read_seqcount_retry(&timekeeper_seq, seq)); - return timespec_to_ktime(wtom); + return timespec64_to_ktime(wtom); } EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset); @@ -1668,7 +1688,8 @@ int do_adjtimex(struct timex *txc) { struct timekeeper *tk = &timekeeper; unsigned long flags; - struct timespec ts; + struct timespec64 ts; + struct timespec tmp; s32 orig_tai, tai; int ret; @@ -1688,7 +1709,8 @@ int do_adjtimex(struct timex *txc) return ret; } - getnstimeofday(&ts); + getnstimeofday(&tmp); + ts = timespec_to_timespec64(tmp); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&timekeeper_seq); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 4d54f97558df..f6bd65236712 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -67,7 +67,7 @@ static int __init tk_debug_sleep_time_init(void) } late_initcall(tk_debug_sleep_time_init); -void tk_debug_account_sleep_time(struct timespec *t) +void tk_debug_account_sleep_time(struct timespec64 *t) { sleep_time_bin[fls(t->tv_sec)]++; } diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 13323ea08ffa..e3d28ad236f9 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -6,7 +6,7 @@ #include #ifdef CONFIG_DEBUG_FS -extern void tk_debug_account_sleep_time(struct timespec *t); +extern void tk_debug_account_sleep_time(struct timespec64 *t); #else #define tk_debug_account_sleep_time(x) #endif -- cgit v1.2.3 From 8b094cd03b4a3793220d8d8d86a173bfea8c285b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:02 +0000 Subject: time: Consolidate the time accessor prototypes Right now we have time related prototypes in 3 different header files. Move it to a single timekeeping header file and move the core internal stuff into a core private header. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/hrtimer.h | 11 ------- include/linux/ktime.h | 8 ++--- include/linux/time.h | 45 +++----------------------- include/linux/timekeeping.h | 78 +++++++++++++++++++++++++++++++++++++++++++++ kernel/time/hrtimer.c | 2 ++ kernel/time/posix-timers.c | 2 ++ kernel/time/tick-internal.h | 2 ++ kernel/time/time.c | 1 + kernel/time/timekeeping.h | 20 ++++++++++++ 9 files changed, 111 insertions(+), 58 deletions(-) create mode 100644 include/linux/timekeeping.h create mode 100644 kernel/time/timekeeping.h (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index adf5056bd7b3..a036d058a249 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -326,17 +326,6 @@ static inline void timerfd_clock_was_set(void) { } #endif extern void hrtimers_resume(void); -extern ktime_t ktime_get(void); -extern ktime_t ktime_get_real(void); -extern ktime_t ktime_get_boottime(void); -extern ktime_t ktime_get_monotonic_offset(void); -extern ktime_t ktime_get_clocktai(void); -extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, - ktime_t *offs_boot, - ktime_t *offs_tai); -extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, - ktime_t *offs_boot, - ktime_t *offs_tai); DECLARE_PER_CPU(struct tick_device, tick_cpu_device); diff --git a/include/linux/ktime.h b/include/linux/ktime.h index da6b680c252b..c9d645ad98ff 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -250,12 +250,6 @@ static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt, #define LOW_RES_NSEC TICK_NSEC #define KTIME_LOW_RES (ktime_t){ .tv64 = LOW_RES_NSEC } -/* Get the monotonic time in timespec format: */ -extern void ktime_get_ts(struct timespec *ts); - -/* Get the real (wall-) time in timespec format: */ -#define ktime_get_real_ts(ts) getnstimeofday(ts) - static inline ktime_t ns_to_ktime(u64 ns) { static const ktime_t ktime_zero = { .tv64 = 0 }; @@ -270,4 +264,6 @@ static inline ktime_t ms_to_ktime(u64 ms) return ktime_add_ms(ktime_zero, ms); } +# include + #endif diff --git a/include/linux/time.h b/include/linux/time.h index 234feac7f1c3..8c42cf8d2444 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -99,25 +99,7 @@ static inline bool timespec_valid_strict(const struct timespec *ts) return true; } -extern bool persistent_clock_exist; - -static inline bool has_persistent_clock(void) -{ - return persistent_clock_exist; -} - -extern void read_persistent_clock(struct timespec *ts); -extern void read_boot_clock(struct timespec *ts); -extern int persistent_clock_is_local; -extern int update_persistent_clock(struct timespec now); -void timekeeping_init(void); -extern int timekeeping_suspended; - -unsigned long get_seconds(void); -struct timespec current_kernel_time(void); -struct timespec __current_kernel_time(void); /* does not take xtime_lock */ -struct timespec get_monotonic_coarse(void); -void timekeeping_inject_sleeptime(struct timespec *delta); +extern struct timespec timespec_trunc(struct timespec t, unsigned gran); #define CURRENT_TIME (current_kernel_time()) #define CURRENT_TIME_SEC ((struct timespec) { get_seconds(), 0 }) @@ -135,33 +117,14 @@ void timekeeping_inject_sleeptime(struct timespec *delta); extern u32 (*arch_gettimeoffset)(void); #endif -extern void do_gettimeofday(struct timeval *tv); -extern int do_settimeofday(const struct timespec *tv); -extern int do_sys_settimeofday(const struct timespec *tv, - const struct timezone *tz); -#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) -extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); struct itimerval; extern int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue); -extern unsigned int alarm_setitimer(unsigned int seconds); extern int do_getitimer(int which, struct itimerval *value); -extern int __getnstimeofday(struct timespec *tv); -extern void getnstimeofday(struct timespec *tv); -extern void getrawmonotonic(struct timespec *ts); -extern void getnstime_raw_and_real(struct timespec *ts_raw, - struct timespec *ts_real); -extern void getboottime(struct timespec *ts); -extern void monotonic_to_bootbased(struct timespec *ts); -extern void get_monotonic_boottime(struct timespec *ts); -extern struct timespec timespec_trunc(struct timespec t, unsigned gran); -extern int timekeeping_valid_for_hres(void); -extern u64 timekeeping_max_deferment(void); -extern int timekeeping_inject_offset(struct timespec *ts); -extern s32 timekeeping_get_tai_offset(void); -extern void timekeeping_set_tai_offset(s32 tai_offset); -extern void timekeeping_clocktai(struct timespec *ts); +extern unsigned int alarm_setitimer(unsigned int seconds); + +extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); struct tms; extern void do_sys_times(struct tms *); diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h new file mode 100644 index 000000000000..e81c35b71da7 --- /dev/null +++ b/include/linux/timekeeping.h @@ -0,0 +1,78 @@ +#ifndef _LINUX_TIMEKEEPING_H +#define _LINUX_TIMEKEEPING_H + +/* Included from linux/ktime.h */ + +void timekeeping_init(void); +extern int timekeeping_suspended; + +/* + * Get and set timeofday + */ +extern void do_gettimeofday(struct timeval *tv); +extern int do_settimeofday(const struct timespec *tv); +extern int do_sys_settimeofday(const struct timespec *tv, + const struct timezone *tz); + +/* + * Kernel time accessors + */ +unsigned long get_seconds(void); +struct timespec current_kernel_time(void); +/* does not take xtime_lock */ +struct timespec __current_kernel_time(void); + +/* + * timespec based interfaces + */ +struct timespec get_monotonic_coarse(void); +extern void getrawmonotonic(struct timespec *ts); +extern void monotonic_to_bootbased(struct timespec *ts); +extern void get_monotonic_boottime(struct timespec *ts); +extern void ktime_get_ts(struct timespec *ts); + +extern int __getnstimeofday(struct timespec *tv); +extern void getnstimeofday(struct timespec *tv); +extern void getboottime(struct timespec *ts); + +#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) +#define ktime_get_real_ts(ts) getnstimeofday(ts) + + +/* + * ktime_t based interfaces + */ +extern ktime_t ktime_get(void); +extern ktime_t ktime_get_real(void); +extern ktime_t ktime_get_boottime(void); +extern ktime_t ktime_get_monotonic_offset(void); +extern ktime_t ktime_get_clocktai(void); + +/* + * RTC specific + */ +extern void timekeeping_inject_sleeptime(struct timespec *delta); + +/* + * PPS accessor + */ +extern void getnstime_raw_and_real(struct timespec *ts_raw, + struct timespec *ts_real); + +/* + * Persistent clock related interfaces + */ +extern bool persistent_clock_exist; +extern int persistent_clock_is_local; + +static inline bool has_persistent_clock(void) +{ + return persistent_clock_exist; +} + +extern void read_persistent_clock(struct timespec *ts); +extern void read_boot_clock(struct timespec *ts); +extern int update_persistent_clock(struct timespec now); + + +#endif diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 64843a836637..1c2fe7de2842 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -54,6 +54,8 @@ #include +#include "timekeeping.h" + /* * The timer bases: * diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 424c2d4265c9..42b463ad90f2 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -49,6 +49,8 @@ #include #include +#include "timekeeping.h" + /* * Management arrays for POSIX timers. Timers are now kept in static hash table * with 512 entries. diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 7ab92b19965a..c19c1d84b6f3 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -4,6 +4,8 @@ #include #include +#include "timekeeping.h" + extern seqlock_t jiffies_lock; #define CS_NAME_LEN 32 diff --git a/kernel/time/time.c b/kernel/time/time.c index e8121a67fd74..278c63cc8054 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -42,6 +42,7 @@ #include #include "timeconst.h" +#include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h new file mode 100644 index 000000000000..adc1fc98bde3 --- /dev/null +++ b/kernel/time/timekeeping.h @@ -0,0 +1,20 @@ +#ifndef _KERNEL_TIME_TIMEKEEPING_H +#define _KERNEL_TIME_TIMEKEEPING_H +/* + * Internal interfaces for kernel/time/ + */ +extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); +extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); + +extern int timekeeping_valid_for_hres(void); +extern u64 timekeeping_max_deferment(void); +extern int timekeeping_inject_offset(struct timespec *ts); +extern s32 timekeeping_get_tai_offset(void); +extern void timekeeping_set_tai_offset(s32 tai_offset); +extern void timekeeping_clocktai(struct timespec *ts); + +#endif -- cgit v1.2.3 From d6d29896c665dfd50e6e0be7a9039901640433a3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:04 +0000 Subject: timekeeping: Provide timespec64 based interfaces To convert callers of the core code to timespec64 we need to provide the proper interfaces. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 66 +++++++++++++++++++++++++++++++++++++++++---- kernel/time/ntp.c | 7 ++--- kernel/time/timekeeping.c | 47 +++++++++++++++----------------- 3 files changed, 87 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index e81c35b71da7..3eb19e34cc20 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -29,15 +29,71 @@ struct timespec get_monotonic_coarse(void); extern void getrawmonotonic(struct timespec *ts); extern void monotonic_to_bootbased(struct timespec *ts); extern void get_monotonic_boottime(struct timespec *ts); -extern void ktime_get_ts(struct timespec *ts); +extern void ktime_get_ts64(struct timespec64 *ts); + +extern int __getnstimeofday64(struct timespec64 *tv); +extern void getnstimeofday64(struct timespec64 *tv); + +#if BITS_PER_LONG == 64 +static inline int __getnstimeofday(struct timespec *ts) +{ + return __getnstimeofday64(ts); +} + +static inline void getnstimeofday(struct timespec *ts) +{ + getnstimeofday64(ts); +} + +static inline void ktime_get_ts(struct timespec *ts) +{ + ktime_get_ts64(ts); +} + +static inline void ktime_get_real_ts(struct timespec *ts) +{ + getnstimeofday64(ts); +} + +#else +static inline int __getnstimeofday(struct timespec *ts) +{ + struct timespec64 ts64; + int ret = __getnstimeofday64(&ts64); + + *ts = timespec64_to_timespec(ts64); + return ret; +} + +static inline void getnstimeofday(struct timespec *ts) +{ + struct timespec64 ts64; + + getnstimeofday64(&ts64); + *ts = timespec64_to_timespec(ts64); +} + +static inline void ktime_get_ts(struct timespec *ts) +{ + struct timespec64 ts64; + + ktime_get_ts64(&ts64); + *ts = timespec64_to_timespec(ts64); +} + +static inline void ktime_get_real_ts(struct timespec *ts) +{ + struct timespec64 ts64; + + getnstimeofday64(&ts64); + *ts = timespec64_to_timespec(ts64); +} +#endif -extern int __getnstimeofday(struct timespec *tv); -extern void getnstimeofday(struct timespec *tv); extern void getboottime(struct timespec *ts); #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) -#define ktime_get_real_ts(ts) getnstimeofday(ts) - +#define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* * ktime_t based interfaces diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 6e87df94122f..87a346fd6d61 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -466,7 +466,8 @@ static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); static void sync_cmos_clock(struct work_struct *work) { - struct timespec now, next; + struct timespec64 now; + struct timespec next; int fail = 1; /* @@ -485,9 +486,9 @@ static void sync_cmos_clock(struct work_struct *work) return; } - getnstimeofday(&now); + getnstimeofday64(&now); if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) { - struct timespec adjust = now; + struct timespec adjust = timespec64_to_timespec(now); fail = -ENODEV; if (persistent_clock_is_local) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 84a2075c3eb4..3210c9e690c5 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -285,13 +285,13 @@ static void timekeeping_forward_now(struct timekeeper *tk) } /** - * __getnstimeofday - Returns the time of day in a timespec. + * __getnstimeofday64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Updates the time of day in the timespec. * Returns 0 on success, or -ve when suspended (timespec will be undefined). */ -int __getnstimeofday(struct timespec *ts) +int __getnstimeofday64(struct timespec64 *ts) { struct timekeeper *tk = &timekeeper; unsigned long seq; @@ -306,7 +306,7 @@ int __getnstimeofday(struct timespec *ts) } while (read_seqcount_retry(&timekeeper_seq, seq)); ts->tv_nsec = 0; - timespec_add_ns(ts, nsecs); + timespec64_add_ns(ts, nsecs); /* * Do not bail out early, in case there were callers still using @@ -316,19 +316,19 @@ int __getnstimeofday(struct timespec *ts) return -EAGAIN; return 0; } -EXPORT_SYMBOL(__getnstimeofday); +EXPORT_SYMBOL(__getnstimeofday64); /** - * getnstimeofday - Returns the time of day in a timespec. + * getnstimeofday64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec (WARN if suspended). */ -void getnstimeofday(struct timespec *ts) +void getnstimeofday64(struct timespec64 *ts) { - WARN_ON(__getnstimeofday(ts)); + WARN_ON(__getnstimeofday64(ts)); } -EXPORT_SYMBOL(getnstimeofday); +EXPORT_SYMBOL(getnstimeofday64); ktime_t ktime_get(void) { @@ -350,17 +350,17 @@ ktime_t ktime_get(void) EXPORT_SYMBOL_GPL(ktime_get); /** - * ktime_get_ts - get the monotonic clock in timespec format + * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec format in the variable pointed to by @ts. */ -void ktime_get_ts(struct timespec *ts) +void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &timekeeper; - struct timespec64 ts64, tomono; + struct timespec64 tomono; s64 nsec; unsigned int seq; @@ -368,18 +368,17 @@ void ktime_get_ts(struct timespec *ts) do { seq = read_seqcount_begin(&timekeeper_seq); - ts64.tv_sec = tk->xtime_sec; + ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(tk); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&timekeeper_seq, seq)); - ts64.tv_sec += tomono.tv_sec; - ts64.tv_nsec = 0; - timespec64_add_ns(&ts64, nsec + tomono.tv_nsec); - *ts = timespec64_to_timespec(ts64); + ts->tv_sec += tomono.tv_sec; + ts->tv_nsec = 0; + timespec64_add_ns(ts, nsec + tomono.tv_nsec); } -EXPORT_SYMBOL_GPL(ktime_get_ts); +EXPORT_SYMBOL_GPL(ktime_get_ts64); /** @@ -473,9 +472,9 @@ EXPORT_SYMBOL(getnstime_raw_and_real); */ void do_gettimeofday(struct timeval *tv) { - struct timespec now; + struct timespec64 now; - getnstimeofday(&now); + getnstimeofday64(&now); tv->tv_sec = now.tv_sec; tv->tv_usec = now.tv_nsec/1000; } @@ -680,11 +679,11 @@ int timekeeping_notify(struct clocksource *clock) */ ktime_t ktime_get_real(void) { - struct timespec now; + struct timespec64 now; - getnstimeofday(&now); + getnstimeofday64(&now); - return timespec_to_ktime(now); + return timespec64_to_ktime(now); } EXPORT_SYMBOL_GPL(ktime_get_real); @@ -1689,7 +1688,6 @@ int do_adjtimex(struct timex *txc) struct timekeeper *tk = &timekeeper; unsigned long flags; struct timespec64 ts; - struct timespec tmp; s32 orig_tai, tai; int ret; @@ -1709,8 +1707,7 @@ int do_adjtimex(struct timex *txc) return ret; } - getnstimeofday(&tmp); - ts = timespec_to_timespec64(tmp); + getnstimeofday64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&timekeeper_seq); -- cgit v1.2.3 From c905fae43f61c2b4508fc01722e8db61b6b8ac0b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:05 +0000 Subject: timekeeper: Move tk_xtime to core code No users outside of the core. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 18 ---------- kernel/time/timekeeping.c | 70 +++++++++++++++++++++++-------------- 2 files changed, 43 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 1b05491e10f9..16de6d7c240a 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -71,16 +71,6 @@ struct timekeeper { }; -static inline struct timespec64 tk_xtime(struct timekeeper *tk) -{ - struct timespec64 ts; - - ts.tv_sec = tk->xtime_sec; - ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); - return ts; -} - - #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void update_vsyscall(struct timekeeper *tk); @@ -92,14 +82,6 @@ extern void update_vsyscall_old(struct timespec *ts, struct timespec *wtm, struct clocksource *c, u32 mult); extern void update_vsyscall_tz(void); -static inline void update_vsyscall(struct timekeeper *tk) -{ - struct timespec xt; - - xt = tk_xtime(tk); - update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); -} - #else static inline void update_vsyscall(struct timekeeper *tk) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3210c9e690c5..983d67b388d7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -51,6 +51,15 @@ static inline void tk_normalize_xtime(struct timekeeper *tk) } } +static inline struct timespec64 tk_xtime(struct timekeeper *tk) +{ + struct timespec64 ts; + + ts.tv_sec = tk->xtime_sec; + ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); + return ts; +} + static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; @@ -199,6 +208,40 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) return nsec + arch_gettimeoffset(); } +#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD + +static inline void update_vsyscall(struct timekeeper *tk) +{ + struct timespec xt; + + xt = tk_xtime(tk); + update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); +} + +static inline void old_vsyscall_fixup(struct timekeeper *tk) +{ + s64 remainder; + + /* + * Store only full nanoseconds into xtime_nsec after rounding + * it up and add the remainder to the error difference. + * XXX - This is necessary to avoid small 1ns inconsistnecies caused + * by truncating the remainder in vsyscalls. However, it causes + * additional work to be done in timekeeping_adjust(). Once + * the vsyscall implementations are converted to use xtime_nsec + * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD + * users are removed, this can be killed. + */ + remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); + tk->xtime_nsec -= remainder; + tk->xtime_nsec += 1ULL << tk->shift; + tk->ntp_error += remainder << tk->ntp_error_shift; + tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift; +} +#else +#define old_vsyscall_fixup(tk) +#endif + static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) @@ -1330,33 +1373,6 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, return offset; } -#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD -static inline void old_vsyscall_fixup(struct timekeeper *tk) -{ - s64 remainder; - - /* - * Store only full nanoseconds into xtime_nsec after rounding - * it up and add the remainder to the error difference. - * XXX - This is necessary to avoid small 1ns inconsistnecies caused - * by truncating the remainder in vsyscalls. However, it causes - * additional work to be done in timekeeping_adjust(). Once - * the vsyscall implementations are converted to use xtime_nsec - * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD - * users are removed, this can be killed. - */ - remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); - tk->xtime_nsec -= remainder; - tk->xtime_nsec += 1ULL << tk->shift; - tk->ntp_error += remainder << tk->ntp_error_shift; - tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift; -} -#else -#define old_vsyscall_fixup(tk) -#endif - - - /** * update_wall_time - Uses the current clocksource to increment the wall time * -- cgit v1.2.3 From 3fdb14fd1df70325e1e91e1203a699a4803ed741 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:07 +0000 Subject: timekeeping: Cache optimize struct timekeeper struct timekeeper is quite badly sorted for the hot readout path. Most time access functions need to load two cache lines. Rearrange it so ktime_get() and getnstimeofday() are happy with a single cache line. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 84 ++++++++-------- kernel/time/timekeeping.c | 185 +++++++++++++++++++----------------- 2 files changed, 143 insertions(+), 126 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 16de6d7c240a..2cb96235c249 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -10,7 +10,22 @@ #include #include -/* Structure holding internal timekeeping values. */ +/* + * Structure holding internal timekeeping values. + * + * Note: wall_to_monotonic is what we need to add to xtime (or xtime + * corrected for sub jiffie times) to get to monotonic time. + * Monotonic is pegged at zero at system boot time, so + * wall_to_monotonic will be negative, however, we will ALWAYS keep + * the tv_nsec part positive so we can use the usual normalization. + * + * wall_to_monotonic is moved after resume from suspend for the + * monotonic time not to jump. We need to add total_sleep_time to + * wall_to_monotonic to get the real boot based time offset. + * + * - wall_to_monotonic is no longer the boot time, getboottime must be + * used instead. + */ struct timekeeper { /* Current clocksource used for timekeeping. */ struct clocksource *clock; @@ -18,6 +33,29 @@ struct timekeeper { u32 mult; /* The shift value of the current clocksource. */ u32 shift; + /* Clock shifted nano seconds */ + u64 xtime_nsec; + + /* Current CLOCK_REALTIME time in seconds */ + u64 xtime_sec; + /* CLOCK_REALTIME to CLOCK_MONOTONIC offset */ + struct timespec64 wall_to_monotonic; + + /* Offset clock monotonic -> clock realtime */ + ktime_t offs_real; + /* Offset clock monotonic -> clock boottime */ + ktime_t offs_boot; + /* Offset clock monotonic -> clock tai */ + ktime_t offs_tai; + + /* time spent in suspend */ + struct timespec64 total_sleep_time; + /* The current UTC to TAI offset in seconds */ + s32 tai_offset; + + /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ + struct timespec64 raw_time; + /* Number of clock cycles in one NTP interval. */ cycle_t cycle_interval; /* Last cycle value (also stored in clock->cycle_last) */ @@ -29,46 +67,16 @@ struct timekeeper { /* Raw nano seconds accumulated per NTP interval. */ u32 raw_interval; - /* Current CLOCK_REALTIME time in seconds */ - u64 xtime_sec; - /* Clock shifted nano seconds */ - u64 xtime_nsec; - - /* Difference between accumulated time and NTP time in ntp - * shifted nano seconds. */ + /* + * Difference between accumulated time and NTP time in ntp + * shifted nano seconds. + */ s64 ntp_error; - /* Shift conversion between clock shifted nano seconds and - * ntp shifted nano seconds. */ - u32 ntp_error_shift; - /* - * wall_to_monotonic is what we need to add to xtime (or xtime corrected - * for sub jiffie times) to get to monotonic time. Monotonic is pegged - * at zero at system boot time, so wall_to_monotonic will be negative, - * however, we will ALWAYS keep the tv_nsec part positive so we can use - * the usual normalization. - * - * wall_to_monotonic is moved after resume from suspend for the - * monotonic time not to jump. We need to add total_sleep_time to - * wall_to_monotonic to get the real boot based time offset. - * - * - wall_to_monotonic is no longer the boot time, getboottime must be - * used instead. + * Shift conversion between clock shifted nano seconds and + * ntp shifted nano seconds. */ - struct timespec64 wall_to_monotonic; - /* Offset clock monotonic -> clock realtime */ - ktime_t offs_real; - /* time spent in suspend */ - struct timespec64 total_sleep_time; - /* Offset clock monotonic -> clock boottime */ - ktime_t offs_boot; - /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ - struct timespec64 raw_time; - /* The current UTC to TAI offset in seconds */ - s32 tai_offset; - /* Offset clock monotonic -> clock tai */ - ktime_t offs_tai; - + u32 ntp_error_shift; }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 983d67b388d7..7ca150ad387d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -32,9 +32,16 @@ #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) -static struct timekeeper timekeeper; +/* + * The most important data for readout fits into a single 64 byte + * cache line. + */ +static struct { + seqcount_t seq; + struct timekeeper timekeeper; +} tk_core ____cacheline_aligned; + static DEFINE_RAW_SPINLOCK(timekeeper_lock); -static seqcount_t timekeeper_seq; static struct timekeeper shadow_timekeeper; /* flag for if timekeeping is suspended */ @@ -254,7 +261,7 @@ static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; @@ -295,7 +302,8 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); if (action & TK_MIRROR) - memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); + memcpy(&shadow_timekeeper, &tk_core.timekeeper, + sizeof(tk_core.timekeeper)); } /** @@ -336,17 +344,17 @@ static void timekeeping_forward_now(struct timekeeper *tk) */ int __getnstimeofday64(struct timespec64 *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; s64 nsecs = 0; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(tk); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); @@ -375,18 +383,18 @@ EXPORT_SYMBOL(getnstimeofday64); ktime_t ktime_get(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; s64 secs, nsecs; WARN_ON(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); secs = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; nsecs = timekeeping_get_ns(tk) + tk->wall_to_monotonic.tv_nsec; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_set(secs, nsecs); } @@ -402,7 +410,7 @@ EXPORT_SYMBOL_GPL(ktime_get); */ void ktime_get_ts64(struct timespec64 *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; s64 nsec; unsigned int seq; @@ -410,12 +418,12 @@ void ktime_get_ts64(struct timespec64 *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(tk); tomono = tk->wall_to_monotonic; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; @@ -432,7 +440,7 @@ EXPORT_SYMBOL_GPL(ktime_get_ts64); */ void timekeeping_clocktai(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts64; unsigned long seq; u64 nsecs; @@ -440,12 +448,12 @@ void timekeeping_clocktai(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ts64.tv_sec = tk->xtime_sec + tk->tai_offset; nsecs = timekeeping_get_ns(tk); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); ts64.tv_nsec = 0; timespec64_add_ns(&ts64, nsecs); @@ -482,14 +490,14 @@ EXPORT_SYMBOL(ktime_get_clocktai); */ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; s64 nsecs_raw, nsecs_real; WARN_ON_ONCE(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); *ts_raw = timespec64_to_timespec(tk->raw_time); ts_real->tv_sec = tk->xtime_sec; @@ -498,7 +506,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) nsecs_raw = timekeeping_get_ns_raw(tk); nsecs_real = timekeeping_get_ns(tk); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); timespec_add_ns(ts_raw, nsecs_raw); timespec_add_ns(ts_real, nsecs_real); @@ -531,7 +539,7 @@ EXPORT_SYMBOL(do_gettimeofday); */ int do_settimeofday(const struct timespec *tv) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt, tmp; unsigned long flags; @@ -539,7 +547,7 @@ int do_settimeofday(const struct timespec *tv) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); @@ -554,7 +562,7 @@ int do_settimeofday(const struct timespec *tv) timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -572,7 +580,7 @@ EXPORT_SYMBOL(do_settimeofday); */ int timekeeping_inject_offset(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 ts64, tmp; int ret = 0; @@ -583,7 +591,7 @@ int timekeeping_inject_offset(struct timespec *ts) ts64 = timespec_to_timespec64(*ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); @@ -600,7 +608,7 @@ int timekeeping_inject_offset(struct timespec *ts) error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -617,14 +625,14 @@ EXPORT_SYMBOL(timekeeping_inject_offset); */ s32 timekeeping_get_tai_offset(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; s32 ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ret = tk->tai_offset; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -645,14 +653,14 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) */ void timekeeping_set_tai_offset(s32 tai_offset) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); __timekeeping_set_tai_offset(tk, tai_offset); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); clock_was_set(); } @@ -664,14 +672,14 @@ void timekeeping_set_tai_offset(s32 tai_offset) */ static int change_clocksource(void *data) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old; unsigned long flags; new = (struct clocksource *) data; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* @@ -691,7 +699,7 @@ static int change_clocksource(void *data) } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return 0; @@ -706,7 +714,7 @@ static int change_clocksource(void *data) */ int timekeeping_notify(struct clocksource *clock) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; if (tk->clock == clock) return 0; @@ -738,17 +746,17 @@ EXPORT_SYMBOL_GPL(ktime_get_real); */ void getrawmonotonic(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts64; unsigned long seq; s64 nsecs; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); nsecs = timekeeping_get_ns_raw(tk); ts64 = tk->raw_time; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); timespec64_add_ns(&ts64, nsecs); *ts = timespec64_to_timespec(ts64); @@ -760,16 +768,16 @@ EXPORT_SYMBOL(getrawmonotonic); */ int timekeeping_valid_for_hres(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; int ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -779,16 +787,16 @@ int timekeeping_valid_for_hres(void) */ u64 timekeeping_max_deferment(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; u64 ret; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ret = tk->clock->max_idle_ns; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } @@ -828,7 +836,7 @@ void __weak read_boot_clock(struct timespec *ts) */ void __init timekeeping_init(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; struct timespec64 now, boot, tmp; @@ -854,7 +862,7 @@ void __init timekeeping_init(void) } raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); @@ -875,9 +883,10 @@ void __init timekeeping_init(void) tmp.tv_nsec = 0; tk_set_sleep_time(tk, tmp); - memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); + memcpy(&shadow_timekeeper, &tk_core.timekeeper, + sizeof(tk_core.timekeeper)); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } @@ -918,7 +927,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, */ void timekeeping_inject_sleeptime(struct timespec *delta) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tmp; unsigned long flags; @@ -930,7 +939,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) return; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); @@ -939,7 +948,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ @@ -955,7 +964,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) */ static void timekeeping_resume(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock = tk->clock; unsigned long flags; struct timespec64 ts_new, ts_delta; @@ -970,7 +979,7 @@ static void timekeeping_resume(void) clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and @@ -1022,7 +1031,7 @@ static void timekeeping_resume(void) tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); @@ -1035,7 +1044,7 @@ static void timekeeping_resume(void) static int timekeeping_suspend(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; @@ -1053,7 +1062,7 @@ static int timekeeping_suspend(void) persistent_clock_exist = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; @@ -1078,7 +1087,7 @@ static int timekeeping_suspend(void) } timekeeping_update(tk, TK_MIRROR); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); @@ -1380,7 +1389,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, void update_wall_time(void) { struct clocksource *clock; - struct timekeeper *real_tk = &timekeeper; + struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; cycle_t offset; int shift = 0, maxshift; @@ -1440,7 +1449,7 @@ void update_wall_time(void) */ clock_set |= accumulate_nsecs_to_secs(tk); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); /* Update clock->cycle_last with the new value */ clock->cycle_last = tk->cycle_last; /* @@ -1450,12 +1459,12 @@ void update_wall_time(void) * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this - * memcpy under the timekeeper_seq against one before we start + * memcpy under the tk_core.seq against one before we start * updating. */ memcpy(real_tk, tk, sizeof(*tk)); timekeeping_update(real_tk, clock_set); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (clock_set) @@ -1476,7 +1485,7 @@ out: */ void getboottime(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec boottime = { .tv_sec = tk->wall_to_monotonic.tv_sec + tk->total_sleep_time.tv_sec, @@ -1499,7 +1508,7 @@ EXPORT_SYMBOL_GPL(getboottime); */ void get_monotonic_boottime(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono, sleep, ret; s64 nsec; unsigned int seq; @@ -1507,13 +1516,13 @@ void get_monotonic_boottime(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ret.tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(tk); tomono = tk->wall_to_monotonic; sleep = tk->total_sleep_time; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); ret.tv_sec += tomono.tv_sec + sleep.tv_sec; ret.tv_nsec = 0; @@ -1545,7 +1554,7 @@ EXPORT_SYMBOL_GPL(ktime_get_boottime); */ void monotonic_to_bootbased(struct timespec *ts) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts64; ts64 = timespec_to_timespec64(*ts); @@ -1556,7 +1565,7 @@ EXPORT_SYMBOL_GPL(monotonic_to_bootbased); unsigned long get_seconds(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } @@ -1564,22 +1573,22 @@ EXPORT_SYMBOL(get_seconds); struct timespec __current_kernel_time(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; return timespec64_to_timespec(tk_xtime(tk)); } struct timespec current_kernel_time(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now; unsigned long seq; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return timespec64_to_timespec(now); } @@ -1587,16 +1596,16 @@ EXPORT_SYMBOL(current_kernel_time); struct timespec get_monotonic_coarse(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned long seq; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); @@ -1624,19 +1633,19 @@ void do_timer(unsigned long ticks) ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts; ktime_t now; unsigned int seq; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); ts = tk_xtime(tk); *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); now = ktime_set(ts.tv_sec, ts.tv_nsec); now = ktime_sub(now, *offs_real); @@ -1656,13 +1665,13 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; ktime_t now; unsigned int seq; u64 secs, nsecs; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); secs = tk->xtime_sec; nsecs = timekeeping_get_ns(tk); @@ -1670,7 +1679,7 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); now = ktime_add_ns(ktime_set(secs, 0), nsecs); now = ktime_sub(now, *offs_real); @@ -1683,14 +1692,14 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, */ ktime_t ktime_get_monotonic_offset(void) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; struct timespec64 wtom; do { - seq = read_seqcount_begin(&timekeeper_seq); + seq = read_seqcount_begin(&tk_core.seq); wtom = tk->wall_to_monotonic; - } while (read_seqcount_retry(&timekeeper_seq, seq)); + } while (read_seqcount_retry(&tk_core.seq, seq)); return timespec64_to_ktime(wtom); } @@ -1701,7 +1710,7 @@ EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset); */ int do_adjtimex(struct timex *txc) { - struct timekeeper *tk = &timekeeper; + struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 ts; s32 orig_tai, tai; @@ -1726,7 +1735,7 @@ int do_adjtimex(struct timex *txc) getnstimeofday64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai); @@ -1735,7 +1744,7 @@ int do_adjtimex(struct timex *txc) __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); } - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (tai != orig_tai) @@ -1755,11 +1764,11 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&timekeeper_seq); + write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); - write_seqcount_end(&timekeeper_seq); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); -- cgit v1.2.3 From 7c032df5570388044b4efda3d9f4d2ffb96a3116 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:10 +0000 Subject: timekeeping: Provide internal ktime_t based data The ktime_t based interfaces are used a lot in performance critical code pathes. Add ktime_t based data so the interfaces don't have to convert from the xtime/timespec based data. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 3 +++ kernel/time/timekeeping.c | 22 ++++++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 2cb96235c249..87e0992564f2 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -36,6 +36,9 @@ struct timekeeper { /* Clock shifted nano seconds */ u64 xtime_nsec; + /* Monotonic base time */ + ktime_t base_mono; + /* Current CLOCK_REALTIME time in seconds */ u64 xtime_sec; /* CLOCK_REALTIME to CLOCK_MONOTONIC offset */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index bfe3ea09afc9..86a92476c027 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -291,6 +291,26 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); +/* + * Update the ktime_t based scalar nsec members of the timekeeper + */ +static inline void tk_update_ktime_data(struct timekeeper *tk) +{ + s64 nsec; + + /* + * The xtime based monotonic readout is: + * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); + * The ktime based monotonic readout is: + * nsec = base_mono + now(); + * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + */ + nsec = (s64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); + nsec *= NSEC_PER_SEC; + nsec += tk->wall_to_monotonic.tv_nsec; + tk->base_mono = ns_to_ktime(nsec); +} + /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { @@ -301,6 +321,8 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); + tk_update_ktime_data(tk); + if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); -- cgit v1.2.3 From 0077dc60f274b9a7e9aa705a34784fefb87e0eee Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:13 +0000 Subject: timekeeping: Provide ktime_get_with_offset() Provide a helper function which lets us implement ktime_t based interfaces for real, boot and tai clocks. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 9 +++++++++ kernel/time/timekeeping.c | 27 +++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 3eb19e34cc20..a58e4b1879db 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -98,7 +98,16 @@ extern void getboottime(struct timespec *ts); /* * ktime_t based interfaces */ + +enum tk_offsets { + TK_OFFS_REAL, + TK_OFFS_BOOT, + TK_OFFS_TAI, + TK_OFFS_MAX, +}; + extern ktime_t ktime_get(void); +extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_real(void); extern ktime_t ktime_get_boottime(void); extern ktime_t ktime_get_monotonic_offset(void); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index d5be1425cc03..7c5f5e4a006c 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -423,6 +423,33 @@ ktime_t ktime_get(void) } EXPORT_SYMBOL_GPL(ktime_get); +static ktime_t *offsets[TK_OFFS_MAX] = { + [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, + [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, + [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, +}; + +ktime_t ktime_get_with_offset(enum tk_offsets offs) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base, *offset = offsets[offs]; + s64 nsecs; + + WARN_ON(timekeeping_suspended); + + do { + seq = read_seqcount_begin(&tk_core.seq); + base = ktime_add(tk->base_mono, *offset); + nsecs = timekeeping_get_ns(tk); + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); + +} +EXPORT_SYMBOL_GPL(ktime_get_with_offset); + /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable -- cgit v1.2.3 From f5264d5d5a0729306cc792d84432b97785d2662a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:14 +0000 Subject: timekeeping: Use ktime_t based data for ktime_get_real() Speed up the readout. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 9 ++++++++- kernel/time/timekeeping.c | 15 --------------- 2 files changed, 8 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index a58e4b1879db..68e6678a743b 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -108,11 +108,18 @@ enum tk_offsets { extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); -extern ktime_t ktime_get_real(void); extern ktime_t ktime_get_boottime(void); extern ktime_t ktime_get_monotonic_offset(void); extern ktime_t ktime_get_clocktai(void); +/** + * ktime_get_real - get the real (wall-) time in ktime_t format + */ +static inline ktime_t ktime_get_real(void) +{ + return ktime_get_with_offset(TK_OFFS_REAL); +} + /* * RTC specific */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 7c5f5e4a006c..56db2e16970a 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -773,21 +773,6 @@ int timekeeping_notify(struct clocksource *clock) return tk->clock == clock ? 0 : -1; } -/** - * ktime_get_real - get the real (wall-) time in ktime_t format - * - * returns the time in ktime_t format - */ -ktime_t ktime_get_real(void) -{ - struct timespec64 now; - - getnstimeofday64(&now); - - return timespec64_to_ktime(now); -} -EXPORT_SYMBOL_GPL(ktime_get_real); - /** * getrawmonotonic - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec to be set -- cgit v1.2.3 From b82c817e2d16e818c472eb71019de521816000a3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:16 +0000 Subject: timekeeping; Use ktime_t based data for ktime_get_boottime() Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 12 +++++++++++- kernel/time/timekeeping.c | 17 ----------------- 2 files changed, 11 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 68e6678a743b..2fc606203c8c 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -108,7 +108,6 @@ enum tk_offsets { extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); -extern ktime_t ktime_get_boottime(void); extern ktime_t ktime_get_monotonic_offset(void); extern ktime_t ktime_get_clocktai(void); @@ -120,6 +119,17 @@ static inline ktime_t ktime_get_real(void) return ktime_get_with_offset(TK_OFFS_REAL); } +/** + * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * + * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the + * time spent in suspend. + */ +static inline ktime_t ktime_get_boottime(void) +{ + return ktime_get_with_offset(TK_OFFS_BOOT); +} + /* * RTC specific */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 56db2e16970a..5e60aa09af79 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1565,23 +1565,6 @@ void get_monotonic_boottime(struct timespec *ts) } EXPORT_SYMBOL_GPL(get_monotonic_boottime); -/** - * ktime_get_boottime - Returns monotonic time since boot in a ktime - * - * Returns the monotonic time since boot in a ktime - * - * This is similar to CLOCK_MONTONIC/ktime_get, but also - * includes the time spent in suspend. - */ -ktime_t ktime_get_boottime(void) -{ - struct timespec ts; - - get_monotonic_boottime(&ts); - return timespec_to_ktime(ts); -} -EXPORT_SYMBOL_GPL(ktime_get_boottime); - /** * monotonic_to_bootbased - Convert the monotonic time to boot based. * @ts: pointer to the timespec to be converted -- cgit v1.2.3 From afab07c0e91ecf098abf34573ccfcd86d6be26f9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:17 +0000 Subject: timekeeping: Use ktime_t based data for ktime_get_clocktai() Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 9 ++++++++- kernel/time/timekeeping.c | 15 --------------- 2 files changed, 8 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 2fc606203c8c..3050a7d0a5a9 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -109,7 +109,6 @@ enum tk_offsets { extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_monotonic_offset(void); -extern ktime_t ktime_get_clocktai(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format @@ -130,6 +129,14 @@ static inline ktime_t ktime_get_boottime(void) return ktime_get_with_offset(TK_OFFS_BOOT); } +/** + * ktime_get_clocktai - Returns the TAI time of day in ktime_t format + */ +static inline ktime_t ktime_get_clocktai(void) +{ + return ktime_get_with_offset(TK_OFFS_TAI); +} + /* * RTC specific */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5e60aa09af79..c083ae2c34b5 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -512,21 +512,6 @@ void timekeeping_clocktai(struct timespec *ts) } EXPORT_SYMBOL(timekeeping_clocktai); - -/** - * ktime_get_clocktai - Returns the TAI time of day in a ktime - * - * Returns the time of day in a ktime. - */ -ktime_t ktime_get_clocktai(void) -{ - struct timespec ts; - - timekeeping_clocktai(&ts); - return timespec_to_ktime(ts); -} -EXPORT_SYMBOL(ktime_get_clocktai); - #ifdef CONFIG_NTP_PPS /** -- cgit v1.2.3 From 9a6b51976ea3a326b6de534beec3fd87275f4ef6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:22 +0000 Subject: timekeeping: Provide ktime_mono_to_any() ktime based conversion function to map a monotonic time stamp to a different CLOCK. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 9 +++++++++ kernel/time/timekeeping.c | 20 ++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 3050a7d0a5a9..910a98ef2154 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -109,6 +109,7 @@ enum tk_offsets { extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_monotonic_offset(void); +extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); /** * ktime_get_real - get the real (wall-) time in ktime_t format @@ -137,6 +138,14 @@ static inline ktime_t ktime_get_clocktai(void) return ktime_get_with_offset(TK_OFFS_TAI); } +/** + * ktime_mono_to_real - Convert monotonic time to clock realtime + */ +static inline ktime_t ktime_mono_to_real(ktime_t mono) +{ + return ktime_mono_to_any(mono, TK_OFFS_REAL); +} + /* * RTC specific */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e99350319eec..032e77a54a79 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -450,6 +450,26 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs) } EXPORT_SYMBOL_GPL(ktime_get_with_offset); +/** + * ktime_mono_to_any() - convert mononotic time to any other time + * @tmono: time to convert. + * @offs: which offset to use + */ +ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) +{ + ktime_t *offset = offsets[offs]; + unsigned long seq; + ktime_t tconv; + + do { + seq = read_seqcount_begin(&tk_core.seq); + tconv = ktime_add(tmono, *offset); + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return tconv; +} +EXPORT_SYMBOL_GPL(ktime_mono_to_any); + /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable -- cgit v1.2.3 From dcaab54e348c5b66cca4802815ceebd37059e70c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:28 +0000 Subject: timekeeping: Remove ktime_get_monotonic_offset() No more users. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 1 - kernel/time/timekeeping.c | 18 ------------------ 2 files changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 910a98ef2154..64c81f367866 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -108,7 +108,6 @@ enum tk_offsets { extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); -extern ktime_t ktime_get_monotonic_offset(void); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); /** diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 032e77a54a79..f7378eaebe67 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1707,24 +1707,6 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, } #endif -/** - * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format - */ -ktime_t ktime_get_monotonic_offset(void) -{ - struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; - struct timespec64 wtom; - - do { - seq = read_seqcount_begin(&tk_core.seq); - wtom = tk->wall_to_monotonic; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - return timespec64_to_ktime(wtom); -} -EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset); - /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ -- cgit v1.2.3 From 897994e32b2b0a41ce4222c3b38a05bd2d1ee9fa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:29 +0000 Subject: timekeeping: Provide ktime_get[*]_ns() helpers A lot of code converts either timespecs or ktime_t to nanoseconds. Provide helper functions. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 64c81f367866..903ecc10fcff 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -145,6 +145,21 @@ static inline ktime_t ktime_mono_to_real(ktime_t mono) return ktime_mono_to_any(mono, TK_OFFS_REAL); } +static inline u64 ktime_get_ns(void) +{ + return ktime_to_ns(ktime_get()); +} + +static inline u64 ktime_get_real_ns(void) +{ + return ktime_to_ns(ktime_get_real()); +} + +static inline u64 ktime_get_boot_ns(void) +{ + return ktime_to_ns(ktime_get_boottime()); +} + /* * RTC specific */ -- cgit v1.2.3 From 57e0be041d9e21a7397eed3b67a7936ac4ac83c0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:32 +0000 Subject: sched: Make task->real_start_time nanoseconds based Simplify the only user of this data by removing the timespec conversion. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- fs/proc/array.c | 7 +------ include/linux/sched.h | 2 +- kernel/fork.c | 3 +-- 3 files changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/array.c b/fs/proc/array.c index 64db2bceac59..d7f9199217bb 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -473,13 +473,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, priority = task_prio(task); nice = task_nice(task); - /* Temporary variable needed for gcc-2.96 */ - /* convert timespec -> nsec*/ - start_time = - (unsigned long long)task->real_start_time.tv_sec * NSEC_PER_SEC - + task->real_start_time.tv_nsec; /* convert nsec -> ticks */ - start_time = nsec_to_clock_t(start_time); + start_time = nsec_to_clock_t(task->real_start_time); seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); seq_put_decimal_ll(m, ' ', ppid); diff --git a/include/linux/sched.h b/include/linux/sched.h index 306f4f0c987a..67678fa76f99 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1368,7 +1368,7 @@ struct task_struct { #endif unsigned long nvcsw, nivcsw; /* context switch counts */ struct timespec start_time; /* monotonic time */ - struct timespec real_start_time; /* boot based time */ + u64 real_start_time; /* boot based time in nsec */ /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; diff --git a/kernel/fork.c b/kernel/fork.c index 8f541930ce26..a7ab82db2f60 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1263,8 +1263,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, posix_cpu_timers_init(p); ktime_get_ts(&p->start_time); - p->real_start_time = p->start_time; - monotonic_to_bootbased(&p->real_start_time); + p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; if (clone_flags & CLONE_THREAD) -- cgit v1.2.3 From ccbf62d8a284cf181ac28c8e8407dd077d90dd4b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:34 +0000 Subject: sched: Make task->start_time nanoseconds based Simplify the timespec to nsec/usec conversions. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/sched.h | 2 +- kernel/acct.c | 10 +++------- kernel/fork.c | 2 +- kernel/tsacct.c | 19 +++++++++---------- 4 files changed, 14 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 67678fa76f99..10c6e829927f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1367,7 +1367,7 @@ struct task_struct { } vtime_snap_whence; #endif unsigned long nvcsw, nivcsw; /* context switch counts */ - struct timespec start_time; /* monotonic time */ + u64 start_time; /* monotonic time in nsec */ u64 real_start_time; /* boot based time in nsec */ /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; diff --git a/kernel/acct.c b/kernel/acct.c index 1be013c6053e..a1844f14c6d6 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -458,9 +458,7 @@ static void do_acct_process(struct bsd_acct_struct *acct, acct_t ac; mm_segment_t fs; unsigned long flim; - u64 elapsed; - u64 run_time; - struct timespec uptime; + u64 elapsed, run_time; struct tty_struct *tty; const struct cred *orig_cred; @@ -484,10 +482,8 @@ static void do_acct_process(struct bsd_acct_struct *acct, strlcpy(ac.ac_comm, current->comm, sizeof(ac.ac_comm)); /* calculate run_time in nsec*/ - ktime_get_ts(&uptime); - run_time = (u64)uptime.tv_sec*NSEC_PER_SEC + uptime.tv_nsec; - run_time -= (u64)current->group_leader->start_time.tv_sec * NSEC_PER_SEC - + current->group_leader->start_time.tv_nsec; + run_time = ktime_get_ns(); + run_time -= current->group_leader->start_time; /* convert nsec -> AHZ */ elapsed = nsec_to_AHZ(run_time); #if ACCT_VERSION==3 diff --git a/kernel/fork.c b/kernel/fork.c index a7ab82db2f60..627b7f80afb0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1262,7 +1262,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, posix_cpu_timers_init(p); - ktime_get_ts(&p->start_time); + p->start_time = ktime_get_ns(); p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index ea6d170452c4..975cb49e32bf 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -31,20 +31,19 @@ void bacct_add_tsk(struct user_namespace *user_ns, struct taskstats *stats, struct task_struct *tsk) { const struct cred *tcred; - struct timespec uptime, ts; cputime_t utime, stime, utimescaled, stimescaled; - u64 ac_etime; + u64 delta; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); - /* calculate task elapsed time in timespec */ - ktime_get_ts(&uptime); - ts = timespec_sub(uptime, tsk->start_time); - /* rebase elapsed time to usec (should never be negative) */ - ac_etime = timespec_to_ns(&ts); - do_div(ac_etime, NSEC_PER_USEC); - stats->ac_etime = ac_etime; - stats->ac_btime = get_seconds() - ts.tv_sec; + /* calculate task elapsed time in nsec */ + delta = ktime_get_ns() - tsk->start_time; + /* Convert to micro seconds */ + do_div(delta, NSEC_PER_USEC); + stats->ac_etime = delta; + /* Convert to seconds for btime */ + do_div(delta, USEC_PER_SEC); + stats->ac_btime = get_seconds() - delta; if (thread_group_leader(tsk)) { stats->ac_exitcode = tsk->exit_code; if (tsk->flags & PF_FORKNOEXEC) -- cgit v1.2.3 From 9667a23db0dc0bd4892f0ada7e4e71528eaeed62 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:35 +0000 Subject: delayacct: Make accounting nanosecond based Kill the timespec juggling and calculate with plain nanoseconds. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/sched.h | 4 ++-- kernel/delayacct.c | 34 ++++++++++++---------------------- 2 files changed, 14 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 10c6e829927f..653744ae8d27 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -813,7 +813,7 @@ struct task_delay_info { * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ - struct timespec blkio_start, blkio_end; /* Shared by blkio, swapin */ + u64 blkio_start; /* Shared by blkio, swapin */ u64 blkio_delay; /* wait for sync block io completion */ u64 swapin_delay; /* wait for swapin block io completion */ u32 blkio_count; /* total count of the number of sync block */ @@ -821,7 +821,7 @@ struct task_delay_info { u32 swapin_count; /* total count of the number of swapin block */ /* io operations performed */ - struct timespec freepages_start, freepages_end; + u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ u32 freepages_count; /* total count of memory reclaim */ }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index de699f42f9bc..cf2e65dddb19 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -46,32 +46,25 @@ void __delayacct_tsk_init(struct task_struct *tsk) } /* - * Finish delay accounting for a statistic using - * its timestamps (@start, @end), accumalator (@total) and @count + * Finish delay accounting for a statistic using its timestamps (@start), + * accumalator (@total) and @count */ - -static void delayacct_end(struct timespec *start, struct timespec *end, - u64 *total, u32 *count) +static void delayacct_end(u64 *start, u64 *total, u32 *count) { - struct timespec ts; - s64 ns; + s64 ns = ktime_get_ns() - *start; unsigned long flags; - ktime_get_ts(end); - ts = timespec_sub(*end, *start); - ns = timespec_to_ns(&ts); - if (ns < 0) - return; - - spin_lock_irqsave(¤t->delays->lock, flags); - *total += ns; - (*count)++; - spin_unlock_irqrestore(¤t->delays->lock, flags); + if (ns > 0) { + spin_lock_irqsave(¤t->delays->lock, flags); + *total += ns; + (*count)++; + spin_unlock_irqrestore(¤t->delays->lock, flags); + } } void __delayacct_blkio_start(void) { - ktime_get_ts(¤t->delays->blkio_start); + current->delays->blkio_start = ktime_get_ns(); } void __delayacct_blkio_end(void) @@ -79,12 +72,10 @@ void __delayacct_blkio_end(void) if (current->delays->flags & DELAYACCT_PF_SWAPIN) /* Swapin block I/O */ delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_end, ¤t->delays->swapin_delay, ¤t->delays->swapin_count); else /* Other block I/O */ delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_end, ¤t->delays->blkio_delay, ¤t->delays->blkio_count); } @@ -159,13 +150,12 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk) void __delayacct_freepages_start(void) { - ktime_get_ts(¤t->delays->freepages_start); + current->delays->freepages_start = ktime_get_ns(); } void __delayacct_freepages_end(void) { delayacct_end(¤t->delays->freepages_start, - ¤t->delays->freepages_end, ¤t->delays->freepages_delay, ¤t->delays->freepages_count); } -- cgit v1.2.3 From 14a7004671246d1b799f545335995a9897de1268 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:44 +0000 Subject: net: mlx5: Use ktime_get_ns() This code is beyond silly: struct timespec ts = ktime_get_ts(); ktime_t ktime = timespec_to_ktime(ts); Further down the code builds the delta of two ktime_t values and converts the result to nanoseconds. Use ktime_get_ns() and replace all the nonsense. Signed-off-by: Thomas Gleixner Cc: Eli Cohen Signed-off-by: John Stultz --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 16 ++++------------ include/linux/mlx5/driver.h | 4 ++-- 2 files changed, 6 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 87d1b018a9c3..67f8f5a1dc86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -548,7 +548,7 @@ static void cmd_work_handler(struct work_struct *work) lay->status_own = CMD_OWNER_HW; set_signature(ent, !cmd->checksum_disabled); dump_command(dev, ent, 1); - ktime_get_ts(&ent->ts1); + ent->ts1 = ktime_get_ns(); /* ring doorbell after the descriptor is valid */ wmb(); @@ -637,7 +637,6 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, { struct mlx5_cmd *cmd = &dev->cmd; struct mlx5_cmd_work_ent *ent; - ktime_t t1, t2, delta; struct mlx5_cmd_stats *stats; int err = 0; s64 ds; @@ -668,10 +667,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (err == -ETIMEDOUT) goto out; - t1 = timespec_to_ktime(ent->ts1); - t2 = timespec_to_ktime(ent->ts2); - delta = ktime_sub(t2, t1); - ds = ktime_to_ns(delta); + ds = ent->ts2 - ent->ts1; op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode); if (op < ARRAY_SIZE(cmd->stats)) { stats = &cmd->stats[op]; @@ -1135,7 +1131,6 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) void *context; int err; int i; - ktime_t t1, t2, delta; s64 ds; struct mlx5_cmd_stats *stats; unsigned long flags; @@ -1149,7 +1144,7 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) sem = &cmd->pages_sem; else sem = &cmd->sem; - ktime_get_ts(&ent->ts2); + ent->ts2 = ktime_get_ns(); memcpy(ent->out->first.data, ent->lay->out, sizeof(ent->lay->out)); dump_command(dev, ent, 0); if (!ent->ret) { @@ -1163,10 +1158,7 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) } free_ent(cmd, ent->idx); if (ent->callback) { - t1 = timespec_to_ktime(ent->ts1); - t2 = timespec_to_ktime(ent->ts2); - delta = ktime_sub(t2, t1); - ds = ktime_to_ns(delta); + ds = ent->ts2 - ent->ts1; if (ent->op < ARRAY_SIZE(cmd->stats)) { stats = &cmd->stats[ent->op]; spin_lock_irqsave(&stats->lock, flags); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2bce4aad2570..52d631ca32cf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -604,8 +604,8 @@ struct mlx5_cmd_work_ent { int page_queue; u8 status; u8 token; - struct timespec ts1; - struct timespec ts2; + u64 ts1; + u64 ts2; u16 op; }; -- cgit v1.2.3 From fb31cc153dec0d4bdd9a5d7ce60d61acd04b4304 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:49 +0000 Subject: iio: Use ktime_get_real_ns() No idea why iio needs wall clock based time stamps, but we can avoid the timespec conversion dance by using the new interfaces. Signed-off-by: Thomas Gleixner Acked-by: Jonathan Cameron Signed-off-by: John Stultz --- include/linux/iio/iio.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index ccde91725f98..15dc6bc2bdd2 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -277,14 +277,7 @@ static inline bool iio_channel_has_info(const struct iio_chan_spec *chan, **/ static inline s64 iio_get_time_ns(void) { - struct timespec ts; - /* - * calls getnstimeofday. - * If hrtimers then up to ns accurate, if not microsecond. - */ - ktime_get_real_ts(&ts); - - return timespec_to_ns(&ts); + return ktime_get_real_ns(); } /* Device operating modes */ -- cgit v1.2.3 From 250fade8af2ac5dda8d5106ea06738b6f9e768a7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:55 +0000 Subject: timekeeping: Remove monotonic_to_bootbased No more users. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 1 - kernel/time/timekeeping.c | 15 --------------- 2 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 903ecc10fcff..8ea3ca1b0ee5 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -27,7 +27,6 @@ struct timespec __current_kernel_time(void); */ struct timespec get_monotonic_coarse(void); extern void getrawmonotonic(struct timespec *ts); -extern void monotonic_to_bootbased(struct timespec *ts); extern void get_monotonic_boottime(struct timespec *ts); extern void ktime_get_ts64(struct timespec64 *ts); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f7378eaebe67..b35613508725 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1570,21 +1570,6 @@ void get_monotonic_boottime(struct timespec *ts) } EXPORT_SYMBOL_GPL(get_monotonic_boottime); -/** - * monotonic_to_bootbased - Convert the monotonic time to boot based. - * @ts: pointer to the timespec to be converted - */ -void monotonic_to_bootbased(struct timespec *ts) -{ - struct timekeeper *tk = &tk_core.timekeeper; - struct timespec64 ts64; - - ts64 = timespec_to_timespec64(*ts); - ts64 = timespec64_add(ts64, tk->total_sleep_time); - *ts = timespec64_to_timespec(ts64); -} -EXPORT_SYMBOL_GPL(monotonic_to_bootbased); - unsigned long get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; -- cgit v1.2.3 From 48f18fd6addc199f330d838d54fe7b0a0892adaa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:04:57 +0000 Subject: timekeeping: Use ktime_get_boottime() for get_monotonic_boottime() get_monotonic_boottime() is not used in fast pathes, so the extra timespec conversion is not problematic. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 9 ++++++++- kernel/time/timekeeping.c | 34 ---------------------------------- 2 files changed, 8 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 8ea3ca1b0ee5..7b8f20007871 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -27,7 +27,6 @@ struct timespec __current_kernel_time(void); */ struct timespec get_monotonic_coarse(void); extern void getrawmonotonic(struct timespec *ts); -extern void get_monotonic_boottime(struct timespec *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern int __getnstimeofday64(struct timespec64 *tv); @@ -159,6 +158,14 @@ static inline u64 ktime_get_boot_ns(void) return ktime_to_ns(ktime_get_boottime()); } +/* + * Timespec interfaces utilizing the ktime based ones + */ +static inline void get_monotonic_boottime(struct timespec *ts) +{ + *ts = ktime_to_timespec(ktime_get_boottime()); +} + /* * RTC specific */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b35613508725..f63476fb0daf 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1536,40 +1536,6 @@ void getboottime(struct timespec *ts) } EXPORT_SYMBOL_GPL(getboottime); -/** - * get_monotonic_boottime - Returns monotonic time since boot - * @ts: pointer to the timespec to be set - * - * Returns the monotonic time since boot in a timespec. - * - * This is similar to CLOCK_MONTONIC/ktime_get_ts, but also - * includes the time spent in suspend. - */ -void get_monotonic_boottime(struct timespec *ts) -{ - struct timekeeper *tk = &tk_core.timekeeper; - struct timespec64 tomono, sleep, ret; - s64 nsec; - unsigned int seq; - - WARN_ON(timekeeping_suspended); - - do { - seq = read_seqcount_begin(&tk_core.seq); - ret.tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(tk); - tomono = tk->wall_to_monotonic; - sleep = tk->total_sleep_time; - - } while (read_seqcount_retry(&tk_core.seq, seq)); - - ret.tv_sec += tomono.tv_sec + sleep.tv_sec; - ret.tv_nsec = 0; - timespec64_add_ns(&ret, nsec + tomono.tv_nsec + sleep.tv_nsec); - *ts = timespec64_to_timespec(ret); -} -EXPORT_SYMBOL_GPL(get_monotonic_boottime); - unsigned long get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; -- cgit v1.2.3 From 47da70d32535000ec29cc206cfc1d318fbd8761f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:05:00 +0000 Subject: timekeeping: Remove timekeeper.total_sleep_time No more users. Remove it Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 6 ++---- kernel/time/timekeeping.c | 14 +++----------- 2 files changed, 5 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 87e0992564f2..8e5d77a01787 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -20,8 +20,8 @@ * the tv_nsec part positive so we can use the usual normalization. * * wall_to_monotonic is moved after resume from suspend for the - * monotonic time not to jump. We need to add total_sleep_time to - * wall_to_monotonic to get the real boot based time offset. + * monotonic time not to jump. To calculate the real boot time offset + * we need to do offs_real - offs_boot. * * - wall_to_monotonic is no longer the boot time, getboottime must be * used instead. @@ -51,8 +51,6 @@ struct timekeeper { /* Offset clock monotonic -> clock tai */ ktime_t offs_tai; - /* time spent in suspend */ - struct timespec64 total_sleep_time; /* The current UTC to TAI offset in seconds */ s32 tai_offset; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3edc0c1d6fe8..50d5de05b837 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -97,13 +97,9 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } -static void tk_set_sleep_time(struct timekeeper *tk, struct timespec64 t) +static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { - /* Verify consistency before modifying */ - WARN_ON_ONCE(tk->offs_boot.tv64 != timespec64_to_ktime(tk->total_sleep_time).tv64); - - tk->total_sleep_time = t; - tk->offs_boot = timespec64_to_ktime(t); + tk->offs_boot = ktime_add(tk->offs_boot, delta); } /** @@ -919,10 +915,6 @@ void __init timekeeping_init(void) set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); tk_set_wall_to_mono(tk, tmp); - tmp.tv_sec = 0; - tmp.tv_nsec = 0; - tk_set_sleep_time(tk, tmp); - timekeeping_update(tk, TK_MIRROR); write_seqcount_end(&tk_core.seq); @@ -950,7 +942,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); - tk_set_sleep_time(tk, timespec64_add(tk->total_sleep_time, *delta)); + tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } -- cgit v1.2.3 From 61edec81d260bc96a73c878bbdb4c614460346da Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:05:01 +0000 Subject: timekeeping: Simplify timekeeping_clocktai() timekeeping_clocktai() is not used in fast pathes, so the extra timespec conversion is not problematic. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeping.h | 5 +++++ kernel/time/timekeeping.c | 31 ------------------------------- 2 files changed, 5 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7b8f20007871..f0f12a84a31b 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -166,6 +166,11 @@ static inline void get_monotonic_boottime(struct timespec *ts) *ts = ktime_to_timespec(ktime_get_boottime()); } +static inline void timekeeping_clocktai(struct timespec *ts) +{ + *ts = ktime_to_timespec(ktime_get_clocktai()); +} + /* * RTC specific */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 50d5de05b837..118e91e3071c 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -497,37 +497,6 @@ void ktime_get_ts64(struct timespec64 *ts) } EXPORT_SYMBOL_GPL(ktime_get_ts64); - -/** - * timekeeping_clocktai - Returns the TAI time of day in a timespec - * @ts: pointer to the timespec to be set - * - * Returns the time of day in a timespec. - */ -void timekeeping_clocktai(struct timespec *ts) -{ - struct timekeeper *tk = &tk_core.timekeeper; - struct timespec64 ts64; - unsigned long seq; - u64 nsecs; - - WARN_ON(timekeeping_suspended); - - do { - seq = read_seqcount_begin(&tk_core.seq); - - ts64.tv_sec = tk->xtime_sec + tk->tai_offset; - nsecs = timekeeping_get_ns(tk); - - } while (read_seqcount_retry(&tk_core.seq, seq)); - - ts64.tv_nsec = 0; - timespec64_add_ns(&ts64, nsecs); - *ts = timespec64_to_timespec(ts64); - -} -EXPORT_SYMBOL(timekeeping_clocktai); - #ifdef CONFIG_NTP_PPS /** -- cgit v1.2.3 From f519b1a2e08c913375324a927992bb328387f169 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:05:04 +0000 Subject: timekeeping: Provide ktime_get_raw() Provide a ktime_t based interface for raw monotonic time. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 3 +++ include/linux/timekeeping.h | 6 ++++++ kernel/time/timekeeping.c | 25 +++++++++++++++++++++++++ 3 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 8e5d77a01787..2e20275a7083 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -54,6 +54,9 @@ struct timekeeper { /* The current UTC to TAI offset in seconds */ s32 tai_offset; + /* Monotonic raw base time */ + ktime_t base_raw; + /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ struct timespec64 raw_time; diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index f0f12a84a31b..58ad7eff83ff 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -107,6 +107,7 @@ enum tk_offsets { extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); +extern ktime_t ktime_get_raw(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format @@ -158,6 +159,11 @@ static inline u64 ktime_get_boot_ns(void) return ktime_to_ns(ktime_get_boottime()); } +static inline u64 ktime_get_raw_ns(void) +{ + return ktime_to_ns(ktime_get_raw()); +} + /* * Timespec interfaces utilizing the ktime based ones */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 118e91e3071c..af8051f4420d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -305,6 +305,9 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) nsec *= NSEC_PER_SEC; nsec += tk->wall_to_monotonic.tv_nsec; tk->base_mono = ns_to_ktime(nsec); + + /* Update the monotonic raw base */ + tk->base_raw = timespec64_to_ktime(tk->raw_time); } /* must hold timekeeper_lock */ @@ -466,6 +469,27 @@ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) } EXPORT_SYMBOL_GPL(ktime_mono_to_any); +/** + * ktime_get_raw - Returns the raw monotonic time in ktime_t format + */ +ktime_t ktime_get_raw(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + ktime_t base; + s64 nsecs; + + do { + seq = read_seqcount_begin(&tk_core.seq); + base = tk->base_raw; + nsecs = timekeeping_get_ns_raw(tk); + + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return ktime_add_ns(base, nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get_raw); + /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable @@ -878,6 +902,7 @@ void __init timekeeping_init(void) tk_set_xtime(tk, &now); tk->raw_time.tv_sec = 0; tk->raw_time.tv_nsec = 0; + tk->base_raw.tv64 = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) boot = tk_xtime(tk); -- cgit v1.2.3 From 4a0e637738f06673725792d74eed67f8779b62c7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:05:13 +0000 Subject: clocksource: Get rid of cycle_last cycle_last was added to the clocksource to support the TSC validation. We moved that to the core code, so we can get rid of the extra copy. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- arch/arm64/kernel/vdso.c | 2 +- arch/ia64/kernel/time.c | 4 ++-- arch/powerpc/kernel/time.c | 4 ++-- arch/s390/kernel/time.c | 2 +- arch/tile/kernel/time.c | 2 +- arch/x86/kernel/vsyscall_gtod.c | 2 +- arch/x86/kvm/x86.c | 2 +- include/linux/clocksource.h | 2 -- include/linux/timekeeper_internal.h | 7 ++++--- kernel/time/timekeeping.c | 23 +++++++++++------------ 10 files changed, 24 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 50384fec56c4..574672f001f7 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -224,7 +224,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { - vdso_data->cs_cycle_last = tk->clock->cycle_last; + vdso_data->cs_cycle_last = tk->cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; vdso_data->xtime_clock_nsec = tk->xtime_nsec; vdso_data->cs_mult = tk->mult; diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 71c52bc7c28d..11dc42da7daf 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -441,7 +441,7 @@ void update_vsyscall_tz(void) } void update_vsyscall_old(struct timespec *wall, struct timespec *wtm, - struct clocksource *c, u32 mult) + struct clocksource *c, u32 mult, cycles_t cycle_last) { write_seqcount_begin(&fsyscall_gtod_data.seq); @@ -450,7 +450,7 @@ void update_vsyscall_old(struct timespec *wall, struct timespec *wtm, fsyscall_gtod_data.clk_mult = mult; fsyscall_gtod_data.clk_shift = c->shift; fsyscall_gtod_data.clk_fsys_mmio = c->archdata.fsys_mmio; - fsyscall_gtod_data.clk_cycle_last = c->cycle_last; + fsyscall_gtod_data.clk_cycle_last = cycle_last; /* copy kernel time structures */ fsyscall_gtod_data.wall_time.tv_sec = wall->tv_sec; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 9fff9cdcc519..368ab374d33c 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -741,7 +741,7 @@ static cycle_t timebase_read(struct clocksource *cs) } void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, - struct clocksource *clock, u32 mult) + struct clocksource *clock, u32 mult, cycle_t cycle_last) { u64 new_tb_to_xs, new_stamp_xsec; u32 frac_sec; @@ -774,7 +774,7 @@ void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, * We expect the caller to have done the first increment of * vdso_data->tb_update_count already. */ - vdso_data->tb_orig_stamp = clock->cycle_last; + vdso_data->tb_orig_stamp = cycle_last; vdso_data->stamp_xsec = new_stamp_xsec; vdso_data->tb_to_xs = new_tb_to_xs; vdso_data->wtom_clock_sec = wtm->tv_sec; diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 0931b110c826..97950f392613 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -220,7 +220,7 @@ void update_vsyscall(struct timekeeper *tk) /* Make userspace gettimeofday spin until we're done. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = tk->clock->cycle_last; + vdso_data->xtime_tod_stamp = tk->cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; vdso_data->xtime_clock_nsec = tk->xtime_nsec; vdso_data->wtom_clock_sec = diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c index ae70155c2f16..d22d5bfc1e4e 100644 --- a/arch/tile/kernel/time.c +++ b/arch/tile/kernel/time.c @@ -269,7 +269,7 @@ void update_vsyscall(struct timekeeper *tk) /* Userspace gettimeofday will spin while this value is odd. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = clock->cycle_last; + vdso_data->xtime_tod_stamp = tk->cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; vdso_data->xtime_clock_nsec = tk->xtime_nsec; vdso_data->wtom_clock_sec = wtm->tv_sec; diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c index 9531fbb123ba..c3cb3c144591 100644 --- a/arch/x86/kernel/vsyscall_gtod.c +++ b/arch/x86/kernel/vsyscall_gtod.c @@ -32,7 +32,7 @@ void update_vsyscall(struct timekeeper *tk) /* copy vsyscall data */ vdata->vclock_mode = tk->clock->archdata.vclock_mode; - vdata->cycle_last = tk->clock->cycle_last; + vdata->cycle_last = tk->cycle_last; vdata->mask = tk->clock->mask; vdata->mult = tk->mult; vdata->shift = tk->shift; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 63832f5110b6..7b25125f3f42 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1001,7 +1001,7 @@ static void update_pvclock_gtod(struct timekeeper *tk) /* copy pvclock gtod data */ vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode; - vdata->clock.cycle_last = tk->clock->cycle_last; + vdata->clock.cycle_last = tk->cycle_last; vdata->clock.mask = tk->clock->mask; vdata->clock.mult = tk->mult; vdata->clock.shift = tk->shift; diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index a16b497d5159..653f0e2b6ca9 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -162,7 +162,6 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary - * @cycle_last: most recent cycle counter value seen by ::read() * @owner: module reference, must be set by clocksource in modules */ struct clocksource { @@ -171,7 +170,6 @@ struct clocksource { * clocksource itself is cacheline aligned. */ cycle_t (*read)(struct clocksource *cs); - cycle_t cycle_last; cycle_t mask; u32 mult; u32 shift; diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 2e20275a7083..cb88096222c0 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -29,6 +29,8 @@ struct timekeeper { /* Current clocksource used for timekeeping. */ struct clocksource *clock; + /* Last cycle value */ + cycle_t cycle_last; /* NTP adjusted clock multiplier */ u32 mult; /* The shift value of the current clocksource. */ @@ -62,8 +64,6 @@ struct timekeeper { /* Number of clock cycles in one NTP interval. */ cycle_t cycle_interval; - /* Last cycle value (also stored in clock->cycle_last) */ - cycle_t cycle_last; /* Number of clock shifted nano seconds in one NTP interval. */ u64 xtime_interval; /* shifted nano seconds left over when rounding cycle_interval */ @@ -91,7 +91,8 @@ extern void update_vsyscall_tz(void); #elif defined(CONFIG_GENERIC_TIME_VSYSCALL_OLD) extern void update_vsyscall_old(struct timespec *ts, struct timespec *wtm, - struct clocksource *c, u32 mult); + struct clocksource *c, u32 mult, + cycles_t cycle_last); extern void update_vsyscall_tz(void); #else diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 531805013786..4e748c404749 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -121,7 +121,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) old_clock = tk->clock; tk->clock = clock; - tk->cycle_last = clock->cycle_last = clock->read(clock); + tk->cycle_last = clock->read(clock); /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; @@ -182,7 +182,7 @@ static inline s64 timekeeping_get_ns(struct timekeeper *tk) cycle_now = clock->read(clock); /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, clock->cycle_last, clock->mask); + delta = clocksource_delta(cycle_now, tk->cycle_last, clock->mask); nsec = delta * tk->mult + tk->xtime_nsec; nsec >>= tk->shift; @@ -202,7 +202,7 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) cycle_now = clock->read(clock); /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, clock->cycle_last, clock->mask); + delta = clocksource_delta(cycle_now, tk->cycle_last, clock->mask); /* convert delta to nanoseconds. */ nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); @@ -218,7 +218,8 @@ static inline void update_vsyscall(struct timekeeper *tk) struct timespec xt; xt = tk_xtime(tk); - update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); + update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult, + tk->cycle_last); } static inline void old_vsyscall_fixup(struct timekeeper *tk) @@ -342,8 +343,8 @@ static void timekeeping_forward_now(struct timekeeper *tk) clock = tk->clock; cycle_now = clock->read(clock); - delta = clocksource_delta(cycle_now, clock->cycle_last, clock->mask); - tk->cycle_last = clock->cycle_last = cycle_now; + delta = clocksource_delta(cycle_now, tk->cycle_last, clock->mask); + tk->cycle_last = cycle_now; tk->xtime_nsec += delta * tk->mult; @@ -1020,13 +1021,13 @@ static void timekeeping_resume(void) */ cycle_now = clock->read(clock); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > clock->cycle_last) { + cycle_now > tk->cycle_last) { u64 num, max = ULLONG_MAX; u32 mult = clock->mult; u32 shift = clock->shift; s64 nsec = 0; - cycle_delta = clocksource_delta(cycle_now, clock->cycle_last, + cycle_delta = clocksource_delta(cycle_now, tk->cycle_last, clock->mask); /* @@ -1053,7 +1054,7 @@ static void timekeeping_resume(void) __timekeeping_inject_sleeptime(tk, &ts_delta); /* Re-base the last cycle value */ - tk->cycle_last = clock->cycle_last = cycle_now; + tk->cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); @@ -1433,7 +1434,7 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(clock->read(clock), clock->cycle_last, + offset = clocksource_delta(clock->read(clock), tk->cycle_last, clock->mask); #endif @@ -1477,8 +1478,6 @@ void update_wall_time(void) clock_set |= accumulate_nsecs_to_secs(tk); write_seqcount_begin(&tk_core.seq); - /* Update clock->cycle_last with the new value */ - clock->cycle_last = tk->cycle_last; /* * Update the real timekeeper. * -- cgit v1.2.3 From 6d3aadf3e180e09dbefab16478c6876b584ce16e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:05:15 +0000 Subject: timekeeping: Restructure the timekeeper some more Access to time requires to touch two cachelines at minimum 1) The timekeeper data structure 2) The clocksource data structure The access to the clocksource data structure can be avoided as almost all clocksource implementations ignore the argument to the read callback, which is a pointer to the clocksource. But the core needs to touch it to access the members @read and @mask. So we are better off by copying the @read function pointer and the @mask from the clocksource to the core data structure itself. For the most used ktime_get() access all required data including the @read and @mask copies fits together with the sequence counter into a single 64 byte cacheline. For the other time access functions we touch in the current code three cache lines in the worst case. But with the clocksource data copies we can reduce that to two adjacent cachelines, which is more efficient than disjunct cache lines. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 4 ++++ kernel/time/timekeeping.c | 35 +++++++++++++++-------------------- 2 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index cb88096222c0..75bb8add78f5 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -29,6 +29,10 @@ struct timekeeper { /* Current clocksource used for timekeeping. */ struct clocksource *clock; + /* Read function of @clock */ + cycle_t (*read)(struct clocksource *cs); + /* Bitmask for two's complement subtraction of non 64bit counters */ + cycle_t mask; /* Last cycle value */ cycle_t cycle_last; /* NTP adjusted clock multiplier */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 4e748c404749..14b7367e6b94 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -121,7 +121,9 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) old_clock = tk->clock; tk->clock = clock; - tk->cycle_last = clock->read(clock); + tk->read = clock->read; + tk->mask = clock->mask; + tk->cycle_last = tk->read(clock); /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; @@ -174,15 +176,13 @@ static inline u32 arch_gettimeoffset(void) { return 0; } static inline s64 timekeeping_get_ns(struct timekeeper *tk) { cycle_t cycle_now, delta; - struct clocksource *clock; s64 nsec; /* read clocksource: */ - clock = tk->clock; - cycle_now = clock->read(clock); + cycle_now = tk->read(tk->clock); /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, tk->cycle_last, clock->mask); + delta = clocksource_delta(cycle_now, tk->cycle_last, tk->mask); nsec = delta * tk->mult + tk->xtime_nsec; nsec >>= tk->shift; @@ -193,16 +193,15 @@ static inline s64 timekeeping_get_ns(struct timekeeper *tk) static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) { + struct clocksource *clock = tk->clock; cycle_t cycle_now, delta; - struct clocksource *clock; s64 nsec; /* read clocksource: */ - clock = tk->clock; - cycle_now = clock->read(clock); + cycle_now = tk->read(clock); /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, tk->cycle_last, clock->mask); + delta = clocksource_delta(cycle_now, tk->cycle_last, tk->mask); /* convert delta to nanoseconds. */ nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); @@ -337,13 +336,12 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { + struct clocksource *clock = tk->clock; cycle_t cycle_now, delta; - struct clocksource *clock; s64 nsec; - clock = tk->clock; - cycle_now = clock->read(clock); - delta = clocksource_delta(cycle_now, tk->cycle_last, clock->mask); + cycle_now = tk->read(clock); + delta = clocksource_delta(cycle_now, tk->cycle_last, tk->mask); tk->cycle_last = cycle_now; tk->xtime_nsec += delta * tk->mult; @@ -1019,7 +1017,7 @@ static void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = clock->read(clock); + cycle_now = tk->read(clock); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && cycle_now > tk->cycle_last) { u64 num, max = ULLONG_MAX; @@ -1028,7 +1026,7 @@ static void timekeeping_resume(void) s64 nsec = 0; cycle_delta = clocksource_delta(cycle_now, tk->cycle_last, - clock->mask); + tk->mask); /* * "cycle_delta * mutl" may cause 64 bits overflow, if the @@ -1415,7 +1413,6 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, */ void update_wall_time(void) { - struct clocksource *clock; struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; cycle_t offset; @@ -1429,13 +1426,11 @@ void update_wall_time(void) if (unlikely(timekeeping_suspended)) goto out; - clock = real_tk->clock; - #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(clock->read(clock), tk->cycle_last, - clock->mask); + offset = clocksource_delta(tk->read(tk->clock), tk->cycle_last, + tk->mask); #endif /* Check if there's really nothing to do */ -- cgit v1.2.3 From d28ede83791defee9a81e558540699dc46dbbe13 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:05:16 +0000 Subject: timekeeping: Create struct tk_read_base and use it in struct timekeeper The members of the new struct are the required ones for the new NMI safe accessor to clcok monotonic. In order to reuse the existing timekeeping code and to make the update of the fast NMI safe timekeepers a simple memcpy use the struct for the timekeeper as well and convert all users. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Mathieu Desnoyers Signed-off-by: John Stultz --- arch/arm64/kernel/vdso.c | 10 +-- arch/s390/kernel/time.c | 16 ++--- arch/tile/kernel/time.c | 10 +-- arch/x86/kernel/vsyscall_gtod.c | 23 ++++--- arch/x86/kvm/x86.c | 14 ++-- include/linux/timekeeper_internal.h | 103 +++++++++++++++------------- kernel/time/timekeeping.c | 132 ++++++++++++++++++------------------ 7 files changed, 158 insertions(+), 150 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 574672f001f7..8296f7f5f0ba 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -211,7 +211,7 @@ struct vm_area_struct *get_gate_vma(struct mm_struct *mm) void update_vsyscall(struct timekeeper *tk) { struct timespec xtime_coarse; - u32 use_syscall = strcmp(tk->clock->name, "arch_sys_counter"); + u32 use_syscall = strcmp(tk->tkr.clock->name, "arch_sys_counter"); ++vdso_data->tb_seq_count; smp_wmb(); @@ -224,11 +224,11 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { - vdso_data->cs_cycle_last = tk->cycle_last; + vdso_data->cs_cycle_last = tk->tkr.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->xtime_nsec; - vdso_data->cs_mult = tk->mult; - vdso_data->cs_shift = tk->shift; + vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; + vdso_data->cs_mult = tk->tkr.mult; + vdso_data->cs_shift = tk->tkr.shift; } smp_wmb(); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 97950f392613..4cef607f3711 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -214,26 +214,26 @@ void update_vsyscall(struct timekeeper *tk) { u64 nsecps; - if (tk->clock != &clocksource_tod) + if (tk->tkr.clock != &clocksource_tod) return; /* Make userspace gettimeofday spin until we're done. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = tk->cycle_last; + vdso_data->xtime_tod_stamp = tk->tkr.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->xtime_nsec; + vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; vdso_data->wtom_clock_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdso_data->wtom_clock_nsec = tk->xtime_nsec + - + ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift); - nsecps = (u64) NSEC_PER_SEC << tk->shift; + vdso_data->wtom_clock_nsec = tk->tkr.xtime_nsec + + + ((u64) tk->wall_to_monotonic.tv_nsec << tk->tkr.shift); + nsecps = (u64) NSEC_PER_SEC << tk->tkr.shift; while (vdso_data->wtom_clock_nsec >= nsecps) { vdso_data->wtom_clock_nsec -= nsecps; vdso_data->wtom_clock_sec++; } - vdso_data->tk_mult = tk->mult; - vdso_data->tk_shift = tk->shift; + vdso_data->tk_mult = tk->tkr.mult; + vdso_data->tk_shift = tk->tkr.shift; smp_wmb(); ++vdso_data->tb_update_count; } diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c index d22d5bfc1e4e..d8fbc289e680 100644 --- a/arch/tile/kernel/time.c +++ b/arch/tile/kernel/time.c @@ -261,7 +261,7 @@ void update_vsyscall_tz(void) void update_vsyscall(struct timekeeper *tk) { struct timespec *wtm = &tk->wall_to_monotonic; - struct clocksource *clock = tk->clock; + struct clocksource *clock = tk->tkr.clock; if (clock != &cycle_counter_cs) return; @@ -269,13 +269,13 @@ void update_vsyscall(struct timekeeper *tk) /* Userspace gettimeofday will spin while this value is odd. */ ++vdso_data->tb_update_count; smp_wmb(); - vdso_data->xtime_tod_stamp = tk->cycle_last; + vdso_data->xtime_tod_stamp = tk->tkr.cycle_last; vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->xtime_nsec; + vdso_data->xtime_clock_nsec = tk->tkr.xtime_nsec; vdso_data->wtom_clock_sec = wtm->tv_sec; vdso_data->wtom_clock_nsec = wtm->tv_nsec; - vdso_data->mult = tk->mult; - vdso_data->shift = tk->shift; + vdso_data->mult = tk->tkr.mult; + vdso_data->shift = tk->tkr.shift; smp_wmb(); ++vdso_data->tb_update_count; } diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c index c3cb3c144591..c7d791f32b98 100644 --- a/arch/x86/kernel/vsyscall_gtod.c +++ b/arch/x86/kernel/vsyscall_gtod.c @@ -31,29 +31,30 @@ void update_vsyscall(struct timekeeper *tk) gtod_write_begin(vdata); /* copy vsyscall data */ - vdata->vclock_mode = tk->clock->archdata.vclock_mode; - vdata->cycle_last = tk->cycle_last; - vdata->mask = tk->clock->mask; - vdata->mult = tk->mult; - vdata->shift = tk->shift; + vdata->vclock_mode = tk->tkr.clock->archdata.vclock_mode; + vdata->cycle_last = tk->tkr.cycle_last; + vdata->mask = tk->tkr.mask; + vdata->mult = tk->tkr.mult; + vdata->shift = tk->tkr.shift; vdata->wall_time_sec = tk->xtime_sec; - vdata->wall_time_snsec = tk->xtime_nsec; + vdata->wall_time_snsec = tk->tkr.xtime_nsec; vdata->monotonic_time_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_snsec = tk->xtime_nsec + vdata->monotonic_time_snsec = tk->tkr.xtime_nsec + ((u64)tk->wall_to_monotonic.tv_nsec - << tk->shift); + << tk->tkr.shift); while (vdata->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->shift)) { + (((u64)NSEC_PER_SEC) << tk->tkr.shift)) { vdata->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->shift; + ((u64)NSEC_PER_SEC) << tk->tkr.shift; vdata->monotonic_time_sec++; } vdata->wall_time_coarse_sec = tk->xtime_sec; - vdata->wall_time_coarse_nsec = (long)(tk->xtime_nsec >> tk->shift); + vdata->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >> + tk->tkr.shift); vdata->monotonic_time_coarse_sec = vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7b25125f3f42..b7e57946d1c1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -995,19 +995,19 @@ static void update_pvclock_gtod(struct timekeeper *tk) struct pvclock_gtod_data *vdata = &pvclock_gtod_data; u64 boot_ns; - boot_ns = ktime_to_ns(ktime_add(tk->base_mono, tk->offs_boot)); + boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot)); write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ - vdata->clock.vclock_mode = tk->clock->archdata.vclock_mode; - vdata->clock.cycle_last = tk->cycle_last; - vdata->clock.mask = tk->clock->mask; - vdata->clock.mult = tk->mult; - vdata->clock.shift = tk->shift; + vdata->clock.vclock_mode = tk->tkr.clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->tkr.cycle_last; + vdata->clock.mask = tk->tkr.mask; + vdata->clock.mult = tk->tkr.mult; + vdata->clock.shift = tk->tkr.shift; vdata->boot_ns = boot_ns; - vdata->nsec_base = tk->xtime_nsec; + vdata->nsec_base = tk->tkr.xtime_nsec; write_seqcount_end(&vdata->seq); } diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 75bb8add78f5..97381997625b 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -10,80 +10,87 @@ #include #include -/* - * Structure holding internal timekeeping values. - * - * Note: wall_to_monotonic is what we need to add to xtime (or xtime - * corrected for sub jiffie times) to get to monotonic time. - * Monotonic is pegged at zero at system boot time, so - * wall_to_monotonic will be negative, however, we will ALWAYS keep - * the tv_nsec part positive so we can use the usual normalization. +/** + * struct tk_read_base - base structure for timekeeping readout + * @clock: Current clocksource used for timekeeping. + * @read: Read function of @clock + * @mask: Bitmask for two's complement subtraction of non 64bit clocks + * @cycle_last: @clock cycle value at last update + * @mult: NTP adjusted multiplier for scaled math conversion + * @shift: Shift value for scaled math conversion + * @xtime_nsec: Shifted (fractional) nano seconds offset for readout + * @base_mono: ktime_t (nanoseconds) base time for readout * - * wall_to_monotonic is moved after resume from suspend for the - * monotonic time not to jump. To calculate the real boot time offset - * we need to do offs_real - offs_boot. + * This struct has size 56 byte on 64 bit. Together with a seqcount it + * occupies a single 64byte cache line. * - * - wall_to_monotonic is no longer the boot time, getboottime must be - * used instead. + * The struct is separate from struct timekeeper as it is also used + * for a fast NMI safe accessor to clock monotonic. */ -struct timekeeper { - /* Current clocksource used for timekeeping. */ +struct tk_read_base { struct clocksource *clock; - /* Read function of @clock */ cycle_t (*read)(struct clocksource *cs); - /* Bitmask for two's complement subtraction of non 64bit counters */ cycle_t mask; - /* Last cycle value */ cycle_t cycle_last; - /* NTP adjusted clock multiplier */ u32 mult; - /* The shift value of the current clocksource. */ u32 shift; - /* Clock shifted nano seconds */ u64 xtime_nsec; - - /* Monotonic base time */ ktime_t base_mono; +}; - /* Current CLOCK_REALTIME time in seconds */ +/** + * struct timekeeper - Structure holding internal timekeeping values. + * @tkr: The readout base structure + * @xtime_sec: Current CLOCK_REALTIME time in seconds + * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset + * @offs_real: Offset clock monotonic -> clock realtime + * @offs_boot: Offset clock monotonic -> clock boottime + * @offs_tai: Offset clock monotonic -> clock tai + * @tai_offset: The current UTC to TAI offset in seconds + * @base_raw: Monotonic raw base time in ktime_t format + * @raw_time: Monotonic raw base time in timespec64 format + * @cycle_interval: Number of clock cycles in one NTP interval + * @xtime_interval: Number of clock shifted nano seconds in one NTP + * interval. + * @xtime_remainder: Shifted nano seconds left over when rounding + * @cycle_interval + * @raw_interval: Raw nano seconds accumulated per NTP interval. + * @ntp_error: Difference between accumulated time and NTP time in ntp + * shifted nano seconds. + * @ntp_error_shift: Shift conversion between clock shifted nano seconds and + * ntp shifted nano seconds. + * + * Note: For timespec(64) based interfaces wall_to_monotonic is what + * we need to add to xtime (or xtime corrected for sub jiffie times) + * to get to monotonic time. Monotonic is pegged at zero at system + * boot time, so wall_to_monotonic will be negative, however, we will + * ALWAYS keep the tv_nsec part positive so we can use the usual + * normalization. + * + * wall_to_monotonic is moved after resume from suspend for the + * monotonic time not to jump. We need to add total_sleep_time to + * wall_to_monotonic to get the real boot based time offset. + * + * wall_to_monotonic is no longer the boot time, getboottime must be + * used instead. + */ +struct timekeeper { + struct tk_read_base tkr; u64 xtime_sec; - /* CLOCK_REALTIME to CLOCK_MONOTONIC offset */ struct timespec64 wall_to_monotonic; - - /* Offset clock monotonic -> clock realtime */ ktime_t offs_real; - /* Offset clock monotonic -> clock boottime */ ktime_t offs_boot; - /* Offset clock monotonic -> clock tai */ ktime_t offs_tai; - - /* The current UTC to TAI offset in seconds */ s32 tai_offset; - - /* Monotonic raw base time */ ktime_t base_raw; - - /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ struct timespec64 raw_time; - /* Number of clock cycles in one NTP interval. */ + /* The following members are for timekeeping internal use */ cycle_t cycle_interval; - /* Number of clock shifted nano seconds in one NTP interval. */ u64 xtime_interval; - /* shifted nano seconds left over when rounding cycle_interval */ s64 xtime_remainder; - /* Raw nano seconds accumulated per NTP interval. */ u32 raw_interval; - - /* - * Difference between accumulated time and NTP time in ntp - * shifted nano seconds. - */ s64 ntp_error; - /* - * Shift conversion between clock shifted nano seconds and - * ntp shifted nano seconds. - */ u32 ntp_error_shift; }; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 14b7367e6b94..ccb69980ef7e 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -52,8 +52,8 @@ bool __read_mostly persistent_clock_exist = false; static inline void tk_normalize_xtime(struct timekeeper *tk) { - while (tk->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) { - tk->xtime_nsec -= (u64)NSEC_PER_SEC << tk->shift; + while (tk->tkr.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr.shift)) { + tk->tkr.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr.shift; tk->xtime_sec++; } } @@ -63,20 +63,20 @@ static inline struct timespec64 tk_xtime(struct timekeeper *tk) struct timespec64 ts; ts.tv_sec = tk->xtime_sec; - ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); + ts.tv_nsec = (long)(tk->tkr.xtime_nsec >> tk->tkr.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; - tk->xtime_nsec = (u64)ts->tv_nsec << tk->shift; + tk->tkr.xtime_nsec = (u64)ts->tv_nsec << tk->tkr.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; - tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift; + tk->tkr.xtime_nsec += (u64)ts->tv_nsec << tk->tkr.shift; tk_normalize_xtime(tk); } @@ -119,11 +119,11 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) u64 tmp, ntpinterval; struct clocksource *old_clock; - old_clock = tk->clock; - tk->clock = clock; - tk->read = clock->read; - tk->mask = clock->mask; - tk->cycle_last = tk->read(clock); + old_clock = tk->tkr.clock; + tk->tkr.clock = clock; + tk->tkr.read = clock->read; + tk->tkr.mask = clock->mask; + tk->tkr.cycle_last = tk->tkr.read(clock); /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; @@ -147,11 +147,11 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) - tk->xtime_nsec >>= -shift_change; + tk->tkr.xtime_nsec >>= -shift_change; else - tk->xtime_nsec <<= shift_change; + tk->tkr.xtime_nsec <<= shift_change; } - tk->shift = clock->shift; + tk->tkr.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; @@ -161,7 +161,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ - tk->mult = clock->mult; + tk->tkr.mult = clock->mult; } /* Timekeeper helper functions. */ @@ -179,13 +179,13 @@ static inline s64 timekeeping_get_ns(struct timekeeper *tk) s64 nsec; /* read clocksource: */ - cycle_now = tk->read(tk->clock); + cycle_now = tk->tkr.read(tk->tkr.clock); /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, tk->cycle_last, tk->mask); + delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); - nsec = delta * tk->mult + tk->xtime_nsec; - nsec >>= tk->shift; + nsec = delta * tk->tkr.mult + tk->tkr.xtime_nsec; + nsec >>= tk->tkr.shift; /* If arch requires, add in get_arch_timeoffset() */ return nsec + arch_gettimeoffset(); @@ -193,15 +193,15 @@ static inline s64 timekeeping_get_ns(struct timekeeper *tk) static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) { - struct clocksource *clock = tk->clock; + struct clocksource *clock = tk->tkr.clock; cycle_t cycle_now, delta; s64 nsec; /* read clocksource: */ - cycle_now = tk->read(clock); + cycle_now = tk->tkr.read(clock); /* calculate the delta since the last update_wall_time: */ - delta = clocksource_delta(cycle_now, tk->cycle_last, tk->mask); + delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); /* convert delta to nanoseconds. */ nsec = clocksource_cyc2ns(delta, clock->mult, clock->shift); @@ -217,8 +217,8 @@ static inline void update_vsyscall(struct timekeeper *tk) struct timespec xt; xt = tk_xtime(tk); - update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult, - tk->cycle_last); + update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->tkr.clock, tk->tkr.mult, + tk->tkr.cycle_last); } static inline void old_vsyscall_fixup(struct timekeeper *tk) @@ -235,11 +235,11 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk) * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD * users are removed, this can be killed. */ - remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); - tk->xtime_nsec -= remainder; - tk->xtime_nsec += 1ULL << tk->shift; + remainder = tk->tkr.xtime_nsec & ((1ULL << tk->tkr.shift) - 1); + tk->tkr.xtime_nsec -= remainder; + tk->tkr.xtime_nsec += 1ULL << tk->tkr.shift; tk->ntp_error += remainder << tk->ntp_error_shift; - tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift; + tk->ntp_error -= (1ULL << tk->tkr.shift) << tk->ntp_error_shift; } #else #define old_vsyscall_fixup(tk) @@ -304,7 +304,7 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) nsec = (s64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec *= NSEC_PER_SEC; nsec += tk->wall_to_monotonic.tv_nsec; - tk->base_mono = ns_to_ktime(nsec); + tk->tkr.base_mono = ns_to_ktime(nsec); /* Update the monotonic raw base */ tk->base_raw = timespec64_to_ktime(tk->raw_time); @@ -336,18 +336,18 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->clock; + struct clocksource *clock = tk->tkr.clock; cycle_t cycle_now, delta; s64 nsec; - cycle_now = tk->read(clock); - delta = clocksource_delta(cycle_now, tk->cycle_last, tk->mask); - tk->cycle_last = cycle_now; + cycle_now = tk->tkr.read(clock); + delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, tk->tkr.mask); + tk->tkr.cycle_last = cycle_now; - tk->xtime_nsec += delta * tk->mult; + tk->tkr.xtime_nsec += delta * tk->tkr.mult; /* If arch requires, add in get_arch_timeoffset() */ - tk->xtime_nsec += (u64)arch_gettimeoffset() << tk->shift; + tk->tkr.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr.shift; tk_normalize_xtime(tk); @@ -412,7 +412,7 @@ ktime_t ktime_get(void) do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->base_mono; + base = tk->tkr.base_mono; nsecs = timekeeping_get_ns(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -438,7 +438,7 @@ ktime_t ktime_get_with_offset(enum tk_offsets offs) do { seq = read_seqcount_begin(&tk_core.seq); - base = ktime_add(tk->base_mono, *offset); + base = ktime_add(tk->tkr.base_mono, *offset); nsecs = timekeeping_get_ns(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -731,7 +731,7 @@ static int change_clocksource(void *data) */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { - old = tk->clock; + old = tk->tkr.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); @@ -759,11 +759,11 @@ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; - if (tk->clock == clock) + if (tk->tkr.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); - return tk->clock == clock ? 0 : -1; + return tk->tkr.clock == clock ? 0 : -1; } /** @@ -803,7 +803,7 @@ int timekeeping_valid_for_hres(void) do { seq = read_seqcount_begin(&tk_core.seq); - ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + ret = tk->tkr.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -822,7 +822,7 @@ u64 timekeeping_max_deferment(void) do { seq = read_seqcount_begin(&tk_core.seq); - ret = tk->clock->max_idle_ns; + ret = tk->tkr.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -989,7 +989,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) static void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; - struct clocksource *clock = tk->clock; + struct clocksource *clock = tk->tkr.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; struct timespec tmp; @@ -1017,16 +1017,16 @@ static void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->read(clock); + cycle_now = tk->tkr.read(clock); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && - cycle_now > tk->cycle_last) { + cycle_now > tk->tkr.cycle_last) { u64 num, max = ULLONG_MAX; u32 mult = clock->mult; u32 shift = clock->shift; s64 nsec = 0; - cycle_delta = clocksource_delta(cycle_now, tk->cycle_last, - tk->mask); + cycle_delta = clocksource_delta(cycle_now, tk->tkr.cycle_last, + tk->tkr.mask); /* * "cycle_delta * mutl" may cause 64 bits overflow, if the @@ -1052,7 +1052,7 @@ static void timekeeping_resume(void) __timekeeping_inject_sleeptime(tk, &ts_delta); /* Re-base the last cycle value */ - tk->cycle_last = cycle_now; + tk->tkr.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); @@ -1239,12 +1239,12 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) } } - if (unlikely(tk->clock->maxadj && - (tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) { + if (unlikely(tk->tkr.clock->maxadj && + (tk->tkr.mult + adj > tk->tkr.clock->mult + tk->tkr.clock->maxadj))) { printk_deferred_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", - tk->clock->name, (long)tk->mult + adj, - (long)tk->clock->mult + tk->clock->maxadj); + tk->tkr.clock->name, (long)tk->tkr.mult + adj, + (long)tk->tkr.clock->mult + tk->tkr.clock->maxadj); } /* * So the following can be confusing. @@ -1295,9 +1295,9 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * * XXX - TODO: Doc ntp_error calculation. */ - tk->mult += adj; + tk->tkr.mult += adj; tk->xtime_interval += interval; - tk->xtime_nsec -= offset; + tk->tkr.xtime_nsec -= offset; tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; out_adjust: @@ -1315,9 +1315,9 @@ out_adjust: * We'll correct this error next time through this function, when * xtime_nsec is not as small. */ - if (unlikely((s64)tk->xtime_nsec < 0)) { - s64 neg = -(s64)tk->xtime_nsec; - tk->xtime_nsec = 0; + if (unlikely((s64)tk->tkr.xtime_nsec < 0)) { + s64 neg = -(s64)tk->tkr.xtime_nsec; + tk->tkr.xtime_nsec = 0; tk->ntp_error += neg << tk->ntp_error_shift; } @@ -1333,13 +1333,13 @@ out_adjust: */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { - u64 nsecps = (u64)NSEC_PER_SEC << tk->shift; + u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr.shift; unsigned int clock_set = 0; - while (tk->xtime_nsec >= nsecps) { + while (tk->tkr.xtime_nsec >= nsecps) { int leap; - tk->xtime_nsec -= nsecps; + tk->tkr.xtime_nsec -= nsecps; tk->xtime_sec++; /* Figure out if its a leap sec and apply if needed */ @@ -1384,9 +1384,9 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, /* Accumulate one shifted interval */ offset -= interval; - tk->cycle_last += interval; + tk->tkr.cycle_last += interval; - tk->xtime_nsec += tk->xtime_interval << shift; + tk->tkr.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ @@ -1429,8 +1429,8 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->read(tk->clock), tk->cycle_last, - tk->mask); + offset = clocksource_delta(tk->tkr.read(tk->tkr.clock), + tk->tkr.cycle_last, tk->tkr.mask); #endif /* Check if there's really nothing to do */ @@ -1591,8 +1591,8 @@ ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->base_mono; - nsecs = tk->xtime_nsec >> tk->shift; + base = tk->tkr.base_mono; + nsecs = tk->tkr.xtime_nsec >> tk->tkr.shift; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; @@ -1623,7 +1623,7 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, do { seq = read_seqcount_begin(&tk_core.seq); - base = tk->base_mono; + base = tk->tkr.base_mono; nsecs = timekeeping_get_ns(tk); *offs_real = tk->offs_real; -- cgit v1.2.3 From 0ea5a520f73ca31abc4c10b6d5bc14a884a0641b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:05:20 +0000 Subject: seqcount: Provide raw_read_seqcount() raw_read_seqcount opens a read critical section of the given seqcount without any lockdep checking and without checking or masking the LSB. Calling code is responsible for handling that. Preparatory patch to provide a NMI safe clock monotonic accessor function. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Mathieu Desnoyers Signed-off-by: John Stultz --- include/linux/seqlock.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 535f158977b9..dcc64b9bfc41 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -116,6 +116,22 @@ repeat: return ret; } +/** + * raw_read_seqcount - Read the raw seqcount + * @s: pointer to seqcount_t + * Returns: count to be passed to read_seqcount_retry + * + * raw_read_seqcount opens a read critical section of the given + * seqcount without any lockdep checking and without checking or + * masking the LSB. Calling code is responsible for handling that. + */ +static inline unsigned raw_read_seqcount(const seqcount_t *s) +{ + unsigned ret = ACCESS_ONCE(s->sequence); + smp_rmb(); + return ret; +} + /** * raw_read_seqcount_begin - start seq-read critical section w/o lockdep * @s: pointer to seqcount_t -- cgit v1.2.3 From 9b0fd802e8c0545148324916055e7b40d97963fa Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 16 Jul 2014 21:05:21 +0000 Subject: seqcount: Add raw_write_seqcount_latch() For NMI safe access to clock monotonic we use the seqcount LSB as index of a timekeeper array. The update sequence looks like this: smp_wmb(); <- prior stores to a[1] seq++; smp_wmb(); <- seq increment before update of a[0] update(a[0]); smp_wmb(); <- update of a[0] seq++; smp_wmb(); <- seq increment before update of a[1] update(a[1]); To avoid open coded barriers, provide a helper function. [ tglx: Split out of a combo patch against the first implementation of the NMI safe accessor ] Signed-off-by: Mathieu Desnoyers Cc: John Stultz Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/seqlock.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index dcc64b9bfc41..cce6e7453592 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -235,6 +235,17 @@ static inline void raw_write_seqcount_end(seqcount_t *s) s->sequence++; } +/* + * raw_write_seqcount_latch - redirect readers to even/odd copy + * @s: pointer to seqcount_t + */ +static inline void raw_write_seqcount_latch(seqcount_t *s) +{ + smp_wmb(); /* prior stores before incrementing "sequence" */ + s->sequence++; + smp_wmb(); /* increment "sequence" before following stores */ +} + /* * Sequence counter only version assumes that callers are using their * own mutexing. -- cgit v1.2.3 From 4396e058c52e167729729cf64ea3dfa229637086 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Jul 2014 21:05:23 +0000 Subject: timekeeping: Provide fast and NMI safe access to CLOCK_MONOTONIC Tracers want a correlated time between the kernel instrumentation and user space. We really do not want to export sched_clock() to user space, so we need to provide something sensible for this. Using separate data structures with an non blocking sequence count based update mechanism allows us to do that. The data structure required for the readout has a sequence counter and two copies of the timekeeping data. On the update side: smp_wmb(); tkf->seq++; smp_wmb(); update(tkf->base[0], tk); smp_wmb(); tkf->seq++; smp_wmb(); update(tkf->base[1], tk); On the reader side: do { seq = tkf->seq; smp_rmb(); idx = seq & 0x01; now = now(tkf->base[idx]); smp_rmb(); } while (seq != tkf->seq) So if a NMI hits the update of base[0] it will use base[1] which is still consistent, but this timestamp is not guaranteed to be monotonic across an update. The timestamp is calculated by: now = base_mono + clock_delta * slope So if the update lowers the slope, readers who are forced to the not yet updated second array are still using the old steeper slope. tmono ^ | o n | o n | u | o |o |12345678---> reader order o = old slope u = update n = new slope So reader 6 will observe time going backwards versus reader 5. While other CPUs are likely to be able observe that, the only way for a CPU local observation is when an NMI hits in the middle of the update. Timestamps taken from that NMI context might be ahead of the following timestamps. Callers need to be aware of that and deal with it. V2: Got rid of clock monotonic raw and reorganized the data structures. Folded in the barrier fix from Mathieu. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Mathieu Desnoyers Signed-off-by: John Stultz --- include/linux/timekeeping.h | 2 + kernel/time/timekeeping.c | 124 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 126 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 58ad7eff83ff..1caa6b04fdc5 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -164,6 +164,8 @@ static inline u64 ktime_get_raw_ns(void) return ktime_to_ns(ktime_get_raw()); } +extern u64 ktime_get_mono_fast_ns(void); + /* * Timespec interfaces utilizing the ktime based ones */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index dee23c9d6c21..8980fb722fc5 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -44,6 +44,22 @@ static struct { static DEFINE_RAW_SPINLOCK(timekeeper_lock); static struct timekeeper shadow_timekeeper; +/** + * struct tk_fast - NMI safe timekeeper + * @seq: Sequence counter for protecting updates. The lowest bit + * is the index for the tk_read_base array + * @base: tk_read_base array. Access is indexed by the lowest bit of + * @seq. + * + * See @update_fast_timekeeper() below. + */ +struct tk_fast { + seqcount_t seq; + struct tk_read_base base[2]; +}; + +static struct tk_fast tk_fast_mono ____cacheline_aligned; + /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; @@ -210,6 +226,112 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) return nsec + arch_gettimeoffset(); } +/** + * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. + * @tk: The timekeeper from which we take the update + * @tkf: The fast timekeeper to update + * @tbase: The time base for the fast timekeeper (mono/raw) + * + * We want to use this from any context including NMI and tracing / + * instrumenting the timekeeping code itself. + * + * So we handle this differently than the other timekeeping accessor + * functions which retry when the sequence count has changed. The + * update side does: + * + * smp_wmb(); <- Ensure that the last base[1] update is visible + * tkf->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * update(tkf->base[0], tk); + * smp_wmb(); <- Ensure that the base[0] update is visible + * tkf->seq++; + * smp_wmb(); <- Ensure that the seqcount update is visible + * update(tkf->base[1], tk); + * + * The reader side does: + * + * do { + * seq = tkf->seq; + * smp_rmb(); + * idx = seq & 0x01; + * now = now(tkf->base[idx]); + * smp_rmb(); + * } while (seq != tkf->seq) + * + * As long as we update base[0] readers are forced off to + * base[1]. Once base[0] is updated readers are redirected to base[0] + * and the base[1] update takes place. + * + * So if a NMI hits the update of base[0] then it will use base[1] + * which is still consistent. In the worst case this can result is a + * slightly wrong timestamp (a few nanoseconds). See + * @ktime_get_mono_fast_ns. + */ +static void update_fast_timekeeper(struct timekeeper *tk) +{ + struct tk_read_base *base = tk_fast_mono.base; + + /* Force readers off to base[1] */ + raw_write_seqcount_latch(&tk_fast_mono.seq); + + /* Update base[0] */ + memcpy(base, &tk->tkr, sizeof(*base)); + + /* Force readers back to base[0] */ + raw_write_seqcount_latch(&tk_fast_mono.seq); + + /* Update base[1] */ + memcpy(base + 1, base, sizeof(*base)); +} + +/** + * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic + * + * This timestamp is not guaranteed to be monotonic across an update. + * The timestamp is calculated by: + * + * now = base_mono + clock_delta * slope + * + * So if the update lowers the slope, readers who are forced to the + * not yet updated second array are still using the old steeper slope. + * + * tmono + * ^ + * | o n + * | o n + * | u + * | o + * |o + * |12345678---> reader order + * + * o = old slope + * u = update + * n = new slope + * + * So reader 6 will observe time going backwards versus reader 5. + * + * While other CPUs are likely to be able observe that, the only way + * for a CPU local observation is when an NMI hits in the middle of + * the update. Timestamps taken from that NMI context might be ahead + * of the following timestamps. Callers need to be aware of that and + * deal with it. + */ +u64 notrace ktime_get_mono_fast_ns(void) +{ + struct tk_read_base *tkr; + unsigned int seq; + u64 now; + + do { + seq = raw_read_seqcount(&tk_fast_mono.seq); + tkr = tk_fast_mono.base + (seq & 0x01); + now = ktime_to_ns(tkr->base_mono) + timekeeping_get_ns(tkr); + + } while (read_seqcount_retry(&tk_fast_mono.seq, seq)); + return now; +} +EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); + #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD static inline void update_vsyscall(struct timekeeper *tk) @@ -325,6 +447,8 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); + + update_fast_timekeeper(tk); } /** -- cgit v1.2.3 From dc491596f6394382fbc74ad331156207d619fa0a Mon Sep 17 00:00:00 2001 From: John Stultz Date: Fri, 6 Dec 2013 17:25:21 -0800 Subject: timekeeping: Rework frequency adjustments to work better w/ nohz The existing timekeeping_adjust logic has always been complicated to understand. Further, since it was developed prior to NOHZ becoming common, its not surprising it performs poorly when NOHZ is enabled. Since Miroslav pointed out the problematic nature of the existing code in the NOHZ case, I've tried to refactor the code to perform better. The problem with the previous approach was that it tried to adjust for the total cumulative error using a scaled dampening factor. This resulted in large errors to be corrected slowly, while small errors were corrected quickly. With NOHZ the timekeeping code doesn't know how far out the next tick will be, so this results in bad over-correction to small errors, and insufficient correction to large errors. Inspired by Miroslav's patch, I've refactored the code to try to address the correction in two steps. 1) Check the future freq error for the next tick, and if the frequency error is large, try to make sure we correct it so it doesn't cause much accumulated error. 2) Then make a small single unit adjustment to correct any cumulative error that has collected over time. This method performs fairly well in the simulator Miroslav created. Major credit to Miroslav for pointing out the issue, providing the original patch to resolve this, a simulator for testing, as well as helping debug and resolve issues in my implementation so that it performed closer to his original implementation. Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Reported-by: Miroslav Lichvar Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 1 + kernel/time/timekeeping.c | 193 ++++++++++++++++-------------------- 2 files changed, 84 insertions(+), 110 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 97381997625b..f7ac48d2edf5 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -92,6 +92,7 @@ struct timekeeper { u32 raw_interval; s64 ntp_error; u32 ntp_error_shift; + u32 ntp_err_mult; }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 2b56b959615b..43c706a7a728 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -178,6 +178,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) * to counteract clock drifting. */ tk->tkr.mult = clock->mult; + tk->ntp_err_mult = 0; } /* Timekeeper helper functions. */ @@ -1257,125 +1258,34 @@ static int __init timekeeping_init_ops(void) register_syscore_ops(&timekeeping_syscore_ops); return 0; } - device_initcall(timekeeping_init_ops); /* - * If the error is already larger, we look ahead even further - * to compensate for late or lost adjustments. - */ -static __always_inline int timekeeping_bigadjust(struct timekeeper *tk, - s64 error, s64 *interval, - s64 *offset) -{ - s64 tick_error, i; - u32 look_ahead, adj; - s32 error2, mult; - - /* - * Use the current error value to determine how much to look ahead. - * The larger the error the slower we adjust for it to avoid problems - * with losing too many ticks, otherwise we would overadjust and - * produce an even larger error. The smaller the adjustment the - * faster we try to adjust for it, as lost ticks can do less harm - * here. This is tuned so that an error of about 1 msec is adjusted - * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks). - */ - error2 = tk->ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ); - error2 = abs(error2); - for (look_ahead = 0; error2 > 0; look_ahead++) - error2 >>= 2; - - /* - * Now calculate the error in (1 << look_ahead) ticks, but first - * remove the single look ahead already included in the error. - */ - tick_error = ntp_tick_length() >> (tk->ntp_error_shift + 1); - tick_error -= tk->xtime_interval >> 1; - error = ((error - tick_error) >> look_ahead) + tick_error; - - /* Finally calculate the adjustment shift value. */ - i = *interval; - mult = 1; - if (error < 0) { - error = -error; - *interval = -*interval; - *offset = -*offset; - mult = -1; - } - for (adj = 0; error > i; adj++) - error >>= 1; - - *interval <<= adj; - *offset <<= adj; - return mult << adj; -} - -/* - * Adjust the multiplier to reduce the error value, - * this is optimized for the most common adjustments of -1,0,1, - * for other values we can do a bit more work. + * Apply a multiplier adjustment to the timekeeper */ -static void timekeeping_adjust(struct timekeeper *tk, s64 offset) +static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, + s64 offset, + bool negative, + int adj_scale) { - s64 error, interval = tk->cycle_interval; - int adj; + s64 interval = tk->cycle_interval; + s32 mult_adj = 1; - /* - * The point of this is to check if the error is greater than half - * an interval. - * - * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs. - * - * Note we subtract one in the shift, so that error is really error*2. - * This "saves" dividing(shifting) interval twice, but keeps the - * (error > interval) comparison as still measuring if error is - * larger than half an interval. - * - * Note: It does not "save" on aggravation when reading the code. - */ - error = tk->ntp_error >> (tk->ntp_error_shift - 1); - if (error > interval) { - /* - * We now divide error by 4(via shift), which checks if - * the error is greater than twice the interval. - * If it is greater, we need a bigadjust, if its smaller, - * we can adjust by 1. - */ - error >>= 2; - if (likely(error <= interval)) - adj = 1; - else - adj = timekeeping_bigadjust(tk, error, &interval, &offset); - } else { - if (error < -interval) { - /* See comment above, this is just switched for the negative */ - error >>= 2; - if (likely(error >= -interval)) { - adj = -1; - interval = -interval; - offset = -offset; - } else { - adj = timekeeping_bigadjust(tk, error, &interval, &offset); - } - } else { - goto out_adjust; - } + if (negative) { + mult_adj = -mult_adj; + interval = -interval; + offset = -offset; } + mult_adj <<= adj_scale; + interval <<= adj_scale; + offset <<= adj_scale; - if (unlikely(tk->tkr.clock->maxadj && - (tk->tkr.mult + adj > tk->tkr.clock->mult + tk->tkr.clock->maxadj))) { - printk_deferred_once(KERN_WARNING - "Adjusting %s more than 11%% (%ld vs %ld)\n", - tk->tkr.clock->name, (long)tk->tkr.mult + adj, - (long)tk->tkr.clock->mult + tk->tkr.clock->maxadj); - } /* * So the following can be confusing. * - * To keep things simple, lets assume adj == 1 for now. + * To keep things simple, lets assume mult_adj == 1 for now. * - * When adj != 1, remember that the interval and offset values + * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier @@ -1419,12 +1329,76 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) * * XXX - TODO: Doc ntp_error calculation. */ - tk->tkr.mult += adj; + tk->tkr.mult += mult_adj; tk->xtime_interval += interval; tk->tkr.xtime_nsec -= offset; tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; +} + +/* + * Calculate the multiplier adjustment needed to match the frequency + * specified by NTP + */ +static __always_inline void timekeeping_freqadjust(struct timekeeper *tk, + s64 offset) +{ + s64 interval = tk->cycle_interval; + s64 xinterval = tk->xtime_interval; + s64 tick_error; + bool negative; + u32 adj; + + /* Remove any current error adj from freq calculation */ + if (tk->ntp_err_mult) + xinterval -= tk->cycle_interval; + + /* Calculate current error per tick */ + tick_error = ntp_tick_length() >> tk->ntp_error_shift; + tick_error -= (xinterval + tk->xtime_remainder); + + /* Don't worry about correcting it if its small */ + if (likely((tick_error >= 0) && (tick_error <= interval))) + return; + + /* preserve the direction of correction */ + negative = (tick_error < 0); + + /* Sort out the magnitude of the correction */ + tick_error = abs(tick_error); + for (adj = 0; tick_error > interval; adj++) + tick_error >>= 1; + + /* scale the corrections */ + timekeeping_apply_adjustment(tk, offset, negative, adj); +} + +/* + * Adjust the timekeeper's multiplier to the correct frequency + * and also to reduce the accumulated error value. + */ +static void timekeeping_adjust(struct timekeeper *tk, s64 offset) +{ + /* Correct for the current frequency error */ + timekeeping_freqadjust(tk, offset); + + /* Next make a small adjustment to fix any cumulative error */ + if (!tk->ntp_err_mult && (tk->ntp_error > 0)) { + tk->ntp_err_mult = 1; + timekeeping_apply_adjustment(tk, offset, 0, 0); + } else if (tk->ntp_err_mult && (tk->ntp_error <= 0)) { + /* Undo any existing error adjustment */ + timekeeping_apply_adjustment(tk, offset, 1, 0); + tk->ntp_err_mult = 0; + } + + if (unlikely(tk->tkr.clock->maxadj && + (tk->tkr.mult > tk->tkr.clock->mult + tk->tkr.clock->maxadj))) { + printk_once(KERN_WARNING + "Adjusting %s more than 11%% (%ld vs %ld)\n", + tk->tkr.clock->name, (long)tk->tkr.mult, + (long)tk->tkr.clock->mult + tk->tkr.clock->maxadj); + } -out_adjust: /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource @@ -1444,7 +1418,6 @@ out_adjust: tk->tkr.xtime_nsec = 0; tk->ntp_error += neg << tk->ntp_error_shift; } - } /** -- cgit v1.2.3 From 375f45b5b53a91dfa8f0c11328e0e044f82acbed Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 23 Apr 2014 20:53:29 -0700 Subject: timekeeping: Use cached ntp_tick_length when accumulating error By caching the ntp_tick_length() when we correct the frequency error, and then using that cached value to accumulate error, we avoid large initial errors when the tick length is changed. This makes convergence happen much faster in the simulator, since the initial error doesn't have to be slowly whittled away. This initially seems like an accounting error, but Miroslav pointed out that ntp_tick_length() can change mid-tick, so when we apply it in the error accumulation, we are applying any recent change to the entire tick. This approach chooses to apply changes in the ntp_tick_length() only to the next tick, which allows us to calculate the freq correction before using the new tick length, which avoids accummulating error. Credit to Miroslav for pointing this out and providing the original patch this functionality has been pulled out from, along with the rational. Cc: Miroslav Lichvar Cc: Richard Cochran Cc: Prarit Bhargava Reported-by: Miroslav Lichvar Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 9 +++++++++ kernel/time/timekeeping.c | 5 ++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index f7ac48d2edf5..e9660e52dc09 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -90,6 +90,15 @@ struct timekeeper { u64 xtime_interval; s64 xtime_remainder; u32 raw_interval; + /* The ntp_tick_length() value currently being used. + * This cached copy ensures we consistently apply the tick + * length for an entire tick, as ntp_tick_length may change + * mid-tick, and we don't want to apply that new value to + * the tick in progress. + */ + u64 ntp_tick; + /* Difference between accumulated time and NTP time in ntp + * shifted nano seconds. */ s64 ntp_error; u32 ntp_error_shift; u32 ntp_err_mult; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 43c706a7a728..f36b02838a47 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -171,6 +171,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; + tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently @@ -1352,6 +1353,8 @@ static __always_inline void timekeeping_freqadjust(struct timekeeper *tk, if (tk->ntp_err_mult) xinterval -= tk->cycle_interval; + tk->ntp_tick = ntp_tick_length(); + /* Calculate current error per tick */ tick_error = ntp_tick_length() >> tk->ntp_error_shift; tick_error -= (xinterval + tk->xtime_remainder); @@ -1497,7 +1500,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, tk->raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ - tk->ntp_error += ntp_tick_length() << shift; + tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); -- cgit v1.2.3 From 953dec21aed4038464fec02f96a2f1b8701a5bce Mon Sep 17 00:00:00 2001 From: John Stultz Date: Fri, 25 Jul 2014 21:37:19 -0700 Subject: timekeeping: Fixup typo in update_vsyscall_old definition In commit 4a0e637738f0 ("clocksource: Get rid of cycle_last"), currently in the -tip tree, there was a small typo where cycles_t was used intstead of cycle_t. This broke ppc64 builds. Fix this by using the proper cycle_t type for this usage, in both the definition and the ia64 implementation. Now, having both cycle_t and cycles_t types seems like a very bad idea just asking for these sorts of issues. But that will be a cleanup for another day. Reported-by: Stephen Rothwell Signed-off-by: John Stultz Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1406349439-11785-1-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- arch/ia64/kernel/time.c | 2 +- include/linux/timekeeper_internal.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 11dc42da7daf..3e71ef85e439 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -441,7 +441,7 @@ void update_vsyscall_tz(void) } void update_vsyscall_old(struct timespec *wall, struct timespec *wtm, - struct clocksource *c, u32 mult, cycles_t cycle_last) + struct clocksource *c, u32 mult, cycle_t cycle_last) { write_seqcount_begin(&fsyscall_gtod_data.seq); diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index e9660e52dc09..95640dcd1899 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -113,7 +113,7 @@ extern void update_vsyscall_tz(void); extern void update_vsyscall_old(struct timespec *ts, struct timespec *wtm, struct clocksource *c, u32 mult, - cycles_t cycle_last); + cycle_t cycle_last); extern void update_vsyscall_tz(void); #else -- cgit v1.2.3