diff --git a/Documentation/hwlat_detector.txt b/Documentation/hwlat_detector.txt new file mode 100644 index 0000000..cb61516 --- /dev/null +++ b/Documentation/hwlat_detector.txt @@ -0,0 +1,64 @@ +Introduction: +------------- + +The module hwlat_detector is a special purpose kernel module that is used to +detect large system latencies induced by the behavior of certain underlying +hardware or firmware, independent of Linux itself. The code was developed +originally to detect SMIs (System Management Interrupts) on x86 systems, +however there is nothing x86 specific about this patchset. It was +originally written for use by the "RT" patch since the Real Time +kernel is highly latency sensitive. + +SMIs are usually not serviced by the Linux kernel, which typically does not +even know that they are occuring. SMIs are instead are set up by BIOS code +and are serviced by BIOS code, usually for "critical" events such as +management of thermal sensors and fans. Sometimes though, SMIs are used for +other tasks and those tasks can spend an inordinate amount of time in the +handler (sometimes measured in milliseconds). Obviously this is a problem if +you are trying to keep event service latencies down in the microsecond range. + +The hardware latency detector works by hogging all of the cpus for configurable +amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter +for some period, then looking for gaps in the TSC data. Any gap indicates a +time when the polling was interrupted and since the machine is stopped and +interrupts turned off the only thing that could do that would be an SMI. + +Note that the SMI detector should *NEVER* be used in a production environment. +It is intended to be run manually to determine if the hardware platform has a +problem with long system firmware service routines. + +Usage: +------ + +Loading the module hwlat_detector passing the parameter "enabled=1" (or by +setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only +step required to start the hwlat_detector. It is possible to redefine the +threshold in microseconds (us) above which latency spikes will be taken +into account (parameter "threshold="). + +Example: + + # modprobe hwlat_detector enabled=1 threshold=100 + +After the module is loaded, it creates a directory named "hwlat_detector" under +the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary +to have debugfs mounted, which might be on /sys/debug on your system. + +The /debug/hwlat_detector interface contains the following files: + +count - number of latency spikes observed since last reset +enable - a global enable/disable toggle (0/1), resets count +max - maximum hardware latency actually observed (usecs) +sample - a pipe from which to read current raw sample data + in the format + (can be opened O_NONBLOCK for a single sample) +threshold - minimum latency value to be considered (usecs) +width - time period to sample with CPUs held (usecs) + must be less than the total window size (enforced) +window - total period of sampling, width being inside (usecs) + +By default we will set width to 500,000 and window to 1,000,000, meaning that +we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we +observe any latencies that exceed the threshold (initially 100 usecs), +then we write to a global sample ring buffer of 8K samples, which is +consumed by reading from the "sample" (pipe) debugfs file interface. diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index 8cb4d78..d458683 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -57,10 +57,17 @@ On PowerPC - Press 'ALT - Print Screen (or F13) - , On other - If you know of the key combos for other architectures, please let me know so I can add them to this section. -On all - write a character to /proc/sysrq-trigger. e.g.: - +On all - write a character to /proc/sysrq-trigger, e.g.: echo t > /proc/sysrq-trigger +On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g. + echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq + Send an ICMP echo request with this pattern plus the particular + SysRq command key. Example: + # ping -c1 -s57 -p0102030468 + will trigger the SysRq-H (help) command. + + * What are the 'command' keys? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 'b' - Will immediately reboot the system without syncing or unmounting diff --git a/Documentation/trace/histograms.txt b/Documentation/trace/histograms.txt new file mode 100644 index 0000000..6f2aeab --- /dev/null +++ b/Documentation/trace/histograms.txt @@ -0,0 +1,186 @@ + Using the Linux Kernel Latency Histograms + + +This document gives a short explanation how to enable, configure and use +latency histograms. Latency histograms are primarily relevant in the +context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT) +and are used in the quality management of the Linux real-time +capabilities. + + +* Purpose of latency histograms + +A latency histogram continuously accumulates the frequencies of latency +data. There are two types of histograms +- potential sources of latencies +- effective latencies + + +* Potential sources of latencies + +Potential sources of latencies are code segments where interrupts, +preemption or both are disabled (aka critical sections). To create +histograms of potential sources of latency, the kernel stores the time +stamp at the start of a critical section, determines the time elapsed +when the end of the section is reached, and increments the frequency +counter of that latency value - irrespective of whether any concurrently +running process is affected by latency or not. +- Configuration items (in the Kernel hacking/Tracers submenu) + CONFIG_INTERRUPT_OFF_LATENCY + CONFIG_PREEMPT_OFF_LATENCY + + +* Effective latencies + +Effective latencies are actually occuring during wakeup of a process. To +determine effective latencies, the kernel stores the time stamp when a +process is scheduled to be woken up, and determines the duration of the +wakeup time shortly before control is passed over to this process. Note +that the apparent latency in user space may be somewhat longer, since the +process may be interrupted after control is passed over to it but before +the execution in user space takes place. Simply measuring the interval +between enqueuing and wakeup may also not appropriate in cases when a +process is scheduled as a result of a timer expiration. The timer may have +missed its deadline, e.g. due to disabled interrupts, but this latency +would not be registered. Therefore, the offsets of missed timers are +recorded in a separate histogram. If both wakeup latency and missed timer +offsets are configured and enabled, a third histogram may be enabled that +records the overall latency as a sum of the timer latency, if any, and the +wakeup latency. This histogram is called "timerandwakeup". +- Configuration items (in the Kernel hacking/Tracers submenu) + CONFIG_WAKEUP_LATENCY + CONFIG_MISSED_TIMER_OFSETS + + +* Usage + +The interface to the administration of the latency histograms is located +in the debugfs file system. To mount it, either enter + +mount -t sysfs nodev /sys +mount -t debugfs nodev /sys/kernel/debug + +from shell command line level, or add + +nodev /sys sysfs defaults 0 0 +nodev /sys/kernel/debug debugfs defaults 0 0 + +to the file /etc/fstab. All latency histogram related files are then +available in the directory /sys/kernel/debug/tracing/latency_hist. A +particular histogram type is enabled by writing non-zero to the related +variable in the /sys/kernel/debug/tracing/latency_hist/enable directory. +Select "preemptirqsoff" for the histograms of potential sources of +latencies and "wakeup" for histograms of effective latencies etc. The +histogram data - one per CPU - are available in the files + +/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx +/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx +/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx +/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx +/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx +/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx +/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx + +The histograms are reset by writing non-zero to the file "reset" in a +particular latency directory. To reset all latency data, use + +#!/bin/sh + +TRACINGDIR=/sys/kernel/debug/tracing +HISTDIR=$TRACINGDIR/latency_hist + +if test -d $HISTDIR +then + cd $HISTDIR + for i in `find . | grep /reset$` + do + echo 1 >$i + done +fi + + +* Data format + +Latency data are stored with a resolution of one microsecond. The +maximum latency is 10,240 microseconds. The data are only valid, if the +overflow register is empty. Every output line contains the latency in +microseconds in the first row and the number of samples in the second +row. To display only lines with a positive latency count, use, for +example, + +grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0 + +#Minimum latency: 0 microseconds. +#Average latency: 0 microseconds. +#Maximum latency: 25 microseconds. +#Total samples: 3104770694 +#There are 0 samples greater or equal than 10240 microseconds +#usecs samples + 0 2984486876 + 1 49843506 + 2 58219047 + 3 5348126 + 4 2187960 + 5 3388262 + 6 959289 + 7 208294 + 8 40420 + 9 4485 + 10 14918 + 11 18340 + 12 25052 + 13 19455 + 14 5602 + 15 969 + 16 47 + 17 18 + 18 14 + 19 1 + 20 3 + 21 2 + 22 5 + 23 2 + 25 1 + + +* Wakeup latency of a selected process + +To only collect wakeup latency data of a particular process, write the +PID of the requested process to + +/sys/kernel/debug/tracing/latency_hist/wakeup/pid + +PIDs are not considered, if this variable is set to 0. + + +* Details of the process with the highest wakeup latency so far + +Selected data of the process that suffered from the highest wakeup +latency that occurred in a particular CPU are available in the file + +/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx. + +In addition, other relevant system data at the time when the +latency occurred are given. + +The format of the data is (all in one line): + () \ +<- + +The value of is only relevant in the combined timer +and wakeup latency recording. In the wakeup recording, it is +always 0, in the missed_timer_offsets recording, it is the same +as . + +When retrospectively searching for the origin of a latency and +tracing was not enabled, it may be helpful to know the name and +some basic data of the task that (finally) was switching to the +late real-tlme task. In addition to the victim's data, also the +data of the possible culprit are therefore displayed after the +"<-" symbol. + +Finally, the timestamp of the time when the latency occurred +in . after the most recent system boot +is provided. + +These data are also reset when the wakeup histogram is reset. diff --git a/arch/Kconfig b/arch/Kconfig index 00e3702..8b1a614 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -6,6 +6,7 @@ config OPROFILE tristate "OProfile system profiling" depends on PROFILING depends on HAVE_OPROFILE + depends on !PREEMPT_RT_FULL select RING_BUFFER select RING_BUFFER_ALLOW_SWAP help diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 0c4132d..fb9eaa4 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -108,7 +108,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, /* If we're in an interrupt context, or have no user context, we must not take the fault. */ - if (!mm || in_atomic()) + if (!mm || pagefault_disabled()) goto no_context; #ifdef CONFIG_ALPHA_LARGE_VMALLOC diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 18a9f5e..b34ff02 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -19,6 +19,7 @@ config ARM select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HARDIRQS_SW_RESEND + select IRQ_FORCED_THREADING select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER @@ -47,6 +48,7 @@ config ARM select HAVE_MEMBLOCK select HAVE_OPROFILE if (HAVE_PERF_EVENTS) select HAVE_PERF_EVENTS + select HAVE_PREEMPT_LAZY select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h index fa09e6b..fbd0ba7 100644 --- a/arch/arm/include/asm/switch_to.h +++ b/arch/arm/include/asm/switch_to.h @@ -3,6 +3,14 @@ #include +#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM +void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p); +#else +static inline void +switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } +#endif + + /* * switch_to(prev, next) should switch from task `prev' to `next' * `prev' will never be the same as `next'. schedule() itself @@ -12,6 +20,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info #define switch_to(prev,next,last) \ do { \ + switch_kmaps(prev, next); \ last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ } while (0) diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index f00b569..1f24211 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -50,6 +50,7 @@ struct cpu_context_save { struct thread_info { unsigned long flags; /* low level flags */ int preempt_count; /* 0 => preemptable, <0 => bug */ + int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ mm_segment_t addr_limit; /* address limit */ struct task_struct *task; /* main task structure */ struct exec_domain *exec_domain; /* execution domain */ @@ -148,6 +149,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define TIF_SIGPENDING 0 #define TIF_NEED_RESCHED 1 #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ +#define TIF_NEED_RESCHED_LAZY 3 #define TIF_SYSCALL_TRACE 8 #define TIF_SYSCALL_AUDIT 9 #define TIF_SYSCALL_TRACEPOINT 10 @@ -160,6 +162,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index ee68cce..b609861 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -53,6 +53,7 @@ int main(void) BLANK(); DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); + DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); DEFINE(TI_TASK, offsetof(struct thread_info, task)); DEFINE(TI_EXEC_DOMAIN, offsetof(struct thread_info, exec_domain)); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 32640ae..a7f2e70 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -205,11 +205,18 @@ __irq_svc: #ifdef CONFIG_PREEMPT get_thread_info tsk ldr r8, [tsk, #TI_PREEMPT] @ get preempt count - ldr r0, [tsk, #TI_FLAGS] @ get flags teq r8, #0 @ if preempt count != 0 + bne 1f @ return from exeption + ldr r0, [tsk, #TI_FLAGS] @ get flags + tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set + blne svc_preempt @ preempt! + + ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count + teq r8, #0 @ if preempt lazy count != 0 movne r0, #0 @ force flags to 0 - tst r0, #_TIF_NEED_RESCHED + tst r0, #_TIF_NEED_RESCHED_LAZY blne svc_preempt +1: #endif svc_exit r5, irq = 1 @ return from exception @@ -224,6 +231,8 @@ svc_preempt: 1: bl preempt_schedule_irq @ irq en/disable is done inside ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS tst r0, #_TIF_NEED_RESCHED + bne 1b + tst r0, #_TIF_NEED_RESCHED_LAZY moveq pc, r8 @ go again b 1b #endif diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 1f2740e..b32b043 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -118,7 +118,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) continue; } - err = request_irq(irq, handler, IRQF_NOBALANCING, "arm-pmu", + err = request_irq(irq, handler, + IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu", cpu_pmu); if (err) { pr_err("unable to request IRQ%d for ARM PMU counters\n", diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index ac4c2e5..b87a74f 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -436,6 +436,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } #ifdef CONFIG_MMU +/* + * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not + * initialized by pgtable_page_ctor() then a coredump of the vector page will + * fail. + */ +static int __init vectors_user_mapping_init_page(void) +{ + struct page *page; + unsigned long addr = 0xffff0000; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset_k(addr); + pud = pud_offset(pgd, addr); + pmd = pmd_offset(pud, addr); + page = pmd_page(*(pmd)); + + pgtable_page_ctor(page); + + return 0; +} +late_initcall(vectors_user_mapping_init_page); + #ifdef CONFIG_KUSER_HELPERS /* * The vectors page is always readable from user space for the diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 5a42c12..fbbe3ff 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -584,7 +584,8 @@ asmlinkage int do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) { do { - if (likely(thread_flags & _TIF_NEED_RESCHED)) { + if (likely(thread_flags & (_TIF_NEED_RESCHED | + _TIF_NEED_RESCHED_LAZY))) { schedule(); } else { if (unlikely(!user_mode(regs))) diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c index 180b302..54dd6af 100644 --- a/arch/arm/mach-at91/at91rm9200_time.c +++ b/arch/arm/mach-at91/at91rm9200_time.c @@ -134,6 +134,7 @@ clkevt32k_mode(enum clock_event_mode mode, struct clock_event_device *dev) break; case CLOCK_EVT_MODE_SHUTDOWN: case CLOCK_EVT_MODE_UNUSED: + remove_irq(AT91_ID_SYS, &at91rm9200_timer_irq); case CLOCK_EVT_MODE_RESUME: irqmask = 0; break; diff --git a/arch/arm/mach-at91/at91sam926x_time.c b/arch/arm/mach-at91/at91sam926x_time.c index 3a4bc2e..4f6af15 100644 --- a/arch/arm/mach-at91/at91sam926x_time.c +++ b/arch/arm/mach-at91/at91sam926x_time.c @@ -77,7 +77,7 @@ static struct clocksource pit_clk = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; - +static struct irqaction at91sam926x_pit_irq; /* * Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16) */ @@ -86,6 +86,8 @@ pit_clkevt_mode(enum clock_event_mode mode, struct clock_event_device *dev) { switch (mode) { case CLOCK_EVT_MODE_PERIODIC: + /* Set up irq handler */ + setup_irq(AT91_ID_SYS, &at91sam926x_pit_irq); /* update clocksource counter */ pit_cnt += pit_cycle * PIT_PICNT(pit_read(AT91_PIT_PIVR)); pit_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN @@ -98,6 +100,7 @@ pit_clkevt_mode(enum clock_event_mode mode, struct clock_event_device *dev) case CLOCK_EVT_MODE_UNUSED: /* disable irq, leaving the clocksource active */ pit_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN); + remove_irq(AT91_ID_SYS, &at91sam926x_pit_irq); break; case CLOCK_EVT_MODE_RESUME: break; diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c index a0e8ff7..68c8028 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -71,7 +71,7 @@ static void __iomem *scu_base_addr(void) return (void __iomem *)(S5P_VA_SCU); } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void __cpuinit exynos_secondary_init(unsigned int cpu) { @@ -84,8 +84,8 @@ static void __cpuinit exynos_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static int __cpuinit exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -97,7 +97,7 @@ static int __cpuinit exynos_boot_secondary(unsigned int cpu, struct task_struct * Set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -126,7 +126,7 @@ static int __cpuinit exynos_boot_secondary(unsigned int cpu, struct task_struct if (timeout == 0) { printk(KERN_ERR "cpu1 power enable failed"); - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return -ETIMEDOUT; } } @@ -165,7 +165,7 @@ static int __cpuinit exynos_boot_secondary(unsigned int cpu, struct task_struct * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c index 00cdb0a..4da2f47 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -30,7 +30,7 @@ extern void msm_secondary_startup(void); -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static inline int get_core_count(void) { @@ -50,8 +50,8 @@ static void __cpuinit msm_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static __cpuinit void prepare_cold_cpu(unsigned int cpu) @@ -88,7 +88,7 @@ static int __cpuinit msm_boot_secondary(unsigned int cpu, struct task_struct *id * set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -122,7 +122,7 @@ static int __cpuinit msm_boot_secondary(unsigned int cpu, struct task_struct *id * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index 2a551f9..6c9a3d5 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -44,7 +44,7 @@ u16 pm44xx_errata; /* SCU base address */ static void __iomem *scu_base; -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); void __iomem *omap4_get_scu_base(void) { @@ -68,8 +68,8 @@ static void __cpuinit omap4_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static int __cpuinit omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -83,7 +83,7 @@ static int __cpuinit omap4_boot_secondary(unsigned int cpu, struct task_struct * * Set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * Update the AuxCoreBoot0 with boot state for secondary core. @@ -160,7 +160,7 @@ static int __cpuinit omap4_boot_secondary(unsigned int cpu, struct task_struct * * Now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return 0; } diff --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c index 1c3de7b..3f13713 100644 --- a/arch/arm/mach-prima2/platsmp.c +++ b/arch/arm/mach-prima2/platsmp.c @@ -23,7 +23,7 @@ static void __iomem *scu_base; static void __iomem *rsc_base; -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static struct map_desc scu_io_desc __initdata = { .length = SZ_4K, @@ -56,8 +56,8 @@ static void __cpuinit sirfsoc_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static struct of_device_id rsc_ids[] = { @@ -95,7 +95,7 @@ static int __cpuinit sirfsoc_boot_secondary(unsigned int cpu, struct task_struct /* make sure write buffer is drained */ mb(); - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -128,7 +128,7 @@ static int __cpuinit sirfsoc_boot_secondary(unsigned int cpu, struct task_struct * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c index 9c4c722..ec5437d 100644 --- a/arch/arm/mach-spear/platsmp.c +++ b/arch/arm/mach-spear/platsmp.c @@ -20,7 +20,7 @@ #include #include "generic.h" -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void __iomem *scu_base = IOMEM(VA_SCU_BASE); @@ -36,8 +36,8 @@ static void __cpuinit spear13xx_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static int __cpuinit spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -48,7 +48,7 @@ static int __cpuinit spear13xx_boot_secondary(unsigned int cpu, struct task_stru * set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -75,7 +75,7 @@ static int __cpuinit spear13xx_boot_secondary(unsigned int cpu, struct task_stru * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c index 14d9046..85d6d14 100644 --- a/arch/arm/mach-ux500/platsmp.c +++ b/arch/arm/mach-ux500/platsmp.c @@ -52,7 +52,7 @@ static void __iomem *scu_base_addr(void) return NULL; } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void __cpuinit ux500_secondary_init(unsigned int cpu) { @@ -65,8 +65,8 @@ static void __cpuinit ux500_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } static int __cpuinit ux500_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -77,7 +77,7 @@ static int __cpuinit ux500_boot_secondary(unsigned int cpu, struct task_struct * * set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * The secondary processor is waiting to be released from @@ -98,7 +98,7 @@ static int __cpuinit ux500_boot_secondary(unsigned int cpu, struct task_struct * * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 5dbf13f..149bab5 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -279,7 +279,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; /* diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index 21b9e1b..bd41dd8 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -38,6 +38,7 @@ EXPORT_SYMBOL(kunmap); void *kmap_atomic(struct page *page) { + pte_t pte = mk_pte(page, kmap_prot); unsigned int idx; unsigned long vaddr; void *kmap; @@ -76,7 +77,10 @@ void *kmap_atomic(struct page *page) * in place, so the contained TLB flush ensures the TLB is updated * with the new mapping. */ - set_top_pte(vaddr, mk_pte(page, kmap_prot)); +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; +#endif + set_top_pte(vaddr, pte); return (void *)vaddr; } @@ -93,12 +97,15 @@ void __kunmap_atomic(void *kvaddr) if (cache_is_vivt()) __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = __pte(0); +#endif #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx)); - set_top_pte(vaddr, __pte(0)); #else (void) idx; /* to kill a warning */ #endif + set_top_pte(vaddr, __pte(0)); kmap_atomic_idx_pop(); } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { /* this address was obtained through kmap_high_get() */ @@ -110,6 +117,7 @@ EXPORT_SYMBOL(__kunmap_atomic); void *kmap_atomic_pfn(unsigned long pfn) { + pte_t pte = pfn_pte(pfn, kmap_prot); unsigned long vaddr; int idx, type; @@ -121,7 +129,10 @@ void *kmap_atomic_pfn(unsigned long pfn) #ifdef CONFIG_DEBUG_HIGHMEM BUG_ON(!pte_none(get_top_pte(vaddr))); #endif - set_top_pte(vaddr, pfn_pte(pfn, kmap_prot)); +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; +#endif + set_top_pte(vaddr, pte); return (void *)vaddr; } @@ -135,3 +146,29 @@ struct page *kmap_atomic_to_page(const void *ptr) return pte_page(get_top_pte(vaddr)); } + +#if defined CONFIG_PREEMPT_RT_FULL +void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) +{ + int i; + + /* + * Clear @prev's kmap_atomic mappings + */ + for (i = 0; i < prev_p->kmap_idx; i++) { + int idx = i + KM_TYPE_NR * smp_processor_id(); + + set_top_pte(__fix_to_virt(FIX_KMAP_BEGIN + idx), __pte(0)); + } + /* + * Restore @next_p's kmap_atomic mappings + */ + for (i = 0; i < next_p->kmap_idx; i++) { + int idx = i + KM_TYPE_NR * smp_processor_id(); + + if (!pte_none(next_p->kmap_pte[i])) + set_top_pte(__fix_to_virt(FIX_KMAP_BEGIN + idx), + next_p->kmap_pte[i]); + } +} +#endif diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c index 1e1b2d7..82c366b 100644 --- a/arch/arm/plat-versatile/platsmp.c +++ b/arch/arm/plat-versatile/platsmp.c @@ -31,7 +31,7 @@ static void __cpuinit write_pen_release(int val) outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1)); } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); void __cpuinit versatile_secondary_init(unsigned int cpu) { @@ -44,8 +44,8 @@ void __cpuinit versatile_secondary_init(unsigned int cpu) /* * Synchronise with the boot thread. */ - spin_lock(&boot_lock); - spin_unlock(&boot_lock); + raw_spin_lock(&boot_lock); + raw_spin_unlock(&boot_lock); } int __cpuinit versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -56,7 +56,7 @@ int __cpuinit versatile_boot_secondary(unsigned int cpu, struct task_struct *idl * Set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* * This is really belt and braces; we hold unintended secondary @@ -86,7 +86,7 @@ int __cpuinit versatile_boot_secondary(unsigned int cpu, struct task_struct *idl * now the secondary core is starting up let it run its * calibrations, then wait for it to finish */ - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return pen_release != -1 ? -ENOSYS : 0; } diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index b2f2d2d..9577e69 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs) * If we're in an interrupt or have no user context, we must * not take the fault... */ - if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM)) + if (!mm || regs->sr & SYSREG_BIT(GM) || pagefault_disabled()) goto no_context; local_irq_enable(); diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 73312ab..1a403d9 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -114,7 +114,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs, * user context, we must not take the fault. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; retry: diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 331c1e2..e87972c 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; down_read(&mm->mmap_sem); diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 6cf0341..dd88415 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -98,7 +98,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re /* * If we're in an interrupt or have no user context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; #ifdef CONFIG_VIRTUAL_MEM_MAP diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index 3cdfa9c..6945056 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -114,7 +114,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, * If we're in an interrupt or have no user context or are running in an * atomic region then we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto bad_area_nosemaphore; /* When running in the kernel we expect faults to occur only to diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index a563727..9ea40db 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -85,7 +85,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; retry: diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index 731f739..81bb846 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -108,7 +108,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11) is_write = 0; - if (unlikely(in_atomic() || !mm)) { + if (unlikely(!mm || pagefault_disabled())) { if (kernel_mode(regs)) goto bad_area_nosemaphore; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index e53e2b4..a8cc8c3 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2115,7 +2115,7 @@ config CPU_R4400_WORKAROUNDS # config HIGHMEM bool "High Memory Support" - depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM + depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !PREEMPT_RT_FULL config CPU_SUPPORTS_HIGHMEM bool diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index fd3ef2c..85cf081 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -572,6 +572,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { local_irq_enable(); + preempt_check_resched(); /* deal with pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 0fead53..cd03005 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -89,7 +89,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, unsigned long writ * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto bad_area_nosemaphore; retry: diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index d48a84f..34a83b9 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -168,7 +168,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; retry: diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index f247a34..39037ba 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -177,7 +177,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, int fault; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; retry: diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index fe404e7..95e5d5c 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -60,10 +60,11 @@ config LOCKDEP_SUPPORT config RWSEM_GENERIC_SPINLOCK bool + default y if PREEMPT_RT_FULL config RWSEM_XCHGADD_ALGORITHM bool - default y + default y if !PREEMPT_RT_FULL config GENERIC_LOCKBREAK bool @@ -132,6 +133,7 @@ config PPC select GENERIC_CLOCKEVENTS select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER + select HAVE_PREEMPT_LAZY select HAVE_MOD_ARCH_SPECIFIC select MODULES_USE_ELF_RELA select CLONE_BACKWARDS @@ -285,7 +287,7 @@ menu "Kernel options" config HIGHMEM bool "High memory support" - depends on PPC32 + depends on PPC32 && !PREEMPT_RT_FULL source kernel/Kconfig.hz source kernel/Kconfig.preempt diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index ba7b197..f50711f 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -43,6 +43,8 @@ struct thread_info { int cpu; /* cpu we're on */ int preempt_count; /* 0 => preemptable, <0 => BUG */ + int preempt_lazy_count; /* 0 => preemptable, + <0 => BUG */ struct restart_block restart_block; unsigned long local_flags; /* private flags for thread */ @@ -90,8 +92,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ -#define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling - TIF_NEED_RESCHED */ +#define TIF_NEED_RESCHED_LAZY 3 /* lazy rescheduling necessary */ #define TIF_32BIT 4 /* 32 bit binary */ #define TIF_PERFMON_WORK 5 /* work for pfm_handle_work() */ #define TIF_PERFMON_CTXSW 6 /* perfmon needs ctxsw calls */ @@ -107,6 +108,8 @@ static inline struct thread_info *current_thread_info(void) #define TIF_EMULATE_STACK_STORE 16 /* Is an instruction emulation for stack store? */ #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ +#define TIF_POLLING_NRFLAG 18 /* true if poll_idle() is polling + TIF_NEED_RESCHED */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1< @@ -239,12 +239,12 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) RFI b . /* prevent speculative execution */ -syscall_error: +syscall_error: oris r5,r5,0x1000 /* Set SO bit in CR */ neg r3,r3 std r5,_CCR(r1) b .Lsyscall_error_cont - + /* Traced system call support */ syscall_dotrace: bl .save_nvgprs @@ -270,7 +270,7 @@ syscall_dotrace: syscall_enosys: li r3,-ENOSYS b syscall_exit - + syscall_exit_work: #ifdef CONFIG_PPC_BOOK3S mtmsrd r10,1 /* Restore RI */ @@ -333,7 +333,7 @@ _GLOBAL(save_nvgprs) std r0,_TRAP(r1) blr - + /* * The sigsuspend and rt_sigsuspend system calls can call do_signal * and thus put the process into the stopped state where we might @@ -406,7 +406,7 @@ DSCR_DEFAULT: * the fork code also. * * The code which creates the new task context is in 'copy_thread' - * in arch/powerpc/kernel/process.c + * in arch/powerpc/kernel/process.c */ .align 7 _GLOBAL(_switch) @@ -653,7 +653,7 @@ _GLOBAL(ret_from_except_lite) andi. r0,r4,_TIF_USER_WORK_MASK beq restore - andi. r0,r4,_TIF_NEED_RESCHED + andi. r0,r4,_TIF_NEED_RESCHED_MASK beq 1f bl .restore_interrupts SCHEDULE_USER @@ -703,10 +703,18 @@ resume_kernel: #ifdef CONFIG_PREEMPT /* Check if we need to preempt */ + lwz r8,TI_PREEMPT(r9) + cmpwi 0,r8,0 /* if non-zero, just restore regs and return */ + bne restore andi. r0,r4,_TIF_NEED_RESCHED + bne+ check_count + + andi. r0,r4,_TIF_NEED_RESCHED_LAZY beq+ restore + lwz r8,TI_PREEMPT_LAZY(r9) + /* Check that preempt_count() == 0 and interrupts are enabled */ - lwz r8,TI_PREEMPT(r9) +check_count: cmpwi cr1,r8,0 ld r0,SOFTE(r1) cmpdi r0,0 @@ -723,7 +731,7 @@ resume_kernel: /* Re-test flags and eventually loop */ CURRENT_THREAD_INFO(r9, r1) ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_NEED_RESCHED + andi. r0,r4,_TIF_NEED_RESCHED_MASK bne 1b /* @@ -890,7 +898,7 @@ restore_check_irq_replay: bl .__check_irq_replay cmpwi cr0,r3,0 beq restore_no_replay - + /* * We need to re-emit an interrupt. We do so by re-using our * existing exception frame. We first change the trap value, @@ -932,7 +940,7 @@ restore_check_irq_replay: b .ret_from_except #endif /* CONFIG_PPC_DOORBELL */ 1: b .ret_from_except /* What else to do here ? */ - + unrecov_restore: addi r3,r1,STACK_FRAME_OVERHEAD bl .unrecoverable_exception @@ -944,7 +952,7 @@ unrecov_restore: * called with the MMU off. * * In addition, we need to be in 32b mode, at least for now. - * + * * Note: r3 is an input parameter to rtas, so don't trash it... */ _GLOBAL(enter_rtas) @@ -978,7 +986,7 @@ _GLOBAL(enter_rtas) li r0,0 mtcr r0 -#ifdef CONFIG_BUG +#ifdef CONFIG_BUG /* There is no way it is acceptable to get here with interrupts enabled, * check it with the asm equivalent of WARN_ON */ @@ -986,7 +994,7 @@ _GLOBAL(enter_rtas) 1: tdnei r0,0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING #endif - + /* Hard-disable interrupts */ mfmsr r6 rldicl r7,r6,48,1 @@ -1000,7 +1008,7 @@ _GLOBAL(enter_rtas) std r1,PACAR1(r13) std r6,PACASAVEDMSR(r13) - /* Setup our real return addr */ + /* Setup our real return addr */ LOAD_REG_ADDR(r4,.rtas_return_loc) clrldi r4,r4,2 /* convert to realmode address */ mtlr r4 @@ -1008,7 +1016,7 @@ _GLOBAL(enter_rtas) li r0,0 ori r0,r0,MSR_EE|MSR_SE|MSR_BE|MSR_RI andc r0,r6,r0 - + li r9,1 rldicr r9,r9,MSR_SF_LG,(63-MSR_SF_LG) ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI @@ -1019,7 +1027,7 @@ _GLOBAL(enter_rtas) LOAD_REG_ADDR(r4, rtas) ld r5,RTASENTRY(r4) /* get the rtas->entry value */ ld r4,RTASBASE(r4) /* get the rtas->base value */ - + mtspr SPRN_SRR0,r5 mtspr SPRN_SRR1,r6 rfid @@ -1037,9 +1045,9 @@ _STATIC(rtas_return_loc) mfmsr r6 li r0,MSR_RI andc r6,r6,r0 - sync + sync mtmsrd r6 - + ld r1,PACAR1(r4) /* Restore our SP */ ld r4,PACASAVEDMSR(r4) /* Restore our MSR */ @@ -1137,7 +1145,7 @@ _GLOBAL(enter_prom) REST_10GPRS(22, r1) ld r4,_CCR(r1) mtcr r4 - + addi r1,r1,PROM_FRAME_SIZE ld r0,16(r1) mtlr r0 diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index ea185e0..7514bc4 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -603,6 +603,7 @@ void irq_ctx_init(void) } } +#ifndef CONFIG_PREEMPT_RT_FULL static inline void do_softirq_onstack(void) { struct thread_info *curtp, *irqtp; @@ -639,6 +640,7 @@ void do_softirq(void) local_irq_restore(flags); } +#endif irq_hw_number_t virq_to_hw(unsigned int virq) { diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index e469f30..7deab8a 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -36,6 +36,7 @@ .text +#ifndef CONFIG_PREEMPT_RT_FULL _GLOBAL(call_do_softirq) mflr r0 stw r0,4(r1) @@ -46,6 +47,7 @@ _GLOBAL(call_do_softirq) lwz r0,4(r1) mtlr r0 blr +#endif _GLOBAL(call_handle_irq) mflr r0 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 6820e45..9ff6d24 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -29,6 +29,7 @@ .text +#ifndef CONFIG_PREEMPT_RT_FULL _GLOBAL(call_do_softirq) mflr r0 std r0,16(r1) @@ -39,6 +40,7 @@ _GLOBAL(call_do_softirq) ld r0,16(r1) mtlr r0 blr +#endif _GLOBAL(call_handle_irq) ld r8,0(r6) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 8726779..87f730e 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -264,7 +264,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, if (!arch_irq_disabled_regs(regs)) local_irq_enable(); - if (in_atomic() || mm == NULL) { + if (in_atomic() || mm == NULL || pagefault_disabled()) { if (!user_mode(regs)) { rc = SIGSEGV; goto bail; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c index b89ef65..2898b73 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c @@ -340,7 +340,7 @@ static int mpc52xx_irqhost_map(struct irq_domain *h, unsigned int virq, { int l1irq; int l2irq; - struct irq_chip *irqchip; + struct irq_chip *uninitialized_var(irqchip); void *hndlr; int type; u32 reg; diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c index 1e12108..806cbbd 100644 --- a/arch/powerpc/platforms/8xx/m8xx_setup.c +++ b/arch/powerpc/platforms/8xx/m8xx_setup.c @@ -43,6 +43,7 @@ static irqreturn_t timebase_interrupt(int irq, void *dev) static struct irqaction tbint_irqaction = { .handler = timebase_interrupt, + .flags = IRQF_NO_THREAD, .name = "tbint", }; diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index d4fa03f..5e6ff38 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -120,6 +120,7 @@ static irqreturn_t cpm_error_interrupt(int irq, void *dev) static struct irqaction cpm_error_irqaction = { .handler = cpm_error_interrupt, + .flags = IRQF_NO_THREAD, .name = "error", }; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 047c3e4..d4f4acf 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -296,7 +296,8 @@ static inline int do_exception(struct pt_regs *regs, int access) * user context. */ fault = VM_FAULT_BADCONTEXT; - if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm)) + if (unlikely(!user_space_fault(trans_exc_code) || + !mm || pagefault_disabled())) goto out; address = trans_exc_code & __FAIL_ADDR_MASK; @@ -440,7 +441,8 @@ void __kprobes do_asce_exception(struct pt_regs *regs) clear_tsk_thread_flag(current, TIF_PER_TRAP); trans_exc_code = regs->int_parm_long; - if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm)) + if (unlikely(!user_space_fault(trans_exc_code) || !mm || + pagefault_disabled())) goto no_context; down_read(&mm->mmap_sem); diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 47b600e..59fccbe 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -72,7 +72,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto bad_area_nosemaphore; down_read(&mm->mmap_sem); diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index 063af10..ae4b141 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -149,6 +149,7 @@ void irq_ctx_exit(int cpu) hardirq_ctx[cpu] = NULL; } +#ifndef CONFIG_PREEMPT_RT_FULL asmlinkage void do_softirq(void) { unsigned long flags; @@ -191,6 +192,7 @@ asmlinkage void do_softirq(void) local_irq_restore(flags); } +#endif #else static inline void handle_one_irq(unsigned int irq) { diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 1f49c28..8ff1613 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -440,7 +440,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, * If we're in an interrupt, have no user context or are running * in an atomic region then we must not take the fault: */ - if (unlikely(in_atomic() || !mm)) { + if (unlikely(!mm || pagefault_disabled())) { bad_area_nosemaphore(regs, error_code, address); return; } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 9ac9f16..6787bd3 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -521,6 +521,10 @@ menu "Executable file formats" source "fs/Kconfig.binfmt" +config EARLY_PRINTK + bool + default y + config COMPAT bool depends on SPARC64 diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 9bcbbe2..1bc5cd8 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -698,6 +698,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs) set_irq_regs(old_regs); } +#ifndef CONFIG_PREEMPT_RT_FULL void do_softirq(void) { unsigned long flags; @@ -723,6 +724,7 @@ void do_softirq(void) local_irq_restore(flags); } +#endif #ifdef CONFIG_HOTPLUG_CPU void fixup_irqs(void) diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index 1434526..0884ccd 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -309,6 +309,7 @@ void __init setup_arch(char **cmdline_p) boot_flags_init(*cmdline_p); + early_console = &prom_early_console; register_console(&prom_early_console); printk("ARCH: "); diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 1378554..6482b87 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -551,6 +551,12 @@ static void __init init_sparc64_elf_hwcap(void) pause_patch(); } +static inline void register_prom_console(void) +{ + early_console = &prom_early_console; + register_console(&prom_early_console); +} + void __init setup_arch(char **cmdline_p) { /* Initialize PROM console and command line. */ @@ -562,7 +568,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EARLYFB if (btext_find_display()) #endif - register_console(&prom_early_console); + register_prom_console(); if (tlb_type == hypervisor) printk("ARCH: SUN4V\n"); diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index e98bfda..18cbe13f 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -200,7 +200,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 5062ff3..2764ac6 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -321,7 +321,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto intr_or_no_mm; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 3d2b81c..1ba0ccc 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -360,7 +360,7 @@ static int handle_page_fault(struct pt_regs *regs, * If we're in an interrupt, have no user context or are running in an * atomic region then we must not take the fault. */ - if (in_atomic() || !mm) { + if (!mm || pagefault_disabled()) { vma = NULL; /* happy compiler */ goto bad_area_nosemaphore; } diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 089f398..991b33a 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -39,7 +39,7 @@ int handle_page_fault(unsigned long address, unsigned long ip, * If the fault was during atomic operation, don't take the fault, just * fail. */ - if (in_atomic()) + if (pagefault_disabled()) goto out_nosemaphore; retry: diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index fe120da..8dc65e2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -121,6 +121,7 @@ config X86 select OLD_SIGACTION if X86_32 select COMPAT_OLD_SIGACTION if IA32_EMULATION select RTC_LIB + select HAVE_PREEMPT_LAZY config INSTRUCTION_DECODER def_bool y @@ -177,8 +178,11 @@ config ARCH_MAY_HAVE_PC_FDC def_bool y depends on ISA_DMA_API +config RWSEM_GENERIC_SPINLOCK + def_bool PREEMPT_RT_FULL + config RWSEM_XCHGADD_ALGORITHM - def_bool y + def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL config GENERIC_CALIBRATE_DELAY def_bool y @@ -460,7 +464,7 @@ config X86_MDFLD select MFD_INTEL_MSIC ---help--- Medfield is Intel's Low Power Intel Architecture (LPIA) based Moblin - Internet Device(MID) platform. + Internet Device(MID) platform. Unlike standard x86 PCs, Medfield does not have many legacy devices nor standard legacy replacement devices/features. e.g. Medfield does not contain i8259, i8254, HPET, legacy BIOS, most of the io ports. @@ -796,7 +800,7 @@ config IOMMU_HELPER config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP && DEBUG_KERNEL - select CPUMASK_OFFSTACK + select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL ---help--- Enable maximum number of CPUS and NUMA Nodes for this architecture. If unsure, say N. diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index f80e668..3fbe870 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -252,14 +252,14 @@ static int ecb_encrypt(struct blkcipher_desc *desc, err = blkcipher_walk_virt(desc, &walk); desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, - nbytes & AES_BLOCK_MASK); + nbytes & AES_BLOCK_MASK); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = blkcipher_walk_done(desc, &walk, nbytes); } - kernel_fpu_end(); return err; } @@ -276,14 +276,14 @@ static int ecb_decrypt(struct blkcipher_desc *desc, err = blkcipher_walk_virt(desc, &walk); desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = blkcipher_walk_done(desc, &walk, nbytes); } - kernel_fpu_end(); return err; } @@ -300,14 +300,14 @@ static int cbc_encrypt(struct blkcipher_desc *desc, err = blkcipher_walk_virt(desc, &walk); desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK, walk.iv); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = blkcipher_walk_done(desc, &walk, nbytes); } - kernel_fpu_end(); return err; } @@ -324,14 +324,14 @@ static int cbc_decrypt(struct blkcipher_desc *desc, err = blkcipher_walk_virt(desc, &walk); desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - kernel_fpu_begin(); while ((nbytes = walk.nbytes)) { + kernel_fpu_begin(); aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK, walk.iv); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = blkcipher_walk_done(desc, &walk, nbytes); } - kernel_fpu_end(); return err; } @@ -364,18 +364,20 @@ static int ctr_crypt(struct blkcipher_desc *desc, err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - kernel_fpu_begin(); while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { + kernel_fpu_begin(); aesni_ctr_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes & AES_BLOCK_MASK, walk.iv); + kernel_fpu_end(); nbytes &= AES_BLOCK_SIZE - 1; err = blkcipher_walk_done(desc, &walk, nbytes); } if (walk.nbytes) { + kernel_fpu_begin(); ctr_crypt_final(ctx, &walk); + kernel_fpu_end(); err = blkcipher_walk_done(desc, &walk, 0); } - kernel_fpu_end(); return err; } diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 6c896fb..3cedb22 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -14,12 +14,21 @@ #define IRQ_STACK_ORDER 2 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER) -#define STACKFAULT_STACK 1 -#define DOUBLEFAULT_STACK 2 -#define NMI_STACK 3 -#define DEBUG_STACK 4 -#define MCE_STACK 5 -#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */ +#ifdef CONFIG_PREEMPT_RT_FULL +# define STACKFAULT_STACK 0 +# define DOUBLEFAULT_STACK 1 +# define NMI_STACK 2 +# define DEBUG_STACK 0 +# define MCE_STACK 3 +# define N_EXCEPTION_STACKS 3 /* hw limit: 7 */ +#else +# define STACKFAULT_STACK 1 +# define DOUBLEFAULT_STACK 2 +# define NMI_STACK 3 +# define DEBUG_STACK 4 +# define MCE_STACK 5 +# define N_EXCEPTION_STACKS 5 /* hw limit: 7 */ +#endif #define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 35e67a4..6ec0792 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -23,6 +23,19 @@ typedef struct { unsigned long sig[_NSIG_WORDS]; } sigset_t; +/* + * Because some traps use the IST stack, we must keep preemption + * disabled while calling do_trap(), but do_trap() may call + * force_sig_info() which will grab the signal spin_locks for the + * task, which in PREEMPT_RT_FULL are mutexes. By defining + * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set + * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the + * trap. + */ +#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_X86_64) +#define ARCH_RT_DELAYS_SIGNAL_SEND +#endif + #ifndef CONFIG_COMPAT typedef sigset_t compat_sigset_t; #endif diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 6a99859..64fb5cb 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -57,7 +57,7 @@ */ static __always_inline void boot_init_stack_canary(void) { - u64 canary; + u64 uninitialized_var(canary); u64 tsc; #ifdef CONFIG_X86_64 @@ -68,8 +68,16 @@ static __always_inline void boot_init_stack_canary(void) * of randomness. The TSC only matters for very early init, * there it already has some randomness on most systems. Later * on during the bootup the random pool has true entropy too. + * + * For preempt-rt we need to weaken the randomness a bit, as + * we can't call into the random generator from atomic context + * due to locking constraints. We just leave canary + * uninitialized and use the TSC based randomness on top of + * it. */ +#ifndef CONFIG_PREEMPT_RT_FULL get_random_bytes(&canary, sizeof(canary)); +#endif tsc = __native_read_tsc(); canary += tsc + (tsc << 32UL); diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index a1df6e8..0365caf 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -30,6 +30,8 @@ struct thread_info { __u32 cpu; /* current CPU */ int preempt_count; /* 0 => preemptable, <0 => BUG */ + int preempt_lazy_count; /* 0 => lazy preemptable, + <0 => BUG */ mm_segment_t addr_limit; struct restart_block restart_block; void __user *sysenter_return; @@ -81,6 +83,7 @@ struct thread_info { #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ +#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */ #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ @@ -106,6 +109,7 @@ struct thread_info { #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) #define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) @@ -156,6 +160,8 @@ struct thread_info { #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG) +#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + #define PREEMPT_ACTIVE 0x10000000 #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 9ed796c..7f116f2 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2391,7 +2391,8 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg) static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) { /* If we are moving the irq we need to mask it */ - if (unlikely(irqd_is_setaffinity_pending(data))) { + if (unlikely(irqd_is_setaffinity_pending(data) && + !irqd_irq_inprogress(data))) { mask_ioapic(cfg); return true; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 2861082..a36d9cf 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -33,6 +33,7 @@ void common(void) { OFFSET(TI_status, thread_info, status); OFFSET(TI_addr_limit, thread_info, addr_limit); OFFSET(TI_preempt_count, thread_info, preempt_count); + OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count); BLANK(); OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index deeb48d..d39993b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1109,7 +1109,9 @@ DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); */ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, +#if DEBUG_STACK > 0 [DEBUG_STACK - 1] = DEBUG_STKSZ +#endif }; static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 9239504..aaf4b9b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -41,6 +42,7 @@ #include #include #include +#include #include #include @@ -1256,7 +1258,7 @@ void mce_log_therm_throt_event(__u64 status) static unsigned long check_interval = 5 * 60; /* 5 minutes */ static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ -static DEFINE_PER_CPU(struct timer_list, mce_timer); +static DEFINE_PER_CPU(struct hrtimer, mce_timer); static unsigned long mce_adjust_timer_default(unsigned long interval) { @@ -1266,13 +1268,10 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static void mce_timer_fn(unsigned long data) +static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer) { - struct timer_list *t = &__get_cpu_var(mce_timer); unsigned long iv; - WARN_ON(smp_processor_id() != data); - if (mce_available(__this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_poll_banks)); @@ -1293,9 +1292,11 @@ static void mce_timer_fn(unsigned long data) __this_cpu_write(mce_next_interval, iv); /* Might have become 0 after CMCI storm subsided */ if (iv) { - t->expires = jiffies + iv; - add_timer_on(t, smp_processor_id()); + hrtimer_forward_now(timer, ns_to_ktime( + jiffies_to_usecs(iv) * 1000ULL)); + return HRTIMER_RESTART; } + return HRTIMER_NORESTART; } /* @@ -1303,28 +1304,37 @@ static void mce_timer_fn(unsigned long data) */ void mce_timer_kick(unsigned long interval) { - struct timer_list *t = &__get_cpu_var(mce_timer); - unsigned long when = jiffies + interval; + struct hrtimer *t = &__get_cpu_var(mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer_pinned(t, when); + if (hrtimer_active(t)) { + s64 exp; + s64 intv_us; + + intv_us = jiffies_to_usecs(interval); + exp = ktime_to_us(hrtimer_expires_remaining(t)); + if (intv_us < exp) { + hrtimer_cancel(t); + hrtimer_start_range_ns(t, + ns_to_ktime(intv_us * 1000), + 0, HRTIMER_MODE_REL_PINNED); + } } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); + hrtimer_start_range_ns(t, + ns_to_ktime(jiffies_to_usecs(interval) * 1000ULL), + 0, HRTIMER_MODE_REL_PINNED); } if (interval < iv) __this_cpu_write(mce_next_interval, interval); } -/* Must not be called in IRQ context where del_timer_sync() can deadlock */ +/* Must not be called in IRQ context where hrtimer_cancel() can deadlock */ static void mce_timer_delete_all(void) { int cpu; for_each_online_cpu(cpu) - del_timer_sync(&per_cpu(mce_timer, cpu)); + hrtimer_cancel(&per_cpu(mce_timer, cpu)); } static void mce_do_trigger(struct work_struct *work) @@ -1334,6 +1344,63 @@ static void mce_do_trigger(struct work_struct *work) static DECLARE_WORK(mce_trigger_work, mce_do_trigger); +static void __mce_notify_work(void) +{ + /* Not more than two messages every minute */ + static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); + + /* wake processes polling /dev/mcelog */ + wake_up_interruptible(&mce_chrdev_wait); + + /* + * There is no risk of missing notifications because + * work_pending is always cleared before the function is + * executed. + */ + if (mce_helper[0] && !work_pending(&mce_trigger_work)) + schedule_work(&mce_trigger_work); + + if (__ratelimit(&ratelimit)) + pr_info(HW_ERR "Machine check events logged\n"); +} + +#ifdef CONFIG_PREEMPT_RT_FULL +struct task_struct *mce_notify_helper; + +static int mce_notify_helper_thread(void *unused) +{ + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + if (kthread_should_stop()) + break; + __mce_notify_work(); + } + return 0; +} + +static int mce_notify_work_init(void) +{ + mce_notify_helper = kthread_run(mce_notify_helper_thread, NULL, + "mce-notify"); + if (!mce_notify_helper) + return -ENOMEM; + + return 0; +} + +static void mce_notify_work(void) +{ + wake_up_process(mce_notify_helper); +} +#else +static void mce_notify_work(void) +{ + __mce_notify_work(); +} +static inline int mce_notify_work_init(void) { return 0; } +#endif + /* * Notify the user(s) about new machine check events. * Can be called from interrupt context, but not from machine check/NMI @@ -1341,19 +1408,8 @@ static DECLARE_WORK(mce_trigger_work, mce_do_trigger); */ int mce_notify_irq(void) { - /* Not more than two messages every minute */ - static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); - if (test_and_clear_bit(0, &mce_need_notify)) { - /* wake processes polling /dev/mcelog */ - wake_up_interruptible(&mce_chrdev_wait); - - if (mce_helper[0]) - schedule_work(&mce_trigger_work); - - if (__ratelimit(&ratelimit)) - pr_info(HW_ERR "Machine check events logged\n"); - + mce_notify_work(); return 1; } return 0; @@ -1624,7 +1680,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct timer_list *t) +static void mce_start_timer(unsigned int cpu, struct hrtimer *t) { unsigned long iv = mce_adjust_timer(check_interval * HZ); @@ -1633,16 +1689,17 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t) if (mca_cfg.ignore_ce || !iv) return; - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, smp_processor_id()); + hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL), + 0, HRTIMER_MODE_REL_PINNED); } static void __mcheck_cpu_init_timer(void) { - struct timer_list *t = &__get_cpu_var(mce_timer); + struct hrtimer *t = &__get_cpu_var(mce_timer); unsigned int cpu = smp_processor_id(); - setup_timer(t, mce_timer_fn, cpu); + hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + t->function = mce_timer_fn; mce_start_timer(cpu, t); } @@ -2299,6 +2356,8 @@ static void __cpuinit mce_disable_cpu(void *h) if (!mce_available(__this_cpu_ptr(&cpu_info))) return; + hrtimer_cancel(&__get_cpu_var(mce_timer)); + if (!(action & CPU_TASKS_FROZEN)) cmci_clear(); for (i = 0; i < mca_cfg.banks; i++) { @@ -2325,6 +2384,7 @@ static void __cpuinit mce_reenable_cpu(void *h) if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); } + __mcheck_cpu_init_timer(); } /* Get notified when a cpu comes on/off. Be hotplug friendly. */ @@ -2332,7 +2392,6 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; - struct timer_list *t = &per_cpu(mce_timer, cpu); switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: @@ -2348,11 +2407,9 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_DOWN_PREPARE: smp_call_function_single(cpu, mce_disable_cpu, &action, 1); - del_timer_sync(t); break; case CPU_DOWN_FAILED: smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); - mce_start_timer(cpu, t); break; } @@ -2414,6 +2471,8 @@ static __init int mcheck_init_device(void) /* register character device /dev/mcelog */ misc_register(&mce_chrdev_device); + err = mce_notify_work_init(); + return err; } device_initcall_sync(mcheck_init_device); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index addb207..52b4bcd 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -21,10 +21,14 @@ (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2) static char x86_stack_ids[][8] = { +#if DEBUG_STACK > 0 [ DEBUG_STACK-1 ] = "#DB", +#endif [ NMI_STACK-1 ] = "NMI", [ DOUBLEFAULT_STACK-1 ] = "#DF", +#if STACKFAULT_STACK > 0 [ STACKFAULT_STACK-1 ] = "#SS", +#endif [ MCE_STACK-1 ] = "#MC", #if DEBUG_STKSZ > EXCEPTION_STKSZ [ N_EXCEPTION_STACKS ... diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 94e52cf..edf727d 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -364,14 +364,22 @@ ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? jnz restore_all -need_resched: movl TI_flags(%ebp), %ecx # need_resched set ? testb $_TIF_NEED_RESCHED, %cl + jnz 1f + + cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? + jnz restore_all + testl $_TIF_NEED_RESCHED_LAZY, %ecx jz restore_all - testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? + +1: testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all call preempt_schedule_irq - jmp need_resched + movl TI_flags(%ebp), %ecx # need_resched set ? + testl $_TIF_NEED_RESCHED_MASK, %ecx + jnz 1b + jmp restore_all END(resume_kernel) #endif CFI_ENDPROC @@ -607,7 +615,7 @@ ENDPROC(system_call) ALIGN RING0_PTREGS_FRAME # can't unwind into user space anyway work_pending: - testb $_TIF_NEED_RESCHED, %cl + testl $_TIF_NEED_RESCHED_MASK, %ecx jz work_notifysig work_resched: call schedule @@ -620,7 +628,7 @@ work_resched: andl $_TIF_WORK_MASK, %ecx # is there any work to be done other # than syscall tracing? jz restore_all - testb $_TIF_NEED_RESCHED, %cl + testl $_TIF_NEED_RESCHED_MASK, %ecx jnz work_resched work_notifysig: # deal with pending signals and diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 7ac938a..e104639 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -673,8 +673,8 @@ sysret_check: /* Handle reschedules */ /* edx: work, edi: workmask */ sysret_careful: - bt $TIF_NEED_RESCHED,%edx - jnc sysret_signal + testl $_TIF_NEED_RESCHED_MASK,%edx + jz sysret_signal TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi @@ -786,8 +786,8 @@ GLOBAL(int_with_check) /* First do a reschedule test. */ /* edx: work, edi: workmask */ int_careful: - bt $TIF_NEED_RESCHED,%edx - jnc int_very_careful + testl $_TIF_NEED_RESCHED_MASK,%edx + jz int_very_careful TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi @@ -1086,8 +1086,8 @@ bad_iret: /* edi: workmask, edx: work */ retint_careful: CFI_RESTORE_STATE - bt $TIF_NEED_RESCHED,%edx - jnc retint_signal + testl $_TIF_NEED_RESCHED_MASK,%edx + jz retint_signal TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) pushq_cfi %rdi @@ -1120,9 +1120,15 @@ retint_signal: ENTRY(retint_kernel) cmpl $0,TI_preempt_count(%rcx) jnz retint_restore_args - bt $TIF_NEED_RESCHED,TI_flags(%rcx) + bt $TIF_NEED_RESCHED,TI_flags(%rcx) + jc 1f + + cmpl $0,TI_preempt_lazy_count(%rcx) + jnz retint_restore_args + bt $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx) jnc retint_restore_args - bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ + +1: bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ jnc retint_restore_args call preempt_schedule_irq jmp exit_intr @@ -1334,6 +1340,7 @@ bad_gs: jmp 2b .previous +#ifndef CONFIG_PREEMPT_RT_FULL /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(call_softirq) CFI_STARTPROC @@ -1353,6 +1360,7 @@ ENTRY(call_softirq) ret CFI_ENDPROC END(call_softirq) +#endif #ifdef CONFIG_XEN zeroentry xen_hypervisor_callback xen_do_hypervisor_callback @@ -1522,7 +1530,7 @@ paranoid_userspace: movq %rsp,%rdi /* &pt_regs */ call sync_regs movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx + testl $_TIF_NEED_RESCHED_MASK,%ebx jnz paranoid_schedule movl %ebx,%edx /* arg3: thread flags */ TRACE_IRQS_ON diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 344faf8..f60ecc0 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -149,6 +149,7 @@ void __cpuinit irq_ctx_init(int cpu) cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu)); } +#ifndef CONFIG_PREEMPT_RT_FULL asmlinkage void do_softirq(void) { unsigned long flags; @@ -179,6 +180,7 @@ asmlinkage void do_softirq(void) local_irq_restore(flags); } +#endif bool handle_irq(unsigned irq, struct pt_regs *regs) { diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index d04d3ec..831f247 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -88,7 +88,7 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) return true; } - +#ifndef CONFIG_PREEMPT_RT_FULL extern void call_softirq(void); asmlinkage void do_softirq(void) @@ -108,3 +108,4 @@ asmlinkage void do_softirq(void) } local_irq_restore(flags); } +#endif diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index ca8f703..129b8bb 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -18,6 +18,7 @@ void smp_irq_work_interrupt(struct pt_regs *regs) irq_exit(); } +#ifndef CONFIG_PREEMPT_RT_FULL void arch_irq_work_raise(void) { #ifdef CONFIG_X86_LOCAL_APIC @@ -28,3 +29,4 @@ void arch_irq_work_raise(void) apic_wait_icr_idle(); #endif } +#endif diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 7305f7d..ee29e6c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -214,6 +215,35 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); +#ifdef CONFIG_PREEMPT_RT_FULL +static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) +{ + int i; + + /* + * Clear @prev's kmap_atomic mappings + */ + for (i = 0; i < prev_p->kmap_idx; i++) { + int idx = i + KM_TYPE_NR * smp_processor_id(); + pte_t *ptep = kmap_pte - idx; + + kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); + } + /* + * Restore @next_p's kmap_atomic mappings + */ + for (i = 0; i < next_p->kmap_idx; i++) { + int idx = i + KM_TYPE_NR * smp_processor_id(); + + if (!pte_none(next_p->kmap_pte[i])) + set_pte(kmap_pte - idx, next_p->kmap_pte[i]); + } +} +#else +static inline void +switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } +#endif + /* * switch_to(x,y) should switch tasks from x to y. @@ -293,6 +323,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) __switch_to_xtra(prev_p, next_p, tss); + switch_kmaps(prev_p, next_p); + /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 087ab2a..d827bf9 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -743,6 +743,14 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) mce_notify_process(); #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */ +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (unlikely(current->forced_info.si_signo)) { + struct task_struct *t = current; + force_sig_info(t->forced_info.si_signo, &t->forced_info, t); + t->forced_info.si_signo = 0; + } +#endif + if (thread_info_flags & _TIF_UPROBE) uprobe_notify_resume(regs); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 772e2a8..cbd25b2 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -85,9 +85,21 @@ static inline void conditional_sti(struct pt_regs *regs) local_irq_enable(); } -static inline void preempt_conditional_sti(struct pt_regs *regs) +static inline void conditional_sti_ist(struct pt_regs *regs) { +#ifdef CONFIG_X86_64 + /* + * X86_64 uses a per CPU stack on the IST for certain traps + * like int3. The task can not be preempted when using one + * of these stacks, thus preemption must be disabled, otherwise + * the stack can be corrupted if the task is scheduled out, + * and another task comes in and uses this stack. + * + * On x86_32 the task keeps its own stack and it is OK if the + * task schedules out. + */ inc_preempt_count(); +#endif if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } @@ -98,11 +110,13 @@ static inline void conditional_cli(struct pt_regs *regs) local_irq_disable(); } -static inline void preempt_conditional_cli(struct pt_regs *regs) +static inline void conditional_cli_ist(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_disable(); +#ifdef CONFIG_X86_64 dec_preempt_count(); +#endif } static int __kprobes @@ -235,9 +249,9 @@ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) prev_state = exception_enter(); if (notify_die(DIE_TRAP, "stack segment", regs, error_code, X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { - preempt_conditional_sti(regs); + conditional_sti_ist(regs); do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); } exception_exit(prev_state); } @@ -340,9 +354,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co * as we may switch to the interrupt stack. */ debug_stack_usage_inc(); - preempt_conditional_sti(regs); + conditional_sti_ist(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); debug_stack_usage_dec(); exit: exception_exit(prev_state); @@ -448,12 +462,12 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_inc(); /* It's safe to allow irq's after DR6 has been saved */ - preempt_conditional_sti(regs); + conditional_sti_ist(regs); if (regs->flags & X86_VM_MASK) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); debug_stack_usage_dec(); goto exit; } @@ -473,7 +487,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) si_code = get_si_code(tsk->thread.debugreg6); if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); debug_stack_usage_dec(); exit: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1bd6ea0..c70ea56 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5328,6 +5328,13 @@ int kvm_arch_init(void *opaque) goto out; } +#ifdef CONFIG_PREEMPT_RT_FULL + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n"); + return -EOPNOTSUPP; + } +#endif + r = kvm_mmu_module_init(); if (r) goto out_free_percpu; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index c1e9e4c..c831250 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1108,7 +1108,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) * If we're in an interrupt, have no user context or are running * in an atomic region then we must not take the fault: */ - if (unlikely(in_atomic() || !mm)) { + if (unlikely(!mm || pagefault_disabled())) { bad_area_nosemaphore(regs, error_code, address); return; } diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 252b8f5..0f00d97 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -31,6 +31,7 @@ EXPORT_SYMBOL(kunmap); */ void *kmap_atomic_prot(struct page *page, pgprot_t prot) { + pte_t pte = mk_pte(page, prot); unsigned long vaddr; int idx, type; @@ -44,7 +45,10 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte-idx))); - set_pte(kmap_pte-idx, mk_pte(page, prot)); +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; +#endif + set_pte(kmap_pte-idx, pte); arch_flush_lazy_mmu_mode(); return (void *)vaddr; @@ -87,6 +91,9 @@ void __kunmap_atomic(void *kvaddr) * is a bad idea also, in case the page changes cacheability * attributes or becomes a protected page in a hypervisor. */ +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = __pte(0); +#endif kpte_clear_flush(kmap_pte-idx, vaddr); kmap_atomic_idx_pop(); arch_flush_lazy_mmu_mode(); diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 7b179b4..62377d6 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -56,6 +56,7 @@ EXPORT_SYMBOL_GPL(iomap_free); void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { + pte_t pte = pfn_pte(pfn, prot); unsigned long vaddr; int idx, type; @@ -64,7 +65,12 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); + WARN_ON(!pte_none(*(kmap_pte - idx))); + +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; +#endif + set_pte(kmap_pte - idx, pte); arch_flush_lazy_mmu_mode(); return (void *)vaddr; @@ -110,6 +116,9 @@ iounmap_atomic(void __iomem *kvaddr) * is a bad idea also, in case the page changes cacheability * attributes or becomes a protected page in a hypervisor. */ +#ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = __pte(0); +#endif kpte_clear_flush(kmap_pte-idx, vaddr); kmap_atomic_idx_pop(); } diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 4b7bc8d..d57c257 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -57,7 +57,7 @@ void do_page_fault(struct pt_regs *regs) /* If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) { + if (!mm || pagefault_disabled()) { bad_page_fault(regs, address, SIGSEGV); return; } diff --git a/block/blk-core.c b/block/blk-core.c index 2c66dab..a1eeb262 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -232,7 +232,7 @@ EXPORT_SYMBOL(blk_delay_queue); **/ void blk_start_queue(struct request_queue *q) { - WARN_ON(!irqs_disabled()); + WARN_ON_NONRT(!irqs_disabled()); queue_flag_clear(QUEUE_FLAG_STOPPED, q); __blk_run_queue(q); @@ -2918,7 +2918,7 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth, blk_run_queue_async(q); else __blk_run_queue(q); - spin_unlock(q->queue_lock); + spin_unlock_irq(q->queue_lock); } static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) @@ -2966,7 +2966,6 @@ EXPORT_SYMBOL(blk_check_plugged); void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct request_queue *q; - unsigned long flags; struct request *rq; LIST_HEAD(list); unsigned int depth; @@ -2984,11 +2983,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) q = NULL; depth = 0; - /* - * Save and disable interrupts here, to avoid doing it for every - * queue lock we have to take. - */ - local_irq_save(flags); while (!list_empty(&list)) { rq = list_entry_rq(list.next); list_del_init(&rq->queuelist); @@ -3001,7 +2995,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) queue_unplugged(q, depth, from_schedule); q = rq->q; depth = 0; - spin_lock(q->queue_lock); + spin_lock_irq(q->queue_lock); } /* @@ -3028,8 +3022,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) */ if (q) queue_unplugged(q, depth, from_schedule); - - local_irq_restore(flags); } void blk_finish_plug(struct blk_plug *plug) diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 9c4bb82..0999d6d 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -8,6 +8,7 @@ #include #include /* for max_pfn/max_low_pfn */ #include +#include #include "blk.h" @@ -110,7 +111,7 @@ static void ioc_release_fn(struct work_struct *work) spin_unlock(q->queue_lock); } else { spin_unlock_irqrestore(&ioc->lock, flags); - cpu_relax(); + cpu_chill(); spin_lock_irqsave_nested(&ioc->lock, flags, 1); } } @@ -187,7 +188,7 @@ retry: spin_unlock(icq->q->queue_lock); } else { spin_unlock_irqrestore(&ioc->lock, flags); - cpu_relax(); + cpu_chill(); goto retry; } } diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c index 58916af..f7ca9b4 100644 --- a/block/blk-iopoll.c +++ b/block/blk-iopoll.c @@ -38,6 +38,7 @@ void blk_iopoll_sched(struct blk_iopoll *iop) list_add_tail(&iop->list, &__get_cpu_var(blk_cpu_iopoll)); __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(blk_iopoll_sched); @@ -135,6 +136,7 @@ static void blk_iopoll_softirq(struct softirq_action *h) __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); } /** @@ -204,6 +206,7 @@ static int __cpuinit blk_iopoll_cpu_notify(struct notifier_block *self, &__get_cpu_var(blk_cpu_iopoll)); __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); } return NOTIFY_OK; diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 467c8de..3fe2368 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -51,6 +51,7 @@ static void trigger_softirq(void *data) raise_softirq_irqoff(BLOCK_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } /* @@ -93,6 +94,7 @@ static int __cpuinit blk_cpu_notify(struct notifier_block *self, &__get_cpu_var(blk_cpu_done)); raise_softirq_irqoff(BLOCK_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); } return NOTIFY_OK; @@ -150,6 +152,7 @@ do_local: goto do_local; local_irq_restore(flags); + preempt_check_resched_rt(); } /** diff --git a/crypto/algapi.c b/crypto/algapi.c index 7a1ae87..5013cad 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -684,13 +684,13 @@ EXPORT_SYMBOL_GPL(crypto_spawn_tfm2); int crypto_register_notifier(struct notifier_block *nb) { - return blocking_notifier_chain_register(&crypto_chain, nb); + return srcu_notifier_chain_register(&crypto_chain, nb); } EXPORT_SYMBOL_GPL(crypto_register_notifier); int crypto_unregister_notifier(struct notifier_block *nb) { - return blocking_notifier_chain_unregister(&crypto_chain, nb); + return srcu_notifier_chain_unregister(&crypto_chain, nb); } EXPORT_SYMBOL_GPL(crypto_unregister_notifier); diff --git a/crypto/api.c b/crypto/api.c index 37c4c72..6768a86 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(crypto_alg_list); DECLARE_RWSEM(crypto_alg_sem); EXPORT_SYMBOL_GPL(crypto_alg_sem); -BLOCKING_NOTIFIER_HEAD(crypto_chain); +SRCU_NOTIFIER_HEAD(crypto_chain); EXPORT_SYMBOL_GPL(crypto_chain); static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg); @@ -236,10 +236,10 @@ int crypto_probing_notify(unsigned long val, void *v) { int ok; - ok = blocking_notifier_call_chain(&crypto_chain, val, v); + ok = srcu_notifier_call_chain(&crypto_chain, val, v); if (ok == NOTIFY_DONE) { request_module("cryptomgr"); - ok = blocking_notifier_call_chain(&crypto_chain, val, v); + ok = srcu_notifier_call_chain(&crypto_chain, val, v); } return ok; diff --git a/crypto/internal.h b/crypto/internal.h index bd39bfc..a5db167 100644 --- a/crypto/internal.h +++ b/crypto/internal.h @@ -48,7 +48,7 @@ struct crypto_larval { extern struct list_head crypto_alg_list; extern struct rw_semaphore crypto_alg_sem; -extern struct blocking_notifier_head crypto_chain; +extern struct srcu_notifier_head crypto_chain; #ifdef CONFIG_PROC_FS void __init crypto_init_proc(void); @@ -142,7 +142,7 @@ static inline int crypto_is_moribund(struct crypto_alg *alg) static inline void crypto_notify(unsigned long val, void *v) { - blocking_notifier_call_chain(&crypto_chain, val, v); + srcu_notifier_call_chain(&crypto_chain, val, v); } #endif /* _CRYPTO_INTERNAL_H */ diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 0716092..b900103 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -223,7 +223,7 @@ ACPI_EXTERN u8 acpi_gbl_global_lock_pending; * interrupt level */ ACPI_EXTERN acpi_spinlock acpi_gbl_gpe_lock; /* For GPE data structs and registers */ -ACPI_EXTERN acpi_spinlock acpi_gbl_hardware_lock; /* For ACPI H/W except GPE registers */ +ACPI_EXTERN acpi_raw_spinlock acpi_gbl_hardware_lock; /* For ACPI H/W except GPE registers */ ACPI_EXTERN acpi_spinlock acpi_gbl_reference_count_lock; /* Mutex for _OSI support */ diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c index 083d655..8d6e648 100644 --- a/drivers/acpi/acpica/hwregs.c +++ b/drivers/acpi/acpica/hwregs.c @@ -269,14 +269,14 @@ acpi_status acpi_hw_clear_acpi_status(void) ACPI_BITMASK_ALL_FIXED_STATUS, ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address))); - lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); + raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); /* Clear the fixed events in PM1 A/B */ status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS, ACPI_BITMASK_ALL_FIXED_STATUS); - acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); + raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); if (ACPI_FAILURE(status)) goto exit; diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c index 04c2e16..eca1807 100644 --- a/drivers/acpi/acpica/hwxface.c +++ b/drivers/acpi/acpica/hwxface.c @@ -365,7 +365,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value) return_ACPI_STATUS(AE_BAD_PARAMETER); } - lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); + raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); /* * At this point, we know that the parent register is one of the @@ -426,7 +426,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value) unlock_and_exit: - acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); + raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); return_ACPI_STATUS(status); } diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c index 08c3232..2f4ed8b 100644 --- a/drivers/acpi/acpica/utmutex.c +++ b/drivers/acpi/acpica/utmutex.c @@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(void) return_ACPI_STATUS (status); } - status = acpi_os_create_lock (&acpi_gbl_hardware_lock); + status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock); if (ACPI_FAILURE (status)) { return_ACPI_STATUS (status); } @@ -141,7 +141,7 @@ void acpi_ut_mutex_terminate(void) /* Delete the spinlocks */ acpi_os_delete_lock(acpi_gbl_gpe_lock); - acpi_os_delete_lock(acpi_gbl_hardware_lock); + acpi_os_delete_raw_lock(acpi_gbl_hardware_lock); acpi_os_delete_lock(acpi_gbl_reference_count_lock); /* Delete the reader/writer lock */ diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b603720..2afbd46 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -678,9 +678,9 @@ unsigned int ata_sff_data_xfer_noirq(struct ata_device *dev, unsigned char *buf, unsigned long flags; unsigned int consumed; - local_irq_save(flags); + local_irq_save_nort(flags); consumed = ata_sff_data_xfer32(dev, buf, buflen, rw); - local_irq_restore(flags); + local_irq_restore_nort(flags); return consumed; } @@ -719,7 +719,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) unsigned long flags; /* FIXME: use a bounce buffer */ - local_irq_save(flags); + local_irq_save_nort(flags); buf = kmap_atomic(page); /* do the actual data transfer */ @@ -727,7 +727,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) do_write); kunmap_atomic(buf); - local_irq_restore(flags); + local_irq_restore_nort(flags); } else { buf = page_address(page); ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size, @@ -864,7 +864,7 @@ next_sg: unsigned long flags; /* FIXME: use bounce buffer */ - local_irq_save(flags); + local_irq_save_nort(flags); buf = kmap_atomic(page); /* do the actual data transfer */ @@ -872,7 +872,7 @@ next_sg: count, rw); kunmap_atomic(buf); - local_irq_restore(flags); + local_irq_restore_nort(flags); } else { buf = page_address(page); consumed = ap->ops->sff_data_xfer(dev, buf + offset, diff --git a/drivers/char/random.c b/drivers/char/random.c index 81eefa1..119dd7e 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -676,9 +676,12 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) preempt_disable(); /* if over the trickle threshold, use only 1 in 4096 samples */ if (input_pool.entropy_count > trickle_thresh && - ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff)) - goto out; + ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff)) { + preempt_enable(); + return; + } + preempt_enable(); sample.jiffies = jiffies; sample.cycles = get_cycles(); sample.num = num; @@ -719,8 +722,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) credit_entropy_bits(&input_pool, min_t(int, fls(delta>>1), 11)); } -out: - preempt_enable(); } void add_input_randomness(unsigned int type, unsigned int code, @@ -741,18 +742,16 @@ EXPORT_SYMBOL_GPL(add_input_randomness); static DEFINE_PER_CPU(struct fast_pool, irq_randomness); -void add_interrupt_randomness(int irq, int irq_flags) +void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) { struct entropy_store *r; struct fast_pool *fast_pool = &__get_cpu_var(irq_randomness); - struct pt_regs *regs = get_irq_regs(); unsigned long now = jiffies; __u32 input[4], cycles = get_cycles(); input[0] = cycles ^ jiffies; input[1] = irq; - if (regs) { - __u64 ip = instruction_pointer(regs); + if (ip) { input[2] = ip; input[3] = ip >> 32; } @@ -766,7 +765,11 @@ void add_interrupt_randomness(int irq, int irq_flags) fast_pool->last = now; r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool; +#ifndef CONFIG_PREEMPT_RT_FULL __mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL); +#else + mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL); +#endif /* * If we don't have a valid cycle counter, and we see * back-to-back timer interrupts, then skip giving credit for diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index 8a61872..c08ec1d 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -23,8 +23,7 @@ * this 32 bit free-running counter. the second channel is not used. * * - The third channel may be used to provide a 16-bit clockevent - * source, used in either periodic or oneshot mode. This runs - * at 32 KiHZ, and can handle delays of up to two seconds. + * source, used in either periodic or oneshot mode. * * A boot clocksource and clockevent source are also currently needed, * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so @@ -74,6 +73,7 @@ static struct clocksource clksrc = { struct tc_clkevt_device { struct clock_event_device clkevt; struct clk *clk; + u32 freq; void __iomem *regs; }; @@ -82,13 +82,6 @@ static struct tc_clkevt_device *to_tc_clkevt(struct clock_event_device *clkevt) return container_of(clkevt, struct tc_clkevt_device, clkevt); } -/* For now, we always use the 32K clock ... this optimizes for NO_HZ, - * because using one of the divided clocks would usually mean the - * tick rate can never be less than several dozen Hz (vs 0.5 Hz). - * - * A divided clock could be good for high resolution timers, since - * 30.5 usec resolution can seem "low". - */ static u32 timer_clock; static void tc_mode(enum clock_event_mode m, struct clock_event_device *d) @@ -111,11 +104,12 @@ static void tc_mode(enum clock_event_mode m, struct clock_event_device *d) case CLOCK_EVT_MODE_PERIODIC: clk_enable(tcd->clk); - /* slow clock, count up to RC, then irq and restart */ + /* count up to RC, then irq and restart */ __raw_writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR)); - __raw_writel((32768 + HZ/2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); + __raw_writel((tcd->freq + HZ/2)/HZ, + tcaddr + ATMEL_TC_REG(2, RC)); /* Enable clock and interrupts on RC compare */ __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); @@ -128,7 +122,7 @@ static void tc_mode(enum clock_event_mode m, struct clock_event_device *d) case CLOCK_EVT_MODE_ONESHOT: clk_enable(tcd->clk); - /* slow clock, count up to RC, then irq and stop */ + /* count up to RC, then irq and stop */ __raw_writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR)); @@ -157,8 +151,12 @@ static struct tc_clkevt_device clkevt = { .name = "tc_clkevt", .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, +#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK /* Should be lower than at91rm9200's system timer */ .rating = 125, +#else + .rating = 200, +#endif .set_next_event = tc_next_event, .set_mode = tc_mode, }, @@ -184,8 +182,9 @@ static struct irqaction tc_irqaction = { .handler = ch2_irq, }; -static void __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) +static void __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) { + unsigned divisor = atmel_tc_divisors[divisor_idx]; struct clk *t2_clk = tc->clk[2]; int irq = tc->irq[2]; @@ -322,8 +321,11 @@ static int __init tcb_clksrc_init(void) clocksource_register_hz(&clksrc, divided_rate); /* channel 2: periodic and oneshot timer support */ +#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK setup_clkevents(tc, clk32k_divisor_idx); - +#else + setup_clkevents(tc, best_divisor_idx); +#endif return 0; } arch_initcall(tcb_clksrc_init); diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index f92da0a..434ea84 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -628,11 +628,6 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc, * code gets preempted or delayed for some reason. */ for (i = 0; i < DRM_TIMESTAMP_MAXRETRIES; i++) { - /* Disable preemption to make it very likely to - * succeed in the first iteration even on PREEMPT_RT kernel. - */ - preempt_disable(); - /* Get system timestamp before query. */ stime = ktime_get(); @@ -644,8 +639,6 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc, if (!drm_timestamp_monotonic) mono_time_offset = ktime_get_monotonic_offset(); - preempt_enable(); - /* Return as no-op if scanout query unsupported or failed. */ if (!(vbl_status & DRM_SCANOUTPOS_VALID)) { DRM_DEBUG("crtc %d : scanoutpos query failed [%d].\n", diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 0a30088..080b1b2 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2713,35 +2713,17 @@ static inline int fence_number(struct drm_i915_private *dev_priv, return fence - dev_priv->fence_regs; } -static void i915_gem_write_fence__ipi(void *data) -{ - wbinvd(); -} - static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj, struct drm_i915_fence_reg *fence, bool enable) { - struct drm_device *dev = obj->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - int fence_reg = fence_number(dev_priv, fence); - - /* In order to fully serialize access to the fenced region and - * the update to the fence register we need to take extreme - * measures on SNB+. In theory, the write to the fence register - * flushes all memory transactions before, and coupled with the - * mb() placed around the register write we serialise all memory - * operations with respect to the changes in the tiler. Yet, on - * SNB+ we need to take a step further and emit an explicit wbinvd() - * on each processor in order to manually flush all memory - * transactions before updating the fence register. - */ - if (HAS_LLC(obj->base.dev)) - on_each_cpu(i915_gem_write_fence__ipi, NULL, 1); - i915_gem_write_fence(dev, fence_reg, enable ? obj : NULL); + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; + int reg = fence_number(dev_priv, fence); + + i915_gem_write_fence(obj->base.dev, reg, enable ? obj : NULL); if (enable) { - obj->fence_reg = fence_reg; + obj->fence_reg = reg; fence->obj = obj; list_move_tail(&fence->lru_list, &dev_priv->mm.fence_list); } else { @@ -4449,7 +4431,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) if (!mutex_is_locked(mutex)) return false; -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES) +#if (defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)) && !defined(CONFIG_PREEMPT_RT_BASE) return mutex->owner == task; #else /* Since UP may be pre-empted, we cannot assume that we own the lock */ diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 117ce38..4602b99 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1071,7 +1071,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto err; } +#ifndef CONFIG_PREEMPT_RT_BASE trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags); +#endif i915_gem_execbuffer_move_to_active(&eb->objects, ring); i915_gem_execbuffer_retire_commands(dev, file, ring); diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index b06be8e..778bf78 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -881,15 +881,12 @@ omap_i2c_isr(int irq, void *dev_id) u16 mask; u16 stat; - spin_lock(&dev->lock); - mask = omap_i2c_read_reg(dev, OMAP_I2C_IE_REG); stat = omap_i2c_read_reg(dev, OMAP_I2C_STAT_REG); + mask = omap_i2c_read_reg(dev, OMAP_I2C_IE_REG); if (stat & mask) ret = IRQ_WAKE_THREAD; - spin_unlock(&dev->lock); - return ret; } diff --git a/drivers/ide/alim15x3.c b/drivers/ide/alim15x3.c index 36f76e2..394f142f 100644 --- a/drivers/ide/alim15x3.c +++ b/drivers/ide/alim15x3.c @@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct pci_dev *dev) isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL); - local_irq_save(flags); + local_irq_save_nort(flags); if (m5229_revision < 0xC2) { /* @@ -325,7 +325,7 @@ out: } pci_dev_put(north); pci_dev_put(isa_dev); - local_irq_restore(flags); + local_irq_restore_nort(flags); return 0; } diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c index 696b6c1..0d0a966 100644 --- a/drivers/ide/hpt366.c +++ b/drivers/ide/hpt366.c @@ -1241,7 +1241,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif, dma_old = inb(base + 2); - local_irq_save(flags); + local_irq_save_nort(flags); dma_new = dma_old; pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma); @@ -1252,7 +1252,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif, if (dma_new != dma_old) outb(dma_new, base + 2); - local_irq_restore(flags); + local_irq_restore_nort(flags); printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n", hwif->name, base, base + 7); diff --git a/drivers/ide/ide-io-std.c b/drivers/ide/ide-io-std.c index 1976397..4169433 100644 --- a/drivers/ide/ide-io-std.c +++ b/drivers/ide/ide-io-std.c @@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf, unsigned long uninitialized_var(flags); if ((io_32bit & 2) && !mmio) { - local_irq_save(flags); + local_irq_save_nort(flags); ata_vlb_sync(io_ports->nsect_addr); } @@ -186,7 +186,7 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf, insl(data_addr, buf, words); if ((io_32bit & 2) && !mmio) - local_irq_restore(flags); + local_irq_restore_nort(flags); if (((len + 1) & 3) < 2) return; @@ -219,7 +219,7 @@ void ide_output_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf, unsigned long uninitialized_var(flags); if ((io_32bit & 2) && !mmio) { - local_irq_save(flags); + local_irq_save_nort(flags); ata_vlb_sync(io_ports->nsect_addr); } @@ -230,7 +230,7 @@ void ide_output_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf, outsl(data_addr, buf, words); if ((io_32bit & 2) && !mmio) - local_irq_restore(flags); + local_irq_restore_nort(flags); if (((len + 1) & 3) < 2) return; diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 177db6d..079ae6b 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -659,7 +659,7 @@ void ide_timer_expiry (unsigned long data) /* disable_irq_nosync ?? */ disable_irq(hwif->irq); /* local CPU only, as if we were handling an interrupt */ - local_irq_disable(); + local_irq_disable_nort(); if (hwif->polling) { startstop = handler(drive); } else if (drive_is_ready(drive)) { diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c index 376f2dc..f014dd1 100644 --- a/drivers/ide/ide-iops.c +++ b/drivers/ide/ide-iops.c @@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive, u8 good, u8 bad, if ((stat & ATA_BUSY) == 0) break; - local_irq_restore(flags); + local_irq_restore_nort(flags); *rstat = stat; return -EBUSY; } } - local_irq_restore(flags); + local_irq_restore_nort(flags); } /* * Allow status to settle, then read it again. diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 068cef0..38e69e1 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *drive, u8 cmd, u16 *id) int bswap = 1; /* local CPU only; some systems need this */ - local_irq_save(flags); + local_irq_save_nort(flags); /* read 512 bytes of id info */ hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE); - local_irq_restore(flags); + local_irq_restore_nort(flags); drive->dev_flags |= IDE_DFLAG_ID_READ; #ifdef DEBUG diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c index 729428e..3a9a1fc 100644 --- a/drivers/ide/ide-taskfile.c +++ b/drivers/ide/ide-taskfile.c @@ -251,7 +251,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd, page_is_high = PageHighMem(page); if (page_is_high) - local_irq_save(flags); + local_irq_save_nort(flags); buf = kmap_atomic(page) + offset; @@ -272,7 +272,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd, kunmap_atomic(buf); if (page_is_high) - local_irq_restore(flags); + local_irq_restore_nort(flags); len -= nr_bytes; } @@ -415,7 +415,7 @@ static ide_startstop_t pre_task_out_intr(ide_drive_t *drive, } if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0) - local_irq_disable(); + local_irq_disable_nort(); ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index cecb98a..3800ef5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -783,7 +783,7 @@ void ipoib_mcast_restart_task(struct work_struct *work) ipoib_mcast_stop_thread(dev, 0); - local_irq_save(flags); + local_irq_save_nort(flags); netif_addr_lock(dev); spin_lock(&priv->lock); @@ -865,7 +865,7 @@ void ipoib_mcast_restart_task(struct work_struct *work) spin_unlock(&priv->lock); netif_addr_unlock(dev); - local_irq_restore(flags); + local_irq_restore_nort(flags); /* We have to cancel outside of the spinlock */ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c index da739d9..18fdafe 100644 --- a/drivers/input/gameport/gameport.c +++ b/drivers/input/gameport/gameport.c @@ -87,12 +87,12 @@ static int gameport_measure_speed(struct gameport *gameport) tx = 1 << 30; for(i = 0; i < 50; i++) { - local_irq_save(flags); + local_irq_save_nort(flags); GET_TIME(t1); for (t = 0; t < 50; t++) gameport_read(gameport); GET_TIME(t2); GET_TIME(t3); - local_irq_restore(flags); + local_irq_restore_nort(flags); udelay(i * 10); if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t; } @@ -111,11 +111,11 @@ static int gameport_measure_speed(struct gameport *gameport) tx = 1 << 30; for(i = 0; i < 50; i++) { - local_irq_save(flags); + local_irq_save_nort(flags); rdtscl(t1); for (t = 0; t < 50; t++) gameport_read(gameport); rdtscl(t2); - local_irq_restore(flags); + local_irq_restore_nort(flags); udelay(i * 10); if (t2 - t1 < tx) tx = t2 - t1; } diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig index f950c9d..5eb76dd 100644 --- a/drivers/md/bcache/Kconfig +++ b/drivers/md/bcache/Kconfig @@ -1,6 +1,7 @@ config BCACHE tristate "Block device as cache" + depends on !PREEMPT_RT_FULL ---help--- Allows a block device to be used as cache for other devices; uses a btree for indexing and the layout is optimized for SSDs. diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 204a59f..cd3b8ca 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1713,14 +1713,14 @@ static void dm_request_fn(struct request_queue *q) if (map_request(ti, clone, md)) goto requeued; - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); spin_lock(q->queue_lock); } goto out; requeued: - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); spin_lock(q->queue_lock); delay_and_out: diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5e3c25d..cc79548 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1430,8 +1430,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) struct raid5_percpu *percpu; unsigned long cpu; - cpu = get_cpu(); + cpu = get_cpu_light(); percpu = per_cpu_ptr(conf->percpu, cpu); + spin_lock(&percpu->lock); if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { ops_run_biofill(sh); overlap_clear++; @@ -1483,7 +1484,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) if (test_and_clear_bit(R5_Overlap, &dev->flags)) wake_up(&sh->raid_conf->wait_for_overlap); } - put_cpu(); + spin_unlock(&percpu->lock); + put_cpu_light(); } static int grow_one_stripe(struct r5conf *conf) @@ -1920,7 +1922,7 @@ static void raid5_end_write_request(struct bio *bi, int error) } static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous); - + static void raid5_build_block(struct stripe_head *sh, int i, int previous) { struct r5dev *dev = &sh->dev[i]; @@ -4341,7 +4343,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) previous, &dd_idx, NULL); pr_debug("raid456: make_request, sector %llu logical %llu\n", - (unsigned long long)new_sector, + (unsigned long long)new_sector, (unsigned long long)logical_sector); sh = get_active_stripe(conf, new_sector, previous, @@ -5049,8 +5051,10 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu { if (conf->level == 6 && !percpu->spare_page) percpu->spare_page = alloc_page(GFP_KERNEL); - if (!percpu->scribble) + if (!percpu->scribble) { percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); + spin_lock_init(&percpu->lock); + } if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) { free_scratch_buffer(conf, percpu); @@ -5309,7 +5313,7 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded return 1; break; case ALGORITHM_PARITY_0_6: - if (raid_disk == 0 || + if (raid_disk == 0 || raid_disk == raid_disks - 1) return 1; break; diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 70c4932..2f910da 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -426,6 +426,7 @@ struct r5conf { int recovery_disabled; /* per cpu variables */ struct raid5_percpu { + spinlock_t lock; /* Protection for -RT */ struct page *spare_page; /* Used when checking P/Q in raid6 */ void *scribble; /* space for constructing buffer * lists and performing address diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index c002d86..0b3a72e 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -63,6 +63,7 @@ config ATMEL_PWM config ATMEL_TCLIB bool "Atmel AT32/AT91 Timer/Counter Library" depends on (AVR32 || ARCH_AT91) + default y if PREEMPT_RT_FULL help Select this if you want a library to allocate the Timer/Counter blocks found on many Atmel processors. This facilitates using @@ -78,8 +79,7 @@ config ATMEL_TCB_CLKSRC are combined to make a single 32-bit timer. When GENERIC_CLOCKEVENTS is defined, the third timer channel - may be used as a clock event device supporting oneshot mode - (delays of up to two seconds) based on the 32 KiHz clock. + may be used as a clock event device supporting oneshot mode. config ATMEL_TCB_CLKSRC_BLOCK int @@ -93,6 +93,15 @@ config ATMEL_TCB_CLKSRC_BLOCK TC can be used for other purposes, such as PWM generation and interval timing. +config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + bool "TC Block use 32 KiHz clock" + depends on ATMEL_TCB_CLKSRC + default y if !PREEMPT_RT_FULL + help + Select this to use 32 KiHz base clock rate as TC block clock + source for clock events. + + config DUMMY_IRQ tristate "Dummy IRQ handler" default n @@ -122,6 +131,35 @@ config IBM_ASM for information on the specific driver level and support statement for your IBM server. +config HWLAT_DETECTOR + tristate "Testing module to detect hardware-induced latencies" + depends on DEBUG_FS + depends on RING_BUFFER + default m + ---help--- + A simple hardware latency detector. Use this module to detect + large latencies introduced by the behavior of the underlying + system firmware external to Linux. We do this using periodic + use of stop_machine to grab all available CPUs and measure + for unexplainable gaps in the CPU timestamp counter(s). By + default, the module is not enabled until the "enable" file + within the "hwlat_detector" debugfs directory is toggled. + + This module is often used to detect SMI (System Management + Interrupts) on x86 systems, though is not x86 specific. To + this end, we default to using a sample window of 1 second, + during which we will sample for 0.5 seconds. If an SMI or + similar event occurs during that time, it is recorded + into an 8K samples global ring buffer until retreived. + + WARNING: This software should never be enabled (it can be built + but should not be turned on after it is loaded) in a production + environment where high latencies are a concern since the + sampling mechanism actually introduces latencies for + regular tasks while the CPU(s) are being held. + + If unsure, say N + config PHANTOM tristate "Sensable PHANToM (PCI)" depends on PCI diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index c235d5b..6bb08da40 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -53,3 +53,4 @@ obj-$(CONFIG_INTEL_MEI) += mei/ obj-$(CONFIG_VMWARE_VMCI) += vmw_vmci/ obj-$(CONFIG_LATTICE_ECP3_CONFIG) += lattice-ecp3-config.o obj-$(CONFIG_SRAM) += sram.o +obj-$(CONFIG_HWLAT_DETECTOR) += hwlat_detector.o diff --git a/drivers/misc/hwlat_detector.c b/drivers/misc/hwlat_detector.c new file mode 100644 index 0000000..d2676b8 --- /dev/null +++ b/drivers/misc/hwlat_detector.c @@ -0,0 +1,1239 @@ +/* + * hwlat_detector.c - A simple Hardware Latency detector. + * + * Use this module to detect large system latencies induced by the behavior of + * certain underlying system hardware or firmware, independent of Linux itself. + * The code was developed originally to detect the presence of SMIs on Intel + * and AMD systems, although there is no dependency upon x86 herein. + * + * The classical example usage of this module is in detecting the presence of + * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a + * somewhat special form of hardware interrupt spawned from earlier CPU debug + * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge + * LPC (or other device) to generate a special interrupt under certain + * circumstances, for example, upon expiration of a special SMI timer device, + * due to certain external thermal readings, on certain I/O address accesses, + * and other situations. An SMI hits a special CPU pin, triggers a special + * SMI mode (complete with special memory map), and the OS is unaware. + * + * Although certain hardware-inducing latencies are necessary (for example, + * a modern system often requires an SMI handler for correct thermal control + * and remote management) they can wreak havoc upon any OS-level performance + * guarantees toward low-latency, especially when the OS is not even made + * aware of the presence of these interrupts. For this reason, we need a + * somewhat brute force mechanism to detect these interrupts. In this case, + * we do it by hogging all of the CPU(s) for configurable timer intervals, + * sampling the built-in CPU timer, looking for discontiguous readings. + * + * WARNING: This implementation necessarily introduces latencies. Therefore, + * you should NEVER use this module in a production environment + * requiring any kind of low-latency performance guarantee(s). + * + * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. + * + * Includes useful feedback from Clark Williams + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */ +#define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */ +#define U64STR_SIZE 22 /* 20 digits max */ + +#define VERSION "1.0.0" +#define BANNER "hwlat_detector: " +#define DRVNAME "hwlat_detector" +#define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */ +#define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */ +#define DEFAULT_LAT_THRESHOLD 10 /* 10us */ + +/* Module metadata */ + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jon Masters "); +MODULE_DESCRIPTION("A simple hardware latency detector"); +MODULE_VERSION(VERSION); + +/* Module parameters */ + +static int debug; +static int enabled; +static int threshold; + +module_param(debug, int, 0); /* enable debug */ +module_param(enabled, int, 0); /* enable detector */ +module_param(threshold, int, 0); /* latency threshold */ + +/* Buffering and sampling */ + +static struct ring_buffer *ring_buffer; /* sample buffer */ +static DEFINE_MUTEX(ring_buffer_mutex); /* lock changes */ +static unsigned long buf_size = BUF_SIZE_DEFAULT; +static struct task_struct *kthread; /* sampling thread */ + +/* DebugFS filesystem entries */ + +static struct dentry *debug_dir; /* debugfs directory */ +static struct dentry *debug_max; /* maximum TSC delta */ +static struct dentry *debug_count; /* total detect count */ +static struct dentry *debug_sample_width; /* sample width us */ +static struct dentry *debug_sample_window; /* sample window us */ +static struct dentry *debug_sample; /* raw samples us */ +static struct dentry *debug_threshold; /* threshold us */ +static struct dentry *debug_enable; /* enable/disable */ + +/* Individual samples and global state */ + +struct sample; /* latency sample */ +struct data; /* Global state */ + +/* Sampling functions */ +static int __buffer_add_sample(struct sample *sample); +static struct sample *buffer_get_sample(struct sample *sample); + +/* Threading and state */ +static int kthread_fn(void *unused); +static int start_kthread(void); +static int stop_kthread(void); +static void __reset_stats(void); +static int init_stats(void); + +/* Debugfs interface */ +static ssize_t simple_data_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos, const u64 *entry); +static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos, u64 *entry); +static int debug_sample_fopen(struct inode *inode, struct file *filp); +static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos); +static int debug_sample_release(struct inode *inode, struct file *filp); +static int debug_enable_fopen(struct inode *inode, struct file *filp); +static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos); +static ssize_t debug_enable_fwrite(struct file *file, + const char __user *user_buffer, + size_t user_size, loff_t *offset); + +/* Initialization functions */ +static int init_debugfs(void); +static void free_debugfs(void); +static int detector_init(void); +static void detector_exit(void); + +/* Individual latency samples are stored here when detected and packed into + * the ring_buffer circular buffer, where they are overwritten when + * more than buf_size/sizeof(sample) samples are received. */ +struct sample { + u64 seqnum; /* unique sequence */ + u64 duration; /* ktime delta */ + u64 outer_duration; /* ktime delta (outer loop) */ + struct timespec timestamp; /* wall time */ + unsigned long lost; +}; + +/* keep the global state somewhere. */ +static struct data { + + struct mutex lock; /* protect changes */ + + u64 count; /* total since reset */ + u64 max_sample; /* max hardware latency */ + u64 threshold; /* sample threshold level */ + + u64 sample_window; /* total sampling window (on+off) */ + u64 sample_width; /* active sampling portion of window */ + + atomic_t sample_open; /* whether the sample file is open */ + + wait_queue_head_t wq; /* waitqeue for new sample values */ + +} data; + +/** + * __buffer_add_sample - add a new latency sample recording to the ring buffer + * @sample: The new latency sample value + * + * This receives a new latency sample and records it in a global ring buffer. + * No additional locking is used in this case. + */ +static int __buffer_add_sample(struct sample *sample) +{ + return ring_buffer_write(ring_buffer, + sizeof(struct sample), sample); +} + +/** + * buffer_get_sample - remove a hardware latency sample from the ring buffer + * @sample: Pre-allocated storage for the sample + * + * This retrieves a hardware latency sample from the global circular buffer + */ +static struct sample *buffer_get_sample(struct sample *sample) +{ + struct ring_buffer_event *e = NULL; + struct sample *s = NULL; + unsigned int cpu = 0; + + if (!sample) + return NULL; + + mutex_lock(&ring_buffer_mutex); + for_each_online_cpu(cpu) { + e = ring_buffer_consume(ring_buffer, cpu, NULL, &sample->lost); + if (e) + break; + } + + if (e) { + s = ring_buffer_event_data(e); + memcpy(sample, s, sizeof(struct sample)); + } else + sample = NULL; + mutex_unlock(&ring_buffer_mutex); + + return sample; +} + +#ifndef CONFIG_TRACING +#define time_type ktime_t +#define time_get() ktime_get() +#define time_to_us(x) ktime_to_us(x) +#define time_sub(a, b) ktime_sub(a, b) +#define init_time(a, b) (a).tv64 = b +#define time_u64(a) (a).tv64 +#else +#define time_type u64 +#define time_get() trace_clock_local() +#define time_to_us(x) div_u64(x, 1000) +#define time_sub(a, b) ((a) - (b)) +#define init_time(a, b) a = b +#define time_u64(a) a +#endif +/** + * get_sample - sample the CPU TSC and look for likely hardware latencies + * + * Used to repeatedly capture the CPU TSC (or similar), looking for potential + * hardware-induced latency. Called with interrupts disabled and with data.lock held. + */ +static int get_sample(void) +{ + time_type start, t1, t2, last_t2; + s64 diff, total = 0; + u64 sample = 0; + u64 outer_sample = 0; + int ret = -1; + + init_time(last_t2, 0); + start = time_get(); /* start timestamp */ + + do { + + t1 = time_get(); /* we'll look for a discontinuity */ + t2 = time_get(); + + if (time_u64(last_t2)) { + /* Check the delta from the outer loop (t2 to next t1) */ + diff = time_to_us(time_sub(t1, last_t2)); + /* This shouldn't happen */ + if (diff < 0) { + printk(KERN_ERR BANNER "time running backwards\n"); + goto out; + } + if (diff > outer_sample) + outer_sample = diff; + } + last_t2 = t2; + + total = time_to_us(time_sub(t2, start)); /* sample width */ + + /* This checks the inner loop (t1 to t2) */ + diff = time_to_us(time_sub(t2, t1)); /* current diff */ + + /* This shouldn't happen */ + if (diff < 0) { + printk(KERN_ERR BANNER "time running backwards\n"); + goto out; + } + + if (diff > sample) + sample = diff; /* only want highest value */ + + } while (total <= data.sample_width); + + ret = 0; + + /* If we exceed the threshold value, we have found a hardware latency */ + if (sample > data.threshold || outer_sample > data.threshold) { + struct sample s; + + ret = 1; + + data.count++; + s.seqnum = data.count; + s.duration = sample; + s.outer_duration = outer_sample; + s.timestamp = CURRENT_TIME; + __buffer_add_sample(&s); + + /* Keep a running maximum ever recorded hardware latency */ + if (sample > data.max_sample) + data.max_sample = sample; + } + +out: + return ret; +} + +/* + * kthread_fn - The CPU time sampling/hardware latency detection kernel thread + * @unused: A required part of the kthread API. + * + * Used to periodically sample the CPU TSC via a call to get_sample. We + * disable interrupts, which does (intentionally) introduce latency since we + * need to ensure nothing else might be running (and thus pre-empting). + * Obviously this should never be used in production environments. + * + * Currently this runs on which ever CPU it was scheduled on, but most + * real-worald hardware latency situations occur across several CPUs, + * but we might later generalize this if we find there are any actualy + * systems with alternate SMI delivery or other hardware latencies. + */ +static int kthread_fn(void *unused) +{ + int ret; + u64 interval; + + while (!kthread_should_stop()) { + + mutex_lock(&data.lock); + + local_irq_disable(); + ret = get_sample(); + local_irq_enable(); + + if (ret > 0) + wake_up(&data.wq); /* wake up reader(s) */ + + interval = data.sample_window - data.sample_width; + do_div(interval, USEC_PER_MSEC); /* modifies interval value */ + + mutex_unlock(&data.lock); + + if (msleep_interruptible(interval)) + break; + } + + return 0; +} + +/** + * start_kthread - Kick off the hardware latency sampling/detector kthread + * + * This starts a kernel thread that will sit and sample the CPU timestamp + * counter (TSC or similar) and look for potential hardware latencies. + */ +static int start_kthread(void) +{ + kthread = kthread_run(kthread_fn, NULL, + DRVNAME); + if (IS_ERR(kthread)) { + printk(KERN_ERR BANNER "could not start sampling thread\n"); + enabled = 0; + return -ENOMEM; + } + + return 0; +} + +/** + * stop_kthread - Inform the hardware latency samping/detector kthread to stop + * + * This kicks the running hardware latency sampling/detector kernel thread and + * tells it to stop sampling now. Use this on unload and at system shutdown. + */ +static int stop_kthread(void) +{ + int ret; + + ret = kthread_stop(kthread); + + return ret; +} + +/** + * __reset_stats - Reset statistics for the hardware latency detector + * + * We use data to store various statistics and global state. We call this + * function in order to reset those when "enable" is toggled on or off, and + * also at initialization. Should be called with data.lock held. + */ +static void __reset_stats(void) +{ + data.count = 0; + data.max_sample = 0; + ring_buffer_reset(ring_buffer); /* flush out old sample entries */ +} + +/** + * init_stats - Setup global state statistics for the hardware latency detector + * + * We use data to store various statistics and global state. We also use + * a global ring buffer (ring_buffer) to keep raw samples of detected hardware + * induced system latencies. This function initializes these structures and + * allocates the global ring buffer also. + */ +static int init_stats(void) +{ + int ret = -ENOMEM; + + mutex_init(&data.lock); + init_waitqueue_head(&data.wq); + atomic_set(&data.sample_open, 0); + + ring_buffer = ring_buffer_alloc(buf_size, BUF_FLAGS); + + if (WARN(!ring_buffer, KERN_ERR BANNER + "failed to allocate ring buffer!\n")) + goto out; + + __reset_stats(); + data.threshold = threshold ?: DEFAULT_LAT_THRESHOLD; /* threshold us */ + data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */ + data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */ + + ret = 0; + +out: + return ret; + +} + +/* + * simple_data_read - Wrapper read function for global state debugfs entries + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * @entry: The entry to read from + * + * This function provides a generic read implementation for the global state + * "data" structure debugfs filesystem entries. It would be nice to use + * simple_attr_read directly, but we need to make sure that the data.lock + * is held during the actual read. + */ +static ssize_t simple_data_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos, const u64 *entry) +{ + char buf[U64STR_SIZE]; + u64 val = 0; + int len = 0; + + memset(buf, 0, sizeof(buf)); + + if (!entry) + return -EFAULT; + + mutex_lock(&data.lock); + val = *entry; + mutex_unlock(&data.lock); + + len = snprintf(buf, sizeof(buf), "%llu\n", (unsigned long long)val); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); + +} + +/* + * simple_data_write - Wrapper write function for global state debugfs entries + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The userspace provided buffer to write value from + * @cnt: The maximum number of bytes to write + * @ppos: The current "file" position + * @entry: The entry to write to + * + * This function provides a generic write implementation for the global state + * "data" structure debugfs filesystem entries. It would be nice to use + * simple_attr_write directly, but we need to make sure that the data.lock + * is held during the actual write. + */ +static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos, u64 *entry) +{ + char buf[U64STR_SIZE]; + int csize = min(cnt, sizeof(buf)); + u64 val = 0; + int err = 0; + + memset(buf, '\0', sizeof(buf)); + if (copy_from_user(buf, ubuf, csize)) + return -EFAULT; + + buf[U64STR_SIZE-1] = '\0'; /* just in case */ + err = strict_strtoull(buf, 10, &val); + if (err) + return -EINVAL; + + mutex_lock(&data.lock); + *entry = val; + mutex_unlock(&data.lock); + + return csize; +} + +/** + * debug_count_fopen - Open function for "count" debugfs entry + * @inode: The in-kernel inode representation of the debugfs "file" + * @filp: The active open file structure for the debugfs "file" + * + * This function provides an open implementation for the "count" debugfs + * interface to the hardware latency detector. + */ +static int debug_count_fopen(struct inode *inode, struct file *filp) +{ + return 0; +} + +/** + * debug_count_fread - Read function for "count" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * + * This function provides a read implementation for the "count" debugfs + * interface to the hardware latency detector. Can be used to read the + * number of latency readings exceeding the configured threshold since + * the detector was last reset (e.g. by writing a zero into "count"). + */ +static ssize_t debug_count_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_data_read(filp, ubuf, cnt, ppos, &data.count); +} + +/** + * debug_count_fwrite - Write function for "count" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The user buffer that contains the value to write + * @cnt: The maximum number of bytes to write to "file" + * @ppos: The current position in the debugfs "file" + * + * This function provides a write implementation for the "count" debugfs + * interface to the hardware latency detector. Can be used to write a + * desired value, especially to zero the total count. + */ +static ssize_t debug_count_fwrite(struct file *filp, + const char __user *ubuf, + size_t cnt, + loff_t *ppos) +{ + return simple_data_write(filp, ubuf, cnt, ppos, &data.count); +} + +/** + * debug_enable_fopen - Dummy open function for "enable" debugfs interface + * @inode: The in-kernel inode representation of the debugfs "file" + * @filp: The active open file structure for the debugfs "file" + * + * This function provides an open implementation for the "enable" debugfs + * interface to the hardware latency detector. + */ +static int debug_enable_fopen(struct inode *inode, struct file *filp) +{ + return 0; +} + +/** + * debug_enable_fread - Read function for "enable" debugfs interface + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * + * This function provides a read implementation for the "enable" debugfs + * interface to the hardware latency detector. Can be used to determine + * whether the detector is currently enabled ("0\n" or "1\n" returned). + */ +static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[4]; + + if ((cnt < sizeof(buf)) || (*ppos)) + return 0; + + buf[0] = enabled ? '1' : '0'; + buf[1] = '\n'; + buf[2] = '\0'; + if (copy_to_user(ubuf, buf, strlen(buf))) + return -EFAULT; + return *ppos = strlen(buf); +} + +/** + * debug_enable_fwrite - Write function for "enable" debugfs interface + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The user buffer that contains the value to write + * @cnt: The maximum number of bytes to write to "file" + * @ppos: The current position in the debugfs "file" + * + * This function provides a write implementation for the "enable" debugfs + * interface to the hardware latency detector. Can be used to enable or + * disable the detector, which will have the side-effect of possibly + * also resetting the global stats and kicking off the measuring + * kthread (on an enable) or the converse (upon a disable). + */ +static ssize_t debug_enable_fwrite(struct file *filp, + const char __user *ubuf, + size_t cnt, + loff_t *ppos) +{ + char buf[4]; + int csize = min(cnt, sizeof(buf)); + long val = 0; + int err = 0; + + memset(buf, '\0', sizeof(buf)); + if (copy_from_user(buf, ubuf, csize)) + return -EFAULT; + + buf[sizeof(buf)-1] = '\0'; /* just in case */ + err = strict_strtoul(buf, 10, &val); + if (0 != err) + return -EINVAL; + + if (val) { + if (enabled) + goto unlock; + enabled = 1; + __reset_stats(); + if (start_kthread()) + return -EFAULT; + } else { + if (!enabled) + goto unlock; + enabled = 0; + err = stop_kthread(); + if (err) { + printk(KERN_ERR BANNER "cannot stop kthread\n"); + return -EFAULT; + } + wake_up(&data.wq); /* reader(s) should return */ + } +unlock: + return csize; +} + +/** + * debug_max_fopen - Open function for "max" debugfs entry + * @inode: The in-kernel inode representation of the debugfs "file" + * @filp: The active open file structure for the debugfs "file" + * + * This function provides an open implementation for the "max" debugfs + * interface to the hardware latency detector. + */ +static int debug_max_fopen(struct inode *inode, struct file *filp) +{ + return 0; +} + +/** + * debug_max_fread - Read function for "max" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * + * This function provides a read implementation for the "max" debugfs + * interface to the hardware latency detector. Can be used to determine + * the maximum latency value observed since it was last reset. + */ +static ssize_t debug_max_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_data_read(filp, ubuf, cnt, ppos, &data.max_sample); +} + +/** + * debug_max_fwrite - Write function for "max" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The user buffer that contains the value to write + * @cnt: The maximum number of bytes to write to "file" + * @ppos: The current position in the debugfs "file" + * + * This function provides a write implementation for the "max" debugfs + * interface to the hardware latency detector. Can be used to reset the + * maximum or set it to some other desired value - if, then, subsequent + * measurements exceed this value, the maximum will be updated. + */ +static ssize_t debug_max_fwrite(struct file *filp, + const char __user *ubuf, + size_t cnt, + loff_t *ppos) +{ + return simple_data_write(filp, ubuf, cnt, ppos, &data.max_sample); +} + + +/** + * debug_sample_fopen - An open function for "sample" debugfs interface + * @inode: The in-kernel inode representation of this debugfs "file" + * @filp: The active open file structure for the debugfs "file" + * + * This function handles opening the "sample" file within the hardware + * latency detector debugfs directory interface. This file is used to read + * raw samples from the global ring_buffer and allows the user to see a + * running latency history. Can be opened blocking or non-blocking, + * affecting whether it behaves as a buffer read pipe, or does not. + * Implements simple locking to prevent multiple simultaneous use. + */ +static int debug_sample_fopen(struct inode *inode, struct file *filp) +{ + if (!atomic_add_unless(&data.sample_open, 1, 1)) + return -EBUSY; + else + return 0; +} + +/** + * debug_sample_fread - A read function for "sample" debugfs interface + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The user buffer that will contain the samples read + * @cnt: The maximum bytes to read from the debugfs "file" + * @ppos: The current position in the debugfs "file" + * + * This function handles reading from the "sample" file within the hardware + * latency detector debugfs directory interface. This file is used to read + * raw samples from the global ring_buffer and allows the user to see a + * running latency history. By default this will block pending a new + * value written into the sample buffer, unless there are already a + * number of value(s) waiting in the buffer, or the sample file was + * previously opened in a non-blocking mode of operation. + */ +static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + int len = 0; + char buf[64]; + struct sample *sample = NULL; + + if (!enabled) + return 0; + + sample = kzalloc(sizeof(struct sample), GFP_KERNEL); + if (!sample) + return -ENOMEM; + + while (!buffer_get_sample(sample)) { + + DEFINE_WAIT(wait); + + if (filp->f_flags & O_NONBLOCK) { + len = -EAGAIN; + goto out; + } + + prepare_to_wait(&data.wq, &wait, TASK_INTERRUPTIBLE); + schedule(); + finish_wait(&data.wq, &wait); + + if (signal_pending(current)) { + len = -EINTR; + goto out; + } + + if (!enabled) { /* enable was toggled */ + len = 0; + goto out; + } + } + + len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\t%llu\n", + sample->timestamp.tv_sec, + sample->timestamp.tv_nsec, + sample->duration, + sample->outer_duration); + + + /* handling partial reads is more trouble than it's worth */ + if (len > cnt) + goto out; + + if (copy_to_user(ubuf, buf, len)) + len = -EFAULT; + +out: + kfree(sample); + return len; +} + +/** + * debug_sample_release - Release function for "sample" debugfs interface + * @inode: The in-kernel inode represenation of the debugfs "file" + * @filp: The active open file structure for the debugfs "file" + * + * This function completes the close of the debugfs interface "sample" file. + * Frees the sample_open "lock" so that other users may open the interface. + */ +static int debug_sample_release(struct inode *inode, struct file *filp) +{ + atomic_dec(&data.sample_open); + + return 0; +} + +/** + * debug_threshold_fopen - Open function for "threshold" debugfs entry + * @inode: The in-kernel inode representation of the debugfs "file" + * @filp: The active open file structure for the debugfs "file" + * + * This function provides an open implementation for the "threshold" debugfs + * interface to the hardware latency detector. + */ +static int debug_threshold_fopen(struct inode *inode, struct file *filp) +{ + return 0; +} + +/** + * debug_threshold_fread - Read function for "threshold" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * + * This function provides a read implementation for the "threshold" debugfs + * interface to the hardware latency detector. It can be used to determine + * the current threshold level at which a latency will be recorded in the + * global ring buffer, typically on the order of 10us. + */ +static ssize_t debug_threshold_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_data_read(filp, ubuf, cnt, ppos, &data.threshold); +} + +/** + * debug_threshold_fwrite - Write function for "threshold" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The user buffer that contains the value to write + * @cnt: The maximum number of bytes to write to "file" + * @ppos: The current position in the debugfs "file" + * + * This function provides a write implementation for the "threshold" debugfs + * interface to the hardware latency detector. It can be used to configure + * the threshold level at which any subsequently detected latencies will + * be recorded into the global ring buffer. + */ +static ssize_t debug_threshold_fwrite(struct file *filp, + const char __user *ubuf, + size_t cnt, + loff_t *ppos) +{ + int ret; + + ret = simple_data_write(filp, ubuf, cnt, ppos, &data.threshold); + + if (enabled) + wake_up_process(kthread); + + return ret; +} + +/** + * debug_width_fopen - Open function for "width" debugfs entry + * @inode: The in-kernel inode representation of the debugfs "file" + * @filp: The active open file structure for the debugfs "file" + * + * This function provides an open implementation for the "width" debugfs + * interface to the hardware latency detector. + */ +static int debug_width_fopen(struct inode *inode, struct file *filp) +{ + return 0; +} + +/** + * debug_width_fread - Read function for "width" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * + * This function provides a read implementation for the "width" debugfs + * interface to the hardware latency detector. It can be used to determine + * for how many us of the total window us we will actively sample for any + * hardware-induced latecy periods. Obviously, it is not possible to + * sample constantly and have the system respond to a sample reader, or, + * worse, without having the system appear to have gone out to lunch. + */ +static ssize_t debug_width_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_width); +} + +/** + * debug_width_fwrite - Write function for "width" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The user buffer that contains the value to write + * @cnt: The maximum number of bytes to write to "file" + * @ppos: The current position in the debugfs "file" + * + * This function provides a write implementation for the "width" debugfs + * interface to the hardware latency detector. It can be used to configure + * for how many us of the total window us we will actively sample for any + * hardware-induced latency periods. Obviously, it is not possible to + * sample constantly and have the system respond to a sample reader, or, + * worse, without having the system appear to have gone out to lunch. It + * is enforced that width is less that the total window size. + */ +static ssize_t debug_width_fwrite(struct file *filp, + const char __user *ubuf, + size_t cnt, + loff_t *ppos) +{ + char buf[U64STR_SIZE]; + int csize = min(cnt, sizeof(buf)); + u64 val = 0; + int err = 0; + + memset(buf, '\0', sizeof(buf)); + if (copy_from_user(buf, ubuf, csize)) + return -EFAULT; + + buf[U64STR_SIZE-1] = '\0'; /* just in case */ + err = strict_strtoull(buf, 10, &val); + if (0 != err) + return -EINVAL; + + mutex_lock(&data.lock); + if (val < data.sample_window) + data.sample_width = val; + else { + mutex_unlock(&data.lock); + return -EINVAL; + } + mutex_unlock(&data.lock); + + if (enabled) + wake_up_process(kthread); + + return csize; +} + +/** + * debug_window_fopen - Open function for "window" debugfs entry + * @inode: The in-kernel inode representation of the debugfs "file" + * @filp: The active open file structure for the debugfs "file" + * + * This function provides an open implementation for the "window" debugfs + * interface to the hardware latency detector. The window is the total time + * in us that will be considered one sample period. Conceptually, windows + * occur back-to-back and contain a sample width period during which + * actual sampling occurs. + */ +static int debug_window_fopen(struct inode *inode, struct file *filp) +{ + return 0; +} + +/** + * debug_window_fread - Read function for "window" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The userspace provided buffer to read value into + * @cnt: The maximum number of bytes to read + * @ppos: The current "file" position + * + * This function provides a read implementation for the "window" debugfs + * interface to the hardware latency detector. The window is the total time + * in us that will be considered one sample period. Conceptually, windows + * occur back-to-back and contain a sample width period during which + * actual sampling occurs. Can be used to read the total window size. + */ +static ssize_t debug_window_fread(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_window); +} + +/** + * debug_window_fwrite - Write function for "window" debugfs entry + * @filp: The active open file structure for the debugfs "file" + * @ubuf: The user buffer that contains the value to write + * @cnt: The maximum number of bytes to write to "file" + * @ppos: The current position in the debugfs "file" + * + * This function provides a write implementation for the "window" debufds + * interface to the hardware latency detetector. The window is the total time + * in us that will be considered one sample period. Conceptually, windows + * occur back-to-back and contain a sample width period during which + * actual sampling occurs. Can be used to write a new total window size. It + * is enfoced that any value written must be greater than the sample width + * size, or an error results. + */ +static ssize_t debug_window_fwrite(struct file *filp, + const char __user *ubuf, + size_t cnt, + loff_t *ppos) +{ + char buf[U64STR_SIZE]; + int csize = min(cnt, sizeof(buf)); + u64 val = 0; + int err = 0; + + memset(buf, '\0', sizeof(buf)); + if (copy_from_user(buf, ubuf, csize)) + return -EFAULT; + + buf[U64STR_SIZE-1] = '\0'; /* just in case */ + err = strict_strtoull(buf, 10, &val); + if (0 != err) + return -EINVAL; + + mutex_lock(&data.lock); + if (data.sample_width < val) + data.sample_window = val; + else { + mutex_unlock(&data.lock); + return -EINVAL; + } + mutex_unlock(&data.lock); + + return csize; +} + +/* + * Function pointers for the "count" debugfs file operations + */ +static const struct file_operations count_fops = { + .open = debug_count_fopen, + .read = debug_count_fread, + .write = debug_count_fwrite, + .owner = THIS_MODULE, +}; + +/* + * Function pointers for the "enable" debugfs file operations + */ +static const struct file_operations enable_fops = { + .open = debug_enable_fopen, + .read = debug_enable_fread, + .write = debug_enable_fwrite, + .owner = THIS_MODULE, +}; + +/* + * Function pointers for the "max" debugfs file operations + */ +static const struct file_operations max_fops = { + .open = debug_max_fopen, + .read = debug_max_fread, + .write = debug_max_fwrite, + .owner = THIS_MODULE, +}; + +/* + * Function pointers for the "sample" debugfs file operations + */ +static const struct file_operations sample_fops = { + .open = debug_sample_fopen, + .read = debug_sample_fread, + .release = debug_sample_release, + .owner = THIS_MODULE, +}; + +/* + * Function pointers for the "threshold" debugfs file operations + */ +static const struct file_operations threshold_fops = { + .open = debug_threshold_fopen, + .read = debug_threshold_fread, + .write = debug_threshold_fwrite, + .owner = THIS_MODULE, +}; + +/* + * Function pointers for the "width" debugfs file operations + */ +static const struct file_operations width_fops = { + .open = debug_width_fopen, + .read = debug_width_fread, + .write = debug_width_fwrite, + .owner = THIS_MODULE, +}; + +/* + * Function pointers for the "window" debugfs file operations + */ +static const struct file_operations window_fops = { + .open = debug_window_fopen, + .read = debug_window_fread, + .write = debug_window_fwrite, + .owner = THIS_MODULE, +}; + +/** + * init_debugfs - A function to initialize the debugfs interface files + * + * This function creates entries in debugfs for "hwlat_detector", including + * files to read values from the detector, current samples, and the + * maximum sample that has been captured since the hardware latency + * dectector was started. + */ +static int init_debugfs(void) +{ + int ret = -ENOMEM; + + debug_dir = debugfs_create_dir(DRVNAME, NULL); + if (!debug_dir) + goto err_debug_dir; + + debug_sample = debugfs_create_file("sample", 0444, + debug_dir, NULL, + &sample_fops); + if (!debug_sample) + goto err_sample; + + debug_count = debugfs_create_file("count", 0444, + debug_dir, NULL, + &count_fops); + if (!debug_count) + goto err_count; + + debug_max = debugfs_create_file("max", 0444, + debug_dir, NULL, + &max_fops); + if (!debug_max) + goto err_max; + + debug_sample_window = debugfs_create_file("window", 0644, + debug_dir, NULL, + &window_fops); + if (!debug_sample_window) + goto err_window; + + debug_sample_width = debugfs_create_file("width", 0644, + debug_dir, NULL, + &width_fops); + if (!debug_sample_width) + goto err_width; + + debug_threshold = debugfs_create_file("threshold", 0644, + debug_dir, NULL, + &threshold_fops); + if (!debug_threshold) + goto err_threshold; + + debug_enable = debugfs_create_file("enable", 0644, + debug_dir, &enabled, + &enable_fops); + if (!debug_enable) + goto err_enable; + + else { + ret = 0; + goto out; + } + +err_enable: + debugfs_remove(debug_threshold); +err_threshold: + debugfs_remove(debug_sample_width); +err_width: + debugfs_remove(debug_sample_window); +err_window: + debugfs_remove(debug_max); +err_max: + debugfs_remove(debug_count); +err_count: + debugfs_remove(debug_sample); +err_sample: + debugfs_remove(debug_dir); +err_debug_dir: +out: + return ret; +} + +/** + * free_debugfs - A function to cleanup the debugfs file interface + */ +static void free_debugfs(void) +{ + /* could also use a debugfs_remove_recursive */ + debugfs_remove(debug_enable); + debugfs_remove(debug_threshold); + debugfs_remove(debug_sample_width); + debugfs_remove(debug_sample_window); + debugfs_remove(debug_max); + debugfs_remove(debug_count); + debugfs_remove(debug_sample); + debugfs_remove(debug_dir); +} + +/** + * detector_init - Standard module initialization code + */ +static int detector_init(void) +{ + int ret = -ENOMEM; + + printk(KERN_INFO BANNER "version %s\n", VERSION); + + ret = init_stats(); + if (0 != ret) + goto out; + + ret = init_debugfs(); + if (0 != ret) + goto err_stats; + + if (enabled) + ret = start_kthread(); + + goto out; + +err_stats: + ring_buffer_free(ring_buffer); +out: + return ret; + +} + +/** + * detector_exit - Standard module cleanup code + */ +static void detector_exit(void) +{ + int err; + + if (enabled) { + enabled = 0; + err = stop_kthread(); + if (err) + printk(KERN_ERR BANNER "cannot stop kthread\n"); + } + + free_debugfs(); + ring_buffer_free(ring_buffer); /* free up the ring buffer */ + +} + +module_init(detector_init); +module_exit(detector_exit); diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index f4f3038..6f9285d 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -976,15 +976,12 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id) struct sg_mapping_iter *sg_miter = &host->sg_miter; struct variant_data *variant = host->variant; void __iomem *base = host->base; - unsigned long flags; u32 status; status = readl(base + MMCISTATUS); dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status); - local_irq_save(flags); - do { unsigned int remain, len; char *buffer; @@ -1024,8 +1021,6 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id) sg_miter_stop(sg_miter); - local_irq_restore(flags); - /* * If we have less than the fifo 'half-full' threshold to transfer, * trigger a PIO interrupt as soon as any data is available. diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 3835321..096de88 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -164,6 +164,7 @@ config VXLAN config NETCONSOLE tristate "Network console logging support" + depends on !PREEMPT_RT_FULL ---help--- If you want to log kernel messages over the network, enable this. See for details. diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 072c6f1..3e340fd 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -842,9 +842,9 @@ static void poll_vortex(struct net_device *dev) { struct vortex_private *vp = netdev_priv(dev); unsigned long flags; - local_irq_save(flags); + local_irq_save_nort(flags); (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev); - local_irq_restore(flags); + local_irq_restore_nort(flags); } #endif @@ -1918,12 +1918,12 @@ static void vortex_tx_timeout(struct net_device *dev) * Block interrupts because vortex_interrupt does a bare spin_lock() */ unsigned long flags; - local_irq_save(flags); + local_irq_save_nort(flags); if (vp->full_bus_master_tx) boomerang_interrupt(dev->irq, dev); else vortex_interrupt(dev->irq, dev); - local_irq_restore(flags); + local_irq_restore_nort(flags); } } diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 11cdf1d..e1de3dc 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2206,11 +2206,7 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb, } tpd_req = atl1c_cal_tpd_req(skb); - if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) { - if (netif_msg_pktdata(adapter)) - dev_info(&adapter->pdev->dev, "tx locked\n"); - return NETDEV_TX_LOCKED; - } + spin_lock_irqsave(&adapter->tx_lock, flags); if (atl1c_tpd_avail(adapter, type) < tpd_req) { /* no enough descriptor, just stop queue */ diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index c23bb02..30ca4af 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -1838,8 +1838,7 @@ static netdev_tx_t atl1e_xmit_frame(struct sk_buff *skb, return NETDEV_TX_OK; } tpd_req = atl1e_cal_tdp_req(skb); - if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) - return NETDEV_TX_LOCKED; + spin_lock_irqsave(&adapter->tx_lock, flags); if (atl1e_tpd_avail(adapter) < tpd_req) { /* no enough descriptor, just stop queue */ diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c index 8061fb0..bfe5c72 100644 --- a/drivers/net/ethernet/chelsio/cxgb/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb/sge.c @@ -1665,8 +1665,7 @@ static int t1_sge_tx(struct sk_buff *skb, struct adapter *adapter, struct cmdQ *q = &sge->cmdQ[qid]; unsigned int credits, pidx, genbit, count, use_sched_skb = 0; - if (!spin_trylock(&q->lock)) - return NETDEV_TX_LOCKED; + spin_lock(&q->lock); reclaim_completed_tx(sge, q); diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 1e9443d..d25961b 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1943,6 +1943,7 @@ static void tulip_remove_one(struct pci_dev *pdev) pci_iounmap(pdev, tp->base_addr); free_netdev (dev); pci_release_regions (pdev); + pci_disable_device (pdev); pci_set_drvdata (pdev, NULL); /* pci_power_off (pdev, -1); */ diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 2375a01..0343a14 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1674,7 +1674,7 @@ void stop_gfar(struct net_device *dev) /* Lock it down */ - local_irq_save(flags); + local_irq_save_nort(flags); lock_tx_qs(priv); lock_rx_qs(priv); @@ -1682,7 +1682,7 @@ void stop_gfar(struct net_device *dev) unlock_rx_qs(priv); unlock_tx_qs(priv); - local_irq_restore(flags); + local_irq_restore_nort(flags); /* Free the IRQs */ if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { @@ -2983,7 +2983,7 @@ static void adjust_link(struct net_device *dev) struct phy_device *phydev = priv->phydev; int new_state = 0; - local_irq_save(flags); + local_irq_save_nort(flags); lock_tx_qs(priv); if (phydev->link) { @@ -3052,7 +3052,7 @@ static void adjust_link(struct net_device *dev) if (new_state && netif_msg_link(priv)) phy_print_status(phydev); unlock_tx_qs(priv); - local_irq_restore(flags); + local_irq_restore_nort(flags); } /* Update the hash table based on the current list of multicast diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 51b0094..809d92c 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -4089,12 +4089,7 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev) [skb->priority & (MAX_TX_FIFOS - 1)]; fifo = &mac_control->fifos[queue]; - if (do_spin_lock) - spin_lock_irqsave(&fifo->tx_lock, flags); - else { - if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags))) - return NETDEV_TX_LOCKED; - } + spin_lock_irqsave(&fifo->tx_lock, flags); if (sp->config.multiq) { if (__netif_subqueue_stopped(dev, fifo->fifo_no)) { diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 0c1c65a..12934e4 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -2109,10 +2109,8 @@ static int pch_gbe_xmit_frame(struct sk_buff *skb, struct net_device *netdev) struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring; unsigned long flags; - if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) { - /* Collision - tell upper layer to requeue */ - return NETDEV_TX_LOCKED; - } + spin_lock_irqsave(&tx_ring->tx_lock, flags); + if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) { netif_stop_queue(netdev); spin_unlock_irqrestore(&tx_ring->tx_lock, flags); diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 3ccedeb..fefe07b 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -2213,7 +2213,7 @@ static void rtl8139_poll_controller(struct net_device *dev) struct rtl8139_private *tp = netdev_priv(dev); const int irq = tp->pci_dev->irq; - disable_irq(irq); + disable_irq_nosync(irq); rtl8139_interrupt(irq, dev); enable_irq(irq); } diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 61a1540..7edf580 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1629,13 +1629,8 @@ static netdev_tx_t bdx_tx_transmit(struct sk_buff *skb, unsigned long flags; ENTER; - local_irq_save(flags); - if (!spin_trylock(&priv->tx_lock)) { - local_irq_restore(flags); - DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n", - BDX_DRV_NAME, ndev->name); - return NETDEV_TX_LOCKED; - } + + spin_lock_irqsave(&priv->tx_lock, flags); /* build tx descriptor */ BDX_ASSERT(f->m.wptr >= f->m.memsz); /* started with valid wptr */ diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index f433b59..c575865 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -174,11 +174,7 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev) unsigned long flags; int add_num = 1; - local_irq_save(flags); - if (!spin_trylock(&rnet->tx_lock)) { - local_irq_restore(flags); - return NETDEV_TX_LOCKED; - } + spin_lock_irqsave(&rnet->tx_lock, flags); if (is_multicast_ether_addr(eth->h_dest)) add_num = nets[rnet->mport->id].nact; diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c index 1f9cb55..a28f298 100644 --- a/drivers/net/wireless/orinoco/orinoco_usb.c +++ b/drivers/net/wireless/orinoco/orinoco_usb.c @@ -714,7 +714,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv, while (!ctx->done.done && msecs--) udelay(1000); } else { - wait_event_interruptible(ctx->done.wait, + swait_event_interruptible(ctx->done.wait, ctx->done.done); } break; diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 061da8c..a61ddd1 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -465,7 +465,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev) WARN_ON(!dev->block_cfg_access); dev->block_cfg_access = 0; - wake_up_all(&pci_cfg_wait); + wake_up_all_locked(&pci_cfg_wait); raw_spin_unlock_irqrestore(&pci_lock, flags); } EXPORT_SYMBOL_GPL(pci_cfg_access_unlock); diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 32ae6c6..7586dd9 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1281,7 +1281,7 @@ static void fcoe_percpu_thread_destroy(unsigned int cpu) struct sk_buff *skb; #ifdef CONFIG_SMP struct fcoe_percpu_s *p0; - unsigned targ_cpu = get_cpu(); + unsigned targ_cpu = get_cpu_light(); #endif /* CONFIG_SMP */ FCOE_DBG("Destroying receive thread for CPU %d\n", cpu); @@ -1337,7 +1337,7 @@ static void fcoe_percpu_thread_destroy(unsigned int cpu) kfree_skb(skb); spin_unlock_bh(&p->fcoe_rx_list.lock); } - put_cpu(); + put_cpu_light(); #else /* * This a non-SMP scenario where the singular Rx thread is @@ -1555,11 +1555,11 @@ err2: static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) { struct fcoe_percpu_s *fps; - int rc; + int rc, cpu = get_cpu_light(); - fps = &get_cpu_var(fcoe_percpu); + fps = &per_cpu(fcoe_percpu, cpu); rc = fcoe_get_paged_crc_eof(skb, tlen, fps); - put_cpu_var(fcoe_percpu); + put_cpu_light(); return rc; } @@ -1757,11 +1757,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport, return 0; } - stats = per_cpu_ptr(lport->stats, get_cpu()); + stats = per_cpu_ptr(lport->stats, get_cpu_light()); stats->InvalidCRCCount++; if (stats->InvalidCRCCount < 5) printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); - put_cpu(); + put_cpu_light(); return -EINVAL; } @@ -1837,13 +1837,13 @@ static void fcoe_recv_frame(struct sk_buff *skb) goto drop; if (!fcoe_filter_frames(lport, fp)) { - put_cpu(); + put_cpu_light(); fc_exch_recv(lport, fp); return; } drop: stats->ErrorFrames++; - put_cpu(); + put_cpu_light(); kfree_skb(skb); } diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 795843d..d25a311 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -792,7 +792,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) INIT_LIST_HEAD(&del_list); - stats = per_cpu_ptr(fip->lp->stats, get_cpu()); + stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; @@ -828,7 +828,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) sel_time = fcf->time; } } - put_cpu(); + put_cpu_light(); list_for_each_entry_safe(fcf, next, &del_list, list) { /* Removes fcf from current list */ diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 0353d7f..3e6d5a8 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -584,7 +584,7 @@ static void set_performant_mode(struct ctlr_info *h, struct CommandList *c) c->busaddr |= 1 | (h->blockFetchTable[c->Header.SGList] << 1); if (likely(h->msix_vector)) c->Header.ReplyQueue = - smp_processor_id() % h->nreply_queues; + raw_smp_processor_id() % h->nreply_queues; } } diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 8b928c6..c53ea66 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -741,10 +741,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport, } memset(ep, 0, sizeof(*ep)); - cpu = get_cpu(); + cpu = get_cpu_light(); pool = per_cpu_ptr(mp->pool, cpu); spin_lock_bh(&pool->lock); - put_cpu(); + put_cpu_light(); /* peek cache of free slot */ if (pool->left != FC_XID_UNKNOWN) { diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index 0a5c895..c387754 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -58,12 +58,12 @@ qla2x00_poll(struct rsp_que *rsp) { unsigned long flags; struct qla_hw_data *ha = rsp->hw; - local_irq_save(flags); + local_irq_save_nort(flags); if (IS_QLA82XX(ha)) qla82xx_poll(0, rsp); else ha->isp_ops->intr_handler(0, rsp); - local_irq_restore(flags); + local_irq_restore_nort(flags); } static inline uint8_t * diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index d28d7af..d2be22a 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -38,6 +38,7 @@ #include #include #include +#include #ifdef CONFIG_SPARC #include #endif @@ -80,7 +81,16 @@ static unsigned int skip_txen_test; /* force skip of txen test at init time */ #define DEBUG_INTR(fmt...) do { } while (0) #endif -#define PASS_LIMIT 512 +/* + * On -rt we can have a more delays, and legitimately + * so - so don't drop work spuriously and spam the + * syslog: + */ +#ifdef CONFIG_PREEMPT_RT_FULL +# define PASS_LIMIT 1000000 +#else +# define PASS_LIMIT 512 +#endif #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) @@ -2864,14 +2874,10 @@ serial8250_console_write(struct console *co, const char *s, unsigned int count) touch_nmi_watchdog(); - local_irq_save(flags); - if (port->sysrq) { - /* serial8250_handle_irq() already took the lock */ - locked = 0; - } else if (oops_in_progress) { - locked = spin_trylock(&port->lock); - } else - spin_lock(&port->lock); + if (port->sysrq || oops_in_progress || in_kdb_printk()) + locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); /* * First save the IER then disable the interrupts @@ -2903,8 +2909,7 @@ serial8250_console_write(struct console *co, const char *s, unsigned int count) serial8250_modem_status(up); if (locked) - spin_unlock(&port->lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&port->lock, flags); } static int __init serial8250_console_setup(struct console *co, char *options) diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 7a55fe7..94404c9 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1929,13 +1929,19 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) clk_enable(uap->clk); - local_irq_save(flags); + /* + * local_irq_save(flags); + * + * This local_irq_save() is nonsense. If we come in via sysrq + * handling then interrupts are already disabled. Aside of + * that the port.sysrq check is racy on SMP regardless. + */ if (uap->port.sysrq) locked = 0; else if (oops_in_progress) - locked = spin_trylock(&uap->port.lock); + locked = spin_trylock_irqsave(&uap->port.lock, flags); else - spin_lock(&uap->port.lock); + spin_lock_irqsave(&uap->port.lock, flags); /* * First save the CR then disable the interrupts @@ -1957,8 +1963,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) writew(old_cr, uap->port.membase + UART011_CR); if (locked) - spin_unlock(&uap->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&uap->port.lock, flags); clk_disable(uap->clk); } diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index f0b9f6b..cf9b0a7 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1169,13 +1169,10 @@ serial_omap_console_write(struct console *co, const char *s, pm_runtime_get_sync(up->dev); - local_irq_save(flags); - if (up->port.sysrq) - locked = 0; - else if (oops_in_progress) - locked = spin_trylock(&up->port.lock); + if (up->port.sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&up->port.lock, flags); else - spin_lock(&up->port.lock); + spin_lock_irqsave(&up->port.lock, flags); /* * First save the IER then disable the interrupts @@ -1204,8 +1201,7 @@ serial_omap_console_write(struct console *co, const char *s, pm_runtime_mark_last_busy(up->dev); pm_runtime_put_autosuspend(up->dev); if (locked) - spin_unlock(&up->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&up->port.lock, flags); } static int __init diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 9121c1f..94d3215 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -517,10 +517,15 @@ void tty_flip_buffer_push(struct tty_port *port) buf->tail->commit = buf->tail->used; spin_unlock_irqrestore(&buf->lock, flags); +#ifndef CONFIG_PREEMPT_RT_FULL if (port->low_latency) flush_to_ldisc(&buf->work); else schedule_work(&buf->work); +#else + flush_to_ldisc(&buf->work); +#endif + } EXPORT_SYMBOL(tty_flip_buffer_push); @@ -545,4 +550,3 @@ void tty_buffer_init(struct tty_port *port) buf->memory_used = 0; INIT_WORK(&buf->work, flush_to_ldisc); } - diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 1afe192..bc4ffe4 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -197,9 +197,10 @@ static inline void tty_ldisc_put(struct tty_ldisc *ld) WARN_ON(!atomic_dec_and_test(&ld->users)); ld->ops->refcount--; + raw_spin_unlock_irqrestore(&tty_ldisc_lock, flags); + module_put(ld->ops->owner); kfree(ld); - raw_spin_unlock_irqrestore(&tty_ldisc_lock, flags); } static void *tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index d53547d..499be83 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2221,7 +2221,7 @@ irqreturn_t usb_hcd_irq (int irq, void *__hcd) * when the first handler doesn't use it. So let's just * assume it's never used. */ - local_irq_save(flags); + local_irq_save_nort(flags); if (unlikely(HCD_DEAD(hcd) || !HCD_HW_ACCESSIBLE(hcd))) rc = IRQ_NONE; @@ -2230,7 +2230,7 @@ irqreturn_t usb_hcd_irq (int irq, void *__hcd) else rc = IRQ_HANDLED; - local_irq_restore(flags); + local_irq_restore_nort(flags); return rc; } EXPORT_SYMBOL_GPL(usb_hcd_irq); diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index b6e9d91..35d9c53 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -1282,7 +1282,7 @@ static void ffs_data_put(struct ffs_data *ffs) pr_info("%s(): freeing\n", __func__); ffs_data_clear(ffs); BUG_ON(waitqueue_active(&ffs->ev.waitq) || - waitqueue_active(&ffs->ep0req_completion.wait)); + swaitqueue_active(&ffs->ep0req_completion.wait)); kfree(ffs->dev_name); kfree(ffs); } diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index 570c005..c60233d 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -340,7 +340,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) spin_unlock_irq (&epdata->dev->lock); if (likely (value == 0)) { - value = wait_event_interruptible (done.wait, done.done); + value = swait_event_interruptible (done.wait, done.done); if (value != 0) { spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { @@ -349,7 +349,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) usb_ep_dequeue (epdata->ep, epdata->req); spin_unlock_irq (&epdata->dev->lock); - wait_event (done.wait, done.done); + swait_event (done.wait, done.done); if (epdata->status == -ECONNRESET) epdata->status = -EINTR; } else { diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 865946c..8b7434fdb 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -863,9 +863,13 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) } if (ints & OHCI_INTR_WDH) { - spin_lock (&ohci->lock); - dl_done_list (ohci); - spin_unlock (&ohci->lock); + if (ohci->hcca->done_head == 0) { + ints &= ~OHCI_INTR_WDH; + } else { + spin_lock (&ohci->lock); + dl_done_list (ohci); + spin_unlock (&ohci->lock); + } } if (quirk_zfmicro(ohci) && (ints & OHCI_INTR_SF)) { diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index 3f1128b..c2ed9c4 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -34,6 +34,7 @@ #include #include #include +#include #include #include diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 13ddec9..b2f1903 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -157,7 +157,7 @@ again: parent = p->d_parent; if (!spin_trylock(&parent->d_lock)) { spin_unlock(&p->d_lock); - cpu_relax(); + cpu_chill(); goto relock; } spin_unlock(&p->d_lock); diff --git a/fs/buffer.c b/fs/buffer.c index 75964d7..13876a8 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -288,8 +288,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) * decide that the page is now completely done. */ first = page_buffers(page); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + flags = bh_uptodate_lock_irqsave(first); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; @@ -302,8 +301,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } while (tmp != bh); - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); + bh_uptodate_unlock_irqrestore(first, flags); /* * If none of the buffers had errors and they are all @@ -315,9 +313,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) return; still_busy: - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - return; + bh_uptodate_unlock_irqrestore(first, flags); } /* @@ -351,8 +347,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) } first = page_buffers(page); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + flags = bh_uptodate_lock_irqsave(first); clear_buffer_async_write(bh); unlock_buffer(bh); @@ -364,15 +359,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); + bh_uptodate_unlock_irqrestore(first, flags); end_page_writeback(page); return; still_busy: - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - return; + bh_uptodate_unlock_irqrestore(first, flags); } EXPORT_SYMBOL(end_buffer_async_write); @@ -3277,6 +3269,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); + buffer_head_init_locks(ret); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); diff --git a/fs/dcache.c b/fs/dcache.c index 9a59653..c65c38e 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "internal.h" #include "mount.h" @@ -453,7 +454,7 @@ static inline struct dentry *dentry_kill(struct dentry *dentry, int ref) if (inode && !spin_trylock(&inode->i_lock)) { relock: spin_unlock(&dentry->d_lock); - cpu_relax(); + cpu_chill(); return dentry; /* try again with same dentry */ } if (IS_ROOT(dentry)) @@ -835,7 +836,7 @@ relock: if (!spin_trylock(&dentry->d_lock)) { spin_unlock(&dcache_lru_lock); - cpu_relax(); + cpu_chill(); goto relock; } @@ -2072,7 +2073,7 @@ again: if (dentry->d_count == 1) { if (!spin_trylock(&inode->i_lock)) { spin_unlock(&dentry->d_lock); - cpu_relax(); + cpu_chill(); goto again; } dentry->d_flags &= ~DCACHE_CANT_MOUNT; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index deecc72..99c53c7 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -500,12 +500,12 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests) */ static void ep_poll_safewake(wait_queue_head_t *wq) { - int this_cpu = get_cpu(); + int this_cpu = get_cpu_light(); ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); - put_cpu(); + put_cpu_light(); } static void ep_remove_wait_queue(struct eppoll_entry *pwq) diff --git a/fs/exec.c b/fs/exec.c index bb60cda..1403be8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -836,10 +836,12 @@ static int exec_mmap(struct mm_struct *mm) } } task_lock(tsk); + preempt_disable_rt(); active_mm = tsk->active_mm; tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + preempt_enable_rt(); task_unlock(tsk); arch_pick_mmap_layout(mm); if (old_mm) { diff --git a/fs/fscache/page.c b/fs/fscache/page.c index ff000e5..c84696c 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -796,11 +796,13 @@ void fscache_invalidate_writes(struct fscache_cookie *cookie) _enter(""); - while (spin_lock(&cookie->stores_lock), - n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, - ARRAY_SIZE(results), - FSCACHE_COOKIE_PENDING_TAG), - n > 0) { + spin_lock(&cookie->stores_lock); + while (1) { + n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, + ARRAY_SIZE(results), + FSCACHE_COOKIE_PENDING_TAG); + if (n == 0) + break; for (i = n - 1; i >= 0; i--) { page = results[i]; radix_tree_delete(&cookie->stores, page->index); @@ -810,6 +812,7 @@ void fscache_invalidate_writes(struct fscache_cookie *cookie) for (i = n - 1; i >= 0; i--) page_cache_release(results[i]); + spin_lock(&cookie->stores_lock); } spin_unlock(&cookie->stores_lock); diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 08c0304..95debd7 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -129,6 +129,8 @@ void __log_wait_for_space(journal_t *journal) if (journal->j_flags & JFS_ABORT) return; spin_unlock(&journal->j_state_lock); + if (current->plug) + io_schedule(); mutex_lock(&journal->j_checkpoint_mutex); /* diff --git a/fs/namespace.c b/fs/namespace.c index a45ba4f..7a4f8d8 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "pnode.h" #include "internal.h" @@ -315,8 +316,11 @@ int __mnt_want_write(struct vfsmount *m) * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); - while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) - cpu_relax(); + while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { + preempt_enable(); + cpu_chill(); + preempt_disable(); + } /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will * be set to match its requirements. So we must not load that until @@ -1286,7 +1290,7 @@ static int do_umount(struct mount *mnt, int flags) return retval; } -/* +/* * Is the caller allowed to modify his namespace? */ static inline bool may_mount(void) @@ -1714,7 +1718,7 @@ static int do_loopback(struct path *path, const char *old_name, err = -EINVAL; if (mnt_ns_loop(&old_path)) - goto out; + goto out; mp = lock_mount(path); err = PTR_ERR(mp); diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index fa9c05f..f5d4565 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -108,8 +108,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) "0x%llx.", (unsigned long long)bh->b_blocknr); } first = page_buffers(page); - local_irq_save(flags); - bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + flags = bh_uptodate_lock_irqsave(first); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; @@ -124,8 +123,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } while (tmp != bh); - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); + bh_uptodate_unlock_irqrestore(first, flags); /* * If none of the buffers had errors then we can set the page uptodate, * but we first have to perform the post read mst fixups, if the @@ -146,13 +144,13 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) recs = PAGE_CACHE_SIZE / rec_size; /* Should have been verified before we got here... */ BUG_ON(!recs); - local_irq_save(flags); + local_irq_save_nort(flags); kaddr = kmap_atomic(page); for (i = 0; i < recs; i++) post_read_mst_fixup((NTFS_RECORD*)(kaddr + i * rec_size), rec_size); kunmap_atomic(kaddr); - local_irq_restore(flags); + local_irq_restore_nort(flags); flush_dcache_page(page); if (likely(page_uptodate && !PageError(page))) SetPageUptodate(page); @@ -160,9 +158,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) unlock_page(page); return; still_busy: - bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); - local_irq_restore(flags); - return; + bh_uptodate_unlock_irqrestore(first, flags); } /** diff --git a/fs/timerfd.c b/fs/timerfd.c index 32b644f..1844c97 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -308,7 +308,7 @@ static int do_timerfd_settime(int ufd, int flags, if (hrtimer_try_to_cancel(&ctx->tmr) >= 0) break; spin_unlock_irq(&ctx->wqh.lock); - cpu_relax(); + hrtimer_wait_for_timer(&ctx->tmr); } /* diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 68534ef..0ef299d 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -72,6 +72,7 @@ #define acpi_cache_t struct kmem_cache #define acpi_spinlock spinlock_t * +#define acpi_raw_spinlock raw_spinlock_t * #define acpi_cpu_flags unsigned long #else /* !__KERNEL__ */ @@ -174,6 +175,19 @@ static inline void *acpi_os_acquire_object(acpi_cache_t * cache) lock ? AE_OK : AE_NO_MEMORY; \ }) +#define acpi_os_create_raw_lock(__handle) \ +({ \ + raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \ + \ + if (lock) { \ + *(__handle) = lock; \ + raw_spin_lock_init(*(__handle)); \ + } \ + lock ? AE_OK : AE_NO_MEMORY; \ +}) + +#define acpi_os_delete_raw_lock(__handle) kfree(__handle) + #endif /* __KERNEL__ */ #endif /* __ACLINUX_H__ */ diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 7d10f96..aee7fd2 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -202,6 +202,20 @@ extern void warn_slowpath_null(const char *file, const int line); # define WARN_ON_SMP(x) ({0;}) #endif +#ifdef CONFIG_PREEMPT_RT_BASE +# define BUG_ON_RT(c) BUG_ON(c) +# define BUG_ON_NONRT(c) do { } while (0) +# define WARN_ON_RT(condition) WARN_ON(condition) +# define WARN_ON_NONRT(condition) do { } while (0) +# define WARN_ON_ONCE_NONRT(condition) do { } while (0) +#else +# define BUG_ON_RT(c) do { } while (0) +# define BUG_ON_NONRT(c) BUG_ON(c) +# define WARN_ON_RT(condition) do { } while (0) +# define WARN_ON_NONRT(condition) WARN_ON(condition) +# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition) +#endif + #endif /* __ASSEMBLY__ */ #endif diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 9e52b0626..2f4697c 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -74,8 +74,52 @@ struct buffer_head { struct address_space *b_assoc_map; /* mapping this buffer is associated with */ atomic_t b_count; /* users using this buffer_head */ +#ifdef CONFIG_PREEMPT_RT_BASE + spinlock_t b_uptodate_lock; +#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \ + defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE) + spinlock_t b_state_lock; + spinlock_t b_journal_head_lock; +#endif +#endif }; +static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh) +{ + unsigned long flags; + +#ifndef CONFIG_PREEMPT_RT_BASE + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &bh->b_state); +#else + spin_lock_irqsave(&bh->b_uptodate_lock, flags); +#endif + return flags; +} + +static inline void +bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags) +{ +#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state); + local_irq_restore(flags); +#else + spin_unlock_irqrestore(&bh->b_uptodate_lock, flags); +#endif +} + +static inline void buffer_head_init_locks(struct buffer_head *bh) +{ +#ifdef CONFIG_PREEMPT_RT_BASE + spin_lock_init(&bh->b_uptodate_lock); +#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \ + defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE) + spin_lock_init(&bh->b_state_lock); + spin_lock_init(&bh->b_journal_head_lock); +#endif +#endif +} + /* * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() * and buffer_foo() functions. diff --git a/include/linux/completion.h b/include/linux/completion.h index 33f0280..e197dcd 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -8,7 +8,7 @@ * See kernel/sched.c for details. */ -#include +#include /* * struct completion - structure used to maintain state for a "completion" @@ -24,11 +24,11 @@ */ struct completion { unsigned int done; - wait_queue_head_t wait; + struct swait_head wait; }; #define COMPLETION_INITIALIZER(work) \ - { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } + { 0, SWAIT_HEAD_INITIALIZER((work).wait) } #define COMPLETION_INITIALIZER_ONSTACK(work) \ ({ init_completion(&work); work; }) @@ -73,7 +73,7 @@ struct completion { static inline void init_completion(struct completion *x) { x->done = 0; - init_waitqueue_head(&x->wait); + init_swait_head(&x->wait); } extern void wait_for_completion(struct completion *); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9f3c7e8..44ed889 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -1,15 +1,15 @@ /* * include/linux/cpu.h - generic cpu definition * - * This is mainly for topological representation. We define the - * basic 'struct cpu' here, which can be embedded in per-arch + * This is mainly for topological representation. We define the + * basic 'struct cpu' here, which can be embedded in per-arch * definitions of processors. * * Basic handling of the devices is done in drivers/base/cpu.c - * and system devices are handled in drivers/base/sys.c. + * and system devices are handled in drivers/base/sys.c. * * CPUs are exported via sysfs in the class/cpu/devices/ - * directory. + * directory. */ #ifndef _LINUX_CPU_H_ #define _LINUX_CPU_H_ @@ -177,6 +177,8 @@ extern void get_online_cpus(void); extern void put_online_cpus(void); extern void cpu_hotplug_disable(void); extern void cpu_hotplug_enable(void); +extern void pin_current_cpu(void); +extern void unpin_current_cpu(void); #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) #define register_hotcpu_notifier(nb) register_cpu_notifier(nb) #define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb) @@ -202,6 +204,8 @@ static inline void cpu_hotplug_driver_unlock(void) #define put_online_cpus() do { } while (0) #define cpu_hotplug_disable() do { } while (0) #define cpu_hotplug_enable() do { } while (0) +static inline void pin_current_cpu(void) { } +static inline void unpin_current_cpu(void) { } #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) /* These aren't inline functions due to a GCC bug. */ #define register_hotcpu_notifier(nb) ({ (void)(nb); 0; }) diff --git a/include/linux/delay.h b/include/linux/delay.h index a6ecb34..e23a7c0 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -52,4 +52,10 @@ static inline void ssleep(unsigned int seconds) msleep(seconds * 1000); } +#ifdef CONFIG_PREEMPT_RT_FULL +# define cpu_chill() msleep(1) +#else +# define cpu_chill() cpu_relax() +#endif + #endif /* defined(_LINUX_DELAY_H) */ diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 120d57a..7a16087 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -56,6 +56,9 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; + unsigned short migrate_disable; + unsigned short padding; + unsigned char preempt_lazy_count; }; #define FTRACE_MAX_EVENT \ diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index c1d6555..260deed 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -61,7 +61,11 @@ #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) -#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) +#ifndef CONFIG_PREEMPT_RT_FULL +# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) +#else +# define SOFTIRQ_DISABLE_OFFSET (0) +#endif #ifndef PREEMPT_ACTIVE #define PREEMPT_ACTIVE_BITS 1 @@ -74,10 +78,17 @@ #endif #define hardirq_count() (preempt_count() & HARDIRQ_MASK) -#define softirq_count() (preempt_count() & SOFTIRQ_MASK) #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ | NMI_MASK)) +#ifndef CONFIG_PREEMPT_RT_FULL +# define softirq_count() (preempt_count() & SOFTIRQ_MASK) +# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) +#else +# define softirq_count() (0UL) +extern int in_serving_softirq(void); +#endif + /* * Are we doing bottom half or hardware interrupt processing? * Are we in a softirq context? Interrupt context? @@ -87,7 +98,6 @@ #define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) -#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) /* * Are we in NMI context? diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 7fb31da..821d523 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -7,6 +7,7 @@ #include #include #include +#include #include @@ -85,32 +86,51 @@ static inline void __kunmap_atomic(void *addr) #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) +#ifndef CONFIG_PREEMPT_RT_FULL DECLARE_PER_CPU(int, __kmap_atomic_idx); +#endif static inline int kmap_atomic_idx_push(void) { +#ifndef CONFIG_PREEMPT_RT_FULL int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; -#ifdef CONFIG_DEBUG_HIGHMEM +# ifdef CONFIG_DEBUG_HIGHMEM WARN_ON_ONCE(in_irq() && !irqs_disabled()); BUG_ON(idx > KM_TYPE_NR); -#endif +# endif return idx; +#else + current->kmap_idx++; + BUG_ON(current->kmap_idx > KM_TYPE_NR); + return current->kmap_idx - 1; +#endif } static inline int kmap_atomic_idx(void) { +#ifndef CONFIG_PREEMPT_RT_FULL return __this_cpu_read(__kmap_atomic_idx) - 1; +#else + return current->kmap_idx - 1; +#endif } static inline void kmap_atomic_idx_pop(void) { -#ifdef CONFIG_DEBUG_HIGHMEM +#ifndef CONFIG_PREEMPT_RT_FULL +# ifdef CONFIG_DEBUG_HIGHMEM int idx = __this_cpu_dec_return(__kmap_atomic_idx); BUG_ON(idx < 0); -#else +# else __this_cpu_dec(__kmap_atomic_idx); +# endif +#else + current->kmap_idx--; +# ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(current->kmap_idx < 0); +# endif #endif } diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index d19a5c2..79a7a35 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -111,6 +111,11 @@ struct hrtimer { enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; unsigned long state; + struct list_head cb_entry; + int irqsafe; +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + ktime_t praecox; +#endif #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; @@ -147,6 +152,7 @@ struct hrtimer_clock_base { int index; clockid_t clockid; struct timerqueue_head active; + struct list_head expired; ktime_t resolution; ktime_t (*get_time)(void); ktime_t softirq_time; @@ -190,6 +196,9 @@ struct hrtimer_cpu_base { unsigned long nr_hangs; ktime_t max_hang_time; #endif +#ifdef CONFIG_PREEMPT_RT_BASE + wait_queue_head_t wait; +#endif struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; }; @@ -385,6 +394,13 @@ static inline int hrtimer_restart(struct hrtimer *timer) return hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } +/* Softirq preemption could deadlock timer removal */ +#ifdef CONFIG_PREEMPT_RT_BASE + extern void hrtimer_wait_for_timer(const struct hrtimer *timer); +#else +# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) +#endif + /* Query timers: */ extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp); diff --git a/include/linux/idr.h b/include/linux/idr.h index 871a213..267527b 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -92,10 +92,14 @@ void idr_init(struct idr *idp); * Each idr_preload() should be matched with an invocation of this * function. See idr_preload() for details. */ +#ifdef CONFIG_PREEMPT_RT_FULL +void idr_preload_end(void); +#else static inline void idr_preload_end(void) { preempt_enable(); } +#endif /** * idr_find - return pointer for given id diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 5cd0f09..766558a 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -143,9 +143,16 @@ extern struct task_group root_task_group; # define INIT_PERF_EVENTS(tsk) #endif +#ifdef CONFIG_PREEMPT_RT_BASE +# define INIT_TIMER_LIST .posix_timer_list = NULL, +#else +# define INIT_TIMER_LIST +#endif + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN # define INIT_VTIME(tsk) \ - .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ + .vtime_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.vtime_lock), \ + .vtime_seq = SEQCNT_ZERO, \ .vtime_snap = 0, \ .vtime_snap_whence = VTIME_SYS, #else @@ -207,6 +214,7 @@ extern struct task_group root_task_group; .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ .timer_slack_ns = 50000, /* 50 usec default slack */ \ + INIT_TIMER_LIST \ .pids = { \ [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \ [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5fa5afe..838d4bd 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -58,6 +58,7 @@ * IRQF_NO_THREAD - Interrupt cannot be threaded * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device * resume time. + * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) */ #define IRQF_DISABLED 0x00000020 #define IRQF_SHARED 0x00000080 @@ -71,6 +72,7 @@ #define IRQF_FORCE_RESUME 0x00008000 #define IRQF_NO_THREAD 0x00010000 #define IRQF_EARLY_RESUME 0x00020000 +#define IRQF_NO_SOFTIRQ_CALL 0x00040000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) @@ -211,7 +213,7 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); #ifdef CONFIG_LOCKDEP # define local_irq_enable_in_hardirq() do { } while (0) #else -# define local_irq_enable_in_hardirq() local_irq_enable() +# define local_irq_enable_in_hardirq() local_irq_enable_nort() #endif extern void disable_irq_nosync(unsigned int irq); @@ -261,6 +263,7 @@ struct irq_affinity_notify { unsigned int irq; struct kref kref; struct work_struct work; + struct list_head list; void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); void (*release)(struct kref *ref); }; @@ -383,9 +386,13 @@ static inline int disable_irq_wake(unsigned int irq) #ifdef CONFIG_IRQ_FORCED_THREADING -extern bool force_irqthreads; +# ifndef CONFIG_PREEMPT_RT_BASE + extern bool force_irqthreads; +# else +# define force_irqthreads (true) +# endif #else -#define force_irqthreads (0) +#define force_irqthreads (false) #endif #ifndef __ARCH_SET_SOFTIRQ_PENDING @@ -441,8 +448,14 @@ struct softirq_action void (*action)(struct softirq_action *); }; +#ifndef CONFIG_PREEMPT_RT_FULL asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); +static inline void thread_do_softirq(void) { do_softirq(); } +#else +extern void thread_do_softirq(void); +#endif + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); @@ -450,6 +463,8 @@ extern void __raise_softirq_irqoff(unsigned int nr); extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); +extern void softirq_check_pending_idle(void); + /* This is the worklist that queues up per-cpu softirq work. * * send_remote_sendirq() adds work to these lists, and @@ -490,8 +505,9 @@ extern void __send_remote_softirq(struct call_single_data *cp, int cpu, to be executed on some cpu at least once after this. * If the tasklet is already scheduled, but its execution is still not started, it will be executed only once. - * If this tasklet is already running on another CPU (or schedule is called - from tasklet itself), it is rescheduled for later. + * If this tasklet is already running on another CPU, it is rescheduled + for later. + * Schedule must not be called from the tasklet itself (a lockup occurs) * Tasklet is strictly serialized wrt itself, but not wrt another tasklets. If client needs some intertask synchronization, he makes it with spinlocks. @@ -516,27 +532,36 @@ struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data } enum { TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ - TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ + TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ + TASKLET_STATE_PENDING /* Tasklet is pending */ }; -#ifdef CONFIG_SMP +#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) +#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) +#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) + +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) static inline int tasklet_trylock(struct tasklet_struct *t) { return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); } +static inline int tasklet_tryunlock(struct tasklet_struct *t) +{ + return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN; +} + static inline void tasklet_unlock(struct tasklet_struct *t) { smp_mb__before_clear_bit(); clear_bit(TASKLET_STATE_RUN, &(t)->state); } -static inline void tasklet_unlock_wait(struct tasklet_struct *t) -{ - while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } -} +extern void tasklet_unlock_wait(struct tasklet_struct *t); + #else #define tasklet_trylock(t) 1 +#define tasklet_tryunlock(t) 1 #define tasklet_unlock_wait(t) do { } while (0) #define tasklet_unlock(t) do { } while (0) #endif @@ -585,17 +610,8 @@ static inline void tasklet_disable(struct tasklet_struct *t) smp_mb(); } -static inline void tasklet_enable(struct tasklet_struct *t) -{ - smp_mb__before_atomic_dec(); - atomic_dec(&t->count); -} - -static inline void tasklet_hi_enable(struct tasklet_struct *t) -{ - smp_mb__before_atomic_dec(); - atomic_dec(&t->count); -} +extern void tasklet_enable(struct tasklet_struct *t); +extern void tasklet_hi_enable(struct tasklet_struct *t); extern void tasklet_kill(struct tasklet_struct *t); extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); @@ -627,6 +643,12 @@ void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer) tasklet_kill(&ttimer->tasklet); } +#ifdef CONFIG_PREEMPT_RT_FULL +extern void softirq_early_init(void); +#else +static inline void softirq_early_init(void) { } +#endif + /* * Autoprobing for irqs: * diff --git a/include/linux/irq.h b/include/linux/irq.h index bc4e066..7fad94a 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -70,6 +70,7 @@ typedef void (*irq_preflow_handler_t)(struct irq_data *data); * IRQ_MOVE_PCNTXT - Interrupt can be migrated from process context * IRQ_NESTED_TRHEAD - Interrupt nests into another thread * IRQ_PER_CPU_DEVID - Dev_id is a per-cpu variable + * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) */ enum { IRQ_TYPE_NONE = 0x00000000, @@ -94,12 +95,14 @@ enum { IRQ_NESTED_THREAD = (1 << 15), IRQ_NOTHREAD = (1 << 16), IRQ_PER_CPU_DEVID = (1 << 17), + IRQ_NO_SOFTIRQ_CALL = (1 << 18), }; #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ - IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID) + IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ + IRQ_NO_SOFTIRQ_CALL) #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 623325e..a7edc47 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -52,6 +52,7 @@ struct irq_desc { unsigned int irq_count; /* For detecting broken IRQs */ unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; + u64 random_ip; raw_spinlock_t lock; struct cpumask *percpu_enabled; #ifdef CONFIG_SMP diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index d176d65..a52b35d 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -25,8 +25,6 @@ # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) # define trace_hardirq_enter() do { current->hardirq_context++; } while (0) # define trace_hardirq_exit() do { current->hardirq_context--; } while (0) -# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) -# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, #else # define trace_hardirqs_on() do { } while (0) @@ -39,9 +37,15 @@ # define trace_softirqs_enabled(p) 0 # define trace_hardirq_enter() do { } while (0) # define trace_hardirq_exit() do { } while (0) +# define INIT_TRACE_IRQFLAGS +#endif + +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) +# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) +# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) +#else # define lockdep_softirq_enter() do { } while (0) # define lockdep_softirq_exit() do { } while (0) -# define INIT_TRACE_IRQFLAGS #endif #if defined(CONFIG_IRQSOFF_TRACER) || \ @@ -147,4 +151,23 @@ #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */ +/* + * local_irq* variants depending on RT/!RT + */ +#ifdef CONFIG_PREEMPT_RT_FULL +# define local_irq_disable_nort() do { } while (0) +# define local_irq_enable_nort() do { } while (0) +# define local_irq_save_nort(flags) do { local_save_flags(flags); } while (0) +# define local_irq_restore_nort(flags) do { (void)(flags); } while (0) +# define local_irq_disable_rt() local_irq_disable() +# define local_irq_enable_rt() local_irq_enable() +#else +# define local_irq_disable_nort() local_irq_disable() +# define local_irq_enable_nort() local_irq_enable() +# define local_irq_save_nort(flags) local_irq_save(flags) +# define local_irq_restore_nort(flags) local_irq_restore(flags) +# define local_irq_disable_rt() do { } while (0) +# define local_irq_enable_rt() do { } while (0) +#endif + #endif diff --git a/include/linux/jbd_common.h b/include/linux/jbd_common.h index 6133679..0dbc151 100644 --- a/include/linux/jbd_common.h +++ b/include/linux/jbd_common.h @@ -39,32 +39,56 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh) static inline void jbd_lock_bh_state(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_lock(BH_State, &bh->b_state); +#else + spin_lock(&bh->b_state_lock); +#endif } static inline int jbd_trylock_bh_state(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE return bit_spin_trylock(BH_State, &bh->b_state); +#else + return spin_trylock(&bh->b_state_lock); +#endif } static inline int jbd_is_locked_bh_state(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE return bit_spin_is_locked(BH_State, &bh->b_state); +#else + return spin_is_locked(&bh->b_state_lock); +#endif } static inline void jbd_unlock_bh_state(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_unlock(BH_State, &bh->b_state); +#else + spin_unlock(&bh->b_state_lock); +#endif } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_lock(BH_JournalHead, &bh->b_state); +#else + spin_lock(&bh->b_journal_head_lock); +#endif } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_unlock(BH_JournalHead, &bh->b_state); +#else + spin_unlock(&bh->b_journal_head_lock); +#endif } #endif diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 0976fc4..40c876b 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -50,7 +50,8 @@ #include #include -#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) && \ + !defined(CONFIG_PREEMPT_BASE) struct static_key { atomic_t enabled; diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 7f6fe6e..680ad23 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -115,7 +115,7 @@ extern int kdb_trap_printk; extern __printf(1, 0) int vkdb_printf(const char *fmt, va_list args); extern __printf(1, 2) int kdb_printf(const char *, ...); typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); - +#define in_kdb_printk() (kdb_trap_printk) extern void kdb_init(int level); /* Access to kdb specific polling devices */ @@ -150,6 +150,7 @@ extern int kdb_register_repeat(char *, kdb_func_t, char *, char *, extern int kdb_unregister(char *); #else /* ! CONFIG_KGDB_KDB */ static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } +#define in_kdb_printk() (0) static inline void kdb_init(int level) {} static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, char *help, short minlen) { return 0; } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e9ef6d6..463f8d7 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -415,6 +415,7 @@ extern enum system_states { SYSTEM_HALT, SYSTEM_POWER_OFF, SYSTEM_RESTART, + SYSTEM_SUSPEND, } system_state; #define TAINT_PROPRIETARY_MODULE 0 diff --git a/include/linux/lglock.h b/include/linux/lglock.h index 0d24e93..d2c0d6d 100644 --- a/include/linux/lglock.h +++ b/include/linux/lglock.h @@ -42,22 +42,37 @@ #endif struct lglock { +#ifndef CONFIG_PREEMPT_RT_FULL arch_spinlock_t __percpu *lock; +#else + struct rt_mutex __percpu *lock; +#endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lock_key; struct lockdep_map lock_dep_map; #endif }; -#define DEFINE_LGLOCK(name) \ +#ifndef CONFIG_PREEMPT_RT_FULL +# define DEFINE_LGLOCK(name) \ static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ = __ARCH_SPIN_LOCK_UNLOCKED; \ struct lglock name = { .lock = &name ## _lock } -#define DEFINE_STATIC_LGLOCK(name) \ +# define DEFINE_STATIC_LGLOCK(name) \ static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ = __ARCH_SPIN_LOCK_UNLOCKED; \ static struct lglock name = { .lock = &name ## _lock } +#else + +# define DEFINE_LGLOCK(name) \ + static DEFINE_PER_CPU(struct rt_mutex, name ## _lock); \ + struct lglock name = { .lock = &name ## _lock } + +# define DEFINE_STATIC_LGLOCK(name) \ + static DEFINE_PER_CPU(struct rt_mutex, name ## _lock); \ + static struct lglock name = { .lock = &name ## _lock } +#endif void lg_lock_init(struct lglock *lg, char *name); void lg_local_lock(struct lglock *lg); diff --git a/include/linux/list.h b/include/linux/list.h index b83e565..f6a9d3a 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -373,6 +373,17 @@ static inline void list_splice_tail_init(struct list_head *list, (!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL) /** + * list_last_entry - get the last element from a list + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_struct within the struct. + * + * Note, that list is expected to be not empty. + */ +#define list_last_entry(ptr, type, member) \ + list_entry((ptr)->prev, type, member) + +/** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index 2eb8855..d8876a0 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -2,6 +2,7 @@ #define _LINUX_LIST_BL_H #include +#include #include /* @@ -32,13 +33,22 @@ struct hlist_bl_head { struct hlist_bl_node *first; +#ifdef CONFIG_PREEMPT_RT_BASE + raw_spinlock_t lock; +#endif }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; -#define INIT_HLIST_BL_HEAD(ptr) \ - ((ptr)->first = NULL) + +static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) +{ + h->first = NULL; +#ifdef CONFIG_PREEMPT_RT_BASE + raw_spin_lock_init(&h->lock); +#endif +} static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { @@ -117,12 +127,26 @@ static inline void hlist_bl_del_init(struct hlist_bl_node *n) static inline void hlist_bl_lock(struct hlist_bl_head *b) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_lock(0, (unsigned long *)b); +#else + raw_spin_lock(&b->lock); +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + __set_bit(0, (unsigned long *)b); +#endif +#endif } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { +#ifndef CONFIG_PREEMPT_RT_BASE __bit_spin_unlock(0, (unsigned long *)b); +#else +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) + __clear_bit(0, (unsigned long *)b); +#endif + raw_spin_unlock(&b->lock); +#endif } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) diff --git a/include/linux/locallock.h b/include/linux/locallock.h new file mode 100644 index 0000000..e7bd8be --- /dev/null +++ b/include/linux/locallock.h @@ -0,0 +1,254 @@ +#ifndef _LINUX_LOCALLOCK_H +#define _LINUX_LOCALLOCK_H + +#include +#include + +#ifdef CONFIG_PREEMPT_RT_BASE + +#ifdef CONFIG_DEBUG_SPINLOCK +# define LL_WARN(cond) WARN_ON(cond) +#else +# define LL_WARN(cond) do { } while (0) +#endif + +/* + * per cpu lock based substitute for local_irq_*() + */ +struct local_irq_lock { + spinlock_t lock; + struct task_struct *owner; + int nestcnt; + unsigned long flags; +}; + +#define DEFINE_LOCAL_IRQ_LOCK(lvar) \ + DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \ + .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) } + +#define DECLARE_LOCAL_IRQ_LOCK(lvar) \ + DECLARE_PER_CPU(struct local_irq_lock, lvar) + +#define local_irq_lock_init(lvar) \ + do { \ + int __cpu; \ + for_each_possible_cpu(__cpu) \ + spin_lock_init(&per_cpu(lvar, __cpu).lock); \ + } while (0) + +static inline void __local_lock(struct local_irq_lock *lv) +{ + if (lv->owner != current) { + spin_lock(&lv->lock); + LL_WARN(lv->owner); + LL_WARN(lv->nestcnt); + lv->owner = current; + } + lv->nestcnt++; +} + +#define local_lock(lvar) \ + do { __local_lock(&get_local_var(lvar)); } while (0) + +static inline int __local_trylock(struct local_irq_lock *lv) +{ + if (lv->owner != current && spin_trylock(&lv->lock)) { + LL_WARN(lv->owner); + LL_WARN(lv->nestcnt); + lv->owner = current; + lv->nestcnt = 1; + return 1; + } + return 0; +} + +#define local_trylock(lvar) \ + ({ \ + int __locked; \ + __locked = __local_trylock(&get_local_var(lvar)); \ + if (!__locked) \ + put_local_var(lvar); \ + __locked; \ + }) + +static inline void __local_unlock(struct local_irq_lock *lv) +{ + LL_WARN(lv->nestcnt == 0); + LL_WARN(lv->owner != current); + if (--lv->nestcnt) + return; + + lv->owner = NULL; + spin_unlock(&lv->lock); +} + +#define local_unlock(lvar) \ + do { \ + __local_unlock(&__get_cpu_var(lvar)); \ + put_local_var(lvar); \ + } while (0) + +static inline void __local_lock_irq(struct local_irq_lock *lv) +{ + spin_lock_irqsave(&lv->lock, lv->flags); + LL_WARN(lv->owner); + LL_WARN(lv->nestcnt); + lv->owner = current; + lv->nestcnt = 1; +} + +#define local_lock_irq(lvar) \ + do { __local_lock_irq(&get_local_var(lvar)); } while (0) + +#define local_lock_irq_on(lvar, cpu) \ + do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) + +static inline void __local_unlock_irq(struct local_irq_lock *lv) +{ + LL_WARN(!lv->nestcnt); + LL_WARN(lv->owner != current); + lv->owner = NULL; + lv->nestcnt = 0; + spin_unlock_irq(&lv->lock); +} + +#define local_unlock_irq(lvar) \ + do { \ + __local_unlock_irq(&__get_cpu_var(lvar)); \ + put_local_var(lvar); \ + } while (0) + +#define local_unlock_irq_on(lvar, cpu) \ + do { \ + __local_unlock_irq(&per_cpu(lvar, cpu)); \ + } while (0) + +static inline int __local_lock_irqsave(struct local_irq_lock *lv) +{ + if (lv->owner != current) { + __local_lock_irq(lv); + return 0; + } else { + lv->nestcnt++; + return 1; + } +} + +#define local_lock_irqsave(lvar, _flags) \ + do { \ + if (__local_lock_irqsave(&get_local_var(lvar))) \ + put_local_var(lvar); \ + _flags = __get_cpu_var(lvar).flags; \ + } while (0) + +#define local_lock_irqsave_on(lvar, _flags, cpu) \ + do { \ + __local_lock_irqsave(&per_cpu(lvar, cpu)); \ + _flags = per_cpu(lvar, cpu).flags; \ + } while (0) + +static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, + unsigned long flags) +{ + LL_WARN(!lv->nestcnt); + LL_WARN(lv->owner != current); + if (--lv->nestcnt) + return 0; + + lv->owner = NULL; + spin_unlock_irqrestore(&lv->lock, lv->flags); + return 1; +} + +#define local_unlock_irqrestore(lvar, flags) \ + do { \ + if (__local_unlock_irqrestore(&__get_cpu_var(lvar), flags)) \ + put_local_var(lvar); \ + } while (0) + +#define local_unlock_irqrestore_on(lvar, flags, cpu) \ + do { \ + __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ + } while (0) + +#define local_spin_trylock_irq(lvar, lock) \ + ({ \ + int __locked; \ + local_lock_irq(lvar); \ + __locked = spin_trylock(lock); \ + if (!__locked) \ + local_unlock_irq(lvar); \ + __locked; \ + }) + +#define local_spin_lock_irq(lvar, lock) \ + do { \ + local_lock_irq(lvar); \ + spin_lock(lock); \ + } while (0) + +#define local_spin_unlock_irq(lvar, lock) \ + do { \ + spin_unlock(lock); \ + local_unlock_irq(lvar); \ + } while (0) + +#define local_spin_lock_irqsave(lvar, lock, flags) \ + do { \ + local_lock_irqsave(lvar, flags); \ + spin_lock(lock); \ + } while (0) + +#define local_spin_unlock_irqrestore(lvar, lock, flags) \ + do { \ + spin_unlock(lock); \ + local_unlock_irqrestore(lvar, flags); \ + } while (0) + +#define get_locked_var(lvar, var) \ + (*({ \ + local_lock(lvar); \ + &__get_cpu_var(var); \ + })) + +#define put_locked_var(lvar, var) local_unlock(lvar) + +#define local_lock_cpu(lvar) \ + ({ \ + local_lock(lvar); \ + smp_processor_id(); \ + }) + +#define local_unlock_cpu(lvar) local_unlock(lvar) + +#else /* PREEMPT_RT_BASE */ + +#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar +#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar + +static inline void local_irq_lock_init(int lvar) { } + +#define local_lock(lvar) preempt_disable() +#define local_unlock(lvar) preempt_enable() +#define local_lock_irq(lvar) local_irq_disable() +#define local_unlock_irq(lvar) local_irq_enable() +#define local_lock_irqsave(lvar, flags) local_irq_save(flags) +#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) + +#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) +#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) +#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) +#define local_spin_lock_irqsave(lvar, lock, flags) \ + spin_lock_irqsave(lock, flags) +#define local_spin_unlock_irqrestore(lvar, lock, flags) \ + spin_unlock_irqrestore(lock, flags) + +#define get_locked_var(lvar, var) get_cpu_var(var) +#define put_locked_var(lvar, var) put_cpu_var(var) + +#define local_lock_cpu(lvar) get_cpu() +#define local_unlock_cpu(lvar) put_cpu() + +#endif + +#endif diff --git a/include/linux/mm.h b/include/linux/mm.h index 3bf21c3..3cf420d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1244,27 +1244,59 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a * overflow into the next struct page (as it might with DEBUG_SPINLOCK). * When freeing, reset page->mapping so free_pages_check won't complain. */ +#ifndef CONFIG_PREEMPT_RT_FULL + #define __pte_lockptr(page) &((page)->ptl) -#define pte_lock_init(_page) do { \ - spin_lock_init(__pte_lockptr(_page)); \ -} while (0) + +static inline struct page *pte_lock_init(struct page *page) +{ + spin_lock_init(__pte_lockptr(page)); + return page; +} + #define pte_lock_deinit(page) ((page)->mapping = NULL) + +#else /* !PREEMPT_RT_FULL */ + +/* + * On PREEMPT_RT_FULL the spinlock_t's are too large to embed in the + * page frame, hence it only has a pointer and we need to dynamically + * allocate the lock when we allocate PTE-pages. + * + * This is an overall win, since only a small fraction of the pages + * will be PTE pages under normal circumstances. + */ + +#define __pte_lockptr(page) ((page)->ptl) + +extern struct page *pte_lock_init(struct page *page); +extern void pte_lock_deinit(struct page *page); + +#endif /* PREEMPT_RT_FULL */ + #define pte_lockptr(mm, pmd) ({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));}) #else /* !USE_SPLIT_PTLOCKS */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ -#define pte_lock_init(page) do {} while (0) +static inline struct page *pte_lock_init(struct page *page) { return page; } #define pte_lock_deinit(page) do {} while (0) #define pte_lockptr(mm, pmd) ({(void)(pmd); &(mm)->page_table_lock;}) #endif /* USE_SPLIT_PTLOCKS */ -static inline void pgtable_page_ctor(struct page *page) +static inline struct page *__pgtable_page_ctor(struct page *page) { - pte_lock_init(page); - inc_zone_page_state(page, NR_PAGETABLE); + page = pte_lock_init(page); + if (page) + inc_zone_page_state(page, NR_PAGETABLE); + return page; } +#define pgtable_page_ctor(page) \ +do { \ + page = __pgtable_page_ctor(page); \ +} while (0) + static inline void pgtable_page_dtor(struct page *page) { pte_lock_deinit(page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 10a9a17..820a409 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -142,7 +143,11 @@ struct page { * system if PG_buddy is set. */ #if USE_SPLIT_PTLOCKS +# ifndef CONFIG_PREEMPT_RT_FULL spinlock_t ptl; +# else + spinlock_t *ptl; +# endif #endif struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */ struct page *first_page; /* Compound tail pages */ @@ -446,6 +451,9 @@ struct mm_struct { bool tlb_flush_pending; #endif struct uprobes_state uprobes_state; +#ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head delayed_drop; +#endif }; /* first nid will either be a valid NID or one of these values */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 433da8a..e7d733c 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -17,6 +17,17 @@ #include +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ + , .dep_map = { .name = #lockname } +#else +# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +#endif + +#ifdef CONFIG_PREEMPT_RT_FULL +# include +#else + /* * Simple, straightforward mutexes with strict semantics: * @@ -98,13 +109,6 @@ do { \ static inline void mutex_destroy(struct mutex *lock) {} #endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ - , .dep_map = { .name = #lockname } -#else -# define __DEP_MAP_MUTEX_INITIALIZER(lockname) -#endif - #define __MUTEX_INITIALIZER(lockname) \ { .count = ATOMIC_INIT(1) \ , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ @@ -170,6 +174,9 @@ extern int __must_check mutex_lock_killable(struct mutex *lock); */ extern int mutex_trylock(struct mutex *lock); extern void mutex_unlock(struct mutex *lock); + +#endif /* !PREEMPT_RT_FULL */ + extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); #ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX diff --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h new file mode 100644 index 0000000..c38a44b --- /dev/null +++ b/include/linux/mutex_rt.h @@ -0,0 +1,84 @@ +#ifndef __LINUX_MUTEX_RT_H +#define __LINUX_MUTEX_RT_H + +#ifndef __LINUX_MUTEX_H +#error "Please include mutex.h" +#endif + +#include + +/* FIXME: Just for __lockfunc */ +#include + +struct mutex { + struct rt_mutex lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __MUTEX_INITIALIZER(mutexname) \ + { \ + .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ + __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ + } + +#define DEFINE_MUTEX(mutexname) \ + struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) + +extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); +extern void __lockfunc _mutex_lock(struct mutex *lock); +extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); +extern int __lockfunc _mutex_lock_killable(struct mutex *lock); +extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); +extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); +extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); +extern int __lockfunc _mutex_trylock(struct mutex *lock); +extern void __lockfunc _mutex_unlock(struct mutex *lock); + +#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) +#define mutex_lock(l) _mutex_lock(l) +#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) +#define mutex_lock_killable(l) _mutex_lock_killable(l) +#define mutex_trylock(l) _mutex_trylock(l) +#define mutex_unlock(l) _mutex_unlock(l) +#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) +# define mutex_lock_interruptible_nested(l, s) \ + _mutex_lock_interruptible_nested(l, s) +# define mutex_lock_killable_nested(l, s) \ + _mutex_lock_killable_nested(l, s) + +# define mutex_lock_nest_lock(lock, nest_lock) \ +do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ +} while (0) + +#else +# define mutex_lock_nested(l, s) _mutex_lock(l) +# define mutex_lock_interruptible_nested(l, s) \ + _mutex_lock_interruptible(l) +# define mutex_lock_killable_nested(l, s) \ + _mutex_lock_killable(l) +# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) +#endif + +# define mutex_init(mutex) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(mutex)->lock); \ + __mutex_do_init((mutex), #mutex, &__key); \ +} while (0) + +# define __mutex_init(mutex, name, key) \ +do { \ + rt_mutex_init(&(mutex)->lock); \ + __mutex_do_init((mutex), name, key); \ +} while (0) + +#endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index abf7756..2f97259 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1139,7 +1139,7 @@ struct net_device { unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_assign_type; /* hw address assignment type */ unsigned char addr_len; /* hardware address length */ - unsigned char neigh_priv_len; + unsigned short neigh_priv_len; unsigned short dev_id; /* for shared network cards */ spinlock_t addr_list_lock; @@ -1601,9 +1601,6 @@ extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern rwlock_t dev_base_lock; /* Device list lock */ -extern seqcount_t devnet_rename_seq; /* Device rename seq */ - - #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_reverse(net, d) \ @@ -1817,6 +1814,7 @@ struct softnet_data { unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + struct sk_buff_head tofree_queue; }; static inline void input_queue_head_incr(struct softnet_data *sd) diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index dd49566..7d083af 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -3,6 +3,7 @@ #include +#include #include /** @@ -284,6 +285,8 @@ extern void xt_free_table_info(struct xt_table_info *info); */ DECLARE_PER_CPU(seqcount_t, xt_recseq); +DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); + /** * xt_write_recseq_begin - start of a write section * @@ -298,6 +301,9 @@ static inline unsigned int xt_write_recseq_begin(void) { unsigned int addend; + /* RT protection */ + local_lock(xt_write_lock); + /* * Low order bit of sequence is set if we already * called xt_write_recseq_begin(). @@ -328,6 +334,7 @@ static inline void xt_write_recseq_end(unsigned int addend) /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ smp_wmb(); __this_cpu_add(xt_recseq.sequence, addend); + local_unlock(xt_write_lock); } /* diff --git a/include/linux/notifier.h b/include/linux/notifier.h index d14a4c3..2e4414a 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -6,7 +6,7 @@ * * Alan Cox */ - + #ifndef _LINUX_NOTIFIER_H #define _LINUX_NOTIFIER_H #include @@ -42,9 +42,7 @@ * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. * As compensation, srcu_notifier_chain_unregister() is rather expensive. * SRCU notifier chains should be used when the chain will be called very - * often but notifier_blocks will seldom be removed. Also, SRCU notifier - * chains are slightly more difficult to use because they require special - * runtime initialization. + * often but notifier_blocks will seldom be removed. */ typedef int (*notifier_fn_t)(struct notifier_block *nb, @@ -88,7 +86,7 @@ struct srcu_notifier_head { (name)->head = NULL; \ } while (0) -/* srcu_notifier_heads must be initialized and cleaned up dynamically */ +/* srcu_notifier_heads must be cleaned up dynamically */ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define srcu_cleanup_notifier_head(name) \ cleanup_srcu_struct(&(name)->srcu); @@ -101,7 +99,13 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } -/* srcu_notifier_heads cannot be initialized statically */ + +#define SRCU_NOTIFIER_INIT(name, pcpu) \ + { \ + .mutex = __MUTEX_INITIALIZER(name.mutex), \ + .head = NULL, \ + .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ + } #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ @@ -113,6 +117,18 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); struct raw_notifier_head name = \ RAW_NOTIFIER_INIT(name) +#define _SRCU_NOTIFIER_HEAD(name, mod) \ + static DEFINE_PER_CPU(struct srcu_struct_array, \ + name##_head_srcu_array); \ + mod struct srcu_notifier_head name = \ + SRCU_NOTIFIER_INIT(name, name##_head_srcu_array) + +#define SRCU_NOTIFIER_HEAD(name) \ + _SRCU_NOTIFIER_HEAD(name, ) + +#define SRCU_NOTIFIER_HEAD_STATIC(name) \ + _SRCU_NOTIFIER_HEAD(name, static) + #ifdef __KERNEL__ extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, @@ -182,12 +198,12 @@ static inline int notifier_to_errno(int ret) /* * Declared notifiers so far. I can imagine quite a few more chains - * over time (eg laptop power reset chains, reboot chain (to clean + * over time (eg laptop power reset chains, reboot chain (to clean * device units up), device [un]mount chain, module load/unload chain, - * low memory chain, screenblank chain (for plug in modular screenblankers) + * low memory chain, screenblank chain (for plug in modular screenblankers) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ - + /* CPU notfiers are defined in include/linux/cpu.h. */ /* netdevice notifiers are defined in include/linux/netdevice.h */ diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 777a524..ca67e80 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -24,6 +24,9 @@ enum { */ struct page_cgroup { unsigned long flags; +#ifdef CONFIG_PREEMPT_RT_BASE + spinlock_t pcg_lock; +#endif struct mem_cgroup *mem_cgroup; }; @@ -74,12 +77,20 @@ static inline void lock_page_cgroup(struct page_cgroup *pc) * Don't take this lock in IRQ context. * This lock is for pc->mem_cgroup, USED, MIGRATION */ +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_lock(PCG_LOCK, &pc->flags); +#else + spin_lock(&pc->pcg_lock); +#endif } static inline void unlock_page_cgroup(struct page_cgroup *pc) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_unlock(PCG_LOCK, &pc->flags); +#else + spin_unlock(&pc->pcg_lock); +#endif } #else /* CONFIG_MEMCG */ @@ -102,6 +113,10 @@ static inline void __init page_cgroup_init_flatmem(void) { } +static inline void page_cgroup_lock_init(struct page_cgroup *pc) +{ +} + #endif /* CONFIG_MEMCG */ #include diff --git a/include/linux/percpu.h b/include/linux/percpu.h index cc88172..12b394f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -48,6 +48,31 @@ preempt_enable(); \ } while (0) +#ifndef CONFIG_PREEMPT_RT_FULL +# define get_local_var(var) get_cpu_var(var) +# define put_local_var(var) put_cpu_var(var) +# define get_local_ptr(var) get_cpu_ptr(var) +# define put_local_ptr(var) put_cpu_ptr(var) +#else +# define get_local_var(var) (*({ \ + migrate_disable(); \ + &__get_cpu_var(var); })) + +# define put_local_var(var) do { \ + (void)&(var); \ + migrate_enable(); \ +} while (0) + +# define get_local_ptr(var) ({ \ + migrate_disable(); \ + this_cpu_ptr(var); }) + +# define put_local_ptr(var) do { \ + (void)(var); \ + migrate_enable(); \ +} while (0) +#endif + /* minimum unit size, also is the maximum supported allocation size */ #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) diff --git a/include/linux/pid.h b/include/linux/pid.h index a089a3c..dffe39c 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -2,6 +2,7 @@ #define _LINUX_PID_H #include +#include enum pid_type { diff --git a/include/linux/preempt.h b/include/linux/preempt.h index f5d4723..c153cf2 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -23,15 +23,38 @@ #define preempt_count() (current_thread_info()->preempt_count) +#ifdef CONFIG_PREEMPT_LAZY +#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) +#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) +#define inc_preempt_lazy_count() add_preempt_lazy_count(1) +#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) +#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) +#else +#define add_preempt_lazy_count(val) do { } while (0) +#define sub_preempt_lazy_count(val) do { } while (0) +#define inc_preempt_lazy_count() do { } while (0) +#define dec_preempt_lazy_count() do { } while (0) +#define preempt_lazy_count() (0) +#endif + #ifdef CONFIG_PREEMPT asmlinkage void preempt_schedule(void); +# ifdef CONFIG_PREEMPT_LAZY #define preempt_check_resched() \ do { \ - if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \ + if (unlikely(test_thread_flag(TIF_NEED_RESCHED) || \ + test_thread_flag(TIF_NEED_RESCHED_LAZY))) \ preempt_schedule(); \ } while (0) +# else +#define preempt_check_resched() \ +do { \ + if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \ + preempt_schedule(); \ +} while (0) +# endif #ifdef CONFIG_CONTEXT_TRACKING @@ -64,17 +87,36 @@ do { \ barrier(); \ } while (0) +#define preempt_lazy_disable() \ +do { \ + inc_preempt_lazy_count(); \ + barrier(); \ +} while (0) + #define sched_preempt_enable_no_resched() \ do { \ barrier(); \ dec_preempt_count(); \ } while (0) -#define preempt_enable_no_resched() sched_preempt_enable_no_resched() +#ifndef CONFIG_PREEMPT_RT_BASE +# define preempt_enable_no_resched() sched_preempt_enable_no_resched() +# define preempt_check_resched_rt() barrier() +#else +# define preempt_enable_no_resched() preempt_enable() +# define preempt_check_resched_rt() preempt_check_resched() +#endif #define preempt_enable() \ do { \ - preempt_enable_no_resched(); \ + sched_preempt_enable_no_resched(); \ + barrier(); \ + preempt_check_resched(); \ +} while (0) + +#define preempt_lazy_enable() \ +do { \ + dec_preempt_lazy_count(); \ barrier(); \ preempt_check_resched(); \ } while (0) @@ -123,9 +165,31 @@ do { \ #define preempt_disable_notrace() barrier() #define preempt_enable_no_resched_notrace() barrier() #define preempt_enable_notrace() barrier() +#define preempt_check_resched_rt() barrier() #endif /* CONFIG_PREEMPT_COUNT */ +#ifdef CONFIG_PREEMPT_RT_FULL +# define preempt_disable_rt() preempt_disable() +# define preempt_enable_rt() preempt_enable() +# define preempt_disable_nort() barrier() +# define preempt_enable_nort() barrier() +# ifdef CONFIG_SMP + extern void migrate_disable(void); + extern void migrate_enable(void); +# else /* CONFIG_SMP */ +# define migrate_disable() barrier() +# define migrate_enable() barrier() +# endif /* CONFIG_SMP */ +#else +# define preempt_disable_rt() barrier() +# define preempt_enable_rt() barrier() +# define preempt_disable_nort() preempt_disable() +# define preempt_enable_nort() preempt_enable() +# define migrate_disable() preempt_disable() +# define migrate_enable() preempt_enable() +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier; diff --git a/include/linux/printk.h b/include/linux/printk.h index 22c7052..ad23974 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -101,9 +101,11 @@ int no_printk(const char *fmt, ...) extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); void early_vprintk(const char *fmt, va_list ap); +extern void printk_kill(void); #else static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } +static inline void printk_kill(void) { } #endif #ifdef CONFIG_PRINTK @@ -137,7 +139,6 @@ extern int __printk_ratelimit(const char *func); #define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); - extern int printk_delay_msec; extern int dmesg_restrict; extern int kptr_restrict; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index ffc444c..7ddfbf9 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -230,7 +230,13 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root, unsigned long index, unsigned long max_scan); unsigned long radix_tree_prev_hole(struct radix_tree_root *root, unsigned long index, unsigned long max_scan); + +#ifndef CONFIG_PREEMPT_RT_FULL int radix_tree_preload(gfp_t gfp_mask); +#else +static inline int radix_tree_preload(gfp_t gm) { return 0; } +#endif + void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag); @@ -255,7 +261,7 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item); static inline void radix_tree_preload_end(void) { - preempt_enable(); + preempt_enable_nort(); } /** diff --git a/include/linux/random.h b/include/linux/random.h index bf9085e..de4894a 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -12,7 +12,7 @@ extern void add_device_randomness(const void *, unsigned int); extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); -extern void add_interrupt_randomness(int irq, int irq_flags); +extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip); extern void get_random_bytes(void *buf, int nbytes); extern void get_random_bytes_arch(void *buf, int nbytes); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ddcc782..9b574a0 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -128,6 +128,9 @@ extern void call_rcu(struct rcu_head *head, #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_PREEMPT_RT_FULL +#define call_rcu_bh call_rcu +#else /** * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. * @head: structure to be used for queueing the RCU updates. @@ -151,6 +154,7 @@ extern void call_rcu(struct rcu_head *head, */ extern void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *head)); +#endif /** * call_rcu_sched() - Queue an RCU for invocation after sched grace period. @@ -190,6 +194,11 @@ void synchronize_rcu(void); * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() (current->rcu_read_lock_nesting) +#ifndef CONFIG_PREEMPT_RT_FULL +#define sched_rcu_preempt_depth() rcu_preempt_depth() +#else +static inline int sched_rcu_preempt_depth(void) { return 0; } +#endif #else /* #ifdef CONFIG_PREEMPT_RCU */ @@ -213,6 +222,8 @@ static inline int rcu_preempt_depth(void) return 0; } +#define sched_rcu_preempt_depth() rcu_preempt_depth() + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ @@ -367,7 +378,14 @@ static inline int rcu_read_lock_held(void) * rcu_read_lock_bh_held() is defined out of line to avoid #include-file * hell. */ +#ifdef CONFIG_PREEMPT_RT_FULL +static inline int rcu_read_lock_bh_held(void) +{ + return rcu_read_lock_held(); +} +#else extern int rcu_read_lock_bh_held(void); +#endif /** * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? @@ -824,10 +842,14 @@ static inline void rcu_read_unlock(void) static inline void rcu_read_lock_bh(void) { local_bh_disable(); +#ifdef CONFIG_PREEMPT_RT_FULL + rcu_read_lock(); +#else __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); rcu_lockdep_assert(!rcu_is_cpu_idle(), "rcu_read_lock_bh() used illegally while idle"); +#endif } /* @@ -837,10 +859,14 @@ static inline void rcu_read_lock_bh(void) */ static inline void rcu_read_unlock_bh(void) { +#ifdef CONFIG_PREEMPT_RT_FULL + rcu_read_unlock(); +#else rcu_lockdep_assert(!rcu_is_cpu_idle(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); +#endif local_bh_enable(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 952b793..f1472a2 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,7 +45,11 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(cpu); } +#ifdef CONFIG_PREEMPT_RT_FULL +# define synchronize_rcu_bh synchronize_rcu +#else extern void synchronize_rcu_bh(void); +#endif extern void synchronize_sched_expedited(void); extern void synchronize_rcu_expedited(void); @@ -73,20 +77,30 @@ static inline void synchronize_rcu_bh_expedited(void) } extern void rcu_barrier(void); +#ifdef CONFIG_PREEMPT_RT_FULL +# define rcu_barrier_bh rcu_barrier +#else extern void rcu_barrier_bh(void); +#endif extern void rcu_barrier_sched(void); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; extern long rcu_batches_completed(void); -extern long rcu_batches_completed_bh(void); extern long rcu_batches_completed_sched(void); extern void rcu_force_quiescent_state(void); -extern void rcu_bh_force_quiescent_state(void); extern void rcu_sched_force_quiescent_state(void); extern void rcu_scheduler_starting(void); extern int rcu_scheduler_active __read_mostly; +#ifndef CONFIG_PREEMPT_RT_FULL +extern void rcu_bh_force_quiescent_state(void); +extern long rcu_batches_completed_bh(void); +#else +# define rcu_bh_force_quiescent_state rcu_force_quiescent_state +# define rcu_batches_completed_bh rcu_batches_completed +#endif + #endif /* __LINUX_RCUTREE_H */ diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index de17134..5ebd0bb 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -14,7 +14,7 @@ #include #include -#include +#include extern int max_lock_depth; /* for sysctl */ @@ -29,9 +29,10 @@ struct rt_mutex { raw_spinlock_t wait_lock; struct plist_head wait_list; struct task_struct *owner; -#ifdef CONFIG_DEBUG_RT_MUTEXES int save_state; - const char *name, *file; +#ifdef CONFIG_DEBUG_RT_MUTEXES + const char *file; + const char *name; int line; void *magic; #endif @@ -56,19 +57,39 @@ struct hrtimer_sleeper; #ifdef CONFIG_DEBUG_RT_MUTEXES # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ , .name = #mutexname, .file = __FILE__, .line = __LINE__ -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__) + +# define rt_mutex_init(mutex) \ + do { \ + raw_spin_lock_init(&(mutex)->wait_lock); \ + __rt_mutex_init(mutex, #mutex); \ + } while (0) + extern void rt_mutex_debug_task_free(struct task_struct *tsk); #else # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) -# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL) + +# define rt_mutex_init(mutex) \ + do { \ + raw_spin_lock_init(&(mutex)->wait_lock); \ + __rt_mutex_init(mutex, #mutex); \ + } while (0) + # define rt_mutex_debug_task_free(t) do { } while (0) #endif -#define __RT_MUTEX_INITIALIZER(mutexname) \ - { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ +#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ , .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \ , .owner = NULL \ - __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} + __DEBUG_RT_MUTEX_INITIALIZER(mutexname) + + +#define __RT_MUTEX_INITIALIZER(mutexname) \ + { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) } + +#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ + { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ + , .save_state = 1 } #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) @@ -90,6 +111,7 @@ extern void rt_mutex_destroy(struct rt_mutex *lock); extern void rt_mutex_lock(struct rt_mutex *lock); extern int rt_mutex_lock_interruptible(struct rt_mutex *lock, int detect_deadlock); +extern int rt_mutex_lock_killable(struct rt_mutex *lock, int detect_deadlock); extern int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout, int detect_deadlock); diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h new file mode 100644 index 0000000..853ee36 --- /dev/null +++ b/include/linux/rwlock_rt.h @@ -0,0 +1,123 @@ +#ifndef __LINUX_RWLOCK_RT_H +#define __LINUX_RWLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +#define rwlock_init(rwl) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(rwl)->lock); \ + __rt_rwlock_init(rwl, #rwl, &__key); \ +} while (0) + +extern void __lockfunc rt_write_lock(rwlock_t *rwlock); +extern void __lockfunc rt_read_lock(rwlock_t *rwlock); +extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); +extern int __lockfunc rt_write_trylock_irqsave(rwlock_t *trylock, unsigned long *flags); +extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); +extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); +extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); +extern unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock); +extern unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock); +extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); + +#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) +#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) + +#define write_trylock_irqsave(lock, flags) \ + __cond_lock(lock, rt_write_trylock_irqsave(lock, &flags)) + +#define read_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + migrate_disable(); \ + flags = rt_read_lock_irqsave(lock); \ + } while (0) + +#define write_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + migrate_disable(); \ + flags = rt_write_lock_irqsave(lock); \ + } while (0) + +#define read_lock(lock) \ + do { \ + migrate_disable(); \ + rt_read_lock(lock); \ + } while (0) + +#define read_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + migrate_disable(); \ + rt_read_lock(lock); \ + } while (0) + +#define read_lock_irq(lock) read_lock(lock) + +#define write_lock(lock) \ + do { \ + migrate_disable(); \ + rt_write_lock(lock); \ + } while (0) + +#define write_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + migrate_disable(); \ + rt_write_lock(lock); \ + } while (0) + +#define write_lock_irq(lock) write_lock(lock) + +#define read_unlock(lock) \ + do { \ + rt_read_unlock(lock); \ + migrate_enable(); \ + } while (0) + +#define read_unlock_bh(lock) \ + do { \ + rt_read_unlock(lock); \ + migrate_enable(); \ + local_bh_enable(); \ + } while (0) + +#define read_unlock_irq(lock) read_unlock(lock) + +#define write_unlock(lock) \ + do { \ + rt_write_unlock(lock); \ + migrate_enable(); \ + } while (0) + +#define write_unlock_bh(lock) \ + do { \ + rt_write_unlock(lock); \ + migrate_enable(); \ + local_bh_enable(); \ + } while (0) + +#define write_unlock_irq(lock) write_unlock(lock) + +#define read_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + rt_read_unlock(lock); \ + migrate_enable(); \ + } while (0) + +#define write_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + rt_write_unlock(lock); \ + migrate_enable(); \ + } while (0) + +#endif diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h index cc0072e..d0da966 100644 --- a/include/linux/rwlock_types.h +++ b/include/linux/rwlock_types.h @@ -1,6 +1,10 @@ #ifndef __LINUX_RWLOCK_TYPES_H #define __LINUX_RWLOCK_TYPES_H +#if !defined(__LINUX_SPINLOCK_TYPES_H) +# error "Do not include directly, include spinlock_types.h" +#endif + /* * include/linux/rwlock_types.h - generic rwlock type definitions * and initializers @@ -43,6 +47,7 @@ typedef struct { RW_DEP_MAP_INIT(lockname) } #endif -#define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x) +#define DEFINE_RWLOCK(name) \ + rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) #endif /* __LINUX_RWLOCK_TYPES_H */ diff --git a/include/linux/rwlock_types_rt.h b/include/linux/rwlock_types_rt.h new file mode 100644 index 0000000..b138321 --- /dev/null +++ b/include/linux/rwlock_types_rt.h @@ -0,0 +1,33 @@ +#ifndef __LINUX_RWLOCK_TYPES_RT_H +#define __LINUX_RWLOCK_TYPES_RT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +/* + * rwlocks - rtmutex which allows single reader recursion + */ +typedef struct { + struct rt_mutex lock; + int read_depth; + unsigned int break_lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} rwlock_t; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +#else +# define RW_DEP_MAP_INIT(lockname) +#endif + +#define __RW_LOCK_UNLOCKED(name) \ + { .lock = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.lock), \ + RW_DEP_MAP_INIT(name) } + +#define DEFINE_RWLOCK(name) \ + rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) + +#endif diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 0616ffe..0ad6070 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -16,6 +16,10 @@ #include +#ifdef CONFIG_PREEMPT_RT_FULL +#include +#else /* PREEMPT_RT_FULL */ + struct rw_semaphore; #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK @@ -149,4 +153,6 @@ extern void up_read_non_owner(struct rw_semaphore *sem); # define up_read_non_owner(sem) up_read(sem) #endif +#endif /* !PREEMPT_RT_FULL */ + #endif /* _LINUX_RWSEM_H */ diff --git a/include/linux/rwsem_rt.h b/include/linux/rwsem_rt.h new file mode 100644 index 0000000..e94d945 --- /dev/null +++ b/include/linux/rwsem_rt.h @@ -0,0 +1,128 @@ +#ifndef _LINUX_RWSEM_RT_H +#define _LINUX_RWSEM_RT_H + +#ifndef _LINUX_RWSEM_H +#error "Include rwsem.h" +#endif + +/* + * RW-semaphores are a spinlock plus a reader-depth count. + * + * Note that the semantics are different from the usual + * Linux rw-sems, in PREEMPT_RT mode we do not allow + * multiple readers to hold the lock at once, we only allow + * a read-lock owner to read-lock recursively. This is + * better for latency, makes the implementation inherently + * fair and makes it simpler as well. + */ + +#include + +struct rw_semaphore { + struct rt_mutex lock; + int read_depth; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +#define __RWSEM_INITIALIZER(name) \ + { .lock = __RT_MUTEX_INITIALIZER(name.lock), \ + RW_DEP_MAP_INIT(name) } + +#define DECLARE_RWSEM(lockname) \ + struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) + +extern void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key); + +#define __rt_init_rwsem(sem, name, key) \ + do { \ + rt_mutex_init(&(sem)->lock); \ + __rt_rwsem_init((sem), (name), (key));\ + } while (0) + +#define __init_rwsem(sem, name, key) __rt_init_rwsem(sem, name, key) + +# define rt_init_rwsem(sem) \ +do { \ + static struct lock_class_key __key; \ + \ + __rt_init_rwsem((sem), #sem, &__key); \ +} while (0) + +extern void rt_down_write(struct rw_semaphore *rwsem); +extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass); +extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass); +extern void rt_down_write_nested_lock(struct rw_semaphore *rwsem, + struct lockdep_map *nest); +extern void rt_down_read(struct rw_semaphore *rwsem); +extern int rt_down_write_trylock(struct rw_semaphore *rwsem); +extern int rt_down_read_trylock(struct rw_semaphore *rwsem); +extern void rt_up_read(struct rw_semaphore *rwsem); +extern void rt_up_write(struct rw_semaphore *rwsem); +extern void rt_downgrade_write(struct rw_semaphore *rwsem); + +#define init_rwsem(sem) rt_init_rwsem(sem) +#define rwsem_is_locked(s) rt_mutex_is_locked(&(s)->lock) + +static inline void down_read(struct rw_semaphore *sem) +{ + rt_down_read(sem); +} + +static inline int down_read_trylock(struct rw_semaphore *sem) +{ + return rt_down_read_trylock(sem); +} + +static inline void down_write(struct rw_semaphore *sem) +{ + rt_down_write(sem); +} + +static inline int down_write_trylock(struct rw_semaphore *sem) +{ + return rt_down_write_trylock(sem); +} + +static inline void up_read(struct rw_semaphore *sem) +{ + rt_up_read(sem); +} + +static inline void up_write(struct rw_semaphore *sem) +{ + rt_up_write(sem); +} + +static inline void downgrade_write(struct rw_semaphore *sem) +{ + rt_downgrade_write(sem); +} + +static inline void down_read_nested(struct rw_semaphore *sem, int subclass) +{ + return rt_down_read_nested(sem, subclass); +} + +static inline void down_write_nested(struct rw_semaphore *sem, int subclass) +{ + rt_down_write_nested(sem, subclass); +} +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static inline void down_write_nest_lock(struct rw_semaphore *sem, + struct rw_semaphore *nest_lock) +{ + rt_down_write_nested_lock(sem, &nest_lock->dep_map); +} + +#else + +static inline void down_write_nest_lock(struct rw_semaphore *sem, + struct rw_semaphore *nest_lock) +{ + rt_down_write_nested_lock(sem, NULL); +} +#endif +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 597c8ab..ecb2f9b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -23,6 +23,7 @@ struct sched_param { #include #include +#include #include #include #include @@ -52,6 +53,7 @@ struct sched_param { #include #include #include +#include #include @@ -1037,6 +1039,7 @@ enum perf_event_task_context { struct task_struct { volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ + volatile long saved_state; /* saved state for "spinlock sleepers" */ void *stack; atomic_t usage; unsigned int flags; /* per process flags, defined below */ @@ -1076,6 +1079,12 @@ struct task_struct { #endif unsigned int policy; +#ifdef CONFIG_PREEMPT_RT_FULL + int migrate_disable; +# ifdef CONFIG_SCHED_DEBUG + int migrate_disable_atomic; +# endif +#endif int nr_cpus_allowed; cpumask_t cpus_allowed; @@ -1171,7 +1180,8 @@ struct task_struct { struct cputime prev_cputime; #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_t vtime_seqlock; + raw_spinlock_t vtime_lock; + seqcount_t vtime_seq; unsigned long long vtime_snap; enum { VTIME_SLEEPING = 0, @@ -1187,6 +1197,9 @@ struct task_struct { struct task_cputime cputime_expires; struct list_head cpu_timers[3]; +#ifdef CONFIG_PREEMPT_RT_BASE + struct task_struct *posix_timer_list; +#endif /* process credentials */ const struct cred __rcu *real_cred; /* objective and real subjective task @@ -1218,10 +1231,15 @@ struct task_struct { /* signal handlers */ struct signal_struct *signal; struct sighand_struct *sighand; + struct sigqueue *sigqueue_cache; sigset_t blocked, real_blocked; sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */ struct sigpending pending; +#ifdef CONFIG_PREEMPT_RT_FULL + /* TODO: move me into ->restart_block ? */ + struct siginfo forced_info; +#endif unsigned long sas_ss_sp; size_t sas_ss_size; @@ -1258,6 +1276,9 @@ struct task_struct { /* mutex deadlock detection */ struct mutex_waiter *blocked_on; #endif +#ifdef CONFIG_PREEMPT_RT_FULL + int pagefault_disabled; +#endif #ifdef CONFIG_TRACE_IRQFLAGS unsigned int irq_events; unsigned long hardirq_enable_ip; @@ -1333,6 +1354,9 @@ struct task_struct { struct mutex perf_event_mutex; struct list_head perf_event_list; #endif +#ifdef CONFIG_DEBUG_PREEMPT + unsigned long preempt_disable_ip; +#endif #ifdef CONFIG_NUMA struct mempolicy *mempolicy; /* Protected by alloc_lock */ short il_next; @@ -1400,6 +1424,12 @@ struct task_struct { unsigned long trace; /* bitmask and counter of trace recursion */ unsigned long trace_recursion; +#ifdef CONFIG_WAKEUP_LATENCY_HIST + u64 preempt_timestamp_hist; +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + long timer_offset; +#endif +#endif #endif /* CONFIG_TRACING */ #ifdef CONFIG_MEMCG /* memcg uses this to do batch job */ struct memcg_batch_info { @@ -1420,11 +1450,19 @@ struct task_struct { unsigned int sequential_io; unsigned int sequential_io_avg; #endif +#ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head put_rcu; + int softirq_nestcnt; + unsigned int softirqs_raised; +#endif +#ifdef CONFIG_PREEMPT_RT_FULL +# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32 + int kmap_idx; + pte_t kmap_pte[KM_TYPE_NR]; +# endif +#endif }; -/* Future-safe accessor for struct task_struct's cpus_allowed. */ -#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) - #ifdef CONFIG_NUMA_BALANCING extern void task_numa_fault(int node, int pages, bool migrated); extern void set_numabalancing_state(bool enabled); @@ -1437,6 +1475,17 @@ static inline void set_numabalancing_state(bool enabled) } #endif +#ifdef CONFIG_PREEMPT_RT_FULL +static inline bool cur_pf_disabled(void) { return current->pagefault_disabled; } +#else +static inline bool cur_pf_disabled(void) { return false; } +#endif + +static inline bool pagefault_disabled(void) +{ + return in_atomic() || cur_pf_disabled(); +} + static inline struct pid *task_pid(struct task_struct *task) { return task->pids[PIDTYPE_PID].pid; @@ -1568,6 +1617,15 @@ extern struct pid *cad_pid; extern void free_task(struct task_struct *tsk); #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) +#ifdef CONFIG_PREEMPT_RT_BASE +extern void __put_task_struct_cb(struct rcu_head *rhp); + +static inline void put_task_struct(struct task_struct *t) +{ + if (atomic_dec_and_test(&t->usage)) + call_rcu(&t->put_rcu, __put_task_struct_cb); +} +#else extern void __put_task_struct(struct task_struct *t); static inline void put_task_struct(struct task_struct *t) @@ -1575,6 +1633,7 @@ static inline void put_task_struct(struct task_struct *t) if (atomic_dec_and_test(&t->usage)) __put_task_struct(t); } +#endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void task_cputime(struct task_struct *t, @@ -1613,6 +1672,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, /* * Per process flags */ +#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ @@ -1757,6 +1817,10 @@ extern void do_set_cpus_allowed(struct task_struct *p, extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); +int migrate_me(void); +void tell_sched_cpu_down_begin(int cpu); +void tell_sched_cpu_down_done(int cpu); + #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) @@ -1769,6 +1833,9 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, return -EINVAL; return 0; } +static inline int migrate_me(void) { return 0; } +static inline void tell_sched_cpu_down_begin(int cpu) { } +static inline void tell_sched_cpu_down_done(int cpu) { } #endif #ifdef CONFIG_NO_HZ_COMMON @@ -1976,6 +2043,7 @@ extern void xtime_update(unsigned long ticks); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); +extern int wake_up_lock_sleeper(struct task_struct * tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); @@ -2090,12 +2158,24 @@ extern struct mm_struct * mm_alloc(void); /* mmdrop drops the mm and the page tables */ extern void __mmdrop(struct mm_struct *); + static inline void mmdrop(struct mm_struct * mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } +#ifdef CONFIG_PREEMPT_RT_BASE +extern void __mmdrop_delayed(struct rcu_head *rhp); +static inline void mmdrop_delayed(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_count)) + call_rcu(&mm->delayed_drop, __mmdrop_delayed); +} +#else +# define mmdrop_delayed(mm) mmdrop(mm) +#endif + /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); /* Grab a reference to a task's mm, if it is not already going away */ @@ -2378,6 +2458,52 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } +#ifdef CONFIG_PREEMPT_LAZY +static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) +{ + set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); +} + +static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) +{ + clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); +} + +static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) +{ + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); +} + +static inline int need_resched_lazy(void) +{ + return test_thread_flag(TIF_NEED_RESCHED_LAZY); +} + +static inline int need_resched_now(void) +{ + return test_thread_flag(TIF_NEED_RESCHED); +} + +static inline int need_resched(void) +{ + return test_thread_flag(TIF_NEED_RESCHED) || + test_thread_flag(TIF_NEED_RESCHED_LAZY); +} +#else +static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } +static inline int need_resched_lazy(void) { return 0; } + +static inline int need_resched_now(void) +{ + return test_thread_flag(TIF_NEED_RESCHED); +} + +static inline int need_resched(void) +{ + return test_thread_flag(TIF_NEED_RESCHED); +} +#endif + static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); @@ -2409,11 +2535,6 @@ static inline int signal_pending_state(long state, struct task_struct *p) return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } -static inline int need_resched(void) -{ - return unlikely(test_thread_flag(TIF_NEED_RESCHED)); -} - /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return @@ -2430,7 +2551,7 @@ extern int _cond_resched(void); extern int __cond_resched_lock(spinlock_t *lock); -#ifdef CONFIG_PREEMPT_COUNT +#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL) #define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET #else #define PREEMPT_LOCK_OFFSET 0 @@ -2441,12 +2562,16 @@ extern int __cond_resched_lock(spinlock_t *lock); __cond_resched_lock(lock); \ }) +#ifndef CONFIG_PREEMPT_RT_FULL extern int __cond_resched_softirq(void); #define cond_resched_softirq() ({ \ __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ __cond_resched_softirq(); \ }) +#else +# define cond_resched_softirq() cond_resched() +#endif /* * Does a critical section need to be broken due to another @@ -2623,6 +2748,26 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +static inline int __migrate_disabled(struct task_struct *p) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + return p->migrate_disable; +#else + return 0; +#endif +} + +/* Future-safe accessor for struct task_struct's cpus_allowed. */ +static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + if (p->migrate_disable) + return cpumask_of(task_cpu(p)); +#endif + + return &p->cpus_allowed; +} + extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 440434d..4d54d6c 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -35,6 +35,7 @@ static inline int rt_task(struct task_struct *p) #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); +extern int rt_mutex_check_prio(struct task_struct *task, int newprio); extern void rt_mutex_adjust_pi(struct task_struct *p); static inline bool tsk_is_pi_blocked(struct task_struct *tsk) { @@ -45,6 +46,10 @@ static inline int rt_mutex_getprio(struct task_struct *p) { return p->normal_prio; } +static inline int rt_mutex_check_prio(struct task_struct *task, int newprio) +{ + return 0; +} # define rt_mutex_adjust_pi(p) do { } while (0) static inline bool tsk_is_pi_blocked(struct task_struct *tsk) { diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 1829905..939ea1a 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -146,18 +146,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) * Sequence counter only version assumes that callers are using their * own mutexing. */ -static inline void write_seqcount_begin(seqcount_t *s) +static inline void __write_seqcount_begin(seqcount_t *s) { s->sequence++; smp_wmb(); } -static inline void write_seqcount_end(seqcount_t *s) +static inline void write_seqcount_begin(seqcount_t *s) +{ + preempt_disable_rt(); + __write_seqcount_begin(s); +} + +static inline void __write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; } +static inline void write_seqcount_end(seqcount_t *s) +{ + __write_seqcount_end(s); + preempt_enable_rt(); +} + /** * write_seqcount_barrier - invalidate in-progress read-side seq operations * @s: pointer to seqcount_t @@ -198,10 +210,33 @@ typedef struct { /* * Read side functions for starting and finalizing a read side section. */ +#ifndef CONFIG_PREEMPT_RT_FULL static inline unsigned read_seqbegin(const seqlock_t *sl) { return read_seqcount_begin(&sl->seqcount); } +#else +/* + * Starvation safe read side for RT + */ +static inline unsigned read_seqbegin(seqlock_t *sl) +{ + unsigned ret; + +repeat: + ret = ACCESS_ONCE(sl->seqcount.sequence); + if (unlikely(ret & 1)) { + /* + * Take the lock and let the writer proceed (i.e. evtl + * boost it), otherwise we could loop here forever. + */ + spin_lock(&sl->lock); + spin_unlock(&sl->lock); + goto repeat; + } + return ret; +} +#endif static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { @@ -216,36 +251,36 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __write_seqcount_begin(&sl->seqcount); } static inline void write_sequnlock(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __write_seqcount_end(&sl->seqcount); spin_unlock(&sl->lock); } static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __write_seqcount_begin(&sl->seqcount); } static inline void write_sequnlock_bh(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __write_seqcount_end(&sl->seqcount); spin_unlock_bh(&sl->lock); } static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); - write_seqcount_begin(&sl->seqcount); + __write_seqcount_begin(&sl->seqcount); } static inline void write_sequnlock_irq(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __write_seqcount_end(&sl->seqcount); spin_unlock_irq(&sl->lock); } @@ -254,7 +289,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) unsigned long flags; spin_lock_irqsave(&sl->lock, flags); - write_seqcount_begin(&sl->seqcount); + __write_seqcount_begin(&sl->seqcount); return flags; } @@ -264,7 +299,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { - write_seqcount_end(&sl->seqcount); + __write_seqcount_end(&sl->seqcount); spin_unlock_irqrestore(&sl->lock, flags); } diff --git a/include/linux/signal.h b/include/linux/signal.h index 2ac423b..1414eb2 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -226,6 +226,7 @@ static inline void init_sigpending(struct sigpending *sig) } extern void flush_sigqueue(struct sigpending *queue); +extern void flush_task_sigqueue(struct task_struct *tsk); /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ static inline int valid_signal(unsigned long sig) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ded45ec..08d639b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -133,6 +133,7 @@ struct sk_buff_head { __u32 qlen; spinlock_t lock; + raw_spinlock_t raw_lock; }; struct sk_buff; @@ -1065,6 +1066,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list) __skb_queue_head_init(list); } +static inline void skb_queue_head_init_raw(struct sk_buff_head *list) +{ + raw_spin_lock_init(&list->raw_lock); + __skb_queue_head_init(list); +} + static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { diff --git a/include/linux/smp.h b/include/linux/smp.h index c848876..5a57c1d 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -223,6 +223,9 @@ static inline void kick_all_cpus_sync(void) { } #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) #define put_cpu() preempt_enable() +#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); }) +#define put_cpu_light() migrate_enable() + /* * Callback to arch code if there's nosmp or maxcpus=0 on the * boot command line: diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 75f3494..a124f92 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -262,7 +262,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) #define raw_spin_can_lock(lock) (!raw_spin_is_locked(lock)) /* Include rwlock functions */ -#include +#ifdef CONFIG_PREEMPT_RT_FULL +# include +#else +# include +#endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: @@ -273,6 +277,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # include #endif +#ifdef CONFIG_PREEMPT_RT_FULL +# include +#else /* PREEMPT_RT_FULL */ + /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ @@ -402,4 +410,6 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) +#endif /* !PREEMPT_RT_FULL */ + #endif /* __LINUX_SPINLOCK_H */ diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 51df117..3f68f50 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -191,6 +191,8 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock) return 0; } -#include +#ifndef CONFIG_PREEMPT_RT_FULL +# include +#endif #endif /* __LINUX_SPINLOCK_API_SMP_H */ diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h new file mode 100644 index 0000000..b3c504b --- /dev/null +++ b/include/linux/spinlock_rt.h @@ -0,0 +1,169 @@ +#ifndef __LINUX_SPINLOCK_RT_H +#define __LINUX_SPINLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +#include + +extern void +__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key); + +#define spin_lock_init(slock) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(slock)->lock); \ + __rt_spin_lock_init(slock, #slock, &__key); \ +} while (0) + +extern void __lockfunc rt_spin_lock(spinlock_t *lock); +extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); +extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); +extern void __lockfunc rt_spin_unlock(spinlock_t *lock); +extern void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock); +extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); +extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); +extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); +extern int __lockfunc rt_spin_trylock(spinlock_t *lock); +extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); + +/* + * lockdep-less calls, for derived types like rwlock: + * (for trylock they can use rt_mutex_trylock() directly. + */ +extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); +extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); + +#define spin_lock_local(lock) rt_spin_lock(lock) +#define spin_unlock_local(lock) rt_spin_unlock(lock) + +#define spin_lock(lock) \ + do { \ + migrate_disable(); \ + rt_spin_lock(lock); \ + } while (0) + +#define spin_lock_bh(lock) \ + do { \ + local_bh_disable(); \ + migrate_disable(); \ + rt_spin_lock(lock); \ + } while (0) + +#define spin_lock_irq(lock) spin_lock(lock) + +#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) + +#define spin_trylock(lock) \ +({ \ + int __locked; \ + migrate_disable(); \ + __locked = spin_do_trylock(lock); \ + if (!__locked) \ + migrate_enable(); \ + __locked; \ +}) + +#ifdef CONFIG_LOCKDEP +# define spin_lock_nested(lock, subclass) \ + do { \ + migrate_disable(); \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) + +# define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + migrate_disable(); \ + rt_spin_lock_nested(lock, subclass); \ + } while (0) +#else +# define spin_lock_nested(lock, subclass) spin_lock(lock) + +# define spin_lock_irqsave_nested(lock, flags, subclass) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) +#endif + +#define spin_lock_irqsave(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = 0; \ + spin_lock(lock); \ + } while (0) + +static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) +{ + unsigned long flags = 0; +#ifdef CONFIG_TRACE_IRQFLAGS + flags = rt_spin_lock_trace_flags(lock); +#else + spin_lock(lock); /* lock_local */ +#endif + return flags; +} + +/* FIXME: we need rt_spin_lock_nest_lock */ +#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) + +#define spin_unlock(lock) \ + do { \ + rt_spin_unlock(lock); \ + migrate_enable(); \ + } while (0) + +#define spin_unlock_bh(lock) \ + do { \ + rt_spin_unlock(lock); \ + migrate_enable(); \ + local_bh_enable(); \ + } while (0) + +#define spin_unlock_irq(lock) spin_unlock(lock) + +#define spin_unlock_irqrestore(lock, flags) \ + do { \ + typecheck(unsigned long, flags); \ + (void) flags; \ + spin_unlock(lock); \ + } while (0) + +#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) +#define spin_trylock_irq(lock) spin_trylock(lock) + +#define spin_trylock_irqsave(lock, flags) \ + rt_spin_trylock_irqsave(lock, &(flags)) + +#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) + +#ifdef CONFIG_GENERIC_LOCKBREAK +# define spin_is_contended(lock) ((lock)->break_lock) +#else +# define spin_is_contended(lock) (((void)(lock), 0)) +#endif + +static inline int spin_can_lock(spinlock_t *lock) +{ + return !rt_mutex_is_locked(&lock->lock); +} + +static inline int spin_is_locked(spinlock_t *lock) +{ + return rt_mutex_is_locked(&lock->lock); +} + +static inline void assert_spin_locked(spinlock_t *lock) +{ + BUG_ON(!spin_is_locked(lock)); +} + +#define atomic_dec_and_lock(atomic, lock) \ + atomic_dec_and_spin_lock(atomic, lock) + +#endif diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index 73548eb..10bac71 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -9,80 +9,15 @@ * Released under the General Public License (GPL). */ -#if defined(CONFIG_SMP) -# include -#else -# include -#endif - -#include - -typedef struct raw_spinlock { - arch_spinlock_t raw_lock; -#ifdef CONFIG_GENERIC_LOCKBREAK - unsigned int break_lock; -#endif -#ifdef CONFIG_DEBUG_SPINLOCK - unsigned int magic, owner_cpu; - void *owner; -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -} raw_spinlock_t; - -#define SPINLOCK_MAGIC 0xdead4ead - -#define SPINLOCK_OWNER_INIT ((void *)-1L) - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } -#else -# define SPIN_DEP_MAP_INIT(lockname) -#endif +#include -#ifdef CONFIG_DEBUG_SPINLOCK -# define SPIN_DEBUG_INIT(lockname) \ - .magic = SPINLOCK_MAGIC, \ - .owner_cpu = -1, \ - .owner = SPINLOCK_OWNER_INIT, +#ifndef CONFIG_PREEMPT_RT_FULL +# include +# include #else -# define SPIN_DEBUG_INIT(lockname) +# include +# include +# include #endif -#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ - { \ - .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ - SPIN_DEBUG_INIT(lockname) \ - SPIN_DEP_MAP_INIT(lockname) } - -#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ - (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) - -#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) - -typedef struct spinlock { - union { - struct raw_spinlock rlock; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) - struct { - u8 __padding[LOCK_PADSIZE]; - struct lockdep_map dep_map; - }; -#endif - }; -} spinlock_t; - -#define __SPIN_LOCK_INITIALIZER(lockname) \ - { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } - -#define __SPIN_LOCK_UNLOCKED(lockname) \ - (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) - -#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) - -#include - #endif /* __LINUX_SPINLOCK_TYPES_H */ diff --git a/include/linux/spinlock_types_nort.h b/include/linux/spinlock_types_nort.h new file mode 100644 index 0000000..f1dac1f --- /dev/null +++ b/include/linux/spinlock_types_nort.h @@ -0,0 +1,33 @@ +#ifndef __LINUX_SPINLOCK_TYPES_NORT_H +#define __LINUX_SPINLOCK_TYPES_NORT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +/* + * The non RT version maps spinlocks to raw_spinlocks + */ +typedef struct spinlock { + union { + struct raw_spinlock rlock; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) + struct { + u8 __padding[LOCK_PADSIZE]; + struct lockdep_map dep_map; + }; +#endif + }; +} spinlock_t; + +#define __SPIN_LOCK_INITIALIZER(lockname) \ + { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } + +#define __SPIN_LOCK_UNLOCKED(lockname) \ + (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) + +#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) + +#endif diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h new file mode 100644 index 0000000..edffc4d --- /dev/null +++ b/include/linux/spinlock_types_raw.h @@ -0,0 +1,56 @@ +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H +#define __LINUX_SPINLOCK_TYPES_RAW_H + +#if defined(CONFIG_SMP) +# include +#else +# include +#endif + +#include + +typedef struct raw_spinlock { + arch_spinlock_t raw_lock; +#ifdef CONFIG_GENERIC_LOCKBREAK + unsigned int break_lock; +#endif +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned int magic, owner_cpu; + void *owner; +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} raw_spinlock_t; + +#define SPINLOCK_MAGIC 0xdead4ead + +#define SPINLOCK_OWNER_INIT ((void *)-1L) + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +#else +# define SPIN_DEP_MAP_INIT(lockname) +#endif + +#ifdef CONFIG_DEBUG_SPINLOCK +# define SPIN_DEBUG_INIT(lockname) \ + .magic = SPINLOCK_MAGIC, \ + .owner_cpu = -1, \ + .owner = SPINLOCK_OWNER_INIT, +#else +# define SPIN_DEBUG_INIT(lockname) +#endif + +#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ + { \ + .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ + SPIN_DEBUG_INIT(lockname) \ + SPIN_DEP_MAP_INIT(lockname) } + +#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ + (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) + +#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) + +#endif diff --git a/include/linux/spinlock_types_rt.h b/include/linux/spinlock_types_rt.h new file mode 100644 index 0000000..9fd4319 --- /dev/null +++ b/include/linux/spinlock_types_rt.h @@ -0,0 +1,51 @@ +#ifndef __LINUX_SPINLOCK_TYPES_RT_H +#define __LINUX_SPINLOCK_TYPES_RT_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +#error "Do not include directly. Include spinlock_types.h instead" +#endif + +#include + +/* + * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: + */ +typedef struct spinlock { + struct rt_mutex lock; + unsigned int break_lock; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +} spinlock_t; + +#ifdef CONFIG_DEBUG_RT_MUTEXES +# define __RT_SPIN_INITIALIZER(name) \ + { \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ + .save_state = 1, \ + .file = __FILE__, \ + .line = __LINE__ , \ + } +#else +# define __RT_SPIN_INITIALIZER(name) \ + { \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ + .save_state = 1, \ + } +#endif + +/* +.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) +*/ + +#define __SPIN_LOCK_UNLOCKED(name) \ + { .lock = __RT_SPIN_INITIALIZER(name.lock), \ + SPIN_DEP_MAP_INIT(name) } + +#define __DEFINE_SPINLOCK(name) \ + spinlock_t name = __SPIN_LOCK_UNLOCKED(name) + +#define DEFINE_SPINLOCK(name) \ + spinlock_t name __cacheline_aligned_in_smp = __SPIN_LOCK_UNLOCKED(name) + +#endif diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 04f4121..60347e5 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -84,10 +84,10 @@ int init_srcu_struct(struct srcu_struct *sp); void process_srcu(struct work_struct *work); -#define __SRCU_STRUCT_INIT(name) \ +#define __SRCU_STRUCT_INIT(name, pcpu_name) \ { \ .completed = -300, \ - .per_cpu_ref = &name##_srcu_array, \ + .per_cpu_ref = &pcpu_name, \ .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \ .running = false, \ .batch_queue = RCU_BATCH_INIT(name.batch_queue), \ @@ -104,11 +104,11 @@ void process_srcu(struct work_struct *work); */ #define DEFINE_SRCU(name) \ static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - struct srcu_struct name = __SRCU_STRUCT_INIT(name); + struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array); #define DEFINE_STATIC_SRCU(name) \ static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name); + static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array); /** * call_srcu() - Queue a callback for invocation after an SRCU grace period diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 14a8ff2..b15655f 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -25,6 +25,7 @@ #include #include #include +#include #include /* For the /proc/sys support */ diff --git a/include/linux/timer.h b/include/linux/timer.h index 8c5a197..5fcd72c 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -241,7 +241,7 @@ extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) extern int del_timer_sync(struct timer_list *timer); #else # define del_timer_sync(t) del_timer(t) diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 5ca0951..44b3751 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -6,38 +6,37 @@ /* * These routines enable/disable the pagefault handler in that - * it will not take any locks and go straight to the fixup table. - * - * They have great resemblance to the preempt_disable/enable calls - * and in fact they are identical; this is because currently there is - * no other way to make the pagefault handlers do this. So we do - * disable preemption but we don't necessarily care about that. + * it will not take any MM locks and go straight to the fixup table. */ -static inline void pagefault_disable(void) +static inline void raw_pagefault_disable(void) { inc_preempt_count(); - /* - * make sure to have issued the store before a pagefault - * can hit. - */ barrier(); } -static inline void pagefault_enable(void) +static inline void raw_pagefault_enable(void) { - /* - * make sure to issue those last loads/stores before enabling - * the pagefault handler again. - */ barrier(); dec_preempt_count(); - /* - * make sure we do.. - */ barrier(); preempt_check_resched(); } +#ifndef CONFIG_PREEMPT_RT_FULL +static inline void pagefault_disable(void) +{ + raw_pagefault_disable(); +} + +static inline void pagefault_enable(void) +{ + raw_pagefault_enable(); +} +#else +extern void pagefault_disable(void); +extern void pagefault_enable(void); +#endif + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline unsigned long __copy_from_user_inatomic_nocache(void *to, @@ -77,9 +76,9 @@ static inline unsigned long __copy_from_user_nocache(void *to, mm_segment_t old_fs = get_fs(); \ \ set_fs(KERNEL_DS); \ - pagefault_disable(); \ + raw_pagefault_disable(); \ ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval)); \ - pagefault_enable(); \ + raw_pagefault_enable(); \ set_fs(old_fs); \ ret; \ }) diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 06f28be..d115f62 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -26,6 +26,7 @@ #include #include +#include struct vm_area_struct; struct mm_struct; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9044769..5c53265 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -29,7 +29,9 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states); static inline void __count_vm_event(enum vm_event_item item) { + preempt_disable_rt(); __this_cpu_inc(vm_event_states.event[item]); + preempt_enable_rt(); } static inline void count_vm_event(enum vm_event_item item) @@ -39,7 +41,9 @@ static inline void count_vm_event(enum vm_event_item item) static inline void __count_vm_events(enum vm_event_item item, long delta) { + preempt_disable_rt(); __this_cpu_add(vm_event_states.event[item], delta); + preempt_enable_rt(); } static inline void count_vm_events(enum vm_event_item item, long delta) diff --git a/include/linux/wait-simple.h b/include/linux/wait-simple.h new file mode 100644 index 0000000..f86bca2 --- /dev/null +++ b/include/linux/wait-simple.h @@ -0,0 +1,207 @@ +#ifndef _LINUX_WAIT_SIMPLE_H +#define _LINUX_WAIT_SIMPLE_H + +#include +#include + +#include + +struct swaiter { + struct task_struct *task; + struct list_head node; +}; + +#define DEFINE_SWAITER(name) \ + struct swaiter name = { \ + .task = current, \ + .node = LIST_HEAD_INIT((name).node), \ + } + +struct swait_head { + raw_spinlock_t lock; + struct list_head list; +}; + +#define SWAIT_HEAD_INITIALIZER(name) { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .list = LIST_HEAD_INIT((name).list), \ + } + +#define DEFINE_SWAIT_HEAD(name) \ + struct swait_head name = SWAIT_HEAD_INITIALIZER(name) + +extern void __init_swait_head(struct swait_head *h, struct lock_class_key *key); + +#define init_swait_head(swh) \ + do { \ + static struct lock_class_key __key; \ + \ + __init_swait_head((swh), &__key); \ + } while (0) + +/* + * Waiter functions + */ +extern void swait_prepare_locked(struct swait_head *head, struct swaiter *w); +extern void swait_prepare(struct swait_head *head, struct swaiter *w, int state); +extern void swait_finish_locked(struct swait_head *head, struct swaiter *w); +extern void swait_finish(struct swait_head *head, struct swaiter *w); + +/* Check whether a head has waiters enqueued */ +static inline bool swaitqueue_active(struct swait_head *h) +{ + /* Make sure the condition is visible before checking list_empty() */ + smp_mb(); + return !list_empty(&h->list); +} + +/* + * Wakeup functions + */ +extern unsigned int __swait_wake(struct swait_head *head, unsigned int state, unsigned int num); +extern unsigned int __swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num); + +#define swait_wake(head) __swait_wake(head, TASK_NORMAL, 1) +#define swait_wake_interruptible(head) __swait_wake(head, TASK_INTERRUPTIBLE, 1) +#define swait_wake_all(head) __swait_wake(head, TASK_NORMAL, 0) +#define swait_wake_all_interruptible(head) __swait_wake(head, TASK_INTERRUPTIBLE, 0) + +/* + * Event API + */ +#define __swait_event(wq, condition) \ +do { \ + DEFINE_SWAITER(__wait); \ + \ + for (;;) { \ + swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ + if (condition) \ + break; \ + schedule(); \ + } \ + swait_finish(&wq, &__wait); \ +} while (0) + +/** + * swait_event - sleep until a condition gets true + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + */ +#define swait_event(wq, condition) \ +do { \ + if (condition) \ + break; \ + __swait_event(wq, condition); \ +} while (0) + +#define __swait_event_interruptible(wq, condition, ret) \ +do { \ + DEFINE_SWAITER(__wait); \ + \ + for (;;) { \ + swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (signal_pending(current)) { \ + ret = -ERESTARTSYS; \ + break; \ + } \ + schedule(); \ + } \ + swait_finish(&wq, &__wait); \ +} while (0) + +#define __swait_event_interruptible_timeout(wq, condition, ret) \ +do { \ + DEFINE_SWAITER(__wait); \ + \ + for (;;) { \ + swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (signal_pending(current)) { \ + ret = -ERESTARTSYS; \ + break; \ + } \ + ret = schedule_timeout(ret); \ + if (!ret) \ + break; \ + } \ + swait_finish(&wq, &__wait); \ +} while (0) + +/** + * swait_event_interruptible - sleep until a condition gets true + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + */ +#define swait_event_interruptible(wq, condition) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __swait_event_interruptible(wq, condition, __ret); \ + __ret; \ +}) + +#define swait_event_interruptible_timeout(wq, condition, timeout) \ +({ \ + int __ret = timeout; \ + if (!(condition)) \ + __swait_event_interruptible_timeout(wq, condition, __ret); \ + __ret; \ +}) + +#define __swait_event_timeout(wq, condition, ret) \ +do { \ + DEFINE_SWAITER(__wait); \ + \ + for (;;) { \ + swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE); \ + if (condition) \ + break; \ + ret = schedule_timeout(ret); \ + if (!ret) \ + break; \ + } \ + swait_finish(&wq, &__wait); \ +} while (0) + +/** + * swait_event_timeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true. The @condition is checked each time + * the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if the @timeout elapsed, and the remaining + * jiffies if the condition evaluated to true before the timeout elapsed. + */ +#define swait_event_timeout(wq, condition, timeout) \ +({ \ + long __ret = timeout; \ + if (!(condition)) \ + __swait_event_timeout(wq, condition, __ret); \ + __ret; \ +}) + +#endif diff --git a/include/net/dst.h b/include/net/dst.h index e0c97f5..bbab941 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -393,7 +393,7 @@ static inline void dst_confirm(struct dst_entry *dst) static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n, struct sk_buff *skb) { - const struct hh_cache *hh; + struct hh_cache *hh; if (dst->pending_confirm) { unsigned long now = jiffies; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 7e748ad..29d842a 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -335,7 +335,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) } #endif -static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) +static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) { unsigned int seq; int hh_len; @@ -390,7 +390,7 @@ struct neighbour_cb { #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) -static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, +static inline void neigh_ha_snapshot(char *dst, struct neighbour *n, const struct net_device *dev) { unsigned int seq; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2ba9de8..5602015 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -57,6 +57,7 @@ struct netns_ipv4 { int sysctl_icmp_echo_ignore_all; int sysctl_icmp_echo_ignore_broadcasts; + int sysctl_icmp_echo_sysrq; int sysctl_icmp_ignore_bogus_error_responses; int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; diff --git a/include/trace/events/hist.h b/include/trace/events/hist.h new file mode 100644 index 0000000..28646db --- /dev/null +++ b/include/trace/events/hist.h @@ -0,0 +1,69 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hist + +#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_HIST_H + +#include "latency_hist.h" +#include + +#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST) +#define trace_preemptirqsoff_hist(a,b) +#else +TRACE_EVENT(preemptirqsoff_hist, + + TP_PROTO(int reason, int starthist), + + TP_ARGS(reason, starthist), + + TP_STRUCT__entry( + __field(int, reason ) + __field(int, starthist ) + ), + + TP_fast_assign( + __entry->reason = reason; + __entry->starthist = starthist; + ), + + TP_printk("reason=%s starthist=%s", getaction(__entry->reason), + __entry->starthist ? "start" : "stop") +); +#endif + +#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST +#define trace_hrtimer_interrupt(a,b,c,d) +#else +TRACE_EVENT(hrtimer_interrupt, + + TP_PROTO(int cpu, long long offset, struct task_struct *curr, struct task_struct *task), + + TP_ARGS(cpu, offset, curr, task), + + TP_STRUCT__entry( + __field(int, cpu ) + __field(long long, offset ) + __array(char, ccomm, TASK_COMM_LEN) + __field(int, cprio ) + __array(char, tcomm, TASK_COMM_LEN) + __field(int, tprio ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->offset = offset; + memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN); + __entry->cprio = curr->prio; + memcpy(__entry->tcomm, task != NULL ? task->comm : "", task != NULL ? TASK_COMM_LEN : 7); + __entry->tprio = task != NULL ? task->prio : -1; + ), + + TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]", + __entry->cpu, __entry->offset, __entry->ccomm, __entry->cprio, __entry->tcomm, __entry->tprio) +); +#endif + +#endif /* _TRACE_HIST_H */ + +/* This part must be outside protection */ +#include diff --git a/include/trace/events/latency_hist.h b/include/trace/events/latency_hist.h new file mode 100644 index 0000000..7f70794 --- /dev/null +++ b/include/trace/events/latency_hist.h @@ -0,0 +1,29 @@ +#ifndef _LATENCY_HIST_H +#define _LATENCY_HIST_H + +enum hist_action { + IRQS_ON, + PREEMPT_ON, + TRACE_STOP, + IRQS_OFF, + PREEMPT_OFF, + TRACE_START, +}; + +static char *actions[] = { + "IRQS_ON", + "PREEMPT_ON", + "TRACE_STOP", + "IRQS_OFF", + "PREEMPT_OFF", + "TRACE_START", +}; + +static inline char *getaction(int action) +{ + if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0])) + return(actions[action]); + return("unknown"); +} + +#endif /* _LATENCY_HIST_H */ diff --git a/init/Kconfig b/init/Kconfig index 2d9b831..c0048eb 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -577,7 +577,7 @@ config RCU_FANOUT_EXACT config RCU_FAST_NO_HZ bool "Accelerate last non-dyntick-idle CPU's grace periods" - depends on NO_HZ_COMMON && SMP + depends on NO_HZ_COMMON && SMP && !PREEMPT_RT_FULL default n help This option permits CPUs to enter dynticks-idle state even if @@ -985,6 +985,7 @@ config CFS_BANDWIDTH config RT_GROUP_SCHED bool "Group scheduling for SCHED_RR/FIFO" depends on CGROUP_SCHED + depends on !PREEMPT_RT_FULL default n help This feature lets you explicitly allocate real CPU bandwidth @@ -1534,6 +1535,7 @@ choice config SLAB bool "SLAB" + depends on !PREEMPT_RT_FULL help The regular slab allocator that is established and known to work well in all environments. It organizes cache hot objects in @@ -1552,6 +1554,7 @@ config SLUB config SLOB depends on EXPERT bool "SLOB (Simple Allocator)" + depends on !PREEMPT_RT_FULL help SLOB replaces the stock allocator with a drastically simpler allocator. SLOB is generally more space efficient but diff --git a/init/Makefile b/init/Makefile index 7bc47ee..88cf473 100644 --- a/init/Makefile +++ b/init/Makefile @@ -33,4 +33,4 @@ silent_chk_compile.h = : include/generated/compile.h: FORCE @$($(quiet)chk_compile.h) $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ - "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)" + "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)" diff --git a/init/main.c b/init/main.c index e83ac04..218371f 100644 --- a/init/main.c +++ b/init/main.c @@ -75,6 +75,7 @@ #include #include #include +#include #include #include @@ -505,6 +506,7 @@ asmlinkage void __init start_kernel(void) setup_command_line(command_line); setup_nr_cpu_ids(); setup_per_cpu_areas(); + softirq_early_init(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ build_all_zonelists(NULL, NULL); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index ae1996d..e9d2b89 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -923,12 +923,17 @@ static inline void pipelined_send(struct mqueue_inode_info *info, struct msg_msg *message, struct ext_wait_queue *receiver) { + /* + * Keep them in one critical section for PREEMPT_RT: + */ + preempt_disable_rt(); receiver->msg = message; list_del(&receiver->list); receiver->state = STATE_PENDING; wake_up_process(receiver->task); smp_wmb(); receiver->state = STATE_READY; + preempt_enable_rt(); } /* pipelined_receive() - if there is task waiting in sys_mq_timedsend() @@ -942,13 +947,18 @@ static inline void pipelined_receive(struct mqueue_inode_info *info) wake_up_interruptible(&info->wait_q); return; } - if (msg_insert(sender->msg, info)) - return; - list_del(&sender->list); - sender->state = STATE_PENDING; - wake_up_process(sender->task); - smp_wmb(); - sender->state = STATE_READY; + /* + * Keep them in one critical section for PREEMPT_RT: + */ + preempt_disable_rt(); + if (!msg_insert(sender->msg, info)) { + list_del(&sender->list); + sender->state = STATE_PENDING; + wake_up_process(sender->task); + smp_wmb(); + sender->state = STATE_READY; + } + preempt_enable_rt(); } SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, diff --git a/ipc/msg.c b/ipc/msg.c index 558aa91..6fdb94c 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -253,10 +253,18 @@ static void expunge_all(struct msg_queue *msq, int res) struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { + /* + * Make sure that the wakeup doesnt preempt + * this CPU prematurely. (on PREEMPT_RT) + */ + preempt_disable_rt(); + msr->r_msg = NULL; wake_up_process(msr->r_tsk); smp_mb(); msr->r_msg = ERR_PTR(res); + + preempt_enable_rt(); } } @@ -636,6 +644,12 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) !security_msg_queue_msgrcv(msq, msg, msr->r_tsk, msr->r_msgtype, msr->r_mode)) { + /* + * Make sure that the wakeup doesnt preempt + * this CPU prematurely. (on PREEMPT_RT) + */ + preempt_disable_rt(); + list_del(&msr->r_list); if (msr->r_maxsize < msg->m_ts) { msr->r_msg = NULL; @@ -649,9 +663,11 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) wake_up_process(msr->r_tsk); smp_mb(); msr->r_msg = msg; + preempt_enable_rt(); return 1; } + preempt_enable_rt(); } } return 0; diff --git a/ipc/sem.c b/ipc/sem.c index db9d241..6a804da 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -607,7 +607,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops, curr = sma->sem_base + sop->sem_num; sem_op = sop->sem_op; result = curr->semval; - + if (!sem_op && result) goto would_block; @@ -634,7 +634,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops, un->semadj[sop->sem_num] -= sop->sem_op; sop--; } - + return 0; out_of_range: @@ -666,6 +666,13 @@ undo: static void wake_up_sem_queue_prepare(struct list_head *pt, struct sem_queue *q, int error) { +#ifdef CONFIG_PREEMPT_RT_BASE + struct task_struct *p = q->sleeper; + get_task_struct(p); + q->status = error; + wake_up_process(p); + put_task_struct(p); +#else if (list_empty(pt)) { /* * Hold preempt off so that we don't get preempted and have the @@ -677,6 +684,7 @@ static void wake_up_sem_queue_prepare(struct list_head *pt, q->pid = error; list_add_tail(&q->list, pt); +#endif } /** @@ -690,6 +698,7 @@ static void wake_up_sem_queue_prepare(struct list_head *pt, */ static void wake_up_sem_queue_do(struct list_head *pt) { +#ifndef CONFIG_PREEMPT_RT_BASE struct sem_queue *q, *t; int did_something; @@ -702,6 +711,7 @@ static void wake_up_sem_queue_do(struct list_head *pt) } if (did_something) preempt_enable(); +#endif } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) @@ -1161,7 +1171,7 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid, err = security_sem_semctl(NULL, cmd); if (err) return err; - + memset(&seminfo,0,sizeof(seminfo)); seminfo.semmni = ns->sc_semmni; seminfo.semmns = ns->sc_semmns; @@ -1875,7 +1885,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, /* We need to sleep on this operation, so we put the current * task into the pending queue and go to sleep. */ - + queue.sops = sops; queue.nsops = nsops; queue.undo = un; @@ -2010,7 +2020,7 @@ int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) return error; atomic_inc(&undo_list->refcnt); tsk->sysvsem.undo_list = undo_list; - } else + } else tsk->sysvsem.undo_list = NULL; return 0; diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 44511d1..f60af90 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -222,4 +222,4 @@ endif config MUTEX_SPIN_ON_OWNER def_bool y - depends on SMP && !DEBUG_MUTEXES + depends on SMP && !DEBUG_MUTEXES && !PREEMPT_RT_FULL diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 3f9c974..11dbe26 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,3 +1,16 @@ +config PREEMPT + bool + select PREEMPT_COUNT + +config PREEMPT_RT_BASE + bool + select PREEMPT + +config HAVE_PREEMPT_LAZY + bool + +config PREEMPT_LAZY + def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL choice prompt "Preemption Model" @@ -33,9 +46,9 @@ config PREEMPT_VOLUNTARY Select this if you are building a kernel for a desktop system. -config PREEMPT +config PREEMPT__LL bool "Preemptible Kernel (Low-Latency Desktop)" - select PREEMPT_COUNT + select PREEMPT select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK help This option reduces the latency of the kernel by making @@ -52,6 +65,22 @@ config PREEMPT embedded system with latency requirements in the milliseconds range. +config PREEMPT_RTB + bool "Preemptible Kernel (Basic RT)" + select PREEMPT_RT_BASE + help + This option is basically the same as (Low-Latency Desktop) but + enables changes which are preliminary for the full preemptible + RT kernel. + +config PREEMPT_RT_FULL + bool "Fully Preemptible Kernel (RT)" + depends on IRQ_FORCED_THREADING + select PREEMPT_RT_BASE + select PREEMPT_RCU + help + All and everything + endchoice config PREEMPT_COUNT diff --git a/kernel/Makefile b/kernel/Makefile index 271fd31..835dfb2 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -7,10 +7,10 @@ obj-y = fork.o exec_domain.o panic.o printk.o \ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ rcupdate.o extable.o params.o posix-timers.o \ - kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \ - hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ + kthread.o wait.o sys_ni.o posix-cpu-timers.o \ + hrtimer.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o cred.o \ - async.o range.o groups.o lglock.o smpboot.o + async.o range.o groups.o lglock.o smpboot.o wait-simple.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files @@ -31,7 +31,11 @@ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ +ifneq ($(CONFIG_PREEMPT_RT_FULL),y) +obj-y += mutex.o obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o +obj-y += rwsem.o +endif obj-$(CONFIG_LOCKDEP) += lockdep.o ifeq ($(CONFIG_PROC_FS),y) obj-$(CONFIG_LOCKDEP) += lockdep_proc.o @@ -43,6 +47,7 @@ endif obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o +obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) diff --git a/kernel/cpu.c b/kernel/cpu.c index 198a388..c62ae01 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -63,6 +63,282 @@ static struct { .refcount = 0, }; +/** + * hotplug_pcp - per cpu hotplug descriptor + * @unplug: set when pin_current_cpu() needs to sync tasks + * @sync_tsk: the task that waits for tasks to finish pinned sections + * @refcount: counter of tasks in pinned sections + * @grab_lock: set when the tasks entering pinned sections should wait + * @synced: notifier for @sync_tsk to tell cpu_down it's finished + * @mutex: the mutex to make tasks wait (used when @grab_lock is true) + * @mutex_init: zero if the mutex hasn't been initialized yet. + * + * Although @unplug and @sync_tsk may point to the same task, the @unplug + * is used as a flag and still exists after @sync_tsk has exited and + * @sync_tsk set to NULL. + */ +struct hotplug_pcp { + struct task_struct *unplug; + struct task_struct *sync_tsk; + int refcount; + int grab_lock; + struct completion synced; + struct completion unplug_wait; +#ifdef CONFIG_PREEMPT_RT_FULL + spinlock_t lock; +#else + struct mutex mutex; +#endif + int mutex_init; +}; + +#ifdef CONFIG_PREEMPT_RT_FULL +# define hotplug_lock(hp) rt_spin_lock(&(hp)->lock) +# define hotplug_unlock(hp) rt_spin_unlock(&(hp)->lock) +#else +# define hotplug_lock(hp) mutex_lock(&(hp)->mutex) +# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex) +#endif + +static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); + +/** + * pin_current_cpu - Prevent the current cpu from being unplugged + * + * Lightweight version of get_online_cpus() to prevent cpu from being + * unplugged when code runs in a migration disabled region. + * + * Must be called with preemption disabled (preempt_count = 1)! + */ +void pin_current_cpu(void) +{ + struct hotplug_pcp *hp; + int force = 0; + +retry: + hp = &__get_cpu_var(hotplug_pcp); + + if (!hp->unplug || hp->refcount || force || preempt_count() > 1 || + hp->unplug == current) { + hp->refcount++; + return; + } + if (hp->grab_lock) { + preempt_enable(); + hotplug_lock(hp); + hotplug_unlock(hp); + } else { + preempt_enable(); + /* + * Try to push this task off of this CPU. + */ + if (!migrate_me()) { + preempt_disable(); + hp = &__get_cpu_var(hotplug_pcp); + if (!hp->grab_lock) { + /* + * Just let it continue it's already pinned + * or about to sleep. + */ + force = 1; + goto retry; + } + preempt_enable(); + } + } + preempt_disable(); + goto retry; +} + +/** + * unpin_current_cpu - Allow unplug of current cpu + * + * Must be called with preemption or interrupts disabled! + */ +void unpin_current_cpu(void) +{ + struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp); + + WARN_ON(hp->refcount <= 0); + + /* This is safe. sync_unplug_thread is pinned to this cpu */ + if (!--hp->refcount && hp->unplug && hp->unplug != current) + wake_up_process(hp->unplug); +} + +static void wait_for_pinned_cpus(struct hotplug_pcp *hp) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + while (hp->refcount) { + schedule_preempt_disabled(); + set_current_state(TASK_UNINTERRUPTIBLE); + } +} + +static int sync_unplug_thread(void *data) +{ + struct hotplug_pcp *hp = data; + + wait_for_completion(&hp->unplug_wait); + preempt_disable(); + hp->unplug = current; + wait_for_pinned_cpus(hp); + + /* + * This thread will synchronize the cpu_down() with threads + * that have pinned the CPU. When the pinned CPU count reaches + * zero, we inform the cpu_down code to continue to the next step. + */ + set_current_state(TASK_UNINTERRUPTIBLE); + preempt_enable(); + complete(&hp->synced); + + /* + * If all succeeds, the next step will need tasks to wait till + * the CPU is offline before continuing. To do this, the grab_lock + * is set and tasks going into pin_current_cpu() will block on the + * mutex. But we still need to wait for those that are already in + * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop() + * will kick this thread out. + */ + while (!hp->grab_lock && !kthread_should_stop()) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + + /* Make sure grab_lock is seen before we see a stale completion */ + smp_mb(); + + /* + * Now just before cpu_down() enters stop machine, we need to make + * sure all tasks that are in pinned CPU sections are out, and new + * tasks will now grab the lock, keeping them from entering pinned + * CPU sections. + */ + if (!kthread_should_stop()) { + preempt_disable(); + wait_for_pinned_cpus(hp); + preempt_enable(); + complete(&hp->synced); + } + + set_current_state(TASK_UNINTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + set_current_state(TASK_RUNNING); + + /* + * Force this thread off this CPU as it's going down and + * we don't want any more work on this CPU. + */ + current->flags &= ~PF_NO_SETAFFINITY; + do_set_cpus_allowed(current, cpu_present_mask); + migrate_me(); + return 0; +} + +static void __cpu_unplug_sync(struct hotplug_pcp *hp) +{ + wake_up_process(hp->sync_tsk); + wait_for_completion(&hp->synced); +} + +static void __cpu_unplug_wait(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + complete(&hp->unplug_wait); + wait_for_completion(&hp->synced); +} + +/* + * Start the sync_unplug_thread on the target cpu and wait for it to + * complete. + */ +static int cpu_unplug_begin(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + int err; + + /* Protected by cpu_hotplug.lock */ + if (!hp->mutex_init) { +#ifdef CONFIG_PREEMPT_RT_FULL + spin_lock_init(&hp->lock); +#else + mutex_init(&hp->mutex); +#endif + hp->mutex_init = 1; + } + + /* Inform the scheduler to migrate tasks off this CPU */ + tell_sched_cpu_down_begin(cpu); + + init_completion(&hp->synced); + init_completion(&hp->unplug_wait); + + hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); + if (IS_ERR(hp->sync_tsk)) { + err = PTR_ERR(hp->sync_tsk); + hp->sync_tsk = NULL; + return err; + } + kthread_bind(hp->sync_tsk, cpu); + + /* + * Wait for tasks to get out of the pinned sections, + * it's still OK if new tasks enter. Some CPU notifiers will + * wait for tasks that are going to enter these sections and + * we must not have them block. + */ + wake_up_process(hp->sync_tsk); + return 0; +} + +static void cpu_unplug_sync(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + init_completion(&hp->synced); + /* The completion needs to be initialzied before setting grab_lock */ + smp_wmb(); + + /* Grab the mutex before setting grab_lock */ + hotplug_lock(hp); + hp->grab_lock = 1; + + /* + * The CPU notifiers have been completed. + * Wait for tasks to get out of pinned CPU sections and have new + * tasks block until the CPU is completely down. + */ + __cpu_unplug_sync(hp); + + /* All done with the sync thread */ + kthread_stop(hp->sync_tsk); + hp->sync_tsk = NULL; +} + +static void cpu_unplug_done(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + hp->unplug = NULL; + /* Let all tasks know cpu unplug is finished before cleaning up */ + smp_wmb(); + + if (hp->sync_tsk) + kthread_stop(hp->sync_tsk); + + if (hp->grab_lock) { + hotplug_unlock(hp); + /* protected by cpu_hotplug.lock */ + hp->grab_lock = 0; + } + tell_sched_cpu_down_done(cpu); +} + void get_online_cpus(void) { might_sleep(); @@ -79,15 +355,14 @@ void put_online_cpus(void) { if (cpu_hotplug.active_writer == current) return; - mutex_lock(&cpu_hotplug.lock); + mutex_lock(&cpu_hotplug.lock); if (WARN_ON(!cpu_hotplug.refcount)) cpu_hotplug.refcount++; /* try to fix things up */ if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer)) wake_up_process(cpu_hotplug.active_writer); mutex_unlock(&cpu_hotplug.lock); - } EXPORT_SYMBOL_GPL(put_online_cpus); @@ -285,13 +560,15 @@ static int __ref take_cpu_down(void *_param) /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) { - int err, nr_calls = 0; + int mycpu, err, nr_calls = 0; void *hcpu = (void *)(long)cpu; unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; struct take_cpu_down_param tcd_param = { .mod = mod, .hcpu = hcpu, }; + cpumask_var_t cpumask; + cpumask_var_t cpumask_org; if (num_online_cpus() == 1) return -EBUSY; @@ -299,7 +576,34 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) if (!cpu_online(cpu)) return -EINVAL; + /* Move the downtaker off the unplug cpu */ + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) { + free_cpumask_var(cpumask); + return -ENOMEM; + } + + cpumask_copy(cpumask_org, tsk_cpus_allowed(current)); + cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); + set_cpus_allowed_ptr(current, cpumask); + free_cpumask_var(cpumask); + migrate_disable(); + mycpu = smp_processor_id(); + if (mycpu == cpu) { + printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); + migrate_enable(); + err = -EBUSY; + goto restore_cpus; + } + migrate_enable(); + cpu_hotplug_begin(); + err = cpu_unplug_begin(cpu); + if (err) { + printk("cpu_unplug_begin(%d) failed\n", cpu); + goto out_cancel; + } err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); if (err) { @@ -309,8 +613,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) __func__, cpu); goto out_release; } + + __cpu_unplug_wait(cpu); smpboot_park_threads(cpu); + /* Notifiers are done. Don't let any more tasks pin this CPU. */ + cpu_unplug_sync(cpu); + err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ @@ -339,9 +648,14 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) check_for_tasks(cpu); out_release: + cpu_unplug_done(cpu); +out_cancel: cpu_hotplug_done(); if (!err) cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); +restore_cpus: + set_cpus_allowed_ptr(current, cpumask_org); + free_cpumask_var(cpumask_org); return err; } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 14ff484..399dba6 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -554,7 +554,6 @@ int vkdb_printf(const char *fmt, va_list ap) int linecount; int colcount; int logging, saved_loglevel = 0; - int saved_trap_printk; int got_printf_lock = 0; int retlen = 0; int fnd, len; @@ -565,8 +564,6 @@ int vkdb_printf(const char *fmt, va_list ap) unsigned long uninitialized_var(flags); preempt_disable(); - saved_trap_printk = kdb_trap_printk; - kdb_trap_printk = 0; /* Serialize kdb_printf if multiple cpus try to write at once. * But if any cpu goes recursive in kdb, just print the output, @@ -833,7 +830,6 @@ kdb_print_out: } else { __release(kdb_printf_lock); } - kdb_trap_printk = saved_trap_printk; preempt_enable(); return retlen; } @@ -843,9 +839,11 @@ int kdb_printf(const char *fmt, ...) va_list ap; int r; + kdb_trap_printk++; va_start(ap, fmt); r = vkdb_printf(fmt, ap); va_end(ap); + kdb_trap_printk--; return r; } diff --git a/kernel/events/core.c b/kernel/events/core.c index e76e495..83c5574 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5737,6 +5737,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event) hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hwc->hrtimer.function = perf_swevent_hrtimer; + hwc->hrtimer.irqsafe = 1; /* * Since hrtimers have a fixed rate, we can do a static freq->period diff --git a/kernel/exit.c b/kernel/exit.c index 7bb73f9..1725584 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -145,7 +145,7 @@ static void __exit_signal(struct task_struct *tsk) * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ - flush_sigqueue(&tsk->pending); + flush_task_sigqueue(tsk); tsk->sighand = NULL; spin_unlock(&sighand->siglock); diff --git a/kernel/fork.c b/kernel/fork.c index ff7be9d..e2d5958 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -94,7 +94,7 @@ int max_threads; /* tunable limit on nr_threads */ DEFINE_PER_CPU(unsigned long, process_counts) = 0; -__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ +DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) @@ -230,7 +230,9 @@ static inline void put_signal_struct(struct signal_struct *sig) if (atomic_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } - +#ifdef CONFIG_PREEMPT_RT_BASE +static +#endif void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); @@ -245,7 +247,18 @@ void __put_task_struct(struct task_struct *tsk) if (!profile_handoff_task(tsk)) free_task(tsk); } +#ifndef CONFIG_PREEMPT_RT_BASE EXPORT_SYMBOL_GPL(__put_task_struct); +#else +void __put_task_struct_cb(struct rcu_head *rhp) +{ + struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); + + __put_task_struct(tsk); + +} +EXPORT_SYMBOL_GPL(__put_task_struct_cb); +#endif void __init __weak arch_task_cache_init(void) { } @@ -605,6 +618,19 @@ void __mmdrop(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(__mmdrop); +#ifdef CONFIG_PREEMPT_RT_BASE +/* + * RCU callback for delayed mm drop. Not strictly rcu, but we don't + * want another facility to make this work. + */ +void __mmdrop_delayed(struct rcu_head *rhp) +{ + struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); + + __mmdrop(mm); +} +#endif + /* * Decrement the use count and release all resources for an mm. */ @@ -1114,6 +1140,9 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p) */ static void posix_cpu_timers_init(struct task_struct *tsk) { +#ifdef CONFIG_PREEMPT_RT_BASE + tsk->posix_timer_list = NULL; +#endif tsk->cputime_expires.prof_exp = 0; tsk->cputime_expires.virt_exp = 0; tsk->cputime_expires.sched_exp = 0; @@ -1233,6 +1262,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); + p->sigqueue_cache = NULL; p->utime = p->stime = p->gtime = 0; p->utimescaled = p->stimescaled = 0; @@ -1240,7 +1270,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->prev_cputime.utime = p->prev_cputime.stime = 0; #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_init(&p->vtime_seqlock); + raw_spin_lock_init(&p->vtime_lock); + seqcount_init(&p->vtime_seq); p->vtime_snap = 0; p->vtime_snap_whence = VTIME_SLEEPING; #endif @@ -1293,6 +1324,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->hardirq_context = 0; p->softirq_context = 0; #endif +#ifdef CONFIG_PREEMPT_RT_FULL + p->pagefault_disabled = 0; +#endif #ifdef CONFIG_LOCKDEP p->lockdep_depth = 0; /* no locks held yet */ p->curr_chain_key = 0; @@ -1661,7 +1695,7 @@ SYSCALL_DEFINE0(fork) #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, 0, NULL, NULL); } #endif diff --git a/kernel/futex.c b/kernel/futex.c index a283b30..70ba961 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -571,7 +571,9 @@ void exit_pi_state_list(struct task_struct *curr) * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock_irq(&curr->pi_lock); spin_unlock(&hb->lock); + raw_spin_lock_irq(&curr->pi_lock); continue; } @@ -1445,6 +1447,16 @@ retry_private: requeue_pi_wake_futex(this, &key2, hb2); drop_count++; continue; + } else if (ret == -EAGAIN) { + /* + * Waiter was woken by timeout or + * signal and has set pi_blocked_on to + * PI_WAKEUP_INPROGRESS before we + * tried to enqueue it on the rtmutex. + */ + this->pi_state = NULL; + free_pi_state(pi_state); + continue; } else if (ret) { /* -EDEADLK */ this->pi_state = NULL; @@ -2288,7 +2300,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, struct hrtimer_sleeper timeout, *to = NULL; struct rt_mutex_waiter rt_waiter; struct rt_mutex *pi_mutex = NULL; - struct futex_hash_bucket *hb; + struct futex_hash_bucket *hb, *hb2; union futex_key key2 = FUTEX_KEY_INIT; struct futex_q q = futex_q_init; int res, ret; @@ -2313,8 +2325,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * The waiter is allocated on our stack, manipulated by the requeue * code while we sleep on uaddr. */ - debug_rt_mutex_init_waiter(&rt_waiter); - rt_waiter.task = NULL; + rt_mutex_init_waiter(&rt_waiter, false); ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); if (unlikely(ret != 0)) @@ -2335,20 +2346,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, /* Queue the futex_q, drop the hb lock, wait for wakeup. */ futex_wait_queue_me(hb, &q, to); - spin_lock(&hb->lock); - ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); - spin_unlock(&hb->lock); - if (ret) - goto out_put_keys; + /* + * On RT we must avoid races with requeue and trying to block + * on two mutexes (hb->lock and uaddr2's rtmutex) by + * serializing access to pi_blocked_on with pi_lock. + */ + raw_spin_lock_irq(¤t->pi_lock); + if (current->pi_blocked_on) { + /* + * We have been requeued or are in the process of + * being requeued. + */ + raw_spin_unlock_irq(¤t->pi_lock); + } else { + /* + * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS + * prevents a concurrent requeue from moving us to the + * uaddr2 rtmutex. After that we can safely acquire + * (and possibly block on) hb->lock. + */ + current->pi_blocked_on = PI_WAKEUP_INPROGRESS; + raw_spin_unlock_irq(¤t->pi_lock); + + spin_lock(&hb->lock); + + /* + * Clean up pi_blocked_on. We might leak it otherwise + * when we succeeded with the hb->lock in the fast + * path. + */ + raw_spin_lock_irq(¤t->pi_lock); + current->pi_blocked_on = NULL; + raw_spin_unlock_irq(¤t->pi_lock); + + ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); + spin_unlock(&hb->lock); + if (ret) + goto out_put_keys; + } /* - * In order for us to be here, we know our q.key == key2, and since - * we took the hb->lock above, we also know that futex_requeue() has - * completed and we no longer have to concern ourselves with a wakeup - * race with the atomic proxy lock acquisition by the requeue code. The - * futex_requeue dropped our key1 reference and incremented our key2 - * reference count. + * In order to be here, we have either been requeued, are in + * the process of being requeued, or requeue successfully + * acquired uaddr2 on our behalf. If pi_blocked_on was + * non-null above, we may be racing with a requeue. Do not + * rely on q->lock_ptr to be hb2->lock until after blocking on + * hb->lock or hb2->lock. The futex_requeue dropped our key1 + * reference and incremented our key2 reference count. */ + hb2 = hash_futex(&key2); /* Check if the requeue code acquired the second futex for us. */ if (!q.rt_waiter) { @@ -2357,9 +2403,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * did a lock-steal - fix up the PI-state in that case. */ if (q.pi_state && (q.pi_state->owner != current)) { - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); - spin_unlock(q.lock_ptr); + spin_unlock(&hb2->lock); } } else { /* @@ -2372,7 +2419,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1); debug_rt_mutex_free_waiter(&rt_waiter); - spin_lock(q.lock_ptr); + spin_lock(&hb2->lock); + BUG_ON(&hb2->lock != q.lock_ptr); /* * Fixup the pi_state owner and possibly acquire the lock if we * haven't already. diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 2288fbd..a63cfaf 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -47,10 +47,12 @@ #include #include #include +#include #include #include +#include /* * The timer bases: @@ -606,8 +608,7 @@ static int hrtimer_reprogram(struct hrtimer *timer, * When the callback is running, we do not reprogram the clock event * device. The timer callback is either running on a different CPU or * the callback is executed in the hrtimer_interrupt context. The - * reprogramming is handled either by the softirq, which called the - * callback or at the end of the hrtimer_interrupt. + * reprogramming is handled at the end of the hrtimer_interrupt. */ if (hrtimer_callback_running(timer)) return 0; @@ -642,6 +643,9 @@ static int hrtimer_reprogram(struct hrtimer *timer, return res; } +static void __run_hrtimer(struct hrtimer *timer, ktime_t *now); +static int hrtimer_rt_defer(struct hrtimer *timer); + /* * Initialize the high resolution related parts of cpu_base */ @@ -658,9 +662,18 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) * and expiry check is done in the hrtimer_interrupt or in the softirq. */ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) + struct hrtimer_clock_base *base, + int wakeup) { - return base->cpu_base->hres_active && hrtimer_reprogram(timer, base); + if (!(base->cpu_base->hres_active && hrtimer_reprogram(timer, base))) + return 0; + if (!wakeup) + return -ETIME; +#ifdef CONFIG_PREEMPT_RT_BASE + if (!hrtimer_rt_defer(timer)) + return -ETIME; +#endif + return 1; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) @@ -728,6 +741,44 @@ static void clock_was_set_work(struct work_struct *work) static DECLARE_WORK(hrtimer_work, clock_was_set_work); +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * RT can not call schedule_work from real interrupt context. + * Need to make a thread to do the real work. + */ +static struct task_struct *clock_set_delay_thread; +static bool do_clock_set_delay; + +static int run_clock_set_delay(void *ignore) +{ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (do_clock_set_delay) { + do_clock_set_delay = false; + schedule_work(&hrtimer_work); + } + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void clock_was_set_delayed(void) +{ + do_clock_set_delay = true; + /* Make visible before waking up process */ + smp_wmb(); + wake_up_process(clock_set_delay_thread); +} + +static __init int create_clock_set_delay_thread(void) +{ + clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd"); + BUG_ON(!clock_set_delay_thread); + return 0; +} +early_initcall(create_clock_set_delay_thread); +#else /* PREEMPT_RT_FULL */ /* * Called from timekeeping and resume code to reprogramm the hrtimer * interrupt device on all cpus. @@ -736,6 +787,7 @@ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } +#endif #else @@ -745,12 +797,18 @@ static inline int hrtimer_switch_to_hres(void) { return 0; } static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) + struct hrtimer_clock_base *base, + int wakeup) { return 0; } static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } static inline void retrigger_next_event(void *arg) { } +static inline int hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + return 0; +} #endif /* CONFIG_HIGH_RES_TIMERS */ @@ -867,6 +925,32 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(hrtimer_forward); +#ifdef CONFIG_PREEMPT_RT_BASE +# define wake_up_timer_waiters(b) wake_up(&(b)->wait) + +/** + * hrtimer_wait_for_timer - Wait for a running timer + * + * @timer: timer to wait for + * + * The function waits in case the timers callback function is + * currently executed on the waitqueue of the timer base. The + * waitqueue is woken up after the timer callback function has + * finished execution. + */ +void hrtimer_wait_for_timer(const struct hrtimer *timer) +{ + struct hrtimer_clock_base *base = timer->base; + + if (base && base->cpu_base && !timer->irqsafe) + wait_event(base->cpu_base->wait, + !(timer->state & HRTIMER_STATE_CALLBACK)); +} + +#else +# define wake_up_timer_waiters(b) do { } while (0) +#endif + /* * enqueue_hrtimer - internal function to (re)start a timer * @@ -910,6 +994,11 @@ static void __remove_hrtimer(struct hrtimer *timer, if (!(timer->state & HRTIMER_STATE_ENQUEUED)) goto out; + if (unlikely(!list_empty(&timer->cb_entry))) { + list_del_init(&timer->cb_entry); + goto out; + } + next_timer = timerqueue_getnext(&base->active); timerqueue_del(&base->active, &timer->node); if (&timer->node == next_timer) { @@ -994,6 +1083,17 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, #endif } +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + { + ktime_t now = new_base->get_time(); + + if (ktime_to_ns(tim) < ktime_to_ns(now)) + timer->praecox = now; + else + timer->praecox = ktime_set(0, 0); + } +#endif + hrtimer_set_expires_range_ns(timer, tim, delta_ns); timer_stats_hrtimer_set_start_info(timer); @@ -1006,9 +1106,19 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * * XXX send_remote_softirq() ? */ - if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases) - && hrtimer_enqueue_reprogram(timer, new_base)) { - if (wakeup) { + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) { + ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup); + if (ret < 0) { + /* + * In case we failed to reprogram the timer (mostly + * because out current timer is already elapsed), + * remove it again and report a failure. This avoids + * stale base->first entries. + */ + debug_deactivate(timer); + __remove_hrtimer(timer, new_base, + timer->state & HRTIMER_STATE_CALLBACK, 0); + } else if (ret > 0) { /* * We need to drop cpu_base->lock to avoid a * lock ordering issue vs. rq->lock. @@ -1016,9 +1126,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, raw_spin_unlock(&new_base->cpu_base->lock); raise_softirq_irqoff(HRTIMER_SOFTIRQ); local_irq_restore(flags); - return ret; - } else { - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + return 0; } } @@ -1108,7 +1216,7 @@ int hrtimer_cancel(struct hrtimer *timer) if (ret >= 0) return ret; - cpu_relax(); + hrtimer_wait_for_timer(timer); } } EXPORT_SYMBOL_GPL(hrtimer_cancel); @@ -1187,6 +1295,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, base = hrtimer_clockid_to_base(clock_id); timer->base = &cpu_base->clock_base[base]; + INIT_LIST_HEAD(&timer->cb_entry); timerqueue_init(&timer->node); #ifdef CONFIG_TIMER_STATS @@ -1270,6 +1379,126 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) timer->state &= ~HRTIMER_STATE_CALLBACK; } +static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer); + +#ifdef CONFIG_PREEMPT_RT_BASE +static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer, + struct hrtimer_clock_base *base) +{ + /* + * Note, we clear the callback flag before we requeue the + * timer otherwise we trigger the callback_running() check + * in hrtimer_reprogram(). + */ + timer->state &= ~HRTIMER_STATE_CALLBACK; + + if (restart != HRTIMER_NORESTART) { + BUG_ON(hrtimer_active(timer)); + /* + * Enqueue the timer, if it's the leftmost timer then + * we need to reprogram it. + */ + if (!enqueue_hrtimer(timer, base)) + return; + +#ifndef CONFIG_HIGH_RES_TIMERS + } +#else + if (base->cpu_base->hres_active && + hrtimer_reprogram(timer, base)) + goto requeue; + + } else if (hrtimer_active(timer)) { + /* + * If the timer was rearmed on another CPU, reprogram + * the event device. + */ + if (&timer->node == base->active.next && + base->cpu_base->hres_active && + hrtimer_reprogram(timer, base)) + goto requeue; + } + return; + +requeue: + /* + * Timer is expired. Thus move it from tree to pending list + * again. + */ + __remove_hrtimer(timer, base, timer->state, 0); + list_add_tail(&timer->cb_entry, &base->expired); +#endif +} + +/* + * The changes in mainline which removed the callback modes from + * hrtimer are not yet working with -rt. The non wakeup_process() + * based callbacks which involve sleeping locks need to be treated + * seperately. + */ +static void hrtimer_rt_run_pending(void) +{ + enum hrtimer_restart (*fn)(struct hrtimer *); + struct hrtimer_cpu_base *cpu_base; + struct hrtimer_clock_base *base; + struct hrtimer *timer; + int index, restart; + + local_irq_disable(); + cpu_base = &per_cpu(hrtimer_bases, smp_processor_id()); + + raw_spin_lock(&cpu_base->lock); + + for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { + base = &cpu_base->clock_base[index]; + + while (!list_empty(&base->expired)) { + timer = list_first_entry(&base->expired, + struct hrtimer, cb_entry); + + /* + * Same as the above __run_hrtimer function + * just we run with interrupts enabled. + */ + debug_hrtimer_deactivate(timer); + __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); + timer_stats_account_hrtimer(timer); + fn = timer->function; + + raw_spin_unlock_irq(&cpu_base->lock); + restart = fn(timer); + raw_spin_lock_irq(&cpu_base->lock); + + hrtimer_rt_reprogram(restart, timer, base); + } + } + + raw_spin_unlock_irq(&cpu_base->lock); + + wake_up_timer_waiters(cpu_base); +} + +static int hrtimer_rt_defer(struct hrtimer *timer) +{ + if (timer->irqsafe) + return 0; + + __remove_hrtimer(timer, timer->base, timer->state, 0); + list_add_tail(&timer->cb_entry, &timer->base->expired); + return 1; +} + +#else + +static inline void hrtimer_rt_run_pending(void) +{ + hrtimer_peek_ahead_timers(); +} + +static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } + +#endif + #ifdef CONFIG_HIGH_RES_TIMERS /* @@ -1280,7 +1509,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); ktime_t expires_next, now, entry_time, delta; - int i, retries = 0; + int i, retries = 0, raise = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; @@ -1315,6 +1544,15 @@ retry: timer = container_of(node, struct hrtimer, node); + trace_hrtimer_interrupt(raw_smp_processor_id(), + ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ? + timer->praecox : hrtimer_get_expires(timer), + basenow)), + current, + timer->function == hrtimer_wakeup ? + container_of(timer, struct hrtimer_sleeper, + timer)->task : NULL); + /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the @@ -1340,7 +1578,10 @@ retry: break; } - __run_hrtimer(timer, &basenow); + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &basenow); + else + raise = 1; } } @@ -1355,7 +1596,7 @@ retry: if (expires_next.tv64 == KTIME_MAX || !tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; - return; + goto out; } /* @@ -1399,6 +1640,9 @@ retry: tick_program_event(expires_next, 1); printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); +out: + if (raise) + raise_softirq_irqoff(HRTIMER_SOFTIRQ); } /* @@ -1434,18 +1678,18 @@ void hrtimer_peek_ahead_timers(void) __hrtimer_peek_ahead_timers(); local_irq_restore(flags); } - -static void run_hrtimer_softirq(struct softirq_action *h) -{ - hrtimer_peek_ahead_timers(); -} - #else /* CONFIG_HIGH_RES_TIMERS */ static inline void __hrtimer_peek_ahead_timers(void) { } #endif /* !CONFIG_HIGH_RES_TIMERS */ + +static void run_hrtimer_softirq(struct softirq_action *h) +{ + hrtimer_rt_run_pending(); +} + /* * Called from timer softirq every jiffy, expire hrtimers: * @@ -1478,7 +1722,7 @@ void hrtimer_run_queues(void) struct timerqueue_node *node; struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); struct hrtimer_clock_base *base; - int index, gettime = 1; + int index, gettime = 1, raise = 0; if (hrtimer_hres_active()) return; @@ -1503,10 +1747,16 @@ void hrtimer_run_queues(void) hrtimer_get_expires_tv64(timer)) break; - __run_hrtimer(timer, &base->softirq_time); + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &base->softirq_time); + else + raise = 1; } raw_spin_unlock(&cpu_base->lock); } + + if (raise) + raise_softirq_irqoff(HRTIMER_SOFTIRQ); } /* @@ -1528,6 +1778,7 @@ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) { sl->timer.function = hrtimer_wakeup; + sl->timer.irqsafe = 1; sl->task = task; } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); @@ -1664,9 +1915,13 @@ static void __cpuinit init_hrtimers_cpu(int cpu) for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { cpu_base->clock_base[i].cpu_base = cpu_base; timerqueue_init_head(&cpu_base->clock_base[i].active); + INIT_LIST_HEAD(&cpu_base->clock_base[i].expired); } hrtimer_init_hres(cpu_base); +#ifdef CONFIG_PREEMPT_RT_BASE + init_waitqueue_head(&cpu_base->wait); +#endif } #ifdef CONFIG_HOTPLUG_CPU @@ -1779,9 +2034,7 @@ void __init hrtimers_init(void) hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); register_cpu_notifier(&hrtimers_nb); -#ifdef CONFIG_HIGH_RES_TIMERS open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); -#endif } /** diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 131ca17..7f50c55 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -132,6 +132,8 @@ static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action) irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) { + struct pt_regs *regs = get_irq_regs(); + u64 ip = regs ? instruction_pointer(regs) : 0; irqreturn_t retval = IRQ_NONE; unsigned int flags = 0, irq = desc->irq_data.irq; @@ -172,7 +174,11 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) action = action->next; } while (action); - add_interrupt_randomness(irq, flags); +#ifndef CONFIG_PREEMPT_RT_FULL + add_interrupt_randomness(irq, flags, ip); +#else + desc->random_ip = ip; +#endif if (!noirqdebug) note_interrupt(irq, desc, retval); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index dc4db32..7d59fb1f9 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -22,6 +22,7 @@ #include "internals.h" #ifdef CONFIG_IRQ_FORCED_THREADING +# ifndef CONFIG_PREEMPT_RT_BASE __read_mostly bool force_irqthreads; static int __init setup_forced_irqthreads(char *arg) @@ -30,6 +31,7 @@ static int __init setup_forced_irqthreads(char *arg) return 0; } early_param("threadirqs", setup_forced_irqthreads); +# endif #endif /** @@ -162,6 +164,62 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, return ret; } +#ifdef CONFIG_PREEMPT_RT_FULL +static void _irq_affinity_notify(struct irq_affinity_notify *notify); +static struct task_struct *set_affinity_helper; +static LIST_HEAD(affinity_list); +static DEFINE_RAW_SPINLOCK(affinity_list_lock); + +static int set_affinity_thread(void *unused) +{ + while (1) { + struct irq_affinity_notify *notify; + int empty; + + set_current_state(TASK_INTERRUPTIBLE); + + raw_spin_lock_irq(&affinity_list_lock); + empty = list_empty(&affinity_list); + raw_spin_unlock_irq(&affinity_list_lock); + + if (empty) + schedule(); + if (kthread_should_stop()) + break; + set_current_state(TASK_RUNNING); +try_next: + notify = NULL; + + raw_spin_lock_irq(&affinity_list_lock); + if (!list_empty(&affinity_list)) { + notify = list_first_entry(&affinity_list, + struct irq_affinity_notify, list); + list_del_init(¬ify->list); + } + raw_spin_unlock_irq(&affinity_list_lock); + + if (!notify) + continue; + _irq_affinity_notify(notify); + goto try_next; + } + return 0; +} + +static void init_helper_thread(void) +{ + if (set_affinity_helper) + return; + set_affinity_helper = kthread_run(set_affinity_thread, NULL, + "affinity-cb"); + WARN_ON(IS_ERR(set_affinity_helper)); +} +#else + +static inline void init_helper_thread(void) { } + +#endif + int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) { struct irq_chip *chip = irq_data_get_irq_chip(data); @@ -180,7 +238,17 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) if (desc->affinity_notify) { kref_get(&desc->affinity_notify->kref); + +#ifdef CONFIG_PREEMPT_RT_FULL + raw_spin_lock(&affinity_list_lock); + if (list_empty(&desc->affinity_notify->list)) + list_add_tail(&affinity_list, + &desc->affinity_notify->list); + raw_spin_unlock(&affinity_list_lock); + wake_up_process(set_affinity_helper); +#else schedule_work(&desc->affinity_notify->work); +#endif } irqd_set(data, IRQD_AFFINITY_SET); @@ -221,10 +289,8 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) } EXPORT_SYMBOL_GPL(irq_set_affinity_hint); -static void irq_affinity_notify(struct work_struct *work) +static void _irq_affinity_notify(struct irq_affinity_notify *notify) { - struct irq_affinity_notify *notify = - container_of(work, struct irq_affinity_notify, work); struct irq_desc *desc = irq_to_desc(notify->irq); cpumask_var_t cpumask; unsigned long flags; @@ -246,6 +312,13 @@ out: kref_put(¬ify->kref, notify->release); } +static void irq_affinity_notify(struct work_struct *work) +{ + struct irq_affinity_notify *notify = + container_of(work, struct irq_affinity_notify, work); + _irq_affinity_notify(notify); +} + /** * irq_set_affinity_notifier - control notification of IRQ affinity changes * @irq: Interrupt for which to enable/disable notification @@ -275,6 +348,8 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) notify->irq = irq; kref_init(¬ify->kref); INIT_WORK(¬ify->work, irq_affinity_notify); + INIT_LIST_HEAD(¬ify->list); + init_helper_thread(); } raw_spin_lock_irqsave(&desc->lock, flags); @@ -781,7 +856,15 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) local_bh_disable(); ret = action->thread_fn(action->irq, action->dev_id); irq_finalize_oneshot(desc, action); - local_bh_enable(); + /* + * Interrupts which have real time requirements can be set up + * to avoid softirq processing in the thread handler. This is + * safe as these interrupts do not raise soft interrupts. + */ + if (irq_settings_no_softirq_call(desc)) + _local_bh_enable(); + else + local_bh_enable(); return ret; } @@ -840,9 +923,6 @@ static void irq_thread_dtor(struct callback_head *unused) static int irq_thread(void *data) { struct callback_head on_exit_work; - static const struct sched_param param = { - .sched_priority = MAX_USER_RT_PRIO/2, - }; struct irqaction *action = data; struct irq_desc *desc = irq_to_desc(action->irq); irqreturn_t (*handler_fn)(struct irq_desc *desc, @@ -854,8 +934,6 @@ static int irq_thread(void *data) else handler_fn = irq_thread_fn; - sched_setscheduler(current, SCHED_FIFO, ¶m); - init_task_work(&on_exit_work, irq_thread_dtor); task_work_add(current, &on_exit_work, false); @@ -870,6 +948,12 @@ static int irq_thread(void *data) if (!noirqdebug) note_interrupt(action->irq, desc, action_ret); +#ifdef CONFIG_PREEMPT_RT_FULL + migrate_disable(); + add_interrupt_randomness(action->irq, 0, + desc->random_ip ^ (unsigned long) action); + migrate_enable(); +#endif wake_threads_waitq(desc); } @@ -950,6 +1034,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ if (new->thread_fn && !nested) { struct task_struct *t; + static const struct sched_param param = { + .sched_priority = MAX_USER_RT_PRIO/2, + }; t = kthread_create(irq_thread, new, "irq/%d-%s", irq, new->name); @@ -957,6 +1044,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) ret = PTR_ERR(t); goto out_mput; } + + sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m); + /* * We keep the reference to the task struct even if * the thread dies to avoid that the interrupt code @@ -1126,6 +1216,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irqd_set(&desc->irq_data, IRQD_NO_BALANCING); } + if (new->flags & IRQF_NO_SOFTIRQ_CALL) + irq_settings_set_no_softirq_call(desc); + /* Set default affinity mask once everything is setup */ setup_affinity(irq, desc, mask); diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 1162f10..0d2c381 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -14,6 +14,7 @@ enum { _IRQ_NO_BALANCING = IRQ_NO_BALANCING, _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; @@ -26,6 +27,7 @@ enum { #define IRQ_NOAUTOEN GOT_YOU_MORON #define IRQ_NESTED_THREAD GOT_YOU_MORON #define IRQ_PER_CPU_DEVID GOT_YOU_MORON +#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON @@ -36,6 +38,16 @@ irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); } +static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; +} + +static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; +} + static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU; diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 7b5f012..38a32b0 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -340,6 +340,11 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true"); static int __init irqfixup_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT_BASE + printk(KERN_WARNING "irqfixup boot option not supported " + "w/ CONFIG_PREEMPT_RT_BASE\n"); + return 1; +#endif irqfixup = 1; printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); printk(KERN_WARNING "This may impact system performance.\n"); @@ -352,6 +357,11 @@ module_param(irqfixup, int, 0644); static int __init irqpoll_setup(char *str) { +#ifdef CONFIG_PREEMPT_RT_BASE + printk(KERN_WARNING "irqpoll boot option not supported " + "w/ CONFIG_PREEMPT_RT_BASE\n"); + return 1; +#endif irqfixup = 2; printk(KERN_WARNING "Misrouted IRQ fixup and polling support " "enabled\n"); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 55fcce6..f6e4377 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -119,8 +119,9 @@ static void __irq_work_run(void) if (llist_empty(this_list)) return; +#ifndef CONFIG_PREEMPT_RT_FULL BUG_ON(!irqs_disabled()); - +#endif llnode = llist_del_all(this_list); while (llnode != NULL) { work = llist_entry(llnode, struct irq_work, llnode); @@ -152,7 +153,9 @@ static void __irq_work_run(void) */ void irq_work_run(void) { +#ifndef CONFIG_PREEMPT_RT_FULL BUG_ON(!in_irq()); +#endif __irq_work_run(); } EXPORT_SYMBOL_GPL(irq_work_run); diff --git a/kernel/itimer.c b/kernel/itimer.c index 8d262b4..d051390 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -213,6 +213,7 @@ again: /* We are sharing ->siglock with it_real_fn() */ if (hrtimer_try_to_cancel(timer) < 0) { spin_unlock_irq(&tsk->sighand->siglock); + hrtimer_wait_for_timer(&tsk->signal->real_timer); goto again; } expires = timeval_to_ktime(value->it_value); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 6ada93c..1c991e3 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -132,6 +132,15 @@ KERNEL_ATTR_RO(vmcoreinfo); #endif /* CONFIG_KEXEC */ +#if defined(CONFIG_PREEMPT_RT_FULL) +static ssize_t realtime_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", 1); +} +KERNEL_ATTR_RO(realtime); +#endif + /* whether file capabilities are enabled */ static ssize_t fscaps_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -197,6 +206,9 @@ static struct attribute * kernel_attrs[] = { &vmcoreinfo_attr.attr, #endif &rcu_expedited_attr.attr, +#ifdef CONFIG_PREEMPT_RT_FULL + &realtime_attr.attr, +#endif NULL }; diff --git a/kernel/lglock.c b/kernel/lglock.c index 6535a66..0bbf5d1 100644 --- a/kernel/lglock.c +++ b/kernel/lglock.c @@ -4,6 +4,15 @@ #include #include +#ifndef CONFIG_PREEMPT_RT_FULL +# define lg_lock_ptr arch_spinlock_t +# define lg_do_lock(l) arch_spin_lock(l) +# define lg_do_unlock(l) arch_spin_unlock(l) +#else +# define lg_lock_ptr struct rt_mutex +# define lg_do_lock(l) __rt_spin_lock(l) +# define lg_do_unlock(l) __rt_spin_unlock(l) +#endif /* * Note there is no uninit, so lglocks cannot be defined in * modules (but it's fine to use them from there) @@ -12,51 +21,60 @@ void lg_lock_init(struct lglock *lg, char *name) { +#ifdef CONFIG_PREEMPT_RT_FULL + int i; + + for_each_possible_cpu(i) { + struct rt_mutex *lock = per_cpu_ptr(lg->lock, i); + + rt_mutex_init(lock); + } +#endif LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); } EXPORT_SYMBOL(lg_lock_init); void lg_local_lock(struct lglock *lg) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; - preempt_disable(); + migrate_disable(); rwlock_acquire_read(&lg->lock_dep_map, 0, 0, _RET_IP_); lock = this_cpu_ptr(lg->lock); - arch_spin_lock(lock); + lg_do_lock(lock); } EXPORT_SYMBOL(lg_local_lock); void lg_local_unlock(struct lglock *lg) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; rwlock_release(&lg->lock_dep_map, 1, _RET_IP_); lock = this_cpu_ptr(lg->lock); - arch_spin_unlock(lock); - preempt_enable(); + lg_do_unlock(lock); + migrate_enable(); } EXPORT_SYMBOL(lg_local_unlock); void lg_local_lock_cpu(struct lglock *lg, int cpu) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; - preempt_disable(); + preempt_disable_nort(); rwlock_acquire_read(&lg->lock_dep_map, 0, 0, _RET_IP_); lock = per_cpu_ptr(lg->lock, cpu); - arch_spin_lock(lock); + lg_do_lock(lock); } EXPORT_SYMBOL(lg_local_lock_cpu); void lg_local_unlock_cpu(struct lglock *lg, int cpu) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; rwlock_release(&lg->lock_dep_map, 1, _RET_IP_); lock = per_cpu_ptr(lg->lock, cpu); - arch_spin_unlock(lock); - preempt_enable(); + lg_do_unlock(lock); + preempt_enable_nort(); } EXPORT_SYMBOL(lg_local_unlock_cpu); @@ -64,12 +82,12 @@ void lg_global_lock(struct lglock *lg) { int i; - preempt_disable(); + preempt_disable_nort(); rwlock_acquire(&lg->lock_dep_map, 0, 0, _RET_IP_); for_each_possible_cpu(i) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; lock = per_cpu_ptr(lg->lock, i); - arch_spin_lock(lock); + lg_do_lock(lock); } } EXPORT_SYMBOL(lg_global_lock); @@ -80,10 +98,10 @@ void lg_global_unlock(struct lglock *lg) rwlock_release(&lg->lock_dep_map, 1, _RET_IP_); for_each_possible_cpu(i) { - arch_spinlock_t *lock; + lg_lock_ptr *lock; lock = per_cpu_ptr(lg->lock, i); - arch_spin_unlock(lock); + lg_do_unlock(lock); } - preempt_enable(); + preempt_enable_nort(); } EXPORT_SYMBOL(lg_global_unlock); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 1f3186b..6cbe12c 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3541,6 +3541,7 @@ static void check_flags(unsigned long flags) } } +#ifndef CONFIG_PREEMPT_RT_FULL /* * We dont accurately track softirq state in e.g. * hardirq contexts (such as on 4KSTACKS), so only @@ -3555,6 +3556,7 @@ static void check_flags(unsigned long flags) DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); } } +#endif if (!debug_locks) print_irqtrace_events(current); diff --git a/kernel/panic.c b/kernel/panic.c index 167ec09..90b6690 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -363,9 +363,11 @@ static u64 oops_id; static int init_oops_id(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!oops_id) get_random_bytes(&oops_id, sizeof(oops_id)); else +#endif oops_id++; return 0; diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 42670e9..b551fd4 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -3,6 +3,7 @@ */ #include +#include #include #include #include @@ -722,7 +723,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, /* * Disarm any old timer after extracting its expiry time. */ - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); ret = 0; old_incr = timer->it.cpu.incr; @@ -1225,7 +1226,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) /* * Now re-arm for the new expiry time. */ - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); arm_timer(timer); spin_unlock(&p->sighand->siglock); @@ -1292,10 +1293,11 @@ static inline int fastpath_timer_check(struct task_struct *tsk) sig = tsk->signal; if (sig->cputimer.running) { struct task_cputime group_sample; + unsigned long flags; - raw_spin_lock(&sig->cputimer.lock); + raw_spin_lock_irqsave(&sig->cputimer.lock, flags); group_sample = sig->cputimer.cputime; - raw_spin_unlock(&sig->cputimer.lock); + raw_spin_unlock_irqrestore(&sig->cputimer.lock, flags); if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; @@ -1309,13 +1311,13 @@ static inline int fastpath_timer_check(struct task_struct *tsk) * already updated our counts. We need to check if any timers fire now. * Interrupts are disabled. */ -void run_posix_cpu_timers(struct task_struct *tsk) +static void __run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; unsigned long flags; - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); /* * The fast path checks that there are no expired thread or thread @@ -1380,6 +1382,190 @@ void run_posix_cpu_timers(struct task_struct *tsk) posix_cpu_timer_kick_nohz(); } +#ifdef CONFIG_PREEMPT_RT_BASE +#include +#include +DEFINE_PER_CPU(struct task_struct *, posix_timer_task); +DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); + +static int posix_cpu_timers_thread(void *data) +{ + int cpu = (long)data; + + BUG_ON(per_cpu(posix_timer_task,cpu) != current); + + while (!kthread_should_stop()) { + struct task_struct *tsk = NULL; + struct task_struct *next = NULL; + + if (cpu_is_offline(cpu)) + goto wait_to_die; + + /* grab task list */ + raw_local_irq_disable(); + tsk = per_cpu(posix_timer_tasklist, cpu); + per_cpu(posix_timer_tasklist, cpu) = NULL; + raw_local_irq_enable(); + + /* its possible the list is empty, just return */ + if (!tsk) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + __set_current_state(TASK_RUNNING); + continue; + } + + /* Process task list */ + while (1) { + /* save next */ + next = tsk->posix_timer_list; + + /* run the task timers, clear its ptr and + * unreference it + */ + __run_posix_cpu_timers(tsk); + tsk->posix_timer_list = NULL; + put_task_struct(tsk); + + /* check if this is the last on the list */ + if (next == tsk) + break; + tsk = next; + } + } + return 0; + +wait_to_die: + /* Wait for kthread_stop */ + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +static inline int __fastpath_timer_check(struct task_struct *tsk) +{ + /* tsk == current, ensure it is safe to use ->signal/sighand */ + if (unlikely(tsk->exit_state)) + return 0; + + if (!task_cputime_zero(&tsk->cputime_expires)) + return 1; + + if (!task_cputime_zero(&tsk->signal->cputime_expires)) + return 1; + + return 0; +} + +void run_posix_cpu_timers(struct task_struct *tsk) +{ + unsigned long cpu = smp_processor_id(); + struct task_struct *tasklist; + + BUG_ON(!irqs_disabled()); + if(!per_cpu(posix_timer_task, cpu)) + return; + /* get per-cpu references */ + tasklist = per_cpu(posix_timer_tasklist, cpu); + + /* check to see if we're already queued */ + if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { + get_task_struct(tsk); + if (tasklist) { + tsk->posix_timer_list = tasklist; + } else { + /* + * The list is terminated by a self-pointing + * task_struct + */ + tsk->posix_timer_list = tsk; + } + per_cpu(posix_timer_tasklist, cpu) = tsk; + + wake_up_process(per_cpu(posix_timer_task, cpu)); + } +} + +/* + * posix_cpu_thread_call - callback that gets triggered when a CPU is added. + * Here we can start up the necessary migration thread for the new CPU. + */ +static int posix_cpu_thread_call(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + struct task_struct *p; + struct sched_param param; + + switch (action) { + case CPU_UP_PREPARE: + p = kthread_create(posix_cpu_timers_thread, hcpu, + "posixcputmr/%d",cpu); + if (IS_ERR(p)) + return NOTIFY_BAD; + p->flags |= PF_NOFREEZE; + kthread_bind(p, cpu); + /* Must be high prio to avoid getting starved */ + param.sched_priority = MAX_RT_PRIO-1; + sched_setscheduler(p, SCHED_FIFO, ¶m); + per_cpu(posix_timer_task,cpu) = p; + break; + case CPU_ONLINE: + /* Strictly unneccessary, as first user will wake it. */ + wake_up_process(per_cpu(posix_timer_task,cpu)); + break; +#ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + /* Unbind it from offline cpu so it can run. Fall thru. */ + kthread_bind(per_cpu(posix_timer_task, cpu), + cpumask_any(cpu_online_mask)); + kthread_stop(per_cpu(posix_timer_task,cpu)); + per_cpu(posix_timer_task,cpu) = NULL; + break; + case CPU_DEAD: + kthread_stop(per_cpu(posix_timer_task,cpu)); + per_cpu(posix_timer_task,cpu) = NULL; + break; +#endif + } + return NOTIFY_OK; +} + +/* Register at highest priority so that task migration (migrate_all_tasks) + * happens before everything else. + */ +static struct notifier_block posix_cpu_thread_notifier = { + .notifier_call = posix_cpu_thread_call, + .priority = 10 +}; + +static int __init posix_cpu_thread_init(void) +{ + void *hcpu = (void *)(long)smp_processor_id(); + /* Start one for boot CPU. */ + unsigned long cpu; + + /* init the per-cpu posix_timer_tasklets */ + for_each_possible_cpu(cpu) + per_cpu(posix_timer_tasklist, cpu) = NULL; + + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu); + posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu); + register_cpu_notifier(&posix_cpu_thread_notifier); + return 0; +} +early_initcall(posix_cpu_thread_init); +#else /* CONFIG_PREEMPT_RT_BASE */ +void run_posix_cpu_timers(struct task_struct *tsk) +{ + __run_posix_cpu_timers(tsk); +} +#endif /* CONFIG_PREEMPT_RT_BASE */ + /* * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller. diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 424c2d4..a22b931 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -497,6 +497,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) static struct pid *good_sigevent(sigevent_t * event) { struct task_struct *rtn = current->group_leader; + int sig = event->sigev_signo; if ((event->sigev_notify & SIGEV_THREAD_ID ) && (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || @@ -505,7 +506,8 @@ static struct pid *good_sigevent(sigevent_t * event) return NULL; if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && - ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) + (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) || + sig_kernel_coredump(sig))) return NULL; return task_pid(rtn); @@ -816,6 +818,20 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) return overrun; } +/* + * Protected by RCU! + */ +static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr) +{ +#ifdef CONFIG_PREEMPT_RT_FULL + if (kc->timer_set == common_timer_set) + hrtimer_wait_for_timer(&timr->it.real.timer); + else + /* FIXME: Whacky hack for posix-cpu-timers */ + schedule_timeout(1); +#endif +} + /* Set a POSIX.1b interval timer. */ /* timr->it_lock is taken. */ static int @@ -893,6 +909,7 @@ retry: if (!timr) return -EINVAL; + rcu_read_lock(); kc = clockid_to_kclock(timr->it_clock); if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; @@ -901,9 +918,12 @@ retry: unlock_timer(timr, flag); if (error == TIMER_RETRY) { + timer_wait_for_callback(kc, timr); rtn = NULL; // We already got the old time... + rcu_read_unlock(); goto retry; } + rcu_read_unlock(); if (old_setting && !error && copy_to_user(old_setting, &old_spec, sizeof (old_spec))) @@ -941,10 +961,15 @@ retry_delete: if (!timer) return -EINVAL; + rcu_read_lock(); if (timer_delete_hook(timer) == TIMER_RETRY) { unlock_timer(timer, flags); + timer_wait_for_callback(clockid_to_kclock(timer->it_clock), + timer); + rcu_read_unlock(); goto retry_delete; } + rcu_read_unlock(); spin_lock(¤t->sighand->siglock); list_del(&timer->list); @@ -970,8 +995,18 @@ static void itimer_delete(struct k_itimer *timer) retry_delete: spin_lock_irqsave(&timer->it_lock, flags); + /* On RT we can race with a deletion */ + if (!timer->it_signal) { + unlock_timer(timer, flags); + return; + } + if (timer_delete_hook(timer) == TIMER_RETRY) { + rcu_read_lock(); unlock_timer(timer, flags); + timer_wait_for_callback(clockid_to_kclock(timer->it_clock), + timer); + rcu_read_unlock(); goto retry_delete; } list_del(&timer->list); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index b26f5f1..3321e2b 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -275,6 +275,8 @@ static int create_image(int platform_mode) local_irq_disable(); + system_state = SYSTEM_SUSPEND; + error = syscore_suspend(); if (error) { printk(KERN_ERR "PM: Some system devices failed to power down, " @@ -302,6 +304,7 @@ static int create_image(int platform_mode) syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -427,6 +430,7 @@ static int resume_target_kernel(bool platform_mode) goto Enable_cpus; local_irq_disable(); + system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) @@ -460,6 +464,7 @@ static int resume_target_kernel(bool platform_mode) syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -542,6 +547,7 @@ int hibernation_platform_enter(void) goto Platform_finish; local_irq_disable(); + system_state = SYSTEM_SUSPEND; syscore_suspend(); if (pm_wakeup_pending()) { error = -EAGAIN; @@ -554,6 +560,7 @@ int hibernation_platform_enter(void) Power_up: syscore_resume(); + system_state = SYSTEM_RUNNING; local_irq_enable(); enable_nonboot_cpus(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index bef86d1..dc19265 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -217,6 +217,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) arch_suspend_disable_irqs(); BUG_ON(!irqs_disabled()); + system_state = SYSTEM_SUSPEND; + error = syscore_suspend(); if (!error) { *wakeup = pm_wakeup_pending(); @@ -227,6 +229,8 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) syscore_resume(); } + system_state = SYSTEM_RUNNING; + arch_suspend_enable_irqs(); BUG_ON(irqs_disabled()); diff --git a/kernel/printk.c b/kernel/printk.c index d37d45c..f462a4e 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1034,6 +1034,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) { char *text; int len = 0; + int attempts = 0; text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); if (!text) @@ -1045,7 +1046,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) u64 seq; u32 idx; enum log_flags prev; - + int num_msg; +try_again: + attempts++; + if (attempts > 10) { + len = -EBUSY; + goto out; + } + num_msg = 0; if (clear_seq < log_first_seq) { /* messages are gone, move to first available one */ clear_seq = log_first_seq; @@ -1066,6 +1074,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) prev = msg->flags; idx = log_next(idx); seq++; + num_msg++; + if (num_msg > 5) { + num_msg = 0; + raw_spin_unlock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); + if (clear_seq < log_first_seq) + goto try_again; + } } /* move first record forward until length fits into the buffer */ @@ -1079,6 +1095,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear) prev = msg->flags; idx = log_next(idx); seq++; + num_msg++; + if (num_msg > 5) { + num_msg = 0; + raw_spin_unlock_irq(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); + if (clear_seq < log_first_seq) + goto try_again; + } } /* last message fitting into this dump */ @@ -1120,6 +1144,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) clear_seq = log_next_seq; clear_idx = log_next_idx; } +out: raw_spin_unlock_irq(&logbuf_lock); kfree(text); @@ -1277,6 +1302,7 @@ static void call_console_drivers(int level, const char *text, size_t len) if (!console_drivers) return; + migrate_disable(); for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; @@ -1289,6 +1315,7 @@ static void call_console_drivers(int level, const char *text, size_t len) continue; con->write(con, text, len); } + migrate_enable(); } /* @@ -1348,12 +1375,18 @@ static inline int can_use_console(unsigned int cpu) * interrupts disabled. It should return with 'lockbuf_lock' * released but interrupts still disabled. */ -static int console_trylock_for_printk(unsigned int cpu) +static int console_trylock_for_printk(unsigned int cpu, unsigned long flags) __releases(&logbuf_lock) { int retval = 0, wake = 0; +#ifdef CONFIG_PREEMPT_RT_FULL + int lock = !early_boot_irqs_disabled && !irqs_disabled_flags(flags) && + (preempt_count() <= 1); +#else + int lock = 1; +#endif - if (console_trylock()) { + if (lock && console_trylock()) { retval = 1; /* @@ -1493,6 +1526,62 @@ static size_t cont_print_text(char *text, size_t size) return textlen; } +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +void early_vprintk(const char *fmt, va_list ap) +{ + if (early_console) { + char buf[512]; + int n = vscnprintf(buf, sizeof(buf), fmt, ap); + + early_console->write(early_console, buf, n); + } +} + +asmlinkage void early_printk(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + early_vprintk(fmt, ap); + va_end(ap); +} + +/* + * This is independent of any log levels - a global + * kill switch that turns off all of printk. + * + * Used by the NMI watchdog if early-printk is enabled. + */ +static bool __read_mostly printk_killswitch; + +static int __init force_early_printk_setup(char *str) +{ + printk_killswitch = true; + return 0; +} +early_param("force_early_printk", force_early_printk_setup); + +void printk_kill(void) +{ + printk_killswitch = true; +} + +static int forced_early_printk(const char *fmt, va_list ap) +{ + if (!printk_killswitch) + return 0; + early_vprintk(fmt, ap); + return 1; +} +#else +static inline int forced_early_printk(const char *fmt, va_list ap) +{ + return 0; +} +#endif + asmlinkage int vprintk_emit(int facility, int level, const char *dict, size_t dictlen, const char *fmt, va_list args) @@ -1506,6 +1595,13 @@ asmlinkage int vprintk_emit(int facility, int level, int this_cpu; int printed_len = 0; + /* + * Fall back to early_printk if a debugging subsystem has + * killed printk output + */ + if (unlikely(forced_early_printk(fmt, args))) + return 1; + boot_delay_msec(level); printk_delay(); @@ -1625,8 +1721,15 @@ asmlinkage int vprintk_emit(int facility, int level, * The console_trylock_for_printk() function will release 'logbuf_lock' * regardless of whether it actually gets the console semaphore or not. */ - if (console_trylock_for_printk(this_cpu)) + if (console_trylock_for_printk(this_cpu, flags)) { +#ifndef CONFIG_PREEMPT_RT_FULL console_unlock(); +#else + raw_local_irq_restore(flags); + console_unlock(); + raw_local_irq_save(flags); +#endif + } lockdep_on(); out_restore_irqs: @@ -1728,29 +1831,6 @@ static size_t cont_print_text(char *text, size_t size) { return 0; } #endif /* CONFIG_PRINTK */ -#ifdef CONFIG_EARLY_PRINTK -struct console *early_console; - -void early_vprintk(const char *fmt, va_list ap) -{ - if (early_console) { - char buf[512]; - int n = vscnprintf(buf, sizeof(buf), fmt, ap); - - early_console->write(early_console, buf, n); - } -} - -asmlinkage void early_printk(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - early_vprintk(fmt, ap); - va_end(ap); -} -#endif - static int __add_preferred_console(char *name, int idx, char *options, char *brl_options) { @@ -2003,11 +2083,16 @@ static void console_cont_flush(char *text, size_t size) goto out; len = cont_print_text(text, size); +#ifndef CONFIG_PREEMPT_RT_FULL raw_spin_unlock(&logbuf_lock); stop_critical_timings(); call_console_drivers(cont.level, text, len); start_critical_timings(); local_irq_restore(flags); +#else + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + call_console_drivers(cont.level, text, len); +#endif return; out: raw_spin_unlock_irqrestore(&logbuf_lock, flags); @@ -2090,12 +2175,17 @@ skip: console_idx = log_next(console_idx); console_seq++; console_prev = msg->flags; - raw_spin_unlock(&logbuf_lock); +#ifndef CONFIG_PREEMPT_RT_FULL + raw_spin_unlock(&logbuf_lock); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(level, text, len); start_critical_timings(); local_irq_restore(flags); +#else + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + call_console_drivers(level, text, len); +#endif } console_locked = 0; mutex_release(&console_lock_dep_map, 1, _RET_IP_); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 48ab703..fdc0945 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -156,6 +156,7 @@ int debug_lockdep_rcu_enabled(void) } EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? * @@ -182,6 +183,7 @@ int rcu_read_lock_bh_held(void) return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); +#endif #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index a0714a5..c3f39bb 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -373,6 +373,7 @@ void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Post an RCU bottom-half callback to be invoked after any subsequent * quiescent state. @@ -382,3 +383,4 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) __call_rcu(head, func, &rcu_bh_ctrlblk); } EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 8a23300..859ff35 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -26,6 +26,7 @@ #include #include #include +#include /* Global control variables for rcupdate callback mechanism. */ struct rcu_ctrlblk { @@ -308,7 +309,7 @@ static void show_tiny_preempt_stats(struct seq_file *m) /* Controls for rcu_kthread() kthread. */ static struct task_struct *rcu_kthread_task; -static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq); +static DEFINE_SWAIT_HEAD(rcu_kthread_wq); static unsigned long have_rcu_kthread_work; /* @@ -609,7 +610,7 @@ void rcu_read_unlock_special(struct task_struct *t) rcu_preempt_cpu_qs(); /* Hardware IRQ handlers cannot block. */ - if (in_irq() || in_serving_softirq()) { + if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { local_irq_restore(flags); return; } @@ -762,7 +763,7 @@ void synchronize_rcu(void) } EXPORT_SYMBOL_GPL(synchronize_rcu); -static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); +static DEFINE_SWAIT_HEAD(sync_rcu_preempt_exp_wq); static unsigned long sync_rcu_preempt_exp_count; static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); @@ -784,7 +785,7 @@ static int rcu_preempted_readers_exp(void) */ static void rcu_report_exp_done(void) { - wake_up(&sync_rcu_preempt_exp_wq); + swait_wake(&sync_rcu_preempt_exp_wq); } /* @@ -836,8 +837,8 @@ void synchronize_rcu_expedited(void) } else { rcu_initiate_boost(); local_irq_restore(flags); - wait_event(sync_rcu_preempt_exp_wq, - !rcu_preempted_readers_exp()); + swait_event(sync_rcu_preempt_exp_wq, + !rcu_preempted_readers_exp()); } /* Clean up and exit. */ @@ -907,7 +908,7 @@ static void invoke_rcu_callbacks(void) { have_rcu_kthread_work = 1; if (rcu_kthread_task != NULL) - wake_up(&rcu_kthread_wq); + swait_wake(&rcu_kthread_wq); } #ifdef CONFIG_RCU_TRACE @@ -937,8 +938,8 @@ static int rcu_kthread(void *arg) unsigned long flags; for (;;) { - wait_event_interruptible(rcu_kthread_wq, - have_rcu_kthread_work != 0); + swait_event_interruptible(rcu_kthread_wq, + have_rcu_kthread_work != 0); morework = rcu_boost(); local_irq_save(flags); work = have_rcu_kthread_work; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 3538001..55915b1 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -182,6 +182,14 @@ void rcu_sched_qs(int cpu) rdp->passed_quiesce = 1; } +#ifdef CONFIG_PREEMPT_RT_FULL +static void rcu_preempt_qs(int cpu); + +void rcu_bh_qs(int cpu) +{ + rcu_preempt_qs(cpu); +} +#else void rcu_bh_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); @@ -190,6 +198,7 @@ void rcu_bh_qs(int cpu) trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs"); rdp->passed_quiesce = 1; } +#endif /* * Note a context switch. This is a quiescent state for RCU-sched, @@ -239,6 +248,7 @@ long rcu_batches_completed_sched(void) } EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Return the number of RCU BH batches processed thus far for debug & stats. */ @@ -256,6 +266,7 @@ void rcu_bh_force_quiescent_state(void) force_quiescent_state(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); +#endif /* * Record the number of times rcutorture tests have been initiated and @@ -1561,7 +1572,7 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Handle grace-period start. */ for (;;) { - wait_event_interruptible(rsp->gp_wq, + swait_event_interruptible(rsp->gp_wq, rsp->gp_flags & RCU_GP_FLAG_INIT); if ((rsp->gp_flags & RCU_GP_FLAG_INIT) && @@ -1580,7 +1591,7 @@ static int __noreturn rcu_gp_kthread(void *arg) } for (;;) { rsp->jiffies_force_qs = jiffies + j; - ret = wait_event_interruptible_timeout(rsp->gp_wq, + ret = swait_event_interruptible_timeout(rsp->gp_wq, (rsp->gp_flags & RCU_GP_FLAG_FQS) || (!ACCESS_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)), @@ -1618,7 +1629,7 @@ static void rsp_wakeup(struct irq_work *work) struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); + swait_wake(&rsp->gp_wq); } /* @@ -1690,7 +1701,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + swait_wake(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ } /* @@ -2255,7 +2266,8 @@ static void force_quiescent_state(struct rcu_state *rsp) } rsp->gp_flags |= RCU_GP_FLAG_FQS; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); - wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ + /* Memory barrier implied by wake_up() path. */ + swait_wake(&rsp->gp_wq); } /* @@ -2448,6 +2460,7 @@ void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /* * Queue an RCU callback for invocation after a quicker grace period. */ @@ -2456,6 +2469,7 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) __call_rcu(head, func, &rcu_bh_state, -1, 0); } EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif /* * Because a context switch is a grace period for RCU-sched and RCU-bh, @@ -2533,6 +2547,7 @@ void synchronize_sched(void) } EXPORT_SYMBOL_GPL(synchronize_sched); +#ifndef CONFIG_PREEMPT_RT_FULL /** * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. * @@ -2559,6 +2574,7 @@ void synchronize_rcu_bh(void) wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +#endif static int synchronize_sched_expedited_cpu_stop(void *data) { @@ -2955,6 +2971,7 @@ static void _rcu_barrier(struct rcu_state *rsp) mutex_unlock(&rsp->barrier_mutex); } +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. */ @@ -2963,6 +2980,7 @@ void rcu_barrier_bh(void) _rcu_barrier(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); +#endif /** * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. @@ -3246,7 +3264,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, } rsp->rda = rda; - init_waitqueue_head(&rsp->gp_wq); + init_swait_head(&rsp->gp_wq); init_irq_work(&rsp->wakeup_work, rsp_wakeup); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 4df5034..8491f47 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -28,6 +28,7 @@ #include #include #include +#include /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -190,7 +191,7 @@ struct rcu_node { /* This can happen due to race conditions. */ #endif /* #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_NOCB_CPU - wait_queue_head_t nocb_gp_wq[2]; + struct swait_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ int need_future_gp[2]; @@ -323,7 +324,7 @@ struct rcu_data { atomic_long_t nocb_q_count_lazy; /* (approximate). */ int nocb_p_count; /* # CBs being invoked by kthread */ int nocb_p_count_lazy; /* (approximate). */ - wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ + struct swait_head nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ @@ -388,7 +389,7 @@ struct rcu_state { unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ - wait_queue_head_t gp_wq; /* Where GP task waits. */ + struct swait_head gp_wq; /* Where GP task waits. */ int gp_flags; /* Commands for GP task. */ /* End of fields guarded by root rcu_node's lock. */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 3db5a37..dc0c4b2 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -362,7 +362,7 @@ void rcu_read_unlock_special(struct task_struct *t) } /* Hardware IRQ handlers cannot block. */ - if (in_irq() || in_serving_softirq()) { + if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { local_irq_restore(flags); return; } @@ -1530,7 +1530,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu) #endif /* #else #ifdef CONFIG_RCU_BOOST */ -#if !defined(CONFIG_RCU_FAST_NO_HZ) +#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) /* * Check to see if any future RCU-related work will need to be done @@ -1546,6 +1546,9 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) *delta_jiffies = ULONG_MAX; return rcu_cpu_has_callbacks(cpu, NULL); } +#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ + +#if !defined(CONFIG_RCU_FAST_NO_HZ) /* * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up @@ -1637,6 +1640,8 @@ static bool rcu_try_advance_all_cbs(void) return cbs_ready; } +#ifndef CONFIG_PREEMPT_RT_FULL + /* * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready * to invoke. If the CPU has callbacks, try to advance them. Tell the @@ -1675,6 +1680,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj) } return 0; } +#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ /* * Prepare a CPU for idle from an RCU perspective. The first major task @@ -2030,7 +2036,7 @@ static int rcu_nocb_needs_gp(struct rcu_state *rsp) */ static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) { - wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + swait_wake_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); } /* @@ -2048,8 +2054,8 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) static void rcu_init_one_nocb(struct rcu_node *rnp) { - init_waitqueue_head(&rnp->nocb_gp_wq[0]); - init_waitqueue_head(&rnp->nocb_gp_wq[1]); + init_swait_head(&rnp->nocb_gp_wq[0]); + init_swait_head(&rnp->nocb_gp_wq[1]); } /* Is the specified CPU a no-CPUs CPU? */ @@ -2089,7 +2095,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, return; len = atomic_long_read(&rdp->nocb_q_count); if (old_rhpp == &rdp->nocb_head) { - wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */ + swait_wake(&rdp->nocb_wq); /* ... only if queue was empty ... */ rdp->qlen_last_fqs_check = 0; } else if (len > rdp->qlen_last_fqs_check + qhimark) { wake_up_process(t); /* ... or if many callbacks queued. */ @@ -2179,7 +2185,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_future_gp(rnp, rdp, c, "StartWait"); for (;;) { - wait_event_interruptible( + swait_event_interruptible( rnp->nocb_gp_wq[c & 0x1], (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c))); if (likely(d)) @@ -2207,7 +2213,7 @@ static int rcu_nocb_kthread(void *arg) for (;;) { /* If not polling, wait for next batch of callbacks. */ if (!rcu_nocb_poll) - wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head); + swait_event_interruptible(rdp->nocb_wq, rdp->nocb_head); list = ACCESS_ONCE(rdp->nocb_head); if (!list) { schedule_timeout_interruptible(1); @@ -2257,7 +2263,7 @@ static int rcu_nocb_kthread(void *arg) static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { rdp->nocb_tail = &rdp->nocb_head; - init_waitqueue_head(&rdp->nocb_wq); + init_swait_head(&rdp->nocb_wq); } /* Create a kthread for each RCU flavor for each no-CBs CPU. */ diff --git a/kernel/relay.c b/kernel/relay.c index b91488b..e03440b 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -339,6 +339,10 @@ static void wakeup_readers(unsigned long data) { struct rchan_buf *buf = (struct rchan_buf *)data; wake_up_interruptible(&buf->read_wait); + /* + * Stupid polling for now: + */ + mod_timer(&buf->timer, jiffies + 1); } /** @@ -356,6 +360,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init) init_waitqueue_head(&buf->read_wait); kref_init(&buf->kref); setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); + mod_timer(&buf->timer, jiffies + 1); } else del_timer_sync(&buf->timer); @@ -739,15 +744,6 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) else buf->early_bytes += buf->chan->subbuf_size - buf->padding[old_subbuf]; - smp_mb(); - if (waitqueue_active(&buf->read_wait)) - /* - * Calling wake_up_interruptible() from here - * will deadlock if we happen to be logging - * from the scheduler (trying to re-grab - * rq->lock), so defer it. - */ - mod_timer(&buf->timer, jiffies + 1); } old = buf->data; diff --git a/kernel/res_counter.c b/kernel/res_counter.c index ff55247..cfecbee 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -49,7 +49,7 @@ static int __res_counter_charge(struct res_counter *counter, unsigned long val, r = ret = 0; *limit_fail_at = NULL; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); r = res_counter_charge_locked(c, val, force); @@ -69,7 +69,7 @@ static int __res_counter_charge(struct res_counter *counter, unsigned long val, spin_unlock(&u->lock); } } - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } @@ -103,7 +103,7 @@ u64 res_counter_uncharge_until(struct res_counter *counter, struct res_counter *c; u64 ret = 0; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != top; c = c->parent) { u64 r; spin_lock(&c->lock); @@ -112,7 +112,7 @@ u64 res_counter_uncharge_until(struct res_counter *counter, ret = r; spin_unlock(&c->lock); } - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } diff --git a/kernel/rt.c b/kernel/rt.c new file mode 100644 index 0000000..433ae42 --- /dev/null +++ b/kernel/rt.c @@ -0,0 +1,453 @@ +/* + * kernel/rt.c + * + * Real-Time Preemption Support + * + * started by Ingo Molnar: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * + * historic credit for proving that Linux spinlocks can be implemented via + * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow + * and others) who prototyped it on 2.4 and did lots of comparative + * research and analysis; TimeSys, for proving that you can implement a + * fully preemptible kernel via the use of IRQ threading and mutexes; + * Bill Huey for persuasively arguing on lkml that the mutex model is the + * right one; and to MontaVista, who ported pmutexes to 2.6. + * + * This code is a from-scratch implementation and is not based on pmutexes, + * but the idea of converting spinlocks to mutexes is used here too. + * + * lock debugging, locking tree, deadlock detection: + * + * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey + * Released under the General Public License (GPL). + * + * Includes portions of the generic R/W semaphore implementation from: + * + * Copyright (c) 2001 David Howells (dhowells@redhat.com). + * - Derived partially from idea by Andrea Arcangeli + * - Derived also from comments by Linus + * + * Pending ownership of locks and ownership stealing: + * + * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt + * + * (also by Steven Rostedt) + * - Converted single pi_lock to individual task locks. + * + * By Esben Nielsen: + * Doing priority inheritance with help of the scheduler. + * + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner + * - major rework based on Esben Nielsens initial patch + * - replaced thread_info references by task_struct refs + * - removed task->pending_owner dependency + * - BKL drop/reacquire for semaphore style locks to avoid deadlocks + * in the scheduler return path as discussed with Steven Rostedt + * + * Copyright (C) 2006, Kihon Technologies Inc. + * Steven Rostedt + * - debugged and patched Thomas Gleixner's rework. + * - added back the cmpxchg to the rework. + * - turned atomic require back on for SMP. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rtmutex_common.h" + +/* + * struct mutex functions + */ +void __mutex_do_init(struct mutex *mutex, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); + lockdep_init_map(&mutex->dep_map, name, key, 0); +#endif + mutex->lock.save_state = 0; +} +EXPORT_SYMBOL(__mutex_do_init); + +void __lockfunc _mutex_lock(struct mutex *lock) +{ + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock); + +int __lockfunc _mutex_lock_interruptible(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_lock_interruptible(&lock->lock, 0); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible); + +int __lockfunc _mutex_lock_killable(struct mutex *lock) +{ + int ret; + + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_lock_killable(&lock->lock, 0); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) +{ + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock_nested); + +void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) +{ + mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); + rt_mutex_lock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_lock_nest_lock); + +int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); + ret = rt_mutex_lock_interruptible(&lock->lock, 0); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_interruptible_nested); + +int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) +{ + int ret; + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + ret = rt_mutex_lock_killable(&lock->lock, 0); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(_mutex_lock_killable_nested); +#endif + +int __lockfunc _mutex_trylock(struct mutex *lock) +{ + int ret = rt_mutex_trylock(&lock->lock); + + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL(_mutex_trylock); + +void __lockfunc _mutex_unlock(struct mutex *lock) +{ + mutex_release(&lock->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&lock->lock); +} +EXPORT_SYMBOL(_mutex_unlock); + +/* + * rwlock_t functions + */ +int __lockfunc rt_write_trylock(rwlock_t *rwlock) +{ + int ret = rt_mutex_trylock(&rwlock->lock); + + migrate_disable(); + if (ret) + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + else + migrate_enable(); + + return ret; +} +EXPORT_SYMBOL(rt_write_trylock); + +int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags) +{ + int ret; + + *flags = 0; + migrate_disable(); + ret = rt_write_trylock(rwlock); + if (!ret) + migrate_enable(); + return ret; +} +EXPORT_SYMBOL(rt_write_trylock_irqsave); + +int __lockfunc rt_read_trylock(rwlock_t *rwlock) +{ + struct rt_mutex *lock = &rwlock->lock; + int ret = 1; + + /* + * recursive read locks succeed when current owns the lock, + * but not when read_depth == 0 which means that the lock is + * write locked. + */ + migrate_disable(); + if (rt_mutex_owner(lock) != current) { + ret = rt_mutex_trylock(lock); + if (ret) + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); + } else if (!rwlock->read_depth) { + ret = 0; + } + + if (ret) + rwlock->read_depth++; + else + migrate_enable(); + + return ret; +} +EXPORT_SYMBOL(rt_read_trylock); + +void __lockfunc rt_write_lock(rwlock_t *rwlock) +{ + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + __rt_spin_lock(&rwlock->lock); +} +EXPORT_SYMBOL(rt_write_lock); + +void __lockfunc rt_read_lock(rwlock_t *rwlock) +{ + struct rt_mutex *lock = &rwlock->lock; + + /* + * recursive read locks succeed when current owns the lock + */ + if (rt_mutex_owner(lock) != current) { + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + __rt_spin_lock(lock); + } + rwlock->read_depth++; +} + +EXPORT_SYMBOL(rt_read_lock); + +void __lockfunc rt_write_unlock(rwlock_t *rwlock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + __rt_spin_unlock(&rwlock->lock); +} +EXPORT_SYMBOL(rt_write_unlock); + +void __lockfunc rt_read_unlock(rwlock_t *rwlock) +{ + /* Release the lock only when read_depth is down to 0 */ + if (--rwlock->read_depth == 0) { + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + __rt_spin_unlock(&rwlock->lock); + } +} +EXPORT_SYMBOL(rt_read_unlock); + +unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock) +{ + rt_write_lock(rwlock); + + return 0; +} +EXPORT_SYMBOL(rt_write_lock_irqsave); + +unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock) +{ + rt_read_lock(rwlock); + + return 0; +} +EXPORT_SYMBOL(rt_read_lock_irqsave); + +void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); + lockdep_init_map(&rwlock->dep_map, name, key, 0); +#endif + rwlock->lock.save_state = 1; + rwlock->read_depth = 0; +} +EXPORT_SYMBOL(__rt_rwlock_init); + +/* + * rw_semaphores + */ + +void rt_up_write(struct rw_semaphore *rwsem) +{ + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_up_write); + +void rt_up_read(struct rw_semaphore *rwsem) +{ + if (--rwsem->read_depth == 0) { + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + rt_mutex_unlock(&rwsem->lock); + } +} +EXPORT_SYMBOL(rt_up_read); + +/* + * downgrade a write lock into a read lock + * - just wake up any readers at the front of the queue + */ +void rt_downgrade_write(struct rw_semaphore *rwsem) +{ + BUG_ON(rt_mutex_owner(&rwsem->lock) != current); + rwsem->read_depth = 1; +} +EXPORT_SYMBOL(rt_downgrade_write); + +int rt_down_write_trylock(struct rw_semaphore *rwsem) +{ + int ret = rt_mutex_trylock(&rwsem->lock); + + if (ret) + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(rt_down_write_trylock); + +void rt_down_write(struct rw_semaphore *rwsem) +{ + rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_down_write); + +void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass) +{ + rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} +EXPORT_SYMBOL(rt_down_write_nested); + +void rt_down_write_nested_lock(struct rw_semaphore *rwsem, + struct lockdep_map *nest) +{ + rwsem_acquire_nest(&rwsem->dep_map, 0, 0, nest, _RET_IP_); + rt_mutex_lock(&rwsem->lock); +} + +int rt_down_read_trylock(struct rw_semaphore *rwsem) +{ + struct rt_mutex *lock = &rwsem->lock; + int ret = 1; + + /* + * recursive read locks succeed when current owns the rwsem, + * but not when read_depth == 0 which means that the rwsem is + * write locked. + */ + if (rt_mutex_owner(lock) != current) { + ret = rt_mutex_trylock(&rwsem->lock); + if (ret) + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); + } else if (!rwsem->read_depth) { + ret = 0; + } + + if (ret) + rwsem->read_depth++; + return ret; +} +EXPORT_SYMBOL(rt_down_read_trylock); + +static void __rt_down_read(struct rw_semaphore *rwsem, int subclass) +{ + struct rt_mutex *lock = &rwsem->lock; + + if (rt_mutex_owner(lock) != current) { + rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); + rt_mutex_lock(&rwsem->lock); + } + rwsem->read_depth++; +} + +void rt_down_read(struct rw_semaphore *rwsem) +{ + __rt_down_read(rwsem, 0); +} +EXPORT_SYMBOL(rt_down_read); + +void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass) +{ + __rt_down_read(rwsem, subclass); +} +EXPORT_SYMBOL(rt_down_read_nested); + +void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem)); + lockdep_init_map(&rwsem->dep_map, name, key, 0); +#endif + rwsem->read_depth = 0; + rwsem->lock.save_state = 0; +} +EXPORT_SYMBOL(__rt_rwsem_init); + +/** + * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 + * @cnt: the atomic which we are to dec + * @lock: the mutex to return holding if we dec to 0 + * + * return true and hold lock if we dec to 0, return false otherwise + */ +int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) +{ + /* dec if we can't possibly hit 0 */ + if (atomic_add_unless(cnt, -1, 1)) + return 0; + /* we might hit 0, so take the lock */ + mutex_lock(lock); + if (!atomic_dec_and_test(cnt)) { + /* when we actually did the dec, we didn't hit 0 */ + mutex_unlock(lock); + return 0; + } + /* we hit 0, and we hold the lock */ + return 1; +} +EXPORT_SYMBOL(atomic_dec_and_mutex_lock); diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index 1e09308..0a64a90 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -8,6 +8,12 @@ * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt * Copyright (C) 2006 Esben Nielsen * + * Adaptive Spinlocks: + * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, + * and Peter Morreale, + * Adaptive Spinlocks simplification: + * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt + * * See Documentation/rt-mutex-design.txt for details. */ #include @@ -68,6 +74,12 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) clear_rt_mutex_waiters(lock); } +static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) +{ + return waiter && waiter != PI_WAKEUP_INPROGRESS && + waiter != PI_REQUEUE_INPROGRESS; +} + /* * We can speed up the acquire/release, if the architecture * supports cmpxchg and if there's no debugging state to be set up @@ -91,6 +103,12 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) } #endif +static inline void init_lists(struct rt_mutex *lock) +{ + if (unlikely(!lock->wait_list.node_list.prev)) + plist_head_init(&lock->wait_list); +} + /* * Calculate task priority from the waiter list priority * @@ -107,6 +125,18 @@ int rt_mutex_getprio(struct task_struct *task) } /* + * Called by sched_setscheduler() to check whether the priority change + * is overruled by a possible priority boosting. + */ +int rt_mutex_check_prio(struct task_struct *task, int newprio) +{ + if (!task_has_pi_waiters(task)) + return 0; + + return task_top_pi_waiter(task)->pi_list_entry.prio <= newprio; +} + +/* * Adjust the priority of a task, after its pi_waiters got modified. * * This can be both boosting and unboosting. task->pi_lock must be held. @@ -137,6 +167,14 @@ static void rt_mutex_adjust_prio(struct task_struct *task) raw_spin_unlock_irqrestore(&task->pi_lock, flags); } +static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) +{ + if (waiter->savestate) + wake_up_lock_sleeper(waiter->task); + else + wake_up_process(waiter->task); +} + /* * Max number of times we'll walk the boosting chain: */ @@ -197,7 +235,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * reached or the state of the chain has changed while we * dropped the locks. */ - if (!waiter) + if (!rt_mutex_real_waiter(waiter)) goto out_unlock_pi; /* @@ -248,13 +286,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* Release the task */ raw_spin_unlock_irqrestore(&task->pi_lock, flags); if (!rt_mutex_owner(lock)) { + struct rt_mutex_waiter *lock_top_waiter; + /* * If the requeue above changed the top waiter, then we need * to wake the new top waiter up to try to get the lock. */ - - if (top_waiter != rt_mutex_top_waiter(lock)) - wake_up_process(rt_mutex_top_waiter(lock)->task); + lock_top_waiter = rt_mutex_top_waiter(lock); + if (top_waiter != lock_top_waiter) + rt_mutex_wake_waiter(lock_top_waiter); raw_spin_unlock(&lock->wait_lock); goto out_put_task; } @@ -299,6 +339,25 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, return ret; } + +#define STEAL_NORMAL 0 +#define STEAL_LATERAL 1 + +/* + * Note that RT tasks are excluded from lateral-steals to prevent the + * introduction of an unbounded latency + */ +static inline int lock_is_stealable(struct task_struct *task, + struct task_struct *pendowner, int mode) +{ + if (mode == STEAL_NORMAL || rt_task(task)) { + if (task->prio >= pendowner->prio) + return 0; + } else if (task->prio > pendowner->prio) + return 0; + return 1; +} + /* * Try to take an rt-mutex * @@ -308,8 +367,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * @task: the task which wants to acquire the lock * @waiter: the waiter that is queued to the lock's wait list. (could be NULL) */ -static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, - struct rt_mutex_waiter *waiter) +static int +__try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter, int mode) { /* * We have to be careful here if the atomic speedups are @@ -342,12 +402,14 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, * 3) it is top waiter */ if (rt_mutex_has_waiters(lock)) { - if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) { - if (!waiter || waiter != rt_mutex_top_waiter(lock)) - return 0; - } + struct task_struct *pown = rt_mutex_top_waiter(lock)->task; + + if (task != pown && !lock_is_stealable(task, pown, mode)) + return 0; } + /* We got the lock. */ + if (waiter || rt_mutex_has_waiters(lock)) { unsigned long flags; struct rt_mutex_waiter *top; @@ -372,7 +434,6 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, raw_spin_unlock_irqrestore(&task->pi_lock, flags); } - /* We got the lock. */ debug_rt_mutex_lock(lock); rt_mutex_set_owner(lock, task); @@ -382,6 +443,13 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, return 1; } +static inline int +try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) +{ + return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); +} + /* * Task blocks on lock. * @@ -400,6 +468,23 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, int chain_walk = 0, res; raw_spin_lock_irqsave(&task->pi_lock, flags); + + /* + * In the case of futex requeue PI, this will be a proxy + * lock. The task will wake unaware that it is enqueueed on + * this lock. Avoid blocking on two locks and corrupting + * pi_blocked_on via the PI_WAKEUP_INPROGRESS + * flag. futex_wait_requeue_pi() sets this when it wakes up + * before requeue (due to a signal or timeout). Do not enqueue + * the task if PI_WAKEUP_INPROGRESS is set. + */ + if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return -EAGAIN; + } + + BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); + __rt_mutex_adjust_prio(task); waiter->task = task; waiter->lock = lock; @@ -424,7 +509,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, plist_add(&waiter->pi_list_entry, &owner->pi_waiters); __rt_mutex_adjust_prio(owner); - if (owner->pi_blocked_on) + if (rt_mutex_real_waiter(owner->pi_blocked_on)) chain_walk = 1; raw_spin_unlock_irqrestore(&owner->pi_lock, flags); } @@ -479,7 +564,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock) raw_spin_unlock_irqrestore(¤t->pi_lock, flags); - wake_up_process(waiter->task); + rt_mutex_wake_waiter(waiter); } /* @@ -518,7 +603,7 @@ static void remove_waiter(struct rt_mutex *lock, } __rt_mutex_adjust_prio(owner); - if (owner->pi_blocked_on) + if (rt_mutex_real_waiter(owner->pi_blocked_on)) chain_walk = 1; raw_spin_unlock_irqrestore(&owner->pi_lock, flags); @@ -552,23 +637,338 @@ void rt_mutex_adjust_pi(struct task_struct *task) raw_spin_lock_irqsave(&task->pi_lock, flags); waiter = task->pi_blocked_on; - if (!waiter || waiter->list_entry.prio == task->prio) { + if (!rt_mutex_real_waiter(waiter) || + waiter->list_entry.prio == task->prio) { raw_spin_unlock_irqrestore(&task->pi_lock, flags); return; } - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(task); + raw_spin_unlock_irqrestore(&task->pi_lock, flags); rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task); } +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * preemptible spin_lock functions: + */ +static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + might_sleep(); + + if (likely(rt_mutex_cmpxchg(lock, NULL, current))) + rt_mutex_deadlock_account_lock(lock, current); + else + slowfn(lock); +} + +static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, + void (*slowfn)(struct rt_mutex *lock)) +{ + if (likely(rt_mutex_cmpxchg(lock, current, NULL))) + rt_mutex_deadlock_account_unlock(current); + else + slowfn(lock); +} + +#ifdef CONFIG_SMP +/* + * Note that owner is a speculative pointer and dereferencing relies + * on rcu_read_lock() and the check against the lock owner. + */ +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *owner) +{ + int res = 0; + + rcu_read_lock(); + for (;;) { + if (owner != rt_mutex_owner(lock)) + break; + /* + * Ensure that owner->on_cpu is dereferenced _after_ + * checking the above to be valid. + */ + barrier(); + if (!owner->on_cpu) { + res = 1; + break; + } + cpu_relax(); + } + rcu_read_unlock(); + return res; +} +#else +static int adaptive_wait(struct rt_mutex *lock, + struct task_struct *orig_owner) +{ + return 1; +} +#endif + +# define pi_lock(lock) raw_spin_lock_irq(lock) +# define pi_unlock(lock) raw_spin_unlock_irq(lock) + +/* + * Slow path lock function spin_lock style: this variant is very + * careful not to miss any non-lock wakeups. + * + * We store the current state under p->pi_lock in p->saved_state and + * the try_to_wake_up() code handles this accordingly. + */ +static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) +{ + struct task_struct *lock_owner, *self = current; + struct rt_mutex_waiter waiter, *top_waiter; + int ret; + + rt_mutex_init_waiter(&waiter, true); + + raw_spin_lock(&lock->wait_lock); + init_lists(lock); + + if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) { + raw_spin_unlock(&lock->wait_lock); + return; + } + + BUG_ON(rt_mutex_owner(lock) == self); + + /* + * We save whatever state the task is in and we'll restore it + * after acquiring the lock taking real wakeups into account + * as well. We are serialized via pi_lock against wakeups. See + * try_to_wake_up(). + */ + pi_lock(&self->pi_lock); + self->saved_state = self->state; + __set_current_state(TASK_UNINTERRUPTIBLE); + pi_unlock(&self->pi_lock); + + ret = task_blocks_on_rt_mutex(lock, &waiter, self, 0); + BUG_ON(ret); + + for (;;) { + /* Try to acquire the lock again. */ + if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL)) + break; + + top_waiter = rt_mutex_top_waiter(lock); + lock_owner = rt_mutex_owner(lock); + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(&waiter); + + if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) + schedule_rt_mutex(lock); + + raw_spin_lock(&lock->wait_lock); + + pi_lock(&self->pi_lock); + __set_current_state(TASK_UNINTERRUPTIBLE); + pi_unlock(&self->pi_lock); + } + + /* + * Restore the task state to current->saved_state. We set it + * to the original state above and the try_to_wake_up() code + * has possibly updated it when a real (non-rtmutex) wakeup + * happened while we were blocked. Clear saved_state so + * try_to_wakeup() does not get confused. + */ + pi_lock(&self->pi_lock); + __set_current_state(self->saved_state); + self->saved_state = TASK_RUNNING; + pi_unlock(&self->pi_lock); + + /* + * try_to_take_rt_mutex() sets the waiter bit + * unconditionally. We might have to fix that up: + */ + fixup_rt_mutex_waiters(lock); + + BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock)); + BUG_ON(!plist_node_empty(&waiter.list_entry)); + + raw_spin_unlock(&lock->wait_lock); + + debug_rt_mutex_free_waiter(&waiter); +} + +/* + * Slow path to release a rt_mutex spin_lock style + */ +static void __sched __rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + debug_rt_mutex_unlock(lock); + + rt_mutex_deadlock_account_unlock(current); + + if (!rt_mutex_has_waiters(lock)) { + lock->owner = NULL; + raw_spin_unlock(&lock->wait_lock); + return; + } + + wakeup_next_waiter(lock); + + raw_spin_unlock(&lock->wait_lock); + + /* Undo pi boosting.when necessary */ + rt_mutex_adjust_prio(current); +} + +static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + raw_spin_lock(&lock->wait_lock); + __rt_spin_lock_slowunlock(lock); +} + +static void noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock) +{ + int ret; + + do { + ret = raw_spin_trylock(&lock->wait_lock); + } while (!ret); + + __rt_spin_lock_slowunlock(lock); +} + +void __lockfunc rt_spin_lock(spinlock_t *lock) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock); + +void __lockfunc __rt_spin_lock(struct rt_mutex *lock) +{ + rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); +} +EXPORT_SYMBOL(__rt_spin_lock); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) +{ + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); +} +EXPORT_SYMBOL(rt_spin_lock_nested); +#endif + +void __lockfunc rt_spin_unlock(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(rt_spin_unlock); + +void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq); +} + +void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) +{ + rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); +} +EXPORT_SYMBOL(__rt_spin_unlock); + +/* + * Wait for the lock to get unlocked: instead of polling for an unlock + * (like raw spinlocks do), we lock and unlock, to force the kernel to + * schedule if there's contention: + */ +void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) +{ + spin_lock(lock); + spin_unlock(lock); +} +EXPORT_SYMBOL(rt_spin_unlock_wait); + +int __lockfunc rt_spin_trylock(spinlock_t *lock) +{ + int ret = rt_mutex_trylock(&lock->lock); + + if (ret) + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock); + +int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) +{ + int ret; + + local_bh_disable(); + ret = rt_mutex_trylock(&lock->lock); + if (ret) { + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else + local_bh_enable(); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_bh); + +int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) +{ + int ret; + + *flags = 0; + migrate_disable(); + ret = rt_mutex_trylock(&lock->lock); + if (ret) + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + else + migrate_enable(); + return ret; +} +EXPORT_SYMBOL(rt_spin_trylock_irqsave); + +int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + migrate_disable(); + rt_spin_lock(lock); + if (atomic_dec_and_test(atomic)) + return 1; + rt_spin_unlock(lock); + migrate_enable(); + return 0; +} +EXPORT_SYMBOL(atomic_dec_and_spin_lock); + +void +__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif +} +EXPORT_SYMBOL(__rt_spin_lock_init); + +#endif /* PREEMPT_RT_FULL */ + /** * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop * @lock: the rt_mutex to take * @state: the state the task should block in (TASK_INTERRUPTIBLE - * or TASK_UNINTERRUPTIBLE) + * or TASK_UNINTERRUPTIBLE) * @timeout: the pre-initialized and started timer, or NULL for none * @waiter: the pre-initialized rt_mutex_waiter * @@ -624,9 +1024,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, struct rt_mutex_waiter waiter; int ret = 0; - debug_rt_mutex_init_waiter(&waiter); + rt_mutex_init_waiter(&waiter, false); raw_spin_lock(&lock->wait_lock); + init_lists(lock); /* Try to acquire the lock again: */ if (try_to_take_rt_mutex(lock, current, NULL)) { @@ -678,7 +1079,9 @@ rt_mutex_slowtrylock(struct rt_mutex *lock) { int ret = 0; - raw_spin_lock(&lock->wait_lock); + if (!raw_spin_trylock(&lock->wait_lock)) + return ret; + init_lists(lock); if (likely(rt_mutex_owner(lock) != current)) { @@ -792,12 +1195,12 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); /** * rt_mutex_lock_interruptible - lock a rt_mutex interruptible * - * @lock: the rt_mutex to be locked + * @lock: the rt_mutex to be locked * @detect_deadlock: deadlock detection on/off * * Returns: - * 0 on success - * -EINTR when interrupted by a signal + * 0 on success + * -EINTR when interrupted by a signal * -EDEADLK when the lock would deadlock (when deadlock detection is on) */ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock, @@ -811,17 +1214,38 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock, EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); /** + * rt_mutex_lock_killable - lock a rt_mutex killable + * + * @lock: the rt_mutex to be locked + * @detect_deadlock: deadlock detection on/off + * + * Returns: + * 0 on success + * -EINTR when interrupted by a signal + * -EDEADLK when the lock would deadlock (when deadlock detection is on) + */ +int __sched rt_mutex_lock_killable(struct rt_mutex *lock, + int detect_deadlock) +{ + might_sleep(); + + return rt_mutex_fastlock(lock, TASK_KILLABLE, + detect_deadlock, rt_mutex_slowlock); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + +/** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided * by the caller * - * @lock: the rt_mutex to be locked + * @lock: the rt_mutex to be locked * @timeout: timeout structure or NULL (no timeout) * @detect_deadlock: deadlock detection on/off * * Returns: - * 0 on success - * -EINTR when interrupted by a signal + * 0 on success + * -EINTR when interrupted by a signal * -ETIMEDOUT when the timeout expired * -EDEADLK when the lock would deadlock (when deadlock detection is on) */ @@ -890,12 +1314,11 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy); void __rt_mutex_init(struct rt_mutex *lock, const char *name) { lock->owner = NULL; - raw_spin_lock_init(&lock->wait_lock); plist_head_init(&lock->wait_list); debug_rt_mutex_init(lock, name); } -EXPORT_SYMBOL_GPL(__rt_mutex_init); +EXPORT_SYMBOL(__rt_mutex_init); /** * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a @@ -910,7 +1333,7 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init); void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner) { - __rt_mutex_init(lock, NULL); + rt_mutex_init(lock); debug_rt_mutex_proxy_lock(lock, proxy_owner); rt_mutex_set_owner(lock, proxy_owner); rt_mutex_deadlock_account_lock(lock, proxy_owner); @@ -959,6 +1382,35 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, return 1; } +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * In PREEMPT_RT there's an added race. + * If the task, that we are about to requeue, times out, + * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue + * to skip this task. But right after the task sets + * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then + * block on the spin_lock(&hb->lock), which in RT is an rtmutex. + * This will replace the PI_WAKEUP_INPROGRESS with the actual + * lock that it blocks on. We *must not* place this task + * on this proxy lock in that case. + * + * To prevent this race, we first take the task's pi_lock + * and check if it has updated its pi_blocked_on. If it has, + * we assume that it woke up and we return -EAGAIN. + * Otherwise, we set the task's pi_blocked_on to + * PI_REQUEUE_INPROGRESS, so that if the task is waking up + * it will know that we are in the process of requeuing it. + */ + raw_spin_lock_irq(&task->pi_lock); + if (task->pi_blocked_on) { + raw_spin_unlock_irq(&task->pi_lock); + raw_spin_unlock(&lock->wait_lock); + return -EAGAIN; + } + task->pi_blocked_on = PI_REQUEUE_INPROGRESS; + raw_spin_unlock_irq(&task->pi_lock); +#endif + ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock); if (ret && !rt_mutex_owner(lock)) { diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h index 53a66c8..6ec3dc1 100644 --- a/kernel/rtmutex_common.h +++ b/kernel/rtmutex_common.h @@ -49,6 +49,7 @@ struct rt_mutex_waiter { struct plist_node pi_list_entry; struct task_struct *task; struct rt_mutex *lock; + bool savestate; #ifdef CONFIG_DEBUG_RT_MUTEXES unsigned long ip; struct pid *deadlock_task_pid; @@ -103,6 +104,9 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) /* * PI-futex support (proxy locking functions, etc.): */ +#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) +#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); @@ -123,4 +127,12 @@ extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, # include "rtmutex.h" #endif +static inline void +rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) +{ + debug_rt_mutex_init_waiter(waiter); + waiter->task = NULL; + waiter->savestate = savestate; +} + #endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b4308d7..87f9054 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -272,7 +272,11 @@ late_initcall(sched_init_debug); * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. */ +#ifndef CONFIG_PREEMPT_RT_FULL const_debug unsigned int sysctl_sched_nr_migrate = 32; +#else +const_debug unsigned int sysctl_sched_nr_migrate = 8; +#endif /* * period over which we average the RT time consumption, measured @@ -489,6 +493,7 @@ static void init_rq_hrtick(struct rq *rq) hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); rq->hrtick_timer.function = hrtick; + rq->hrtick_timer.irqsafe = 1; } #else /* CONFIG_SCHED_HRTICK */ static inline void hrtick_clear(struct rq *rq) @@ -533,6 +538,37 @@ void resched_task(struct task_struct *p) smp_send_reschedule(cpu); } +#ifdef CONFIG_PREEMPT_LAZY +void resched_task_lazy(struct task_struct *p) +{ + int cpu; + + if (!sched_feat(PREEMPT_LAZY)) { + resched_task(p); + return; + } + + assert_raw_spin_locked(&task_rq(p)->lock); + + if (test_tsk_need_resched(p)) + return; + + if (test_tsk_need_resched_lazy(p)) + return; + + set_tsk_need_resched_lazy(p); + + cpu = task_cpu(p); + if (cpu == smp_processor_id()) + return; + + /* NEED_RESCHED_LAZY must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(p)) + smp_send_reschedule(cpu); +} +#endif + void resched_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -697,6 +733,17 @@ void resched_task(struct task_struct *p) assert_raw_spin_locked(&task_rq(p)->lock); set_tsk_need_resched(p); } +#ifdef CONFIG_PREEMPT_LAZY +void resched_task_lazy(struct task_struct *p) +{ + if (!sched_feat(PREEMPT_LAZY)) { + resched_task(p); + return; + } + assert_raw_spin_locked(&task_rq(p)->lock); + set_tsk_need_resched_lazy(p); +} +#endif #endif /* CONFIG_SMP */ #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ @@ -1079,7 +1126,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * is actually now running somewhere else! */ while (task_running(rq, p)) { - if (match_state && unlikely(p->state != match_state)) + if (match_state && unlikely(p->state != match_state) + && unlikely(p->saved_state != match_state)) return 0; cpu_relax(); } @@ -1094,7 +1142,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) running = task_running(rq, p); on_rq = p->on_rq; ncsw = 0; - if (!match_state || p->state == match_state) + if (!match_state || p->state == match_state + || p->saved_state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ task_rq_unlock(rq, p, &flags); @@ -1240,6 +1289,12 @@ out: } } + /* + * Clear PF_NO_SETAFFINITY, otherwise we wreckage + * migrate_disable/enable. See optimization for + * PF_NO_SETAFFINITY tasks there. + */ + p->flags &= ~PF_NO_SETAFFINITY; return dest_cpu; } @@ -1319,10 +1374,6 @@ static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) { activate_task(rq, p, en_flags); p->on_rq = 1; - - /* if a worker is waking up, notify workqueue */ - if (p->flags & PF_WQ_WORKER) - wq_worker_waking_up(p, cpu_of(rq)); } /* @@ -1495,8 +1546,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ smp_mb__before_spinlock(); raw_spin_lock_irqsave(&p->pi_lock, flags); - if (!(p->state & state)) + if (!(p->state & state)) { + /* + * The task might be running due to a spinlock sleeper + * wakeup. Check the saved state and set it to running + * if the wakeup condition is true. + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) { + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + success = 1; + } + } goto out; + } + + /* + * If this is a regular wakeup, then we can unconditionally + * clear the saved state of a "lock sleeper". + */ + if (!(wake_flags & WF_LOCK_SLEEPER)) + p->saved_state = TASK_RUNNING; success = 1; /* we're going to change ->state */ cpu = task_cpu(p); @@ -1539,42 +1609,6 @@ out: } /** - * try_to_wake_up_local - try to wake up a local task with rq lock held - * @p: the thread to be awakened - * - * Put @p on the run-queue if it's not already there. The caller must - * ensure that this_rq() is locked, @p is bound to this_rq() and not - * the current task. - */ -static void try_to_wake_up_local(struct task_struct *p) -{ - struct rq *rq = task_rq(p); - - if (WARN_ON_ONCE(rq != this_rq()) || - WARN_ON_ONCE(p == current)) - return; - - lockdep_assert_held(&rq->lock); - - if (!raw_spin_trylock(&p->pi_lock)) { - raw_spin_unlock(&rq->lock); - raw_spin_lock(&p->pi_lock); - raw_spin_lock(&rq->lock); - } - - if (!(p->state & TASK_NORMAL)) - goto out; - - if (!p->on_rq) - ttwu_activate(rq, p, ENQUEUE_WAKEUP); - - ttwu_do_wakeup(rq, p, 0); - ttwu_stat(p, smp_processor_id(), 0); -out: - raw_spin_unlock(&p->pi_lock); -} - -/** * wake_up_process - Wake up a specific process * @p: The process to be woken up. * @@ -1592,6 +1626,18 @@ int wake_up_process(struct task_struct *p) } EXPORT_SYMBOL(wake_up_process); +/** + * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" + * @p: The process to be woken up. + * + * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate + * the nature of the wakeup. + */ +int wake_up_lock_sleeper(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER); +} + int wake_up_state(struct task_struct *p, unsigned int state) { return try_to_wake_up(p, state, 0); @@ -1738,6 +1784,9 @@ void sched_fork(struct task_struct *p) /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; #endif +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(p)->preempt_lazy_count = 0; +#endif #ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); #endif @@ -1902,8 +1951,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) finish_arch_post_lock_switch(); fire_sched_in_preempt_notifiers(current); + /* + * We use mmdrop_delayed() here so we don't have to do the + * full __mmdrop() when we are the last user. + */ if (mm) - mmdrop(mm); + mmdrop_delayed(mm); if (unlikely(prev_state == TASK_DEAD)) { /* * Remove function-return probe instances associated with this @@ -2814,8 +2867,13 @@ void __kprobes add_preempt_count(int val) DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); #endif - if (preempt_count() == val) - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + if (preempt_count() == val) { + unsigned long ip = get_parent_ip(CALLER_ADDR1); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } } EXPORT_SYMBOL(add_preempt_count); @@ -2858,6 +2916,13 @@ static noinline void __schedule_bug(struct task_struct *prev) print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); +#ifdef CONFIG_DEBUG_PREEMPT + if (in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } @@ -2881,6 +2946,134 @@ static inline void schedule_debug(struct task_struct *prev) schedstat_inc(this_rq(), sched_count); } +#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP) +#define MIGRATE_DISABLE_SET_AFFIN (1<<30) /* Can't make a negative */ +#define migrate_disabled_updated(p) ((p)->migrate_disable & MIGRATE_DISABLE_SET_AFFIN) +#define migrate_disable_count(p) ((p)->migrate_disable & ~MIGRATE_DISABLE_SET_AFFIN) + +static inline void update_migrate_disable(struct task_struct *p) +{ + const struct cpumask *mask; + + if (likely(!p->migrate_disable)) + return; + + /* Did we already update affinity? */ + if (unlikely(migrate_disabled_updated(p))) + return; + + /* + * Since this is always current we can get away with only locking + * rq->lock, the ->cpus_allowed value can normally only be changed + * while holding both p->pi_lock and rq->lock, but seeing that this + * is current, we cannot actually be waking up, so all code that + * relies on serialization against p->pi_lock is out of scope. + * + * Having rq->lock serializes us against things like + * set_cpus_allowed_ptr() that can still happen concurrently. + */ + mask = tsk_cpus_allowed(p); + + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, mask); + p->nr_cpus_allowed = cpumask_weight(mask); + + /* Let migrate_enable know to fix things back up */ + p->migrate_disable |= MIGRATE_DISABLE_SET_AFFIN; +} + +void migrate_disable(void) +{ + struct task_struct *p = current; + + if (in_atomic()) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +#endif + + preempt_disable(); + if (p->migrate_disable) { + p->migrate_disable++; + preempt_enable(); + return; + } + + preempt_lazy_disable(); + pin_current_cpu(); + p->migrate_disable = 1; + preempt_enable(); +} +EXPORT_SYMBOL(migrate_disable); + +void migrate_enable(void) +{ + struct task_struct *p = current; + const struct cpumask *mask; + unsigned long flags; + struct rq *rq; + + if (in_atomic()) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +#endif + WARN_ON_ONCE(p->migrate_disable <= 0); + + preempt_disable(); + if (migrate_disable_count(p) > 1) { + p->migrate_disable--; + preempt_enable(); + return; + } + + if (unlikely(migrate_disabled_updated(p))) { + /* + * Undo whatever update_migrate_disable() did, also see there + * about locking. + */ + rq = this_rq(); + raw_spin_lock_irqsave(&rq->lock, flags); + + /* + * Clearing migrate_disable causes tsk_cpus_allowed to + * show the tasks original cpu affinity. + */ + p->migrate_disable = 0; + mask = tsk_cpus_allowed(p); + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, mask); + p->nr_cpus_allowed = cpumask_weight(mask); + raw_spin_unlock_irqrestore(&rq->lock, flags); + } else + p->migrate_disable = 0; + + unpin_current_cpu(); + preempt_enable(); + preempt_lazy_enable(); +} +EXPORT_SYMBOL(migrate_enable); +#else +static inline void update_migrate_disable(struct task_struct *p) { } +#define migrate_disabled_updated(p) 0 +#endif + static void put_prev_task(struct rq *rq, struct task_struct *prev) { if (prev->on_rq || rq->skip_clock_update < 0) @@ -2980,6 +3173,8 @@ need_resched: smp_mb__before_spinlock(); raw_spin_lock_irq(&rq->lock); + update_migrate_disable(prev); + switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { if (unlikely(signal_pending_state(prev->state, prev))) { @@ -2987,19 +3182,6 @@ need_resched: } else { deactivate_task(rq, prev, DEQUEUE_SLEEP); prev->on_rq = 0; - - /* - * If a worker went to sleep, notify and ask workqueue - * whether it wants to wake up a task to maintain - * concurrency. - */ - if (prev->flags & PF_WQ_WORKER) { - struct task_struct *to_wakeup; - - to_wakeup = wq_worker_sleeping(prev, cpu); - if (to_wakeup) - try_to_wake_up_local(to_wakeup); - } } switch_count = &prev->nvcsw; } @@ -3012,6 +3194,7 @@ need_resched: put_prev_task(rq, prev); next = pick_next_task(rq); clear_tsk_need_resched(prev); + clear_tsk_need_resched_lazy(prev); rq->skip_clock_update = 0; if (likely(prev != next)) { @@ -3042,6 +3225,14 @@ static inline void sched_submit_work(struct task_struct *tsk) { if (!tsk->state || tsk_is_pi_blocked(tsk)) return; + + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. + */ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_sleeping(tsk); + /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. @@ -3050,12 +3241,19 @@ static inline void sched_submit_work(struct task_struct *tsk) blk_schedule_flush_plug(tsk); } +static inline void sched_update_worker(struct task_struct *tsk) +{ + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); +} + asmlinkage void __sched schedule(void) { struct task_struct *tsk = current; sched_submit_work(tsk); __schedule(); + sched_update_worker(tsk); } EXPORT_SYMBOL(schedule); @@ -3103,9 +3301,26 @@ asmlinkage void __sched notrace preempt_schedule(void) if (likely(ti->preempt_count || irqs_disabled())) return; +#ifdef CONFIG_PREEMPT_LAZY + /* + * Check for lazy preemption + */ + if (ti->preempt_lazy_count && !test_thread_flag(TIF_NEED_RESCHED)) + return; +#endif + do { add_preempt_count_notrace(PREEMPT_ACTIVE); + /* + * The add/subtract must not be traced by the function + * tracer. But we still want to account for the + * preempt off latency tracer. Since the _notrace versions + * of add/subtract skip the accounting for latency tracer + * we must force it manually. + */ + start_critical_timings(); __schedule(); + stop_critical_timings(); sub_preempt_count_notrace(PREEMPT_ACTIVE); /* @@ -3278,10 +3493,10 @@ void complete(struct completion *x) { unsigned long flags; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); x->done++; - __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); - spin_unlock_irqrestore(&x->wait.lock, flags); + __swait_wake_locked(&x->wait, TASK_NORMAL, 1); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); } EXPORT_SYMBOL(complete); @@ -3298,10 +3513,10 @@ void complete_all(struct completion *x) { unsigned long flags; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); x->done += UINT_MAX/2; - __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); - spin_unlock_irqrestore(&x->wait.lock, flags); + __swait_wake_locked(&x->wait, TASK_NORMAL, 0); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); } EXPORT_SYMBOL(complete_all); @@ -3310,20 +3525,20 @@ do_wait_for_common(struct completion *x, long (*action)(long), long timeout, int state) { if (!x->done) { - DECLARE_WAITQUEUE(wait, current); + DEFINE_SWAITER(wait); - __add_wait_queue_tail_exclusive(&x->wait, &wait); + swait_prepare_locked(&x->wait, &wait); do { if (signal_pending_state(state, current)) { timeout = -ERESTARTSYS; break; } __set_current_state(state); - spin_unlock_irq(&x->wait.lock); + raw_spin_unlock_irq(&x->wait.lock); timeout = action(timeout); - spin_lock_irq(&x->wait.lock); + raw_spin_lock_irq(&x->wait.lock); } while (!x->done && timeout); - __remove_wait_queue(&x->wait, &wait); + swait_finish_locked(&x->wait, &wait); if (!x->done) return timeout; } @@ -3337,9 +3552,9 @@ __wait_for_common(struct completion *x, { might_sleep(); - spin_lock_irq(&x->wait.lock); + raw_spin_lock_irq(&x->wait.lock); timeout = do_wait_for_common(x, action, timeout, state); - spin_unlock_irq(&x->wait.lock); + raw_spin_unlock_irq(&x->wait.lock); return timeout; } @@ -3515,12 +3730,12 @@ bool try_wait_for_completion(struct completion *x) unsigned long flags; int ret = 1; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; else x->done--; - spin_unlock_irqrestore(&x->wait.lock, flags); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(try_wait_for_completion); @@ -3538,10 +3753,10 @@ bool completion_done(struct completion *x) unsigned long flags; int ret = 1; - spin_lock_irqsave(&x->wait.lock, flags); + raw_spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; - spin_unlock_irqrestore(&x->wait.lock, flags); + raw_spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(completion_done); @@ -3602,7 +3817,8 @@ EXPORT_SYMBOL(sleep_on_timeout); * This function changes the 'effective' priority of a task. It does * not touch ->normal_prio like __setscheduler(). * - * Used by the rt_mutex code to implement priority inheritance logic. + * Used by the rt_mutex code to implement priority inheritance + * logic. Call site only calls if the priority of the task changed. */ void rt_mutex_setprio(struct task_struct *p, int prio) { @@ -3825,20 +4041,25 @@ static struct task_struct *find_process_by_pid(pid_t pid) return pid ? find_task_by_vpid(pid) : current; } -/* Actually do priority change: must hold rq lock. */ -static void -__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) +static void __setscheduler_params(struct task_struct *p, int policy, int prio) { p->policy = policy; p->rt_priority = prio; p->normal_prio = normal_prio(p); + set_load_weight(p); +} + +/* Actually do priority change: must hold rq lock. */ +static void +__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) +{ + __setscheduler_params(p, policy, prio); /* we are holding p->pi_lock already */ p->prio = rt_mutex_getprio(p); if (rt_prio(p->prio)) p->sched_class = &rt_sched_class; else p->sched_class = &fair_sched_class; - set_load_weight(p); } /* @@ -3860,6 +4081,7 @@ static bool check_same_owner(struct task_struct *p) static int __sched_setscheduler(struct task_struct *p, int policy, const struct sched_param *param, bool user) { + int newprio = MAX_RT_PRIO - 1 - param->sched_priority; int retval, oldprio, oldpolicy = -1, on_rq, running; unsigned long flags; const struct sched_class *prev_class; @@ -3955,10 +4177,13 @@ recheck: } /* - * If not changing anything there's no need to proceed further: + * If not changing anything there's no need to proceed + * further, but store a possible modification of + * reset_on_fork. */ if (unlikely(policy == p->policy && (!rt_policy(policy) || param->sched_priority == p->rt_priority))) { + p->sched_reset_on_fork = reset_on_fork; task_rq_unlock(rq, p, &flags); return 0; } @@ -3984,6 +4209,25 @@ recheck: task_rq_unlock(rq, p, &flags); goto recheck; } + + p->sched_reset_on_fork = reset_on_fork; + oldprio = p->prio; + + /* + * Special case for priority boosted tasks. + * + * If the new priority is lower or equal (user space view) + * than the current (boosted) priority, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + if (rt_mutex_check_prio(p, newprio)) { + __setscheduler_params(p, policy, param->sched_priority); + task_rq_unlock(rq, p, &flags); + return 0; + } + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) @@ -3991,17 +4235,18 @@ recheck: if (running) p->sched_class->put_prev_task(rq, p); - p->sched_reset_on_fork = reset_on_fork; - - oldprio = p->prio; prev_class = p->sched_class; __setscheduler(rq, p, policy, param->sched_priority); if (running) p->sched_class->set_curr_task(rq); - if (on_rq) - enqueue_task(rq, p, 0); - + if (on_rq) { + /* + * We enqueue to tail when the priority of a task is + * increased (user space view). + */ + enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0); + } check_class_changed(rq, p, prev_class, oldprio); task_rq_unlock(rq, p, &flags); @@ -4357,9 +4602,17 @@ static inline int should_resched(void) static void __cond_resched(void) { - add_preempt_count(PREEMPT_ACTIVE); - __schedule(); - sub_preempt_count(PREEMPT_ACTIVE); + do { + add_preempt_count(PREEMPT_ACTIVE); + __schedule(); + sub_preempt_count(PREEMPT_ACTIVE); + /* + * Check again in case we missed a preemption + * opportunity between schedule and now. + */ + barrier(); + + } while (need_resched()); } int __sched _cond_resched(void) @@ -4400,6 +4653,7 @@ int __cond_resched_lock(spinlock_t *lock) } EXPORT_SYMBOL(__cond_resched_lock); +#ifndef CONFIG_PREEMPT_RT_FULL int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); @@ -4413,6 +4667,7 @@ int __sched __cond_resched_softirq(void) return 0; } EXPORT_SYMBOL(__cond_resched_softirq); +#endif /** * yield - yield the current processor to other threads. @@ -4757,6 +5012,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; + idle->on_rq = 1; #if defined(CONFIG_SMP) idle->on_cpu = 1; #endif @@ -4764,7 +5020,9 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) /* Set the preempt count _outside_ the spinlocks! */ task_thread_info(idle)->preempt_count = 0; - +#ifdef CONFIG_HAVE_PREEMPT_LAZY + task_thread_info(idle)->preempt_lazy_count = 0; +#endif /* * The idle tasks have their own, simple scheduling class: */ @@ -4779,11 +5037,90 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) #ifdef CONFIG_SMP void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { - if (p->sched_class && p->sched_class->set_cpus_allowed) - p->sched_class->set_cpus_allowed(p, new_mask); - + if (!migrate_disabled_updated(p)) { + if (p->sched_class && p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); + } cpumask_copy(&p->cpus_allowed, new_mask); - p->nr_cpus_allowed = cpumask_weight(new_mask); +} + +static DEFINE_PER_CPU(struct cpumask, sched_cpumasks); +static DEFINE_MUTEX(sched_down_mutex); +static cpumask_t sched_down_cpumask; + +void tell_sched_cpu_down_begin(int cpu) +{ + mutex_lock(&sched_down_mutex); + cpumask_set_cpu(cpu, &sched_down_cpumask); + mutex_unlock(&sched_down_mutex); +} + +void tell_sched_cpu_down_done(int cpu) +{ + mutex_lock(&sched_down_mutex); + cpumask_clear_cpu(cpu, &sched_down_cpumask); + mutex_unlock(&sched_down_mutex); +} + +/** + * migrate_me - try to move the current task off this cpu + * + * Used by the pin_current_cpu() code to try to get tasks + * to move off the current CPU as it is going down. + * It will only move the task if the task isn't pinned to + * the CPU (with migrate_disable, affinity or NO_SETAFFINITY) + * and the task has to be in a RUNNING state. Otherwise the + * movement of the task will wake it up (change its state + * to running) when the task did not expect it. + * + * Returns 1 if it succeeded in moving the current task + * 0 otherwise. + */ +int migrate_me(void) +{ + struct task_struct *p = current; + struct migration_arg arg; + struct cpumask *cpumask; + struct cpumask *mask; + unsigned long flags; + unsigned int dest_cpu; + struct rq *rq; + + /* + * We can not migrate tasks bounded to a CPU or tasks not + * running. The movement of the task will wake it up. + */ + if (p->flags & PF_NO_SETAFFINITY || p->state) + return 0; + + mutex_lock(&sched_down_mutex); + rq = task_rq_lock(p, &flags); + + cpumask = &__get_cpu_var(sched_cpumasks); + mask = &p->cpus_allowed; + + cpumask_andnot(cpumask, mask, &sched_down_cpumask); + + if (!cpumask_weight(cpumask)) { + /* It's only on this CPU? */ + task_rq_unlock(rq, p, &flags); + mutex_unlock(&sched_down_mutex); + return 0; + } + + dest_cpu = cpumask_any_and(cpu_active_mask, cpumask); + + arg.task = p; + arg.dest_cpu = dest_cpu; + + task_rq_unlock(rq, p, &flags); + + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); + mutex_unlock(&sched_down_mutex); + + return 1; } /* @@ -4829,7 +5166,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) do_set_cpus_allowed(p, new_mask); /* Can the task run on the task's current CPU? If so, we're done */ - if (cpumask_test_cpu(task_cpu(p), new_mask)) + if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); @@ -4918,6 +5255,8 @@ static int migration_cpu_stop(void *data) #ifdef CONFIG_HOTPLUG_CPU +static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); + /* * Ensures that the idle task is using init_mm right before its cpu goes * offline. @@ -4930,7 +5269,12 @@ void idle_task_exit(void) if (mm != &init_mm) switch_mm(mm, &init_mm, current); - mmdrop(mm); + + /* + * Defer the cleanup to an alive cpu. On RT we can neither + * call mmdrop() nor mmdrop_delayed() from here. + */ + per_cpu(idle_last_mm, smp_processor_id()) = mm; } /* @@ -5247,6 +5591,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_DEAD: calc_load_migrate(rq); + if (per_cpu(idle_last_mm, cpu)) { + mmdrop(per_cpu(idle_last_mm, cpu)); + per_cpu(idle_last_mm, cpu) = NULL; + } break; #endif } @@ -7100,7 +7448,8 @@ void __init sched_init(void) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline int preempt_count_equals(int preempt_offset) { - int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); + int nested = (preempt_count() & ~PREEMPT_ACTIVE) + + sched_rcu_preempt_depth(); return (nested == preempt_offset); } @@ -7110,7 +7459,8 @@ void __might_sleep(const char *file, int line, int preempt_offset) static unsigned long prev_jiffy; /* ratelimiting */ rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ - if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current)) || system_state != SYSTEM_RUNNING || oops_in_progress) return; if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) @@ -7128,6 +7478,13 @@ void __might_sleep(const char *file, int line, int preempt_offset) debug_show_held_locks(current); if (irqs_disabled()) print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif dump_stack(); } EXPORT_SYMBOL(__might_sleep); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 1101d92..e4fdaad 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -671,9 +671,11 @@ void vtime_account_system(struct task_struct *tsk) if (!vtime_accounting_enabled()) return; - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); __vtime_account_system(tsk); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_account_irq_exit(struct task_struct *tsk) @@ -681,11 +683,13 @@ void vtime_account_irq_exit(struct task_struct *tsk) if (!vtime_accounting_enabled()) return; - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); if (context_tracking_in_user()) tsk->vtime_snap_whence = VTIME_USER; __vtime_account_system(tsk); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_account_user(struct task_struct *tsk) @@ -697,10 +701,12 @@ void vtime_account_user(struct task_struct *tsk) delta_cpu = get_vtime_delta(tsk); - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); tsk->vtime_snap_whence = VTIME_SYS; account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_user_enter(struct task_struct *tsk) @@ -708,26 +714,32 @@ void vtime_user_enter(struct task_struct *tsk) if (!vtime_accounting_enabled()) return; - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); tsk->vtime_snap_whence = VTIME_USER; __vtime_account_system(tsk); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_guest_enter(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); __vtime_account_system(tsk); current->flags |= PF_VCPU; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_guest_exit(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + raw_spin_lock(&tsk->vtime_lock); + write_seqcount_begin(&tsk->vtime_seq); __vtime_account_system(tsk); current->flags &= ~PF_VCPU; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seq); + raw_spin_unlock(&tsk->vtime_lock); } void vtime_account_idle(struct task_struct *tsk) @@ -744,24 +756,30 @@ bool vtime_accounting_enabled(void) void arch_vtime_task_switch(struct task_struct *prev) { - write_seqlock(&prev->vtime_seqlock); + raw_spin_lock(&prev->vtime_lock); + write_seqcount_begin(&prev->vtime_seq); prev->vtime_snap_whence = VTIME_SLEEPING; - write_sequnlock(&prev->vtime_seqlock); + write_seqcount_end(&prev->vtime_seq); + raw_spin_unlock(&prev->vtime_lock); - write_seqlock(¤t->vtime_seqlock); + raw_spin_lock(¤t->vtime_lock); + write_seqcount_begin(¤t->vtime_seq); current->vtime_snap_whence = VTIME_SYS; current->vtime_snap = sched_clock_cpu(smp_processor_id()); - write_sequnlock(¤t->vtime_seqlock); + write_seqcount_end(¤t->vtime_seq); + raw_spin_unlock(¤t->vtime_lock); } void vtime_init_idle(struct task_struct *t, int cpu) { unsigned long flags; - write_seqlock_irqsave(&t->vtime_seqlock, flags); + raw_spin_lock_irqsave(&t->vtime_lock, flags); + write_seqcount_begin(&t->vtime_seq); t->vtime_snap_whence = VTIME_SYS; t->vtime_snap = sched_clock_cpu(cpu); - write_sequnlock_irqrestore(&t->vtime_seqlock, flags); + write_seqcount_end(&t->vtime_seq); + raw_spin_unlock_irqrestore(&t->vtime_lock, flags); } cputime_t task_gtime(struct task_struct *t) @@ -770,13 +788,13 @@ cputime_t task_gtime(struct task_struct *t) cputime_t gtime; do { - seq = read_seqbegin(&t->vtime_seqlock); + seq = read_seqcount_begin(&t->vtime_seq); gtime = t->gtime; if (t->flags & PF_VCPU) gtime += vtime_delta(t); - } while (read_seqretry(&t->vtime_seqlock, seq)); + } while (read_seqcount_retry(&t->vtime_seq, seq)); return gtime; } @@ -799,7 +817,7 @@ fetch_task_cputime(struct task_struct *t, *udelta = 0; *sdelta = 0; - seq = read_seqbegin(&t->vtime_seqlock); + seq = read_seqcount_begin(&t->vtime_seq); if (u_dst) *u_dst = *u_src; @@ -823,7 +841,7 @@ fetch_task_cputime(struct task_struct *t, if (t->vtime_snap_whence == VTIME_SYS) *sdelta = delta; } - } while (read_seqretry(&t->vtime_seqlock, seq)); + } while (read_seqcount_retry(&t->vtime_seq, seq)); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e745a15..7686629 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -254,6 +254,9 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) P(rt_throttled); PN(rt_time); PN(rt_runtime); +#ifdef CONFIG_SMP + P(rt_nr_migratory); +#endif #undef PN #undef P @@ -576,6 +579,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) P(se.load.weight); P(policy); P(prio); +#ifdef CONFIG_PREEMPT_RT_FULL + P(migrate_disable); +#endif + P(nr_cpus_allowed); #undef PN #undef __PN #undef P diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 305ef88..5892154 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1854,7 +1854,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) ideal_runtime = sched_slice(cfs_rq, curr); delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; if (delta_exec > ideal_runtime) { - resched_task(rq_of(cfs_rq)->curr); + resched_task_lazy(rq_of(cfs_rq)->curr); /* * The current task ran long enough, ensure it doesn't get * re-elected due to buddy favours. @@ -1878,7 +1878,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) return; if (delta > ideal_runtime) - resched_task(rq_of(cfs_rq)->curr); + resched_task_lazy(rq_of(cfs_rq)->curr); } static void @@ -1999,7 +1999,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) * validating it and just reschedule. */ if (queued) { - resched_task(rq_of(cfs_rq)->curr); + resched_task_lazy(rq_of(cfs_rq)->curr); return; } /* @@ -2190,7 +2190,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, * hierarchy can be throttled */ if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) - resched_task(rq_of(cfs_rq)->curr); + resched_task_lazy(rq_of(cfs_rq)->curr); } static __always_inline @@ -2792,7 +2792,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) if (delta < 0) { if (rq->curr == p) - resched_task(p); + resched_task_lazy(p); return; } @@ -3617,7 +3617,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; preempt: - resched_task(curr); + resched_task_lazy(curr); /* * Only set the backward buddy when the current task is still * on the rq. This can happen when a wakeup gets interleaved @@ -5826,7 +5826,7 @@ static void task_fork_fair(struct task_struct *p) * 'current' within the tree based on its new key value. */ swap(curr->vruntime, se->vruntime); - resched_task(rq->curr); + resched_task_lazy(rq->curr); } se->vruntime -= cfs_rq->min_vruntime; @@ -5851,7 +5851,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) */ if (rq->curr == p) { if (p->prio > oldprio) - resched_task(rq->curr); + resched_task_lazy(rq->curr); } else check_preempt_curr(rq, p, 0); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 99399f8..4594051 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -50,11 +50,18 @@ SCHED_FEAT(LB_BIAS, true) */ SCHED_FEAT(NONTASK_POWER, true) +#ifndef CONFIG_PREEMPT_RT_FULL /* * Queue remote wakeups on the target CPU and process them * using the scheduler IPI. Reduces rq->lock contention/bounces. */ SCHED_FEAT(TTWU_QUEUE, true) +#else +SCHED_FEAT(TTWU_QUEUE, false) +# ifdef CONFIG_PREEMPT_LAZY +SCHED_FEAT(PREEMPT_LAZY, true) +# endif +#endif SCHED_FEAT(FORCE_SD_OVERLAP, false) SCHED_FEAT(RT_RUNTIME_SHARE, true) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 15334e6..cf00f3b 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -43,6 +43,7 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rt_b->rt_period_timer.irqsafe = 1; rt_b->rt_period_timer.function = sched_rt_period_timer; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index dfa31d5..98eea66 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -882,7 +882,8 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) */ #define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ #define WF_FORK 0x02 /* child wakeup after fork */ -#define WF_MIGRATED 0x4 /* internal use, task got migrated */ +#define WF_MIGRATED 0x04 /* internal use, task got migrated */ +#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ static inline void update_load_add(struct load_weight *lw, unsigned long inc) { @@ -1058,6 +1059,15 @@ extern void init_sched_fair_class(void); extern void resched_task(struct task_struct *p); extern void resched_cpu(int cpu); +#ifdef CONFIG_PREEMPT_LAZY +extern void resched_task_lazy(struct task_struct *tsk); +#else +static inline void resched_task_lazy(struct task_struct *tsk) +{ + resched_task(tsk); +} +#endif + extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); diff --git a/kernel/signal.c b/kernel/signal.c index 113411b..2f223e1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -349,13 +350,45 @@ static bool task_participate_group_stop(struct task_struct *task) return false; } +#ifdef __HAVE_ARCH_CMPXCHG +static inline struct sigqueue *get_task_cache(struct task_struct *t) +{ + struct sigqueue *q = t->sigqueue_cache; + + if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) + return NULL; + return q; +} + +static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) +{ + if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) + return 0; + return 1; +} + +#else + +static inline struct sigqueue *get_task_cache(struct task_struct *t) +{ + return NULL; +} + +static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) +{ + return 1; +} + +#endif + /* * 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 flags, int override_rlimit) +__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit, int fromslab) { struct sigqueue *q = NULL; struct user_struct *user; @@ -372,7 +405,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi if (override_rlimit || atomic_read(&user->sigpending) <= task_rlimit(t, RLIMIT_SIGPENDING)) { - q = kmem_cache_alloc(sigqueue_cachep, flags); + if (!fromslab) + q = get_task_cache(t); + if (!q) + q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } @@ -389,6 +425,13 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi return q; } +static struct sigqueue * +__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, + int override_rlimit) +{ + return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); +} + static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) @@ -398,6 +441,21 @@ static void __sigqueue_free(struct sigqueue *q) kmem_cache_free(sigqueue_cachep, q); } +static void sigqueue_free_current(struct sigqueue *q) +{ + struct user_struct *up; + + if (q->flags & SIGQUEUE_PREALLOC) + return; + + up = q->user; + if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { + atomic_dec(&up->sigpending); + free_uid(up); + } else + __sigqueue_free(q); +} + void flush_sigqueue(struct sigpending *queue) { struct sigqueue *q; @@ -411,6 +469,21 @@ void flush_sigqueue(struct sigpending *queue) } /* + * Called from __exit_signal. Flush tsk->pending and + * tsk->sigqueue_cache + */ +void flush_task_sigqueue(struct task_struct *tsk) +{ + struct sigqueue *q; + + flush_sigqueue(&tsk->pending); + + q = get_task_cache(tsk); + if (q) + kmem_cache_free(sigqueue_cachep, q); +} + +/* * Flush all pending signals for a task. */ void __flush_signals(struct task_struct *t) @@ -562,7 +635,7 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); - __sigqueue_free(first); + sigqueue_free_current(first); } else { /* * Ok, it wasn't in the queue. This must be @@ -608,6 +681,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) { int signr; + WARN_ON_ONCE(tsk != current); + /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ @@ -1230,8 +1305,8 @@ int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, * We don't want to have recursive SIGSEGV's etc, for example, * that is why we also clear SIGNAL_UNKILLABLE. */ -int -force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +static int +do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) { unsigned long int flags; int ret, blocked, ignored; @@ -1256,6 +1331,39 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t) return ret; } +int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +{ +/* + * On some archs, PREEMPT_RT has to delay sending a signal from a trap + * since it can not enable preemption, and the signal code's spin_locks + * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will + * send the signal on exit of the trap. + */ +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (in_atomic()) { + if (WARN_ON_ONCE(t != current)) + return 0; + if (WARN_ON_ONCE(t->forced_info.si_signo)) + return 0; + + if (is_si_special(info)) { + WARN_ON_ONCE(info != SEND_SIG_PRIV); + t->forced_info.si_signo = sig; + t->forced_info.si_errno = 0; + t->forced_info.si_code = SI_KERNEL; + t->forced_info.si_pid = 0; + t->forced_info.si_uid = 0; + } else { + t->forced_info = *info; + } + + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); + return 0; + } +#endif + return do_force_sig_info(sig, info, t); +} + /* * Nuke all other threads in the group. */ @@ -1286,12 +1394,12 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, struct sighand_struct *sighand; for (;;) { - local_irq_save(*flags); + local_irq_save_nort(*flags); rcu_read_lock(); sighand = rcu_dereference(tsk->sighand); if (unlikely(sighand == NULL)) { rcu_read_unlock(); - local_irq_restore(*flags); + local_irq_restore_nort(*flags); break; } @@ -1302,7 +1410,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, } spin_unlock(&sighand->siglock); rcu_read_unlock(); - local_irq_restore(*flags); + local_irq_restore_nort(*flags); } return sighand; @@ -1547,7 +1655,8 @@ EXPORT_SYMBOL(kill_pid); */ struct sigqueue *sigqueue_alloc(void) { - struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); + /* Preallocated sigqueue objects always from the slabcache ! */ + struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); if (q) q->flags |= SIGQUEUE_PREALLOC; @@ -1908,15 +2017,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) if (gstop_done && ptrace_reparented(current)) do_notify_parent_cldstop(current, false, why); - /* - * Don't want to allow preemption here, because - * sys_ptrace() needs this task to be inactive. - * - * XXX: implement read_unlock_no_resched(). - */ - preempt_disable(); read_unlock(&tasklist_lock); - preempt_enable_no_resched(); freezable_schedule(); } else { /* @@ -2375,7 +2476,7 @@ relock: } /** - * signal_delivered - + * signal_delivered - * @sig: number of signal being delivered * @info: siginfo_t of signal being delivered * @ka: sigaction setting that chose the handler @@ -3134,7 +3235,7 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) return 0; } -static int +static int do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long sp) { stack_t oss; @@ -3278,7 +3379,7 @@ int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) */ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set) { - return sys_rt_sigpending((sigset_t __user *)set, sizeof(old_sigset_t)); + return sys_rt_sigpending((sigset_t __user *)set, sizeof(old_sigset_t)); } #endif @@ -3403,7 +3504,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigaction, int, sig, ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { sigset_to_compat(&mask, &old_ka.sa.sa_mask); - ret = put_user(ptr_to_compat(old_ka.sa.sa_handler), + ret = put_user(ptr_to_compat(old_ka.sa.sa_handler), &oact->sa_handler); ret |= copy_to_user(&oact->sa_mask, &mask, sizeof(mask)); ret |= __put_user(old_ka.sa.sa_flags, &oact->sa_flags); @@ -3579,7 +3680,7 @@ SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize) return -EFAULT; return sigsuspend(&newset); } - + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(rt_sigsuspend, compat_sigset_t __user *, unewset, compat_size_t, sigsetsize) { diff --git a/kernel/softirq.c b/kernel/softirq.c index 787b3a0..541adf3 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -21,10 +21,12 @@ #include #include #include +#include #include #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -62,6 +64,98 @@ char *softirq_to_name[NR_SOFTIRQS] = { "TASKLET", "SCHED", "HRTIMER", "RCU" }; +#ifdef CONFIG_NO_HZ_COMMON +# ifdef CONFIG_PREEMPT_RT_FULL + +struct softirq_runner { + struct task_struct *runner[NR_SOFTIRQS]; +}; + +static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); + +static inline void softirq_set_runner(unsigned int sirq) +{ + struct softirq_runner *sr = &__get_cpu_var(softirq_runners); + + sr->runner[sirq] = current; +} + +static inline void softirq_clr_runner(unsigned int sirq) +{ + struct softirq_runner *sr = &__get_cpu_var(softirq_runners); + + sr->runner[sirq] = NULL; +} + +/* + * On preempt-rt a softirq running context might be blocked on a + * lock. There might be no other runnable task on this CPU because the + * lock owner runs on some other CPU. So we have to go into idle with + * the pending bit set. Therefor we need to check this otherwise we + * warn about false positives which confuses users and defeats the + * whole purpose of this test. + * + * This code is called with interrupts disabled. + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + struct softirq_runner *sr = &__get_cpu_var(softirq_runners); + u32 warnpending; + int i; + + if (rate_limit >= 10) + return; + + warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; + for (i = 0; i < NR_SOFTIRQS; i++) { + struct task_struct *tsk = sr->runner[i]; + + /* + * The wakeup code in rtmutex.c wakes up the task + * _before_ it sets pi_blocked_on to NULL under + * tsk->pi_lock. So we need to check for both: state + * and pi_blocked_on. + */ + if (tsk) { + raw_spin_lock(&tsk->pi_lock); + if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { + /* Clear all bits pending in that task */ + warnpending &= ~(tsk->softirqs_raised); + warnpending &= ~(1 << i); + } + raw_spin_unlock(&tsk->pi_lock); + } + } + + if (warnpending) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + warnpending); + rate_limit++; + } +} +# else +/* + * On !PREEMPT_RT we just printk rate limited: + */ +void softirq_check_pending_idle(void) +{ + static int rate_limit; + + if (rate_limit < 10 && + (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + local_softirq_pending()); + rate_limit++; + } +} +# endif + +#else /* !CONFIG_NO_HZ_COMMON */ +static inline void softirq_set_runner(unsigned int sirq) { } +static inline void softirq_clr_runner(unsigned int sirq) { } +#endif + /* * we cannot loop indefinitely here to avoid userspace starvation, * but we also don't want to introduce a worst case 1/HZ latency @@ -77,6 +171,57 @@ static void wakeup_softirqd(void) wake_up_process(tsk); } +static void handle_softirq(unsigned int vec_nr, int cpu, int need_rcu_bh_qs) +{ + struct softirq_action *h = softirq_vec + vec_nr; + unsigned int prev_count = preempt_count(); + + kstat_incr_softirqs_this_cpu(vec_nr); + trace_softirq_entry(vec_nr); + h->action(h); + trace_softirq_exit(vec_nr); + + if (unlikely(prev_count != preempt_count())) { + pr_err("softirq %u %s %p preempt count leak: %08x -> %08x\n", + vec_nr, softirq_to_name[vec_nr], h->action, + prev_count, (unsigned int) preempt_count()); + preempt_count() = prev_count; + } + if (need_rcu_bh_qs) + rcu_bh_qs(cpu); +} + +#ifndef CONFIG_PREEMPT_RT_FULL +static inline int ksoftirqd_softirq_pending(void) +{ + return local_softirq_pending(); +} + +static void handle_pending_softirqs(u32 pending, int cpu, int need_rcu_bh_qs) +{ + unsigned int vec_nr; + + local_irq_enable(); + for (vec_nr = 0; pending; vec_nr++, pending >>= 1) { + if (pending & 1) + handle_softirq(vec_nr, cpu, need_rcu_bh_qs); + } + local_irq_disable(); +} + +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + if (ksoftirqd_softirq_pending()) { + __do_softirq(); + rcu_note_context_switch(cpu); + local_irq_enable(); + cond_resched(); + return; + } + local_irq_enable(); +} + /* * preempt_count and SOFTIRQ_OFFSET usage: * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving @@ -210,9 +355,46 @@ EXPORT_SYMBOL(local_bh_enable_ip); #define MAX_SOFTIRQ_TIME msecs_to_jiffies(2) #define MAX_SOFTIRQ_RESTART 10 +#ifdef CONFIG_TRACE_IRQFLAGS +/* + * Convoluted means of passing __do_softirq() a message through the various + * architecture execute_on_stack() bits. + * + * When we run softirqs from irq_exit() and thus on the hardirq stack we need + * to keep the lockdep irq context tracking as tight as possible in order to + * not miss-qualify lock contexts and miss possible deadlocks. + */ +static DEFINE_PER_CPU(int, softirq_from_hardirq); + +static inline void lockdep_softirq_from_hardirq(void) +{ + this_cpu_write(softirq_from_hardirq, 1); +} + +static inline void lockdep_softirq_start(void) +{ + if (this_cpu_read(softirq_from_hardirq)) + trace_hardirq_exit(); + lockdep_softirq_enter(); +} + +static inline void lockdep_softirq_end(void) +{ + lockdep_softirq_exit(); + if (this_cpu_read(softirq_from_hardirq)) { + this_cpu_write(softirq_from_hardirq, 0); + trace_hardirq_enter(); + } +} + +#else +static inline void lockdep_softirq_from_hardirq(void) { } +static inline void lockdep_softirq_start(void) { } +static inline void lockdep_softirq_end(void) { } +#endif + asmlinkage void __do_softirq(void) { - struct softirq_action *h; __u32 pending; unsigned long end = jiffies + MAX_SOFTIRQ_TIME; int cpu; @@ -230,44 +412,15 @@ asmlinkage void __do_softirq(void) account_irq_enter_time(current); __local_bh_disable((unsigned long)__builtin_return_address(0), - SOFTIRQ_OFFSET); - lockdep_softirq_enter(); + SOFTIRQ_OFFSET); + lockdep_softirq_start(); cpu = smp_processor_id(); restart: /* Reset the pending bitmask before enabling irqs */ set_softirq_pending(0); - local_irq_enable(); - - h = softirq_vec; - - do { - if (pending & 1) { - unsigned int vec_nr = h - softirq_vec; - int prev_count = preempt_count(); - - kstat_incr_softirqs_this_cpu(vec_nr); - - trace_softirq_entry(vec_nr); - h->action(h); - trace_softirq_exit(vec_nr); - if (unlikely(prev_count != preempt_count())) { - printk(KERN_ERR "huh, entered softirq %u %s %p" - "with preempt_count %08x," - " exited with %08x?\n", vec_nr, - softirq_to_name[vec_nr], h->action, - prev_count, preempt_count()); - preempt_count() = prev_count; - } - - rcu_bh_qs(cpu); - } - h++; - pending >>= 1; - } while (pending); - - local_irq_disable(); + handle_pending_softirqs(pending, cpu, 1); pending = local_softirq_pending(); if (pending) { @@ -278,8 +431,7 @@ restart: wakeup_softirqd(); } - lockdep_softirq_exit(); - + lockdep_softirq_end(); account_irq_exit_time(current); __local_bh_enable(SOFTIRQ_OFFSET); tsk_restore_flags(current, old_flags, PF_MEMALLOC); @@ -308,6 +460,259 @@ asmlinkage void do_softirq(void) #endif /* + * This function must run with irqs disabled! + */ +void raise_softirq_irqoff(unsigned int nr) +{ + __raise_softirq_irqoff(nr); + + /* + * If we're in an interrupt or softirq, we're done + * (this also catches softirq-disabled code). We will + * actually run the softirq once we return from + * the irq or softirq. + * + * Otherwise we wake up ksoftirqd to make sure we + * schedule the softirq soon. + */ + if (!in_interrupt()) + wakeup_softirqd(); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); +} + +static inline void local_bh_disable_nort(void) { local_bh_disable(); } +static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } +static void ksoftirqd_set_sched_params(unsigned int cpu) { } +static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } + +#else /* !PREEMPT_RT_FULL */ + +/* + * On RT we serialize softirq execution with a cpu local lock per softirq + */ +static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); + +void __init softirq_early_init(void) +{ + int i; + + for (i = 0; i < NR_SOFTIRQS; i++) + local_irq_lock_init(local_softirq_locks[i]); +} + +static void lock_softirq(int which) +{ + __local_lock(&__get_cpu_var(local_softirq_locks[which])); +} + +static void unlock_softirq(int which) +{ + __local_unlock(&__get_cpu_var(local_softirq_locks[which])); +} + +static void do_single_softirq(int which, int need_rcu_bh_qs) +{ + unsigned long old_flags = current->flags; + + current->flags &= ~PF_MEMALLOC; + vtime_account_irq_enter(current); + current->flags |= PF_IN_SOFTIRQ; + lockdep_softirq_enter(); + local_irq_enable(); + handle_softirq(which, smp_processor_id(), need_rcu_bh_qs); + local_irq_disable(); + lockdep_softirq_exit(); + current->flags &= ~PF_IN_SOFTIRQ; + vtime_account_irq_enter(current); + tsk_restore_flags(current, old_flags, PF_MEMALLOC); +} + +/* + * Called with interrupts disabled. Process softirqs which were raised + * in current context (or on behalf of ksoftirqd). + */ +static void do_current_softirqs(int need_rcu_bh_qs) +{ + while (current->softirqs_raised) { + int i = __ffs(current->softirqs_raised); + unsigned int pending, mask = (1U << i); + + current->softirqs_raised &= ~mask; + local_irq_enable(); + + /* + * If the lock is contended, we boost the owner to + * process the softirq or leave the critical section + * now. + */ + lock_softirq(i); + local_irq_disable(); + softirq_set_runner(i); + /* + * Check with the local_softirq_pending() bits, + * whether we need to process this still or if someone + * else took care of it. + */ + pending = local_softirq_pending(); + if (pending & mask) { + set_softirq_pending(pending & ~mask); + do_single_softirq(i, need_rcu_bh_qs); + } + softirq_clr_runner(i); + unlock_softirq(i); + WARN_ON(current->softirq_nestcnt != 1); + } +} + +void local_bh_disable(void) +{ + migrate_disable(); + current->softirq_nestcnt++; +} +EXPORT_SYMBOL(local_bh_disable); + +void local_bh_enable(void) +{ + if (WARN_ON(current->softirq_nestcnt == 0)) + return; + + local_irq_disable(); + if (current->softirq_nestcnt == 1 && current->softirqs_raised) + do_current_softirqs(1); + local_irq_enable(); + + current->softirq_nestcnt--; + migrate_enable(); +} +EXPORT_SYMBOL(local_bh_enable); + +void local_bh_enable_ip(unsigned long ip) +{ + local_bh_enable(); +} +EXPORT_SYMBOL(local_bh_enable_ip); + +void _local_bh_enable(void) +{ + current->softirq_nestcnt--; + migrate_enable(); +} +EXPORT_SYMBOL(_local_bh_enable); + +int in_serving_softirq(void) +{ + return current->flags & PF_IN_SOFTIRQ; +} +EXPORT_SYMBOL(in_serving_softirq); + +/* Called with preemption disabled */ +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + current->softirq_nestcnt++; + do_current_softirqs(1); + current->softirq_nestcnt--; + rcu_note_context_switch(cpu); + local_irq_enable(); +} + +/* + * Called from netif_rx_ni(). Preemption enabled, but migration + * disabled. So the cpu can't go away under us. + */ +void thread_do_softirq(void) +{ + if (!in_serving_softirq() && current->softirqs_raised) { + current->softirq_nestcnt++; + do_current_softirqs(0); + current->softirq_nestcnt--; + } +} + +static void do_raise_softirq_irqoff(unsigned int nr) +{ + trace_softirq_raise(nr); + or_softirq_pending(1UL << nr); + + /* + * If we are not in a hard interrupt and inside a bh disabled + * region, we simply raise the flag on current. local_bh_enable() + * will make sure that the softirq is executed. Otherwise we + * delegate it to ksoftirqd. + */ + if (!in_irq() && current->softirq_nestcnt) + current->softirqs_raised |= (1U << nr); + else if (__this_cpu_read(ksoftirqd)) + __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); +} + +void __raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + if (!in_irq() && !current->softirq_nestcnt) + wakeup_softirqd(); +} + +/* + * This function must run with irqs disabled! + */ +void raise_softirq_irqoff(unsigned int nr) +{ + do_raise_softirq_irqoff(nr); + + /* + * If we're in an hard interrupt we let irq return code deal + * with the wakeup of ksoftirqd. + */ + if (in_irq()) + return; + + /* + * If we are in thread context but outside of a bh disabled + * region, we need to wake ksoftirqd as well. + * + * CHECKME: Some of the places which do that could be wrapped + * into local_bh_disable/enable pairs. Though it's unclear + * whether this is worth the effort. To find those places just + * raise a WARN() if the condition is met. + */ + if (!current->softirq_nestcnt) + wakeup_softirqd(); +} + +static inline int ksoftirqd_softirq_pending(void) +{ + return current->softirqs_raised; +} + +static inline void local_bh_disable_nort(void) { } +static inline void _local_bh_enable_nort(void) { } + +static inline void ksoftirqd_set_sched_params(unsigned int cpu) +{ + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); + /* Take over all pending softirqs when starting */ + local_irq_disable(); + current->softirqs_raised = local_softirq_pending(); + local_irq_enable(); +} + +static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) +{ + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); +} + +#endif /* PREEMPT_RT_FULL */ +/* * Enter an interrupt context. */ void irq_enter(void) @@ -320,9 +725,9 @@ void irq_enter(void) * Prevent raise_softirq from needlessly waking up ksoftirqd * here, as softirq will be serviced on return from interrupt. */ - local_bh_disable(); + local_bh_disable_nort(); tick_check_idle(cpu); - _local_bh_enable(); + _local_bh_enable_nort(); } __irq_enter(); @@ -330,7 +735,9 @@ void irq_enter(void) static inline void invoke_softirq(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!force_irqthreads) { + lockdep_softirq_from_hardirq(); /* * We can safely execute softirq on the current stack if * it is the irq stack, because it should be near empty @@ -343,6 +750,16 @@ static inline void invoke_softirq(void) } else { wakeup_softirqd(); } +#else /* PREEMPT_RT_FULL */ + unsigned long flags; + + local_irq_save(flags); + if (__this_cpu_read(ksoftirqd) && + __this_cpu_read(ksoftirqd)->softirqs_raised) + + wakeup_softirqd(); + local_irq_restore(flags); +#endif } static inline void tick_irq_exit(void) @@ -370,33 +787,13 @@ void irq_exit(void) #endif account_irq_exit_time(current); - trace_hardirq_exit(); sub_preempt_count(HARDIRQ_OFFSET); if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); tick_irq_exit(); rcu_irq_exit(); -} - -/* - * This function must run with irqs disabled! - */ -inline void raise_softirq_irqoff(unsigned int nr) -{ - __raise_softirq_irqoff(nr); - - /* - * If we're in an interrupt or softirq, we're done - * (this also catches softirq-disabled code). We will - * actually run the softirq once we return from - * the irq or softirq. - * - * Otherwise we wake up ksoftirqd to make sure we - * schedule the softirq soon. - */ - if (!in_interrupt()) - wakeup_softirqd(); + trace_hardirq_exit(); /* must be last! */ } void raise_softirq(unsigned int nr) @@ -408,12 +805,6 @@ void raise_softirq(unsigned int nr) local_irq_restore(flags); } -void __raise_softirq_irqoff(unsigned int nr) -{ - trace_softirq_raise(nr); - or_softirq_pending(1UL << nr); -} - void open_softirq(int nr, void (*action)(struct softirq_action *)) { softirq_vec[nr].action = action; @@ -431,15 +822,45 @@ struct tasklet_head static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec); static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec); +static void inline +__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr) +{ + if (tasklet_trylock(t)) { +again: + /* We may have been preempted before tasklet_trylock + * and __tasklet_action may have already run. + * So double check the sched bit while the takslet + * is locked before adding it to the list. + */ + if (test_bit(TASKLET_STATE_SCHED, &t->state)) { + t->next = NULL; + *head->tail = t; + head->tail = &(t->next); + raise_softirq_irqoff(nr); + tasklet_unlock(t); + } else { + /* This is subtle. If we hit the corner case above + * It is possible that we get preempted right here, + * and another task has successfully called + * tasklet_schedule(), then this function, and + * failed on the trylock. Thus we must be sure + * before releasing the tasklet lock, that the + * SCHED_BIT is clear. Otherwise the tasklet + * may get its SCHED_BIT set, but not added to the + * list + */ + if (!tasklet_tryunlock(t)) + goto again; + } + } +} + void __tasklet_schedule(struct tasklet_struct *t) { unsigned long flags; local_irq_save(flags); - t->next = NULL; - *__this_cpu_read(tasklet_vec.tail) = t; - __this_cpu_write(tasklet_vec.tail, &(t->next)); - raise_softirq_irqoff(TASKLET_SOFTIRQ); + __tasklet_common_schedule(t, &__get_cpu_var(tasklet_vec), TASKLET_SOFTIRQ); local_irq_restore(flags); } @@ -450,10 +871,7 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) unsigned long flags; local_irq_save(flags); - t->next = NULL; - *__this_cpu_read(tasklet_hi_vec.tail) = t; - __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); - raise_softirq_irqoff(HI_SOFTIRQ); + __tasklet_common_schedule(t, &__get_cpu_var(tasklet_hi_vec), HI_SOFTIRQ); local_irq_restore(flags); } @@ -461,50 +879,119 @@ EXPORT_SYMBOL(__tasklet_hi_schedule); void __tasklet_hi_schedule_first(struct tasklet_struct *t) { - BUG_ON(!irqs_disabled()); - - t->next = __this_cpu_read(tasklet_hi_vec.head); - __this_cpu_write(tasklet_hi_vec.head, t); - __raise_softirq_irqoff(HI_SOFTIRQ); + __tasklet_hi_schedule(t); } EXPORT_SYMBOL(__tasklet_hi_schedule_first); -static void tasklet_action(struct softirq_action *a) +void tasklet_enable(struct tasklet_struct *t) { - struct tasklet_struct *list; + if (!atomic_dec_and_test(&t->count)) + return; + if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) + tasklet_schedule(t); +} - local_irq_disable(); - list = __this_cpu_read(tasklet_vec.head); - __this_cpu_write(tasklet_vec.head, NULL); - __this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head); - local_irq_enable(); +EXPORT_SYMBOL(tasklet_enable); + +void tasklet_hi_enable(struct tasklet_struct *t) +{ + if (!atomic_dec_and_test(&t->count)) + return; + if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) + tasklet_hi_schedule(t); +} + +EXPORT_SYMBOL(tasklet_hi_enable); + +static void +__tasklet_action(struct softirq_action *a, struct tasklet_struct *list) +{ + int loops = 1000000; while (list) { struct tasklet_struct *t = list; list = list->next; - if (tasklet_trylock(t)) { - if (!atomic_read(&t->count)) { - if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) - BUG(); - t->func(t->data); - tasklet_unlock(t); - continue; - } - tasklet_unlock(t); + /* + * Should always succeed - after a tasklist got on the + * list (after getting the SCHED bit set from 0 to 1), + * nothing but the tasklet softirq it got queued to can + * lock it: + */ + if (!tasklet_trylock(t)) { + WARN_ON(1); + continue; } - local_irq_disable(); t->next = NULL; - *__this_cpu_read(tasklet_vec.tail) = t; - __this_cpu_write(tasklet_vec.tail, &(t->next)); - __raise_softirq_irqoff(TASKLET_SOFTIRQ); - local_irq_enable(); + + /* + * If we cannot handle the tasklet because it's disabled, + * mark it as pending. tasklet_enable() will later + * re-schedule the tasklet. + */ + if (unlikely(atomic_read(&t->count))) { +out_disabled: + /* implicit unlock: */ + wmb(); + t->state = TASKLET_STATEF_PENDING; + continue; + } + + /* + * After this point on the tasklet might be rescheduled + * on another CPU, but it can only be added to another + * CPU's tasklet list if we unlock the tasklet (which we + * dont do yet). + */ + if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + WARN_ON(1); + +again: + t->func(t->data); + + /* + * Try to unlock the tasklet. We must use cmpxchg, because + * another CPU might have scheduled or disabled the tasklet. + * We only allow the STATE_RUN -> 0 transition here. + */ + while (!tasklet_tryunlock(t)) { + /* + * If it got disabled meanwhile, bail out: + */ + if (atomic_read(&t->count)) + goto out_disabled; + /* + * If it got scheduled meanwhile, re-execute + * the tasklet function: + */ + if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) + goto again; + if (!--loops) { + printk("hm, tasklet state: %08lx\n", t->state); + WARN_ON(1); + tasklet_unlock(t); + break; + } + } } } +static void tasklet_action(struct softirq_action *a) +{ + struct tasklet_struct *list; + + local_irq_disable(); + list = __get_cpu_var(tasklet_vec).head; + __get_cpu_var(tasklet_vec).head = NULL; + __get_cpu_var(tasklet_vec).tail = &__get_cpu_var(tasklet_vec).head; + local_irq_enable(); + + __tasklet_action(a, list); +} + static void tasklet_hi_action(struct softirq_action *a) { struct tasklet_struct *list; @@ -515,29 +1002,7 @@ static void tasklet_hi_action(struct softirq_action *a) __this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head); local_irq_enable(); - while (list) { - struct tasklet_struct *t = list; - - list = list->next; - - if (tasklet_trylock(t)) { - if (!atomic_read(&t->count)) { - if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) - BUG(); - t->func(t->data); - tasklet_unlock(t); - continue; - } - tasklet_unlock(t); - } - - local_irq_disable(); - t->next = NULL; - *__this_cpu_read(tasklet_hi_vec.tail) = t; - __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); - __raise_softirq_irqoff(HI_SOFTIRQ); - local_irq_enable(); - } + __tasklet_action(a, list); } @@ -560,7 +1025,7 @@ void tasklet_kill(struct tasklet_struct *t) while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { do { - yield(); + msleep(1); } while (test_bit(TASKLET_STATE_SCHED, &t->state)); } tasklet_unlock_wait(t); @@ -764,22 +1229,26 @@ void __init softirq_init(void) open_softirq(HI_SOFTIRQ, tasklet_hi_action); } -static int ksoftirqd_should_run(unsigned int cpu) +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) +void tasklet_unlock_wait(struct tasklet_struct *t) { - return local_softirq_pending(); + while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { + /* + * Hack for now to avoid this busy-loop: + */ +#ifdef CONFIG_PREEMPT_RT_FULL + msleep(1); +#else + barrier(); +#endif + } } +EXPORT_SYMBOL(tasklet_unlock_wait); +#endif -static void run_ksoftirqd(unsigned int cpu) +static int ksoftirqd_should_run(unsigned int cpu) { - local_irq_disable(); - if (local_softirq_pending()) { - __do_softirq(); - rcu_note_context_switch(cpu); - local_irq_enable(); - cond_resched(); - return; - } - local_irq_enable(); + return ksoftirqd_softirq_pending(); } #ifdef CONFIG_HOTPLUG_CPU @@ -862,6 +1331,8 @@ static struct notifier_block __cpuinitdata cpu_nfb = { static struct smp_hotplug_thread softirq_threads = { .store = &ksoftirqd, + .setup = ksoftirqd_set_sched_params, + .cleanup = ksoftirqd_clr_sched_params, .thread_should_run = ksoftirqd_should_run, .thread_fn = run_ksoftirqd, .thread_comm = "ksoftirqd/%u", diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 5cdd806..da9775b 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -110,8 +110,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock) \ * __[spin|read|write]_lock_bh() */ BUILD_LOCK_OPS(spin, raw_spinlock); + +#ifndef CONFIG_PREEMPT_RT_FULL BUILD_LOCK_OPS(read, rwlock); BUILD_LOCK_OPS(write, rwlock); +#endif #endif @@ -195,6 +198,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) EXPORT_SYMBOL(_raw_spin_unlock_bh); #endif +#ifndef CONFIG_PREEMPT_RT_FULL + #ifndef CONFIG_INLINE_READ_TRYLOCK int __lockfunc _raw_read_trylock(rwlock_t *lock) { @@ -339,6 +344,8 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock) EXPORT_SYMBOL(_raw_write_unlock_bh); #endif +#endif /* !PREEMPT_RT_FULL */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index c09f295..5f02a3f 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -29,12 +29,12 @@ struct cpu_stop_done { atomic_t nr_todo; /* nr left to execute */ bool executed; /* actually executed? */ int ret; /* collected return value */ - struct completion completion; /* fired if nr_todo reaches 0 */ + struct task_struct *waiter; /* woken when nr_todo reaches 0 */ }; /* the actual stopper, one per every possible cpu, enabled on online cpus */ struct cpu_stopper { - spinlock_t lock; + raw_spinlock_t lock; bool enabled; /* is this stopper enabled? */ struct list_head works; /* list of pending works */ }; @@ -47,7 +47,7 @@ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) { memset(done, 0, sizeof(*done)); atomic_set(&done->nr_todo, nr_todo); - init_completion(&done->completion); + done->waiter = current; } /* signal completion unless @done is NULL */ @@ -56,8 +56,10 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed) if (done) { if (executed) done->executed = true; - if (atomic_dec_and_test(&done->nr_todo)) - complete(&done->completion); + if (atomic_dec_and_test(&done->nr_todo)) { + wake_up_process(done->waiter); + done->waiter = NULL; + } } } @@ -69,7 +71,7 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) unsigned long flags; - spin_lock_irqsave(&stopper->lock, flags); + raw_spin_lock_irqsave(&stopper->lock, flags); if (stopper->enabled) { list_add_tail(&work->list, &stopper->works); @@ -77,7 +79,23 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) } else cpu_stop_signal_done(work->done, false); - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); +} + +static void wait_for_stop_done(struct cpu_stop_done *done) +{ + set_current_state(TASK_UNINTERRUPTIBLE); + while (atomic_read(&done->nr_todo)) { + schedule(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + /* + * We need to wait until cpu_stop_signal_done() has cleared + * done->waiter. + */ + while (done->waiter) + cpu_relax(); + set_current_state(TASK_RUNNING); } /** @@ -111,7 +129,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) cpu_stop_init_done(&done, 1); cpu_stop_queue_work(cpu, &work); - wait_for_completion(&done.completion); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -137,11 +155,12 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, /* static data for stop_cpus */ static DEFINE_MUTEX(stop_cpus_mutex); +static DEFINE_MUTEX(stopper_lock); static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work); static void queue_stop_cpus_work(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg, - struct cpu_stop_done *done) + struct cpu_stop_done *done, bool inactive) { struct cpu_stop_work *work; unsigned int cpu; @@ -155,14 +174,18 @@ static void queue_stop_cpus_work(const struct cpumask *cpumask, } /* - * Disable preemption while queueing to avoid getting - * preempted by a stopper which might wait for other stoppers - * to enter @fn which can lead to deadlock. + * Make sure that all work is queued on all cpus before we + * any of the cpus can execute it. */ - preempt_disable(); + if (!inactive) { + mutex_lock(&stopper_lock); + } else { + while (!mutex_trylock(&stopper_lock)) + cpu_relax(); + } for_each_cpu(cpu, cpumask) cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu)); - preempt_enable(); + mutex_unlock(&stopper_lock); } static int __stop_cpus(const struct cpumask *cpumask, @@ -171,8 +194,8 @@ static int __stop_cpus(const struct cpumask *cpumask, struct cpu_stop_done done; cpu_stop_init_done(&done, cpumask_weight(cpumask)); - queue_stop_cpus_work(cpumask, fn, arg, &done); - wait_for_completion(&done.completion); + queue_stop_cpus_work(cpumask, fn, arg, &done, false); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -251,9 +274,9 @@ static int cpu_stop_should_run(unsigned int cpu) unsigned long flags; int run; - spin_lock_irqsave(&stopper->lock, flags); + raw_spin_lock_irqsave(&stopper->lock, flags); run = !list_empty(&stopper->works); - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); return run; } @@ -265,13 +288,13 @@ static void cpu_stopper_thread(unsigned int cpu) repeat: work = NULL; - spin_lock_irq(&stopper->lock); + raw_spin_lock_irq(&stopper->lock); if (!list_empty(&stopper->works)) { work = list_first_entry(&stopper->works, struct cpu_stop_work, list); list_del_init(&work->list); } - spin_unlock_irq(&stopper->lock); + raw_spin_unlock_irq(&stopper->lock); if (work) { cpu_stop_fn_t fn = work->fn; @@ -279,6 +302,16 @@ repeat: struct cpu_stop_done *done = work->done; char ksym_buf[KSYM_NAME_LEN] __maybe_unused; + /* + * Wait until the stopper finished scheduling on all + * cpus + */ + mutex_lock(&stopper_lock); + /* + * Let other cpu threads continue as well + */ + mutex_unlock(&stopper_lock); + /* cpu stop callbacks are not allowed to sleep */ preempt_disable(); @@ -293,7 +326,13 @@ repeat: kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL, ksym_buf), arg); + /* + * Make sure that the wakeup and setting done->waiter + * to NULL is atomic. + */ + local_irq_disable(); cpu_stop_signal_done(done, true); + local_irq_enable(); goto repeat; } } @@ -312,20 +351,20 @@ static void cpu_stop_park(unsigned int cpu) unsigned long flags; /* drain remaining works */ - spin_lock_irqsave(&stopper->lock, flags); + raw_spin_lock_irqsave(&stopper->lock, flags); list_for_each_entry(work, &stopper->works, list) cpu_stop_signal_done(work->done, false); stopper->enabled = false; - spin_unlock_irqrestore(&stopper->lock, flags); + raw_spin_unlock_irqrestore(&stopper->lock, flags); } static void cpu_stop_unpark(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - spin_lock_irq(&stopper->lock); + raw_spin_lock_irq(&stopper->lock); stopper->enabled = true; - spin_unlock_irq(&stopper->lock); + raw_spin_unlock_irq(&stopper->lock); } static struct smp_hotplug_thread cpu_stop_threads = { @@ -347,7 +386,7 @@ static int __init cpu_stop_init(void) for_each_possible_cpu(cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - spin_lock_init(&stopper->lock); + raw_spin_lock_init(&stopper->lock); INIT_LIST_HEAD(&stopper->works); } @@ -530,11 +569,11 @@ int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, set_state(&smdata, STOPMACHINE_PREPARE); cpu_stop_init_done(&done, num_active_cpus()); queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata, - &done); + &done, true); ret = stop_machine_cpu_stop(&smdata); /* Busy wait for completion. */ - while (!completion_done(&done.completion)) + while (atomic_read(&done.nr_todo)) cpu_relax(); mutex_unlock(&stop_cpus_mutex); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a6a5bf5..23d7203 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -73,7 +73,8 @@ static struct clocksource clocksource_jiffies = { .shift = JIFFIES_SHIFT, }; -__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); +__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); +__cacheline_aligned_in_smp seqcount_t jiffies_seq; #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void) @@ -82,9 +83,9 @@ u64 get_jiffies_64(void) u64 ret; do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); ret = jiffies_64; - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); return ret; } EXPORT_SYMBOL(get_jiffies_64); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index af8d1d4..d6132cd 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -517,10 +518,49 @@ static void sync_cmos_clock(struct work_struct *work) schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next)); } +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * RT can not call schedule_delayed_work from real interrupt context. + * Need to make a thread to do the real work. + */ +static struct task_struct *cmos_delay_thread; +static bool do_cmos_delay; + +static int run_cmos_delay(void *ignore) +{ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (do_cmos_delay) { + do_cmos_delay = false; + schedule_delayed_work(&sync_cmos_work, 0); + } + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void ntp_notify_cmos_timer(void) +{ + do_cmos_delay = true; + /* Make visible before waking up process */ + smp_wmb(); + wake_up_process(cmos_delay_thread); +} + +static __init int create_cmos_delay_thread(void) +{ + cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd"); + BUG_ON(!cmos_delay_thread); + return 0; +} +early_initcall(create_cmos_delay_thread); +#else void ntp_notify_cmos_timer(void) { schedule_delayed_work(&sync_cmos_work, 0); } +#endif /* CONFIG_PREEMPT_RT_FULL */ #else void ntp_notify_cmos_timer(void) { } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 086216c..9a4dce1 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -64,13 +64,15 @@ int tick_is_oneshot_available(void) static void tick_periodic(int cpu) { if (tick_do_timer_cpu == cpu) { - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); /* Keep track of the next tick event */ tick_next_period = ktime_add(tick_next_period, tick_period); do_timer(1); - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); } update_process_times(user_mode(get_irq_regs())); @@ -131,9 +133,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) ktime_t next; do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); next = tick_next_period; - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 60742fe..7b392f0 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -4,7 +4,8 @@ #include #include -extern seqlock_t jiffies_lock; +extern raw_spinlock_t jiffies_lock; +extern seqcount_t jiffies_seq; #ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 4251374..4e657e5 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -61,7 +61,8 @@ static void tick_do_update_jiffies64(ktime_t now) return; /* Reevalute with jiffies_lock held */ - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, last_jiffies_update); if (delta.tv64 >= tick_period.tv64) { @@ -84,7 +85,8 @@ static void tick_do_update_jiffies64(ktime_t now) /* Keep the tick_next_period variable up to date */ tick_next_period = ktime_add(last_jiffies_update, tick_period); } - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); } /* @@ -94,12 +96,14 @@ static ktime_t tick_init_jiffy_update(void) { ktime_t period; - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); /* Did we start the jiffies update yet ? */ if (last_jiffies_update.tv64 == 0) last_jiffies_update = tick_next_period; period = last_jiffies_update; - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); return period; } @@ -547,11 +551,11 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, /* Read jiffies and the time when jiffies were updated last */ do { - seq = read_seqbegin(&jiffies_lock); + seq = read_seqcount_begin(&jiffies_seq); last_update = last_jiffies_update; last_jiffies = jiffies; time_delta = timekeeping_max_deferment(); - } while (read_seqretry(&jiffies_lock, seq)); + } while (read_seqcount_retry(&jiffies_seq, seq)); if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || arch_needs_cpu(cpu) || irq_work_needs_cpu()) { @@ -727,14 +731,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; if (unlikely(local_softirq_pending() && cpu_online(cpu))) { - static int ratelimit; - - if (ratelimit < 10 && - (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { - pr_warn("NOHZ: local_softirq_pending %02x\n", - (unsigned int) local_softirq_pending()); - ratelimit++; - } + softirq_check_pending_idle(); return false; } @@ -1124,6 +1121,7 @@ void tick_setup_sched_timer(void) * Emulate tick processing via per-CPU hrtimers: */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + ts->sched_timer.irqsafe = 1; ts->sched_timer.function = tick_sched_timer; /* Get the next period (per cpu) */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 76fefb1..2b72c66 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1729,7 +1729,9 @@ EXPORT_SYMBOL(hardpps); */ void xtime_update(unsigned long ticks) { - write_seqlock(&jiffies_lock); + raw_spin_lock(&jiffies_lock); + write_seqcount_begin(&jiffies_seq); do_timer(ticks); - write_sequnlock(&jiffies_lock); + write_seqcount_end(&jiffies_seq); + raw_spin_unlock(&jiffies_lock); } diff --git a/kernel/timer.c b/kernel/timer.c index 15bc1b4..48652cc 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -78,6 +78,9 @@ struct tvec_root { struct tvec_base { spinlock_t lock; struct timer_list *running_timer; +#ifdef CONFIG_PREEMPT_RT_FULL + wait_queue_head_t wait_for_running_timer; +#endif unsigned long timer_jiffies; unsigned long next_timer; unsigned long active_timers; @@ -720,6 +723,36 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer, } } +#ifndef CONFIG_PREEMPT_RT_FULL +static inline struct tvec_base *switch_timer_base(struct timer_list *timer, + struct tvec_base *old, + struct tvec_base *new) +{ + /* See the comment in lock_timer_base() */ + timer_set_base(timer, NULL); + spin_unlock(&old->lock); + spin_lock(&new->lock); + timer_set_base(timer, new); + return new; +} +#else +static inline struct tvec_base *switch_timer_base(struct timer_list *timer, + struct tvec_base *old, + struct tvec_base *new) +{ + /* + * We cannot do the above because we might be preempted and + * then the preempter would see NULL and loop forever. + */ + if (spin_trylock(&new->lock)) { + timer_set_base(timer, new); + spin_unlock(&old->lock); + return new; + } + return old; +} +#endif + static inline int __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only, int pinned) @@ -739,12 +772,15 @@ __mod_timer(struct timer_list *timer, unsigned long expires, debug_activate(timer, expires); + preempt_disable_rt(); cpu = smp_processor_id(); #if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) cpu = get_nohz_timer_target(); #endif + preempt_enable_rt(); + new_base = per_cpu(tvec_bases, cpu); if (base != new_base) { @@ -755,14 +791,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, * handler yet has not finished. This also guarantees that * the timer is serialized wrt itself. */ - if (likely(base->running_timer != timer)) { - /* See the comment in lock_timer_base() */ - timer_set_base(timer, NULL); - spin_unlock(&base->lock); - base = new_base; - spin_lock(&base->lock); - timer_set_base(timer, base); - } + if (likely(base->running_timer != timer)) + base = switch_timer_base(timer, base, new_base); } timer->expires = expires; @@ -945,6 +975,29 @@ void add_timer_on(struct timer_list *timer, int cpu) } EXPORT_SYMBOL_GPL(add_timer_on); +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * Wait for a running timer + */ +static void wait_for_running_timer(struct timer_list *timer) +{ + struct tvec_base *base = timer->base; + + if (base->running_timer == timer) + wait_event(base->wait_for_running_timer, + base->running_timer != timer); +} + +# define wakeup_timer_waiters(b) wake_up(&(b)->wait_for_running_timer) +#else +static inline void wait_for_running_timer(struct timer_list *timer) +{ + cpu_relax(); +} + +# define wakeup_timer_waiters(b) do { } while (0) +#endif + /** * del_timer - deactive a timer. * @timer: the timer to be deactivated @@ -1002,7 +1055,7 @@ int try_to_del_timer_sync(struct timer_list *timer) } EXPORT_SYMBOL(try_to_del_timer_sync); -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1062,7 +1115,7 @@ int del_timer_sync(struct timer_list *timer) int ret = try_to_del_timer_sync(timer); if (ret >= 0) return ret; - cpu_relax(); + wait_for_running_timer(timer); } } EXPORT_SYMBOL(del_timer_sync); @@ -1179,15 +1232,17 @@ static inline void __run_timers(struct tvec_base *base) if (irqsafe) { spin_unlock(&base->lock); call_timer_fn(timer, fn, data); + base->running_timer = NULL; spin_lock(&base->lock); } else { spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); + base->running_timer = NULL; spin_lock_irq(&base->lock); } } } - base->running_timer = NULL; + wakeup_timer_waiters(base); spin_unlock_irq(&base->lock); } @@ -1327,17 +1382,31 @@ unsigned long get_next_timer_interrupt(unsigned long now) if (cpu_is_offline(smp_processor_id())) return expires; +#ifdef CONFIG_PREEMPT_RT_FULL + /* + * On PREEMPT_RT we cannot sleep here. If the trylock does not + * succeed then we return the worst-case 'expires in 1 tick' + * value. We use the rt functions here directly to avoid a + * migrate_disable() call. + */ + if (!spin_do_trylock(&base->lock)) + return now + 1; +#else spin_lock(&base->lock); +#endif if (base->active_timers) { if (time_before_eq(base->next_timer, base->timer_jiffies)) base->next_timer = __next_timer_interrupt(base); expires = base->next_timer; } +#ifdef CONFIG_PREEMPT_RT_FULL + rt_spin_unlock_after_trylock_in_irq(&base->lock); +#else spin_unlock(&base->lock); +#endif if (time_before_eq(expires, now)) return now; - return cmp_next_hrtimer_event(now, expires); } #endif @@ -1353,13 +1422,13 @@ void update_process_times(int user_tick) /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); + scheduler_tick(); run_local_timers(); rcu_check_callbacks(cpu, user_tick); -#ifdef CONFIG_IRQ_WORK +#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL) if (in_irq()) irq_work_run(); #endif - scheduler_tick(); run_posix_cpu_timers(p); } @@ -1370,6 +1439,10 @@ static void run_timer_softirq(struct softirq_action *h) { struct tvec_base *base = __this_cpu_read(tvec_bases); +#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) + irq_work_run(); +#endif + hrtimer_run_pending(); if (time_after_eq(jiffies, base->timer_jiffies)) @@ -1547,6 +1620,9 @@ static int __cpuinit init_timers_cpu(int cpu) base = per_cpu(tvec_bases, cpu); } +#ifdef CONFIG_PREEMPT_RT_FULL + init_waitqueue_head(&base->wait_for_running_timer); +#endif for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); @@ -1585,7 +1661,7 @@ static void __cpuinit migrate_timers(int cpu) BUG_ON(cpu_online(cpu)); old_base = per_cpu(tvec_bases, cpu); - new_base = get_cpu_var(tvec_bases); + new_base = get_local_var(tvec_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. @@ -1606,7 +1682,7 @@ static void __cpuinit migrate_timers(int cpu) spin_unlock(&old_base->lock); spin_unlock_irq(&new_base->lock); - put_cpu_var(tvec_bases); + put_local_var(tvec_bases); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 015f85a..bbe95b9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -192,6 +192,24 @@ config IRQSOFF_TRACER enabled. This option and the preempt-off timing option can be used together or separately.) +config INTERRUPT_OFF_HIST + bool "Interrupts-off Latency Histogram" + depends on IRQSOFF_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the duration of time periods with interrupts disabled. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff + + If PREEMPT_OFF_HIST is also selected, additional histograms (one + per cpu) are generated that accumulate the duration of time periods + when both interrupts and preemption are disabled. The histogram data + will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/irqsoff + config PREEMPT_TRACER bool "Preemption-off Latency Tracer" default n @@ -216,6 +234,24 @@ config PREEMPT_TRACER enabled. This option and the irqs-off timing option can be used together or separately.) +config PREEMPT_OFF_HIST + bool "Preemption-off Latency Histogram" + depends on PREEMPT_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the duration of time periods with preemption disabled. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff + + If INTERRUPT_OFF_HIST is also selected, additional histograms (one + per cpu) are generated that accumulate the duration of time periods + when both interrupts and preemption are disabled. The histogram data + will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/preemptoff + config SCHED_TRACER bool "Scheduling Latency Tracer" select GENERIC_TRACER @@ -226,6 +262,74 @@ config SCHED_TRACER This tracer tracks the latency of the highest priority task to be scheduled in, starting from the point it has woken up. +config WAKEUP_LATENCY_HIST + bool "Scheduling Latency Histogram" + depends on SCHED_TRACER + help + This option generates continuously updated histograms (one per cpu) + of the scheduling latency of the highest priority task. + The histograms are disabled by default. To enable them, write a + non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/wakeup + + Two different algorithms are used, one to determine the latency of + processes that exclusively use the highest priority of the system and + another one to determine the latency of processes that share the + highest system priority with other processes. The former is used to + improve hardware and system software, the latter to optimize the + priority design of a given system. The histogram data will be + located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/wakeup + + and + + /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio + + If both Scheduling Latency Histogram and Missed Timer Offsets + Histogram are selected, additional histogram data will be collected + that contain, in addition to the wakeup latency, the timer latency, in + case the wakeup was triggered by an expired timer. These histograms + are available in the + + /sys/kernel/debug/tracing/latency_hist/timerandwakeup + + directory. They reflect the apparent interrupt and scheduling latency + and are best suitable to determine the worst-case latency of a given + system. To enable these histograms, write a non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup + +config MISSED_TIMER_OFFSETS_HIST + depends on HIGH_RES_TIMERS + select GENERIC_TRACER + bool "Missed Timer Offsets Histogram" + help + Generate a histogram of missed timer offsets in microseconds. The + histograms are disabled by default. To enable them, write a non-zero + number to + + /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets + + The histogram data will be located in the debug file system at + + /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets + + If both Scheduling Latency Histogram and Missed Timer Offsets + Histogram are selected, additional histogram data will be collected + that contain, in addition to the wakeup latency, the timer latency, in + case the wakeup was triggered by an expired timer. These histograms + are available in the + + /sys/kernel/debug/tracing/latency_hist/timerandwakeup + + directory. They reflect the apparent interrupt and scheduling latency + and are best suitable to determine the worst-case latency of a given + system. To enable these histograms, write a non-zero number to + + /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup + config ENABLE_DEFAULT_TRACERS bool "Trace process context switches and events" depends on !GENERIC_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index d7e2068..f5e0243 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -34,6 +34,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o +obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o +obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o +obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o +obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o obj-$(CONFIG_NOP_TRACER) += trace_nop.o obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o diff --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c new file mode 100644 index 0000000..011c232 --- /dev/null +++ b/kernel/trace/latency_hist.c @@ -0,0 +1,1177 @@ +/* + * kernel/trace/latency_hist.c + * + * Add support for histograms of preemption-off latency and + * interrupt-off latency and wakeup latency, it depends on + * Real-Time Preemption Support. + * + * Copyright (C) 2005 MontaVista Software, Inc. + * Yi Yang + * + * Converted to work with the new latency tracer. + * Copyright (C) 2008 Red Hat, Inc. + * Steven Rostedt + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" +#include + +#define NSECS_PER_USECS 1000L + +#define CREATE_TRACE_POINTS +#include + +enum { + IRQSOFF_LATENCY = 0, + PREEMPTOFF_LATENCY, + PREEMPTIRQSOFF_LATENCY, + WAKEUP_LATENCY, + WAKEUP_LATENCY_SHAREDPRIO, + MISSED_TIMER_OFFSETS, + TIMERANDWAKEUP_LATENCY, + MAX_LATENCY_TYPE, +}; + +#define MAX_ENTRY_NUM 10240 + +struct hist_data { + atomic_t hist_mode; /* 0 log, 1 don't log */ + long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */ + long min_lat; + long max_lat; + unsigned long long below_hist_bound_samples; + unsigned long long above_hist_bound_samples; + long long accumulate_lat; + unsigned long long total_samples; + unsigned long long hist_array[MAX_ENTRY_NUM]; +}; + +struct enable_data { + int latency_type; + int enabled; +}; + +static char *latency_hist_dir_root = "latency_hist"; + +#ifdef CONFIG_INTERRUPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); +static char *irqsoff_hist_dir = "irqsoff"; +static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); +static DEFINE_PER_CPU(int, hist_irqsoff_counting); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST +static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); +static char *preemptoff_hist_dir = "preemptoff"; +static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); +static DEFINE_PER_CPU(int, hist_preemptoff_counting); +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) +static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); +static char *preemptirqsoff_hist_dir = "preemptirqsoff"; +static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); +static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); +#endif + +#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start); +static struct enable_data preemptirqsoff_enabled_data = { + .latency_type = PREEMPTIRQSOFF_LATENCY, + .enabled = 0, +}; +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +struct maxlatproc_data { + char comm[FIELD_SIZEOF(struct task_struct, comm)]; + char current_comm[FIELD_SIZEOF(struct task_struct, comm)]; + int pid; + int current_pid; + int prio; + int current_prio; + long latency; + long timeroffset; + cycle_t timestamp; +}; +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); +static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio); +static char *wakeup_latency_hist_dir = "wakeup"; +static char *wakeup_latency_hist_dir_sharedprio = "sharedprio"; +static notrace void probe_wakeup_latency_hist_start(void *v, + struct task_struct *p, int success); +static notrace void probe_wakeup_latency_hist_stop(void *v, + struct task_struct *prev, struct task_struct *next); +static notrace void probe_sched_migrate_task(void *, + struct task_struct *task, int cpu); +static struct enable_data wakeup_latency_enabled_data = { + .latency_type = WAKEUP_LATENCY, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); +static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio); +static DEFINE_PER_CPU(struct task_struct *, wakeup_task); +static DEFINE_PER_CPU(int, wakeup_sharedprio); +static unsigned long wakeup_pid; +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST +static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets); +static char *missed_timer_offsets_dir = "missed_timer_offsets"; +static notrace void probe_hrtimer_interrupt(void *v, int cpu, + long long offset, struct task_struct *curr, struct task_struct *task); +static struct enable_data missed_timer_offsets_enabled_data = { + .latency_type = MISSED_TIMER_OFFSETS, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc); +static unsigned long missed_timer_offsets_pid; +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist); +static char *timerandwakeup_latency_hist_dir = "timerandwakeup"; +static struct enable_data timerandwakeup_enabled_data = { + .latency_type = TIMERANDWAKEUP_LATENCY, + .enabled = 0, +}; +static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); +#endif + +void notrace latency_hist(int latency_type, int cpu, long latency, + long timeroffset, cycle_t stop, + struct task_struct *p) +{ + struct hist_data *my_hist; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + struct maxlatproc_data *mp = NULL; +#endif + + if (cpu < 0 || cpu >= NR_CPUS || latency_type < 0 || + latency_type >= MAX_LATENCY_TYPE) + return; + + switch (latency_type) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + my_hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + my_hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif +#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + my_hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + my_hist = &per_cpu(wakeup_latency_hist, cpu); + mp = &per_cpu(wakeup_maxlatproc, cpu); + break; + case WAKEUP_LATENCY_SHAREDPRIO: + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + my_hist = &per_cpu(missed_timer_offsets, cpu); + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + my_hist = &per_cpu(timerandwakeup_latency_hist, cpu); + mp = &per_cpu(timerandwakeup_maxlatproc, cpu); + break; +#endif + + default: + return; + } + + latency += my_hist->offset; + + if (atomic_read(&my_hist->hist_mode) == 0) + return; + + if (latency < 0 || latency >= MAX_ENTRY_NUM) { + if (latency < 0) + my_hist->below_hist_bound_samples++; + else + my_hist->above_hist_bound_samples++; + } else + my_hist->hist_array[latency]++; + + if (unlikely(latency > my_hist->max_lat || + my_hist->min_lat == LONG_MAX)) { +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + if (latency_type == WAKEUP_LATENCY || + latency_type == WAKEUP_LATENCY_SHAREDPRIO || + latency_type == MISSED_TIMER_OFFSETS || + latency_type == TIMERANDWAKEUP_LATENCY) { + strncpy(mp->comm, p->comm, sizeof(mp->comm)); + strncpy(mp->current_comm, current->comm, + sizeof(mp->current_comm)); + mp->pid = task_pid_nr(p); + mp->current_pid = task_pid_nr(current); + mp->prio = p->prio; + mp->current_prio = current->prio; + mp->latency = latency; + mp->timeroffset = timeroffset; + mp->timestamp = stop; + } +#endif + my_hist->max_lat = latency; + } + if (unlikely(latency < my_hist->min_lat)) + my_hist->min_lat = latency; + my_hist->total_samples++; + my_hist->accumulate_lat += latency; +} + +static void *l_start(struct seq_file *m, loff_t *pos) +{ + loff_t *index_ptr = NULL; + loff_t index = *pos; + struct hist_data *my_hist = m->private; + + if (index == 0) { + char minstr[32], avgstr[32], maxstr[32]; + + atomic_dec(&my_hist->hist_mode); + + if (likely(my_hist->total_samples)) { + long avg = (long) div64_s64(my_hist->accumulate_lat, + my_hist->total_samples); + snprintf(minstr, sizeof(minstr), "%ld", + my_hist->min_lat - my_hist->offset); + snprintf(avgstr, sizeof(avgstr), "%ld", + avg - my_hist->offset); + snprintf(maxstr, sizeof(maxstr), "%ld", + my_hist->max_lat - my_hist->offset); + } else { + strcpy(minstr, ""); + strcpy(avgstr, minstr); + strcpy(maxstr, minstr); + } + + seq_printf(m, "#Minimum latency: %s microseconds\n" + "#Average latency: %s microseconds\n" + "#Maximum latency: %s microseconds\n" + "#Total samples: %llu\n" + "#There are %llu samples lower than %ld" + " microseconds.\n" + "#There are %llu samples greater or equal" + " than %ld microseconds.\n" + "#usecs\t%16s\n", + minstr, avgstr, maxstr, + my_hist->total_samples, + my_hist->below_hist_bound_samples, + -my_hist->offset, + my_hist->above_hist_bound_samples, + MAX_ENTRY_NUM - my_hist->offset, + "samples"); + } + if (index < MAX_ENTRY_NUM) { + index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL); + if (index_ptr) + *index_ptr = index; + } + + return index_ptr; +} + +static void *l_next(struct seq_file *m, void *p, loff_t *pos) +{ + loff_t *index_ptr = p; + struct hist_data *my_hist = m->private; + + if (++*pos >= MAX_ENTRY_NUM) { + atomic_inc(&my_hist->hist_mode); + return NULL; + } + *index_ptr = *pos; + return index_ptr; +} + +static void l_stop(struct seq_file *m, void *p) +{ + kfree(p); +} + +static int l_show(struct seq_file *m, void *p) +{ + int index = *(loff_t *) p; + struct hist_data *my_hist = m->private; + + seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset, + my_hist->hist_array[index]); + return 0; +} + +static struct seq_operations latency_hist_seq_op = { + .start = l_start, + .next = l_next, + .stop = l_stop, + .show = l_show +}; + +static int latency_hist_open(struct inode *inode, struct file *file) +{ + int ret; + + ret = seq_open(file, &latency_hist_seq_op); + if (!ret) { + struct seq_file *seq = file->private_data; + seq->private = inode->i_private; + } + return ret; +} + +static struct file_operations latency_hist_fops = { + .open = latency_hist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static void clear_maxlatprocdata(struct maxlatproc_data *mp) +{ + mp->comm[0] = mp->current_comm[0] = '\0'; + mp->prio = mp->current_prio = mp->pid = mp->current_pid = + mp->latency = mp->timeroffset = -1; + mp->timestamp = 0; +} +#endif + +static void hist_reset(struct hist_data *hist) +{ + atomic_dec(&hist->hist_mode); + + memset(hist->hist_array, 0, sizeof(hist->hist_array)); + hist->below_hist_bound_samples = 0ULL; + hist->above_hist_bound_samples = 0ULL; + hist->min_lat = LONG_MAX; + hist->max_lat = LONG_MIN; + hist->total_samples = 0ULL; + hist->accumulate_lat = 0LL; + + atomic_inc(&hist->hist_mode); +} + +static ssize_t +latency_hist_reset(struct file *file, const char __user *a, + size_t size, loff_t *off) +{ + int cpu; + struct hist_data *hist = NULL; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + struct maxlatproc_data *mp = NULL; +#endif + off_t latency_type = (off_t) file->private_data; + + for_each_online_cpu(cpu) { + + switch (latency_type) { +#ifdef CONFIG_PREEMPT_OFF_HIST + case PREEMPTOFF_LATENCY: + hist = &per_cpu(preemptoff_hist, cpu); + break; +#endif +#ifdef CONFIG_INTERRUPT_OFF_HIST + case IRQSOFF_LATENCY: + hist = &per_cpu(irqsoff_hist, cpu); + break; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + hist = &per_cpu(preemptirqsoff_hist, cpu); + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + hist = &per_cpu(wakeup_latency_hist, cpu); + mp = &per_cpu(wakeup_maxlatproc, cpu); + break; + case WAKEUP_LATENCY_SHAREDPRIO: + hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); + mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + hist = &per_cpu(missed_timer_offsets, cpu); + mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + hist = &per_cpu(timerandwakeup_latency_hist, cpu); + mp = &per_cpu(timerandwakeup_maxlatproc, cpu); + break; +#endif + } + + hist_reset(hist); +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + if (latency_type == WAKEUP_LATENCY || + latency_type == WAKEUP_LATENCY_SHAREDPRIO || + latency_type == MISSED_TIMER_OFFSETS || + latency_type == TIMERANDWAKEUP_LATENCY) + clear_maxlatprocdata(mp); +#endif + } + + return size; +} + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static ssize_t +show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + unsigned long *this_pid = file->private_data; + + r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t do_pid(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + unsigned long pid; + unsigned long *this_pid = file->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = '\0'; + + if (strict_strtoul(buf, 10, &pid)) + return(-EINVAL); + + *this_pid = pid; + + return cnt; +} +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static ssize_t +show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + int r; + struct maxlatproc_data *mp = file->private_data; + int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8); + unsigned long long t; + unsigned long usecs, secs; + char *buf; + + if (mp->pid == -1 || mp->current_pid == -1) { + buf = "(none)\n"; + return simple_read_from_buffer(ubuf, cnt, ppos, buf, + strlen(buf)); + } + + buf = kmalloc(strmaxlen, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + t = ns2usecs(mp->timestamp); + usecs = do_div(t, USEC_PER_SEC); + secs = (unsigned long) t; + r = snprintf(buf, strmaxlen, + "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid, + MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm, + mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm, + secs, usecs); + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + kfree(buf); + return r; +} +#endif + +static ssize_t +show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + struct enable_data *ed = file->private_data; + int r; + + r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) +{ + char buf[64]; + long enable; + struct enable_data *ed = file->private_data; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + if (strict_strtol(buf, 10, &enable)) + return(-EINVAL); + + if ((enable && ed->enabled) || (!enable && !ed->enabled)) + return cnt; + + if (enable) { + int ret; + + switch (ed->latency_type) { +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + ret = register_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_preemptirqsoff_hist " + "to trace_preemptirqsoff_hist\n"); + return ret; + } + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + ret = register_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup\n"); + return ret; + } + ret = register_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_start " + "to trace_sched_wakeup_new\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + return ret; + } + ret = register_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_wakeup_latency_hist_stop " + "to trace_sched_switch\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + return ret; + } + ret = register_trace_sched_migrate_task( + probe_sched_migrate_task, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_sched_migrate_task " + "to trace_sched_migrate_task\n"); + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + return ret; + } + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + ret = register_trace_hrtimer_interrupt( + probe_hrtimer_interrupt, NULL); + if (ret) { + pr_info("wakeup trace: Couldn't assign " + "probe_hrtimer_interrupt " + "to trace_hrtimer_interrupt\n"); + return ret; + } + break; +#endif +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + case TIMERANDWAKEUP_LATENCY: + if (!wakeup_latency_enabled_data.enabled || + !missed_timer_offsets_enabled_data.enabled) + return -EINVAL; + break; +#endif + default: + break; + } + } else { + switch (ed->latency_type) { +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + case PREEMPTIRQSOFF_LATENCY: + { + int cpu; + + unregister_trace_preemptirqsoff_hist( + probe_preemptirqsoff_hist, NULL); + for_each_online_cpu(cpu) { +#ifdef CONFIG_INTERRUPT_OFF_HIST + per_cpu(hist_irqsoff_counting, + cpu) = 0; +#endif +#ifdef CONFIG_PREEMPT_OFF_HIST + per_cpu(hist_preemptoff_counting, + cpu) = 0; +#endif +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + per_cpu(hist_preemptirqsoff_counting, + cpu) = 0; +#endif + } + } + break; +#endif +#ifdef CONFIG_WAKEUP_LATENCY_HIST + case WAKEUP_LATENCY: + { + int cpu; + + unregister_trace_sched_wakeup( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_wakeup_new( + probe_wakeup_latency_hist_start, NULL); + unregister_trace_sched_switch( + probe_wakeup_latency_hist_stop, NULL); + unregister_trace_sched_migrate_task( + probe_sched_migrate_task, NULL); + + for_each_online_cpu(cpu) { + per_cpu(wakeup_task, cpu) = NULL; + per_cpu(wakeup_sharedprio, cpu) = 0; + } + } +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + timerandwakeup_enabled_data.enabled = 0; +#endif + break; +#endif +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + case MISSED_TIMER_OFFSETS: + unregister_trace_hrtimer_interrupt( + probe_hrtimer_interrupt, NULL); +#ifdef CONFIG_WAKEUP_LATENCY_HIST + timerandwakeup_enabled_data.enabled = 0; +#endif + break; +#endif + default: + break; + } + } + ed->enabled = enable; + return cnt; +} + +static const struct file_operations latency_hist_reset_fops = { + .open = tracing_open_generic, + .write = latency_hist_reset, +}; + +static const struct file_operations enable_fops = { + .open = tracing_open_generic, + .read = show_enable, + .write = do_enable, +}; + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) +static const struct file_operations pid_fops = { + .open = tracing_open_generic, + .read = show_pid, + .write = do_pid, +}; + +static const struct file_operations maxlatproc_fops = { + .open = tracing_open_generic, + .read = show_maxlatproc, +}; +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) +static notrace void probe_preemptirqsoff_hist(void *v, int reason, + int starthist) +{ + int cpu = raw_smp_processor_id(); + int time_set = 0; + + if (starthist) { + cycle_t uninitialized_var(start); + + if (!preempt_count() && !irqs_disabled()) + return; + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_OFF || reason == TRACE_START) && + !per_cpu(hist_irqsoff_counting, cpu)) { + per_cpu(hist_irqsoff_counting, cpu) = 1; + start = ftrace_now(cpu); + time_set++; + per_cpu(hist_irqsoff_start, cpu) = start; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_OFF || reason == TRACE_START) && + !per_cpu(hist_preemptoff_counting, cpu)) { + per_cpu(hist_preemptoff_counting, cpu) = 1; + if (!(time_set++)) + start = ftrace_now(cpu); + per_cpu(hist_preemptoff_start, cpu) = start; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if (per_cpu(hist_irqsoff_counting, cpu) && + per_cpu(hist_preemptoff_counting, cpu) && + !per_cpu(hist_preemptirqsoff_counting, cpu)) { + per_cpu(hist_preemptirqsoff_counting, cpu) = 1; + if (!time_set) + start = ftrace_now(cpu); + per_cpu(hist_preemptirqsoff_start, cpu) = start; + } +#endif + } else { + cycle_t uninitialized_var(stop); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + if ((reason == IRQS_ON || reason == TRACE_STOP) && + per_cpu(hist_irqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_irqsoff_start, cpu); + + stop = ftrace_now(cpu); + time_set++; + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, + stop, NULL); + } + per_cpu(hist_irqsoff_counting, cpu) = 0; + } +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + if ((reason == PREEMPT_ON || reason == TRACE_STOP) && + per_cpu(hist_preemptoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptoff_start, cpu); + + if (!(time_set++)) + stop = ftrace_now(cpu); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(PREEMPTOFF_LATENCY, cpu, latency, + 0, stop, NULL); + } + per_cpu(hist_preemptoff_counting, cpu) = 0; + } +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + if ((!per_cpu(hist_irqsoff_counting, cpu) || + !per_cpu(hist_preemptoff_counting, cpu)) && + per_cpu(hist_preemptirqsoff_counting, cpu)) { + cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); + + if (!time_set) + stop = ftrace_now(cpu); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + + latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, + latency, 0, stop, NULL); + } + per_cpu(hist_preemptirqsoff_counting, cpu) = 0; + } +#endif + } +} +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST +static DEFINE_RAW_SPINLOCK(wakeup_lock); +static notrace void probe_sched_migrate_task(void *v, struct task_struct *task, + int cpu) +{ + int old_cpu = task_cpu(task); + + if (cpu != old_cpu) { + unsigned long flags; + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, old_cpu); + if (task == cpu_wakeup_task) { + put_task_struct(cpu_wakeup_task); + per_cpu(wakeup_task, old_cpu) = NULL; + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task; + get_task_struct(cpu_wakeup_task); + } + + raw_spin_unlock_irqrestore(&wakeup_lock, flags); + } +} + +static notrace void probe_wakeup_latency_hist_start(void *v, + struct task_struct *p, int success) +{ + unsigned long flags; + struct task_struct *curr = current; + int cpu = task_cpu(p); + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, cpu); + + if (wakeup_pid) { + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || + p->prio == curr->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + if (likely(wakeup_pid != task_pid_nr(p))) + goto out; + } else { + if (likely(!rt_task(p)) || + (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) || + p->prio > curr->prio) + goto out; + if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || + p->prio == curr->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + } + + if (cpu_wakeup_task) + put_task_struct(cpu_wakeup_task); + cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p; + get_task_struct(cpu_wakeup_task); + cpu_wakeup_task->preempt_timestamp_hist = + ftrace_now(raw_smp_processor_id()); +out: + raw_spin_unlock_irqrestore(&wakeup_lock, flags); +} + +static notrace void probe_wakeup_latency_hist_stop(void *v, + struct task_struct *prev, struct task_struct *next) +{ + unsigned long flags; + int cpu = task_cpu(next); + long latency; + cycle_t stop; + struct task_struct *cpu_wakeup_task; + + raw_spin_lock_irqsave(&wakeup_lock, flags); + + cpu_wakeup_task = per_cpu(wakeup_task, cpu); + + if (cpu_wakeup_task == NULL) + goto out; + + /* Already running? */ + if (unlikely(current == cpu_wakeup_task)) + goto out_reset; + + if (next != cpu_wakeup_task) { + if (next->prio < cpu_wakeup_task->prio) + goto out_reset; + + if (next->prio == cpu_wakeup_task->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + + goto out; + } + + if (current->prio == cpu_wakeup_task->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + + /* + * The task we are waiting for is about to be switched to. + * Calculate latency and store it in histogram. + */ + stop = ftrace_now(raw_smp_processor_id()); + + latency = ((long) (stop - next->preempt_timestamp_hist)) / + NSECS_PER_USECS; + + if (per_cpu(wakeup_sharedprio, cpu)) { + latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, + next); + per_cpu(wakeup_sharedprio, cpu) = 0; + } else { + latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next); +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + if (timerandwakeup_enabled_data.enabled) { + latency_hist(TIMERANDWAKEUP_LATENCY, cpu, + next->timer_offset + latency, next->timer_offset, + stop, next); + } +#endif + } + +out_reset: +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + next->timer_offset = 0; +#endif + put_task_struct(cpu_wakeup_task); + per_cpu(wakeup_task, cpu) = NULL; +out: + raw_spin_unlock_irqrestore(&wakeup_lock, flags); +} +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST +static notrace void probe_hrtimer_interrupt(void *v, int cpu, + long long latency_ns, struct task_struct *curr, struct task_struct *task) +{ + if (latency_ns <= 0 && task != NULL && rt_task(task) && + (task->prio < curr->prio || + (task->prio == curr->prio && + !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { + long latency; + cycle_t now; + + if (missed_timer_offsets_pid) { + if (likely(missed_timer_offsets_pid != + task_pid_nr(task))) + return; + } + + now = ftrace_now(cpu); + latency = (long) div_s64(-latency_ns, NSECS_PER_USECS); + latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, + task); +#ifdef CONFIG_WAKEUP_LATENCY_HIST + task->timer_offset = latency; +#endif + } +} +#endif + +static __init int latency_hist_init(void) +{ + struct dentry *latency_hist_root = NULL; + struct dentry *dentry; +#ifdef CONFIG_WAKEUP_LATENCY_HIST + struct dentry *dentry_sharedprio; +#endif + struct dentry *entry; + struct dentry *enable_root; + int i = 0; + struct hist_data *my_hist; + char name[64]; + char *cpufmt = "CPU%d"; +#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + char *cpufmt_maxlatproc = "max_latency-CPU%d"; + struct maxlatproc_data *mp = NULL; +#endif + + dentry = tracing_init_dentry(); + latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry); + enable_root = debugfs_create_dir("enable", latency_hist_root); + +#ifdef CONFIG_INTERRUPT_OFF_HIST + dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(irqsoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(irqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#ifdef CONFIG_PREEMPT_OFF_HIST + dentry = debugfs_create_dir(preemptoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(preemptoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) + dentry = debugfs_create_dir(preemptirqsoff_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); + my_hist = &per_cpu(preemptirqsoff_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); +#endif + +#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) + entry = debugfs_create_file("preemptirqsoff", 0644, + enable_root, (void *)&preemptirqsoff_enabled_data, + &enable_fops); +#endif + +#ifdef CONFIG_WAKEUP_LATENCY_HIST + dentry = debugfs_create_dir(wakeup_latency_hist_dir, + latency_hist_root); + dentry_sharedprio = debugfs_create_dir( + wakeup_latency_hist_dir_sharedprio, dentry); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(wakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + entry = debugfs_create_file(name, 0444, dentry_sharedprio, + &per_cpu(wakeup_latency_hist_sharedprio, i), + &latency_hist_fops); + my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + + mp = &per_cpu(wakeup_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + + mp = &per_cpu(wakeup_maxlatproc_sharedprio, i); + entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&wakeup_pid, &pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)WAKEUP_LATENCY, &latency_hist_reset_fops); + entry = debugfs_create_file("reset", 0644, dentry_sharedprio, + (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops); + entry = debugfs_create_file("wakeup", 0644, + enable_root, (void *)&wakeup_latency_enabled_data, + &enable_fops); +#endif + +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + dentry = debugfs_create_dir(missed_timer_offsets_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(missed_timer_offsets, i), &latency_hist_fops); + my_hist = &per_cpu(missed_timer_offsets, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + mp = &per_cpu(missed_timer_offsets_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("pid", 0644, dentry, + (void *)&missed_timer_offsets_pid, &pid_fops); + entry = debugfs_create_file("reset", 0644, dentry, + (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops); + entry = debugfs_create_file("missed_timer_offsets", 0644, + enable_root, (void *)&missed_timer_offsets_enabled_data, + &enable_fops); +#endif + +#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ + defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) + dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir, + latency_hist_root); + for_each_possible_cpu(i) { + sprintf(name, cpufmt, i); + entry = debugfs_create_file(name, 0444, dentry, + &per_cpu(timerandwakeup_latency_hist, i), + &latency_hist_fops); + my_hist = &per_cpu(timerandwakeup_latency_hist, i); + atomic_set(&my_hist->hist_mode, 1); + my_hist->min_lat = LONG_MAX; + + sprintf(name, cpufmt_maxlatproc, i); + mp = &per_cpu(timerandwakeup_maxlatproc, i); + entry = debugfs_create_file(name, 0444, dentry, mp, + &maxlatproc_fops); + clear_maxlatprocdata(mp); + } + entry = debugfs_create_file("reset", 0644, dentry, + (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops); + entry = debugfs_create_file("timerandwakeup", 0644, + enable_root, (void *)&timerandwakeup_enabled_data, + &enable_fops); +#endif + return 0; +} + +__initcall(latency_hist_init); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6dbdf27..2e835e7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -431,7 +431,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) local_save_flags(irq_flags); buffer = global_trace.trace_buffer.buffer; - event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, + event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, irq_flags, preempt_count()); if (!event) return 0; @@ -1492,6 +1492,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, struct task_struct *tsk = current; entry->preempt_count = pc & 0xff; + entry->preempt_lazy_count = preempt_lazy_count(); entry->pid = (tsk) ? tsk->pid : 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT @@ -1501,7 +1502,10 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, #endif ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | - (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); + (need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | + (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; } EXPORT_SYMBOL_GPL(tracing_generic_entry_update); @@ -2400,14 +2404,17 @@ get_total_entries(struct trace_buffer *buf, static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n"); - seq_puts(m, "# / _-----=> irqs-off \n"); - seq_puts(m, "# | / _----=> need-resched \n"); - seq_puts(m, "# || / _---=> hardirq/softirq \n"); - seq_puts(m, "# ||| / _--=> preempt-depth \n"); - seq_puts(m, "# |||| / delay \n"); - seq_puts(m, "# cmd pid ||||| time | caller \n"); - seq_puts(m, "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _--------=> CPU# \n"); + seq_puts(m, "# / _-------=> irqs-off \n"); + seq_puts(m, "# | / _------=> need-resched \n"); + seq_puts(m, "# || / _-----=> need-resched_lazy \n"); + seq_puts(m, "# ||| / _----=> hardirq/softirq \n"); + seq_puts(m, "# |||| / _---=> preempt-depth \n"); + seq_puts(m, "# ||||| / _--=> preempt-lazy-depth\n"); + seq_puts(m, "# |||||| / _-=> migrate-disable \n"); + seq_puts(m, "# ||||||| / delay \n"); + seq_puts(m, "# cmd pid |||||||| time | caller \n"); + seq_puts(m, "# \\ / |||||||| \\ | / \n"); } static void print_event_info(struct trace_buffer *buf, struct seq_file *m) @@ -2431,13 +2438,16 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m) static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m) { print_event_info(buf, m); - seq_puts(m, "# _-----=> irqs-off\n"); - seq_puts(m, "# / _----=> need-resched\n"); - seq_puts(m, "# | / _---=> hardirq/softirq\n"); - seq_puts(m, "# || / _--=> preempt-depth\n"); - seq_puts(m, "# ||| / delay\n"); - seq_puts(m, "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n"); - seq_puts(m, "# | | | |||| | |\n"); + seq_puts(m, "# _-------=> irqs-off \n"); + seq_puts(m, "# / _------=> need-resched \n"); + seq_puts(m, "# |/ _-----=> need-resched_lazy \n"); + seq_puts(m, "# ||/ _----=> hardirq/softirq \n"); + seq_puts(m, "# |||/ _---=> preempt-depth \n"); + seq_puts(m, "# ||||/ _--=> preempt-lazy-depth\n"); + seq_puts(m, "# ||||| / _-=> migrate-disable \n"); + seq_puts(m, "# |||||| / delay\n"); + seq_puts(m, "# TASK-PID CPU# |||||| TIMESTAMP FUNCTION\n"); + seq_puts(m, "# | | | |||||| | |\n"); } void diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 51b4448..f705ef9 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -117,6 +117,7 @@ struct kretprobe_trace_entry_head { * NEED_RESCHED - reschedule is requested * HARDIRQ - inside an interrupt handler * SOFTIRQ - inside a softirq handler + * NEED_RESCHED_LAZY - lazy reschedule is requested */ enum trace_flag_type { TRACE_FLAG_IRQS_OFF = 0x01, @@ -124,6 +125,7 @@ enum trace_flag_type { TRACE_FLAG_NEED_RESCHED = 0x04, TRACE_FLAG_HARDIRQ = 0x08, TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_NEED_RESCHED_LAZY = 0x20, }; #define TRACE_BUF_SIZE 1024 diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 3d18aad..540cc6e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -166,6 +166,8 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); + __common_field(unsigned short, migrate_disable); + __common_field(unsigned short, padding); return ret; } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 2aefbee..2f4eb37 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -17,6 +17,7 @@ #include #include "trace.h" +#include static struct trace_array *irqsoff_trace __read_mostly; static int tracer_enabled __read_mostly; @@ -439,11 +440,13 @@ void start_critical_timings(void) { if (preempt_trace() || irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(TRACE_START, 1); } EXPORT_SYMBOL_GPL(start_critical_timings); void stop_critical_timings(void) { + trace_preemptirqsoff_hist(TRACE_STOP, 0); if (preempt_trace() || irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } @@ -453,6 +456,7 @@ EXPORT_SYMBOL_GPL(stop_critical_timings); #ifdef CONFIG_PROVE_LOCKING void time_hardirqs_on(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(a0, a1); } @@ -461,6 +465,7 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1) { if (!preempt_trace() && irq_trace()) start_critical_timing(a0, a1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } #else /* !CONFIG_PROVE_LOCKING */ @@ -486,6 +491,7 @@ inline void print_irqtrace_events(struct task_struct *curr) */ void trace_hardirqs_on(void) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } @@ -495,11 +501,13 @@ void trace_hardirqs_off(void) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } EXPORT_SYMBOL(trace_hardirqs_off); void trace_hardirqs_on_caller(unsigned long caller_addr) { + trace_preemptirqsoff_hist(IRQS_ON, 0); if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, caller_addr); } @@ -509,6 +517,7 @@ void trace_hardirqs_off_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, caller_addr); + trace_preemptirqsoff_hist(IRQS_OFF, 1); } EXPORT_SYMBOL(trace_hardirqs_off_caller); @@ -518,12 +527,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller); #ifdef CONFIG_PREEMPT_TRACER void trace_preempt_on(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(PREEMPT_ON, 0); if (preempt_trace() && !irq_trace()) stop_critical_timing(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { + trace_preemptirqsoff_hist(PREEMPT_ON, 1); if (preempt_trace() && !irq_trace()) start_critical_timing(a0, a1); } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bb922d9..2f7f9cb 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -606,6 +606,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) { char hardsoft_irq; char need_resched; + char need_resched_lazy; char irqs_off; int hardirq; int softirq; @@ -620,14 +621,17 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) '.'; need_resched = (entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.'; + need_resched_lazy = + (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; hardsoft_irq = (hardirq && softirq) ? 'H' : hardirq ? 'h' : softirq ? 's' : '.'; - if (!trace_seq_printf(s, "%c%c%c", - irqs_off, need_resched, hardsoft_irq)) + if (!trace_seq_printf(s, "%c%c%c%c", + irqs_off, need_resched, need_resched_lazy, + hardsoft_irq)) return 0; if (entry->preempt_count) @@ -635,6 +639,16 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) else ret = trace_seq_putc(s, '.'); + if (entry->preempt_lazy_count) + ret = trace_seq_printf(s, "%x", entry->preempt_lazy_count); + else + ret = trace_seq_putc(s, '.'); + + if (entry->migrate_disable) + ret = trace_seq_printf(s, "%x", entry->migrate_disable); + else + ret = trace_seq_putc(s, '.'); + return ret; } diff --git a/kernel/user.c b/kernel/user.c index 69b4c3d..b34eeaa 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -156,11 +156,11 @@ void free_uid(struct user_struct *up) if (!up) return; - local_irq_save(flags); + local_irq_save_nort(flags); if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) free_user(up, flags); else - local_irq_restore(flags); + local_irq_restore_nort(flags); } struct user_struct *alloc_uid(kuid_t uid) diff --git a/kernel/wait-simple.c b/kernel/wait-simple.c new file mode 100644 index 0000000..7dfa86d --- /dev/null +++ b/kernel/wait-simple.c @@ -0,0 +1,115 @@ +/* + * Simple waitqueues without fancy flags and callbacks + * + * (C) 2011 Thomas Gleixner + * + * Based on kernel/wait.c + * + * For licencing details see kernel-base/COPYING + */ +#include +#include +#include +#include + +/* Adds w to head->list. Must be called with head->lock locked. */ +static inline void __swait_enqueue(struct swait_head *head, struct swaiter *w) +{ + list_add(&w->node, &head->list); + /* We can't let the condition leak before the setting of head */ + smp_mb(); +} + +/* Removes w from head->list. Must be called with head->lock locked. */ +static inline void __swait_dequeue(struct swaiter *w) +{ + list_del_init(&w->node); +} + +void __init_swait_head(struct swait_head *head, struct lock_class_key *key) +{ + raw_spin_lock_init(&head->lock); + lockdep_set_class(&head->lock, key); + INIT_LIST_HEAD(&head->list); +} +EXPORT_SYMBOL(__init_swait_head); + +void swait_prepare_locked(struct swait_head *head, struct swaiter *w) +{ + w->task = current; + if (list_empty(&w->node)) + __swait_enqueue(head, w); +} + +void swait_prepare(struct swait_head *head, struct swaiter *w, int state) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&head->lock, flags); + swait_prepare_locked(head, w); + __set_current_state(state); + raw_spin_unlock_irqrestore(&head->lock, flags); +} +EXPORT_SYMBOL(swait_prepare); + +void swait_finish_locked(struct swait_head *head, struct swaiter *w) +{ + __set_current_state(TASK_RUNNING); + if (w->task) + __swait_dequeue(w); +} + +void swait_finish(struct swait_head *head, struct swaiter *w) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + if (w->task) { + raw_spin_lock_irqsave(&head->lock, flags); + __swait_dequeue(w); + raw_spin_unlock_irqrestore(&head->lock, flags); + } +} +EXPORT_SYMBOL(swait_finish); + +unsigned int +__swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num) +{ + struct swaiter *curr, *next; + int woken = 0; + + list_for_each_entry_safe(curr, next, &head->list, node) { + if (wake_up_state(curr->task, state)) { + __swait_dequeue(curr); + /* + * The waiting task can free the waiter as + * soon as curr->task = NULL is written, + * without taking any locks. A memory barrier + * is required here to prevent the following + * store to curr->task from getting ahead of + * the dequeue operation. + */ + smp_wmb(); + curr->task = NULL; + if (++woken == num) + break; + } + } + return woken; +} + +unsigned int +__swait_wake(struct swait_head *head, unsigned int state, unsigned int num) +{ + unsigned long flags; + int woken; + + if (!swaitqueue_active(head)) + return 0; + + raw_spin_lock_irqsave(&head->lock, flags); + woken = __swait_wake_locked(head, state, num); + raw_spin_unlock_irqrestore(&head->lock, flags); + return woken; +} +EXPORT_SYMBOL(__swait_wake); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 05039e3..3ff8baf 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -205,6 +205,8 @@ static int is_softlockup(unsigned long touch_ts) #ifdef CONFIG_HARDLOCKUP_DETECTOR +static DEFINE_RAW_SPINLOCK(watchdog_output_lock); + static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, @@ -239,10 +241,19 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - if (hardlockup_panic) + /* + * If early-printk is enabled then make sure we do not + * lock up in printk() and kill console logging: + */ + printk_kill(); + + if (hardlockup_panic) { panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu); - else + } else { + raw_spin_lock(&watchdog_output_lock); WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu); + raw_spin_unlock(&watchdog_output_lock); + } __this_cpu_write(hard_watchdog_warn, true); return; @@ -346,6 +357,7 @@ static void watchdog_enable(unsigned int cpu) /* kick off the timer for the hardlockup detector */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; + hrtimer->irqsafe = 1; if (!watchdog_enabled) { kthread_park(current); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 68086a3..2a81f06 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -47,6 +47,8 @@ #include #include #include +#include +#include #include "workqueue_internal.h" @@ -128,11 +130,11 @@ enum { * * PL: wq_pool_mutex protected. * - * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. + * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * WQ: wq->mutex protected. * - * WR: wq->mutex protected for writes. Sched-RCU protected for reads. + * WR: wq->mutex protected for writes. RCU protected for reads. * * MD: wq_mayday_lock protected. */ @@ -177,7 +179,7 @@ struct worker_pool { atomic_t nr_running ____cacheline_aligned_in_smp; /* - * Destruction of pool is sched-RCU protected to allow dereferences + * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; @@ -206,7 +208,7 @@ struct pool_workqueue { /* * Release of unbound pwq is punted to system_wq. See put_pwq() * and pwq_unbound_release_workfn() for details. pool_workqueue - * itself is also sched-RCU protected so that the first pwq can be + * itself is also RCU protected so that the first pwq can be * determined without grabbing wq->mutex. */ struct work_struct unbound_release_work; @@ -309,6 +311,8 @@ EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_wq); +static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); + static int worker_thread(void *__worker); static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from); @@ -317,14 +321,14 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, #include #define assert_rcu_or_pool_mutex() \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + rcu_lockdep_assert(rcu_read_lock_held() || \ lockdep_is_held(&wq_pool_mutex), \ - "sched RCU or wq_pool_mutex should be held") + "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex(wq) \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + rcu_lockdep_assert(rcu_read_lock_held() || \ lockdep_is_held(&wq->mutex), \ - "sched RCU or wq->mutex should be held") + "RCU or wq->mutex should be held") #ifdef CONFIG_LOCKDEP #define assert_manager_or_pool_lock(pool) \ @@ -346,7 +350,7 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, * @pool: iteration cursor * @pi: integer used for iteration * - * This must be called either with wq_pool_mutex held or sched RCU read + * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * @@ -379,7 +383,7 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, * @pwq: iteration cursor * @wq: the target workqueue * - * This must be called either with wq->mutex held or sched RCU read locked. + * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * @@ -527,7 +531,7 @@ static int worker_pool_assign_id(struct worker_pool *pool) * @wq: the target workqueue * @node: the node ID * - * This must be called either with pwq_lock held or sched RCU read locked. + * This must be called either with pwq_lock held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. */ @@ -631,8 +635,8 @@ static struct pool_workqueue *get_work_pwq(struct work_struct *work) * Return the worker_pool @work was last associated with. %NULL if none. * * Pools are created and destroyed under wq_pool_mutex, and allows read - * access under sched-RCU read lock. As such, this function should be - * called under wq_pool_mutex or with preemption disabled. + * access under RCU read lock. As such, this function should be + * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used @@ -788,44 +792,31 @@ static void wake_up_worker(struct worker_pool *pool) } /** - * wq_worker_waking_up - a worker is waking up - * @task: task waking up - * @cpu: CPU @task is waking up to - * - * This function is called during try_to_wake_up() when a worker is - * being awoken. + * wq_worker_running - a worker is running again + * @task: task returning from sleep * - * CONTEXT: - * spin_lock_irq(rq->lock) + * This function is called when a worker returns from schedule() */ -void wq_worker_waking_up(struct task_struct *task, int cpu) +void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); - if (!(worker->flags & WORKER_NOT_RUNNING)) { - WARN_ON_ONCE(worker->pool->cpu != cpu); + if (!worker->sleeping) + return; + if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&worker->pool->nr_running); - } + worker->sleeping = 0; } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep - * @cpu: CPU in question, must be the current CPU number - * - * This function is called during schedule() when a busy worker is - * going to sleep. Worker on the same cpu can be woken up by - * returning pointer to its task. - * - * CONTEXT: - * spin_lock_irq(rq->lock) - * - * RETURNS: - * Worker task on @cpu to wake up, %NULL if none. + * This function is called from schedule() when a busy worker is + * going to sleep. */ -struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) +void wq_worker_sleeping(struct task_struct *task) { - struct worker *worker = kthread_data(task), *to_wakeup = NULL; + struct worker *next, *worker = kthread_data(task); struct worker_pool *pool; /* @@ -834,14 +825,15 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) - return NULL; + return; pool = worker->pool; - /* this can only happen on the local cpu */ - if (WARN_ON_ONCE(cpu != raw_smp_processor_id())) - return NULL; + if (WARN_ON_ONCE(worker->sleeping)) + return; + worker->sleeping = 1; + spin_lock_irq(&pool->lock); /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). @@ -854,9 +846,12 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) * lock is safe. */ if (atomic_dec_and_test(&pool->nr_running) && - !list_empty(&pool->worklist)) - to_wakeup = first_worker(pool); - return to_wakeup ? to_wakeup->task : NULL; + !list_empty(&pool->worklist)) { + next = first_worker(pool); + if (next) + wake_up_process(next->task); + } + spin_unlock_irq(&pool->lock); } /** @@ -1063,12 +1058,12 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* - * As both pwqs and pools are sched-RCU protected, the + * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ - spin_lock_irq(&pwq->pool->lock); + local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); put_pwq(pwq); - spin_unlock_irq(&pwq->pool->lock); + local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); } } @@ -1168,7 +1163,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, struct worker_pool *pool; struct pool_workqueue *pwq; - local_irq_save(*flags); + local_lock_irqsave(pendingb_lock, *flags); /* try to steal the timer if it exists */ if (is_dwork) { @@ -1187,6 +1182,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; + rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. @@ -1225,14 +1221,16 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, set_work_pool_and_keep_pending(work, pool->id); spin_unlock(&pool->lock); + rcu_read_unlock(); return 1; } spin_unlock(&pool->lock); fail: - local_irq_restore(*flags); + rcu_read_unlock(); + local_unlock_irqrestore(pendingb_lock, *flags); if (work_is_canceling(work)) return -ENOENT; - cpu_relax(); + cpu_chill(); return -EAGAIN; } @@ -1301,7 +1299,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ - WARN_ON_ONCE(!irqs_disabled()); + WARN_ON_ONCE_NONRT(!irqs_disabled()); debug_work_activate(work); @@ -1309,6 +1307,8 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; + + rcu_read_lock(); retry: if (req_cpu == WORK_CPU_UNBOUND) cpu = raw_smp_processor_id(); @@ -1365,10 +1365,8 @@ retry: /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); - if (WARN_ON(!list_empty(&work->entry))) { - spin_unlock(&pwq->pool->lock); - return; - } + if (WARN_ON(!list_empty(&work->entry))) + goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); @@ -1384,7 +1382,9 @@ retry: insert_work(pwq, work, worklist, work_flags); +out: spin_unlock(&pwq->pool->lock); + rcu_read_unlock(); } /** @@ -1404,14 +1404,14 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, bool ret = false; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(pendingb_lock,flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_work(cpu, wq, work); ret = true; } - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } EXPORT_SYMBOL(queue_work_on); @@ -1478,14 +1478,14 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, unsigned long flags; /* read the comment in __queue_work() */ - local_irq_save(flags); + local_lock_irqsave(pendingb_lock, flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); @@ -1520,7 +1520,7 @@ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, if (likely(ret >= 0)) { __queue_delayed_work(cpu, wq, dwork, delay); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); } /* -ENOENT from try_to_grab_pending() becomes %true */ @@ -2775,14 +2775,14 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) might_sleep(); - local_irq_disable(); + rcu_read_lock(); pool = get_work_pool(work); if (!pool) { - local_irq_enable(); + rcu_read_unlock(); return false; } - spin_lock(&pool->lock); + spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { @@ -2809,10 +2809,11 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) else lock_map_acquire_read(&pwq->wq->lockdep_map); lock_map_release(&pwq->wq->lockdep_map); - + rcu_read_unlock(); return true; already_gone: spin_unlock_irq(&pool->lock); + rcu_read_unlock(); return false; } @@ -2861,7 +2862,7 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) /* tell other tasks trying to grab @work to back off */ mark_work_canceling(work); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); flush_work(work); clear_work_data(work); @@ -2906,10 +2907,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync); */ bool flush_delayed_work(struct delayed_work *dwork) { - local_irq_disable(); + local_lock_irq(pendingb_lock); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); - local_irq_enable(); + local_unlock_irq(pendingb_lock); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); @@ -2940,7 +2941,7 @@ bool cancel_delayed_work(struct delayed_work *dwork) set_work_pool_and_clear_pending(&dwork->work, get_work_pool_id(&dwork->work)); - local_irq_restore(flags); + local_unlock_irqrestore(pendingb_lock, flags); return ret; } EXPORT_SYMBOL(cancel_delayed_work); @@ -3123,7 +3124,8 @@ static ssize_t wq_pool_ids_show(struct device *dev, const char *delim = ""; int node, written = 0; - rcu_read_lock_sched(); + get_online_cpus(); + rcu_read_lock(); for_each_node(node) { written += scnprintf(buf + written, PAGE_SIZE - written, "%s%d:%d", delim, node, @@ -3131,7 +3133,8 @@ static ssize_t wq_pool_ids_show(struct device *dev, delim = " "; } written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); - rcu_read_unlock_sched(); + rcu_read_unlock(); + put_online_cpus(); return written; } @@ -3494,7 +3497,7 @@ static void rcu_free_pool(struct rcu_head *rcu) * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * - * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU + * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). @@ -3541,8 +3544,8 @@ static void put_unbound_pool(struct worker_pool *pool) del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); - /* sched-RCU protected to allow dereferences from get_work_pool() */ - call_rcu_sched(&pool->rcu, rcu_free_pool); + /* RCU protected to allow dereferences from get_work_pool() */ + call_rcu(&pool->rcu, rcu_free_pool); } /** @@ -3652,7 +3655,7 @@ static void pwq_unbound_release_workfn(struct work_struct *work) put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); - call_rcu_sched(&pwq->rcu, rcu_free_pwq); + call_rcu(&pwq->rcu, rcu_free_pwq); /* * If we're the last pwq going away, @wq is already dead and no one @@ -4357,7 +4360,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) struct pool_workqueue *pwq; bool ret; - rcu_read_lock_sched(); + rcu_read_lock(); + preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); @@ -4368,7 +4372,8 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); ret = !list_empty(&pwq->delayed_works); - rcu_read_unlock_sched(); + preempt_enable(); + rcu_read_unlock(); return ret; } @@ -4394,16 +4399,15 @@ unsigned int work_busy(struct work_struct *work) if (work_pending(work)) ret |= WORK_BUSY_PENDING; - local_irq_save(flags); + rcu_read_lock(); pool = get_work_pool(work); if (pool) { - spin_lock(&pool->lock); + spin_lock_irqsave(&pool->lock, flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; - spin_unlock(&pool->lock); + spin_unlock_irqrestore(&pool->lock, flags); } - local_irq_restore(flags); - + rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); @@ -4848,16 +4852,16 @@ bool freeze_workqueues_busy(void) * nr_active is monotonically decreasing. It's safe * to peek without lock. */ - rcu_read_lock_sched(); + rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; - rcu_read_unlock_sched(); + rcu_read_unlock(); goto out_unlock; } } - rcu_read_unlock_sched(); + rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index ad83c96..ddf1d34 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -41,6 +41,7 @@ struct worker { unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ + int sleeping; /* None */ /* * Opaque string set with work_set_desc(). Printed out with task @@ -66,7 +67,7 @@ static inline struct worker *current_wq_worker(void) * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched.c and workqueue.c. */ -void wq_worker_waking_up(struct task_struct *task, int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); +void wq_worker_running(struct task_struct *task); +void wq_worker_sleeping(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ diff --git a/lib/Kconfig b/lib/Kconfig index fe01d41..8bc3068 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -315,6 +315,7 @@ config CHECK_SIGNATURE config CPUMASK_OFFSTACK bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS + depends on !PREEMPT_RT_FULL help Use dynamic allocation for cpumask_var_t, instead of putting them on the stack. This is a bit more expensive, but avoids diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 74fdc5c..0996f48 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -164,7 +164,7 @@ config DEBUG_KERNEL config DEBUG_SHIRQ bool "Debug shared IRQ handlers" - depends on DEBUG_KERNEL && GENERIC_HARDIRQS + depends on DEBUG_KERNEL && GENERIC_HARDIRQS && !PREEMPT_RT_BASE help Enable this to generate a spurious interrupt as soon as a shared interrupt handler is registered, and just before one is deregistered. diff --git a/lib/Makefile b/lib/Makefile index 9efe480..ab76fa2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -41,8 +41,11 @@ obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o + +ifneq ($(CONFIG_PREEMPT_RT_FULL),y) lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o +endif lib-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o GCOV_PROFILE_hweight.o := n diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 37061ed..0ee67a1 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -308,7 +308,10 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack) struct debug_obj *obj; unsigned long flags; - fill_pool(); +#ifdef CONFIG_PREEMPT_RT_FULL + if (preempt_count() == 0 && !irqs_disabled()) +#endif + fill_pool(); db = get_bucket((unsigned long) addr); diff --git a/lib/idr.c b/lib/idr.c index cca4b93..b11de4e 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -37,6 +37,7 @@ #include #include #include +#include #define MAX_IDR_SHIFT (sizeof(int) * 8 - 1) #define MAX_IDR_BIT (1U << MAX_IDR_SHIFT) @@ -389,6 +390,36 @@ int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id) } EXPORT_SYMBOL(__idr_get_new_above); +#ifdef CONFIG_PREEMPT_RT_FULL +static DEFINE_LOCAL_IRQ_LOCK(idr_lock); + +static inline void idr_preload_lock(void) +{ + local_lock(idr_lock); +} + +static inline void idr_preload_unlock(void) +{ + local_unlock(idr_lock); +} + +void idr_preload_end(void) +{ + idr_preload_unlock(); +} +EXPORT_SYMBOL(idr_preload_end); +#else +static inline void idr_preload_lock(void) +{ + preempt_disable(); +} + +static inline void idr_preload_unlock(void) +{ + preempt_enable(); +} +#endif + /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading @@ -423,7 +454,7 @@ void idr_preload(gfp_t gfp_mask) WARN_ON_ONCE(in_interrupt()); might_sleep_if(gfp_mask & __GFP_WAIT); - preempt_disable(); + idr_preload_lock(); /* * idr_alloc() is likely to succeed w/o full idr_layer buffer and @@ -435,9 +466,9 @@ void idr_preload(gfp_t gfp_mask) while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) { struct idr_layer *new; - preempt_enable(); + idr_preload_unlock(); new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); - preempt_disable(); + idr_preload_lock(); if (!new) break; diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index c3eb261..23b8564 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -1175,6 +1175,7 @@ void locking_selftest(void) printk(" --------------------------------------------------------------------------\n"); +#ifndef CONFIG_PREEMPT_RT_FULL /* * irq-context testcases: */ @@ -1187,6 +1188,28 @@ void locking_selftest(void) DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); +#else + /* On -rt, we only do hardirq context test for raw spinlock */ + DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); + DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); + + DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); + DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); + + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); + + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); + DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); +#endif if (unexpected_testcase_failures) { printk("-----------------------------------------------------------------\n"); diff --git a/lib/percpu-rwsem.c b/lib/percpu-rwsem.c index 652a8ee..2db0f42 100644 --- a/lib/percpu-rwsem.c +++ b/lib/percpu-rwsem.c @@ -84,8 +84,12 @@ void percpu_down_read(struct percpu_rw_semaphore *brw) down_read(&brw->rw_sem); atomic_inc(&brw->slow_read_ctr); +#ifdef CONFIG_PREEMPT_RT_FULL + up_read(&brw->rw_sem); +#else /* avoid up_read()->rwsem_release() */ __up_read(&brw->rw_sem); +#endif } void percpu_up_read(struct percpu_rw_semaphore *brw) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index e796429..63bac7d 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -215,12 +215,13 @@ radix_tree_node_alloc(struct radix_tree_root *root) * succeed in getting a node here (and never reach * kmem_cache_alloc) */ - rtp = &__get_cpu_var(radix_tree_preloads); + rtp = &get_cpu_var(radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes[rtp->nr - 1]; rtp->nodes[rtp->nr - 1] = NULL; rtp->nr--; } + put_cpu_var(radix_tree_preloads); } if (ret == NULL) ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); @@ -255,6 +256,7 @@ radix_tree_node_free(struct radix_tree_node *node) call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } +#ifndef CONFIG_PREEMPT_RT_FULL /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On @@ -289,6 +291,7 @@ out: return ret; } EXPORT_SYMBOL(radix_tree_preload); +#endif /* * Return the maximum key which can be store into a diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 3e7df38..49e45de 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -534,7 +534,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter) flush_kernel_dcache_page(miter->page); if (miter->__flags & SG_MITER_ATOMIC) { - WARN_ON_ONCE(preemptible()); + WARN_ON_ONCE(!pagefault_disabled()); kunmap_atomic(miter->addr); } else kunmap(miter->page); @@ -574,7 +574,7 @@ static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, sg_miter_start(&miter, sgl, nents, sg_flags); - local_irq_save(flags); + local_irq_save_nort(flags); while (sg_miter_next(&miter) && offset < buflen) { unsigned int len; @@ -591,7 +591,7 @@ static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, sg_miter_stop(&miter); - local_irq_restore(flags); + local_irq_restore_nort(flags); return offset; } diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 4c0d0e5..dbb1570 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -39,9 +39,9 @@ notrace unsigned int debug_smp_processor_id(void) if (!printk_ratelimit()) goto out_enable; - printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] " - "code: %s/%d\n", - preempt_count() - 1, current->comm, current->pid); + printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x %08x] " + "code: %s/%d\n", preempt_count() - 1, + __migrate_disabled(current), current->comm, current->pid); print_symbol("caller is %s\n", (long)__builtin_return_address(0)); dump_stack(); diff --git a/lib/spinlock_debug.c b/lib/spinlock_debug.c index 0374a59..9497033 100644 --- a/lib/spinlock_debug.c +++ b/lib/spinlock_debug.c @@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, EXPORT_SYMBOL(__raw_spin_lock_init); +#ifndef CONFIG_PREEMPT_RT_FULL void __rwlock_init(rwlock_t *lock, const char *name, struct lock_class_key *key) { @@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const char *name, } EXPORT_SYMBOL(__rwlock_init); +#endif static void spin_dump(raw_spinlock_t *lock, const char *msg) { @@ -159,6 +161,7 @@ void do_raw_spin_unlock(raw_spinlock_t *lock) arch_spin_unlock(&lock->raw_lock); } +#ifndef CONFIG_PREEMPT_RT_FULL static void rwlock_bug(rwlock_t *lock, const char *msg) { if (!debug_locks_off()) @@ -300,3 +303,5 @@ void do_raw_write_unlock(rwlock_t *lock) debug_write_unlock(lock); arch_write_unlock(&lock->raw_lock); } + +#endif diff --git a/localversion-rt b/localversion-rt new file mode 100644 index 0000000..b72862e --- /dev/null +++ b/localversion-rt @@ -0,0 +1 @@ +-rt30 diff --git a/mm/Kconfig b/mm/Kconfig index e742d06..4ff7729 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -384,7 +384,7 @@ config NOMMU_INITIAL_TRIM_EXCESS config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" - depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE + depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL select COMPACTION help Transparent Hugepages allows the kernel to use huge pages and diff --git a/mm/bounce.c b/mm/bounce.c index 5a7d58f..b09bb4e 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -51,11 +51,11 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) unsigned long flags; unsigned char *vto; - local_irq_save(flags); + local_irq_save_nort(flags); vto = kmap_atomic(to->bv_page); memcpy(vto + to->bv_offset, vfrom, to->bv_len); kunmap_atomic(vto); - local_irq_restore(flags); + local_irq_restore_nort(flags); } #else /* CONFIG_HIGHMEM */ diff --git a/mm/filemap.c b/mm/filemap.c index 7905fe7..bf2060d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1974,7 +1974,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, char *kaddr; size_t copied; - BUG_ON(!in_atomic()); + BUG_ON(!pagefault_disabled()); kaddr = kmap_atomic(page); if (likely(i->nr_segs == 1)) { int left; diff --git a/mm/highmem.c b/mm/highmem.c index b32b70c..b1c7d43 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -29,10 +29,11 @@ #include #include - +#ifndef CONFIG_PREEMPT_RT_FULL #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) DEFINE_PER_CPU(int, __kmap_atomic_idx); #endif +#endif /* * Virtual_count is not a pure "count". @@ -47,8 +48,9 @@ DEFINE_PER_CPU(int, __kmap_atomic_idx); unsigned long totalhigh_pages __read_mostly; EXPORT_SYMBOL(totalhigh_pages); - +#ifndef CONFIG_PREEMPT_RT_FULL EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); +#endif unsigned int nr_free_highpages (void) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 134e210..17a0546 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2440,7 +2440,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync) /* Notify other cpus that system-wide "drain" is running */ get_online_cpus(); - curcpu = get_cpu(); + curcpu = get_cpu_light(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; @@ -2457,7 +2457,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync) schedule_work_on(cpu, &stock->work); } } - put_cpu(); + put_cpu_light(); if (!sync) goto out; diff --git a/mm/memory.c b/mm/memory.c index 4b60011..ee422e6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3746,6 +3746,32 @@ unlock: return 0; } +#ifdef CONFIG_PREEMPT_RT_FULL +void pagefault_disable(void) +{ + migrate_disable(); + current->pagefault_disabled++; + /* + * make sure to have issued the store before a pagefault + * can hit. + */ + barrier(); +} +EXPORT_SYMBOL(pagefault_disable); + +void pagefault_enable(void) +{ + /* + * make sure to issue those last loads/stores before enabling + * the pagefault handler again. + */ + barrier(); + current->pagefault_disabled--; + migrate_enable(); +} +EXPORT_SYMBOL(pagefault_enable); +#endif + /* * By the time we get here, we already hold the mm semaphore */ @@ -4294,3 +4320,35 @@ void copy_user_huge_page(struct page *dst, struct page *src, } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + +#if defined(CONFIG_PREEMPT_RT_FULL) && (USE_SPLIT_PTLOCKS > 0) +/* + * Heinous hack, relies on the caller doing something like: + * + * pte = alloc_pages(PGALLOC_GFP, 0); + * if (pte) + * pgtable_page_ctor(pte); + * return pte; + * + * This ensures we release the page and return NULL when the + * lock allocation fails. + */ +struct page *pte_lock_init(struct page *page) +{ + page->ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL); + if (page->ptl) { + spin_lock_init(__pte_lockptr(page)); + } else { + __free_page(page); + page = NULL; + } + return page; +} + +void pte_lock_deinit(struct page *page) +{ + kfree(page->ptl); + page->mapping = NULL; +} + +#endif diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 8a8cd02..adfce87 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -23,6 +23,7 @@ void use_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); + preempt_disable_rt(); active_mm = tsk->active_mm; if (active_mm != mm) { atomic_inc(&mm->mm_count); @@ -30,6 +31,7 @@ void use_mm(struct mm_struct *mm) } tsk->mm = mm; switch_mm(active_mm, mm, tsk); + preempt_enable_rt(); task_unlock(tsk); if (active_mm != mm) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2ee0fd3..b94a58e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -60,6 +60,7 @@ #include #include #include +#include #include #include @@ -221,6 +222,18 @@ EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif +static DEFINE_LOCAL_IRQ_LOCK(pa_lock); + +#ifdef CONFIG_PREEMPT_RT_BASE +# define cpu_lock_irqsave(cpu, flags) \ + local_lock_irqsave_on(pa_lock, flags, cpu) +# define cpu_unlock_irqrestore(cpu, flags) \ + local_unlock_irqrestore_on(pa_lock, flags, cpu) +#else +# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) +# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) +#endif + int page_group_by_mobility_disabled __read_mostly; void set_pageblock_migratetype(struct page *page, int migratetype) @@ -621,7 +634,7 @@ static inline int free_pages_check(struct page *page) } /* - * Frees a number of pages from the PCP lists + * Frees a number of pages which have been collected from the pcp lists. * Assumes all pages on list are in same zone, and of same order. * count is the number of pages to free. * @@ -632,16 +645,50 @@ static inline int free_pages_check(struct page *page) * pinned" detection logic. */ static void free_pcppages_bulk(struct zone *zone, int count, - struct per_cpu_pages *pcp) + struct list_head *list) { - int migratetype = 0; - int batch_free = 0; int to_free = count; + unsigned long flags; - spin_lock(&zone->lock); + spin_lock_irqsave(&zone->lock, flags); zone->all_unreclaimable = 0; zone->pages_scanned = 0; + while (!list_empty(list)) { + struct page *page = list_first_entry(list, struct page, lru); + int mt; /* migratetype of the to-be-freed page */ + + /* must delete as __free_one_page list manipulates */ + list_del(&page->lru); + + mt = get_freepage_migratetype(page); + /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ + __free_one_page(page, zone, 0, mt); + trace_mm_page_pcpu_drain(page, 0, mt); + if (likely(!is_migrate_isolate_page(page))) { + __mod_zone_page_state(zone, NR_FREE_PAGES, 1); + if (is_migrate_cma(mt)) + __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); + } + + to_free--; + } + WARN_ON(to_free != 0); + spin_unlock_irqrestore(&zone->lock, flags); +} + +/* + * Moves a number of pages from the PCP lists to free list which + * is freed outside of the locked region. + * + * Assumes all pages on list are in same zone, and of same order. + * count is the number of pages to free. + */ +static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, + struct list_head *dst) +{ + int migratetype = 0, batch_free = 0; + while (to_free) { struct page *page; struct list_head *list; @@ -657,7 +704,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, batch_free++; if (++migratetype == MIGRATE_PCPTYPES) migratetype = 0; - list = &pcp->lists[migratetype]; + list = &src->lists[migratetype]; } while (list_empty(list)); /* This is the only non-empty list. Free them all. */ @@ -665,36 +712,26 @@ static void free_pcppages_bulk(struct zone *zone, int count, batch_free = to_free; do { - int mt; /* migratetype of the to-be-freed page */ - - page = list_entry(list->prev, struct page, lru); - /* must delete as __free_one_page list manipulates */ + page = list_last_entry(list, struct page, lru); list_del(&page->lru); - mt = get_freepage_migratetype(page); - /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, mt); - trace_mm_page_pcpu_drain(page, 0, mt); - if (likely(!is_migrate_isolate_page(page))) { - __mod_zone_page_state(zone, NR_FREE_PAGES, 1); - if (is_migrate_cma(mt)) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); - } + list_add(&page->lru, dst); } while (--to_free && --batch_free && !list_empty(list)); } - spin_unlock(&zone->lock); } static void free_one_page(struct zone *zone, struct page *page, int order, int migratetype) { - spin_lock(&zone->lock); + unsigned long flags; + + spin_lock_irqsave(&zone->lock, flags); zone->all_unreclaimable = 0; zone->pages_scanned = 0; __free_one_page(page, zone, order, migratetype); if (unlikely(!is_migrate_isolate(migratetype))) __mod_zone_freepage_state(zone, 1 << order, migratetype); - spin_unlock(&zone->lock); + spin_unlock_irqrestore(&zone->lock, flags); } static bool free_pages_prepare(struct page *page, unsigned int order) @@ -731,12 +768,12 @@ static void __free_pages_ok(struct page *page, unsigned int order) if (!free_pages_prepare(page, order)) return; - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); __count_vm_events(PGFREE, 1 << order); migratetype = get_pageblock_migratetype(page); set_freepage_migratetype(page, migratetype); free_one_page(page_zone(page), page, order, migratetype); - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); } /* @@ -1178,18 +1215,20 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) { unsigned long flags; + LIST_HEAD(dst); int to_drain; - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); if (pcp->count >= pcp->batch) to_drain = pcp->batch; else to_drain = pcp->count; if (to_drain > 0) { - free_pcppages_bulk(zone, to_drain, pcp); + isolate_pcp_pages(to_drain, pcp, &dst); pcp->count -= to_drain; } - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); + free_pcppages_bulk(zone, to_drain, &dst); } #endif @@ -1208,16 +1247,21 @@ static void drain_pages(unsigned int cpu) for_each_populated_zone(zone) { struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; + LIST_HEAD(dst); + int count; - local_irq_save(flags); + cpu_lock_irqsave(cpu, flags); pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; - if (pcp->count) { - free_pcppages_bulk(zone, pcp->count, pcp); + count = pcp->count; + if (count) { + isolate_pcp_pages(count, pcp, &dst); pcp->count = 0; } - local_irq_restore(flags); + cpu_unlock_irqrestore(cpu, flags); + if (count) + free_pcppages_bulk(zone, count, &dst); } } @@ -1270,7 +1314,12 @@ void drain_all_pages(void) else cpumask_clear_cpu(cpu, &cpus_with_pcps); } +#ifndef CONFIG_PREEMPT_RT_BASE on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1); +#else + for_each_cpu(cpu, &cpus_with_pcps) + drain_pages(cpu); +#endif } #ifdef CONFIG_HIBERNATION @@ -1325,7 +1374,7 @@ void free_hot_cold_page(struct page *page, int cold) migratetype = get_pageblock_migratetype(page); set_freepage_migratetype(page, migratetype); - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); __count_vm_event(PGFREE); /* @@ -1350,12 +1399,19 @@ void free_hot_cold_page(struct page *page, int cold) list_add(&page->lru, &pcp->lists[migratetype]); pcp->count++; if (pcp->count >= pcp->high) { - free_pcppages_bulk(zone, pcp->batch, pcp); + LIST_HEAD(dst); + int count; + + isolate_pcp_pages(pcp->batch, pcp, &dst); pcp->count -= pcp->batch; + count = pcp->batch; + local_unlock_irqrestore(pa_lock, flags); + free_pcppages_bulk(zone, count, &dst); + return; } out: - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); } /* @@ -1485,7 +1541,7 @@ again: struct per_cpu_pages *pcp; struct list_head *list; - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; if (list_empty(list)) { @@ -1517,18 +1573,20 @@ again: */ WARN_ON_ONCE(order > 1); } - spin_lock_irqsave(&zone->lock, flags); + local_spin_lock_irqsave(pa_lock, &zone->lock, flags); page = __rmqueue(zone, order, migratetype); - spin_unlock(&zone->lock); - if (!page) + if (!page) { + spin_unlock(&zone->lock); goto failed; + } __mod_zone_freepage_state(zone, -(1 << order), get_pageblock_migratetype(page)); + spin_unlock(&zone->lock); } __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); VM_BUG_ON(bad_range(zone, page)); if (prep_new_page(page, order, gfp_flags)) @@ -1536,7 +1594,7 @@ again: return page; failed: - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); return NULL; } @@ -2182,8 +2240,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct page *page; /* Page migration frees to the PCP lists but we want merging */ - drain_pages(get_cpu()); - put_cpu(); + drain_pages(get_cpu_light()); + put_cpu_light(); page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, @@ -5233,6 +5291,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self, void __init page_alloc_init(void) { hotcpu_notifier(page_alloc_cpu_notify, 0); + local_irq_lock_init(pa_lock); } /* @@ -5471,11 +5530,11 @@ int __meminit init_per_zone_wmark_min(void) module_init(init_per_zone_wmark_min) /* - * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so + * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so * that we can call two helper functions whenever min_free_kbytes * changes. */ -int min_free_kbytes_sysctl_handler(ctl_table *table, int write, +int min_free_kbytes_sysctl_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); @@ -6051,21 +6110,23 @@ static int __meminit __zone_pcp_update(void *data) { struct zone *zone = data; int cpu; - unsigned long batch = zone_batchsize(zone), flags; + unsigned long flags; for_each_possible_cpu(cpu) { struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; + LIST_HEAD(dst); pset = per_cpu_ptr(zone->pageset, cpu); pcp = &pset->pcp; - local_irq_save(flags); - if (pcp->count > 0) - free_pcppages_bulk(zone, pcp->count, pcp); + cpu_lock_irqsave(cpu, flags); + if (pcp->count > 0) { + isolate_pcp_pages(pcp->count, pcp, &dst); + free_pcppages_bulk(zone, pcp->count, &dst); + } drain_zonestat(zone, pset); - setup_pageset(pset, batch); - local_irq_restore(flags); + cpu_unlock_irqrestore(cpu, flags); } return 0; } @@ -6083,7 +6144,7 @@ void zone_pcp_reset(struct zone *zone) struct per_cpu_pageset *pset; /* avoid races with drain_pages() */ - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); if (zone->pageset != &boot_pageset) { for_each_online_cpu(cpu) { pset = per_cpu_ptr(zone->pageset, cpu); @@ -6092,7 +6153,7 @@ void zone_pcp_reset(struct zone *zone) free_percpu(zone->pageset); zone->pageset = &boot_pageset; } - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); } #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 6d757e3a..98caeee 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -13,6 +13,14 @@ static unsigned long total_usage; +static void page_cgroup_lock_init(struct page_cgroup *pc, int nr_pages) +{ +#ifdef CONFIG_PREEMPT_RT_BASE + for (; nr_pages; nr_pages--, pc++) + spin_lock_init(&pc->pcg_lock); +#endif +} + #if !defined(CONFIG_SPARSEMEM) @@ -60,6 +68,7 @@ static int __init alloc_node_page_cgroup(int nid) return -ENOMEM; NODE_DATA(nid)->node_page_cgroup = base; total_usage += table_size; + page_cgroup_lock_init(base, nr_pages); return 0; } @@ -150,6 +159,8 @@ static int __meminit init_section_page_cgroup(unsigned long pfn, int nid) return -ENOMEM; } + page_cgroup_lock_init(base, PAGES_PER_SECTION); + /* * The passed "pfn" may not be aligned to SECTION. For the calculation * we need to apply a mask. diff --git a/mm/slab.c b/mm/slab.c index bd88411..1e9330f 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -116,6 +116,7 @@ #include #include #include +#include #include @@ -633,12 +634,78 @@ static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep) #endif static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); +static DEFINE_PER_CPU(struct list_head, slab_free_list); +static DEFINE_LOCAL_IRQ_LOCK(slab_lock); + +#ifndef CONFIG_PREEMPT_RT_BASE +# define slab_on_each_cpu(func, cp) on_each_cpu(func, cp, 1) +#else +/* + * execute func() for all CPUs. On PREEMPT_RT we dont actually have + * to run on the remote CPUs - we only have to take their CPU-locks. + * (This is a rare operation, so cacheline bouncing is not an issue.) + */ +static void +slab_on_each_cpu(void (*func)(void *arg, int this_cpu), void *arg) +{ + unsigned int i; + + get_cpu_light(); + for_each_online_cpu(i) + func(arg, i); + put_cpu_light(); +} + +static void lock_slab_on(unsigned int cpu) +{ + local_lock_irq_on(slab_lock, cpu); +} + +static void unlock_slab_on(unsigned int cpu) +{ + local_unlock_irq_on(slab_lock, cpu); +} +#endif + +static void free_delayed(struct list_head *h) +{ + while(!list_empty(h)) { + struct page *page = list_first_entry(h, struct page, lru); + + list_del(&page->lru); + __free_pages(page, page->index); + } +} + +static void unlock_l3_and_free_delayed(spinlock_t *list_lock) +{ + LIST_HEAD(tmp); + + list_splice_init(&__get_cpu_var(slab_free_list), &tmp); + local_spin_unlock_irq(slab_lock, list_lock); + free_delayed(&tmp); +} + +static void unlock_slab_and_free_delayed(unsigned long flags) +{ + LIST_HEAD(tmp); + + list_splice_init(&__get_cpu_var(slab_free_list), &tmp); + local_unlock_irqrestore(slab_lock, flags); + free_delayed(&tmp); +} static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) { return cachep->array[smp_processor_id()]; } +static inline struct array_cache *cpu_cache_get_on_cpu(struct kmem_cache *cachep, + int cpu) +{ + return cachep->array[cpu]; +} + static size_t slab_mgmt_size(size_t nr_objs, size_t align) { return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align); @@ -1073,9 +1140,10 @@ static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n) if (n->alien) { struct array_cache *ac = n->alien[node]; - if (ac && ac->avail && spin_trylock_irq(&ac->lock)) { + if (ac && ac->avail && + local_spin_trylock_irq(slab_lock, &ac->lock)) { __drain_alien_cache(cachep, ac, node); - spin_unlock_irq(&ac->lock); + local_spin_unlock_irq(slab_lock, &ac->lock); } } } @@ -1090,9 +1158,9 @@ static void drain_alien_cache(struct kmem_cache *cachep, for_each_online_node(i) { ac = alien[i]; if (ac) { - spin_lock_irqsave(&ac->lock, flags); + local_spin_lock_irqsave(slab_lock, &ac->lock, flags); __drain_alien_cache(cachep, ac, i); - spin_unlock_irqrestore(&ac->lock, flags); + local_spin_unlock_irqrestore(slab_lock, &ac->lock, flags); } } } @@ -1171,11 +1239,11 @@ static int init_cache_node_node(int node) cachep->node[node] = n; } - spin_lock_irq(&cachep->node[node]->list_lock); + local_spin_lock_irq(slab_lock, &cachep->node[node]->list_lock); cachep->node[node]->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - spin_unlock_irq(&cachep->node[node]->list_lock); + local_spin_unlock_irq(slab_lock, &cachep->node[node]->list_lock); } return 0; } @@ -1200,7 +1268,7 @@ static void __cpuinit cpuup_canceled(long cpu) if (!n) goto free_array_cache; - spin_lock_irq(&n->list_lock); + local_spin_lock_irq(slab_lock, &n->list_lock); /* Free limit for this kmem_cache_node */ n->free_limit -= cachep->batchcount; @@ -1208,7 +1276,7 @@ static void __cpuinit cpuup_canceled(long cpu) free_block(cachep, nc->entry, nc->avail, node); if (!cpumask_empty(mask)) { - spin_unlock_irq(&n->list_lock); + unlock_l3_and_free_delayed(&n->list_lock); goto free_array_cache; } @@ -1222,7 +1290,7 @@ static void __cpuinit cpuup_canceled(long cpu) alien = n->alien; n->alien = NULL; - spin_unlock_irq(&n->list_lock); + unlock_l3_and_free_delayed(&n->list_lock); kfree(shared); if (alien) { @@ -1296,7 +1364,7 @@ static int __cpuinit cpuup_prepare(long cpu) n = cachep->node[node]; BUG_ON(!n); - spin_lock_irq(&n->list_lock); + local_spin_lock_irq(slab_lock, &n->list_lock); if (!n->shared) { /* * We are serialised from CPU_DEAD or @@ -1311,7 +1379,7 @@ static int __cpuinit cpuup_prepare(long cpu) alien = NULL; } #endif - spin_unlock_irq(&n->list_lock); + local_spin_unlock_irq(slab_lock, &n->list_lock); kfree(shared); free_alien_cache(alien); if (cachep->flags & SLAB_DEBUG_OBJECTS) @@ -1512,6 +1580,10 @@ void __init kmem_cache_init(void) if (num_possible_nodes() == 1) use_alien_caches = 0; + local_irq_lock_init(slab_lock); + for_each_possible_cpu(i) + INIT_LIST_HEAD(&per_cpu(slab_free_list, i)); + for (i = 0; i < NUM_INIT_LISTS; i++) kmem_cache_node_init(&init_kmem_cache_node[i]); @@ -1789,12 +1861,14 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) /* * Interface to system's page release. */ -static void kmem_freepages(struct kmem_cache *cachep, void *addr) +static void kmem_freepages(struct kmem_cache *cachep, void *addr, bool delayed) { unsigned long i = (1 << cachep->gfporder); - struct page *page = virt_to_page(addr); + struct page *page, *basepage = virt_to_page(addr); const unsigned long nr_freed = i; + page = basepage; + kmemcheck_free_shadow(page, cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) @@ -1813,7 +1887,12 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) memcg_release_pages(cachep, cachep->gfporder); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; - free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder); + if (!delayed) { + free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder); + } else { + basepage->index = cachep->gfporder; + list_add(&basepage->lru, &__get_cpu_var(slab_free_list)); + } } static void kmem_rcu_free(struct rcu_head *head) @@ -1821,7 +1900,7 @@ static void kmem_rcu_free(struct rcu_head *head) struct slab_rcu *slab_rcu = (struct slab_rcu *)head; struct kmem_cache *cachep = slab_rcu->cachep; - kmem_freepages(cachep, slab_rcu->addr); + kmem_freepages(cachep, slab_rcu->addr, false); if (OFF_SLAB(cachep)) kmem_cache_free(cachep->slabp_cache, slab_rcu); } @@ -2038,7 +2117,8 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab * Before calling the slab must have been unlinked from the cache. The * cache-lock is not held/needed. */ -static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp) +static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp, + bool delayed) { void *addr = slabp->s_mem - slabp->colouroff; @@ -2051,7 +2131,7 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp) slab_rcu->addr = addr; call_rcu(&slab_rcu->head, kmem_rcu_free); } else { - kmem_freepages(cachep, addr); + kmem_freepages(cachep, addr, delayed); if (OFF_SLAB(cachep)) kmem_cache_free(cachep->slabp_cache, slabp); } @@ -2408,7 +2488,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) #if DEBUG static void check_irq_off(void) { - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); } static void check_irq_on(void) @@ -2443,26 +2523,43 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, struct array_cache *ac, int force, int node); -static void do_drain(void *arg) +static void __do_drain(void *arg, unsigned int cpu) { struct kmem_cache *cachep = arg; struct array_cache *ac; - int node = numa_mem_id(); + int node = cpu_to_mem(cpu); - check_irq_off(); - ac = cpu_cache_get(cachep); + ac = cpu_cache_get_on_cpu(cachep, cpu); spin_lock(&cachep->node[node]->list_lock); free_block(cachep, ac->entry, ac->avail, node); spin_unlock(&cachep->node[node]->list_lock); ac->avail = 0; } +#ifndef CONFIG_PREEMPT_RT_BASE +static void do_drain(void *arg) +{ + __do_drain(arg, smp_processor_id()); +} +#else +static void do_drain(void *arg, int cpu) +{ + LIST_HEAD(tmp); + + lock_slab_on(cpu); + __do_drain(arg, cpu); + list_splice_init(&per_cpu(slab_free_list, cpu), &tmp); + unlock_slab_on(cpu); + free_delayed(&tmp); +} +#endif + static void drain_cpu_caches(struct kmem_cache *cachep) { struct kmem_cache_node *n; int node; - on_each_cpu(do_drain, cachep, 1); + slab_on_each_cpu(do_drain, cachep); check_irq_on(); for_each_online_node(node) { n = cachep->node[node]; @@ -2493,10 +2590,10 @@ static int drain_freelist(struct kmem_cache *cache, nr_freed = 0; while (nr_freed < tofree && !list_empty(&n->slabs_free)) { - spin_lock_irq(&n->list_lock); + local_spin_lock_irq(slab_lock, &n->list_lock); p = n->slabs_free.prev; if (p == &n->slabs_free) { - spin_unlock_irq(&n->list_lock); + local_spin_unlock_irq(slab_lock, &n->list_lock); goto out; } @@ -2510,8 +2607,8 @@ static int drain_freelist(struct kmem_cache *cache, * to the cache. */ n->free_objects -= cache->num; - spin_unlock_irq(&n->list_lock); - slab_destroy(cache, slabp); + local_spin_unlock_irq(slab_lock, &n->list_lock); + slab_destroy(cache, slabp, false); nr_freed++; } out: @@ -2785,7 +2882,7 @@ static int cache_grow(struct kmem_cache *cachep, offset *= cachep->colour_off; if (local_flags & __GFP_WAIT) - local_irq_enable(); + local_unlock_irq(slab_lock); /* * The test for missing atomic flag is performed here, rather than @@ -2815,7 +2912,7 @@ static int cache_grow(struct kmem_cache *cachep, cache_init_objs(cachep, slabp); if (local_flags & __GFP_WAIT) - local_irq_disable(); + local_lock_irq(slab_lock); check_irq_off(); spin_lock(&n->list_lock); @@ -2826,10 +2923,10 @@ static int cache_grow(struct kmem_cache *cachep, spin_unlock(&n->list_lock); return 1; opps1: - kmem_freepages(cachep, objp); + kmem_freepages(cachep, objp, false); failed: if (local_flags & __GFP_WAIT) - local_irq_disable(); + local_lock_irq(slab_lock); return 0; } @@ -3243,11 +3340,11 @@ retry: * set and go into memory reserves if necessary. */ if (local_flags & __GFP_WAIT) - local_irq_enable(); + local_unlock_irq(slab_lock); kmem_flagcheck(cache, flags); obj = kmem_getpages(cache, local_flags, numa_mem_id()); if (local_flags & __GFP_WAIT) - local_irq_disable(); + local_lock_irq(slab_lock); if (obj) { /* * Insert into the appropriate per node queues @@ -3368,7 +3465,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, cachep = memcg_kmem_get_cache(cachep, flags); cache_alloc_debugcheck_before(cachep, flags); - local_irq_save(save_flags); + local_lock_irqsave(slab_lock, save_flags); if (nodeid == NUMA_NO_NODE) nodeid = slab_node; @@ -3393,7 +3490,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, /* ___cache_alloc_node can fall back to other nodes */ ptr = ____cache_alloc_node(cachep, flags, nodeid); out: - local_irq_restore(save_flags); + local_unlock_irqrestore(slab_lock, save_flags); ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller); kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags, flags); @@ -3455,9 +3552,9 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) cachep = memcg_kmem_get_cache(cachep, flags); cache_alloc_debugcheck_before(cachep, flags); - local_irq_save(save_flags); + local_lock_irqsave(slab_lock, save_flags); objp = __do_cache_alloc(cachep, flags); - local_irq_restore(save_flags); + local_unlock_irqrestore(slab_lock, save_flags); objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); kmemleak_alloc_recursive(objp, cachep->object_size, 1, cachep->flags, flags); @@ -3508,7 +3605,7 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects, * a different cache, refer to comments before * alloc_slabmgmt. */ - slab_destroy(cachep, slabp); + slab_destroy(cachep, slabp, true); } else { list_add(&slabp->list, &n->slabs_free); } @@ -3771,12 +3868,12 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) if (!cachep) return; - local_irq_save(flags); debug_check_no_locks_freed(objp, cachep->object_size); if (!(cachep->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(objp, cachep->object_size); + local_lock_irqsave(slab_lock, flags); __cache_free(cachep, objp, _RET_IP_); - local_irq_restore(flags); + unlock_slab_and_free_delayed(flags); trace_kmem_cache_free(_RET_IP_, objp); } @@ -3800,14 +3897,14 @@ void kfree(const void *objp) if (unlikely(ZERO_OR_NULL_PTR(objp))) return; - local_irq_save(flags); kfree_debugcheck(objp); c = virt_to_cache(objp); debug_check_no_locks_freed(objp, c->object_size); debug_check_no_obj_freed(objp, c->object_size); + local_lock_irqsave(slab_lock, flags); __cache_free(c, (void *)objp, _RET_IP_); - local_irq_restore(flags); + unlock_slab_and_free_delayed(flags); } EXPORT_SYMBOL(kfree); @@ -3844,7 +3941,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) if (n) { struct array_cache *shared = n->shared; - spin_lock_irq(&n->list_lock); + local_spin_lock_irq(slab_lock, &n->list_lock); if (shared) free_block(cachep, shared->entry, @@ -3857,7 +3954,8 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) } n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - spin_unlock_irq(&n->list_lock); + unlock_l3_and_free_delayed(&n->list_lock); + kfree(shared); free_alien_cache(new_alien); continue; @@ -3904,18 +4002,29 @@ struct ccupdate_struct { struct array_cache *new[0]; }; -static void do_ccupdate_local(void *info) +static void __do_ccupdate_local(void *info, int cpu) { struct ccupdate_struct *new = info; struct array_cache *old; - check_irq_off(); - old = cpu_cache_get(new->cachep); + old = cpu_cache_get_on_cpu(new->cachep, cpu); - new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()]; - new->new[smp_processor_id()] = old; + new->cachep->array[cpu] = new->new[cpu]; + new->new[cpu] = old; } +#ifndef CONFIG_PREEMPT_RT_BASE +static void do_ccupdate_local(void *info) +{ + __do_ccupdate_local(info, smp_processor_id()); +} +#else +static void do_ccupdate_local(void *info, int cpu) +{ + __do_ccupdate_local(info, cpu); +} +#endif + /* Always called with the slab_mutex held */ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount, int shared, gfp_t gfp) @@ -3940,7 +4049,7 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, } new->cachep = cachep; - on_each_cpu(do_ccupdate_local, (void *)new, 1); + slab_on_each_cpu(do_ccupdate_local, (void *)new); check_irq_on(); cachep->batchcount = batchcount; @@ -3951,9 +4060,11 @@ static int __do_tune_cpucache(struct kmem_cache *cachep, int limit, struct array_cache *ccold = new->new[i]; if (!ccold) continue; - spin_lock_irq(&cachep->node[cpu_to_mem(i)]->list_lock); + local_spin_lock_irq(slab_lock, + &cachep->node[cpu_to_mem(i)]->list_lock); free_block(cachep, ccold->entry, ccold->avail, cpu_to_mem(i)); - spin_unlock_irq(&cachep->node[cpu_to_mem(i)]->list_lock); + + unlock_l3_and_free_delayed(&cachep->node[cpu_to_mem(i)]->list_lock); kfree(ccold); } kfree(new); @@ -4068,7 +4179,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, if (ac->touched && !force) { ac->touched = 0; } else { - spin_lock_irq(&n->list_lock); + local_spin_lock_irq(slab_lock, &n->list_lock); if (ac->avail) { tofree = force ? ac->avail : (ac->limit + 4) / 5; if (tofree > ac->avail) @@ -4078,7 +4189,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n, memmove(ac->entry, &(ac->entry[tofree]), sizeof(void *) * ac->avail); } - spin_unlock_irq(&n->list_lock); + local_spin_unlock_irq(slab_lock, &n->list_lock); } } @@ -4171,7 +4282,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) continue; check_irq_on(); - spin_lock_irq(&n->list_lock); + local_spin_lock_irq(slab_lock, &n->list_lock); list_for_each_entry(slabp, &n->slabs_full, list) { if (slabp->inuse != cachep->num && !error) @@ -4196,7 +4307,7 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo) if (n->shared) shared_avail += n->shared->avail; - spin_unlock_irq(&n->list_lock); + local_spin_unlock_irq(slab_lock, &n->list_lock); } num_slabs += active_slabs; num_objs = num_slabs * cachep->num; @@ -4396,13 +4507,13 @@ static int leaks_show(struct seq_file *m, void *p) continue; check_irq_on(); - spin_lock_irq(&n->list_lock); + local_spin_lock_irq(slab_lock, &n->list_lock); list_for_each_entry(slabp, &n->slabs_full, list) handle_slab(x, cachep, slabp); list_for_each_entry(slabp, &n->slabs_partial, list) handle_slab(x, cachep, slabp); - spin_unlock_irq(&n->list_lock); + local_spin_unlock_irq(slab_lock, &n->list_lock); } name = cachep->name; if (x[0] == x[1]) { diff --git a/mm/slab.h b/mm/slab.h index 4d6d836..fc3c097 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -247,7 +247,11 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) * The slab lists for all objects. */ struct kmem_cache_node { +#ifdef CONFIG_SLAB spinlock_t list_lock; +#else + raw_spinlock_t list_lock; +#endif #ifdef CONFIG_SLAB struct list_head slabs_partial; /* partial list first, better asm code */ diff --git a/mm/slub.c b/mm/slub.c index deaed7b..8d8a3a6 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1071,7 +1071,7 @@ static noinline struct kmem_cache_node *free_debug_processing( { struct kmem_cache_node *n = get_node(s, page_to_nid(page)); - spin_lock_irqsave(&n->list_lock, *flags); + raw_spin_lock_irqsave(&n->list_lock, *flags); slab_lock(page); if (!check_slab(s, page)) @@ -1119,7 +1119,7 @@ out: fail: slab_unlock(page); - spin_unlock_irqrestore(&n->list_lock, *flags); + raw_spin_unlock_irqrestore(&n->list_lock, *flags); slab_fix(s, "Object at 0x%p not freed", object); return NULL; } @@ -1254,6 +1254,12 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) {} #endif /* CONFIG_SLUB_DEBUG */ +struct slub_free_list { + raw_spinlock_t lock; + struct list_head list; +}; +static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); + /* * Slab allocation and freeing */ @@ -1275,10 +1281,15 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) struct page *page; struct kmem_cache_order_objects oo = s->oo; gfp_t alloc_gfp; + bool enableirqs; flags &= gfp_allowed_mask; - if (flags & __GFP_WAIT) + enableirqs = (flags & __GFP_WAIT) != 0; +#ifdef CONFIG_PREEMPT_RT_FULL + enableirqs |= system_state == SYSTEM_RUNNING; +#endif + if (enableirqs) local_irq_enable(); flags |= s->allocflags; @@ -1318,7 +1329,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) kmemcheck_mark_unallocated_pages(page, pages); } - if (flags & __GFP_WAIT) + if (enableirqs) local_irq_disable(); if (!page) return NULL; @@ -1336,8 +1347,10 @@ static void setup_object(struct kmem_cache *s, struct page *page, void *object) { setup_object_debug(s, page, object); +#ifndef CONFIG_PREEMPT_RT_FULL if (unlikely(s->ctor)) s->ctor(object); +#endif } static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -1415,6 +1428,16 @@ static void __free_slab(struct kmem_cache *s, struct page *page) __free_memcg_kmem_pages(page, order); } +static void free_delayed(struct list_head *h) +{ + while(!list_empty(h)) { + struct page *page = list_first_entry(h, struct page, lru); + + list_del(&page->lru); + __free_slab(page->slab_cache, page); + } +} + #define need_reserve_slab_rcu \ (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head)) @@ -1449,6 +1472,12 @@ static void free_slab(struct kmem_cache *s, struct page *page) } call_rcu(head, rcu_free_slab); + } else if (irqs_disabled()) { + struct slub_free_list *f = &__get_cpu_var(slub_free_list); + + raw_spin_lock(&f->lock); + list_add(&page->lru, &f->list); + raw_spin_unlock(&f->lock); } else __free_slab(s, page); } @@ -1553,7 +1582,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, if (!n || !n->nr_partial) return NULL; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); list_for_each_entry_safe(page, page2, &n->partial, lru) { void *t; @@ -1577,7 +1606,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, break; } - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); return object; } @@ -1819,7 +1848,7 @@ redo: * that acquire_slab() will see a slab page that * is frozen */ - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } } else { m = M_FULL; @@ -1830,7 +1859,7 @@ redo: * slabs from diagnostic functions will not see * any frozen slabs. */ - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } } @@ -1865,7 +1894,7 @@ redo: goto redo; if (lock) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); if (m == M_FREE) { stat(s, DEACTIVATE_EMPTY); @@ -1896,10 +1925,10 @@ static void unfreeze_partials(struct kmem_cache *s, n2 = get_node(s, page_to_nid(page)); if (n != n2) { if (n) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); n = n2; - spin_lock(&n->list_lock); + raw_spin_lock(&n->list_lock); } do { @@ -1928,7 +1957,7 @@ static void unfreeze_partials(struct kmem_cache *s, } if (n) - spin_unlock(&n->list_lock); + raw_spin_unlock(&n->list_lock); while (discard_page) { page = discard_page; @@ -1964,14 +1993,21 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) pobjects = oldpage->pobjects; pages = oldpage->pages; if (drain && pobjects > s->cpu_partial) { + struct slub_free_list *f; unsigned long flags; + LIST_HEAD(tofree); /* * partial array is full. Move the existing * set to the per node partial list. */ local_irq_save(flags); unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); + f = &__get_cpu_var(slub_free_list); + raw_spin_lock(&f->lock); + list_splice_init(&f->list, &tofree); + raw_spin_unlock(&f->lock); local_irq_restore(flags); + free_delayed(&tofree); oldpage = NULL; pobjects = 0; pages = 0; @@ -2033,7 +2069,22 @@ static bool has_cpu_slab(int cpu, void *info) static void flush_all(struct kmem_cache *s) { + LIST_HEAD(tofree); + int cpu; + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); + for_each_online_cpu(cpu) { + struct slub_free_list *f; + + if (!has_cpu_slab(cpu, s)) + continue; + + f = &per_cpu(slub_free_list, cpu); + raw_spin_lock_irq(&f->lock); + list_splice_init(&f->list, &tofree); + raw_spin_unlock_irq(&f->lock); + free_delayed(&tofree); + } } /* @@ -2061,10 +2112,10 @@ static unsigned long count_partial(struct kmem_cache_node *n, unsigned long x = 0; struct page *page; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) x += get_count(page); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return x; } @@ -2207,9 +2258,11 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { + struct slub_free_list *f; void *freelist; struct page *page; unsigned long flags; + LIST_HEAD(tofree); local_irq_save(flags); #ifdef CONFIG_PREEMPT @@ -2272,7 +2325,13 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); +out: + f = &__get_cpu_var(slub_free_list); + raw_spin_lock(&f->lock); + list_splice_init(&f->list, &tofree); + raw_spin_unlock(&f->lock); local_irq_restore(flags); + free_delayed(&tofree); return freelist; new_slab: @@ -2290,9 +2349,7 @@ new_slab: if (unlikely(!freelist)) { if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit()) slab_out_of_memory(s, gfpflags, node); - - local_irq_restore(flags); - return NULL; + goto out; } page = c->page; @@ -2306,8 +2363,7 @@ new_slab: deactivate_slab(s, page, get_freepointer(s, freelist)); c->page = NULL; c->freelist = NULL; - local_irq_restore(flags); - return freelist; + goto out; } /* @@ -2390,6 +2446,10 @@ redo: if (unlikely(gfpflags & __GFP_ZERO) && object) memset(object, 0, s->object_size); +#ifdef CONFIG_PREEMPT_RT_FULL + if (unlikely(s->ctor) && object) + s->ctor(object); +#endif slab_post_alloc_hook(s, gfpflags, object); @@ -2484,7 +2544,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, do { if (unlikely(n)) { - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); n = NULL; } prior = page->freelist; @@ -2514,7 +2574,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, * Otherwise the list_lock will synchronize with * other processors updating the list of slabs. */ - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); } } @@ -2555,7 +2615,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, add_partial(n, page, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return; slab_empty: @@ -2569,7 +2629,7 @@ slab_empty: /* Slab must be on the full list */ remove_full(s, page); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); discard_slab(s, page); } @@ -2771,7 +2831,7 @@ static void init_kmem_cache_node(struct kmem_cache_node *n) { n->nr_partial = 0; - spin_lock_init(&n->list_lock); + raw_spin_lock_init(&n->list_lock); INIT_LIST_HEAD(&n->partial); #ifdef CONFIG_SLUB_DEBUG atomic_long_set(&n->nr_slabs, 0); @@ -3393,7 +3453,7 @@ int kmem_cache_shrink(struct kmem_cache *s) for (i = 0; i < objects; i++) INIT_LIST_HEAD(slabs_by_inuse + i); - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); /* * Build lists indexed by the items in use in each slab. @@ -3414,7 +3474,7 @@ int kmem_cache_shrink(struct kmem_cache *s) for (i = objects - 1; i > 0; i--) list_splice(slabs_by_inuse + i, n->partial.prev); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); /* Release empty slabs */ list_for_each_entry_safe(page, t, slabs_by_inuse, lru) @@ -3590,6 +3650,12 @@ void __init kmem_cache_init(void) { static __initdata struct kmem_cache boot_kmem_cache, boot_kmem_cache_node; + int cpu; + + for_each_possible_cpu(cpu) { + raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); + INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); + } if (debug_guardpage_minorder()) slub_max_order = 0; @@ -3894,7 +3960,7 @@ static int validate_slab_node(struct kmem_cache *s, struct page *page; unsigned long flags; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) { validate_slab_slab(s, page, map); @@ -3917,7 +3983,7 @@ static int validate_slab_node(struct kmem_cache *s, atomic_long_read(&n->nr_slabs)); out: - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); return count; } @@ -4107,12 +4173,12 @@ static int list_locations(struct kmem_cache *s, char *buf, if (!atomic_long_read(&n->nr_slabs)) continue; - spin_lock_irqsave(&n->list_lock, flags); + raw_spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) process_slab(&t, s, page, alloc, map); list_for_each_entry(page, &n->full, lru) process_slab(&t, s, page, alloc, map); - spin_unlock_irqrestore(&n->list_lock, flags); + raw_spin_unlock_irqrestore(&n->list_lock, flags); } for (i = 0; i < t.count; i++) { diff --git a/mm/swap.c b/mm/swap.c index ea58dbd..40b0b75 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "internal.h" @@ -42,6 +43,9 @@ static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); +static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); +static DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); + /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. @@ -405,11 +409,11 @@ void rotate_reclaimable_page(struct page *page) unsigned long flags; page_cache_get(page); - local_irq_save(flags); + local_lock_irqsave(rotate_lock, flags); pvec = &__get_cpu_var(lru_rotate_pvecs); if (!pagevec_add(pvec, page)) pagevec_move_tail(pvec); - local_irq_restore(flags); + local_unlock_irqrestore(rotate_lock, flags); } } @@ -454,12 +458,13 @@ static void activate_page_drain(int cpu) void activate_page(struct page *page) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { - struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); + struct pagevec *pvec = &get_locked_var(swapvec_lock, + activate_page_pvecs); page_cache_get(page); if (!pagevec_add(pvec, page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); - put_cpu_var(activate_page_pvecs); + put_locked_var(swapvec_lock, activate_page_pvecs); } } @@ -507,13 +512,13 @@ EXPORT_SYMBOL(mark_page_accessed); */ void __lru_cache_add(struct page *page, enum lru_list lru) { - struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru]; + struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvecs)[lru]; page_cache_get(page); if (!pagevec_space(pvec)) __pagevec_lru_add(pvec, lru); pagevec_add(pvec, page); - put_cpu_var(lru_add_pvecs); + put_locked_var(swapvec_lock, lru_add_pvecs); } EXPORT_SYMBOL(__lru_cache_add); @@ -648,9 +653,9 @@ void lru_add_drain_cpu(int cpu) unsigned long flags; /* No harm done if a racing interrupt already did this */ - local_irq_save(flags); + local_lock_irqsave(rotate_lock, flags); pagevec_move_tail(pvec); - local_irq_restore(flags); + local_unlock_irqrestore(rotate_lock, flags); } pvec = &per_cpu(lru_deactivate_pvecs, cpu); @@ -678,18 +683,19 @@ void deactivate_page(struct page *page) return; if (likely(get_page_unless_zero(page))) { - struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + struct pagevec *pvec = &get_locked_var(swapvec_lock, + lru_deactivate_pvecs); if (!pagevec_add(pvec, page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); - put_cpu_var(lru_deactivate_pvecs); + put_locked_var(swapvec_lock, lru_deactivate_pvecs); } } void lru_add_drain(void) { - lru_add_drain_cpu(get_cpu()); - put_cpu(); + lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); + local_unlock_cpu(swapvec_lock); } static void lru_add_drain_per_cpu(struct work_struct *dummy) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d456560..f9a9a24 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -792,7 +792,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; - int node, err; + int node, err, cpu; node = numa_node_id(); @@ -831,12 +831,13 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) BUG_ON(err); radix_tree_preload_end(); - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = &__get_cpu_var(vmap_block_queue); vb->vbq = vbq; spin_lock(&vbq->lock); list_add_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_var(vmap_block_queue); + put_cpu_light(); return vb; } @@ -910,7 +911,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) struct vmap_block *vb; unsigned long addr = 0; unsigned int order; - int purge = 0; + int purge = 0, cpu; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -926,7 +927,8 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) again: rcu_read_lock(); - vbq = &get_cpu_var(vmap_block_queue); + cpu = get_cpu_light(); + vbq = &__get_cpu_var(vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { int i; @@ -963,7 +965,7 @@ next: if (purge) purge_fragmented_blocks_thiscpu(); - put_cpu_var(vmap_block_queue); + put_cpu_light(); rcu_read_unlock(); if (!addr) { diff --git a/mm/vmstat.c b/mm/vmstat.c index 10bbb54..e026462 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -214,6 +214,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long x; long t; + preempt_disable_rt(); x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); @@ -223,6 +224,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, x = 0; } __this_cpu_write(*p, x); + preempt_enable_rt(); } EXPORT_SYMBOL(__mod_zone_page_state); @@ -255,6 +257,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; + preempt_disable_rt(); v = __this_cpu_inc_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v > t)) { @@ -263,6 +266,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) zone_page_state_add(v + overstep, zone, item); __this_cpu_write(*p, -overstep); } + preempt_enable_rt(); } void __inc_zone_page_state(struct page *page, enum zone_stat_item item) @@ -277,6 +281,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; + preempt_disable_rt(); v = __this_cpu_dec_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v < - t)) { @@ -285,6 +290,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item) zone_page_state_add(v - overstep, zone, item); __this_cpu_write(*p, overstep); } + preempt_enable_rt(); } void __dec_zone_page_state(struct page *page, enum zone_stat_item item) diff --git a/net/core/dev.c b/net/core/dev.c index 1283c84..2542362 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -166,7 +166,8 @@ static struct list_head offload_base __read_mostly; DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); -seqcount_t devnet_rename_seq; +static seqcount_t devnet_rename_seq; +static DEFINE_MUTEX(devnet_rename_mutex); static inline void dev_base_seq_inc(struct net *net) { @@ -188,14 +189,14 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) static inline void rps_lock(struct softnet_data *sd) { #ifdef CONFIG_RPS - spin_lock(&sd->input_pkt_queue.lock); + raw_spin_lock(&sd->input_pkt_queue.raw_lock); #endif } static inline void rps_unlock(struct softnet_data *sd) { #ifdef CONFIG_RPS - spin_unlock(&sd->input_pkt_queue.lock); + raw_spin_unlock(&sd->input_pkt_queue.raw_lock); #endif } @@ -818,7 +819,8 @@ retry: strcpy(name, dev->name); rcu_read_unlock(); if (read_seqcount_retry(&devnet_rename_seq, seq)) { - cond_resched(); + mutex_lock(&devnet_rename_mutex); + mutex_unlock(&devnet_rename_mutex); goto retry; } @@ -1084,30 +1086,28 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - write_seqcount_begin(&devnet_rename_seq); + mutex_lock(&devnet_rename_mutex); + __write_seqcount_begin(&devnet_rename_seq); - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - write_seqcount_end(&devnet_rename_seq); - return 0; - } + if (strncmp(newname, dev->name, IFNAMSIZ) == 0) + goto outunlock; memcpy(oldname, dev->name, IFNAMSIZ); err = dev_get_valid_name(net, dev, newname); - if (err < 0) { - write_seqcount_end(&devnet_rename_seq); - return err; - } + if (err < 0) + goto outunlock; rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); - write_seqcount_end(&devnet_rename_seq); - return ret; + err = ret; + goto outunlock; } - write_seqcount_end(&devnet_rename_seq); + __write_seqcount_end(&devnet_rename_seq); + mutex_unlock(&devnet_rename_mutex); write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); @@ -1126,7 +1126,8 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - write_seqcount_begin(&devnet_rename_seq); + mutex_lock(&devnet_rename_mutex); + __write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; } else { @@ -1136,6 +1137,11 @@ rollback: } return err; + +outunlock: + __write_seqcount_end(&devnet_rename_seq); + mutex_unlock(&devnet_rename_mutex); + return err; } /** @@ -2108,6 +2114,7 @@ static inline void __netif_reschedule(struct Qdisc *q) sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } void __netif_schedule(struct Qdisc *q) @@ -2129,6 +2136,7 @@ void dev_kfree_skb_irq(struct sk_buff *skb) sd->completion_queue = skb; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } } EXPORT_SYMBOL(dev_kfree_skb_irq); @@ -3138,6 +3146,7 @@ enqueue: rps_unlock(sd); local_irq_restore(flags); + preempt_check_resched_rt(); atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); @@ -3175,7 +3184,7 @@ int netif_rx(struct sk_buff *skb) struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - preempt_disable(); + migrate_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -3185,13 +3194,13 @@ int netif_rx(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - preempt_enable(); + migrate_enable(); } else #endif { unsigned int qtail; - ret = enqueue_to_backlog(skb, get_cpu(), &qtail); - put_cpu(); + ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); + put_cpu_light(); } return ret; } @@ -3201,16 +3210,44 @@ int netif_rx_ni(struct sk_buff *skb) { int err; - preempt_disable(); + local_bh_disable(); err = netif_rx(skb); - if (local_softirq_pending()) - do_softirq(); - preempt_enable(); + local_bh_enable(); return err; } EXPORT_SYMBOL(netif_rx_ni); +#ifdef CONFIG_PREEMPT_RT_FULL +/* + * RT runs ksoftirqd as a real time thread and the root_lock is a + * "sleeping spinlock". If the trylock fails then we can go into an + * infinite loop when ksoftirqd preempted the task which actually + * holds the lock, because we requeue q and raise NET_TX softirq + * causing ksoftirqd to loop forever. + * + * It's safe to use spin_lock on RT here as softirqs run in thread + * context and cannot deadlock against the thread which is holding + * root_lock. + * + * On !RT the trylock might fail, but there we bail out from the + * softirq loop after 10 attempts which we can't do on RT. And the + * task holding root_lock cannot be preempted, so the only downside of + * that trylock is that we need 10 loops to decide that we should have + * given up in the first one :) + */ +static inline int take_root_lock(spinlock_t *lock) +{ + spin_lock(lock); + return 1; +} +#else +static inline int take_root_lock(spinlock_t *lock) +{ + return spin_trylock(lock); +} +#endif + static void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = &__get_cpu_var(softnet_data); @@ -3249,7 +3286,7 @@ static void net_tx_action(struct softirq_action *h) head = head->next_sched; root_lock = qdisc_lock(q); - if (spin_trylock(root_lock)) { + if (take_root_lock(root_lock)) { smp_mb__before_clear_bit(); clear_bit(__QDISC_STATE_SCHED, &q->state); @@ -3640,7 +3677,7 @@ static void flush_backlog(void *arg) skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev == dev) { __skb_unlink(skb, &sd->input_pkt_queue); - kfree_skb(skb); + __skb_queue_tail(&sd->tofree_queue, skb); input_queue_head_incr(sd); } } @@ -3649,10 +3686,13 @@ static void flush_backlog(void *arg) skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev == dev) { __skb_unlink(skb, &sd->process_queue); - kfree_skb(skb); + __skb_queue_tail(&sd->tofree_queue, skb); input_queue_head_incr(sd); } } + + if (!skb_queue_empty(&sd->tofree_queue)) + raise_softirq_irqoff(NET_RX_SOFTIRQ); } static int napi_gro_complete(struct sk_buff *skb) @@ -4009,6 +4049,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) } else #endif local_irq_enable(); + preempt_check_resched_rt(); } static int process_backlog(struct napi_struct *napi, int quota) @@ -4081,6 +4122,7 @@ void __napi_schedule(struct napi_struct *n) local_irq_save(flags); ____napi_schedule(&__get_cpu_var(softnet_data), n); local_irq_restore(flags); + preempt_check_resched_rt(); } EXPORT_SYMBOL(__napi_schedule); @@ -4158,10 +4200,17 @@ static void net_rx_action(struct softirq_action *h) struct softnet_data *sd = &__get_cpu_var(softnet_data); unsigned long time_limit = jiffies + 2; int budget = netdev_budget; + struct sk_buff *skb; void *have; local_irq_disable(); + while ((skb = __skb_dequeue(&sd->tofree_queue))) { + local_irq_enable(); + kfree_skb(skb); + local_irq_disable(); + } + while (!list_empty(&sd->poll_list)) { struct napi_struct *n; int work, weight; @@ -6012,6 +6061,7 @@ static int dev_cpu_callback(struct notifier_block *nfb, raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); + preempt_check_resched_rt(); /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { @@ -6022,6 +6072,9 @@ static int dev_cpu_callback(struct notifier_block *nfb, netif_rx(skb); input_queue_head_incr(oldsd); } + while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { + kfree_skb(skb); + } return NOTIFY_OK; } @@ -6294,8 +6347,9 @@ static int __init net_dev_init(void) struct softnet_data *sd = &per_cpu(softnet_data, i); memset(sd, 0, sizeof(*sd)); - skb_queue_head_init(&sd->input_pkt_queue); - skb_queue_head_init(&sd->process_queue); + skb_queue_head_init_raw(&sd->input_pkt_queue); + skb_queue_head_init_raw(&sd->process_queue); + skb_queue_head_init_raw(&sd->tofree_queue); sd->completion_queue = NULL; INIT_LIST_HEAD(&sd->poll_list); sd->output_queue = NULL; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 20ee14d..32bbae3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -60,6 +60,7 @@ #include #include #include +#include #include #include @@ -337,6 +338,7 @@ struct netdev_alloc_cache { unsigned int pagecnt_bias; }; static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); +static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { @@ -345,7 +347,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) int order; unsigned long flags; - local_irq_save(flags); + local_lock_irqsave(netdev_alloc_lock, flags); nc = &__get_cpu_var(netdev_alloc_cache); if (unlikely(!nc->frag.page)) { refill: @@ -379,7 +381,7 @@ recycle: nc->frag.offset += fragsz; nc->pagecnt_bias--; end: - local_irq_restore(flags); + local_unlock_irqrestore(netdev_alloc_lock, flags); return data; } diff --git a/net/core/sock.c b/net/core/sock.c index 50a345e..72a603f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2289,12 +2289,11 @@ void lock_sock_nested(struct sock *sk, int subclass) if (sk->sk_lock.owned) __lock_sock(sk); sk->sk_lock.owned = 1; - spin_unlock(&sk->sk_lock.slock); + spin_unlock_bh(&sk->sk_lock.slock); /* * The sk_lock has mutex_lock() semantics here: */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); - local_bh_enable(); } EXPORT_SYMBOL(lock_sock_nested); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 76e10b4..7815db0 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -69,6 +69,7 @@ #include #include #include +#include #include #include #include @@ -768,6 +769,30 @@ static void icmp_redirect(struct sk_buff *skb) } /* + * 32bit and 64bit have different timestamp length, so we check for + * the cookie at offset 20 and verify it is repeated at offset 50 + */ +#define CO_POS0 20 +#define CO_POS1 50 +#define CO_SIZE sizeof(int) +#define ICMP_SYSRQ_SIZE 57 + +/* + * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie + * pattern and if it matches send the next byte as a trigger to sysrq. + */ +static void icmp_check_sysrq(struct net *net, struct sk_buff *skb) +{ + int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq); + char *p = skb->data; + + if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) && + !memcmp(&cookie, p + CO_POS1, CO_SIZE) && + p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE]) + handle_sysrq(p[CO_POS0 + CO_SIZE]); +} + +/* * Handle ICMP_ECHO ("ping") requests. * * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo @@ -794,6 +819,11 @@ static void icmp_echo(struct sk_buff *skb) icmp_param.data_len = skb->len; icmp_param.head_len = sizeof(struct icmphdr); icmp_reply(&icmp_param, skb); + + if (skb->len == ICMP_SYSRQ_SIZE && + net->ipv4.sysctl_icmp_echo_sysrq) { + icmp_check_sysrq(net, skb); + } } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6ca5873..2d69b1b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1508,7 +1508,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, if (IS_ERR(rt)) return; - inet = &get_cpu_var(unicast_sock); + get_cpu_light(); + inet = &__get_cpu_var(unicast_sock); inet->tos = arg->tos; sk = &inet->sk; @@ -1532,7 +1533,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, ip_push_pending_frames(sk, &fl4); } - put_cpu_var(unicast_sock); + put_cpu_light(); ip_rt_put(rt); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 90b26be..5afa42e 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -804,6 +804,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { + .procname = "icmp_echo_sysrq", + .data = &init_net.ipv4.sysctl_icmp_echo_sysrq, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "icmp_ignore_bogus_error_responses", .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, .maxlen = sizeof(int), diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fae73b0..dad437e 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3244,7 +3244,7 @@ void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) struct ieee80211_supported_band *sband; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - WARN_ON_ONCE(softirq_count() == 0); + WARN_ON_ONCE_NONRT(softirq_count() == 0); if (WARN_ON(status->band >= IEEE80211_NUM_BANDS)) goto drop; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 857ca9f..6ea9852 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -21,11 +21,17 @@ #include #include #include +#include #include #include #include "nf_internals.h" +#ifdef CONFIG_PREEMPT_RT_BASE +DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); +EXPORT_PER_CPU_SYMBOL(xt_write_lock); +#endif + static DEFINE_MUTEX(afinfo_mutex); const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e8b5a0d..7cc464a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -88,6 +88,7 @@ #include #include #include +#include #ifdef CONFIG_INET #include @@ -630,7 +631,7 @@ static void prb_retire_rx_blk_timer_expired(unsigned long data) if (BLOCK_NUM_PKTS(pbd)) { while (atomic_read(&pkc->blk_fill_in_prog)) { /* Waiting for skb_copy_bits to finish... */ - cpu_relax(); + cpu_chill(); } } @@ -881,7 +882,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, if (!(status & TP_STATUS_BLK_TMO)) { while (atomic_read(&pkc->blk_fill_in_prog)) { /* Waiting for skb_copy_bits to finish... */ - cpu_relax(); + cpu_chill(); } } prb_close_block(pkc, pbd, po, status); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index e8fdb17..5a44c6e 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "rds.h" #include "ib.h" @@ -286,7 +287,7 @@ static inline void wait_clean_list_grace(void) for_each_online_cpu(cpu) { flag = &per_cpu(clean_list_grace, cpu); while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) - cpu_relax(); + cpu_chill(); } } diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h index f221ddf..5f44009 100755 --- a/scripts/mkcompile_h +++ b/scripts/mkcompile_h @@ -4,7 +4,8 @@ TARGET=$1 ARCH=$2 SMP=$3 PREEMPT=$4 -CC=$5 +RT=$5 +CC=$6 vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } @@ -57,6 +58,7 @@ UTS_VERSION="#$VERSION" CONFIG_FLAGS="" if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi +if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" # Truncate to maximum length