diff options
90 files changed, 2357 insertions, 2159 deletions
diff --git a/Documentation/dev-tools/checkpatch.rst b/Documentation/dev-tools/checkpatch.rst index a9fac978a525..abb3ff682076 100644 --- a/Documentation/dev-tools/checkpatch.rst +++ b/Documentation/dev-tools/checkpatch.rst @@ -470,8 +470,6 @@ API usage usleep_range() should be preferred over udelay(). The proper way of using usleep_range() is mentioned in the kernel docs. - See: https://www.kernel.org/doc/html/latest/timers/timers-howto.html#delays-information-on-the-various-kernel-delay-sleep-mechanisms - Comments -------- diff --git a/Documentation/devicetree/bindings/timer/actions,owl-timer.txt b/Documentation/devicetree/bindings/timer/actions,owl-timer.txt deleted file mode 100644 index 977054f87563..000000000000 --- a/Documentation/devicetree/bindings/timer/actions,owl-timer.txt +++ /dev/null @@ -1,21 +0,0 @@ -Actions Semi Owl Timer - -Required properties: -- compatible : "actions,s500-timer" for S500 - "actions,s700-timer" for S700 - "actions,s900-timer" for S900 -- reg : Offset and length of the register set for the device. -- interrupts : Should contain the interrupts. -- interrupt-names : Valid names are: "2hz0", "2hz1", - "timer0", "timer1", "timer2", "timer3" - See ../resource-names.txt - -Example: - - timer@b0168000 { - compatible = "actions,s500-timer"; - reg = <0xb0168000 0x100>; - interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "timer0", "timer1"; - }; diff --git a/Documentation/devicetree/bindings/timer/actions,owl-timer.yaml b/Documentation/devicetree/bindings/timer/actions,owl-timer.yaml new file mode 100644 index 000000000000..646c554a390a --- /dev/null +++ b/Documentation/devicetree/bindings/timer/actions,owl-timer.yaml @@ -0,0 +1,107 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/timer/actions,owl-timer.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Actions Semi Owl timer + +maintainers: + - Andreas Färber <afaerber@suse.de> + +description: + Actions Semi Owl SoCs provide 32bit and 2Hz timers. + The 32bit timers support dynamic irq, as well as one-shot mode. + +properties: + compatible: + enum: + - actions,s500-timer + - actions,s700-timer + - actions,s900-timer + + clocks: + maxItems: 1 + + interrupts: + minItems: 1 + maxItems: 6 + + interrupt-names: + minItems: 1 + maxItems: 6 + items: + enum: + - 2hz0 + - 2hz1 + - timer0 + - timer1 + - timer2 + - timer3 + + reg: + maxItems: 1 + +required: + - compatible + - clocks + - interrupts + - interrupt-names + - reg + +allOf: + - if: + properties: + compatible: + contains: + enum: + - actions,s500-timer + then: + properties: + interrupts: + minItems: 4 + maxItems: 4 + interrupt-names: + items: + - const: 2hz0 + - const: 2hz1 + - const: timer0 + - const: timer1 + + - if: + properties: + compatible: + contains: + enum: + - actions,s700-timer + - actions,s900-timer + then: + properties: + interrupts: + minItems: 1 + maxItems: 1 + interrupt-names: + items: + - const: timer1 + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + soc { + #address-cells = <1>; + #size-cells = <1>; + timer@b0168000 { + compatible = "actions,s500-timer"; + reg = <0xb0168000 0x100>; + clocks = <&hosc>; + interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "2hz0", "2hz1", "timer0", "timer1"; + }; + }; +... diff --git a/Documentation/timers/delay_sleep_functions.rst b/Documentation/timers/delay_sleep_functions.rst new file mode 100644 index 000000000000..49d603a3f113 --- /dev/null +++ b/Documentation/timers/delay_sleep_functions.rst @@ -0,0 +1,121 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Delay and sleep mechanisms +========================== + +This document seeks to answer the common question: "What is the +RightWay (TM) to insert a delay?" + +This question is most often faced by driver writers who have to +deal with hardware delays and who may not be the most intimately +familiar with the inner workings of the Linux Kernel. + +The following table gives a rough overview about the existing function +'families' and their limitations. This overview table does not replace the +reading of the function description before usage! + +.. list-table:: + :widths: 20 20 20 20 20 + :header-rows: 2 + + * - + - `*delay()` + - `usleep_range*()` + - `*sleep()` + - `fsleep()` + * - + - busy-wait loop + - hrtimers based + - timer list timers based + - combines the others + * - Usage in atomic Context + - yes + - no + - no + - no + * - precise on "short intervals" + - yes + - yes + - depends + - yes + * - precise on "long intervals" + - Do not use! + - yes + - max 12.5% slack + - yes + * - interruptible variant + - no + - yes + - yes + - no + +A generic advice for non atomic contexts could be: + +#. Use `fsleep()` whenever unsure (as it combines all the advantages of the + others) +#. Use `*sleep()` whenever possible +#. Use `usleep_range*()` whenever accuracy of `*sleep()` is not sufficient +#. Use `*delay()` for very, very short delays + +Find some more detailed information about the function 'families' in the next +sections. + +`*delay()` family of functions +------------------------------ + +These functions use the jiffy estimation of clock speed and will busy wait for +enough loop cycles to achieve the desired delay. udelay() is the basic +implementation and ndelay() as well as mdelay() are variants. + +These functions are mainly used to add a delay in atomic context. Please make +sure to ask yourself before adding a delay in atomic context: Is this really +required? + +.. kernel-doc:: include/asm-generic/delay.h + :identifiers: udelay ndelay + +.. kernel-doc:: include/linux/delay.h + :identifiers: mdelay + + +`usleep_range*()` and `*sleep()` family of functions +---------------------------------------------------- + +These functions use hrtimers or timer list timers to provide the requested +sleeping duration. In order to decide which function is the right one to use, +take some basic information into account: + +#. hrtimers are more expensive as they are using an rb-tree (instead of hashing) +#. hrtimers are more expensive when the requested sleeping duration is the first + timer which means real hardware has to be programmed +#. timer list timers always provide some sort of slack as they are jiffy based + +The generic advice is repeated here: + +#. Use `fsleep()` whenever unsure (as it combines all the advantages of the + others) +#. Use `*sleep()` whenever possible +#. Use `usleep_range*()` whenever accuracy of `*sleep()` is not sufficient + +First check fsleep() function description and to learn more about accuracy, +please check msleep() function description. + + +`usleep_range*()` +~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/linux/delay.h + :identifiers: usleep_range usleep_range_idle + +.. kernel-doc:: kernel/time/sleep_timeout.c + :identifiers: usleep_range_state + + +`*sleep()` +~~~~~~~~~~ + +.. kernel-doc:: kernel/time/sleep_timeout.c + :identifiers: msleep msleep_interruptible + +.. kernel-doc:: include/linux/delay.h + :identifiers: ssleep fsleep diff --git a/Documentation/timers/index.rst b/Documentation/timers/index.rst index 983f91f8f023..4e88116e4dcf 100644 --- a/Documentation/timers/index.rst +++ b/Documentation/timers/index.rst @@ -12,7 +12,7 @@ Timers hrtimers no_hz timekeeping - timers-howto + delay_sleep_functions .. only:: subproject and html diff --git a/Documentation/timers/timers-howto.rst b/Documentation/timers/timers-howto.rst deleted file mode 100644 index ef7a4652ccc9..000000000000 --- a/Documentation/timers/timers-howto.rst +++ /dev/null @@ -1,115 +0,0 @@ -=================================================================== -delays - Information on the various kernel delay / sleep mechanisms -=================================================================== - -This document seeks to answer the common question: "What is the -RightWay (TM) to insert a delay?" - -This question is most often faced by driver writers who have to -deal with hardware delays and who may not be the most intimately -familiar with the inner workings of the Linux Kernel. - - -Inserting Delays ----------------- - -The first, and most important, question you need to ask is "Is my -code in an atomic context?" This should be followed closely by "Does -it really need to delay in atomic context?" If so... - -ATOMIC CONTEXT: - You must use the `*delay` family of functions. These - functions use the jiffy estimation of clock speed - and will busy wait for enough loop cycles to achieve - the desired delay: - - ndelay(unsigned long nsecs) - udelay(unsigned long usecs) - mdelay(unsigned long msecs) - - udelay is the generally preferred API; ndelay-level - precision may not actually exist on many non-PC devices. - - mdelay is macro wrapper around udelay, to account for - possible overflow when passing large arguments to udelay. - In general, use of mdelay is discouraged and code should - be refactored to allow for the use of msleep. - -NON-ATOMIC CONTEXT: - You should use the `*sleep[_range]` family of functions. - There are a few more options here, while any of them may - work correctly, using the "right" sleep function will - help the scheduler, power management, and just make your - driver better :) - - -- Backed by busy-wait loop: - - udelay(unsigned long usecs) - - -- Backed by hrtimers: - - usleep_range(unsigned long min, unsigned long max) - - -- Backed by jiffies / legacy_timers - - msleep(unsigned long msecs) - msleep_interruptible(unsigned long msecs) - - Unlike the `*delay` family, the underlying mechanism - driving each of these calls varies, thus there are - quirks you should be aware of. - - - SLEEPING FOR "A FEW" USECS ( < ~10us? ): - * Use udelay - - - Why not usleep? - On slower systems, (embedded, OR perhaps a speed- - stepped PC!) the overhead of setting up the hrtimers - for usleep *may* not be worth it. Such an evaluation - will obviously depend on your specific situation, but - it is something to be aware of. - - SLEEPING FOR ~USECS OR SMALL MSECS ( 10us - 20ms): - * Use usleep_range - - - Why not msleep for (1ms - 20ms)? - Explained originally here: - https://lore.kernel.org/r/15327.1186166232@lwn.net - - msleep(1~20) may not do what the caller intends, and - will often sleep longer (~20 ms actual sleep for any - value given in the 1~20ms range). In many cases this - is not the desired behavior. - - - Why is there no "usleep" / What is a good range? - Since usleep_range is built on top of hrtimers, the - wakeup will be very precise (ish), thus a simple - usleep function would likely introduce a large number - of undesired interrupts. - - With the introduction of a range, the scheduler is - free to coalesce your wakeup with any other wakeup - that may have happened for other reasons, or at the - worst case, fire an interrupt for your upper bound. - - The larger a range you supply, the greater a chance - that you will not trigger an interrupt; this should - be balanced with what is an acceptable upper bound on - delay / performance for your specific code path. Exact - tolerances here are very situation specific, thus it - is left to the caller to determine a reasonable range. - - SLEEPING FOR LARGER MSECS ( 10ms+ ) - * Use msleep or possibly msleep_interruptible - - - What's the difference? - msleep sets the current task to TASK_UNINTERRUPTIBLE - whereas msleep_interruptible sets the current task to - TASK_INTERRUPTIBLE before scheduling the sleep. In - short, the difference is whether the sleep can be ended - early by a signal. In general, just use msleep unless - you know you have a need for the interruptible variant. - - FLEXIBLE SLEEPING (any delay, uninterruptible) - * Use fsleep diff --git a/MAINTAINERS b/MAINTAINERS index b23f8e9f23b3..a4628d566e98 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1998,7 +1998,7 @@ F: Documentation/devicetree/bindings/mmc/owl-mmc.yaml F: Documentation/devicetree/bindings/net/actions,owl-emac.yaml F: Documentation/devicetree/bindings/pinctrl/actions,* F: Documentation/devicetree/bindings/power/actions,owl-sps.txt -F: Documentation/devicetree/bindings/timer/actions,owl-timer.txt +F: Documentation/devicetree/bindings/timer/actions,owl-timer.yaml F: arch/arm/boot/dts/actions/ F: arch/arm/mach-actions/ F: arch/arm64/boot/dts/actions/ @@ -10138,10 +10138,12 @@ S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core F: Documentation/timers/ F: include/linux/clockchips.h +F: include/linux/delay.h F: include/linux/hrtimer.h F: include/linux/timer.h F: kernel/time/clockevents.c F: kernel/time/hrtimer.c +F: kernel/time/sleep_timeout.c F: kernel/time/timer.c F: kernel/time/timer_list.c F: kernel/time/timer_migration.* diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 9a14f721a2b0..42a3706e16a6 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -93,7 +93,6 @@ static void twd_timer_stop(void) { struct clock_event_device *clk = raw_cpu_ptr(twd_evt); - twd_shutdown(clk); disable_percpu_irq(clk->irq); } diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 08c012a2591f..910d059ec70b 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -1,13 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 if RALINK -config CLKEVT_RT3352 - bool - depends on SOC_RT305X || SOC_MT7620 - default y - select TIMER_OF - select CLKSRC_MMIO - config RALINK_ILL_ACC bool depends on SOC_RT305X diff --git a/arch/mips/ralink/Makefile b/arch/mips/ralink/Makefile index 26fabbdea1f1..0c109eae1953 100644 --- a/arch/mips/ralink/Makefile +++ b/arch/mips/ralink/Makefile @@ -10,8 +10,6 @@ ifndef CONFIG_MIPS_GIC obj-y += clk.o timer.o endif -obj-$(CONFIG_CLKEVT_RT3352) += cevt-rt3352.o - obj-$(CONFIG_RALINK_ILL_ACC) += ill_acc.o obj-$(CONFIG_IRQ_INTC) += irq.o diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index f7e86e09c49f..d31c9799cab2 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1390,21 +1390,14 @@ bool __ref rtas_busy_delay(int status) */ ms = clamp(ms, 1U, 1000U); /* - * The delay hint is an order-of-magnitude suggestion, not - * a minimum. It is fine, possibly even advantageous, for - * us to pause for less time than hinted. For small values, - * use usleep_range() to ensure we don't sleep much longer - * than actually needed. - * - * See Documentation/timers/timers-howto.rst for - * explanation of the threshold used here. In effect we use - * usleep_range() for 9900 and 9901, msleep() for - * 9902-9905. + * The delay hint is an order-of-magnitude suggestion, not a + * minimum. It is fine, possibly even advantageous, for us to + * pause for less time than hinted. To make sure pause time will + * not be way longer than requested independent of HZ + * configuration, use fsleep(). See fsleep() for details of + * used sleeping functions. */ - if (ms <= 20) - usleep_range(ms * 100, ms * 1000); - else - msleep(ms); + fsleep(ms * 1000); break; case RTAS_BUSY: ret = true; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 5b1d6325df85..1d5e13b148f2 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -302,7 +302,6 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_WQ_WATCHDOG=y -CONFIG_DEBUG_TIMEKEEPING=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_SPINLOCK=y CONFIG_DEBUG_MUTEXES=y diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8f5362a2498f..a3c31b784edc 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -146,7 +146,6 @@ config X86 select ARCH_HAS_PARANOID_L1D_FLUSH select BUILDTIME_TABLE_SORT select CLKEVT_I8253 - select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CLOCKSOURCE_WATCHDOG # Word-size accesses may read uninitialized data past the trailing \0 # in strings and cause false KMSAN reports. diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 7365dd4acffb..23baf8c9b34c 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -6,8 +6,6 @@ #include <linux/interrupt.h> #include <linux/math64.h> -#define TICK_SIZE (tick_nsec / 1000) - unsigned long long native_sched_clock(void); extern void recalibrate_cpu_khz(void); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 622fe24da910..a909b817b9c0 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -263,13 +263,6 @@ static void kvm_xen_stop_timer(struct kvm_vcpu *vcpu) atomic_set(&vcpu->arch.xen.timer_pending, 0); } -static void kvm_xen_init_timer(struct kvm_vcpu *vcpu) -{ - hrtimer_init(&vcpu->arch.xen.timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_HARD); - vcpu->arch.xen.timer.function = xen_timer_callback; -} - static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) { struct kvm_vcpu_xen *vx = &v->arch.xen; @@ -1070,9 +1063,6 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } - if (!vcpu->arch.xen.timer.function) - kvm_xen_init_timer(vcpu); - /* Stop the timer (if it's running) before changing the vector */ kvm_xen_stop_timer(vcpu); vcpu->arch.xen.timer_virq = data->u.timer.port; @@ -2235,6 +2225,8 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.xen.poll_evtchn = 0; timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0); + hrtimer_init(&vcpu->arch.xen.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + vcpu->arch.xen.timer.function = xen_timer_callback; kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm); kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm); diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 95dd4660b5b6..487c85259967 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -400,7 +400,8 @@ config ARM_GT_INITIAL_PRESCALER_VAL This affects CPU_FREQ max delta from the initial frequency. config ARM_TIMER_SP804 - bool "Support for Dual Timer SP804 module" if COMPILE_TEST + bool "Support for Dual Timer SP804 module" + depends on ARM || ARM64 || COMPILE_TEST depends on GENERIC_SCHED_CLOCK && HAVE_CLK select CLKSRC_MMIO select TIMER_OF if OF @@ -753,4 +754,13 @@ config EP93XX_TIMER Enables support for the Cirrus Logic timer block EP93XX. +config RALINK_TIMER + bool "Ralink System Tick Counter" + depends on SOC_RT305X || SOC_MT7620 || COMPILE_TEST + select CLKSRC_MMIO + select TIMER_OF + help + Enables support for system tick counter present on + Ralink SoCs RT3352 and MT7620. + endmenu diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 22743785299e..43ef16a4efa6 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -91,3 +91,4 @@ obj-$(CONFIG_GOLDFISH_TIMER) += timer-goldfish.o obj-$(CONFIG_GXP_TIMER) += timer-gxp.o obj-$(CONFIG_CLKSRC_LOONGSON1_PWM) += timer-loongson1-pwm.o obj-$(CONFIG_EP93XX_TIMER) += timer-ep93xx.o +obj-$(CONFIG_RALINK_TIMER) += timer-ralink.o diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 03733101e231..808f259781fd 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -1179,8 +1179,6 @@ static void arch_timer_stop(struct clock_event_device *clk) disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]); if (arch_timer_has_nonsecure_ppi()) disable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]); - - clk->set_state_shutdown(clk); } static int arch_timer_dying_cpu(unsigned int cpu) @@ -1430,7 +1428,7 @@ static int __init arch_timer_of_init(struct device_node *np) arch_timers_present |= ARCH_TIMER_TYPE_CP15; - has_names = of_property_read_bool(np, "interrupt-names"); + has_names = of_property_present(np, "interrupt-names"); for (i = ARCH_TIMER_PHYS_SECURE_PPI; i < ARCH_TIMER_MAX_TIMER_PPI; i++) { if (has_names) diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index a05cfaab5f84..2d86bbc2764a 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -195,7 +195,6 @@ static int gt_dying_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(gt_evt); - gt_clockevent_shutdown(clk); disable_percpu_irq(clk->irq); return 0; } diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c index f5f24a95ee82..3a55ae5fe225 100644 --- a/drivers/clocksource/dw_apb_timer.c +++ b/drivers/clocksource/dw_apb_timer.c @@ -68,25 +68,6 @@ static inline void apbt_writel_relaxed(struct dw_apb_timer *timer, u32 val, writel_relaxed(val, timer->base + offs); } -static void apbt_disable_int(struct dw_apb_timer *timer) -{ - u32 ctrl = apbt_readl(timer, APBTMR_N_CONTROL); - - ctrl |= APBTMR_CONTROL_INT; - apbt_writel(timer, ctrl, APBTMR_N_CONTROL); -} - -/** - * dw_apb_clockevent_pause() - stop the clock_event_device from running - * - * @dw_ced: The APB clock to stop generating events. - */ -void dw_apb_clockevent_pause(struct dw_apb_clock_event_device *dw_ced) -{ - disable_irq(dw_ced->timer.irq); - apbt_disable_int(&dw_ced->timer); -} - static void apbt_eoi(struct dw_apb_timer *timer) { apbt_readl_relaxed(timer, APBTMR_N_EOI); @@ -285,26 +266,6 @@ dw_apb_clockevent_init(int cpu, const char *name, unsigned rating, } /** - * dw_apb_clockevent_resume() - resume a clock that has been paused. - * - * @dw_ced: The APB clock to resume. - */ -void dw_apb_clockevent_resume(struct dw_apb_clock_event_device *dw_ced) -{ - enable_irq(dw_ced->timer.irq); -} - -/** - * dw_apb_clockevent_stop() - stop the clock_event_device and release the IRQ. - * - * @dw_ced: The APB clock to stop generating the events. - */ -void dw_apb_clockevent_stop(struct dw_apb_clock_event_device *dw_ced) -{ - free_irq(dw_ced->timer.irq, &dw_ced->ced); -} - -/** * dw_apb_clockevent_register() - register the clock with the generic layer * * @dw_ced: The APB clock to register as a clock_event_device. diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index ef8cb1b71be4..e6a02e351d77 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -496,7 +496,6 @@ static int exynos4_mct_dying_cpu(unsigned int cpu) per_cpu_ptr(&percpu_mct_tick, cpu); struct clock_event_device *evt = &mevt->evt; - evt->set_state_shutdown(evt); if (mct_int_type == MCT_INT_SPI) { if (evt->irq != -1) disable_irq_nosync(evt->irq); diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c index 110347707ff9..7907b740497a 100644 --- a/drivers/clocksource/mips-gic-timer.c +++ b/drivers/clocksource/mips-gic-timer.c @@ -166,6 +166,37 @@ static u64 gic_hpt_read(struct clocksource *cs) return gic_read_count(); } +static u64 gic_hpt_read_multicluster(struct clocksource *cs) +{ + unsigned int hi, hi2, lo; + u64 count; + + mips_cm_lock_other(0, 0, 0, CM_GCR_Cx_OTHER_BLOCK_GLOBAL); + + if (mips_cm_is64) { + count = read_gic_redir_counter(); + goto out; + } + + hi = read_gic_redir_counter_32h(); + while (true) { + lo = read_gic_redir_counter_32l(); + + /* If hi didn't change then lo didn't wrap & we're done */ + hi2 = read_gic_redir_counter_32h(); + if (hi2 == hi) + break; + + /* Otherwise, repeat with the latest hi value */ + hi = hi2; + } + + count = (((u64)hi) << 32) + lo; +out: + mips_cm_unlock_other(); + return count; +} + static struct clocksource gic_clocksource = { .name = "GIC", .read = gic_hpt_read, @@ -203,6 +234,11 @@ static int __init __gic_clocksource_init(void) gic_clocksource.rating = 200; gic_clocksource.rating += clamp(gic_frequency / 10000000, 0, 99); + if (mips_cps_multicluster_cpus()) { + gic_clocksource.read = &gic_hpt_read_multicluster; + gic_clocksource.vdso_clock_mode = VDSO_CLOCKMODE_NONE; + } + ret = clocksource_register_hz(&gic_clocksource, gic_frequency); if (ret < 0) pr_warn("Unable to register clocksource\n"); @@ -261,7 +297,8 @@ static int __init gic_clocksource_of_init(struct device_node *node) * stable CPU frequency or on the platforms with CM3 and CPU frequency * change performed by the CPC core clocks divider. */ - if (mips_cm_revision() >= CM_REV_CM3 || !IS_ENABLED(CONFIG_CPU_FREQ)) { + if ((mips_cm_revision() >= CM_REV_CM3 || !IS_ENABLED(CONFIG_CPU_FREQ)) && + !mips_cps_multicluster_cpus()) { sched_clock_register(mips_cm_is64 ? gic_read_count_64 : gic_read_count_2x32, gic_count_width, gic_frequency); diff --git a/drivers/clocksource/timer-armada-370-xp.c b/drivers/clocksource/timer-armada-370-xp.c index 6ec565d6939a..54284c1c0651 100644 --- a/drivers/clocksource/timer-armada-370-xp.c +++ b/drivers/clocksource/timer-armada-370-xp.c @@ -201,7 +201,6 @@ static int armada_370_xp_timer_dying_cpu(unsigned int cpu) { struct clock_event_device *evt = per_cpu_ptr(armada_370_xp_evt, cpu); - evt->set_state_shutdown(evt); disable_percpu_irq(evt->irq); return 0; } diff --git a/drivers/clocksource/timer-gxp.c b/drivers/clocksource/timer-gxp.c index 57aa2e2cce53..48a73c101eb8 100644 --- a/drivers/clocksource/timer-gxp.c +++ b/drivers/clocksource/timer-gxp.c @@ -85,7 +85,7 @@ static int __init gxp_timer_init(struct device_node *node) clk = of_clk_get(node, 0); if (IS_ERR(clk)) { - ret = (int)PTR_ERR(clk); + ret = PTR_ERR(clk); pr_err("%pOFn clock not found: %d\n", node, ret); goto err_free; } diff --git a/drivers/clocksource/timer-qcom.c b/drivers/clocksource/timer-qcom.c index eac4c95c6127..ddb1debe6a6b 100644 --- a/drivers/clocksource/timer-qcom.c +++ b/drivers/clocksource/timer-qcom.c @@ -130,7 +130,6 @@ static int msm_local_timer_dying_cpu(unsigned int cpu) { struct clock_event_device *evt = per_cpu_ptr(msm_evt, cpu); - evt->set_state_shutdown(evt); disable_percpu_irq(evt->irq); return 0; } diff --git a/arch/mips/ralink/cevt-rt3352.c b/drivers/clocksource/timer-ralink.c index 269d4877d120..6ecdb4228f76 100644 --- a/arch/mips/ralink/cevt-rt3352.c +++ b/drivers/clocksource/timer-ralink.c @@ -1,7 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. + * Ralink System Tick Counter driver present on RT3352 and MT7620 SoCs. * * Copyright (C) 2013 by John Crispin <john@phrozen.org> */ @@ -16,8 +15,6 @@ #include <linux/of_irq.h> #include <linux/of_address.h> -#include <asm/mach-ralink/ralink_regs.h> - #define SYSTICK_FREQ (50 * 1000) #define SYSTICK_CONFIG 0x00 @@ -40,7 +37,7 @@ static int systick_set_oneshot(struct clock_event_device *evt); static int systick_shutdown(struct clock_event_device *evt); static int systick_next_event(unsigned long delta, - struct clock_event_device *evt) + struct clock_event_device *evt) { struct systick_device *sdev; u32 count; @@ -60,7 +57,7 @@ static void systick_event_handler(struct clock_event_device *dev) static irqreturn_t systick_interrupt(int irq, void *dev_id) { - struct clock_event_device *dev = (struct clock_event_device *) dev_id; + struct clock_event_device *dev = (struct clock_event_device *)dev_id; dev->event_handler(dev); diff --git a/drivers/clocksource/timer-tegra.c b/drivers/clocksource/timer-tegra.c index e9635c25eef4..35b6ce9deffa 100644 --- a/drivers/clocksource/timer-tegra.c +++ b/drivers/clocksource/timer-tegra.c @@ -158,7 +158,6 @@ static int tegra_timer_stop(unsigned int cpu) { struct timer_of *to = per_cpu_ptr(&tegra_to, cpu); - to->clkevt.set_state_shutdown(&to->clkevt); disable_irq_nosync(to->clkevt.irq); return 0; diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index c2dcd8d68e45..985a6d08512b 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -202,10 +202,10 @@ static bool __init dmtimer_is_preferred(struct device_node *np) /* Secure gptimer12 is always clocked with a fixed source */ if (!of_property_read_bool(np, "ti,timer-secure")) { - if (!of_property_read_bool(np, "assigned-clocks")) + if (!of_property_present(np, "assigned-clocks")) return false; - if (!of_property_read_bool(np, "assigned-clock-parents")) + if (!of_property_present(np, "assigned-clock-parents")) return false; } @@ -686,9 +686,9 @@ subsys_initcall(dmtimer_percpu_timer_startup); static int __init dmtimer_percpu_quirk_init(struct device_node *np, u32 pa) { - struct device_node *arm_timer; + struct device_node *arm_timer __free(device_node) = + of_find_compatible_node(NULL, NULL, "arm,armv7-timer"); - arm_timer = of_find_compatible_node(NULL, NULL, "arm,armv7-timer"); if (of_device_is_available(arm_timer)) { pr_warn_once("ARM architected timer wrap issue i940 detected\n"); return 0; diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index b7a34b1a975e..3666d94cc8dd 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -1104,8 +1104,12 @@ static int omap_dm_timer_probe(struct platform_device *pdev) return -ENOMEM; timer->irq = platform_get_irq(pdev, 0); - if (timer->irq < 0) - return timer->irq; + if (timer->irq < 0) { + if (of_property_read_bool(dev->of_node, "ti,timer-pwm")) + dev_info(dev, "Did not find timer interrupt, timer usable in PWM mode only\n"); + else + return timer->irq; + } timer->io_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(timer->io_base)) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 519e096c607c..8f62cfa23fb7 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -273,11 +273,6 @@ i915_request_active_engine(struct i915_request *rq, return ret; } -static void __rq_init_watchdog(struct i915_request *rq) -{ - rq->watchdog.timer.function = NULL; -} - static enum hrtimer_restart __rq_watchdog_expired(struct hrtimer *hrtimer) { struct i915_request *rq = @@ -294,6 +289,14 @@ static enum hrtimer_restart __rq_watchdog_expired(struct hrtimer *hrtimer) return HRTIMER_NORESTART; } +static void __rq_init_watchdog(struct i915_request *rq) +{ + struct i915_request_watchdog *wdg = &rq->watchdog; + + hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + wdg->timer.function = __rq_watchdog_expired; +} + static void __rq_arm_watchdog(struct i915_request *rq) { struct i915_request_watchdog *wdg = &rq->watchdog; @@ -304,8 +307,6 @@ static void __rq_arm_watchdog(struct i915_request *rq) i915_request_get(rq); - hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - wdg->timer.function = __rq_watchdog_expired; hrtimer_start_range_ns(&wdg->timer, ns_to_ktime(ce->watchdog.timeout_us * NSEC_PER_USEC), @@ -317,7 +318,7 @@ static void __rq_cancel_watchdog(struct i915_request *rq) { struct i915_request_watchdog *wdg = &rq->watchdog; - if (wdg->timer.function && hrtimer_try_to_cancel(&wdg->timer) > 0) + if (hrtimer_try_to_cancel(&wdg->timer) > 0) i915_request_put(rq); } diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c index 8699846eb416..bea12cdc85e8 100644 --- a/drivers/media/usb/dvb-usb-v2/anysee.c +++ b/drivers/media/usb/dvb-usb-v2/anysee.c @@ -46,24 +46,15 @@ static int anysee_ctrl_msg(struct dvb_usb_device *d, dev_dbg(&d->udev->dev, "%s: >>> %*ph\n", __func__, slen, state->buf); - /* We need receive one message more after dvb_usb_generic_rw due - to weird transaction flow, which is 1 x send + 2 x receive. */ + /* + * We need receive one message more after dvb_usbv2_generic_rw_locked() + * due to weird transaction flow, which is 1 x send + 2 x receive. + */ ret = dvb_usbv2_generic_rw_locked(d, state->buf, sizeof(state->buf), state->buf, sizeof(state->buf)); if (ret) goto error_unlock; - /* TODO FIXME: dvb_usb_generic_rw() fails rarely with error code -32 - * (EPIPE, Broken pipe). Function supports currently msleep() as a - * parameter but I would not like to use it, since according to - * Documentation/timers/timers-howto.rst it should not be used such - * short, under < 20ms, sleeps. Repeating failed message would be - * better choice as not to add unwanted delays... - * Fixing that correctly is one of those or both; - * 1) use repeat if possible - * 2) add suitable delay - */ - /* get answer, retry few times if error returned */ for (i = 0; i < 3; i++) { /* receive 2nd answer */ diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c index 8fd22c69855f..a6d50149e0c3 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c @@ -823,8 +823,6 @@ int rt2x00usb_probe(struct usb_interface *usb_intf, INIT_WORK(&rt2x00dev->rxdone_work, rt2x00usb_work_rxdone); INIT_WORK(&rt2x00dev->txdone_work, rt2x00usb_work_txdone); - hrtimer_init(&rt2x00dev->txstatus_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL); retval = rt2x00usb_alloc_reg(rt2x00dev); if (retval) diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c index 96f0a7fbf105..09ec0ecf1486 100644 --- a/drivers/power/supply/charger-manager.c +++ b/drivers/power/supply/charger-manager.c @@ -1412,10 +1412,9 @@ static inline struct charger_desc *cm_get_drv_data(struct platform_device *pdev) return dev_get_platdata(&pdev->dev); } -static enum alarmtimer_restart cm_timer_func(struct alarm *alarm, ktime_t now) +static void cm_timer_func(struct alarm *alarm, ktime_t now) { cm_timer_set = false; - return ALARMTIMER_NORESTART; } static int charger_manager_probe(struct platform_device *pdev) @@ -1335,7 +1335,7 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr, if (until == 0 || ret < 0 || ret >= min_nr) return ret; - hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_setup_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); if (until != KTIME_MAX) { hrtimer_set_expires_range_ns(&t.timer, until, current->timer_slack_ns); hrtimer_sleeper_start_expires(&t, HRTIMER_MODE_REL); diff --git a/fs/proc/base.c b/fs/proc/base.c index e9d7ddc52f69..3e31a4805427 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2552,8 +2552,8 @@ static int show_timer(struct seq_file *m, void *v) seq_printf(m, "ID: %d\n", timer->it_id); seq_printf(m, "signal: %d/%px\n", - timer->sigq->info.si_signo, - timer->sigq->info.si_value.sival_ptr); + timer->sigq.info.si_signo, + timer->sigq.info.si_value.sival_ptr); seq_printf(m, "notify: %s/%s.%d\n", nstr[notify & ~SIGEV_THREAD_ID], (notify & SIGEV_THREAD_ID) ? "tid" : "pid", diff --git a/fs/timerfd.c b/fs/timerfd.c index 4c32244b0508..9f7eb451a60f 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -79,13 +79,11 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) return HRTIMER_NORESTART; } -static enum alarmtimer_restart timerfd_alarmproc(struct alarm *alarm, - ktime_t now) +static void timerfd_alarmproc(struct alarm *alarm, ktime_t now) { struct timerfd_ctx *ctx = container_of(alarm, struct timerfd_ctx, t.alarm); timerfd_triggered(ctx); - return ALARMTIMER_NORESTART; } /* diff --git a/include/asm-generic/delay.h b/include/asm-generic/delay.h index e448ac61430c..76cf237b6e4c 100644 --- a/include/asm-generic/delay.h +++ b/include/asm-generic/delay.h @@ -2,6 +2,9 @@ #ifndef __ASM_GENERIC_DELAY_H #define __ASM_GENERIC_DELAY_H +#include <linux/math.h> +#include <vdso/time64.h> + /* Undefined functions to get compile-time errors */ extern void __bad_udelay(void); extern void __bad_ndelay(void); @@ -12,34 +15,73 @@ extern void __const_udelay(unsigned long xloops); extern void __delay(unsigned long loops); /* - * The weird n/20000 thing suppresses a "comparison is always false due to - * limited range of data type" warning with non-const 8-bit arguments. + * The microseconds/nanosecond delay multiplicators are used to convert a + * constant microseconds/nanoseconds value to a value which can be used by the + * architectures specific implementation to transform it into loops. + */ +#define UDELAY_CONST_MULT ((unsigned long)DIV_ROUND_UP(1ULL << 32, USEC_PER_SEC)) +#define NDELAY_CONST_MULT ((unsigned long)DIV_ROUND_UP(1ULL << 32, NSEC_PER_SEC)) + +/* + * The maximum constant udelay/ndelay value picked out of thin air to prevent + * too long constant udelays/ndelays. */ +#define DELAY_CONST_MAX 20000 -/* 0x10c7 is 2**32 / 1000000 (rounded up) */ -#define udelay(n) \ - ({ \ - if (__builtin_constant_p(n)) { \ - if ((n) / 20000 >= 1) \ - __bad_udelay(); \ - else \ - __const_udelay((n) * 0x10c7ul); \ - } else { \ - __udelay(n); \ - } \ - }) - -/* 0x5 is 2**32 / 1000000000 (rounded up) */ -#define ndelay(n) \ - ({ \ - if (__builtin_constant_p(n)) { \ - if ((n) / 20000 >= 1) \ - __bad_ndelay(); \ - else \ - __const_udelay((n) * 5ul); \ - } else { \ - __ndelay(n); \ - } \ - }) +/** + * udelay - Inserting a delay based on microseconds with busy waiting + * @usec: requested delay in microseconds + * + * When delaying in an atomic context ndelay(), udelay() and mdelay() are the + * only valid variants of delaying/sleeping to go with. + * + * When inserting delays in non atomic context which are shorter than the time + * which is required to queue e.g. an hrtimer and to enter then the scheduler, + * it is also valuable to use udelay(). But it is not simple to specify a + * generic threshold for this which will fit for all systems. An approximation + * is a threshold for all delays up to 10 microseconds. + * + * When having a delay which is larger than the architecture specific + * %MAX_UDELAY_MS value, please make sure mdelay() is used. Otherwise a overflow + * risk is given. + * + * Please note that ndelay(), udelay() and mdelay() may return early for several + * reasons (https://lists.openwall.net/linux-kernel/2011/01/09/56): + * + * #. computed loops_per_jiffy too low (due to the time taken to execute the + * timer interrupt.) + * #. cache behaviour affecting the time it takes to execute the loop function. + * #. CPU clock rate changes. + */ +static __always_inline void udelay(unsigned long usec) +{ + if (__builtin_constant_p(usec)) { + if (usec >= DELAY_CONST_MAX) + __bad_udelay(); + else + __const_udelay(usec * UDELAY_CONST_MULT); + } else { + __udelay(usec); + } +} + +/** + * ndelay - Inserting a delay based on nanoseconds with busy waiting + * @nsec: requested delay in nanoseconds + * + * See udelay() for basic information about ndelay() and it's variants. + */ +static __always_inline void ndelay(unsigned long nsec) +{ + if (__builtin_constant_p(nsec)) { + if (nsec >= DELAY_CONST_MAX) + __bad_udelay(); + else + __const_udelay(nsec * NDELAY_CONST_MULT); + } else { + __udelay(nsec); + } +} +#define ndelay(x) ndelay(x) #endif /* __ASM_GENERIC_DELAY_H */ diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 05e758b8b894..3ffa5341dce2 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -20,12 +20,6 @@ enum alarmtimer_type { ALARM_BOOTTIME_FREEZER, }; -enum alarmtimer_restart { - ALARMTIMER_NORESTART, - ALARMTIMER_RESTART, -}; - - #define ALARMTIMER_STATE_INACTIVE 0x00 #define ALARMTIMER_STATE_ENQUEUED 0x01 @@ -42,14 +36,14 @@ enum alarmtimer_restart { struct alarm { struct timerqueue_node node; struct hrtimer timer; - enum alarmtimer_restart (*function)(struct alarm *, ktime_t now); + void (*function)(struct alarm *, ktime_t now); enum alarmtimer_type type; int state; void *data; }; void alarm_init(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); + void (*function)(struct alarm *, ktime_t)); void alarm_start(struct alarm *alarm, ktime_t start); void alarm_start_relative(struct alarm *alarm, ktime_t start); void alarm_restart(struct alarm *alarm); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d35b677b08fe..ef1b16da6ad5 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -215,7 +215,6 @@ static inline s64 clocksource_cyc2ns(u64 cycles, u32 mult, u32 shift) extern int clocksource_unregister(struct clocksource*); extern void clocksource_touch_watchdog(void); -extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); extern struct clocksource * __init clocksource_default_clock(void); diff --git a/include/linux/delay.h b/include/linux/delay.h index ff9cda975e30..89866bab100d 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -6,21 +6,12 @@ * Copyright (C) 1993 Linus Torvalds * * Delay routines, using a pre-computed "loops_per_jiffy" value. - * - * Please note that ndelay(), udelay() and mdelay() may return early for - * several reasons: - * 1. computed loops_per_jiffy too low (due to the time taken to - * execute the timer interrupt.) - * 2. cache behaviour affecting the time it takes to execute the - * loop function. - * 3. CPU clock rate changes. - * - * Please see this thread: - * https://lists.openwall.net/linux-kernel/2011/01/09/56 + * Sleep routines using timer list timers or hrtimers. */ #include <linux/math.h> #include <linux/sched.h> +#include <linux/jiffies.h> extern unsigned long loops_per_jiffy; @@ -35,12 +26,21 @@ extern unsigned long loops_per_jiffy; * The 2nd mdelay() definition ensures GCC will optimize away the * while loop for the common cases where n <= MAX_UDELAY_MS -- Paul G. */ - #ifndef MAX_UDELAY_MS #define MAX_UDELAY_MS 5 #endif #ifndef mdelay +/** + * mdelay - Inserting a delay based on milliseconds with busy waiting + * @n: requested delay in milliseconds + * + * See udelay() for basic information about mdelay() and it's variants. + * + * Please double check, whether mdelay() is the right way to go or whether a + * refactoring of the code is the better variant to be able to use msleep() + * instead. + */ #define mdelay(n) (\ (__builtin_constant_p(n) && (n)<=MAX_UDELAY_MS) ? udelay((n)*1000) : \ ({unsigned long __ms=(n); while (__ms--) udelay(1000);})) @@ -63,30 +63,75 @@ unsigned long msleep_interruptible(unsigned int msecs); void usleep_range_state(unsigned long min, unsigned long max, unsigned int state); +/** + * usleep_range - Sleep for an approximate time + * @min: Minimum time in microseconds to sleep + * @max: Maximum time in microseconds to sleep + * + * For basic information please refere to usleep_range_state(). + * + * The task will be in the state TASK_UNINTERRUPTIBLE during the sleep. + */ static inline void usleep_range(unsigned long min, unsigned long max) { usleep_range_state(min, max, TASK_UNINTERRUPTIBLE); } -static inline void usleep_idle_range(unsigned long min, unsigned long max) +/** + * usleep_range_idle - Sleep for an approximate time with idle time accounting + * @min: Minimum time in microseconds to sleep + * @max: Maximum time in microseconds to sleep + * + * For basic information please refere to usleep_range_state(). + * + * The sleeping task has the state TASK_IDLE during the sleep to prevent + * contribution to the load avarage. + */ +static inline void usleep_range_idle(unsigned long min, unsigned long max) { usleep_range_state(min, max, TASK_IDLE); } +/** + * ssleep - wrapper for seconds around msleep + * @seconds: Requested sleep duration in seconds + * + * Please refere to msleep() for detailed information. + */ static inline void ssleep(unsigned int seconds) { msleep(seconds * 1000); } -/* see Documentation/timers/timers-howto.rst for the thresholds */ +static const unsigned int max_slack_shift = 2; +#define USLEEP_RANGE_UPPER_BOUND ((TICK_NSEC << max_slack_shift) / NSEC_PER_USEC) + +/** + * fsleep - flexible sleep which autoselects the best mechanism + * @usecs: requested sleep duration in microseconds + * + * flseep() selects the best mechanism that will provide maximum 25% slack + * to the requested sleep duration. Therefore it uses: + * + * * udelay() loop for sleep durations <= 10 microseconds to avoid hrtimer + * overhead for really short sleep durations. + * * usleep_range() for sleep durations which would lead with the usage of + * msleep() to a slack larger than 25%. This depends on the granularity of + * jiffies. + * * msleep() for all other sleep durations. + * + * Note: When %CONFIG_HIGH_RES_TIMERS is not set, all sleeps are processed with + * the granularity of jiffies and the slack might exceed 25% especially for + * short sleep durations. + */ static inline void fsleep(unsigned long usecs) { if (usecs <= 10) udelay(usecs); - else if (usecs <= 20000) - usleep_range(usecs, 2 * usecs); + else if (usecs < USLEEP_RANGE_UPPER_BOUND) + usleep_range(usecs, usecs + (usecs >> max_slack_shift)); else - msleep(DIV_ROUND_UP(usecs, 1000)); + msleep(DIV_ROUND_UP(usecs, USEC_PER_MSEC)); } #endif /* defined(_LINUX_DELAY_H) */ diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h index 82ebf9223948..f8811c46b89e 100644 --- a/include/linux/dw_apb_timer.h +++ b/include/linux/dw_apb_timer.h @@ -34,9 +34,6 @@ struct dw_apb_clocksource { }; void dw_apb_clockevent_register(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_pause(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_resume(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_stop(struct dw_apb_clock_event_device *dw_ced); struct dw_apb_clock_event_device * dw_apb_clockevent_init(int cpu, const char *name, unsigned rating, diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index aa1e65ccb615..7ef5f7ef31a9 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -228,32 +228,17 @@ static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) /* Initialize timers: */ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); -extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, - enum hrtimer_mode mode); +extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode); +extern void hrtimer_setup_on_stack(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode); +extern void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, + enum hrtimer_mode mode); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS -extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, - enum hrtimer_mode mode); -extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, - enum hrtimer_mode mode); - extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else -static inline void hrtimer_init_on_stack(struct hrtimer *timer, - clockid_t which_clock, - enum hrtimer_mode mode) -{ - hrtimer_init(timer, which_clock, mode); -} - -static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, - enum hrtimer_mode mode) -{ - hrtimer_init_sleeper(sl, clock_id, mode); -} - static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif @@ -337,6 +322,28 @@ static inline int hrtimer_callback_running(struct hrtimer *timer) return timer->base->running == timer; } +/** + * hrtimer_update_function - Update the timer's callback function + * @timer: Timer to update + * @function: New callback function + * + * Only safe to call if the timer is not enqueued. Can be called in the callback function if the + * timer is not enqueued at the same time (see the comments above HRTIMER_STATE_ENQUEUED). + */ +static inline void hrtimer_update_function(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *)) +{ + guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock); + + if (WARN_ON_ONCE(hrtimer_is_queued(timer))) + return; + + if (WARN_ON_ONCE(!function)) + return; + + timer->function = function; +} + /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index 19a7b00baff4..91324c331a4b 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -19,19 +19,19 @@ * @op: accessor function (takes @args as its arguments) * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. * @args: arguments for @op poll * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @args is stored in @val. Must not - * be called from atomic context if sleep_us or timeout_us are used. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. */ #define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \ sleep_before_read, args...) \ @@ -64,22 +64,22 @@ * @op: accessor function (takes @args as its arguments) * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). Should - * be less than ~10us since udelay is used (see - * Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @delay_before_read: if it is true, delay @delay_us before read. * @args: arguments for @op poll * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @args is stored in @val. - * * This macro does not rely on timekeeping. Hence it is safe to call even when * timekeeping is suspended, at the expense of an underestimation of wall clock * time, which is rather minimal with a non-zero delay_us. * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. */ #define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \ delay_before_read, args...) \ @@ -119,17 +119,17 @@ * @addr: Address to poll * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @addr is stored in @val. Must not - * be called from atomic context if sleep_us or timeout_us are used. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. */ #define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us) \ read_poll_timeout(op, val, cond, sleep_us, timeout_us, false, addr) @@ -140,16 +140,16 @@ * @addr: Address to poll * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). Should - * be less than ~10us since udelay is used (see - * Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @addr is stored in @val. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. */ #define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \ read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, false, addr) diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1220f0fbe5bf..ed945f42e064 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -502,7 +502,7 @@ static inline unsigned long _msecs_to_jiffies(const unsigned int m) * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. - * for the details see __msecs_to_jiffies() + * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the @@ -526,6 +526,19 @@ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m) } } +/** + * secs_to_jiffies: - convert seconds to jiffies + * @_secs: time in seconds + * + * Conversion is done by simple multiplication with HZ + * + * secs_to_jiffies() is defined as a macro rather than a static inline + * function so it can be used in static initializers. + * + * Return: jiffies value + */ +#define secs_to_jiffies(_secs) ((_secs) * HZ) + extern unsigned long __usecs_to_jiffies(const unsigned int u); #if !(USEC_PER_SEC % HZ) static inline unsigned long _usecs_to_jiffies(const unsigned int u) diff --git a/include/linux/phy.h b/include/linux/phy.h index a98bc91a0cde..504766d4b2d5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1378,12 +1378,13 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); * @regnum: The register on the MMD to read * @val: Variable to read the register into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. */ diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 453691710839..f11f10c97bd9 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -5,12 +5,16 @@ #include <linux/alarmtimer.h> #include <linux/list.h> #include <linux/mutex.h> +#include <linux/pid.h> #include <linux/posix-timers_types.h> +#include <linux/rcuref.h> #include <linux/spinlock.h> #include <linux/timerqueue.h> struct kernel_siginfo; struct task_struct; +struct sigqueue; +struct k_itimer; static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) @@ -35,6 +39,8 @@ static inline int clockid_to_fd(const clockid_t clk) #ifdef CONFIG_POSIX_TIMERS +#include <linux/signal_types.h> + /** * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig @@ -42,6 +48,7 @@ static inline int clockid_to_fd(const clockid_t clk) * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing + * @nanosleep: Timer is used for nanosleep and is not a regular posix-timer * @handling: Pointer to the task which handles expiry */ struct cpu_timer { @@ -49,7 +56,8 @@ struct cpu_timer { struct timerqueue_head *head; struct pid *pid; struct list_head elist; - int firing; + bool firing; + bool nanosleep; struct task_struct __rcu *handling; }; @@ -101,6 +109,12 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } +void posixtimer_rearm_itimer(struct task_struct *p); +bool posixtimer_init_sigqueue(struct sigqueue *q); +void posixtimer_send_sigqueue(struct k_itimer *tmr); +bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); +void posixtimer_free_timer(struct k_itimer *timer); + /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ .nextevt = U64_MAX, \ @@ -122,6 +136,10 @@ struct cpu_timer { }; static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } +static inline void posixtimer_rearm_itimer(struct task_struct *p) { } +static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info, + struct sigqueue *timer_sigq) { return false; } +static inline void posixtimer_free_timer(struct k_itimer *timer) { } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK @@ -132,50 +150,56 @@ static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif -#define REQUEUE_PENDING 1 - /** * struct k_itimer - POSIX.1b interval timer structure. - * @list: List head for binding the timer to signals->posix_timers + * @list: List node for binding the timer to tsk::signal::posix_timers + * @ignored_list: List node for tracking ignored timers in tsk::signal::ignored_posix_timers * @t_hash: Entry in the posix timer hash table * @it_lock: Lock protecting the timer * @kclock: Pointer to the k_clock struct handling this timer * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer - * @it_active: Marker that timer is active + * @it_status: The status of the timer + * @it_sig_periodic: The periodic status at signal delivery * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal - * @it_requeue_pending: Indicator that timer waits for being requeued on - * signal delivery + * @it_signal_seq: Sequence count to control signal delivery + * @it_sigqueue_seq: The sequence count at the point where the signal was queued * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) - * @sigq: Pointer to preallocated sigqueue + * @rcuref: Reference count for life time management + * @sigq: Embedded sigqueue * @it: Union representing the various posix timer type * internals. * @rcu: RCU head for freeing the timer. */ struct k_itimer { struct hlist_node list; + struct hlist_node ignored_list; struct hlist_node t_hash; spinlock_t it_lock; const struct k_clock *kclock; clockid_t it_clock; timer_t it_id; - int it_active; + int it_status; + bool it_sig_periodic; s64 it_overrun; s64 it_overrun_last; - int it_requeue_pending; + unsigned int it_signal_seq; + unsigned int it_sigqueue_seq; int it_sigev_notify; + enum pid_type it_pid_type; ktime_t it_interval; struct signal_struct *it_signal; union { struct pid *it_pid; struct task_struct *it_process; }; - struct sigqueue *sigq; + struct sigqueue sigq; + rcuref_t rcuref; union { struct { struct hrtimer timer; @@ -196,5 +220,29 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); -void posixtimer_rearm(struct kernel_siginfo *info); +#ifdef CONFIG_POSIX_TIMERS +static inline void posixtimer_putref(struct k_itimer *tmr) +{ + if (rcuref_put(&tmr->rcuref)) + posixtimer_free_timer(tmr); +} + +static inline void posixtimer_sigqueue_getref(struct sigqueue *q) +{ + struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); + + WARN_ON_ONCE(!rcuref_get(&tmr->rcuref)); +} + +static inline void posixtimer_sigqueue_putref(struct sigqueue *q) +{ + struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); + + posixtimer_putref(tmr); +} +#else /* CONFIG_POSIX_TIMERS */ +static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { } +static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { } +#endif /* !CONFIG_POSIX_TIMERS */ + #endif diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f9ccad32fc5c..75f162b60ba1 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -106,17 +106,17 @@ struct reg_sequence { * @addr: Address to poll * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read + * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_read * error return value in case of a error read. In the two former cases, * the last read value at @addr is stored in @val. Must not be called * from atomic context if sleep_us or timeout_us are used. - * - * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. */ #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \ ({ \ @@ -133,20 +133,20 @@ struct reg_sequence { * @addr: Address to poll * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). - * Should be less than ~10us since udelay is used - * (see Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read - * error return value in case of a error read. In the two former cases, - * the last read value at @addr is stored in @val. - * * This is modelled after the readx_poll_timeout_atomic macros in linux/iopoll.h. * * Note: In general regmap cannot be used in atomic context. If you want to use * this macro then first setup your regmap for atomic use (flat or no cache * and MMIO regmap). + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_read + * error return value in case of a error read. In the two former cases, + * the last read value at @addr is stored in @val. */ #define regmap_read_poll_timeout_atomic(map, addr, val, cond, delay_us, timeout_us) \ ({ \ @@ -177,17 +177,17 @@ struct reg_sequence { * @field: Regmap field to read from * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_field_read + * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_field_read * error return value in case of a error read. In the two former cases, * the last read value at @addr is stored in @val. Must not be called * from atomic context if sleep_us or timeout_us are used. - * - * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. */ #define regmap_field_read_poll_timeout(field, val, cond, sleep_us, timeout_us) \ ({ \ diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index c8ed09ac29ac..d5d03d919df8 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -138,6 +138,7 @@ struct signal_struct { /* POSIX.1b Interval Timers */ unsigned int next_posix_timer_id; struct hlist_head posix_timers; + struct hlist_head ignored_posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; @@ -338,9 +339,6 @@ extern void force_fatal_sig(int); extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); -extern struct sigqueue *sigqueue_alloc(void); -extern void sigqueue_free(struct sigqueue *); -extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) diff --git a/include/linux/tick.h b/include/linux/tick.h index 99c9c5a7252a..b8ddc8e631a3 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -20,12 +20,10 @@ extern void __init tick_init(void); extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ extern void tick_resume_local(void); -extern void tick_cleanup_dead_cpu(int cpu); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } -static inline void tick_cleanup_dead_cpu(int cpu) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ #if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_HOTPLUG_CPU) diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 902c20ef495a..e39d4d563b19 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -26,7 +26,7 @@ * occupies a single 64byte cache line. * * The struct is separate from struct timekeeper as it is also used - * for a fast NMI safe accessors. + * for the fast NMI safe accessors. * * @base_real is for the fast NMI safe accessor to allow reading clock * realtime from any context. @@ -44,33 +44,38 @@ struct tk_read_base { /** * struct timekeeper - Structure holding internal timekeeping values. - * @tkr_mono: The readout base structure for CLOCK_MONOTONIC - * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW - * @xtime_sec: Current CLOCK_REALTIME time in seconds - * @ktime_sec: Current CLOCK_MONOTONIC 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 - * @clock_was_set_seq: The sequence number of clock was set events - * @cs_was_changed_seq: The sequence number of clocksource change events - * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second - * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds - * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset - * @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: Shifted 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. - * @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING) - * @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING) - * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) + * @tkr_mono: The readout base structure for CLOCK_MONOTONIC + * @xtime_sec: Current CLOCK_REALTIME time in seconds + * @ktime_sec: Current CLOCK_MONOTONIC 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 + * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW + * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds + * @clock_was_set_seq: The sequence number of clock was set events + * @cs_was_changed_seq: The sequence number of clocksource change events + * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset + * @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: Shifted raw nano seconds accumulated per NTP interval. + * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second + * @ntp_tick: 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. + * @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. + * @ntp_err_mult: Multiplication factor for scaled math conversion + * @skip_second_overflow: Flag used to avoid updating NTP twice with same second * * Note: For timespec(64) based interfaces wall_to_monotonic is what * we need to add to xtime (or xtime corrected for sub jiffy times) @@ -88,10 +93,28 @@ struct tk_read_base { * * @monotonic_to_boottime is a timespec64 representation of @offs_boot to * accelerate the VDSO update for CLOCK_BOOTTIME. + * + * The cacheline ordering of the structure is optimized for in kernel usage of + * the ktime_get() and ktime_get_ts64() family of time accessors. Struct + * timekeeper is prepended in the core timekeeping code with a sequence count, + * which results in the following cacheline layout: + * + * 0: seqcount, tkr_mono + * 1: xtime_sec ... tai_offset + * 2: tkr_raw, raw_sec + * 3,4: Internal variables + * + * Cacheline 0,1 contain the data which is used for accessing + * CLOCK_MONOTONIC/REALTIME/BOOTTIME/TAI, while cacheline 2 contains the + * data for accessing CLOCK_MONOTONIC_RAW. Cacheline 3,4 are internal + * variables which are only accessed during timekeeper updates once per + * tick. */ struct timekeeper { + /* Cacheline 0 (together with prepended seqcount of timekeeper core): */ struct tk_read_base tkr_mono; - struct tk_read_base tkr_raw; + + /* Cacheline 1: */ u64 xtime_sec; unsigned long ktime_sec; struct timespec64 wall_to_monotonic; @@ -99,43 +122,28 @@ struct timekeeper { ktime_t offs_boot; ktime_t offs_tai; s32 tai_offset; + + /* Cacheline 2: */ + struct tk_read_base tkr_raw; + u64 raw_sec; + + /* Cachline 3 and 4 (timekeeping internal variables): */ unsigned int clock_was_set_seq; u8 cs_was_changed_seq; - ktime_t next_leap_ktime; - u64 raw_sec; + struct timespec64 monotonic_to_boot; - /* The following members are for timekeeping internal use */ u64 cycle_interval; u64 xtime_interval; s64 xtime_remainder; u64 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. - */ + + ktime_t next_leap_ktime; 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; - /* Flag used to avoid updating NTP twice with same second */ u32 skip_second_overflow; -#ifdef CONFIG_DEBUG_TIMEKEEPING - long last_warning; - /* - * These simple flag variables are managed - * without locks, which is racy, but they are - * ok since we don't really care about being - * super precise about how many events were - * seen, just that a problem was observed. - */ - int underflow_seen; - int overflow_seen; -#endif }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 84a035e86ac8..0e035f675efe 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -280,6 +280,7 @@ struct ktime_timestamps { * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time + * @boot: Boot time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events @@ -288,6 +289,7 @@ struct ktime_timestamps { struct system_time_snapshot { u64 cycles; ktime_t real; + ktime_t boot; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; diff --git a/include/linux/timex.h b/include/linux/timex.h index 3871b06bd302..4ee32eff3f22 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -139,14 +139,6 @@ unsigned long random_get_entropy_fallback(void); #define MAXSEC 2048 /* max interval between updates (s) */ #define NTP_PHASE_LIMIT ((MAXPHASE / NSEC_PER_USEC) << 5) /* beyond max. dispersion */ -/* - * kernel variables - * Note: maximum error = NTP sync distance = dispersion + delay / 2; - * estimated error = NTP dispersion. - */ -extern unsigned long tick_usec; /* USER_HZ period (usec) */ -extern unsigned long tick_nsec; /* SHIFTED_HZ period (nsec) */ - /* Required to safely shift negative values */ #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ diff --git a/include/linux/wait.h b/include/linux/wait.h index 2b322a9b88a2..6d90ad974408 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -542,8 +542,8 @@ do { \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ - hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ - HRTIMER_MODE_REL); \ + hrtimer_setup_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ + HRTIMER_MODE_REL); \ if ((timeout) != KTIME_MAX) { \ hrtimer_set_expires_range_ns(&__t.timer, timeout, \ current->timer_slack_ns); \ diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index b7bc545ec3b2..5a1ca43b5fc6 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -46,7 +46,7 @@ union __sifields { __kernel_timer_t _tid; /* timer id */ int _overrun; /* overrun count */ sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ + int _sys_private; /* Not used by the kernel. Historic leftover. Always 0. */ } _timer; /* POSIX.1b signals */ diff --git a/init/init_task.c b/init/init_task.c index 136a8231355a..e557f622bd90 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -30,8 +30,9 @@ static struct signal_struct init_signals = { .cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex), .exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock), #ifdef CONFIG_POSIX_TIMERS - .posix_timers = HLIST_HEAD_INIT, - .cputimer = { + .posix_timers = HLIST_HEAD_INIT, + .ignored_posix_timers = HLIST_HEAD_INIT, + .cputimer = { .cputime_atomic = INIT_CPUTIME_ATOMIC, }, #endif diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 73af59863300..801293399883 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2408,13 +2408,14 @@ static int io_cqring_schedule_timeout(struct io_wait_queue *iowq, { ktime_t timeout; - hrtimer_init_on_stack(&iowq->t, clock_id, HRTIMER_MODE_ABS); if (iowq->min_timeout) { timeout = ktime_add_ns(iowq->min_timeout, start_time); - iowq->t.function = io_cqring_min_timer_wakeup; + hrtimer_setup_on_stack(&iowq->t, io_cqring_min_timer_wakeup, clock_id, + HRTIMER_MODE_ABS); } else { timeout = iowq->timeout; - iowq->t.function = io_cqring_timer_wakeup; + hrtimer_setup_on_stack(&iowq->t, io_cqring_timer_wakeup, clock_id, + HRTIMER_MODE_ABS); } hrtimer_set_expires_range_ns(&iowq->t, timeout, 0); diff --git a/io_uring/rw.c b/io_uring/rw.c index cce8bc2ecd3f..0bcb83e4ce3c 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -1176,7 +1176,7 @@ static u64 io_hybrid_iopoll_delay(struct io_ring_ctx *ctx, struct io_kiocb *req) req->flags |= REQ_F_IOPOLL_STATE; mode = HRTIMER_MODE_REL; - hrtimer_init_sleeper_on_stack(&timer, CLOCK_MONOTONIC, mode); + hrtimer_setup_sleeper_on_stack(&timer, CLOCK_MONOTONIC, mode); hrtimer_set_expires(&timer.timer, kt); set_current_state(TASK_INTERRUPTIBLE); hrtimer_sleeper_start_expires(&timer, mode); diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 5b12bd6a804c..f3d502717aeb 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -76,7 +76,6 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts) /* re-arm timer */ spin_lock_irq(&ctx->timeout_lock); list_add(&timeout->list, ctx->timeout_list.prev); - data->timer.function = io_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); spin_unlock_irq(&ctx->timeout_lock); return; diff --git a/kernel/cpu.c b/kernel/cpu.c index c4aaf73dec9e..6e34b52cb5ce 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1339,7 +1339,6 @@ static int takedown_cpu(unsigned int cpu) cpuhp_bp_sync_dead(cpu); lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu)); - tick_cleanup_dead_cpu(cpu); /* * Callbacks must be re-integrated right away to the RCU state machine. diff --git a/kernel/fork.c b/kernel/fork.c index f6752b0dca97..e58d27c05788 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1862,6 +1862,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) #ifdef CONFIG_POSIX_TIMERS INIT_HLIST_HEAD(&sig->posix_timers); + INIT_HLIST_HEAD(&sig->ignored_posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 692912bf1252..326bfe6549d7 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -140,9 +140,9 @@ futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, if (!time) return NULL; - hrtimer_init_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? - CLOCK_REALTIME : CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); + hrtimer_setup_sleeper_on_stack(timeout, + (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index ab911d1335ba..621696269584 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -398,8 +398,8 @@ void play_idle_precise(u64 duration_ns, u64 latency_ns) cpuidle_use_deepest_state(latency_ns); it.done = 0; - hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); - it.timer.function = idle_inject_timer_fn; + hrtimer_setup_on_stack(&it.timer, idle_inject_timer_fn, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_HARD); hrtimer_start(&it.timer, ns_to_ktime(duration_ns), HRTIMER_MODE_REL_PINNED_HARD); diff --git a/kernel/signal.c b/kernel/signal.c index 65fd233f6f23..98b65cb35830 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -59,6 +59,8 @@ #include <asm/cacheflush.h> #include <asm/syscall.h> /* for syscall_get_* */ +#include "time/posix-timers.h" + /* * SLAB caches for signal bits. */ @@ -396,16 +398,9 @@ void task_join_group_stop(struct task_struct *task) task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING); } -/* - * allocate a new signal queue record - * - this may be called without locks if and only if t == current, otherwise an - * appropriate lock must be held to stop the target task from exiting - */ -static struct sigqueue * -__sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, - int override_rlimit, const unsigned int sigqueue_flags) +static struct ucounts *sig_get_ucounts(struct task_struct *t, int sig, + int override_rlimit) { - struct sigqueue *q = NULL; struct ucounts *ucounts; long sigpending; @@ -425,26 +420,53 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, if (!sigpending) return NULL; - if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { - q = kmem_cache_alloc(sigqueue_cachep, gfp_flags); - } else { + if (unlikely(!override_rlimit && sigpending > task_rlimit(t, RLIMIT_SIGPENDING))) { + dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); print_dropped_signal(sig); + return NULL; } - if (unlikely(q == NULL)) { + return ucounts; +} + +static void __sigqueue_init(struct sigqueue *q, struct ucounts *ucounts, + const unsigned int sigqueue_flags) +{ + INIT_LIST_HEAD(&q->list); + q->flags = sigqueue_flags; + q->ucounts = ucounts; +} + +/* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appropriate lock must be held to stop the target task from exiting + */ +static struct sigqueue *sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, + int override_rlimit) +{ + struct ucounts *ucounts = sig_get_ucounts(t, sig, override_rlimit); + struct sigqueue *q; + + if (!ucounts) + return NULL; + + q = kmem_cache_alloc(sigqueue_cachep, gfp_flags); + if (!q) { dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); - } else { - INIT_LIST_HEAD(&q->list); - q->flags = sigqueue_flags; - q->ucounts = ucounts; + return NULL; } + + __sigqueue_init(q, ucounts, 0); return q; } static void __sigqueue_free(struct sigqueue *q) { - if (q->flags & SIGQUEUE_PREALLOC) + if (q->flags & SIGQUEUE_PREALLOC) { + posixtimer_sigqueue_putref(q); return; + } if (q->ucounts) { dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING); q->ucounts = NULL; @@ -479,42 +501,6 @@ void flush_signals(struct task_struct *t) } EXPORT_SYMBOL(flush_signals); -#ifdef CONFIG_POSIX_TIMERS -static void __flush_itimer_signals(struct sigpending *pending) -{ - sigset_t signal, retain; - struct sigqueue *q, *n; - - signal = pending->signal; - sigemptyset(&retain); - - list_for_each_entry_safe(q, n, &pending->list, list) { - int sig = q->info.si_signo; - - if (likely(q->info.si_code != SI_TIMER)) { - sigaddset(&retain, sig); - } else { - sigdelset(&signal, sig); - list_del_init(&q->list); - __sigqueue_free(q); - } - } - - sigorsets(&pending->signal, &signal, &retain); -} - -void flush_itimer_signals(void) -{ - struct task_struct *tsk = current; - unsigned long flags; - - spin_lock_irqsave(&tsk->sighand->siglock, flags); - __flush_itimer_signals(&tsk->pending); - __flush_itimer_signals(&tsk->signal->shared_pending); - spin_unlock_irqrestore(&tsk->sighand->siglock, flags); -} -#endif - void ignore_signals(struct task_struct *t) { int i; @@ -564,7 +550,7 @@ bool unhandled_signal(struct task_struct *tsk, int sig) } static void collect_signal(int sig, struct sigpending *list, kernel_siginfo_t *info, - bool *resched_timer) + struct sigqueue **timer_sigq) { struct sigqueue *q, *first = NULL; @@ -587,12 +573,17 @@ still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); - *resched_timer = - (first->flags & SIGQUEUE_PREALLOC) && - (info->si_code == SI_TIMER) && - (info->si_sys_private); - - __sigqueue_free(first); + /* + * posix-timer signals are preallocated and freed when the last + * reference count is dropped in posixtimer_deliver_signal() or + * immediately on timer deletion when the signal is not pending. + * Spare the extra round through __sigqueue_free() which is + * ignoring preallocated signals. + */ + if (unlikely((first->flags & SIGQUEUE_PREALLOC) && (info->si_code == SI_TIMER))) + *timer_sigq = first; + else + __sigqueue_free(first); } else { /* * Ok, it wasn't in the queue. This must be @@ -609,12 +600,12 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - kernel_siginfo_t *info, bool *resched_timer) + kernel_siginfo_t *info, struct sigqueue **timer_sigq) { int sig = next_signal(pending, mask); if (sig) - collect_signal(sig, pending, info, resched_timer); + collect_signal(sig, pending, info, timer_sigq); return sig; } @@ -626,42 +617,22 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) { struct task_struct *tsk = current; - bool resched_timer = false; + struct sigqueue *timer_sigq; int signr; lockdep_assert_held(&tsk->sighand->siglock); +again: *type = PIDTYPE_PID; - signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); + timer_sigq = NULL; + signr = __dequeue_signal(&tsk->pending, mask, info, &timer_sigq); if (!signr) { *type = PIDTYPE_TGID; signr = __dequeue_signal(&tsk->signal->shared_pending, - mask, info, &resched_timer); -#ifdef CONFIG_POSIX_TIMERS - /* - * itimer signal ? - * - * itimers are process shared and we restart periodic - * itimers in the signal delivery path to prevent DoS - * attacks in the high resolution timer case. This is - * compliant with the old way of self-restarting - * itimers, as the SIGALRM is a legacy signal and only - * queued once. Changing the restart behaviour to - * restart the timer in the signal dequeue path is - * reducing the timer noise on heavy loaded !highres - * systems too. - */ - if (unlikely(signr == SIGALRM)) { - struct hrtimer *tmr = &tsk->signal->real_timer; - - if (!hrtimer_is_queued(tmr) && - tsk->signal->it_real_incr != 0) { - hrtimer_forward(tmr, tmr->base->get_time(), - tsk->signal->it_real_incr); - hrtimer_restart(tmr); - } - } -#endif + mask, info, &timer_sigq); + + if (unlikely(signr == SIGALRM)) + posixtimer_rearm_itimer(tsk); } recalc_sigpending(); @@ -683,22 +654,12 @@ int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) */ current->jobctl |= JOBCTL_STOP_DEQUEUED; } -#ifdef CONFIG_POSIX_TIMERS - if (resched_timer) { - /* - * Release the siglock to ensure proper locking order - * of timer locks outside of siglocks. Note, we leave - * irqs disabled here, since the posix-timers code is - * about to disable them again anyway. - */ - spin_unlock(&tsk->sighand->siglock); - posixtimer_rearm(info); - spin_lock(&tsk->sighand->siglock); - /* Don't expose the si_sys_private value to userspace */ - info->si_sys_private = 0; + if (IS_ENABLED(CONFIG_POSIX_TIMERS) && unlikely(timer_sigq)) { + if (!posixtimer_deliver_signal(info, timer_sigq)) + goto again; } -#endif + return signr; } EXPORT_SYMBOL_GPL(dequeue_signal); @@ -773,17 +734,24 @@ void signal_wake_up_state(struct task_struct *t, unsigned int state) kick_process(t); } -/* - * Remove signals in mask from the pending set and queue. - * Returns 1 if any signals were found. - * - * All callers must be holding the siglock. - */ -static void flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) +static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q); + +static void sigqueue_free_ignored(struct task_struct *tsk, struct sigqueue *q) +{ + if (likely(!(q->flags & SIGQUEUE_PREALLOC) || q->info.si_code != SI_TIMER)) + __sigqueue_free(q); + else + posixtimer_sig_ignore(tsk, q); +} + +/* Remove signals in mask from the pending set and queue. */ +static void flush_sigqueue_mask(struct task_struct *p, sigset_t *mask, struct sigpending *s) { struct sigqueue *q, *n; sigset_t m; + lockdep_assert_held(&p->sighand->siglock); + sigandsets(&m, mask, &s->signal); if (sigisemptyset(&m)) return; @@ -792,7 +760,7 @@ static void flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) list_for_each_entry_safe(q, n, &s->list, list) { if (sigismember(mask, q->info.si_signo)) { list_del_init(&q->list); - __sigqueue_free(q); + sigqueue_free_ignored(p, q); } } } @@ -917,18 +885,18 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) * This is a stop signal. Remove SIGCONT from all queues. */ siginitset(&flush, sigmask(SIGCONT)); - flush_sigqueue_mask(&flush, &signal->shared_pending); + flush_sigqueue_mask(p, &flush, &signal->shared_pending); for_each_thread(p, t) - flush_sigqueue_mask(&flush, &t->pending); + flush_sigqueue_mask(p, &flush, &t->pending); } else if (sig == SIGCONT) { unsigned int why; /* * Remove all stop signals from all queues, wake all threads. */ siginitset(&flush, SIG_KERNEL_STOP_MASK); - flush_sigqueue_mask(&flush, &signal->shared_pending); + flush_sigqueue_mask(p, &flush, &signal->shared_pending); for_each_thread(p, t) { - flush_sigqueue_mask(&flush, &t->pending); + flush_sigqueue_mask(p, &flush, &t->pending); task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); if (likely(!(t->ptrace & PT_SEIZED))) { t->jobctl &= ~JOBCTL_STOPPED; @@ -1115,7 +1083,7 @@ static int __send_signal_locked(int sig, struct kernel_siginfo *info, else override_rlimit = 0; - q = __sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit, 0); + q = sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit); if (q) { list_add_tail(&q->list, &pending->list); @@ -1923,112 +1891,242 @@ int kill_pid(struct pid *pid, int sig, int priv) } EXPORT_SYMBOL(kill_pid); +#ifdef CONFIG_POSIX_TIMERS /* - * These functions support sending signals using preallocated sigqueue - * structures. This is needed "because realtime applications cannot - * afford to lose notifications of asynchronous events, like timer - * expirations or I/O completions". In the case of POSIX Timers - * we allocate the sigqueue structure from the timer_create. If this - * allocation fails we are able to report the failure to the application - * with an EAGAIN error. + * These functions handle POSIX timer signals. POSIX timers use + * preallocated sigqueue structs for sending signals. */ -struct sigqueue *sigqueue_alloc(void) +static void __flush_itimer_signals(struct sigpending *pending) { - return __sigqueue_alloc(-1, current, GFP_KERNEL, 0, SIGQUEUE_PREALLOC); + sigset_t signal, retain; + struct sigqueue *q, *n; + + signal = pending->signal; + sigemptyset(&retain); + + list_for_each_entry_safe(q, n, &pending->list, list) { + int sig = q->info.si_signo; + + if (likely(q->info.si_code != SI_TIMER)) { + sigaddset(&retain, sig); + } else { + sigdelset(&signal, sig); + list_del_init(&q->list); + __sigqueue_free(q); + } + } + + sigorsets(&pending->signal, &signal, &retain); } -void sigqueue_free(struct sigqueue *q) +void flush_itimer_signals(void) { - spinlock_t *lock = ¤t->sighand->siglock; - unsigned long flags; + struct task_struct *tsk = current; - if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC))) - return; - /* - * We must hold ->siglock while testing q->list - * to serialize with collect_signal() or with - * __exit_signal()->flush_sigqueue(). - */ - spin_lock_irqsave(lock, flags); - q->flags &= ~SIGQUEUE_PREALLOC; - /* - * If it is queued it will be freed when dequeued, - * like the "regular" sigqueue. - */ - if (!list_empty(&q->list)) - q = NULL; - spin_unlock_irqrestore(lock, flags); + guard(spinlock_irqsave)(&tsk->sighand->siglock); + __flush_itimer_signals(&tsk->pending); + __flush_itimer_signals(&tsk->signal->shared_pending); +} - if (q) - __sigqueue_free(q); +bool posixtimer_init_sigqueue(struct sigqueue *q) +{ + struct ucounts *ucounts = sig_get_ucounts(current, -1, 0); + + if (!ucounts) + return false; + clear_siginfo(&q->info); + __sigqueue_init(q, ucounts, SIGQUEUE_PREALLOC); + return true; } -int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type) +static void posixtimer_queue_sigqueue(struct sigqueue *q, struct task_struct *t, enum pid_type type) { - int sig = q->info.si_signo; struct sigpending *pending; + int sig = q->info.si_signo; + + signalfd_notify(t, sig); + pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; + list_add_tail(&q->list, &pending->list); + sigaddset(&pending->signal, sig); + complete_signal(sig, t, type); +} + +/* + * This function is used by POSIX timers to deliver a timer signal. + * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID + * set), the signal must be delivered to the specific thread (queues + * into t->pending). + * + * Where type is not PIDTYPE_PID, signals must be delivered to the + * process. In this case, prefer to deliver to current if it is in + * the same thread group as the target process, which avoids + * unnecessarily waking up a potentially idle task. + */ +static inline struct task_struct *posixtimer_get_target(struct k_itimer *tmr) +{ + struct task_struct *t = pid_task(tmr->it_pid, tmr->it_pid_type); + + if (t && tmr->it_pid_type != PIDTYPE_PID && same_thread_group(t, current)) + t = current; + return t; +} + +void posixtimer_send_sigqueue(struct k_itimer *tmr) +{ + struct sigqueue *q = &tmr->sigq; + int sig = q->info.si_signo; struct task_struct *t; unsigned long flags; - int ret, result; + int result; - if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC))) - return 0; - if (WARN_ON_ONCE(q->info.si_code != SI_TIMER)) - return 0; + guard(rcu)(); - ret = -1; - rcu_read_lock(); + t = posixtimer_get_target(tmr); + if (!t) + return; + + if (!likely(lock_task_sighand(t, &flags))) + return; /* - * This function is used by POSIX timers to deliver a timer signal. - * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID - * set), the signal must be delivered to the specific thread (queues - * into t->pending). - * - * Where type is not PIDTYPE_PID, signals must be delivered to the - * process. In this case, prefer to deliver to current if it is in - * the same thread group as the target process, which avoids - * unnecessarily waking up a potentially idle task. + * Update @tmr::sigqueue_seq for posix timer signals with sighand + * locked to prevent a race against dequeue_signal(). */ - t = pid_task(pid, type); - if (!t) - goto ret; - if (type != PIDTYPE_PID && same_thread_group(t, current)) - t = current; - if (!likely(lock_task_sighand(t, &flags))) - goto ret; + tmr->it_sigqueue_seq = tmr->it_signal_seq; - ret = 1; /* the signal is ignored */ - result = TRACE_SIGNAL_IGNORED; - if (!prepare_signal(sig, t, false)) + /* + * Set the signal delivery status under sighand lock, so that the + * ignored signal handling can distinguish between a periodic and a + * non-periodic timer. + */ + tmr->it_sig_periodic = tmr->it_status == POSIX_TIMER_REQUEUE_PENDING; + + if (!prepare_signal(sig, t, false)) { + result = TRACE_SIGNAL_IGNORED; + + if (!list_empty(&q->list)) { + /* + * If task group is exiting with the signal already pending, + * wait for __exit_signal() to do its job. Otherwise if + * ignored, it's not supposed to be queued. Try to survive. + */ + WARN_ON_ONCE(!(t->signal->flags & SIGNAL_GROUP_EXIT)); + goto out; + } + + /* Periodic timers with SIG_IGN are queued on the ignored list */ + if (tmr->it_sig_periodic) { + /* + * Already queued means the timer was rearmed after + * the previous expiry got it on the ignore list. + * Nothing to do for that case. + */ + if (hlist_unhashed(&tmr->ignored_list)) { + /* + * Take a signal reference and queue it on + * the ignored list. + */ + posixtimer_sigqueue_getref(q); + posixtimer_sig_ignore(t, q); + } + } else if (!hlist_unhashed(&tmr->ignored_list)) { + /* + * Covers the case where a timer was periodic and + * then the signal was ignored. Later it was rearmed + * as oneshot timer. The previous signal is invalid + * now, and this oneshot signal has to be dropped. + * Remove it from the ignored list and drop the + * reference count as the signal is not longer + * queued. + */ + hlist_del_init(&tmr->ignored_list); + posixtimer_putref(tmr); + } goto out; + } + + /* This should never happen and leaks a reference count */ + if (WARN_ON_ONCE(!hlist_unhashed(&tmr->ignored_list))) + hlist_del_init(&tmr->ignored_list); - ret = 0; if (unlikely(!list_empty(&q->list))) { - /* - * If an SI_TIMER entry is already queue just increment - * the overrun count. - */ - q->info.si_overrun++; + /* This holds a reference count already */ result = TRACE_SIGNAL_ALREADY_PENDING; goto out; } - q->info.si_overrun = 0; - signalfd_notify(t, sig); - pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; - list_add_tail(&q->list, &pending->list); - sigaddset(&pending->signal, sig); - complete_signal(sig, t, type); + posixtimer_sigqueue_getref(q); + posixtimer_queue_sigqueue(q, t, tmr->it_pid_type); result = TRACE_SIGNAL_DELIVERED; out: - trace_signal_generate(sig, &q->info, t, type != PIDTYPE_PID, result); + trace_signal_generate(sig, &q->info, t, tmr->it_pid_type != PIDTYPE_PID, result); unlock_task_sighand(t, &flags); -ret: - rcu_read_unlock(); - return ret; } +static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q) +{ + struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); + + /* + * If the timer is marked deleted already or the signal originates + * from a non-periodic timer, then just drop the reference + * count. Otherwise queue it on the ignored list. + */ + if (tmr->it_signal && tmr->it_sig_periodic) + hlist_add_head(&tmr->ignored_list, &tsk->signal->ignored_posix_timers); + else + posixtimer_putref(tmr); +} + +static void posixtimer_sig_unignore(struct task_struct *tsk, int sig) +{ + struct hlist_head *head = &tsk->signal->ignored_posix_timers; + struct hlist_node *tmp; + struct k_itimer *tmr; + + if (likely(hlist_empty(head))) + return; + + /* + * Rearming a timer with sighand lock held is not possible due to + * lock ordering vs. tmr::it_lock. Just stick the sigqueue back and + * let the signal delivery path deal with it whether it needs to be + * rearmed or not. This cannot be decided here w/o dropping sighand + * lock and creating a loop retry horror show. + */ + hlist_for_each_entry_safe(tmr, tmp , head, ignored_list) { + struct task_struct *target; + + /* + * tmr::sigq.info.si_signo is immutable, so accessing it + * without holding tmr::it_lock is safe. + */ + if (tmr->sigq.info.si_signo != sig) + continue; + + hlist_del_init(&tmr->ignored_list); + + /* This should never happen and leaks a reference count */ + if (WARN_ON_ONCE(!list_empty(&tmr->sigq.list))) + continue; + + /* + * Get the target for the signal. If target is a thread and + * has exited by now, drop the reference count. + */ + guard(rcu)(); + target = posixtimer_get_target(tmr); + if (target) + posixtimer_queue_sigqueue(&tmr->sigq, target, tmr->it_pid_type); + else + posixtimer_putref(tmr); + } +} +#else /* CONFIG_POSIX_TIMERS */ +static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q) { } +static inline void posixtimer_sig_unignore(struct task_struct *tsk, int sig) { } +#endif /* !CONFIG_POSIX_TIMERS */ + void do_notify_pidfd(struct task_struct *task) { struct pid *pid = task_pid(task); @@ -4145,8 +4243,8 @@ void kernel_sigaction(int sig, __sighandler_t action) sigemptyset(&mask); sigaddset(&mask, sig); - flush_sigqueue_mask(&mask, ¤t->signal->shared_pending); - flush_sigqueue_mask(&mask, ¤t->pending); + flush_sigqueue_mask(current, &mask, ¤t->signal->shared_pending); + flush_sigqueue_mask(current, &mask, ¤t->pending); recalc_sigpending(); } spin_unlock_irq(¤t->sighand->siglock); @@ -4196,6 +4294,8 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) sigaction_compat_abi(act, oact); if (act) { + bool was_ignored = k->sa.sa_handler == SIG_IGN; + sigdelsetmask(&act->sa.sa_mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); *k = *act; @@ -4213,9 +4313,11 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) if (sig_handler_ignored(sig_handler(p, sig), sig)) { sigemptyset(&mask); sigaddset(&mask, sig); - flush_sigqueue_mask(&mask, &p->signal->shared_pending); + flush_sigqueue_mask(p, &mask, &p->signal->shared_pending); for_each_thread(p, t) - flush_sigqueue_mask(&mask, &t->pending); + flush_sigqueue_mask(p, &mask, &t->pending); + } else if (was_ignored) { + posixtimer_sig_unignore(p, sig); } } diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 8ebb6d5a106b..b0b97a60aaa6 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -17,11 +17,6 @@ config ARCH_CLOCKSOURCE_DATA config ARCH_CLOCKSOURCE_INIT bool -# Clocksources require validation of the clocksource against the last -# cycle update - x86/TSC misfeature -config CLOCKSOURCE_VALIDATE_LAST_CYCLE - bool - # Timekeeping vsyscall support config GENERIC_TIME_VSYSCALL bool diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 4af2a264a160..fe0ae82124fe 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y += time.o timer.o hrtimer.o +obj-y += time.o timer.o hrtimer.o sleep_timeout.o obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o obj-y += timeconv.o timecounter.o alarmtimer.o diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 8bf888641694..0ddccdff119a 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -197,28 +197,15 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) { struct alarm *alarm = container_of(timer, struct alarm, timer); struct alarm_base *base = &alarm_bases[alarm->type]; - unsigned long flags; - int ret = HRTIMER_NORESTART; - int restart = ALARMTIMER_NORESTART; - spin_lock_irqsave(&base->lock, flags); - alarmtimer_dequeue(base, alarm); - spin_unlock_irqrestore(&base->lock, flags); + scoped_guard (spinlock_irqsave, &base->lock) + alarmtimer_dequeue(base, alarm); if (alarm->function) - restart = alarm->function(alarm, base->get_ktime()); - - spin_lock_irqsave(&base->lock, flags); - if (restart != ALARMTIMER_NORESTART) { - hrtimer_set_expires(&alarm->timer, alarm->node.expires); - alarmtimer_enqueue(base, alarm); - ret = HRTIMER_RESTART; - } - spin_unlock_irqrestore(&base->lock, flags); + alarm->function(alarm, base->get_ktime()); trace_alarmtimer_fired(alarm, base->get_ktime()); - return ret; - + return HRTIMER_NORESTART; } ktime_t alarm_expires_remaining(const struct alarm *alarm) @@ -334,10 +321,9 @@ static int alarmtimer_resume(struct device *dev) static void __alarm_init(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) + void (*function)(struct alarm *, ktime_t)) { timerqueue_init(&alarm->node); - alarm->timer.function = alarmtimer_fired; alarm->function = function; alarm->type = type; alarm->state = ALARMTIMER_STATE_INACTIVE; @@ -350,10 +336,10 @@ __alarm_init(struct alarm *alarm, enum alarmtimer_type type, * @function: callback that is run when the alarm fires */ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) + void (*function)(struct alarm *, ktime_t)) { - hrtimer_init(&alarm->timer, alarm_bases[type].base_clockid, - HRTIMER_MODE_ABS); + hrtimer_setup(&alarm->timer, alarmtimer_fired, alarm_bases[type].base_clockid, + HRTIMER_MODE_ABS); __alarm_init(alarm, type, function); } EXPORT_SYMBOL_GPL(alarm_init); @@ -480,35 +466,11 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(alarm_forward); -static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle) +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) { struct alarm_base *base = &alarm_bases[alarm->type]; - ktime_t now = base->get_ktime(); - - if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) { - /* - * Same issue as with posix_timer_fn(). Timers which are - * periodic but the signal is ignored can starve the system - * with a very small interval. The real fix which was - * promised in the context of posix_timer_fn() never - * materialized, but someone should really work on it. - * - * To prevent DOS fake @now to be 1 jiffy out which keeps - * the overrun accounting correct but creates an - * inconsistency vs. timer_gettime(2). - */ - ktime_t kj = NSEC_PER_SEC / HZ; - if (interval < kj) - now = ktime_add(now, kj); - } - - return alarm_forward(alarm, now, interval); -} - -u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) -{ - return __alarm_forward_now(alarm, interval, false); + return alarm_forward(alarm, base->get_ktime(), interval); } EXPORT_SYMBOL_GPL(alarm_forward_now); @@ -567,30 +529,12 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) * * Return: whether the timer is to be restarted */ -static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, - ktime_t now) +static void alarm_handle_timer(struct alarm *alarm, ktime_t now) { - struct k_itimer *ptr = container_of(alarm, struct k_itimer, - it.alarm.alarmtimer); - enum alarmtimer_restart result = ALARMTIMER_NORESTART; - unsigned long flags; + struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); - spin_lock_irqsave(&ptr->it_lock, flags); - - if (posix_timer_queue_signal(ptr) && ptr->it_interval) { - /* - * Handle ignored signals and rearm the timer. This will go - * away once we handle ignored signals proper. Ensure that - * small intervals cannot starve the system. - */ - ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); - ++ptr->it_requeue_pending; - ptr->it_active = 1; - result = ALARMTIMER_RESTART; - } - spin_unlock_irqrestore(&ptr->it_lock, flags); - - return result; + guard(spinlock_irqsave)(&ptr->it_lock); + posix_timer_queue_signal(ptr); } /** @@ -751,18 +695,14 @@ static int alarm_timer_create(struct k_itimer *new_timer) * @now: time at the timer expiration * * Wakes up the task that set the alarmtimer - * - * Return: ALARMTIMER_NORESTART */ -static enum alarmtimer_restart alarmtimer_nsleep_wakeup(struct alarm *alarm, - ktime_t now) +static void alarmtimer_nsleep_wakeup(struct alarm *alarm, ktime_t now) { struct task_struct *task = alarm->data; alarm->data = NULL; if (task) wake_up_process(task); - return ALARMTIMER_NORESTART; } /** @@ -814,10 +754,10 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp, static void alarm_init_on_stack(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) + void (*function)(struct alarm *, ktime_t)) { - hrtimer_init_on_stack(&alarm->timer, alarm_bases[type].base_clockid, - HRTIMER_MODE_ABS); + hrtimer_setup_on_stack(&alarm->timer, alarmtimer_fired, alarm_bases[type].base_clockid, + HRTIMER_MODE_ABS); __alarm_init(alarm, type, function); } diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 78c7bd64d0dd..f3e831f62906 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -337,13 +337,21 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, } /* - * Called after a notify add to make devices available which were - * released from the notifier call. + * Called after a clockevent has been added which might + * have replaced a current regular or broadcast device. A + * released normal device might be a suitable replacement + * for the current broadcast device. Similarly a released + * broadcast device might be a suitable replacement for a + * normal device. */ static void clockevents_notify_released(void) { struct clock_event_device *dev; + /* + * Keep iterating as long as tick_check_new_device() + * replaces a device. + */ while (!list_empty(&clockevents_released)) { dev = list_entry(clockevents_released.next, struct clock_event_device, list); @@ -610,39 +618,30 @@ void clockevents_resume(void) #ifdef CONFIG_HOTPLUG_CPU -# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST /** - * tick_offline_cpu - Take CPU out of the broadcast mechanism + * tick_offline_cpu - Shutdown all clock events related + * to this CPU and take it out of the + * broadcast mechanism. * @cpu: The outgoing CPU * - * Called on the outgoing CPU after it took itself offline. + * Called by the dying CPU during teardown. */ void tick_offline_cpu(unsigned int cpu) { - raw_spin_lock(&clockevents_lock); - tick_broadcast_offline(cpu); - raw_spin_unlock(&clockevents_lock); -} -# endif - -/** - * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu - * @cpu: The dead CPU - */ -void tick_cleanup_dead_cpu(int cpu) -{ struct clock_event_device *dev, *tmp; - unsigned long flags; - raw_spin_lock_irqsave(&clockevents_lock, flags); + raw_spin_lock(&clockevents_lock); + tick_broadcast_offline(cpu); tick_shutdown(cpu); + /* * Unregister the clock event devices which were - * released from the users in the notify chain. + * released above. */ list_for_each_entry_safe(dev, tmp, &clockevents_released, list) list_del(&dev->list); + /* * Now check whether the CPU has left unused per cpu devices */ @@ -654,7 +653,8 @@ void tick_cleanup_dead_cpu(int cpu) list_del(&dev->list); } } - raw_spin_unlock_irqrestore(&clockevents_lock, flags); + + raw_spin_unlock(&clockevents_lock); } #endif diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 23336eecb4f4..aab6472853fa 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -20,6 +20,8 @@ #include "tick-internal.h" #include "timekeeping_internal.h" +static void clocksource_enqueue(struct clocksource *cs); + static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) { u64 delta = clocksource_delta(end, start, cs->mask); @@ -171,7 +173,6 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) } static int clocksource_watchdog_kthread(void *data); -static void __clocksource_change_rating(struct clocksource *cs, int rating); static void clocksource_watchdog_work(struct work_struct *work) { @@ -191,6 +192,13 @@ static void clocksource_watchdog_work(struct work_struct *work) kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); } +static void clocksource_change_rating(struct clocksource *cs, int rating) +{ + list_del(&cs->list); + cs->rating = rating; + clocksource_enqueue(cs); +} + static void __clocksource_unstable(struct clocksource *cs) { cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); @@ -697,7 +705,7 @@ static int __clocksource_watchdog_kthread(void) list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { if (cs->flags & CLOCK_SOURCE_UNSTABLE) { list_del_init(&cs->wd_list); - __clocksource_change_rating(cs, 0); + clocksource_change_rating(cs, 0); select = 1; } if (cs->flags & CLOCK_SOURCE_RESELECT) { @@ -1255,34 +1263,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) } EXPORT_SYMBOL_GPL(__clocksource_register_scale); -static void __clocksource_change_rating(struct clocksource *cs, int rating) -{ - list_del(&cs->list); - cs->rating = rating; - clocksource_enqueue(cs); -} - -/** - * clocksource_change_rating - Change the rating of a registered clocksource - * @cs: clocksource to be changed - * @rating: new rating - */ -void clocksource_change_rating(struct clocksource *cs, int rating) -{ - unsigned long flags; - - mutex_lock(&clocksource_mutex); - clocksource_watchdog_lock(&flags); - __clocksource_change_rating(cs, rating); - clocksource_watchdog_unlock(&flags); - - clocksource_select(); - clocksource_select_watchdog(false); - clocksource_suspend_select(false); - mutex_unlock(&clocksource_mutex); -} -EXPORT_SYMBOL(clocksource_change_rating); - /* * Unbind clocksource @cs. Called with clocksource_mutex held */ diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index d9911516e743..80fe3749d2db 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -417,6 +417,11 @@ static inline void debug_hrtimer_init(struct hrtimer *timer) debug_object_init(timer, &hrtimer_debug_descr); } +static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) +{ + debug_object_init_on_stack(timer, &hrtimer_debug_descr); +} + static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { @@ -428,28 +433,6 @@ static inline void debug_hrtimer_deactivate(struct hrtimer *timer) debug_object_deactivate(timer, &hrtimer_debug_descr); } -static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, - enum hrtimer_mode mode); - -void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, - enum hrtimer_mode mode) -{ - debug_object_init_on_stack(timer, &hrtimer_debug_descr); - __hrtimer_init(timer, clock_id, mode); -} -EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); - -static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, - clockid_t clock_id, enum hrtimer_mode mode); - -void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, enum hrtimer_mode mode) -{ - debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr); - __hrtimer_init_sleeper(sl, clock_id, mode); -} -EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); - void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); @@ -459,6 +442,7 @@ EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } +static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } @@ -472,6 +456,13 @@ debug_init(struct hrtimer *timer, clockid_t clockid, trace_hrtimer_init(timer, clockid, mode); } +static inline void debug_init_on_stack(struct hrtimer *timer, clockid_t clockid, + enum hrtimer_mode mode) +{ + debug_hrtimer_init_on_stack(timer); + trace_hrtimer_init(timer, clockid, mode); +} + static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { @@ -1544,6 +1535,11 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id) return HRTIMER_BASE_MONOTONIC; } +static enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) +{ + return HRTIMER_NORESTART; +} + static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { @@ -1580,6 +1576,18 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, timerqueue_init(&timer->node); } +static void __hrtimer_setup(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode) +{ + __hrtimer_init(timer, clock_id, mode); + + if (WARN_ON_ONCE(!function)) + timer->function = hrtimer_dummy_timeout; + else + timer->function = function; +} + /** * hrtimer_init - initialize a timer to the given clock * @timer: the timer to be initialized @@ -1600,6 +1608,46 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, } EXPORT_SYMBOL_GPL(hrtimer_init); +/** + * hrtimer_setup - initialize a timer to the given clock + * @timer: the timer to be initialized + * @function: the callback function + * @clock_id: the clock to be used + * @mode: The modes which are relevant for initialization: + * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, + * HRTIMER_MODE_REL_SOFT + * + * The PINNED variants of the above can be handed in, + * but the PINNED bit is ignored as pinning happens + * when the hrtimer is started + */ +void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode) +{ + debug_init(timer, clock_id, mode); + __hrtimer_setup(timer, function, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_setup); + +/** + * hrtimer_setup_on_stack - initialize a timer on stack memory + * @timer: The timer to be initialized + * @function: the callback function + * @clock_id: The clock to be used + * @mode: The timer mode + * + * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack + * memory. + */ +void hrtimer_setup_on_stack(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode) +{ + debug_init_on_stack(timer, clock_id, mode); + __hrtimer_setup(timer, function, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack); + /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated @@ -1944,7 +1992,7 @@ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because - * hrtimer_init_sleeper() determines the delivery mode on RT so the + * __hrtimer_init_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) @@ -1987,19 +2035,18 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, } /** - * hrtimer_init_sleeper - initialize sleeper to the given clock + * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ -void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, - enum hrtimer_mode mode) +void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, + clockid_t clock_id, enum hrtimer_mode mode) { - debug_init(&sl->timer, clock_id, mode); + debug_init_on_stack(&sl->timer, clock_id, mode); __hrtimer_init_sleeper(sl, clock_id, mode); - } -EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); +EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { @@ -2060,8 +2107,7 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) struct hrtimer_sleeper t; int ret; - hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid, - HRTIMER_MODE_ABS); + hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); @@ -2075,7 +2121,7 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, struct hrtimer_sleeper t; int ret = 0; - hrtimer_init_sleeper_on_stack(&t, clockid, mode); + hrtimer_setup_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) @@ -2242,123 +2288,3 @@ void __init hrtimers_init(void) hrtimers_prepare_cpu(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } - -/** - * schedule_hrtimeout_range_clock - sleep until timeout - * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) - * @mode: timer mode - * @clock_id: timer clock to be used - */ -int __sched -schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, - const enum hrtimer_mode mode, clockid_t clock_id) -{ - struct hrtimer_sleeper t; - - /* - * Optimize when a zero timeout value is given. It does not - * matter whether this is an absolute or a relative time. - */ - if (expires && *expires == 0) { - __set_current_state(TASK_RUNNING); - return 0; - } - - /* - * A NULL parameter means "infinite" - */ - if (!expires) { - schedule(); - return -EINTR; - } - - hrtimer_init_sleeper_on_stack(&t, clock_id, mode); - hrtimer_set_expires_range_ns(&t.timer, *expires, delta); - hrtimer_sleeper_start_expires(&t, mode); - - if (likely(t.task)) - schedule(); - - hrtimer_cancel(&t.timer); - destroy_hrtimer_on_stack(&t.timer); - - __set_current_state(TASK_RUNNING); - - return !t.task ? 0 : -EINTR; -} -EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); - -/** - * schedule_hrtimeout_range - sleep until timeout - * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) - * @mode: timer mode - * - * Make the current task sleep until the given expiry time has - * elapsed. The routine will return immediately unless - * the current task state has been set (see set_current_state()). - * - * The @delta argument gives the kernel the freedom to schedule the - * actual wakeup to a time that is both power and performance friendly - * for regular (non RT/DL) tasks. - * The kernel give the normal best effort behavior for "@expires+@delta", - * but may decide to fire the timer earlier, but no earlier than @expires. - * - * You can set the task state as follows - - * - * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to - * pass before the routine returns unless the current task is explicitly - * woken up, (e.g. by wake_up_process()). - * - * %TASK_INTERRUPTIBLE - the routine may return early if a signal is - * delivered to the current task or the current task is explicitly woken - * up. - * - * The current task state is guaranteed to be TASK_RUNNING when this - * routine returns. - * - * Returns 0 when the timer has expired. If the task was woken before the - * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or - * by an explicit wakeup, it returns -EINTR. - */ -int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta, - const enum hrtimer_mode mode) -{ - return schedule_hrtimeout_range_clock(expires, delta, mode, - CLOCK_MONOTONIC); -} -EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); - -/** - * schedule_hrtimeout - sleep until timeout - * @expires: timeout value (ktime_t) - * @mode: timer mode - * - * Make the current task sleep until the given expiry time has - * elapsed. The routine will return immediately unless - * the current task state has been set (see set_current_state()). - * - * You can set the task state as follows - - * - * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to - * pass before the routine returns unless the current task is explicitly - * woken up, (e.g. by wake_up_process()). - * - * %TASK_INTERRUPTIBLE - the routine may return early if a signal is - * delivered to the current task or the current task is explicitly woken - * up. - * - * The current task state is guaranteed to be TASK_RUNNING when this - * routine returns. - * - * Returns 0 when the timer has expired. If the task was woken before the - * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or - * by an explicit wakeup, it returns -EINTR. - */ -int __sched schedule_hrtimeout(ktime_t *expires, - const enum hrtimer_mode mode) -{ - return schedule_hrtimeout_range(expires, 0, mode); -} -EXPORT_SYMBOL_GPL(schedule_hrtimeout); diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 00629e658ca1..876d389b2e21 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -151,7 +151,27 @@ COMPAT_SYSCALL_DEFINE2(getitimer, int, which, #endif /* - * The timer is automagically restarted, when interval != 0 + * Invoked from dequeue_signal() when SIG_ALRM is delivered. + * + * Restart the ITIMER_REAL timer if it is armed as periodic timer. Doing + * this in the signal delivery path instead of self rearming prevents a DoS + * with small increments in the high reolution timer case and reduces timer + * noise in general. + */ +void posixtimer_rearm_itimer(struct task_struct *tsk) +{ + struct hrtimer *tmr = &tsk->signal->real_timer; + + if (!hrtimer_is_queued(tmr) && tsk->signal->it_real_incr != 0) { + hrtimer_forward(tmr, tmr->base->get_time(), + tsk->signal->it_real_incr); + hrtimer_restart(tmr); + } +} + +/* + * Interval timers are restarted in the signal delivery path. See + * posixtimer_rearm_itimer(). */ enum hrtimer_restart it_real_fn(struct hrtimer *timer) { diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 802b336f4b8c..b550ebe0f03b 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -22,22 +22,79 @@ #include "ntp_internal.h" #include "timekeeping_internal.h" - -/* - * NTP timekeeping variables: +/** + * struct ntp_data - Structure holding all NTP related state + * @tick_usec: USER_HZ period in microseconds + * @tick_length: Adjusted tick length + * @tick_length_base: Base value for @tick_length + * @time_state: State of the clock synchronization + * @time_status: Clock status bits + * @time_offset: Time adjustment in nanoseconds + * @time_constant: PLL time constant + * @time_maxerror: Maximum error in microseconds holding the NTP sync distance + * (NTP dispersion + delay / 2) + * @time_esterror: Estimated error in microseconds holding NTP dispersion + * @time_freq: Frequency offset scaled nsecs/secs + * @time_reftime: Time at last adjustment in seconds + * @time_adjust: Adjustment value + * @ntp_tick_adj: Constant boot-param configurable NTP tick adjustment (upscaled) + * @ntp_next_leap_sec: Second value of the next pending leapsecond, or TIME64_MAX if no leap * - * Note: All of the NTP state is protected by the timekeeping locks. + * @pps_valid: PPS signal watchdog counter + * @pps_tf: PPS phase median filter + * @pps_jitter: PPS current jitter in nanoseconds + * @pps_fbase: PPS beginning of the last freq interval + * @pps_shift: PPS current interval duration in seconds (shift value) + * @pps_intcnt: PPS interval counter + * @pps_freq: PPS frequency offset in scaled ns/s + * @pps_stabil: PPS current stability in scaled ns/s + * @pps_calcnt: PPS monitor: calibration intervals + * @pps_jitcnt: PPS monitor: jitter limit exceeded + * @pps_stbcnt: PPS monitor: stability limit exceeded + * @pps_errcnt: PPS monitor: calibration errors + * + * Protected by the timekeeping locks. */ +struct ntp_data { + unsigned long tick_usec; + u64 tick_length; + u64 tick_length_base; + int time_state; + int time_status; + s64 time_offset; + long time_constant; + long time_maxerror; + long time_esterror; + s64 time_freq; + time64_t time_reftime; + long time_adjust; + s64 ntp_tick_adj; + time64_t ntp_next_leap_sec; +#ifdef CONFIG_NTP_PPS + int pps_valid; + long pps_tf[3]; + long pps_jitter; + struct timespec64 pps_fbase; + int pps_shift; + int pps_intcnt; + s64 pps_freq; + long pps_stabil; + long pps_calcnt; + long pps_jitcnt; + long pps_stbcnt; + long pps_errcnt; +#endif +}; - -/* USER_HZ period (usecs): */ -unsigned long tick_usec = USER_TICK_USEC; - -/* SHIFTED_HZ period (nsecs): */ -unsigned long tick_nsec; - -static u64 tick_length; -static u64 tick_length_base; +static struct ntp_data tk_ntp_data = { + .tick_usec = USER_TICK_USEC, + .time_state = TIME_OK, + .time_status = STA_UNSYNC, + .time_constant = 2, + .time_maxerror = NTP_PHASE_LIMIT, + .time_esterror = NTP_PHASE_LIMIT, + .ntp_next_leap_sec = TIME64_MAX, +}; #define SECS_PER_DAY 86400 #define MAX_TICKADJ 500LL /* usecs */ @@ -45,46 +102,6 @@ static u64 tick_length_base; (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) #define MAX_TAI_OFFSET 100000 -/* - * phase-lock loop variables - */ - -/* - * clock synchronization status - * - * (TIME_ERROR prevents overwriting the CMOS clock) - */ -static int time_state = TIME_OK; - -/* clock status bits: */ -static int time_status = STA_UNSYNC; - -/* time adjustment (nsecs): */ -static s64 time_offset; - -/* pll time constant: */ -static long time_constant = 2; - -/* maximum error (usecs): */ -static long time_maxerror = NTP_PHASE_LIMIT; - -/* estimated error (usecs): */ -static long time_esterror = NTP_PHASE_LIMIT; - -/* frequency offset (scaled nsecs/secs): */ -static s64 time_freq; - -/* time at last adjustment (secs): */ -static time64_t time_reftime; - -static long time_adjust; - -/* constant (boot-param configurable) NTP tick adjustment (upscaled) */ -static s64 ntp_tick_adj; - -/* second value of the next pending leapsecond, or TIME64_MAX if no leap */ -static time64_t ntp_next_leap_sec = TIME64_MAX; - #ifdef CONFIG_NTP_PPS /* @@ -101,128 +118,115 @@ static time64_t ntp_next_leap_sec = TIME64_MAX; intervals to decrease it */ #define PPS_MAXWANDER 100000 /* max PPS freq wander (ns/s) */ -static int pps_valid; /* signal watchdog counter */ -static long pps_tf[3]; /* phase median filter */ -static long pps_jitter; /* current jitter (ns) */ -static struct timespec64 pps_fbase; /* beginning of the last freq interval */ -static int pps_shift; /* current interval duration (s) (shift) */ -static int pps_intcnt; /* interval counter */ -static s64 pps_freq; /* frequency offset (scaled ns/s) */ -static long pps_stabil; /* current stability (scaled ns/s) */ - /* - * PPS signal quality monitors - */ -static long pps_calcnt; /* calibration intervals */ -static long pps_jitcnt; /* jitter limit exceeded */ -static long pps_stbcnt; /* stability limit exceeded */ -static long pps_errcnt; /* calibration errors */ - - -/* PPS kernel consumer compensates the whole phase error immediately. + * PPS kernel consumer compensates the whole phase error immediately. * Otherwise, reduce the offset by a fixed factor times the time constant. */ -static inline s64 ntp_offset_chunk(s64 offset) +static inline s64 ntp_offset_chunk(struct ntp_data *ntpdata, s64 offset) { - if (time_status & STA_PPSTIME && time_status & STA_PPSSIGNAL) + if (ntpdata->time_status & STA_PPSTIME && ntpdata->time_status & STA_PPSSIGNAL) return offset; else - return shift_right(offset, SHIFT_PLL + time_constant); + return shift_right(offset, SHIFT_PLL + ntpdata->time_constant); } -static inline void pps_reset_freq_interval(void) +static inline void pps_reset_freq_interval(struct ntp_data *ntpdata) { - /* the PPS calibration interval may end - surprisingly early */ - pps_shift = PPS_INTMIN; - pps_intcnt = 0; + /* The PPS calibration interval may end surprisingly early */ + ntpdata->pps_shift = PPS_INTMIN; + ntpdata->pps_intcnt = 0; } /** * pps_clear - Clears the PPS state variables + * @ntpdata: Pointer to ntp data */ -static inline void pps_clear(void) +static inline void pps_clear(struct ntp_data *ntpdata) { - pps_reset_freq_interval(); - pps_tf[0] = 0; - pps_tf[1] = 0; - pps_tf[2] = 0; - pps_fbase.tv_sec = pps_fbase.tv_nsec = 0; - pps_freq = 0; + pps_reset_freq_interval(ntpdata); + ntpdata->pps_tf[0] = 0; + ntpdata->pps_tf[1] = 0; + ntpdata->pps_tf[2] = 0; + ntpdata->pps_fbase.tv_sec = ntpdata->pps_fbase.tv_nsec = 0; + ntpdata->pps_freq = 0; } -/* Decrease pps_valid to indicate that another second has passed since - * the last PPS signal. When it reaches 0, indicate that PPS signal is - * missing. +/* + * Decrease pps_valid to indicate that another second has passed since the + * last PPS signal. When it reaches 0, indicate that PPS signal is missing. */ -static inline void pps_dec_valid(void) +static inline void pps_dec_valid(struct ntp_data *ntpdata) { - if (pps_valid > 0) - pps_valid--; - else { - time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER | - STA_PPSWANDER | STA_PPSERROR); - pps_clear(); + if (ntpdata->pps_valid > 0) { + ntpdata->pps_valid--; + } else { + ntpdata->time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER | + STA_PPSWANDER | STA_PPSERROR); + pps_clear(ntpdata); } } -static inline void pps_set_freq(s64 freq) +static inline void pps_set_freq(struct ntp_data *ntpdata) { - pps_freq = freq; + ntpdata->pps_freq = ntpdata->time_freq; } -static inline int is_error_status(int status) +static inline bool is_error_status(int status) { return (status & (STA_UNSYNC|STA_CLOCKERR)) - /* PPS signal lost when either PPS time or - * PPS frequency synchronization requested + /* + * PPS signal lost when either PPS time or PPS frequency + * synchronization requested */ || ((status & (STA_PPSFREQ|STA_PPSTIME)) && !(status & STA_PPSSIGNAL)) - /* PPS jitter exceeded when - * PPS time synchronization requested */ + /* + * PPS jitter exceeded when PPS time synchronization + * requested + */ || ((status & (STA_PPSTIME|STA_PPSJITTER)) == (STA_PPSTIME|STA_PPSJITTER)) - /* PPS wander exceeded or calibration error when - * PPS frequency synchronization requested + /* + * PPS wander exceeded or calibration error when PPS + * frequency synchronization requested */ || ((status & STA_PPSFREQ) && (status & (STA_PPSWANDER|STA_PPSERROR))); } -static inline void pps_fill_timex(struct __kernel_timex *txc) +static inline void pps_fill_timex(struct ntp_data *ntpdata, struct __kernel_timex *txc) { - txc->ppsfreq = shift_right((pps_freq >> PPM_SCALE_INV_SHIFT) * + txc->ppsfreq = shift_right((ntpdata->pps_freq >> PPM_SCALE_INV_SHIFT) * PPM_SCALE_INV, NTP_SCALE_SHIFT); - txc->jitter = pps_jitter; - if (!(time_status & STA_NANO)) - txc->jitter = pps_jitter / NSEC_PER_USEC; - txc->shift = pps_shift; - txc->stabil = pps_stabil; - txc->jitcnt = pps_jitcnt; - txc->calcnt = pps_calcnt; - txc->errcnt = pps_errcnt; - txc->stbcnt = pps_stbcnt; + txc->jitter = ntpdata->pps_jitter; + if (!(ntpdata->time_status & STA_NANO)) + txc->jitter = ntpdata->pps_jitter / NSEC_PER_USEC; + txc->shift = ntpdata->pps_shift; + txc->stabil = ntpdata->pps_stabil; + txc->jitcnt = ntpdata->pps_jitcnt; + txc->calcnt = ntpdata->pps_calcnt; + txc->errcnt = ntpdata->pps_errcnt; + txc->stbcnt = ntpdata->pps_stbcnt; } #else /* !CONFIG_NTP_PPS */ -static inline s64 ntp_offset_chunk(s64 offset) +static inline s64 ntp_offset_chunk(struct ntp_data *ntpdata, s64 offset) { - return shift_right(offset, SHIFT_PLL + time_constant); + return shift_right(offset, SHIFT_PLL + ntpdata->time_constant); } -static inline void pps_reset_freq_interval(void) {} -static inline void pps_clear(void) {} -static inline void pps_dec_valid(void) {} -static inline void pps_set_freq(s64 freq) {} +static inline void pps_reset_freq_interval(struct ntp_data *ntpdata) {} +static inline void pps_clear(struct ntp_data *ntpdata) {} +static inline void pps_dec_valid(struct ntp_data *ntpdata) {} +static inline void pps_set_freq(struct ntp_data *ntpdata) {} -static inline int is_error_status(int status) +static inline bool is_error_status(int status) { return status & (STA_UNSYNC|STA_CLOCKERR); } -static inline void pps_fill_timex(struct __kernel_timex *txc) +static inline void pps_fill_timex(struct ntp_data *ntpdata, struct __kernel_timex *txc) { /* PPS is not implemented, so these are zero */ txc->ppsfreq = 0; @@ -237,138 +241,123 @@ static inline void pps_fill_timex(struct __kernel_timex *txc) #endif /* CONFIG_NTP_PPS */ - -/** - * ntp_synced - Returns 1 if the NTP status is not UNSYNC - * - */ -static inline int ntp_synced(void) -{ - return !(time_status & STA_UNSYNC); -} - - /* - * NTP methods: + * Update tick_length and tick_length_base, based on tick_usec, ntp_tick_adj and + * time_freq: */ - -/* - * Update (tick_length, tick_length_base, tick_nsec), based - * on (tick_usec, ntp_tick_adj, time_freq): - */ -static void ntp_update_frequency(void) +static void ntp_update_frequency(struct ntp_data *ntpdata) { - u64 second_length; - u64 new_base; + u64 second_length, new_base, tick_usec = (u64)ntpdata->tick_usec; - second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) - << NTP_SCALE_SHIFT; + second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ) << NTP_SCALE_SHIFT; - second_length += ntp_tick_adj; - second_length += time_freq; + second_length += ntpdata->ntp_tick_adj; + second_length += ntpdata->time_freq; - tick_nsec = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT; new_base = div_u64(second_length, NTP_INTERVAL_FREQ); /* - * Don't wait for the next second_overflow, apply - * the change to the tick length immediately: + * Don't wait for the next second_overflow, apply the change to the + * tick length immediately: */ - tick_length += new_base - tick_length_base; - tick_length_base = new_base; + ntpdata->tick_length += new_base - ntpdata->tick_length_base; + ntpdata->tick_length_base = new_base; } -static inline s64 ntp_update_offset_fll(s64 offset64, long secs) +static inline s64 ntp_update_offset_fll(struct ntp_data *ntpdata, s64 offset64, long secs) { - time_status &= ~STA_MODE; + ntpdata->time_status &= ~STA_MODE; if (secs < MINSEC) return 0; - if (!(time_status & STA_FLL) && (secs <= MAXSEC)) + if (!(ntpdata->time_status & STA_FLL) && (secs <= MAXSEC)) return 0; - time_status |= STA_MODE; + ntpdata->time_status |= STA_MODE; return div64_long(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs); } -static void ntp_update_offset(long offset) +static void ntp_update_offset(struct ntp_data *ntpdata, long offset) { - s64 freq_adj; - s64 offset64; - long secs; + s64 freq_adj, offset64; + long secs, real_secs; - if (!(time_status & STA_PLL)) + if (!(ntpdata->time_status & STA_PLL)) return; - if (!(time_status & STA_NANO)) { + if (!(ntpdata->time_status & STA_NANO)) { /* Make sure the multiplication below won't overflow */ offset = clamp(offset, -USEC_PER_SEC, USEC_PER_SEC); offset *= NSEC_PER_USEC; } - /* - * Scale the phase adjustment and - * clamp to the operating range. - */ + /* Scale the phase adjustment and clamp to the operating range. */ offset = clamp(offset, -MAXPHASE, MAXPHASE); /* * Select how the frequency is to be controlled * and in which mode (PLL or FLL). */ - secs = (long)(__ktime_get_real_seconds() - time_reftime); - if (unlikely(time_status & STA_FREQHOLD)) + real_secs = __ktime_get_real_seconds(); + secs = (long)(real_secs - ntpdata->time_reftime); + if (unlikely(ntpdata->time_status & STA_FREQHOLD)) secs = 0; - time_reftime = __ktime_get_real_seconds(); + ntpdata->time_reftime = real_secs; offset64 = offset; - freq_adj = ntp_update_offset_fll(offset64, secs); + freq_adj = ntp_update_offset_fll(ntpdata, offset64, secs); /* * Clamp update interval to reduce PLL gain with low * sampling rate (e.g. intermittent network connection) * to avoid instability. */ - if (unlikely(secs > 1 << (SHIFT_PLL + 1 + time_constant))) - secs = 1 << (SHIFT_PLL + 1 + time_constant); + if (unlikely(secs > 1 << (SHIFT_PLL + 1 + ntpdata->time_constant))) + secs = 1 << (SHIFT_PLL + 1 + ntpdata->time_constant); freq_adj += (offset64 * secs) << - (NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant)); + (NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + ntpdata->time_constant)); - freq_adj = min(freq_adj + time_freq, MAXFREQ_SCALED); + freq_adj = min(freq_adj + ntpdata->time_freq, MAXFREQ_SCALED); - time_freq = max(freq_adj, -MAXFREQ_SCALED); + ntpdata->time_freq = max(freq_adj, -MAXFREQ_SCALED); - time_offset = div_s64(offset64 << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ); + ntpdata->time_offset = div_s64(offset64 << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ); } -/** - * ntp_clear - Clears the NTP state variables - */ -void ntp_clear(void) +static void __ntp_clear(struct ntp_data *ntpdata) { - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; + /* Stop active adjtime() */ + ntpdata->time_adjust = 0; + ntpdata->time_status |= STA_UNSYNC; + ntpdata->time_maxerror = NTP_PHASE_LIMIT; + ntpdata->time_esterror = NTP_PHASE_LIMIT; - ntp_update_frequency(); + ntp_update_frequency(ntpdata); - tick_length = tick_length_base; - time_offset = 0; + ntpdata->tick_length = ntpdata->tick_length_base; + ntpdata->time_offset = 0; - ntp_next_leap_sec = TIME64_MAX; + ntpdata->ntp_next_leap_sec = TIME64_MAX; /* Clear PPS state variables */ - pps_clear(); + pps_clear(ntpdata); +} + +/** + * ntp_clear - Clears the NTP state variables + */ +void ntp_clear(void) +{ + __ntp_clear(&tk_ntp_data); } u64 ntp_tick_length(void) { - return tick_length; + return tk_ntp_data.tick_length; } /** @@ -379,16 +368,17 @@ u64 ntp_tick_length(void) */ ktime_t ntp_get_next_leap(void) { + struct ntp_data *ntpdata = &tk_ntp_data; ktime_t ret; - if ((time_state == TIME_INS) && (time_status & STA_INS)) - return ktime_set(ntp_next_leap_sec, 0); + if ((ntpdata->time_state == TIME_INS) && (ntpdata->time_status & STA_INS)) + return ktime_set(ntpdata->ntp_next_leap_sec, 0); ret = KTIME_MAX; return ret; } /* - * this routine handles the overflow of the microsecond field + * This routine handles the overflow of the microsecond field * * The tricky bits of code to handle the accurate clock support * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame. @@ -399,6 +389,7 @@ ktime_t ntp_get_next_leap(void) */ int second_overflow(time64_t secs) { + struct ntp_data *ntpdata = &tk_ntp_data; s64 delta; int leap = 0; s32 rem; @@ -408,87 +399,84 @@ int second_overflow(time64_t secs) * day, the system clock is set back one second; if in leap-delete * state, the system clock is set ahead one second. */ - switch (time_state) { + switch (ntpdata->time_state) { case TIME_OK: - if (time_status & STA_INS) { - time_state = TIME_INS; + if (ntpdata->time_status & STA_INS) { + ntpdata->time_state = TIME_INS; div_s64_rem(secs, SECS_PER_DAY, &rem); - ntp_next_leap_sec = secs + SECS_PER_DAY - rem; - } else if (time_status & STA_DEL) { - time_state = TIME_DEL; + ntpdata->ntp_next_leap_sec = secs + SECS_PER_DAY - rem; + } else if (ntpdata->time_status & STA_DEL) { + ntpdata->time_state = TIME_DEL; div_s64_rem(secs + 1, SECS_PER_DAY, &rem); - ntp_next_leap_sec = secs + SECS_PER_DAY - rem; + ntpdata->ntp_next_leap_sec = secs + SECS_PER_DAY - rem; } break; case TIME_INS: - if (!(time_status & STA_INS)) { - ntp_next_leap_sec = TIME64_MAX; - time_state = TIME_OK; - } else if (secs == ntp_next_leap_sec) { + if (!(ntpdata->time_status & STA_INS)) { + ntpdata->ntp_next_leap_sec = TIME64_MAX; + ntpdata->time_state = TIME_OK; + } else if (secs == ntpdata->ntp_next_leap_sec) { leap = -1; - time_state = TIME_OOP; - printk(KERN_NOTICE - "Clock: inserting leap second 23:59:60 UTC\n"); + ntpdata->time_state = TIME_OOP; + pr_notice("Clock: inserting leap second 23:59:60 UTC\n"); } break; case TIME_DEL: - if (!(time_status & STA_DEL)) { - ntp_next_leap_sec = TIME64_MAX; - time_state = TIME_OK; - } else if (secs == ntp_next_leap_sec) { + if (!(ntpdata->time_status & STA_DEL)) { + ntpdata->ntp_next_leap_sec = TIME64_MAX; + ntpdata->time_state = TIME_OK; + } else if (secs == ntpdata->ntp_next_leap_sec) { leap = 1; - ntp_next_leap_sec = TIME64_MAX; - time_state = TIME_WAIT; - printk(KERN_NOTICE - "Clock: deleting leap second 23:59:59 UTC\n"); + ntpdata->ntp_next_leap_sec = TIME64_MAX; + ntpdata->time_state = TIME_WAIT; + pr_notice("Clock: deleting leap second 23:59:59 UTC\n"); } break; case TIME_OOP: - ntp_next_leap_sec = TIME64_MAX; - time_state = TIME_WAIT; + ntpdata->ntp_next_leap_sec = TIME64_MAX; + ntpdata->time_state = TIME_WAIT; break; case TIME_WAIT: - if (!(time_status & (STA_INS | STA_DEL))) - time_state = TIME_OK; + if (!(ntpdata->time_status & (STA_INS | STA_DEL))) + ntpdata->time_state = TIME_OK; break; } - /* Bump the maxerror field */ - time_maxerror += MAXFREQ / NSEC_PER_USEC; - if (time_maxerror > NTP_PHASE_LIMIT) { - time_maxerror = NTP_PHASE_LIMIT; - time_status |= STA_UNSYNC; + ntpdata->time_maxerror += MAXFREQ / NSEC_PER_USEC; + if (ntpdata->time_maxerror > NTP_PHASE_LIMIT) { + ntpdata->time_maxerror = NTP_PHASE_LIMIT; + ntpdata->time_status |= STA_UNSYNC; } /* Compute the phase adjustment for the next second */ - tick_length = tick_length_base; + ntpdata->tick_length = ntpdata->tick_length_base; - delta = ntp_offset_chunk(time_offset); - time_offset -= delta; - tick_length += delta; + delta = ntp_offset_chunk(ntpdata, ntpdata->time_offset); + ntpdata->time_offset -= delta; + ntpdata->tick_length += delta; /* Check PPS signal */ - pps_dec_valid(); + pps_dec_valid(ntpdata); - if (!time_adjust) + if (!ntpdata->time_adjust) goto out; - if (time_adjust > MAX_TICKADJ) { - time_adjust -= MAX_TICKADJ; - tick_length += MAX_TICKADJ_SCALED; + if (ntpdata->time_adjust > MAX_TICKADJ) { + ntpdata->time_adjust -= MAX_TICKADJ; + ntpdata->tick_length += MAX_TICKADJ_SCALED; goto out; } - if (time_adjust < -MAX_TICKADJ) { - time_adjust += MAX_TICKADJ; - tick_length -= MAX_TICKADJ_SCALED; + if (ntpdata->time_adjust < -MAX_TICKADJ) { + ntpdata->time_adjust += MAX_TICKADJ; + ntpdata->tick_length -= MAX_TICKADJ_SCALED; goto out; } - tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) - << NTP_SCALE_SHIFT; - time_adjust = 0; + ntpdata->tick_length += (s64)(ntpdata->time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) + << NTP_SCALE_SHIFT; + ntpdata->time_adjust = 0; out: return leap; @@ -611,6 +599,15 @@ static inline int update_rtc(struct timespec64 *to_set, unsigned long *offset_ns } #endif +/** + * ntp_synced - Tells whether the NTP status is not UNSYNC + * Returns: true if not UNSYNC, false otherwise + */ +static inline bool ntp_synced(void) +{ + return !(tk_ntp_data.time_status & STA_UNSYNC); +} + /* * If we have an externally synchronized Linux clock, then update RTC clock * accordingly every ~11 minutes. Generally RTCs can only store second @@ -691,162 +688,156 @@ static inline void __init ntp_init_cmos_sync(void) { } /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(const struct __kernel_timex *txc) +static inline void process_adj_status(struct ntp_data *ntpdata, const struct __kernel_timex *txc) { - if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { - time_state = TIME_OK; - time_status = STA_UNSYNC; - ntp_next_leap_sec = TIME64_MAX; - /* restart PPS frequency calibration */ - pps_reset_freq_interval(); + if ((ntpdata->time_status & STA_PLL) && !(txc->status & STA_PLL)) { + ntpdata->time_state = TIME_OK; + ntpdata->time_status = STA_UNSYNC; + ntpdata->ntp_next_leap_sec = TIME64_MAX; + /* Restart PPS frequency calibration */ + pps_reset_freq_interval(ntpdata); } /* * If we turn on PLL adjustments then reset the * reference time to current time. */ - if (!(time_status & STA_PLL) && (txc->status & STA_PLL)) - time_reftime = __ktime_get_real_seconds(); + if (!(ntpdata->time_status & STA_PLL) && (txc->status & STA_PLL)) + ntpdata->time_reftime = __ktime_get_real_seconds(); /* only set allowed bits */ - time_status &= STA_RONLY; - time_status |= txc->status & ~STA_RONLY; + ntpdata->time_status &= STA_RONLY; + ntpdata->time_status |= txc->status & ~STA_RONLY; } - -static inline void process_adjtimex_modes(const struct __kernel_timex *txc, +static inline void process_adjtimex_modes(struct ntp_data *ntpdata, const struct __kernel_timex *txc, s32 *time_tai) { if (txc->modes & ADJ_STATUS) - process_adj_status(txc); + process_adj_status(ntpdata, txc); if (txc->modes & ADJ_NANO) - time_status |= STA_NANO; + ntpdata->time_status |= STA_NANO; if (txc->modes & ADJ_MICRO) - time_status &= ~STA_NANO; + ntpdata->time_status &= ~STA_NANO; if (txc->modes & ADJ_FREQUENCY) { - time_freq = txc->freq * PPM_SCALE; - time_freq = min(time_freq, MAXFREQ_SCALED); - time_freq = max(time_freq, -MAXFREQ_SCALED); - /* update pps_freq */ - pps_set_freq(time_freq); + ntpdata->time_freq = txc->freq * PPM_SCALE; + ntpdata->time_freq = min(ntpdata->time_freq, MAXFREQ_SCALED); + ntpdata->time_freq = max(ntpdata->time_freq, -MAXFREQ_SCALED); + /* Update pps_freq */ + pps_set_freq(ntpdata); } if (txc->modes & ADJ_MAXERROR) - time_maxerror = clamp(txc->maxerror, 0, NTP_PHASE_LIMIT); + ntpdata->time_maxerror = clamp(txc->maxerror, 0, NTP_PHASE_LIMIT); if (txc->modes & ADJ_ESTERROR) - time_esterror = clamp(txc->esterror, 0, NTP_PHASE_LIMIT); + ntpdata->time_esterror = clamp(txc->esterror, 0, NTP_PHASE_LIMIT); if (txc->modes & ADJ_TIMECONST) { - time_constant = clamp(txc->constant, 0, MAXTC); - if (!(time_status & STA_NANO)) - time_constant += 4; - time_constant = clamp(time_constant, 0, MAXTC); + ntpdata->time_constant = clamp(txc->constant, 0, MAXTC); + if (!(ntpdata->time_status & STA_NANO)) + ntpdata->time_constant += 4; + ntpdata->time_constant = clamp(ntpdata->time_constant, 0, MAXTC); } - if (txc->modes & ADJ_TAI && - txc->constant >= 0 && txc->constant <= MAX_TAI_OFFSET) + if (txc->modes & ADJ_TAI && txc->constant >= 0 && txc->constant <= MAX_TAI_OFFSET) *time_tai = txc->constant; if (txc->modes & ADJ_OFFSET) - ntp_update_offset(txc->offset); + ntp_update_offset(ntpdata, txc->offset); if (txc->modes & ADJ_TICK) - tick_usec = txc->tick; + ntpdata->tick_usec = txc->tick; if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET)) - ntp_update_frequency(); + ntp_update_frequency(ntpdata); } - /* - * adjtimex mainly allows reading (and writing, if superuser) of + * adjtimex() mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, s32 *time_tai, struct audit_ntp_data *ad) { + struct ntp_data *ntpdata = &tk_ntp_data; int result; if (txc->modes & ADJ_ADJTIME) { - long save_adjust = time_adjust; + long save_adjust = ntpdata->time_adjust; if (!(txc->modes & ADJ_OFFSET_READONLY)) { /* adjtime() is independent from ntp_adjtime() */ - time_adjust = txc->offset; - ntp_update_frequency(); + ntpdata->time_adjust = txc->offset; + ntp_update_frequency(ntpdata); audit_ntp_set_old(ad, AUDIT_NTP_ADJUST, save_adjust); - audit_ntp_set_new(ad, AUDIT_NTP_ADJUST, time_adjust); + audit_ntp_set_new(ad, AUDIT_NTP_ADJUST, ntpdata->time_adjust); } txc->offset = save_adjust; } else { /* If there are input parameters, then process them: */ if (txc->modes) { - audit_ntp_set_old(ad, AUDIT_NTP_OFFSET, time_offset); - audit_ntp_set_old(ad, AUDIT_NTP_FREQ, time_freq); - audit_ntp_set_old(ad, AUDIT_NTP_STATUS, time_status); + audit_ntp_set_old(ad, AUDIT_NTP_OFFSET, ntpdata->time_offset); + audit_ntp_set_old(ad, AUDIT_NTP_FREQ, ntpdata->time_freq); + audit_ntp_set_old(ad, AUDIT_NTP_STATUS, ntpdata->time_status); audit_ntp_set_old(ad, AUDIT_NTP_TAI, *time_tai); - audit_ntp_set_old(ad, AUDIT_NTP_TICK, tick_usec); + audit_ntp_set_old(ad, AUDIT_NTP_TICK, ntpdata->tick_usec); - process_adjtimex_modes(txc, time_tai); + process_adjtimex_modes(ntpdata, txc, time_tai); - audit_ntp_set_new(ad, AUDIT_NTP_OFFSET, time_offset); - audit_ntp_set_new(ad, AUDIT_NTP_FREQ, time_freq); - audit_ntp_set_new(ad, AUDIT_NTP_STATUS, time_status); + audit_ntp_set_new(ad, AUDIT_NTP_OFFSET, ntpdata->time_offset); + audit_ntp_set_new(ad, AUDIT_NTP_FREQ, ntpdata->time_freq); + audit_ntp_set_new(ad, AUDIT_NTP_STATUS, ntpdata->time_status); audit_ntp_set_new(ad, AUDIT_NTP_TAI, *time_tai); - audit_ntp_set_new(ad, AUDIT_NTP_TICK, tick_usec); + audit_ntp_set_new(ad, AUDIT_NTP_TICK, ntpdata->tick_usec); } - txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, - NTP_SCALE_SHIFT); - if (!(time_status & STA_NANO)) + txc->offset = shift_right(ntpdata->time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); + if (!(ntpdata->time_status & STA_NANO)) txc->offset = (u32)txc->offset / NSEC_PER_USEC; } - result = time_state; /* mostly `TIME_OK' */ - /* check for errors */ - if (is_error_status(time_status)) + result = ntpdata->time_state; + if (is_error_status(ntpdata->time_status)) result = TIME_ERROR; - txc->freq = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) * + txc->freq = shift_right((ntpdata->time_freq >> PPM_SCALE_INV_SHIFT) * PPM_SCALE_INV, NTP_SCALE_SHIFT); - txc->maxerror = time_maxerror; - txc->esterror = time_esterror; - txc->status = time_status; - txc->constant = time_constant; + txc->maxerror = ntpdata->time_maxerror; + txc->esterror = ntpdata->time_esterror; + txc->status = ntpdata->time_status; + txc->constant = ntpdata->time_constant; txc->precision = 1; txc->tolerance = MAXFREQ_SCALED / PPM_SCALE; - txc->tick = tick_usec; + txc->tick = ntpdata->tick_usec; txc->tai = *time_tai; - /* fill PPS status fields */ - pps_fill_timex(txc); + /* Fill PPS status fields */ + pps_fill_timex(ntpdata, txc); txc->time.tv_sec = ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; - if (!(time_status & STA_NANO)) + if (!(ntpdata->time_status & STA_NANO)) txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC; /* Handle leapsec adjustments */ - if (unlikely(ts->tv_sec >= ntp_next_leap_sec)) { - if ((time_state == TIME_INS) && (time_status & STA_INS)) { + if (unlikely(ts->tv_sec >= ntpdata->ntp_next_leap_sec)) { + if ((ntpdata->time_state == TIME_INS) && (ntpdata->time_status & STA_INS)) { result = TIME_OOP; txc->tai++; txc->time.tv_sec--; } - if ((time_state == TIME_DEL) && (time_status & STA_DEL)) { + if ((ntpdata->time_state == TIME_DEL) && (ntpdata->time_status & STA_DEL)) { result = TIME_WAIT; txc->tai--; txc->time.tv_sec++; } - if ((time_state == TIME_OOP) && - (ts->tv_sec == ntp_next_leap_sec)) { + if ((ntpdata->time_state == TIME_OOP) && (ts->tv_sec == ntpdata->ntp_next_leap_sec)) result = TIME_WAIT; - } } return result; @@ -854,17 +845,21 @@ int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, #ifdef CONFIG_NTP_PPS -/* actually struct pps_normtime is good old struct timespec, but it is +/* + * struct pps_normtime is basically a struct timespec, but it is * semantically different (and it is the reason why it was invented): * pps_normtime.nsec has a range of ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] - * while timespec.tv_nsec has a range of [0, NSEC_PER_SEC) */ + * while timespec.tv_nsec has a range of [0, NSEC_PER_SEC) + */ struct pps_normtime { s64 sec; /* seconds */ long nsec; /* nanoseconds */ }; -/* normalize the timestamp so that nsec is in the - ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] interval */ +/* + * Normalize the timestamp so that nsec is in the + * [ -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] interval + */ static inline struct pps_normtime pps_normalize_ts(struct timespec64 ts) { struct pps_normtime norm = { @@ -880,54 +875,57 @@ static inline struct pps_normtime pps_normalize_ts(struct timespec64 ts) return norm; } -/* get current phase correction and jitter */ -static inline long pps_phase_filter_get(long *jitter) +/* Get current phase correction and jitter */ +static inline long pps_phase_filter_get(struct ntp_data *ntpdata, long *jitter) { - *jitter = pps_tf[0] - pps_tf[1]; + *jitter = ntpdata->pps_tf[0] - ntpdata->pps_tf[1]; if (*jitter < 0) *jitter = -*jitter; /* TODO: test various filters */ - return pps_tf[0]; + return ntpdata->pps_tf[0]; } -/* add the sample to the phase filter */ -static inline void pps_phase_filter_add(long err) +/* Add the sample to the phase filter */ +static inline void pps_phase_filter_add(struct ntp_data *ntpdata, long err) { - pps_tf[2] = pps_tf[1]; - pps_tf[1] = pps_tf[0]; - pps_tf[0] = err; + ntpdata->pps_tf[2] = ntpdata->pps_tf[1]; + ntpdata->pps_tf[1] = ntpdata->pps_tf[0]; + ntpdata->pps_tf[0] = err; } -/* decrease frequency calibration interval length. - * It is halved after four consecutive unstable intervals. +/* + * Decrease frequency calibration interval length. It is halved after four + * consecutive unstable intervals. */ -static inline void pps_dec_freq_interval(void) +static inline void pps_dec_freq_interval(struct ntp_data *ntpdata) { - if (--pps_intcnt <= -PPS_INTCOUNT) { - pps_intcnt = -PPS_INTCOUNT; - if (pps_shift > PPS_INTMIN) { - pps_shift--; - pps_intcnt = 0; + if (--ntpdata->pps_intcnt <= -PPS_INTCOUNT) { + ntpdata->pps_intcnt = -PPS_INTCOUNT; + if (ntpdata->pps_shift > PPS_INTMIN) { + ntpdata->pps_shift--; + ntpdata->pps_intcnt = 0; } } } -/* increase frequency calibration interval length. - * It is doubled after four consecutive stable intervals. +/* + * Increase frequency calibration interval length. It is doubled after + * four consecutive stable intervals. */ -static inline void pps_inc_freq_interval(void) +static inline void pps_inc_freq_interval(struct ntp_data *ntpdata) { - if (++pps_intcnt >= PPS_INTCOUNT) { - pps_intcnt = PPS_INTCOUNT; - if (pps_shift < PPS_INTMAX) { - pps_shift++; - pps_intcnt = 0; + if (++ntpdata->pps_intcnt >= PPS_INTCOUNT) { + ntpdata->pps_intcnt = PPS_INTCOUNT; + if (ntpdata->pps_shift < PPS_INTMAX) { + ntpdata->pps_shift++; + ntpdata->pps_intcnt = 0; } } } -/* update clock frequency based on MONOTONIC_RAW clock PPS signal +/* + * Update clock frequency based on MONOTONIC_RAW clock PPS signal * timestamps * * At the end of the calibration interval the difference between the @@ -936,90 +934,88 @@ static inline void pps_inc_freq_interval(void) * too long, the data are discarded. * Returns the difference between old and new frequency values. */ -static long hardpps_update_freq(struct pps_normtime freq_norm) +static long hardpps_update_freq(struct ntp_data *ntpdata, struct pps_normtime freq_norm) { long delta, delta_mod; s64 ftemp; - /* check if the frequency interval was too long */ - if (freq_norm.sec > (2 << pps_shift)) { - time_status |= STA_PPSERROR; - pps_errcnt++; - pps_dec_freq_interval(); - printk_deferred(KERN_ERR - "hardpps: PPSERROR: interval too long - %lld s\n", - freq_norm.sec); + /* Check if the frequency interval was too long */ + if (freq_norm.sec > (2 << ntpdata->pps_shift)) { + ntpdata->time_status |= STA_PPSERROR; + ntpdata->pps_errcnt++; + pps_dec_freq_interval(ntpdata); + printk_deferred(KERN_ERR "hardpps: PPSERROR: interval too long - %lld s\n", + freq_norm.sec); return 0; } - /* here the raw frequency offset and wander (stability) is - * calculated. If the wander is less than the wander threshold - * the interval is increased; otherwise it is decreased. + /* + * Here the raw frequency offset and wander (stability) is + * calculated. If the wander is less than the wander threshold the + * interval is increased; otherwise it is decreased. */ ftemp = div_s64(((s64)(-freq_norm.nsec)) << NTP_SCALE_SHIFT, freq_norm.sec); - delta = shift_right(ftemp - pps_freq, NTP_SCALE_SHIFT); - pps_freq = ftemp; + delta = shift_right(ftemp - ntpdata->pps_freq, NTP_SCALE_SHIFT); + ntpdata->pps_freq = ftemp; if (delta > PPS_MAXWANDER || delta < -PPS_MAXWANDER) { - printk_deferred(KERN_WARNING - "hardpps: PPSWANDER: change=%ld\n", delta); - time_status |= STA_PPSWANDER; - pps_stbcnt++; - pps_dec_freq_interval(); - } else { /* good sample */ - pps_inc_freq_interval(); + printk_deferred(KERN_WARNING "hardpps: PPSWANDER: change=%ld\n", delta); + ntpdata->time_status |= STA_PPSWANDER; + ntpdata->pps_stbcnt++; + pps_dec_freq_interval(ntpdata); + } else { + /* Good sample */ + pps_inc_freq_interval(ntpdata); } - /* the stability metric is calculated as the average of recent - * frequency changes, but is used only for performance - * monitoring + /* + * The stability metric is calculated as the average of recent + * frequency changes, but is used only for performance monitoring */ delta_mod = delta; if (delta_mod < 0) delta_mod = -delta_mod; - pps_stabil += (div_s64(((s64)delta_mod) << - (NTP_SCALE_SHIFT - SHIFT_USEC), - NSEC_PER_USEC) - pps_stabil) >> PPS_INTMIN; - - /* if enabled, the system clock frequency is updated */ - if ((time_status & STA_PPSFREQ) != 0 && - (time_status & STA_FREQHOLD) == 0) { - time_freq = pps_freq; - ntp_update_frequency(); + ntpdata->pps_stabil += (div_s64(((s64)delta_mod) << (NTP_SCALE_SHIFT - SHIFT_USEC), + NSEC_PER_USEC) - ntpdata->pps_stabil) >> PPS_INTMIN; + + /* If enabled, the system clock frequency is updated */ + if ((ntpdata->time_status & STA_PPSFREQ) && !(ntpdata->time_status & STA_FREQHOLD)) { + ntpdata->time_freq = ntpdata->pps_freq; + ntp_update_frequency(ntpdata); } return delta; } -/* correct REALTIME clock phase error against PPS signal */ -static void hardpps_update_phase(long error) +/* Correct REALTIME clock phase error against PPS signal */ +static void hardpps_update_phase(struct ntp_data *ntpdata, long error) { long correction = -error; long jitter; - /* add the sample to the median filter */ - pps_phase_filter_add(correction); - correction = pps_phase_filter_get(&jitter); + /* Add the sample to the median filter */ + pps_phase_filter_add(ntpdata, correction); + correction = pps_phase_filter_get(ntpdata, &jitter); - /* Nominal jitter is due to PPS signal noise. If it exceeds the + /* + * Nominal jitter is due to PPS signal noise. If it exceeds the * threshold, the sample is discarded; otherwise, if so enabled, * the time offset is updated. */ - if (jitter > (pps_jitter << PPS_POPCORN)) { - printk_deferred(KERN_WARNING - "hardpps: PPSJITTER: jitter=%ld, limit=%ld\n", - jitter, (pps_jitter << PPS_POPCORN)); - time_status |= STA_PPSJITTER; - pps_jitcnt++; - } else if (time_status & STA_PPSTIME) { - /* correct the time using the phase offset */ - time_offset = div_s64(((s64)correction) << NTP_SCALE_SHIFT, - NTP_INTERVAL_FREQ); - /* cancel running adjtime() */ - time_adjust = 0; + if (jitter > (ntpdata->pps_jitter << PPS_POPCORN)) { + printk_deferred(KERN_WARNING "hardpps: PPSJITTER: jitter=%ld, limit=%ld\n", + jitter, (ntpdata->pps_jitter << PPS_POPCORN)); + ntpdata->time_status |= STA_PPSJITTER; + ntpdata->pps_jitcnt++; + } else if (ntpdata->time_status & STA_PPSTIME) { + /* Correct the time using the phase offset */ + ntpdata->time_offset = div_s64(((s64)correction) << NTP_SCALE_SHIFT, + NTP_INTERVAL_FREQ); + /* Cancel running adjtime() */ + ntpdata->time_adjust = 0; } - /* update jitter */ - pps_jitter += (jitter - pps_jitter) >> PPS_INTMIN; + /* Update jitter */ + ntpdata->pps_jitter += (jitter - ntpdata->pps_jitter) >> PPS_INTMIN; } /* @@ -1037,60 +1033,62 @@ static void hardpps_update_phase(long error) void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { struct pps_normtime pts_norm, freq_norm; + struct ntp_data *ntpdata = &tk_ntp_data; pts_norm = pps_normalize_ts(*phase_ts); - /* clear the error bits, they will be set again if needed */ - time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); + /* Clear the error bits, they will be set again if needed */ + ntpdata->time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); /* indicate signal presence */ - time_status |= STA_PPSSIGNAL; - pps_valid = PPS_VALID; + ntpdata->time_status |= STA_PPSSIGNAL; + ntpdata->pps_valid = PPS_VALID; - /* when called for the first time, - * just start the frequency interval */ - if (unlikely(pps_fbase.tv_sec == 0)) { - pps_fbase = *raw_ts; + /* + * When called for the first time, just start the frequency + * interval + */ + if (unlikely(ntpdata->pps_fbase.tv_sec == 0)) { + ntpdata->pps_fbase = *raw_ts; return; } - /* ok, now we have a base for frequency calculation */ - freq_norm = pps_normalize_ts(timespec64_sub(*raw_ts, pps_fbase)); - - /* check that the signal is in the range - * [1s - MAXFREQ us, 1s + MAXFREQ us], otherwise reject it */ - if ((freq_norm.sec == 0) || - (freq_norm.nsec > MAXFREQ * freq_norm.sec) || - (freq_norm.nsec < -MAXFREQ * freq_norm.sec)) { - time_status |= STA_PPSJITTER; - /* restart the frequency calibration interval */ - pps_fbase = *raw_ts; + /* Ok, now we have a base for frequency calculation */ + freq_norm = pps_normalize_ts(timespec64_sub(*raw_ts, ntpdata->pps_fbase)); + + /* + * Check that the signal is in the range + * [1s - MAXFREQ us, 1s + MAXFREQ us], otherwise reject it + */ + if ((freq_norm.sec == 0) || (freq_norm.nsec > MAXFREQ * freq_norm.sec) || + (freq_norm.nsec < -MAXFREQ * freq_norm.sec)) { + ntpdata->time_status |= STA_PPSJITTER; + /* Restart the frequency calibration interval */ + ntpdata->pps_fbase = *raw_ts; printk_deferred(KERN_ERR "hardpps: PPSJITTER: bad pulse\n"); return; } - /* signal is ok */ - - /* check if the current frequency interval is finished */ - if (freq_norm.sec >= (1 << pps_shift)) { - pps_calcnt++; - /* restart the frequency calibration interval */ - pps_fbase = *raw_ts; - hardpps_update_freq(freq_norm); + /* Signal is ok. Check if the current frequency interval is finished */ + if (freq_norm.sec >= (1 << ntpdata->pps_shift)) { + ntpdata->pps_calcnt++; + /* Restart the frequency calibration interval */ + ntpdata->pps_fbase = *raw_ts; + hardpps_update_freq(ntpdata, freq_norm); } - hardpps_update_phase(pts_norm.nsec); + hardpps_update_phase(ntpdata, pts_norm.nsec); } #endif /* CONFIG_NTP_PPS */ static int __init ntp_tick_adj_setup(char *str) { - int rc = kstrtos64(str, 0, &ntp_tick_adj); + int rc = kstrtos64(str, 0, &tk_ntp_data.ntp_tick_adj); if (rc) return rc; - ntp_tick_adj <<= NTP_SCALE_SHIFT; + tk_ntp_data.ntp_tick_adj <<= NTP_SCALE_SHIFT; return 1; } diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 6bcee4704059..50e8d04ab661 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -453,7 +453,6 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) struct cpu_timer *ctmr = &timer->it.cpu; struct posix_cputimer_base *base; - timer->it_active = 0; if (!cpu_timer_dequeue(ctmr)) return; @@ -494,19 +493,28 @@ static int posix_cpu_timer_del(struct k_itimer *timer) */ WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); } else { - if (timer->it.cpu.firing) + if (timer->it.cpu.firing) { + /* + * Prevent signal delivery. The timer cannot be dequeued + * because it is on the firing list which is not protected + * by sighand->lock. The delivery path is waiting for + * the timer lock. So go back, unlock and retry. + */ + timer->it.cpu.firing = false; ret = TIMER_RETRY; - else + } else { disarm_timer(timer, p); - + } unlock_task_sighand(p, &flags); } out: rcu_read_unlock(); - if (!ret) - put_pid(ctmr->pid); + if (!ret) { + put_pid(ctmr->pid); + timer->it_status = POSIX_TIMER_DISARMED; + } return ret; } @@ -560,7 +568,7 @@ static void arm_timer(struct k_itimer *timer, struct task_struct *p) struct cpu_timer *ctmr = &timer->it.cpu; u64 newexp = cpu_timer_getexpires(ctmr); - timer->it_active = 1; + timer->it_status = POSIX_TIMER_ARMED; if (!cpu_timer_enqueue(&base->tqhead, ctmr)) return; @@ -586,29 +594,20 @@ static void cpu_timer_fire(struct k_itimer *timer) { struct cpu_timer *ctmr = &timer->it.cpu; - timer->it_active = 0; - if (unlikely(timer->sigq == NULL)) { + timer->it_status = POSIX_TIMER_DISARMED; + + if (unlikely(ctmr->nanosleep)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. */ wake_up_process(timer->it_process); cpu_timer_setexpires(ctmr, 0); - } else if (!timer->it_interval) { - /* - * One-shot timer. Clear it as soon as it's fired. - */ + } else { posix_timer_queue_signal(timer); - cpu_timer_setexpires(ctmr, 0); - } else if (posix_timer_queue_signal(timer)) { - /* - * The signal did not get queued because the signal - * was ignored, so we won't get any callback to - * reload the timer. But we need to keep it - * ticking in case the signal is deliverable next time. - */ - posix_cpu_timer_rearm(timer); - ++timer->it_requeue_pending; + /* Disable oneshot timers */ + if (!timer->it_interval) + cpu_timer_setexpires(ctmr, 0); } } @@ -667,11 +666,17 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, old_expires = cpu_timer_getexpires(ctmr); if (unlikely(timer->it.cpu.firing)) { - timer->it.cpu.firing = -1; + /* + * Prevent signal delivery. The timer cannot be dequeued + * because it is on the firing list which is not protected + * by sighand->lock. The delivery path is waiting for + * the timer lock. So go back, unlock and retry. + */ + timer->it.cpu.firing = false; ret = TIMER_RETRY; } else { cpu_timer_dequeue(ctmr); - timer->it_active = 0; + timer->it_status = POSIX_TIMER_DISARMED; } /* @@ -745,7 +750,7 @@ static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *i * - Timers which expired, but the signal has not yet been * delivered */ - if (iv && ((timer->it_requeue_pending & REQUEUE_PENDING) || sigev_none)) + if (iv && timer->it_status != POSIX_TIMER_ARMED) expires = bump_cpu_timer(timer, now); else expires = cpu_timer_getexpires(&timer->it.cpu); @@ -808,7 +813,7 @@ static u64 collect_timerqueue(struct timerqueue_head *head, if (++i == MAX_COLLECTED || now < expires) return expires; - ctmr->firing = 1; + ctmr->firing = true; /* See posix_cpu_timer_wait_running() */ rcu_assign_pointer(ctmr->handling, current); cpu_timer_dequeue(ctmr); @@ -1363,7 +1368,7 @@ static void handle_posix_cpu_timers(struct task_struct *tsk) * timer call will interfere. */ list_for_each_entry_safe(timer, next, &firing, it.cpu.elist) { - int cpu_firing; + bool cpu_firing; /* * spin_lock() is sufficient here even independent of the @@ -1375,13 +1380,13 @@ static void handle_posix_cpu_timers(struct task_struct *tsk) spin_lock(&timer->it_lock); list_del_init(&timer->it.cpu.elist); cpu_firing = timer->it.cpu.firing; - timer->it.cpu.firing = 0; + timer->it.cpu.firing = false; /* - * The firing flag is -1 if we collided with a reset - * of the timer, which already reported this - * almost-firing as an overrun. So don't generate an event. + * If the firing flag is cleared then this raced with a + * timer rearm/delete operation. So don't generate an + * event. */ - if (likely(cpu_firing >= 0)) + if (likely(cpu_firing)) cpu_timer_fire(timer); /* See posix_cpu_timer_wait_running() */ rcu_assign_pointer(timer->it.cpu.handling, NULL); @@ -1478,6 +1483,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, timer.it_overrun = -1; error = posix_cpu_timer_create(&timer); timer.it_process = current; + timer.it.cpu.nanosleep = true; if (!error) { static struct itimerspec64 zero_it; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 4576aaed13b2..881a9ce96af7 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -233,11 +233,12 @@ __initcall(init_posix_timers); * The siginfo si_overrun field and the return value of timer_getoverrun(2) * are of type int. Clamp the overrun value to INT_MAX */ -static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval) +static inline int timer_overrun_to_int(struct k_itimer *timr) { - s64 sum = timr->it_overrun_last + (s64)baseval; + if (timr->it_overrun_last > (s64)INT_MAX) + return INT_MAX; - return sum > (s64)INT_MAX ? INT_MAX : (int)sum; + return (int)timr->it_overrun_last; } static void common_hrtimer_rearm(struct k_itimer *timr) @@ -249,62 +250,62 @@ static void common_hrtimer_rearm(struct k_itimer *timr) hrtimer_restart(timer); } +static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_itimer *timr) +{ + guard(spinlock)(&timr->it_lock); + + /* + * Check if the timer is still alive or whether it got modified + * since the signal was queued. In either case, don't rearm and + * drop the signal. + */ + if (timr->it_signal_seq != timr->it_sigqueue_seq || WARN_ON_ONCE(!timr->it_signal)) + return false; + + if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) + return true; + + timr->kclock->timer_rearm(timr); + timr->it_status = POSIX_TIMER_ARMED; + timr->it_overrun_last = timr->it_overrun; + timr->it_overrun = -1LL; + ++timr->it_signal_seq; + info->si_overrun = timer_overrun_to_int(timr); + return true; +} + /* - * This function is called from the signal delivery code if - * info->si_sys_private is not zero, which indicates that the timer has to - * be rearmed. Restart the timer and update info::si_overrun. + * This function is called from the signal delivery code. It decides + * whether the signal should be dropped and rearms interval timers. The + * timer can be unconditionally accessed as there is a reference held on + * it. */ -void posixtimer_rearm(struct kernel_siginfo *info) +bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { - struct k_itimer *timr; - unsigned long flags; - - timr = lock_timer(info->si_tid, &flags); - if (!timr) - return; + struct k_itimer *timr = container_of(timer_sigq, struct k_itimer, sigq); + bool ret; - if (timr->it_interval && timr->it_requeue_pending == info->si_sys_private) { - timr->kclock->timer_rearm(timr); + /* + * Release siglock to ensure proper locking order versus + * timr::it_lock. Keep interrupts disabled. + */ + spin_unlock(¤t->sighand->siglock); - timr->it_active = 1; - timr->it_overrun_last = timr->it_overrun; - timr->it_overrun = -1LL; - ++timr->it_requeue_pending; + ret = __posixtimer_deliver_signal(info, timr); - info->si_overrun = timer_overrun_to_int(timr, info->si_overrun); - } + /* Drop the reference which was acquired when the signal was queued */ + posixtimer_putref(timr); - unlock_timer(timr, flags); + spin_lock(¤t->sighand->siglock); + return ret; } -int posix_timer_queue_signal(struct k_itimer *timr) +void posix_timer_queue_signal(struct k_itimer *timr) { - int ret, si_private = 0; - enum pid_type type; - lockdep_assert_held(&timr->it_lock); - timr->it_active = 0; - if (timr->it_interval) - si_private = ++timr->it_requeue_pending; - - /* - * FIXME: if ->sigq is queued we can race with - * dequeue_signal()->posixtimer_rearm(). - * - * If dequeue_signal() sees the "right" value of - * si_sys_private it calls posixtimer_rearm(). - * We re-queue ->sigq and drop ->it_lock(). - * posixtimer_rearm() locks the timer - * and re-schedules it while ->sigq is pending. - * Not really bad, but not that we want. - */ - timr->sigq->info.si_sys_private = si_private; - - type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID; - ret = send_sigqueue(timr->sigq, timr->it_pid, type); - /* If we failed to send the signal the timer stops. */ - return ret > 0; + timr->it_status = timr->it_interval ? POSIX_TIMER_REQUEUE_PENDING : POSIX_TIMER_DISARMED; + posixtimer_send_sigqueue(timr); } /* @@ -317,62 +318,10 @@ int posix_timer_queue_signal(struct k_itimer *timr) static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) { struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer); - enum hrtimer_restart ret = HRTIMER_NORESTART; - unsigned long flags; - - spin_lock_irqsave(&timr->it_lock, flags); - - if (posix_timer_queue_signal(timr)) { - /* - * The signal was not queued due to SIG_IGN. As a - * consequence the timer is not going to be rearmed from - * the signal delivery path. But as a real signal handler - * can be installed later the timer must be rearmed here. - */ - if (timr->it_interval != 0) { - ktime_t now = hrtimer_cb_get_time(timer); - - /* - * FIXME: What we really want, is to stop this - * timer completely and restart it in case the - * SIG_IGN is removed. This is a non trivial - * change to the signal handling code. - * - * For now let timers with an interval less than a - * jiffy expire every jiffy and recheck for a - * valid signal handler. - * - * This avoids interrupt starvation in case of a - * very small interval, which would expire the - * timer immediately again. - * - * Moving now ahead of time by one jiffy tricks - * hrtimer_forward() to expire the timer later, - * while it still maintains the overrun accuracy - * for the price of a slight inconsistency in the - * timer_gettime() case. This is at least better - * than a timer storm. - * - * Only required when high resolution timers are - * enabled as the periodic tick based timers are - * automatically aligned to the next tick. - */ - if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS)) { - ktime_t kj = TICK_NSEC; - - if (timr->it_interval < kj) - now = ktime_add(now, kj); - } - - timr->it_overrun += hrtimer_forward(timer, now, timr->it_interval); - ret = HRTIMER_RESTART; - ++timr->it_requeue_pending; - timr->it_active = 1; - } - } - unlock_timer(timr, flags); - return ret; + guard(spinlock_irqsave)(&timr->it_lock); + posix_timer_queue_signal(timr); + return HRTIMER_NORESTART; } static struct pid *good_sigevent(sigevent_t * event) @@ -399,32 +348,27 @@ static struct pid *good_sigevent(sigevent_t * event) } } -static struct k_itimer * alloc_posix_timer(void) +static struct k_itimer *alloc_posix_timer(void) { struct k_itimer *tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); if (!tmr) return tmr; - if (unlikely(!(tmr->sigq = sigqueue_alloc()))) { + + if (unlikely(!posixtimer_init_sigqueue(&tmr->sigq))) { kmem_cache_free(posix_timers_cache, tmr); return NULL; } - clear_siginfo(&tmr->sigq->info); + rcuref_init(&tmr->rcuref, 1); return tmr; } -static void k_itimer_rcu_free(struct rcu_head *head) -{ - struct k_itimer *tmr = container_of(head, struct k_itimer, rcu); - - kmem_cache_free(posix_timers_cache, tmr); -} - -static void posix_timer_free(struct k_itimer *tmr) +void posixtimer_free_timer(struct k_itimer *tmr) { put_pid(tmr->it_pid); - sigqueue_free(tmr->sigq); - call_rcu(&tmr->rcu, k_itimer_rcu_free); + if (tmr->sigq.ucounts) + dec_rlimit_put_ucounts(tmr->sigq.ucounts, UCOUNT_RLIMIT_SIGPENDING); + kfree_rcu(tmr, rcu); } static void posix_timer_unhash_and_free(struct k_itimer *tmr) @@ -432,7 +376,7 @@ static void posix_timer_unhash_and_free(struct k_itimer *tmr) spin_lock(&hash_lock); hlist_del_rcu(&tmr->t_hash); spin_unlock(&hash_lock); - posix_timer_free(tmr); + posixtimer_putref(tmr); } static int common_timer_create(struct k_itimer *new_timer) @@ -467,7 +411,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, */ new_timer_id = posix_timer_add(new_timer); if (new_timer_id < 0) { - posix_timer_free(new_timer); + posixtimer_free_timer(new_timer); return new_timer_id; } @@ -485,18 +429,23 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, goto out; } new_timer->it_sigev_notify = event->sigev_notify; - new_timer->sigq->info.si_signo = event->sigev_signo; - new_timer->sigq->info.si_value = event->sigev_value; + new_timer->sigq.info.si_signo = event->sigev_signo; + new_timer->sigq.info.si_value = event->sigev_value; } else { new_timer->it_sigev_notify = SIGEV_SIGNAL; - new_timer->sigq->info.si_signo = SIGALRM; - memset(&new_timer->sigq->info.si_value, 0, sizeof(sigval_t)); - new_timer->sigq->info.si_value.sival_int = new_timer->it_id; + new_timer->sigq.info.si_signo = SIGALRM; + memset(&new_timer->sigq.info.si_value, 0, sizeof(sigval_t)); + new_timer->sigq.info.si_value.sival_int = new_timer->it_id; new_timer->it_pid = get_pid(task_tgid(current)); } - new_timer->sigq->info.si_tid = new_timer->it_id; - new_timer->sigq->info.si_code = SI_TIMER; + if (new_timer->it_sigev_notify & SIGEV_THREAD_ID) + new_timer->it_pid_type = PIDTYPE_PID; + else + new_timer->it_pid_type = PIDTYPE_TGID; + + new_timer->sigq.info.si_tid = new_timer->it_id; + new_timer->sigq.info.si_code = SI_TIMER; if (copy_to_user(created_timer_id, &new_timer_id, sizeof (new_timer_id))) { error = -EFAULT; @@ -580,7 +529,14 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) * 1) Set timr::it_signal to NULL with timr::it_lock held * 2) Release timr::it_lock * 3) Remove from the hash under hash_lock - * 4) Call RCU for removal after the grace period + * 4) Put the reference count. + * + * The reference count might not drop to zero if timr::sigq is + * queued. In that case the signal delivery or flush will put the + * last reference count. + * + * When the reference count reaches zero, the timer is scheduled + * for RCU removal after the grace period. * * Holding rcu_read_lock() accross the lookup ensures that * the timer cannot be freed. @@ -647,10 +603,10 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) /* interval timer ? */ if (iv) { cur_setting->it_interval = ktime_to_timespec64(iv); - } else if (!timr->it_active) { + } else if (timr->it_status == POSIX_TIMER_DISARMED) { /* * SIGEV_NONE oneshot timers are never queued and therefore - * timr->it_active is always false. The check below + * timr->it_status is always DISARMED. The check below * vs. remaining time will handle this case. * * For all other timers there is nothing to update here, so @@ -667,7 +623,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) * is a SIGEV_NONE timer move the expiry time forward by intervals, * so expiry is > now. */ - if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none)) + if (iv && timr->it_status != POSIX_TIMER_ARMED) timr->it_overrun += kc->timer_forward(timr, now); remaining = kc->timer_remaining(timr, now); @@ -775,7 +731,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) if (!timr) return -EINVAL; - overrun = timer_overrun_to_int(timr, 0); + overrun = timer_overrun_to_int(timr); unlock_timer(timr, flags); return overrun; @@ -867,8 +823,6 @@ void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_set else timer->it_interval = 0; - /* Prevent reloading in case there is a signal pending */ - timer->it_requeue_pending = (timer->it_requeue_pending + 2) & ~REQUEUE_PENDING; /* Reset overrun accounting */ timer->it_overrun_last = 0; timer->it_overrun = -1LL; @@ -886,8 +840,6 @@ int common_timer_set(struct k_itimer *timr, int flags, if (old_setting) common_timer_get(timr, old_setting); - /* Prevent rearming by clearing the interval */ - timr->it_interval = 0; /* * Careful here. On SMP systems the timer expiry function could be * active and spinning on timr->it_lock. @@ -895,7 +847,7 @@ int common_timer_set(struct k_itimer *timr, int flags, if (kc->timer_try_to_cancel(timr) < 0) return TIMER_RETRY; - timr->it_active = 0; + timr->it_status = POSIX_TIMER_DISARMED; posix_timer_set_common(timr, new_setting); /* Keep timer disarmed when it_value is zero */ @@ -908,7 +860,8 @@ int common_timer_set(struct k_itimer *timr, int flags, sigev_none = timr->it_sigev_notify == SIGEV_NONE; kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); - timr->it_active = !sigev_none; + if (!sigev_none) + timr->it_status = POSIX_TIMER_ARMED; return 0; } @@ -936,6 +889,9 @@ retry: if (old_spec64) old_spec64->it_interval = ktime_to_timespec64(timr->it_interval); + /* Prevent signal delivery and rearming. */ + timr->it_signal_seq++; + kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; @@ -1004,17 +960,31 @@ int common_timer_del(struct k_itimer *timer) { const struct k_clock *kc = timer->kclock; - timer->it_interval = 0; if (kc->timer_try_to_cancel(timer) < 0) return TIMER_RETRY; - timer->it_active = 0; + timer->it_status = POSIX_TIMER_DISARMED; return 0; } +/* + * If the deleted timer is on the ignored list, remove it and + * drop the associated reference. + */ +static inline void posix_timer_cleanup_ignored(struct k_itimer *tmr) +{ + if (!hlist_unhashed(&tmr->ignored_list)) { + hlist_del_init(&tmr->ignored_list); + posixtimer_putref(tmr); + } +} + static inline int timer_delete_hook(struct k_itimer *timer) { const struct k_clock *kc = timer->kclock; + /* Prevent signal delivery and rearming. */ + timer->it_signal_seq++; + if (WARN_ON_ONCE(!kc || !kc->timer_del)) return -EINVAL; return kc->timer_del(timer); @@ -1040,12 +1010,18 @@ retry_delete: spin_lock(¤t->sighand->siglock); hlist_del(&timer->list); - spin_unlock(¤t->sighand->siglock); + posix_timer_cleanup_ignored(timer); /* * A concurrent lookup could check timer::it_signal lockless. It * will reevaluate with timer::it_lock held and observe the NULL. + * + * It must be written with siglock held so that the signal code + * observes timer->it_signal == NULL in do_sigaction(SIG_IGN), + * which prevents it from moving a pending signal of a deleted + * timer to the ignore list. */ WRITE_ONCE(timer->it_signal, NULL); + spin_unlock(¤t->sighand->siglock); unlock_timer(timer, flags); posix_timer_unhash_and_free(timer); @@ -1091,6 +1067,8 @@ retry_delete: } hlist_del(&timer->list); + posix_timer_cleanup_ignored(timer); + /* * Setting timer::it_signal to NULL is technically not required * here as nothing can access the timer anymore legitimately via @@ -1123,6 +1101,19 @@ void exit_itimers(struct task_struct *tsk) /* The timers are not longer accessible via tsk::signal */ while (!hlist_empty(&timers)) itimer_delete(hlist_entry(timers.first, struct k_itimer, list)); + + /* + * There should be no timers on the ignored list. itimer_delete() has + * mopped them up. + */ + if (!WARN_ON_ONCE(!hlist_empty(&tsk->signal->ignored_posix_timers))) + return; + + hlist_move_list(&tsk->signal->ignored_posix_timers, &timers); + while (!hlist_empty(&timers)) { + posix_timer_cleanup_ignored(hlist_entry(timers.first, struct k_itimer, + ignored_list)); + } } SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 4784ea65f685..61906f0688c1 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -1,6 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ #define TIMER_RETRY 1 +enum posix_timer_state { + POSIX_TIMER_DISARMED, + POSIX_TIMER_ARMED, + POSIX_TIMER_REQUEUE_PENDING, +}; + struct k_clock { int (*clock_getres)(const clockid_t which_clock, struct timespec64 *tp); @@ -36,7 +42,7 @@ extern const struct k_clock clock_process; extern const struct k_clock clock_thread; extern const struct k_clock alarm_clock; -int posix_timer_queue_signal(struct k_itimer *timr); +void posix_timer_queue_signal(struct k_itimer *timr); void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting); int common_timer_set(struct k_itimer *timr, int flags, diff --git a/kernel/time/sleep_timeout.c b/kernel/time/sleep_timeout.c new file mode 100644 index 000000000000..dfe939f6e4ec --- /dev/null +++ b/kernel/time/sleep_timeout.c @@ -0,0 +1,377 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Kernel internal schedule timeout and sleeping functions + */ + +#include <linux/delay.h> +#include <linux/jiffies.h> +#include <linux/timer.h> +#include <linux/sched/signal.h> +#include <linux/sched/debug.h> + +#include "tick-internal.h" + +/* + * Since schedule_timeout()'s timer is defined on the stack, it must store + * the target task on the stack as well. + */ +struct process_timer { + struct timer_list timer; + struct task_struct *task; +}; + +static void process_timeout(struct timer_list *t) +{ + struct process_timer *timeout = from_timer(timeout, t, timer); + + wake_up_process(timeout->task); +} + +/** + * schedule_timeout - sleep until timeout + * @timeout: timeout value in jiffies + * + * Make the current task sleep until @timeout jiffies have elapsed. + * The function behavior depends on the current task state + * (see also set_current_state() description): + * + * %TASK_RUNNING - the scheduler is called, but the task does not sleep + * at all. That happens because sched_submit_work() does nothing for + * tasks in %TASK_RUNNING state. + * + * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to + * pass before the routine returns unless the current task is explicitly + * woken up, (e.g. by wake_up_process()). + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task or the current task is explicitly woken + * up. + * + * The current task state is guaranteed to be %TASK_RUNNING when this + * routine returns. + * + * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule + * the CPU away without a bound on the timeout. In this case the return + * value will be %MAX_SCHEDULE_TIMEOUT. + * + * Returns: 0 when the timer has expired otherwise the remaining time in + * jiffies will be returned. In all cases the return value is guaranteed + * to be non-negative. + */ +signed long __sched schedule_timeout(signed long timeout) +{ + struct process_timer timer; + unsigned long expire; + + switch (timeout) { + case MAX_SCHEDULE_TIMEOUT: + /* + * These two special cases are useful to be comfortable + * in the caller. Nothing more. We could take + * MAX_SCHEDULE_TIMEOUT from one of the negative value + * but I' d like to return a valid offset (>=0) to allow + * the caller to do everything it want with the retval. + */ + schedule(); + goto out; + default: + /* + * Another bit of PARANOID. Note that the retval will be + * 0 since no piece of kernel is supposed to do a check + * for a negative retval of schedule_timeout() (since it + * should never happens anyway). You just have the printk() + * that will tell you if something is gone wrong and where. + */ + if (timeout < 0) { + pr_err("%s: wrong timeout value %lx\n", __func__, timeout); + dump_stack(); + __set_current_state(TASK_RUNNING); + goto out; + } + } + + expire = timeout + jiffies; + + timer.task = current; + timer_setup_on_stack(&timer.timer, process_timeout, 0); + timer.timer.expires = expire; + add_timer(&timer.timer); + schedule(); + del_timer_sync(&timer.timer); + + /* Remove the timer from the object tracker */ + destroy_timer_on_stack(&timer.timer); + + timeout = expire - jiffies; + + out: + return timeout < 0 ? 0 : timeout; +} +EXPORT_SYMBOL(schedule_timeout); + +/* + * __set_current_state() can be used in schedule_timeout_*() functions, because + * schedule_timeout() calls schedule() unconditionally. + */ + +/** + * schedule_timeout_interruptible - sleep until timeout (interruptible) + * @timeout: timeout value in jiffies + * + * See schedule_timeout() for details. + * + * Task state is set to TASK_INTERRUPTIBLE before starting the timeout. + */ +signed long __sched schedule_timeout_interruptible(signed long timeout) +{ + __set_current_state(TASK_INTERRUPTIBLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_interruptible); + +/** + * schedule_timeout_killable - sleep until timeout (killable) + * @timeout: timeout value in jiffies + * + * See schedule_timeout() for details. + * + * Task state is set to TASK_KILLABLE before starting the timeout. + */ +signed long __sched schedule_timeout_killable(signed long timeout) +{ + __set_current_state(TASK_KILLABLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_killable); + +/** + * schedule_timeout_uninterruptible - sleep until timeout (uninterruptible) + * @timeout: timeout value in jiffies + * + * See schedule_timeout() for details. + * + * Task state is set to TASK_UNINTERRUPTIBLE before starting the timeout. + */ +signed long __sched schedule_timeout_uninterruptible(signed long timeout) +{ + __set_current_state(TASK_UNINTERRUPTIBLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_uninterruptible); + +/** + * schedule_timeout_idle - sleep until timeout (idle) + * @timeout: timeout value in jiffies + * + * See schedule_timeout() for details. + * + * Task state is set to TASK_IDLE before starting the timeout. It is similar to + * schedule_timeout_uninterruptible(), except this task will not contribute to + * load average. + */ +signed long __sched schedule_timeout_idle(signed long timeout) +{ + __set_current_state(TASK_IDLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_idle); + +/** + * schedule_hrtimeout_range_clock - sleep until timeout + * @expires: timeout value (ktime_t) + * @delta: slack in expires timeout (ktime_t) + * @mode: timer mode + * @clock_id: timer clock to be used + * + * Details are explained in schedule_hrtimeout_range() function description as + * this function is commonly used. + */ +int __sched schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, + const enum hrtimer_mode mode, clockid_t clock_id) +{ + struct hrtimer_sleeper t; + + /* + * Optimize when a zero timeout value is given. It does not + * matter whether this is an absolute or a relative time. + */ + if (expires && *expires == 0) { + __set_current_state(TASK_RUNNING); + return 0; + } + + /* + * A NULL parameter means "infinite" + */ + if (!expires) { + schedule(); + return -EINTR; + } + + hrtimer_setup_sleeper_on_stack(&t, clock_id, mode); + hrtimer_set_expires_range_ns(&t.timer, *expires, delta); + hrtimer_sleeper_start_expires(&t, mode); + + if (likely(t.task)) + schedule(); + + hrtimer_cancel(&t.timer); + destroy_hrtimer_on_stack(&t.timer); + + __set_current_state(TASK_RUNNING); + + return !t.task ? 0 : -EINTR; +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); + +/** + * schedule_hrtimeout_range - sleep until timeout + * @expires: timeout value (ktime_t) + * @delta: slack in expires timeout (ktime_t) + * @mode: timer mode + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * The @delta argument gives the kernel the freedom to schedule the + * actual wakeup to a time that is both power and performance friendly + * for regular (non RT/DL) tasks. + * The kernel give the normal best effort behavior for "@expires+@delta", + * but may decide to fire the timer earlier, but no earlier than @expires. + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns unless the current task is explicitly + * woken up, (e.g. by wake_up_process()). + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task or the current task is explicitly woken + * up. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns: 0 when the timer has expired. If the task was woken before the + * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or + * by an explicit wakeup, it returns -EINTR. + */ +int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta, + const enum hrtimer_mode mode) +{ + return schedule_hrtimeout_range_clock(expires, delta, mode, + CLOCK_MONOTONIC); +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); + +/** + * schedule_hrtimeout - sleep until timeout + * @expires: timeout value (ktime_t) + * @mode: timer mode + * + * See schedule_hrtimeout_range() for details. @delta argument of + * schedule_hrtimeout_range() is set to 0 and has therefore no impact. + */ +int __sched schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode) +{ + return schedule_hrtimeout_range(expires, 0, mode); +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout); + +/** + * msleep - sleep safely even with waitqueue interruptions + * @msecs: Requested sleep duration in milliseconds + * + * msleep() uses jiffy based timeouts for the sleep duration. Because of the + * design of the timer wheel, the maximum additional percentage delay (slack) is + * 12.5%. This is only valid for timers which will end up in level 1 or a higher + * level of the timer wheel. For explanation of those 12.5% please check the + * detailed description about the basics of the timer wheel. + * + * The slack of timers which will end up in level 0 depends on sleep duration + * (msecs) and HZ configuration and can be calculated in the following way (with + * the timer wheel design restriction that the slack is not less than 12.5%): + * + * ``slack = MSECS_PER_TICK / msecs`` + * + * When the allowed slack of the callsite is known, the calculation could be + * turned around to find the minimal allowed sleep duration to meet the + * constraints. For example: + * + * * ``HZ=1000`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 1 / (1/4) = 4``: + * all sleep durations greater or equal 4ms will meet the constraints. + * * ``HZ=1000`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 1 / (1/8) = 8``: + * all sleep durations greater or equal 8ms will meet the constraints. + * * ``HZ=250`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 4 / (1/4) = 16``: + * all sleep durations greater or equal 16ms will meet the constraints. + * * ``HZ=250`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 4 / (1/8) = 32``: + * all sleep durations greater or equal 32ms will meet the constraints. + * + * See also the signal aware variant msleep_interruptible(). + */ +void msleep(unsigned int msecs) +{ + unsigned long timeout = msecs_to_jiffies(msecs); + + while (timeout) + timeout = schedule_timeout_uninterruptible(timeout); +} +EXPORT_SYMBOL(msleep); + +/** + * msleep_interruptible - sleep waiting for signals + * @msecs: Requested sleep duration in milliseconds + * + * See msleep() for some basic information. + * + * The difference between msleep() and msleep_interruptible() is that the sleep + * could be interrupted by a signal delivery and then returns early. + * + * Returns: The remaining time of the sleep duration transformed to msecs (see + * schedule_timeout() for details). + */ +unsigned long msleep_interruptible(unsigned int msecs) +{ + unsigned long timeout = msecs_to_jiffies(msecs); + + while (timeout && !signal_pending(current)) + timeout = schedule_timeout_interruptible(timeout); + return jiffies_to_msecs(timeout); +} +EXPORT_SYMBOL(msleep_interruptible); + +/** + * usleep_range_state - Sleep for an approximate time in a given state + * @min: Minimum time in usecs to sleep + * @max: Maximum time in usecs to sleep + * @state: State of the current task that will be while sleeping + * + * usleep_range_state() sleeps at least for the minimum specified time but not + * longer than the maximum specified amount of time. The range might reduce + * power usage by allowing hrtimers to coalesce an already scheduled interrupt + * with this hrtimer. In the worst case, an interrupt is scheduled for the upper + * bound. + * + * The sleeping task is set to the specified state before starting the sleep. + * + * In non-atomic context where the exact wakeup time is flexible, use + * usleep_range() or its variants instead of udelay(). The sleep improves + * responsiveness by avoiding the CPU-hogging busy-wait of udelay(). + */ +void __sched usleep_range_state(unsigned long min, unsigned long max, unsigned int state) +{ + ktime_t exp = ktime_add_us(ktime_get(), min); + u64 delta = (u64)(max - min) * NSEC_PER_USEC; + + if (WARN_ON_ONCE(max < min)) + delta = 0; + + for (;;) { + __set_current_state(state); + /* Do not return before the requested sleep time has elapsed */ + if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) + break; + } +} +EXPORT_SYMBOL(usleep_range_state); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 5f2105e637bd..faac36de35b9 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -25,6 +25,7 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); extern void tick_check_new_device(struct clock_event_device *dev); +extern void tick_offline_cpu(unsigned int cpu); extern void tick_shutdown(unsigned int cpu); extern void tick_suspend(void); extern void tick_resume(void); @@ -142,10 +143,8 @@ static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_ #endif /* !(BROADCAST && ONESHOT) */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) -extern void tick_offline_cpu(unsigned int cpu); extern void tick_broadcast_offline(unsigned int cpu); #else -static inline void tick_offline_cpu(unsigned int cpu) { } static inline void tick_broadcast_offline(unsigned int cpu) { } #endif diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index e0c47259e91a..fa058510af9c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -311,14 +311,6 @@ static enum hrtimer_restart tick_nohz_handler(struct hrtimer *timer) return HRTIMER_RESTART; } -static void tick_sched_timer_cancel(struct tick_sched *ts) -{ - if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) - hrtimer_cancel(&ts->sched_timer); - else if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) - tick_program_event(KTIME_MAX, 1); -} - #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; EXPORT_SYMBOL_GPL(tick_nohz_full_mask); @@ -1061,7 +1053,10 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) * the tick timer. */ if (unlikely(expires == KTIME_MAX)) { - tick_sched_timer_cancel(ts); + if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) + hrtimer_cancel(&ts->sched_timer); + else + tick_program_event(KTIME_MAX, 1); return; } @@ -1610,21 +1605,13 @@ void tick_setup_sched_timer(bool hrtimer) */ void tick_sched_timer_dying(int cpu) { - struct tick_device *td = &per_cpu(tick_cpu_device, cpu); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); - struct clock_event_device *dev = td->evtdev; ktime_t idle_sleeptime, iowait_sleeptime; unsigned long idle_calls, idle_sleeps; /* This must happen before hrtimers are migrated! */ - tick_sched_timer_cancel(ts); - - /* - * If the clockevents doesn't support CLOCK_EVT_STATE_ONESHOT_STOPPED, - * make sure not to call low-res tick handler. - */ - if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) - dev->event_handler = clockevents_handle_noop; + if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) + hrtimer_cancel(&ts->sched_timer); idle_sleeptime = ts->idle_sleeptime; iowait_sleeptime = ts->iowait_sleeptime; diff --git a/kernel/time/time.c b/kernel/time/time.c index 642647f5046b..1b69caa87480 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -556,9 +556,9 @@ EXPORT_SYMBOL(ns_to_timespec64); * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. - * for the details see __msecs_to_jiffies() + * for the details see _msecs_to_jiffies() * - * __msecs_to_jiffies() checks for the passed in value being a constant + * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at @@ -866,7 +866,7 @@ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, * * Handles compat or 32-bit modes. * - * Return: %0 on success or negative errno on error + * Return: 0 on success or negative errno on error */ int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) @@ -897,7 +897,7 @@ EXPORT_SYMBOL_GPL(get_timespec64); * @ts: input &struct timespec64 * @uts: user's &struct __kernel_timespec * - * Return: %0 on success or negative errno on error + * Return: 0 on success or negative errno on error */ int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) @@ -944,7 +944,7 @@ static int __put_old_timespec32(const struct timespec64 *ts64, * * Handles X86_X32_ABI compatibility conversion. * - * Return: %0 on success or negative errno on error + * Return: 0 on success or negative errno on error */ int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { @@ -963,7 +963,7 @@ EXPORT_SYMBOL_GPL(get_old_timespec32); * * Handles X86_X32_ABI compatibility conversion. * - * Return: %0 on success or negative errno on error + * Return: 0 on success or negative errno on error */ int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { @@ -979,7 +979,7 @@ EXPORT_SYMBOL_GPL(put_old_timespec32); * @it: destination &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * - * Return: %0 on success or negative errno on error + * Return: 0 on success or negative errno on error */ int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) @@ -1002,7 +1002,7 @@ EXPORT_SYMBOL_GPL(get_itimerspec64); * @it: input &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * - * Return: %0 on success or negative errno on error + * Return: 0 on success or negative errno on error */ int put_itimerspec64(const struct itimerspec64 *it, struct __kernel_itimerspec __user *uit) @@ -1024,7 +1024,7 @@ EXPORT_SYMBOL_GPL(put_itimerspec64); * @its: destination &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * - * Return: %0 on success or negative errno on error + * Return: 0 on success or negative errno on error */ int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits) @@ -1043,7 +1043,7 @@ EXPORT_SYMBOL_GPL(get_old_itimerspec32); * @its: input &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * - * Return: %0 on success or negative errno on error + * Return: 0 on success or negative errno on error */ int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index cdd61990cd14..0ca85ff4fbb4 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -30,8 +30,9 @@ #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) -#define TK_MIRROR (1 << 1) -#define TK_CLOCK_WAS_SET (1 << 2) +#define TK_CLOCK_WAS_SET (1 << 1) + +#define TK_UPDATE_ALL (TK_CLEAR_NTP | TK_CLOCK_WAS_SET) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ @@ -41,20 +42,18 @@ enum timekeeping_adv_mode { TK_ADV_FREQ }; -DEFINE_RAW_SPINLOCK(timekeeper_lock); - /* * The most important data for readout fits into a single 64 byte * cache line. */ -static struct { +struct tk_data { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; -} tk_core ____cacheline_aligned = { - .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock), -}; + struct timekeeper shadow_timekeeper; + raw_spinlock_t lock; +} ____cacheline_aligned; -static struct timekeeper shadow_timekeeper; +static struct tk_data tk_core; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; @@ -114,6 +113,19 @@ static struct tk_fast tk_fast_raw ____cacheline_aligned = { .base[1] = FAST_TK_INIT, }; +unsigned long timekeeper_lock_irqsave(void) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&tk_core.lock, flags); + return flags; +} + +void timekeeper_unlock_irqrestore(unsigned long flags) +{ + raw_spin_unlock_irqrestore(&tk_core.lock, flags); +} + /* * Multigrain timestamps require tracking the latest fine-grained timestamp * that has been issued, and never returning a coarse-grained timestamp that is @@ -178,13 +190,15 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; 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)); + /* Paired with READ_ONCE() in ktime_mono_to_any() */ + WRITE_ONCE(tk->offs_real, timespec64_to_ktime(tmp)); + WRITE_ONCE(tk->offs_tai, ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0))); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { - tk->offs_boot = ktime_add(tk->offs_boot, delta); + /* Paired with READ_ONCE() in ktime_mono_to_any() */ + WRITE_ONCE(tk->offs_boot, ktime_add(tk->offs_boot, delta)); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. @@ -201,7 +215,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. - * This isn't necessary to use when holding the timekeeper_lock or doing + * This isn't necessary to use when holding the tk_core.lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ @@ -212,97 +226,6 @@ static inline u64 tk_clock_read(const struct tk_read_base *tkr) return clock->read(clock); } -#ifdef CONFIG_DEBUG_TIMEKEEPING -#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ - -static void timekeeping_check_update(struct timekeeper *tk, u64 offset) -{ - - u64 max_cycles = tk->tkr_mono.clock->max_cycles; - const char *name = tk->tkr_mono.clock->name; - - if (offset > max_cycles) { - printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", - offset, name, max_cycles); - printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); - } else { - if (offset > (max_cycles >> 1)) { - printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", - offset, name, max_cycles >> 1); - printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); - } - } - - if (tk->underflow_seen) { - if (jiffies - tk->last_warning > WARNING_FREQ) { - printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); - printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); - printk_deferred(" Your kernel is probably still fine.\n"); - tk->last_warning = jiffies; - } - tk->underflow_seen = 0; - } - - if (tk->overflow_seen) { - if (jiffies - tk->last_warning > WARNING_FREQ) { - printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); - printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); - printk_deferred(" Your kernel is probably still fine.\n"); - tk->last_warning = jiffies; - } - tk->overflow_seen = 0; - } -} - -static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles); - -static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) -{ - struct timekeeper *tk = &tk_core.timekeeper; - u64 now, last, mask, max, delta; - unsigned int seq; - - /* - * Since we're called holding a seqcount, the data may shift - * under us while we're doing the calculation. This can cause - * false positives, since we'd note a problem but throw the - * results away. So nest another seqcount here to atomically - * grab the points we are checking with. - */ - do { - seq = read_seqcount_begin(&tk_core.seq); - now = tk_clock_read(tkr); - last = tkr->cycle_last; - mask = tkr->mask; - max = tkr->clock->max_cycles; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - delta = clocksource_delta(now, last, mask); - - /* - * Try to catch underflows by checking if we are seeing small - * mask-relative negative values. - */ - if (unlikely((~delta & mask) < (mask >> 3))) - tk->underflow_seen = 1; - - /* Check for multiplication overflows */ - if (unlikely(delta > max)) - tk->overflow_seen = 1; - - /* timekeeping_cycles_to_ns() handles both under and overflow */ - return timekeeping_cycles_to_ns(tkr, now); -} -#else -static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) -{ -} -static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) -{ - BUG(); -} -#endif - /** * tk_setup_internals - Set up internals to use clocksource clock. * @@ -407,19 +330,11 @@ static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 c return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } -static __always_inline u64 __timekeeping_get_ns(const struct tk_read_base *tkr) +static __always_inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } -static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) -{ - if (IS_ENABLED(CONFIG_DEBUG_TIMEKEEPING)) - return timekeeping_debug_get_ns(tkr); - - return __timekeeping_get_ns(tkr); -} - /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update @@ -465,7 +380,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) seq = read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); - now += __timekeeping_get_ns(tkr); + now += timekeeping_get_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; @@ -536,7 +451,7 @@ EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); - * timekeeping_update(tk, TK_CLEAR_NTP...); + * timekeeping_update_staged(tkd, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this @@ -581,7 +496,7 @@ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); - delta = __timekeeping_get_ns(tkr); + delta = timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) @@ -695,13 +610,11 @@ static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long flags; int ret; - raw_spin_lock_irqsave(&timekeeper_lock, flags); + guard(raw_spinlock_irqsave)(&tk_core.lock); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } @@ -714,14 +627,8 @@ EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&timekeeper_lock, flags); - ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); - - return ret; + guard(raw_spinlock_irqsave)(&tk_core.lock); + return raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); @@ -737,6 +644,18 @@ static inline void tk_update_leap_state(struct timekeeper *tk) } /* + * Leap state update for both shadow and the real timekeeper + * Separate to spare a full memcpy() of the timekeeper. + */ +static void tk_update_leap_state_all(struct tk_data *tkd) +{ + write_seqcount_begin(&tkd->seq); + tk_update_leap_state(&tkd->shadow_timekeeper); + tkd->timekeeper.next_leap_ktime = tkd->shadow_timekeeper.next_leap_ktime; + write_seqcount_end(&tkd->seq); +} + +/* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) @@ -769,9 +688,30 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } -/* must hold timekeeper_lock */ -static void timekeeping_update(struct timekeeper *tk, unsigned int action) +/* + * Restore the shadow timekeeper from the real timekeeper. + */ +static void timekeeping_restore_shadow(struct tk_data *tkd) +{ + lockdep_assert_held(&tkd->lock); + memcpy(&tkd->shadow_timekeeper, &tkd->timekeeper, sizeof(tkd->timekeeper)); +} + +static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int action) { + struct timekeeper *tk = &tk_core.shadow_timekeeper; + + lockdep_assert_held(&tkd->lock); + + /* + * Block out readers before running the updates below because that + * updates VDSO and other time related infrastructure. Not blocking + * the readers might let a reader see time going backwards when + * reading from the VDSO after the VDSO update and then reading in + * the kernel from the timekeeper before that got updated. + */ + write_seqcount_begin(&tkd->seq); + if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); @@ -789,14 +729,17 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; + /* - * The mirroring of the data to the shadow-timekeeper needs - * to happen last here to ensure we don't over-write the - * timekeeper structure on the next update with stale data + * Update the real timekeeper. + * + * We could avoid this memcpy() by switching pointers, but that has + * the downside that the reader side does not longer benefit from + * the cacheline optimized data layout of the timekeeper and requires + * another indirection. */ - if (action & TK_MIRROR) - memcpy(&shadow_timekeeper, &tk_core.timekeeper, - sizeof(tk_core.timekeeper)); + memcpy(&tkd->timekeeper, tk, sizeof(*tk)); + write_seqcount_end(&tkd->seq); } /** @@ -949,6 +892,14 @@ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) unsigned int seq; ktime_t tconv; + if (IS_ENABLED(CONFIG_64BIT)) { + /* + * Paired with WRITE_ONCE()s in tk_set_wall_to_mono() and + * tk_update_sleep_time(). + */ + return ktime_add(tmono, READ_ONCE(*offset)); + } + do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); @@ -1079,6 +1030,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) unsigned int seq; ktime_t base_raw; ktime_t base_real; + ktime_t base_boot; u64 nsec_raw; u64 nsec_real; u64 now; @@ -1093,6 +1045,8 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); + base_boot = ktime_add(tk->tkr_mono.base, + tk_core.timekeeper.offs_boot); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); @@ -1100,6 +1054,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); + systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); @@ -1459,45 +1414,35 @@ EXPORT_SYMBOL_GPL(timekeeping_clocksource_has_base); */ int do_settimeofday64(const struct timespec64 *ts) { - struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; - unsigned long flags; - int ret = 0; if (!timespec64_valid_settod(ts)) return -EINVAL; - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - - timekeeping_forward_now(tk); + scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { + struct timekeeper *tks = &tk_core.shadow_timekeeper; - xt = tk_xtime(tk); - ts_delta = timespec64_sub(*ts, xt); + timekeeping_forward_now(tks); - if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { - ret = -EINVAL; - goto out; - } - - tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); + xt = tk_xtime(tks); + ts_delta = timespec64_sub(*ts, xt); - tk_set_xtime(tk, ts); -out: - timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); + if (timespec64_compare(&tks->wall_to_monotonic, &ts_delta) > 0) { + timekeeping_restore_shadow(&tk_core); + return -EINVAL; + } - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, ts_delta)); + tk_set_xtime(tks, ts); + timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); + } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); - if (!ret) { - audit_tk_injoffset(ts_delta); - add_device_randomness(ts, sizeof(*ts)); - } - - return ret; + audit_tk_injoffset(ts_delta); + add_device_randomness(ts, sizeof(*ts)); + return 0; } EXPORT_SYMBOL(do_settimeofday64); @@ -1509,40 +1454,31 @@ EXPORT_SYMBOL(do_settimeofday64); */ static int timekeeping_inject_offset(const struct timespec64 *ts) { - struct timekeeper *tk = &tk_core.timekeeper; - unsigned long flags; - struct timespec64 tmp; - int ret = 0; - if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - - timekeeping_forward_now(tk); - - /* Make sure the proposed value is valid */ - tmp = timespec64_add(tk_xtime(tk), *ts); - if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || - !timespec64_valid_settod(&tmp)) { - ret = -EINVAL; - goto error; - } + scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { + struct timekeeper *tks = &tk_core.shadow_timekeeper; + struct timespec64 tmp; - tk_xtime_add(tk, ts); - tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *ts)); + timekeeping_forward_now(tks); -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); + /* Make sure the proposed value is valid */ + tmp = timespec64_add(tk_xtime(tks), *ts); + if (timespec64_compare(&tks->wall_to_monotonic, ts) > 0 || + !timespec64_valid_settod(&tmp)) { + timekeeping_restore_shadow(&tk_core); + return -EINVAL; + } - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + tk_xtime_add(tks, ts); + tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, *ts)); + timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); + } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); - - return ret; + return 0; } /* @@ -1595,43 +1531,34 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) */ static int change_clocksource(void *data) { - struct timekeeper *tk = &tk_core.timekeeper; - struct clocksource *new, *old = NULL; - unsigned long flags; - bool change = false; - - new = (struct clocksource *) data; + struct clocksource *new = data, *old = NULL; /* - * If the cs is in module, get a module reference. Succeeds - * for built-in code (owner == NULL) as well. + * If the clocksource is in a module, get a module reference. + * Succeeds for built-in code (owner == NULL) as well. Abort if the + * reference can't be acquired. */ - if (try_module_get(new->owner)) { - if (!new->enable || new->enable(new) == 0) - change = true; - else - module_put(new->owner); - } - - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - - timekeeping_forward_now(tk); + if (!try_module_get(new->owner)) + return 0; - if (change) { - old = tk->tkr_mono.clock; - tk_setup_internals(tk, new); + /* Abort if the device can't be enabled */ + if (new->enable && new->enable(new) != 0) { + module_put(new->owner); + return 0; } - timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); + scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { + struct timekeeper *tks = &tk_core.shadow_timekeeper; - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + timekeeping_forward_now(tks); + old = tks->tkr_mono.clock; + tk_setup_internals(tks, new); + timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); + } if (old) { if (old->disable) old->disable(old); - module_put(old->owner); } @@ -1756,6 +1683,12 @@ read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, *boot_offset = ns_to_timespec64(local_clock()); } +static __init void tkd_basic_setup(struct tk_data *tkd) +{ + raw_spin_lock_init(&tkd->lock); + seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock); +} + /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * @@ -1780,9 +1713,10 @@ static bool persistent_clock_exists; void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; - struct timekeeper *tk = &tk_core.timekeeper; + struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock; - unsigned long flags; + + tkd_basic_setup(&tk_core); read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && @@ -1802,24 +1736,21 @@ void __init timekeeping_init(void) */ wall_to_mono = timespec64_sub(boot_offset, wall_time); - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); + guard(raw_spinlock_irqsave)(&tk_core.lock); + ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); - tk_setup_internals(tk, clock); - - tk_set_xtime(tk, &wall_time); - tk->raw_sec = 0; + tk_setup_internals(tks, clock); - tk_set_wall_to_mono(tk, wall_to_mono); + tk_set_xtime(tks, &wall_time); + tks->raw_sec = 0; - timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); + tk_set_wall_to_mono(tks, wall_to_mono); - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); } /* time in seconds when suspend began for persistent clock */ @@ -1897,22 +1828,14 @@ bool timekeeping_rtc_skipsuspend(void) */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { - struct timekeeper *tk = &tk_core.timekeeper; - unsigned long flags; + scoped_guard(raw_spinlock_irqsave, &tk_core.lock) { + struct timekeeper *tks = &tk_core.shadow_timekeeper; - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - - suspend_timing_needed = false; - - timekeeping_forward_now(tk); - - __timekeeping_inject_sleeptime(tk, delta); - - timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); - - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + suspend_timing_needed = false; + timekeeping_forward_now(tks); + __timekeeping_inject_sleeptime(tks, delta); + timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); + } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); @@ -1924,20 +1847,19 @@ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) */ void timekeeping_resume(void) { - struct timekeeper *tk = &tk_core.timekeeper; - struct clocksource *clock = tk->tkr_mono.clock; - unsigned long flags; + struct timekeeper *tks = &tk_core.shadow_timekeeper; + struct clocksource *clock = tks->tkr_mono.clock; struct timespec64 ts_new, ts_delta; - u64 cycle_now, nsec; bool inject_sleeptime = false; + u64 cycle_now, nsec; + unsigned long flags; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); + raw_spin_lock_irqsave(&tk_core.lock, flags); /* * After system resumes, we need to calculate the suspended time and @@ -1951,7 +1873,7 @@ 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_clock_read(&tk->tkr_mono); + cycle_now = tk_clock_read(&tks->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); @@ -1963,18 +1885,17 @@ void timekeeping_resume(void) if (inject_sleeptime) { suspend_timing_needed = false; - __timekeeping_inject_sleeptime(tk, &ts_delta); + __timekeeping_inject_sleeptime(tks, &ts_delta); } /* Re-base the last cycle value */ - tk->tkr_mono.cycle_last = cycle_now; - tk->tkr_raw.cycle_last = cycle_now; + tks->tkr_mono.cycle_last = cycle_now; + tks->tkr_raw.cycle_last = cycle_now; - tk->ntp_error = 0; + tks->ntp_error = 0; timekeeping_suspended = 0; - timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); + raw_spin_unlock_irqrestore(&tk_core.lock, flags); touch_softlockup_watchdog(); @@ -1986,11 +1907,11 @@ void timekeeping_resume(void) int timekeeping_suspend(void) { - struct timekeeper *tk = &tk_core.timekeeper; - unsigned long flags; - struct timespec64 delta, delta_delta; - static struct timespec64 old_delta; + struct timekeeper *tks = &tk_core.shadow_timekeeper; + struct timespec64 delta, delta_delta; + static struct timespec64 old_delta; struct clocksource *curr_clock; + unsigned long flags; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); @@ -2005,9 +1926,8 @@ int timekeeping_suspend(void) suspend_timing_needed = true; - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - timekeeping_forward_now(tk); + raw_spin_lock_irqsave(&tk_core.lock, flags); + timekeeping_forward_now(tks); timekeeping_suspended = 1; /* @@ -2015,8 +1935,8 @@ int timekeeping_suspend(void) * just read from the current clocksource. Save this to potentially * use in suspend timing. */ - curr_clock = tk->tkr_mono.clock; - cycle_now = tk->tkr_mono.cycle_last; + curr_clock = tks->tkr_mono.clock; + cycle_now = tks->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { @@ -2026,7 +1946,7 @@ int timekeeping_suspend(void) * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ - delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); + delta = timespec64_sub(tk_xtime(tks), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* @@ -2041,10 +1961,9 @@ int timekeeping_suspend(void) } } - timekeeping_update(tk, TK_MIRROR); - halt_fast_timekeeper(tk); - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + timekeeping_update_from_shadow(&tk_core, 0); + halt_fast_timekeeper(tks); + raw_spin_unlock_irqrestore(&tk_core.lock, flags); tick_suspend(); clocksource_suspend(); @@ -2149,16 +2068,17 @@ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { + u64 ntp_tl = ntp_tick_length(); u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ - if (likely(tk->ntp_tick == ntp_tick_length())) { + if (likely(tk->ntp_tick == ntp_tl)) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { - tk->ntp_tick = ntp_tick_length(); + tk->ntp_tick = ntp_tl; mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } @@ -2297,28 +2217,24 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, */ static bool timekeeping_advance(enum timekeeping_adv_mode mode) { + struct timekeeper *tk = &tk_core.shadow_timekeeper; struct timekeeper *real_tk = &tk_core.timekeeper; - struct timekeeper *tk = &shadow_timekeeper; - u64 offset; - int shift = 0, maxshift; unsigned int clock_set = 0; - unsigned long flags; + int shift = 0, maxshift; + u64 offset; - raw_spin_lock_irqsave(&timekeeper_lock, flags); + guard(raw_spinlock_irqsave)(&tk_core.lock); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) - goto out; + return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) - goto out; - - /* Do some additional sanity checking */ - timekeeping_check_update(tk, offset); + return false; /* * With NO_HZ we may have to accumulate many cycle_intervals @@ -2334,8 +2250,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { - offset = logarithmic_accumulation(tk, offset, shift, - &clock_set); + offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } @@ -2349,23 +2264,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) */ clock_set |= accumulate_nsecs_to_secs(tk); - write_seqcount_begin(&tk_core.seq); - /* - * Update the real timekeeper. - * - * We could avoid this memcpy by switching pointers, but that - * 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 tk_core.seq against one before we start - * updating. - */ - timekeeping_update(tk, clock_set); - memcpy(real_tk, tk, sizeof(*tk)); - /* The memcpy must come last. Do not put anything here! */ - write_seqcount_end(&tk_core.seq); -out: - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + timekeeping_update_from_shadow(&tk_core, clock_set); return !!clock_set; } @@ -2658,13 +2557,10 @@ EXPORT_SYMBOL_GPL(random_get_entropy_fallback); */ int do_adjtimex(struct __kernel_timex *txc) { - struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; bool offset_set = false; bool clock_set = false; struct timespec64 ts; - unsigned long flags; - s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ @@ -2675,6 +2571,7 @@ int do_adjtimex(struct __kernel_timex *txc) if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; + delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) @@ -2692,21 +2589,21 @@ int do_adjtimex(struct __kernel_timex *txc) ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); + scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { + struct timekeeper *tks = &tk_core.shadow_timekeeper; + s32 orig_tai, tai; - orig_tai = tai = tk->tai_offset; - ret = __do_adjtimex(txc, &ts, &tai, &ad); + orig_tai = tai = tks->tai_offset; + ret = __do_adjtimex(txc, &ts, &tai, &ad); - if (tai != orig_tai) { - __timekeeping_set_tai_offset(tk, tai); - timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); - clock_set = true; + if (tai != orig_tai) { + __timekeeping_set_tai_offset(tks, tai); + timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); + clock_set = true; + } else { + tk_update_leap_state_all(&tk_core); + } } - tk_update_leap_state(tk); - - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); audit_ntp_log(&ad); @@ -2730,15 +2627,8 @@ int do_adjtimex(struct __kernel_timex *txc) */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { - unsigned long flags; - - raw_spin_lock_irqsave(&timekeeper_lock, flags); - write_seqcount_begin(&tk_core.seq); - + guard(raw_spinlock_irqsave)(&tk_core.lock); __hardpps(phase_ts, raw_ts); - - write_seqcount_end(&tk_core.seq); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 0bbae825bc02..63e600e943a7 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -30,7 +30,6 @@ static inline void timekeeping_inc_mg_floor_swaps(void) #endif -#ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) { u64 ret = (now - last) & mask; @@ -41,14 +40,9 @@ static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) */ return ret & ~(mask >> 1) ? 0 : ret; } -#else -static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) -{ - return (now - last) & mask; -} -#endif /* Semi public for serialization of non timekeeper VDSO updates. */ -extern raw_spinlock_t timekeeper_lock; +unsigned long timekeeper_lock_irqsave(void); +void timekeeper_unlock_irqrestore(unsigned long flags); #endif /* _TIMEKEEPING_INTERNAL_H */ diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 06f0bc1db6d9..a5860bf6d16f 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -37,7 +37,6 @@ #include <linux/tick.h> #include <linux/kallsyms.h> #include <linux/irq_work.h> -#include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> @@ -2422,7 +2421,8 @@ static inline void __run_timers(struct timer_base *base) static void __run_timer_base(struct timer_base *base) { - if (time_before(jiffies, base->next_expiry)) + /* Can race against a remote CPU updating next_expiry under the lock */ + if (time_before(jiffies, READ_ONCE(base->next_expiry))) return; timer_base_lock_expiry(base); @@ -2526,141 +2526,6 @@ void update_process_times(int user_tick) run_posix_cpu_timers(); } -/* - * Since schedule_timeout()'s timer is defined on the stack, it must store - * the target task on the stack as well. - */ -struct process_timer { - struct timer_list timer; - struct task_struct *task; -}; - -static void process_timeout(struct timer_list *t) -{ - struct process_timer *timeout = from_timer(timeout, t, timer); - - wake_up_process(timeout->task); -} - -/** - * schedule_timeout - sleep until timeout - * @timeout: timeout value in jiffies - * - * Make the current task sleep until @timeout jiffies have elapsed. - * The function behavior depends on the current task state - * (see also set_current_state() description): - * - * %TASK_RUNNING - the scheduler is called, but the task does not sleep - * at all. That happens because sched_submit_work() does nothing for - * tasks in %TASK_RUNNING state. - * - * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to - * pass before the routine returns unless the current task is explicitly - * woken up, (e.g. by wake_up_process()). - * - * %TASK_INTERRUPTIBLE - the routine may return early if a signal is - * delivered to the current task or the current task is explicitly woken - * up. - * - * The current task state is guaranteed to be %TASK_RUNNING when this - * routine returns. - * - * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule - * the CPU away without a bound on the timeout. In this case the return - * value will be %MAX_SCHEDULE_TIMEOUT. - * - * Returns 0 when the timer has expired otherwise the remaining time in - * jiffies will be returned. In all cases the return value is guaranteed - * to be non-negative. - */ -signed long __sched schedule_timeout(signed long timeout) -{ - struct process_timer timer; - unsigned long expire; - - switch (timeout) - { - case MAX_SCHEDULE_TIMEOUT: - /* - * These two special cases are useful to be comfortable - * in the caller. Nothing more. We could take - * MAX_SCHEDULE_TIMEOUT from one of the negative value - * but I' d like to return a valid offset (>=0) to allow - * the caller to do everything it want with the retval. - */ - schedule(); - goto out; - default: - /* - * Another bit of PARANOID. Note that the retval will be - * 0 since no piece of kernel is supposed to do a check - * for a negative retval of schedule_timeout() (since it - * should never happens anyway). You just have the printk() - * that will tell you if something is gone wrong and where. - */ - if (timeout < 0) { - printk(KERN_ERR "schedule_timeout: wrong timeout " - "value %lx\n", timeout); - dump_stack(); - __set_current_state(TASK_RUNNING); - goto out; - } - } - - expire = timeout + jiffies; - - timer.task = current; - timer_setup_on_stack(&timer.timer, process_timeout, 0); - __mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING); - schedule(); - del_timer_sync(&timer.timer); - - /* Remove the timer from the object tracker */ - destroy_timer_on_stack(&timer.timer); - - timeout = expire - jiffies; - - out: - return timeout < 0 ? 0 : timeout; -} -EXPORT_SYMBOL(schedule_timeout); - -/* - * We can use __set_current_state() here because schedule_timeout() calls - * schedule() unconditionally. - */ -signed long __sched schedule_timeout_interruptible(signed long timeout) -{ - __set_current_state(TASK_INTERRUPTIBLE); - return schedule_timeout(timeout); -} -EXPORT_SYMBOL(schedule_timeout_interruptible); - -signed long __sched schedule_timeout_killable(signed long timeout) -{ - __set_current_state(TASK_KILLABLE); - return schedule_timeout(timeout); -} -EXPORT_SYMBOL(schedule_timeout_killable); - -signed long __sched schedule_timeout_uninterruptible(signed long timeout) -{ - __set_current_state(TASK_UNINTERRUPTIBLE); - return schedule_timeout(timeout); -} -EXPORT_SYMBOL(schedule_timeout_uninterruptible); - -/* - * Like schedule_timeout_uninterruptible(), except this task will not contribute - * to load average. - */ -signed long __sched schedule_timeout_idle(signed long timeout) -{ - __set_current_state(TASK_IDLE); - return schedule_timeout(timeout); -} -EXPORT_SYMBOL(schedule_timeout_idle); - #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { @@ -2757,59 +2622,3 @@ void __init init_timers(void) posix_cputimers_init_work(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } - -/** - * msleep - sleep safely even with waitqueue interruptions - * @msecs: Time in milliseconds to sleep for - */ -void msleep(unsigned int msecs) -{ - unsigned long timeout = msecs_to_jiffies(msecs); - - while (timeout) - timeout = schedule_timeout_uninterruptible(timeout); -} - -EXPORT_SYMBOL(msleep); - -/** - * msleep_interruptible - sleep waiting for signals - * @msecs: Time in milliseconds to sleep for - */ -unsigned long msleep_interruptible(unsigned int msecs) -{ - unsigned long timeout = msecs_to_jiffies(msecs); - - while (timeout && !signal_pending(current)) - timeout = schedule_timeout_interruptible(timeout); - return jiffies_to_msecs(timeout); -} - -EXPORT_SYMBOL(msleep_interruptible); - -/** - * usleep_range_state - Sleep for an approximate time in a given state - * @min: Minimum time in usecs to sleep - * @max: Maximum time in usecs to sleep - * @state: State of the current task that will be while sleeping - * - * In non-atomic context where the exact wakeup time is flexible, use - * usleep_range_state() instead of udelay(). The sleep improves responsiveness - * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces - * power usage by allowing hrtimers to take advantage of an already- - * scheduled interrupt instead of scheduling a new one just for this sleep. - */ -void __sched usleep_range_state(unsigned long min, unsigned long max, - unsigned int state) -{ - ktime_t exp = ktime_add_us(ktime_get(), min); - u64 delta = (u64)(max - min) * NSEC_PER_USEC; - - for (;;) { - __set_current_state(state); - /* Do not return before the requested sleep time has elapsed */ - if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) - break; - } -} -EXPORT_SYMBOL(usleep_range_state); diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 28706a13c222..05d383143165 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -151,9 +151,8 @@ void update_vsyscall_tz(void) unsigned long vdso_update_begin(void) { struct vdso_data *vdata = __arch_get_k_vdso_data(); - unsigned long flags; + unsigned long flags = timekeeper_lock_irqsave(); - raw_spin_lock_irqsave(&timekeeper_lock, flags); vdso_write_begin(vdata); return flags; } @@ -172,5 +171,5 @@ void vdso_update_end(unsigned long flags) vdso_write_end(vdata); __arch_sync_vdso_data(vdata); - raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + timekeeper_unlock_irqrestore(flags); } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 188f3fd6bdd3..652ec5f5fdfb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1328,19 +1328,6 @@ config SCHEDSTATS endmenu -config DEBUG_TIMEKEEPING - bool "Enable extra timekeeping sanity checking" - help - This option will enable additional timekeeping sanity checks - which may be helpful when diagnosing issues where timekeeping - problems are suspected. - - This may include checks in the timekeeping hotpaths, so this - option may have a (very small) performance impact to some - workloads. - - If unsure, say N. - config DEBUG_PREEMPT bool "Debug preemptible kernel" depends on DEBUG_KERNEL && PREEMPTION && TRACE_IRQFLAGS_SUPPORT diff --git a/mm/damon/core.c b/mm/damon/core.c index 511c3f61ab44..8b8e2933dcd4 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1906,11 +1906,10 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme) static void kdamond_usleep(unsigned long usecs) { - /* See Documentation/timers/timers-howto.rst for the thresholds */ - if (usecs > 20 * USEC_PER_MSEC) + if (usecs >= USLEEP_RANGE_UPPER_BOUND) schedule_timeout_idle(usecs_to_jiffies(usecs)); else - usleep_idle_range(usecs, usecs + 1); + usleep_range_idle(usecs, usecs + 1); } /* Returns negative error code if it's not activated but should return */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0bbad90ddd6f..7b35c58bbbeb 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -42,8 +42,6 @@ #define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ "\x00\x00\x00\x00\x00\x00\x00\x00" -#define secs_to_jiffies(_secs) msecs_to_jiffies((_secs) * 1000) - /* Handle HCI Event packets */ static void *hci_ev_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 34f68ef74b8f..7e23cacbe66e 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2285,7 +2285,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) s64 remaining; struct hrtimer_sleeper t; - hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_setup_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); hrtimer_set_expires(&t.timer, spin_until); remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer)); diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index f8b25b6f5da7..85f017e37cfc 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -107,14 +107,12 @@ static void idletimer_tg_expired(struct timer_list *t) schedule_work(&timer->work); } -static enum alarmtimer_restart idletimer_tg_alarmproc(struct alarm *alarm, - ktime_t now) +static void idletimer_tg_alarmproc(struct alarm *alarm, ktime_t now) { struct idletimer_tg *timer = alarm->data; pr_debug("alarm %s expired\n", timer->attr.attr.name); schedule_work(&timer->work); - return ALARMTIMER_NORESTART; } static int idletimer_check_sysfs_name(const char *name, unsigned int size) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 4427572b2477..98790fe5115d 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -6597,11 +6597,11 @@ sub process { # ignore udelay's < 10, however if (! ($delay < 10) ) { CHK("USLEEP_RANGE", - "usleep_range is preferred over udelay; see Documentation/timers/timers-howto.rst\n" . $herecurr); + "usleep_range is preferred over udelay; see function description of usleep_range() and udelay().\n" . $herecurr); } if ($delay > 2000) { WARN("LONG_UDELAY", - "long udelay - prefer mdelay; see arch/arm/include/asm/delay.h\n" . $herecurr); + "long udelay - prefer mdelay; see function description of mdelay().\n" . $herecurr); } } @@ -6609,7 +6609,7 @@ sub process { if ($line =~ /\bmsleep\s*\((\d+)\);/) { if ($1 < 20) { WARN("MSLEEP", - "msleep < 20ms can sleep for up to 20ms; see Documentation/timers/timers-howto.rst\n" . $herecurr); + "msleep < 20ms can sleep for up to 20ms; see function description of msleep().\n" . $herecurr); } } @@ -7077,11 +7077,11 @@ sub process { my $max = $7; if ($min eq $max) { WARN("USLEEP_RANGE", - "usleep_range should not use min == max args; see Documentation/timers/timers-howto.rst\n" . "$here\n$stat\n"); + "usleep_range should not use min == max args; see function description of usleep_range().\n" . "$here\n$stat\n"); } elsif ($min =~ /^\d+$/ && $max =~ /^\d+$/ && $min > $max) { WARN("USLEEP_RANGE", - "usleep_range args reversed, use min then max; see Documentation/timers/timers-howto.rst\n" . "$here\n$stat\n"); + "usleep_range args reversed, use min then max; see function description of usleep_range().\n" . "$here\n$stat\n"); } } diff --git a/sound/soc/sof/ops.h b/sound/soc/sof/ops.h index 2584621c3b2d..d73644e85b6e 100644 --- a/sound/soc/sof/ops.h +++ b/sound/soc/sof/ops.h @@ -597,12 +597,12 @@ snd_sof_is_chain_dma_supported(struct snd_sof_dev *sdev, u32 dai_type) * @addr: Address to poll * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @addr is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. * diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index 9d172210e2c6..139fd9aa8b12 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -31,7 +31,6 @@ CONFIG_SCHED_DEBUG=y CONFIG_SCHED_INFO=y CONFIG_SCHEDSTATS=y CONFIG_SCHED_STACK_END_CHECK=y -CONFIG_DEBUG_TIMEKEEPING=y CONFIG_DEBUG_PREEMPT=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_SPINLOCK=y |