diff options
347 files changed, 9431 insertions, 2109 deletions
diff --git a/Documentation/hwlat_detector.txt b/Documentation/hwlat_detector.txt new file mode 100644 index 000000000000..cb61516483d3 --- /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 <timestamp> <latency observed usecs> + (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 312e3754e8c5..9981f307ef0e 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -57,10 +57,17 @@ On PowerPC - Press 'ALT - Print Screen (or F13) - <command key>, 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 000000000000..6f2aeabf7faa --- /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): +<PID> <Priority> <Latency> (<Timeroffset>) <Command> \ +<- <PID> <Priority> <Command> <Timestamp> + +The value of <Timeroffset> 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 <Latency>. + +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 <seconds>.<microseconds> after the most recent system boot +is provided. + +These data are also reset when the wakeup histogram is reset. diff --git a/MAINTAINERS b/MAINTAINERS index f986e7dc904b..b2574771c3bc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3008,6 +3008,15 @@ L: linuxppc-dev@lists.ozlabs.org S: Odd Fixes F: drivers/tty/hvc/ +HARDWARE LATENCY DETECTOR +P: Jon Masters +M: jcm@jonmasters.org +W: http://www.kernel.org/pub/linux/kernel/people/jcm/hwlat_detector/ +S: Supported +L: linux-kernel@vger.kernel.org +F: Documentation/hwlat_detector.txt +F: drivers/misc/hwlat_detector.c + HARDWARE MONITORING M: Jean Delvare <khali@linux-fr.org> M: Guenter Roeck <guenter.roeck@ericsson.com> diff --git a/arch/Kconfig b/arch/Kconfig index 4b0669cbb3b0..73fc7cd51582 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 fadd5f882ff9..4a0a0aff8fd0 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -107,7 +107,7 @@ 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 ab3740ec79a3..0e53586543f5 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -29,6 +29,7 @@ config ARM select HAVE_GENERIC_HARDIRQS select HAVE_SPARSE_IRQ select GENERIC_IRQ_SHOW + select IRQ_FORCED_THREADING select CPU_PM if (SUSPEND || CPU_IDLE) help The ARM series is a line of low-power-consumption RISC chip designs @@ -1667,7 +1668,7 @@ config HAVE_ARCH_PFN_VALID config HIGHMEM bool "High Memory Support" - depends on MMU + depends on MMU && !PREEMPT_RT_FULL help The address space of ARM processors is only 4 Gigabytes large and it has to accommodate user address space, kernel address diff --git a/arch/arm/kernel/early_printk.c b/arch/arm/kernel/early_printk.c index 85aa2b292692..43076536965c 100644 --- a/arch/arm/kernel/early_printk.c +++ b/arch/arm/kernel/early_printk.c @@ -29,28 +29,17 @@ static void early_console_write(struct console *con, const char *s, unsigned n) early_write(s, n); } -static struct console early_console = { +static struct console early_console_dev = { .name = "earlycon", .write = early_console_write, .flags = CON_PRINTBUFFER | CON_BOOT, .index = -1, }; -asmlinkage void early_printk(const char *fmt, ...) -{ - char buf[512]; - int n; - va_list ap; - - va_start(ap, fmt); - n = vscnprintf(buf, sizeof(buf), fmt, ap); - early_write(buf, n); - va_end(ap); -} - static int __init setup_early_printk(char *buf) { - register_console(&early_console); + early_console = &early_console_dev; + register_console(&early_console_dev); return 0; } diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index ecebb893f1e7..e1286fb056f4 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -435,7 +435,7 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu) } err = request_irq(irq, handle_irq, - IRQF_DISABLED | IRQF_NOBALANCING, + IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu", armpmu); 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 3d0c6fb74ae4..75227b36c234 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -214,9 +214,7 @@ void cpu_idle(void) } leds_event(led_idle_end); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } @@ -491,6 +489,31 @@ 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); + /* * The vectors page is always readable from user space for the * atomic helpers and the signal restart code. Let's declare a mapping diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 9e617bd4a146..c7001bc72eb0 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -672,6 +672,9 @@ static void do_signal(struct pt_regs *regs, int syscall) if (!user_mode(regs)) return; + local_irq_enable(); + preempt_check_resched(); + /* * If we were from a system call, check for system call restarting... */ diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c index 1dd69c85dfec..06665701bebf 100644 --- a/arch/arm/mach-at91/at91rm9200_time.c +++ b/arch/arm/mach-at91/at91rm9200_time.c @@ -114,6 +114,7 @@ clkevt32k_mode(enum clock_event_mode mode, struct clock_event_device *dev) last_crtr = read_CRTR(); switch (mode) { case CLOCK_EVT_MODE_PERIODIC: + setup_irq(AT91_ID_SYS, &at91rm9200_timer_irq); /* PIT for periodic irqs; fixed rate of 1/HZ */ irqmask = AT91_ST_PITS; at91_sys_write(AT91_ST_PIMR, LATCH); @@ -127,6 +128,7 @@ 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 4ba85499fa97..97d1e1459942 100644 --- a/arch/arm/mach-at91/at91sam926x_time.c +++ b/arch/arm/mach-at91/at91sam926x_time.c @@ -54,7 +54,7 @@ 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) */ @@ -63,6 +63,9 @@ 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(at91_sys_read(AT91_PIT_PIVR)); at91_sys_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN @@ -75,6 +78,7 @@ pit_clkevt_mode(enum clock_event_mode mode, struct clock_event_device *dev) case CLOCK_EVT_MODE_UNUSED: /* disable irq, leaving the clocksource active */ at91_sys_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 69ffb2fb3875..fe321b0d2ba9 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -63,7 +63,7 @@ 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 exynos4_gic_secondary_init(void) { @@ -108,8 +108,8 @@ void __cpuinit platform_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 boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -120,7 +120,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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 @@ -149,7 +149,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) if (timeout == 0) { printk(KERN_ERR "cpu1 power enable failed"); - spin_unlock(&boot_lock); + raw_spin_unlock(&boot_lock); return -ETIMEDOUT; } } @@ -177,7 +177,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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 fdec58aaa35c..cad6b8114a92 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -39,7 +39,7 @@ extern void msm_secondary_startup(void); */ volatile int pen_release = -1; -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static inline int get_core_count(void) { @@ -69,8 +69,8 @@ void __cpuinit platform_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) @@ -107,7 +107,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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 @@ -141,7 +141,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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 4412ddb7b3f6..490de9c330cd 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -29,7 +29,7 @@ /* SCU base address */ static void __iomem *scu_base; -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); void __cpuinit platform_secondary_init(unsigned int cpu) { @@ -43,8 +43,8 @@ void __cpuinit platform_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 boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -53,7 +53,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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. @@ -70,7 +70,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c index 7d2b5d03c1df..571f61a35894 100644 --- a/arch/arm/mach-tegra/platsmp.c +++ b/arch/arm/mach-tegra/platsmp.c @@ -28,7 +28,7 @@ extern void tegra_secondary_startup(void); -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); static void __iomem *scu_base = IO_ADDRESS(TEGRA_ARM_PERIF_BASE); #define EVP_CPU_RESET_VECTOR \ @@ -50,8 +50,8 @@ void __cpuinit platform_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 boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -65,7 +65,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * set synchronisation state between this boot processor * and the secondary one */ - spin_lock(&boot_lock); + raw_spin_lock(&boot_lock); /* set the reset vector to point to the secondary_startup routine */ @@ -101,7 +101,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c index a19e398dade3..9e92c6cc9817 100644 --- a/arch/arm/mach-ux500/platsmp.c +++ b/arch/arm/mach-ux500/platsmp.c @@ -57,7 +57,7 @@ static void __iomem *scu_base_addr(void) return NULL; } -static DEFINE_SPINLOCK(boot_lock); +static DEFINE_RAW_SPINLOCK(boot_lock); void __cpuinit platform_secondary_init(unsigned int cpu) { @@ -77,8 +77,8 @@ void __cpuinit platform_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 boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -89,7 +89,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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 @@ -110,7 +110,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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 aa33949fef60..d717bd361a7b 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -294,7 +294,7 @@ 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/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c index 92f18d372b69..287bbb5b6854 100644 --- a/arch/arm/plat-versatile/platsmp.c +++ b/arch/arm/plat-versatile/platsmp.c @@ -37,7 +37,7 @@ 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 platform_secondary_init(unsigned int cpu) { @@ -57,8 +57,8 @@ void __cpuinit platform_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 boot_secondary(unsigned int cpu, struct task_struct *idle) @@ -69,7 +69,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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 @@ -99,7 +99,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) * 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/kernel/process.c b/arch/avr32/kernel/process.c index ef5a2a08fcca..c8724c90d4ca 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -38,9 +38,7 @@ void cpu_idle(void) while (!need_resched()) cpu_idle_sleep(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index f7040a1e399f..155ad8daecf9 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/blackfin/kernel/early_printk.c b/arch/blackfin/kernel/early_printk.c index 84ed8375113c..61fbd2de993d 100644 --- a/arch/blackfin/kernel/early_printk.c +++ b/arch/blackfin/kernel/early_printk.c @@ -25,8 +25,6 @@ extern struct console *bfin_earlyserial_init(unsigned int port, extern struct console *bfin_jc_early_init(void); #endif -static struct console *early_console; - /* Default console */ #define DEFAULT_PORT 0 #define DEFAULT_CFLAG CS8|B57600 diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 6a80a9e9fc4a..11acc10e6381 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -92,9 +92,7 @@ void cpu_idle(void) while (!need_resched()) idle(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index aa585e4e979e..d8f50ff6fadd 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -115,9 +115,7 @@ void cpu_idle (void) idle = default_idle; idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 9dcac8ec8fa0..ba9cfbe818f1 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -111,7 +111,7 @@ 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; down_read(&mm->mmap_sem); diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 3901df1213c0..29cc49783787 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -92,9 +92,7 @@ void cpu_idle(void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index a325d57a83d5..a9ce0f056565 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -79,7 +79,7 @@ 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/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 933bd388efb2..1a173b35f475 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -81,9 +81,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c index af5650169043..106aeb670e54 100644 --- a/arch/ia64/kernel/asm-offsets.c +++ b/arch/ia64/kernel/asm-offsets.c @@ -269,8 +269,8 @@ void foo(void) BLANK(); /* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */ - DEFINE(IA64_GTOD_LOCK_OFFSET, - offsetof (struct fsyscall_gtod_data_t, lock)); + DEFINE(IA64_GTOD_SEQ_OFFSET, + offsetof (struct fsyscall_gtod_data_t, seq); DEFINE(IA64_GTOD_WALL_TIME_OFFSET, offsetof (struct fsyscall_gtod_data_t, wall_time)); DEFINE(IA64_GTOD_MONO_TIME_OFFSET, diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S index 331d42bda77a..fa77de7032b3 100644 --- a/arch/ia64/kernel/fsys.S +++ b/arch/ia64/kernel/fsys.S @@ -174,7 +174,7 @@ ENTRY(fsys_set_tid_address) FSYS_RETURN END(fsys_set_tid_address) -#if IA64_GTOD_LOCK_OFFSET !=0 +#if IA64_GTOD_SEQ_OFFSET !=0 #error fsys_gettimeofday incompatible with changes to struct fsyscall_gtod_data_t #endif #if IA64_ITC_JITTER_OFFSET !=0 diff --git a/arch/ia64/kernel/fsyscall_gtod_data.h b/arch/ia64/kernel/fsyscall_gtod_data.h index 57d2ee6c83e1..146b15b5fec3 100644 --- a/arch/ia64/kernel/fsyscall_gtod_data.h +++ b/arch/ia64/kernel/fsyscall_gtod_data.h @@ -6,7 +6,7 @@ */ struct fsyscall_gtod_data_t { - seqlock_t lock; + seqcount_t seq; struct timespec wall_time; struct timespec monotonic_time; cycle_t clk_mask; diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6d33c5cc94f0..9dc52b63fc87 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -330,9 +330,7 @@ cpu_idle (void) normal_xtp(); #endif } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); if (cpu_is_offline(cpu)) play_dead(); diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 43920de425f1..8e991a0b5e35 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -35,9 +35,7 @@ static cycle_t itc_get_cycles(struct clocksource *cs); -struct fsyscall_gtod_data_t fsyscall_gtod_data = { - .lock = __SEQLOCK_UNLOCKED(fsyscall_gtod_data.lock), -}; +struct fsyscall_gtod_data_t fsyscall_gtod_data; struct itc_jitter_data_t itc_jitter_data; @@ -460,9 +458,7 @@ void update_vsyscall_tz(void) void update_vsyscall(struct timespec *wall, struct timespec *wtm, struct clocksource *c, u32 mult) { - unsigned long flags; - - write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags); + write_seqcount_begin(&fsyscall_gtod_data.seq); /* copy fsyscall clock data */ fsyscall_gtod_data.clk_mask = c->mask; @@ -485,6 +481,6 @@ void update_vsyscall(struct timespec *wall, struct timespec *wtm, fsyscall_gtod_data.monotonic_time.tv_sec++; } - write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags); + write_seqcount_end(&fsyscall_gtod_data.seq); } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 20b359376128..05946c2933e1 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -89,7 +89,7 @@ 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/kernel/process.c b/arch/m32r/kernel/process.c index 422bea9f1dbc..3a4a32b27208 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -90,9 +90,7 @@ void cpu_idle (void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index 2c9aeb453847..6d763f64f48c 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -115,7 +115,7 @@ 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/kernel/process_mm.c b/arch/m68k/kernel/process_mm.c index aa4ffb882366..c413aa05e4f7 100644 --- a/arch/m68k/kernel/process_mm.c +++ b/arch/m68k/kernel/process_mm.c @@ -94,9 +94,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m68k/kernel/process_no.c b/arch/m68k/kernel/process_no.c index 5e1078cabe0e..f7fe6c348595 100644 --- a/arch/m68k/kernel/process_no.c +++ b/arch/m68k/kernel/process_no.c @@ -73,9 +73,7 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 2db6099784ba..74fe5593abbb 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; down_read(&mm->mmap_sem); diff --git a/arch/microblaze/kernel/early_printk.c b/arch/microblaze/kernel/early_printk.c index d26d92d47754..04206249fb0d 100644 --- a/arch/microblaze/kernel/early_printk.c +++ b/arch/microblaze/kernel/early_printk.c @@ -21,7 +21,6 @@ #include <asm/setup.h> #include <asm/prom.h> -static u32 early_console_initialized; static u32 base_addr; #ifdef CONFIG_SERIAL_UARTLITE_CONSOLE @@ -109,27 +108,11 @@ static struct console early_serial_uart16550_console = { }; #endif /* CONFIG_SERIAL_8250_CONSOLE */ -static struct console *early_console; - -void early_printk(const char *fmt, ...) -{ - char buf[512]; - int n; - va_list ap; - - if (early_console_initialized) { - va_start(ap, fmt); - n = vscnprintf(buf, 512, fmt, ap); - early_console->write(early_console, buf, n); - va_end(ap); - } -} - int __init setup_early_printk(char *opt) { int version = 0; - if (early_console_initialized) + if (early_console) return 1; base_addr = of_early_console(&version); @@ -159,7 +142,6 @@ int __init setup_early_printk(char *opt) } register_console(early_console); - early_console_initialized = 1; return 0; } return 1; @@ -169,7 +151,7 @@ int __init setup_early_printk(char *opt) * only for early console because of performance degression */ void __init remap_early_printk(void) { - if (!early_console_initialized || !early_console) + if (!early_console) return; printk(KERN_INFO "early_printk_console remaping from 0x%x to ", base_addr); @@ -179,9 +161,9 @@ void __init remap_early_printk(void) void __init disable_early_printk(void) { - if (!early_console_initialized || !early_console) + if (!early_console) return; printk(KERN_WARNING "disabling early console\n"); unregister_console(early_console); - early_console_initialized = 0; + early_console = NULL; } diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 95cc295976a7..d3b2b42ad6ac 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -108,9 +108,7 @@ void cpu_idle(void) idle(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index ae97d2ccdc22..4cdd84db9c4d 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -107,7 +107,7 @@ 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 d46f1da18a3c..9f02e8b5392f 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2040,7 +2040,7 @@ 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/early_printk.c b/arch/mips/kernel/early_printk.c index 9ae813eb782e..973c995c0a86 100644 --- a/arch/mips/kernel/early_printk.c +++ b/arch/mips/kernel/early_printk.c @@ -25,20 +25,18 @@ early_console_write(struct console *con, const char *s, unsigned n) } } -static struct console early_console __initdata = { +static struct console early_console_prom = { .name = "early", .write = early_console_write, .flags = CON_PRINTBUFFER | CON_BOOT, .index = -1 }; -static int early_console_initialized __initdata; - void __init setup_early_printk(void) { - if (early_console_initialized) + if (early_console) return; - early_console_initialized = 1; + early_console = &early_console_prom; - register_console(&early_console); + register_console(&early_console_prom); } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index c47f96e453c0..4dbf66d641b7 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -78,9 +78,7 @@ void __noreturn cpu_idle(void) play_dead(); #endif tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index f8524003676a..1c8f34c62ea1 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -604,6 +604,9 @@ static void do_signal(struct pt_regs *regs) if (!user_mode(regs)) return; + local_irq_enable(); + preempt_check_resched(); + if (test_thread_flag(TIF_RESTORE_SIGMASK)) oldset = ¤t->saved_sigmask; else diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 937cf3368164..7ade72b93f3e 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -88,7 +88,7 @@ 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; down_read(&mm->mmap_sem); diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 28eec3102535..cac401d37f75 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -123,9 +123,7 @@ void cpu_idle(void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 0945409a8022..2fea01cbb27f 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; down_read(&mm->mmap_sem); diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 4b4b9181a1a0..f6eb36736cf0 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -71,9 +71,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) barrier(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 18162ce4261e..df22f39fb545 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -176,7 +176,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, unsigned long acc_type; int fault; - if (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; down_read(&mm->mmap_sem); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 951e18f5335b..d01baf829664 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -69,10 +69,11 @@ 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 IRQ_PER_CPU select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL + select IRQ_FORCED_THREADING select HAVE_RCU_TABLE_FREE if SMP select HAVE_SYSCALL_TRACEPOINTS select HAVE_BPF_JIT if (PPC64 && NET) @@ -274,7 +276,7 @@ menu "Kernel options" config HIGHMEM bool "High memory support" - depends on PPC32 + depends on PPC32 && !PREEMPT_RT_FULL source kernel/time/Kconfig source kernel/Kconfig.hz diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 39a2baa6ad58..5d70d1046e11 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -94,11 +94,11 @@ void cpu_idle(void) HMT_medium(); ppc64_runlatch_on(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - if (cpu_should_die()) + if (cpu_should_die()) { + __preempt_enable_no_resched(); cpu_die(); - schedule(); - preempt_disable(); + } + schedule_preempt_disabled(); } } diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 745c1e7c10fd..e0ee53177ea5 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -440,6 +440,7 @@ void irq_ctx_init(void) } } +#ifndef CONFIG_PREEMPT_RT_FULL static inline void do_softirq_onstack(void) { struct thread_info *curtp, *irqtp; @@ -476,7 +477,7 @@ void do_softirq(void) local_irq_restore(flags); } - +#endif /* * IRQ controller and virtual interrupts diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 7cd07b42ca1a..46c607300b29 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 616921ef1439..2961d7521726 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/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6df70907d60a..abdedd3a314d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -187,8 +187,8 @@ int smp_request_message_ipi(int virq, int msg) return 1; } #endif - err = request_irq(virq, smp_ipi_action[msg], IRQF_PERCPU, - smp_ipi_name[msg], 0); + err = request_irq(virq, smp_ipi_action[msg], + IRQF_PERCPU | IRQF_NO_THREAD, smp_ipi_name[msg], 0); WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n", virq, smp_ipi_name[msg], err); diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 57fa2c0a531c..1b9174d96dcc 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -182,15 +182,13 @@ static struct console udbg_console = { .index = 0, }; -static int early_console_initialized; - /* * Called by setup_system after ppc_md->probe and ppc_md->early_init. * Call it again after setting udbg_putc in ppc_md->setup_arch. */ void __init register_early_udbg_console(void) { - if (early_console_initialized) + if (early_console) return; if (!udbg_putc) @@ -200,7 +198,7 @@ void __init register_early_udbg_console(void) printk(KERN_INFO "early console immortal !\n"); udbg_console.flags &= ~CON_BOOT; } - early_console_initialized = 1; + early_console = &udbg_console; register_console(&udbg_console); } diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 5efe8c96d37f..94bedd4032aa 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -162,7 +162,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address, } #endif - if (in_atomic() || mm == NULL) { + if (!mm || pagefault_disabled()) { if (!user_mode(regs)) return SIGSEGV; /* in_atomic() in user mode is really bad, diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c index 66cb8d64079f..7e2a4d231e74 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c @@ -177,7 +177,7 @@ static irqreturn_t mpc85xx_8259_cascade_action(int irq, void *dev_id) static struct irqaction mpc85xxcds_8259_irqaction = { .handler = mpc85xx_8259_cascade_action, - .flags = IRQF_SHARED, + .flags = IRQF_SHARED | IRQF_NO_THREAD, .name = "8259 cascade", }; #endif /* PPC_I8259 */ diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index ea0acbd8966d..e0c5b4953c2f 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -582,9 +582,7 @@ static void iseries_shared_idle(void) if (hvlpevent_is_pending()) process_iSeries_events(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } @@ -611,9 +609,7 @@ static void iseries_dedicated_idle(void) ppc64_runlatch_on(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 3394254f305f..8d75ac8a6bd7 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -200,7 +200,7 @@ static int psurge_secondary_ipi_init(void) if (psurge_secondary_virq) rc = request_irq(psurge_secondary_virq, psurge_ipi_intr, - IRQF_PERCPU, "IPI", NULL); + IRQF_NO_THREAD | IRQF_PERCPU, "IPI", NULL); if (rc) pr_err("Failed to setup secondary cpu IPI\n"); @@ -408,7 +408,7 @@ static int __init smp_psurge_kick_cpu(int nr) static struct irqaction psurge_irqaction = { .handler = psurge_ipi_intr, - .flags = IRQF_PERCPU, + .flags = IRQF_PERCPU | IRQF_NO_THREAD, .name = "primary IPI", }; diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c index be05631a3c1c..19f353dfcd03 100644 --- a/arch/powerpc/platforms/wsp/opb_pic.c +++ b/arch/powerpc/platforms/wsp/opb_pic.c @@ -320,7 +320,8 @@ void __init opb_pic_init(void) } /* Attach opb interrupt handler to new virtual IRQ */ - rc = request_irq(virq, opb_irq_handler, 0, "OPB LS Cascade", opb); + rc = request_irq(virq, opb_irq_handler, IRQF_NO_THREAD, + "OPB LS Cascade", opb); if (rc) { printk("opb: request_irq failed: %d\n", rc); continue; diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index 63762c672a03..4ba61941acbe 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -134,10 +134,11 @@ static void xics_request_ipi(void) BUG_ON(ipi == NO_IRQ); /* - * IPIs are marked IRQF_PERCPU. The handler was set in map. + * IPIs are marked PERCPU and also IRQF_NO_THREAD as they must + * run in hard interrupt context. The handler was set in map. */ BUG_ON(request_irq(ipi, icp_ops->ipi_action, - IRQF_PERCPU, "IPI", NULL)); + IRQF_NO_THREAD|IRQF_PERCPU, "IPI", NULL)); } int __init xics_smp_probe(void) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 53088e208427..fa093f72386b 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -94,9 +94,7 @@ void cpu_idle(void) while (!need_resched()) default_idle(); tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index c7f0fbc00fc8..a68d8363853e 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -294,7 +294,8 @@ 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; @@ -425,7 +426,8 @@ void __kprobes do_asce_exception(struct pt_regs *regs, long pgm_int_code, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - 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/kernel/process.c b/arch/score/kernel/process.c index 25d08030a883..2707023c7563 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -53,9 +53,7 @@ void __noreturn cpu_idle(void) while (!need_resched()) barrier(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 47b600e4b2c5..59fccbe9777b 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/idle.c b/arch/sh/kernel/idle.c index db4ecd731a00..b7c18f0899c9 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -112,9 +112,7 @@ void cpu_idle(void) } tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index a3ee91971129..9127bc05d629 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/kernel/sh_bios.c b/arch/sh/kernel/sh_bios.c index 47475cca068a..a5b51b9d7338 100644 --- a/arch/sh/kernel/sh_bios.c +++ b/arch/sh/kernel/sh_bios.c @@ -144,8 +144,6 @@ static struct console bios_console = { .index = -1, }; -static struct console *early_console; - static int __init setup_early_printk(char *buf) { int keep_early = 0; diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c index 7bebd044f2a1..643670db6664 100644 --- a/arch/sh/mm/fault_32.c +++ b/arch/sh/mm/fault_32.c @@ -166,7 +166,7 @@ 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 (in_atomic() || !mm) + if (!mm || pagefault_disabled()) goto no_context; down_read(&mm->mmap_sem); diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index d45b710ea7e4..c3a3737df3c7 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -699,6 +699,7 @@ 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; @@ -724,6 +725,7 @@ void do_softirq(void) local_irq_restore(flags); } +#endif #ifdef CONFIG_HOTPLUG_CPU void fixup_irqs(void) diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index f793742eec2b..935fdbcd88c2 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -113,9 +113,7 @@ void cpu_idle(void) while (!need_resched()) cpu_relax(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } @@ -138,9 +136,7 @@ void cpu_idle(void) while (!need_resched()) cpu_relax(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 3739a06a76cb..86fe09afc89a 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -102,15 +102,13 @@ void cpu_idle(void) tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - #ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(cpu)) + if (cpu_is_offline(cpu)) { + __preempt_enable_no_resched(); cpu_play_dead(); + } #endif - - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c index 741df916c124..ca73a288e179 100644 --- a/arch/sparc/kernel/prom_common.c +++ b/arch/sparc/kernel/prom_common.c @@ -65,7 +65,7 @@ int of_set_property(struct device_node *dp, const char *name, void *val, int len err = -ENODEV; mutex_lock(&of_set_property_mutex); - write_lock(&devtree_lock); + raw_spin_lock(&devtree_lock); prevp = &dp->properties; while (*prevp) { struct property *prop = *prevp; @@ -92,7 +92,7 @@ int of_set_property(struct device_node *dp, const char *name, void *val, int len } prevp = &(*prevp)->next; } - write_unlock(&devtree_lock); + raw_spin_unlock(&devtree_lock); mutex_unlock(&of_set_property_mutex); /* XXX Upate procfs if necessary... */ diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index fe1e3fc31bc5..e6475f03231d 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -221,6 +221,7 @@ void __init setup_arch(char **cmdline_p) boot_flags_init(*cmdline_p); + early_console = &prom_early_console; register_console(&prom_early_console); /* Set sparc_cpu_model */ diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index a854a1c240ff..b85d039678af 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -487,6 +487,12 @@ static void __init init_sparc64_elf_hwcap(void) popc_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. */ @@ -498,7 +504,7 @@ 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 8023fd7e77b5..054cf56ce057 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -247,8 +247,8 @@ 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) - goto no_context; + 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 504c0622f729..f6572f87d07e 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -322,7 +322,7 @@ 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/kernel/early_printk.c b/arch/tile/kernel/early_printk.c index 493a0e66d916..ba2ac0028f2e 100644 --- a/arch/tile/kernel/early_printk.c +++ b/arch/tile/kernel/early_printk.c @@ -32,25 +32,8 @@ static struct console early_hv_console = { }; /* Direct interface for emergencies */ -static struct console *early_console = &early_hv_console; -static int early_console_initialized; static int early_console_complete; -static void early_vprintk(const char *fmt, va_list ap) -{ - char buf[512]; - int n = vscnprintf(buf, sizeof(buf), fmt, ap); - early_console->write(early_console, buf, n); -} - -void early_printk(const char *fmt, ...) -{ - va_list ap; - va_start(ap, fmt); - early_vprintk(fmt, ap); - va_end(ap); -} - void early_panic(const char *fmt, ...) { va_list ap; @@ -68,14 +51,13 @@ static int __initdata keep_early; static int __init setup_early_printk(char *str) { - if (early_console_initialized) + if (early_console) return 1; if (str != NULL && strncmp(str, "keep", 4) == 0) keep_early = 1; early_console = &early_hv_console; - early_console_initialized = 1; register_console(early_console); return 0; @@ -84,12 +66,12 @@ static int __init setup_early_printk(char *str) void __init disable_early_printk(void) { early_console_complete = 1; - if (!early_console_initialized || !early_console) + if (!early_console) return; if (!keep_early) { early_printk("disabling early console\n"); unregister_console(early_console); - early_console_initialized = 0; + early_console = NULL; } else { early_printk("keeping early console\n"); } @@ -97,7 +79,7 @@ void __init disable_early_printk(void) void warn_early_printk(void) { - if (early_console_complete || early_console_initialized) + if (early_console_complete || early_console) return; early_printk("\ Machine shutting down before console output is fully initialized.\n\ diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 9c45d8bbdf57..5a8b631eedff 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -106,9 +106,7 @@ void cpu_idle(void) current_thread_info()->status |= TS_POLLING; } tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 25b7b90fd620..1b6fa511010d 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -346,7 +346,7 @@ 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/early_printk.c b/arch/um/kernel/early_printk.c index ec649bf72f68..183060f76a11 100644 --- a/arch/um/kernel/early_printk.c +++ b/arch/um/kernel/early_printk.c @@ -16,7 +16,7 @@ static void early_console_write(struct console *con, const char *s, unsigned int um_early_printk(s, n); } -static struct console early_console = { +static struct console early_console_dev = { .name = "earlycon", .write = early_console_write, .flags = CON_BOOT, @@ -25,8 +25,10 @@ static struct console early_console = { static int __init setup_early_printk(char *buf) { - register_console(&early_console); - + if (!early_console) { + early_console = &early_console_dev; + register_console(&early_console_dev); + } return 0; } diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index dafc94715950..78780693eb6d 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -37,7 +37,7 @@ 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 (!mm || pagefault_disabled()) goto out_nosemaphore; down_read(&mm->mmap_sem); diff --git a/arch/unicore32/kernel/early_printk.c b/arch/unicore32/kernel/early_printk.c index 3922255f1fa8..9be0d5d02a9a 100644 --- a/arch/unicore32/kernel/early_printk.c +++ b/arch/unicore32/kernel/early_printk.c @@ -33,21 +33,17 @@ static struct console early_ocd_console = { .index = -1, }; -/* Direct interface for emergencies */ -static struct console *early_console = &early_ocd_console; - -static int __initdata keep_early; - static int __init setup_early_printk(char *buf) { - if (!buf) + int keep_early; + + if (!buf || early_console) return 0; if (strstr(buf, "keep")) keep_early = 1; - if (!strncmp(buf, "ocd", 3)) - early_console = &early_ocd_console; + early_console = &early_ocd_console; if (keep_early) early_console->flags &= ~CON_BOOT; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index efb42949cc09..c42146edf618 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -161,10 +161,10 @@ config ARCH_MAY_HAVE_PC_FDC def_bool ISA_DMA_API config RWSEM_GENERIC_SPINLOCK - def_bool !X86_XADD + def_bool !X86_XADD || PREEMPT_RT_FULL config RWSEM_XCHGADD_ALGORITHM - def_bool X86_XADD + def_bool X86_XADD && !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL config ARCH_HAS_CPU_IDLE_WAIT def_bool y @@ -730,7 +730,7 @@ config IOMMU_HELPER config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP && DEBUG_KERNEL && EXPERIMENTAL - 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 545d0ce59818..0c9eaf1ca0a1 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -289,14 +289,14 @@ 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; } @@ -313,14 +313,14 @@ 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; } @@ -359,14 +359,14 @@ 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; } @@ -383,14 +383,14 @@ 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; } @@ -445,18 +445,20 @@ 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/acpi.h b/arch/x86/include/asm/acpi.h index 610001d385dd..c1c23d256ac6 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -51,8 +51,8 @@ #define ACPI_ASM_MACROS #define BREAKPOINT3 -#define ACPI_DISABLE_IRQS() local_irq_disable() -#define ACPI_ENABLE_IRQS() local_irq_enable() +#define ACPI_DISABLE_IRQS() local_irq_disable_nort() +#define ACPI_ENABLE_IRQS() local_irq_enable_nort() #define ACPI_FLUSH_CPU_CACHE() wbinvd() int __acpi_acquire_global_lock(unsigned int *lock); diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 7639dbf5d223..0883ecdbc905 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 598457cbd0f8..1213ebd7bee7 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -31,6 +31,19 @@ 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 + #else /* Here we must cater to libcs that poke about in kernel headers. */ diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 157517763565..ac0703bcfe17 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -58,7 +58,7 @@ */ static __always_inline void boot_init_stack_canary(void) { - u64 canary; + u64 uninitialized_var(canary); u64 tsc; #ifdef CONFIG_X86_64 @@ -69,8 +69,16 @@ 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/vgtod.h b/arch/x86/include/asm/vgtod.h index 815285bcaceb..1f007178c813 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -5,7 +5,7 @@ #include <linux/clocksource.h> struct vsyscall_gtod_data { - seqlock_t lock; + seqcount_t seq; /* open coded 'struct timespec' */ time_t wall_time_sec; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index f98d84caf94c..2cd2d93643dc 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -876,8 +876,8 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) * Besides, if we don't timer interrupts ignore the global * interrupt lock, which is the WrongThing (tm) to do. */ - exit_idle(); irq_enter(); + exit_idle(); local_apic_timer_interrupt(); irq_exit(); @@ -1809,8 +1809,8 @@ void smp_spurious_interrupt(struct pt_regs *regs) { u32 v; - exit_idle(); irq_enter(); + exit_idle(); /* * Check if this really is a spurious interrupt and ACK it * if it is a vectored one. Just in case... @@ -1846,8 +1846,8 @@ void smp_error_interrupt(struct pt_regs *regs) "Illegal register address", /* APIC Error Bit 7 */ }; - exit_idle(); irq_enter(); + exit_idle(); /* First tickle the hardware, only then report what went on. -- REW */ v0 = apic_read(APIC_ESR); apic_write(APIC_ESR, 0); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index a25e276bf41e..e568a3c9d810 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2421,8 +2421,8 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) unsigned vector, me; ack_APIC_irq(); - exit_idle(); irq_enter(); + exit_idle(); me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { @@ -2521,7 +2521,8 @@ static void ack_apic_level(struct irq_data *data) irq_complete_move(cfg); #ifdef CONFIG_GENERIC_PENDING_IRQ /* 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))) { do_unmask_irq = 1; mask_ioapic(cfg); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index aa003b13a831..d39b525fd321 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1055,7 +1055,9 @@ DEFINE_PER_CPU(unsigned int, irq_count) = -1; */ 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 2af127d4c3d1..f1f1cb1cdad9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -38,6 +38,7 @@ #include <linux/debugfs.h> #include <linux/irq_work.h> #include <linux/export.h> +#include <linux/jiffies.h> #include <asm/processor.h> #include <asm/mce.h> @@ -1106,17 +1107,14 @@ void mce_log_therm_throt_event(__u64 status) * poller finds an MCE, poll 2x faster. When the poller finds no more * errors, poll 2x slower (up to check_interval seconds). */ -static int check_interval = 5 * 60; /* 5 minutes */ +static unsigned long check_interval = 5 * 60; /* 5 minutes */ -static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */ -static DEFINE_PER_CPU(struct timer_list, mce_timer); +static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ +static DEFINE_PER_CPU(struct hrtimer, mce_timer); -static void mce_start_timer(unsigned long data) +static enum hrtimer_restart mce_start_timer(struct hrtimer *timer) { - struct timer_list *t = &per_cpu(mce_timer, data); - int *n; - - WARN_ON(smp_processor_id() != data); + unsigned long *n; if (mce_available(__this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, @@ -1129,21 +1127,22 @@ static void mce_start_timer(unsigned long data) */ n = &__get_cpu_var(mce_next_interval); if (mce_notify_irq()) - *n = max(*n/2, HZ/100); + *n = max(*n/2, HZ/100UL); else - *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ)); + *n = min(*n*2, round_jiffies_relative(check_interval*HZ)); - t->expires = jiffies + *n; - add_timer_on(t, smp_processor_id()); + hrtimer_forward(timer, timer->base->get_time(), + ns_to_ktime(jiffies_to_usecs(*n) * 1000)); + return HRTIMER_RESTART; } -/* 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) @@ -1375,10 +1374,11 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) static void __mcheck_cpu_init_timer(void) { - struct timer_list *t = &__get_cpu_var(mce_timer); - int *n = &__get_cpu_var(mce_next_interval); + struct hrtimer *t = &__get_cpu_var(mce_timer); + unsigned long *n = &__get_cpu_var(mce_next_interval); - setup_timer(t, mce_start_timer, smp_processor_id()); + hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + t->function = mce_start_timer; if (mce_ignore_ce) return; @@ -1386,8 +1386,9 @@ static void __mcheck_cpu_init_timer(void) *n = check_interval * HZ; if (!*n) return; - t->expires = round_jiffies(jiffies + *n); - add_timer_on(t, smp_processor_id()); + + hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(*n) * 1000), + 0 , HRTIMER_MODE_REL_PINNED); } /* Handle unconfigured int18 (should never happen) */ @@ -2023,6 +2024,8 @@ 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 < banks; i++) { @@ -2049,6 +2052,7 @@ 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. */ @@ -2056,7 +2060,6 @@ 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) { case CPU_ONLINE: @@ -2073,16 +2076,10 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: - del_timer_sync(t); smp_call_function_single(cpu, mce_disable_cpu, &action, 1); break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - if (!mce_ignore_ce && check_interval) { - t->expires = round_jiffies(jiffies + - __get_cpu_var(mce_next_interval)); - add_timer_on(t, cpu); - } smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); break; case CPU_POST_DEAD: diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 787e06c84ea6..ce215616d5b9 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -397,8 +397,8 @@ static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; asmlinkage void smp_thermal_interrupt(struct pt_regs *regs) { - exit_idle(); irq_enter(); + exit_idle(); inc_irq_stat(irq_thermal_count); smp_thermal_vector(); irq_exit(); diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index d746df2909c9..aa578cadb940 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -19,8 +19,8 @@ void (*mce_threshold_vector)(void) = default_threshold_interrupt; asmlinkage void smp_threshold_interrupt(void) { - exit_idle(); irq_enter(); + exit_idle(); inc_irq_stat(irq_threshold_count); mce_threshold_vector(); irq_exit(); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6d728d9284bd..352beb75ef78 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/early_printk.c b/arch/x86/kernel/early_printk.c index cd28a350f7f9..5f3d9c5e89c7 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -169,25 +169,9 @@ static struct console early_serial_console = { .index = -1, }; -/* Direct interface for emergencies */ -static struct console *early_console = &early_vga_console; -static int __initdata early_console_initialized; - -asmlinkage void early_printk(const char *fmt, ...) -{ - char buf[512]; - int n; - va_list ap; - - va_start(ap, fmt); - n = vscnprintf(buf, sizeof(buf), fmt, ap); - early_console->write(early_console, buf, n); - va_end(ap); -} - static inline void early_console_register(struct console *con, int keep_early) { - if (early_console->index != -1) { + if (con->index != -1) { printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n", con->name); return; @@ -207,9 +191,8 @@ static int __init setup_early_printk(char *buf) if (!buf) return 0; - if (early_console_initialized) + if (early_console) return 0; - early_console_initialized = 1; keep = (strstr(buf, "keep") != NULL); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index bcda8163bb00..426cf512fdef 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -629,7 +629,11 @@ work_notifysig: # deal with pending signals and jne work_notifysig_v86 # returning to kernel-space or # vm86-space xorl %edx, %edx + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) call do_notify_resume + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF jmp resume_userspace_sig ALIGN @@ -642,7 +646,11 @@ work_notifysig_v86: movl %esp, %eax #endif xorl %edx, %edx + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) call do_notify_resume + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF jmp resume_userspace_sig END(work_pending) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index faf8d5e74b0b..fb0f57824bd8 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1192,6 +1192,7 @@ ENTRY(kernel_execve) CFI_ENDPROC END(kernel_execve) +#ifndef CONFIG_PREEMPT_RT_FULL /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(call_softirq) CFI_STARTPROC @@ -1211,6 +1212,7 @@ ENTRY(call_softirq) ret CFI_ENDPROC END(call_softirq) +#endif #ifdef CONFIG_XEN zeroentry xen_hypervisor_callback xen_do_hypervisor_callback diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 1bb0bf4d92cd..d86b82190b80 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -9,6 +9,7 @@ #include <linux/slab.h> #include <linux/hpet.h> #include <linux/init.h> +#include <linux/dmi.h> #include <linux/cpu.h> #include <linux/pm.h> #include <linux/io.h> @@ -568,6 +569,30 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu) #define RESERVE_TIMERS 0 #endif +static int __init dmi_disable_hpet_msi(const struct dmi_system_id *d) +{ + hpet_msi_disable = 1; + return 0; +} + +static struct dmi_system_id __initdata dmi_hpet_table[] = { + /* + * MSI based per cpu timers lose interrupts when intel_idle() + * is enabled - independent of the c-state. With idle=poll the + * problem cannot be observed. We have no idea yet, whether + * this is a W510 specific issue or a general chipset oddity. + */ + { + .callback = dmi_disable_hpet_msi, + .ident = "Lenovo W510", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W510"), + }, + }, + {} +}; + static void hpet_msi_capability_lookup(unsigned int start_timer) { unsigned int id; @@ -575,6 +600,8 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int num_timers_used = 0; int i; + dmi_check_system(dmi_hpet_table); + if (hpet_msi_disable) return; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 429e0c92924e..5d31e5bdbf85 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -181,8 +181,8 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) unsigned vector = ~regs->orig_ax; unsigned irq; - exit_idle(); irq_enter(); + exit_idle(); irq = __this_cpu_read(vector_irq[vector]); @@ -209,10 +209,10 @@ void smp_x86_platform_ipi(struct pt_regs *regs) ack_APIC_irq(); - exit_idle(); - irq_enter(); + exit_idle(); + inc_irq_stat(x86_platform_ipis); if (x86_platform_ipi_callback) diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 72090705a656..84417a251c3f 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 69bca468c47a..3fbc07df72e1 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -65,7 +65,7 @@ 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) @@ -85,3 +85,4 @@ 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 ca8f703a1e70..129b8bb73de2 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/kprobes.c b/arch/x86/kernel/kprobes.c index 7da647d8b64c..5604455ebc75 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -478,7 +478,6 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, * stepping. */ regs->ip = (unsigned long)p->ainsn.insn; - preempt_enable_no_resched(); return; } #endif diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 859829614085..20f15731ec90 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -39,6 +39,7 @@ #include <linux/io.h> #include <linux/kdebug.h> #include <linux/cpuidle.h> +#include <linux/highmem.h> #include <asm/pgtable.h> #include <asm/system.h> @@ -117,9 +118,7 @@ void cpu_idle(void) start_critical_timings(); } tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } @@ -341,6 +340,41 @@ __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); +#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM + /* + * Save @prev's kmap_atomic stack + */ + prev_p->kmap_idx = __this_cpu_read(__kmap_atomic_idx); + if (unlikely(prev_p->kmap_idx)) { + int i; + + for (i = 0; i < prev_p->kmap_idx; i++) { + int idx = i + KM_TYPE_NR * smp_processor_id(); + + pte_t *ptep = kmap_pte - idx; + prev_p->kmap_pte[i] = *ptep; + kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); + } + + __this_cpu_write(__kmap_atomic_idx, 0); + } + + /* + * Restore @next_p's kmap_atomic stack + */ + if (unlikely(next_p->kmap_idx)) { + int i; + + __this_cpu_write(__kmap_atomic_idx, next_p->kmap_idx); + + for (i = 0; i < next_p->kmap_idx; i++) { + int idx = i + KM_TYPE_NR * smp_processor_id(); + + set_pte(kmap_pte - idx, next_p->kmap_pte[i]); + } + } +#endif + /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6a364a67e2b7..08840ab61a2e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -150,9 +150,7 @@ void cpu_idle(void) } tick_nohz_restart_sched_tick(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 54ddaeb221c1..12c4d53e09a1 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -820,6 +820,15 @@ 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 + /* deal with pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 31d9d0f04c2b..cc88aec09888 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -87,9 +87,21 @@ 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(); } @@ -100,11 +112,13 @@ 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 void __kprobes @@ -222,9 +236,9 @@ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) if (notify_die(DIE_TRAP, "stack segment", regs, error_code, 12, SIGBUS) == NOTIFY_STOP) return; - preempt_conditional_sti(regs); + conditional_sti_ist(regs); do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); } dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) @@ -316,9 +330,9 @@ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) return; #endif - preempt_conditional_sti(regs); + conditional_sti_ist(regs); do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); } #ifdef CONFIG_X86_64 @@ -412,12 +426,12 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) return; /* 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, 1); - preempt_conditional_cli(regs); + conditional_cli_ist(regs); return; } @@ -436,7 +450,7 @@ 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); return; } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index e4d4a22e8b94..50392ee9a626 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -52,10 +52,7 @@ #include "vsyscall_trace.h" DEFINE_VVAR(int, vgetcpu_mode); -DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = -{ - .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), -}; +DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); static enum { EMULATE, NATIVE, NONE } vsyscall_mode = NATIVE; @@ -80,20 +77,13 @@ early_param("vsyscall", vsyscall_setup); void update_vsyscall_tz(void) { - unsigned long flags; - - write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags); - /* sys_tz has changed */ vsyscall_gtod_data.sys_tz = sys_tz; - write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, struct clocksource *clock, u32 mult) { - unsigned long flags; - - write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags); + write_seqcount_begin(&vsyscall_gtod_data.seq); /* copy vsyscall data */ vsyscall_gtod_data.clock.vclock_mode = clock->archdata.vclock_mode; @@ -106,7 +96,7 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, vsyscall_gtod_data.wall_to_monotonic = *wtm; vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); - write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); + write_seqcount_end(&vsyscall_gtod_data.seq); } static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e04cae195e10..66d2844fd705 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5207,6 +5207,13 @@ 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; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 5db0490deb07..b567837c8374 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1084,7 +1084,7 @@ 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 f4f29b19fac5..71bd7d64e63c 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -43,7 +43,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot) type = kmap_atomic_idx_push(); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - BUG_ON(!pte_none(*(kmap_pte-idx))); + WARN_ON(!pte_none(*(kmap_pte-idx))); set_pte(kmap_pte-idx, mk_pte(page, prot)); arch_flush_lazy_mmu_mode(); diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 6bc0e723b6e8..d8511fb90c64 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -86,11 +86,11 @@ notrace static noinline int do_realtime(struct timespec *ts) { unsigned long seq, ns; do { - seq = read_seqbegin(>od->lock); + seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_sec; ts->tv_nsec = gtod->wall_time_nsec; ns = vgetns(); - } while (unlikely(read_seqretry(>od->lock, seq))); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); timespec_add_ns(ts, ns); return 0; } @@ -99,12 +99,12 @@ notrace static noinline int do_monotonic(struct timespec *ts) { unsigned long seq, ns, secs; do { - seq = read_seqbegin(>od->lock); + seq = read_seqcount_begin(>od->seq); secs = gtod->wall_time_sec; ns = gtod->wall_time_nsec + vgetns(); secs += gtod->wall_to_monotonic.tv_sec; ns += gtod->wall_to_monotonic.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); /* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec * are all guaranteed to be nonnegative. @@ -123,10 +123,10 @@ notrace static noinline int do_realtime_coarse(struct timespec *ts) { unsigned long seq; do { - seq = read_seqbegin(>od->lock); + seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_coarse.tv_sec; ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); return 0; } @@ -134,12 +134,12 @@ notrace static noinline int do_monotonic_coarse(struct timespec *ts) { unsigned long seq, ns, secs; do { - seq = read_seqbegin(>od->lock); + seq = read_seqcount_begin(>od->seq); secs = gtod->wall_time_coarse.tv_sec; ns = gtod->wall_time_coarse.tv_nsec; secs += gtod->wall_to_monotonic.tv_sec; ns += gtod->wall_to_monotonic.tv_nsec; - } while (unlikely(read_seqretry(>od->lock, seq))); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); /* wall_time_nsec and wall_to_monotonic.tv_nsec are * guaranteed to be between 0 and NSEC_PER_SEC. diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 47041e7c088c..2c9004770c4e 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -113,9 +113,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) platform_idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index e367e3026436..8f3f52a7d82e 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 15de223c7f93..ca732c065018 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -235,7 +235,7 @@ 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); @@ -300,7 +300,11 @@ void __blk_run_queue(struct request_queue *q) { if (unlikely(blk_queue_stopped(q))) return; - + /* + * q->request_fn() can drop q->queue_lock and reenable + * interrupts, but must return with q->queue_lock held and + * interrupts disabled. + */ q->request_fn(q); } EXPORT_SYMBOL(__blk_run_queue); @@ -2745,11 +2749,11 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth, * this lock). */ if (from_schedule) { - spin_unlock(q->queue_lock); + spin_unlock_irq(q->queue_lock); blk_run_queue_async(q); } else { __blk_run_queue(q); - spin_unlock(q->queue_lock); + spin_unlock_irq(q->queue_lock); } } @@ -2775,7 +2779,6 @@ static void flush_plug_callbacks(struct blk_plug *plug) 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; @@ -2796,11 +2799,6 @@ 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); @@ -2813,7 +2811,7 @@ 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); } /* * rq is already accounted, so use raw insert @@ -2831,8 +2829,6 @@ 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-iopoll.c b/block/blk-iopoll.c index 58916afbbda5..f7ca9b411d2a 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 1366a89d8e66..60a88ab5f19e 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -50,6 +50,7 @@ static void trigger_softirq(void *data) raise_softirq_irqoff(BLOCK_SOFTIRQ); local_irq_restore(flags); + preempt_check_resched_rt(); } /* @@ -92,6 +93,7 @@ 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/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 4cadfa28f940..100f85c4b1ab 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, KM_IRQ0); /* do the actual data transfer */ @@ -727,7 +727,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) do_write); kunmap_atomic(buf, KM_IRQ0); - 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, KM_IRQ0); /* do the actual data transfer */ @@ -872,7 +872,7 @@ next_sg: count, rw); kunmap_atomic(buf, KM_IRQ0); - 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 6035ab8d5ef7..026bdbb46f8a 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -433,7 +433,7 @@ static struct entropy_store input_pool = { .poolinfo = &poolinfo_table[0], .name = "input", .limit = 1, - .lock = __SPIN_LOCK_UNLOCKED(&input_pool.lock), + .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), .pool = input_pool_data }; @@ -442,7 +442,7 @@ static struct entropy_store blocking_pool = { .name = "blocking", .limit = 1, .pull = &input_pool, - .lock = __SPIN_LOCK_UNLOCKED(&blocking_pool.lock), + .lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock), .pool = blocking_pool_data }; @@ -450,7 +450,7 @@ static struct entropy_store nonblocking_pool = { .poolinfo = &poolinfo_table[1], .name = "nonblocking", .pull = &input_pool, - .lock = __SPIN_LOCK_UNLOCKED(&nonblocking_pool.lock), + .lock = __SPIN_LOCK_UNLOCKED(nonblocking_pool.lock), .pool = nonblocking_pool_data }; @@ -633,8 +633,11 @@ 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(); @@ -676,8 +679,6 @@ 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, diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index 79c47e88d5d1..8976b3d10dc0 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -21,8 +21,7 @@ * resolution better than 200 nsec). * * - 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 @@ -68,6 +67,7 @@ static struct clocksource clksrc = { struct tc_clkevt_device { struct clock_event_device clkevt; struct clk *clk; + u32 freq; void __iomem *regs; }; @@ -76,13 +76,6 @@ 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) @@ -105,11 +98,12 @@ 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)); @@ -122,7 +116,7 @@ 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)); @@ -152,8 +146,12 @@ static struct tc_clkevt_device clkevt = { .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, .shift = 32, +#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, }, @@ -179,8 +177,9 @@ 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]; @@ -188,11 +187,17 @@ static void __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) clkevt.clk = t2_clk; tc_irqaction.dev_id = &clkevt; - timer_clock = clk32k_divisor_idx; + timer_clock = divisor_idx; - clkevt.clkevt.mult = div_sc(32768, NSEC_PER_SEC, clkevt.clkevt.shift); - clkevt.clkevt.max_delta_ns - = clockevent_delta2ns(0xffff, &clkevt.clkevt); + if (!divisor) + clkevt.freq = 32768; + else + clkevt.freq = clk_get_rate(t2_clk)/divisor; + + clkevt.clkevt.mult = div_sc(clkevt.freq, NSEC_PER_SEC, + clkevt.clkevt.shift); + clkevt.clkevt.max_delta_ns = + clockevent_delta2ns(0xffff, &clkevt.clkevt); clkevt.clkevt.min_delta_ns = clockevent_delta2ns(1, &clkevt.clkevt) + 1; clkevt.clkevt.cpumask = cpumask_of(0); @@ -295,8 +300,11 @@ static int __init tcb_clksrc_init(void) clocksource_register(&clksrc); /* 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/ide/alim15x3.c b/drivers/ide/alim15x3.c index 2c8016ad0e26..6fd6037741b1 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 58c51cddc100..d2a40595b334 100644 --- a/drivers/ide/hpt366.c +++ b/drivers/ide/hpt366.c @@ -1241,7 +1241,7 @@ static int __devinit 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 __devinit 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 19763977568c..4169433faab5 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 177db6d5b2f5..079ae6bebf18 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 376f2dc410c5..f014dd1b73dc 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 068cef0a987a..38e69e1793d8 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 5bc2839ebcfd..da861a680f09 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, KM_BIO_SRC_IRQ) + offset; @@ -272,7 +272,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd, kunmap_atomic(buf, KM_BIO_SRC_IRQ); 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/idle/i7300_idle.c b/drivers/idle/i7300_idle.c index c976285d313e..5537d7c482c0 100644 --- a/drivers/idle/i7300_idle.c +++ b/drivers/idle/i7300_idle.c @@ -75,7 +75,7 @@ static unsigned long past_skip; static struct pci_dev *fbd_dev; -static spinlock_t i7300_idle_lock; +static raw_spinlock_t i7300_idle_lock; static int i7300_idle_active; static u8 i7300_idle_thrtctl_saved; @@ -457,7 +457,7 @@ static int i7300_idle_notifier(struct notifier_block *nb, unsigned long val, idle_begin_time = ktime_get(); } - spin_lock_irqsave(&i7300_idle_lock, flags); + raw_spin_lock_irqsave(&i7300_idle_lock, flags); if (val == IDLE_START) { cpumask_set_cpu(smp_processor_id(), idle_cpumask); @@ -506,7 +506,7 @@ static int i7300_idle_notifier(struct notifier_block *nb, unsigned long val, } } end: - spin_unlock_irqrestore(&i7300_idle_lock, flags); + raw_spin_unlock_irqrestore(&i7300_idle_lock, flags); return 0; } @@ -554,7 +554,7 @@ struct debugfs_file_info { static int __init i7300_idle_init(void) { - spin_lock_init(&i7300_idle_lock); + raw_spin_lock_init(&i7300_idle_lock); total_us = 0; if (i7300_idle_platform_probe(&fbd_dev, &ioat_dev, forceload)) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index e5069b41d395..268319299797 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -799,7 +799,7 @@ 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); @@ -881,7 +881,7 @@ 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 c351aa421f8f..1ecaf60a564e 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/dm.c b/drivers/md/dm.c index 4720f68f817e..b1eff426c2fc 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1648,14 +1648,14 @@ 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 858fdbb7eb07..c2401e86b271 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1245,8 +1245,9 @@ 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++; @@ -1298,7 +1299,8 @@ 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(); } #ifdef CONFIG_MULTICORE_RAID456 @@ -4539,6 +4541,7 @@ static int raid5_alloc_percpu(struct r5conf *conf) break; } per_cpu_ptr(conf->percpu, cpu)->scribble = scribble; + spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); } #ifdef CONFIG_HOTPLUG_CPU conf->cpu_notify.notifier_call = raid456_cpu_notify; diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index e10c5531f9c5..010a96916bc2 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -405,6 +405,7 @@ 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 5664696f2d3a..951ae6c75011 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -82,6 +82,7 @@ config AB8500_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 @@ -97,8 +98,7 @@ 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 @@ -112,6 +112,14 @@ 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 IBM_ASM tristate "Device driver for IBM RSA service processor" depends on X86 && PCI && INPUT && EXPERIMENTAL @@ -133,6 +141,35 @@ 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 b26495a02554..84c45540db3a 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -48,3 +48,4 @@ obj-y += lis3lv02d/ obj-y += carma/ obj-$(CONFIG_USB_SWITCH_FSA9480) += fsa9480.o obj-$(CONFIG_ALTERA_STAPL) +=altera-stapl/ +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 000000000000..b7b7c903f88d --- /dev/null +++ b/drivers/misc/hwlat_detector.c @@ -0,0 +1,1212 @@ +/* + * 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. <jcm@redhat.com> + * + * Includes useful feedback from Clark Williams <clark@redhat.com> + * + * 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 <linux/module.h> +#include <linux/init.h> +#include <linux/ring_buffer.h> +#include <linux/stop_machine.h> +#include <linux/time.h> +#include <linux/hrtimer.h> +#include <linux/kthread.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/uaccess.h> +#include <linux/version.h> +#include <linux/delay.h> +#include <linux/slab.h> + +#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 <jcm@redhat.com>"); +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); +static int get_sample(void *unused); + +/* 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 */ + struct timespec timestamp; /* wall time */ + unsigned long lost; +}; + +/* keep the global state somewhere. Mostly used under stop_machine. */ +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 - suited for stop_machine use. + */ +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; +} + +/** + * get_sample - sample the CPU TSC and look for likely hardware latencies + * @unused: This is not used but is a part of the stop_machine API + * + * Used to repeatedly capture the CPU TSC (or similar), looking for potential + * hardware-induced latency. Called under stop_machine, with data.lock held. + */ +static int get_sample(void *unused) +{ + ktime_t start, t1, t2; + s64 diff, total = 0; + u64 sample = 0; + int ret = 1; + + start = ktime_get(); /* start timestamp */ + + do { + + t1 = ktime_get(); /* we'll look for a discontinuity */ + t2 = ktime_get(); + + total = ktime_to_us(ktime_sub(t2, start)); /* sample width */ + diff = ktime_to_us(ktime_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); + + /* If we exceed the threshold value, we have found a hardware latency */ + if (sample > data.threshold) { + struct sample s; + + data.count++; + s.seqnum = data.count; + s.duration = 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; + } + + ret = 0; +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 + * use stop_machine, whith 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. + * + * stop_machine will schedule us typically only on CPU0 which is fine for + * almost every real-world hardware latency situation - but we might later + * generalize this if we find there are any actualy systems with alternate + * SMI delivery or other non CPU0 hardware latencies. + */ +static int kthread_fn(void *unused) +{ + int err = 0; + u64 interval = 0; + + while (!kthread_should_stop()) { + + mutex_lock(&data.lock); + + err = stop_machine(get_sample, unused, 0); + if (err) { + /* Houston, we have a problem */ + mutex_unlock(&data.lock); + goto err_out; + } + + 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)) + goto out; + } + goto out; +err_out: + printk(KERN_ERR BANNER "could not call stop_machine, disabling\n"); + enabled = 0; +out: + return err; + +} + +/** + * 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 = 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 + * spinlock is held during the actual read (even though we likely won't ever + * actually race here as the updater runs under a stop_machine context). + */ +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 + * spinlock is held during the actual write (even though we likely won't ever + * actually race here as the updater runs under a stop_machine context). + */ +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\n", + sample->timestamp.tv_sec, + sample->timestamp.tv_nsec, + sample->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/net/Kconfig b/drivers/net/Kconfig index 654a5e94e0e7..0f5149d62324 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -154,6 +154,7 @@ config MACVTAP 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 <file:Documentation/networking/netconsole.txt> for details. diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index e0c552967921..af31580d47b9 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -843,9 +843,9 @@ 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 @@ -1921,12 +1921,12 @@ 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 eccdcff7a21f..ee8d8a233de9 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2236,11 +2236,7 @@ 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 95483bcac1d0..eaf84e96f69e 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -1819,8 +1819,7 @@ 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/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c index 56624d303487..ad4dbea804d4 100644 --- a/drivers/net/ethernet/cadence/at91_ether.c +++ b/drivers/net/ethernet/cadence/at91_ether.c @@ -200,7 +200,9 @@ static irqreturn_t at91ether_phy_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *) dev_id; struct at91_private *lp = netdev_priv(dev); unsigned int phy; + unsigned long flags; + spin_lock_irqsave(&lp->lock, flags); /* * This hander is triggered on both edges, but the PHY chips expect * level-triggering. We therefore have to check if the PHY actually has @@ -242,6 +244,7 @@ static irqreturn_t at91ether_phy_interrupt(int irq, void *dev_id) done: disable_mdi(); + spin_unlock_irqrestore(&lp->lock, flags); return IRQ_HANDLED; } @@ -398,9 +401,11 @@ static void at91ether_check_link(unsigned long dev_id) struct net_device *dev = (struct net_device *) dev_id; struct at91_private *lp = netdev_priv(dev); + spin_lock_irq(&lp->lock); enable_mdi(); update_linkspeed(dev, 1); disable_mdi(); + spin_unlock_irq(&lp->lock); mod_timer(&lp->check_timer, jiffies + LINK_POLL_INTERVAL); } diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c index f9b602300040..6d7412a67927 100644 --- a/drivers/net/ethernet/chelsio/cxgb/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb/sge.c @@ -1678,8 +1678,7 @@ 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 9656dd0647d9..ef7df09c7585 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1949,6 +1949,7 @@ static void __devexit 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 83199fd0d62b..97d238c0a114 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1671,7 +1671,7 @@ 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); @@ -1679,7 +1679,7 @@ 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) { @@ -2949,7 +2949,7 @@ 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) { @@ -3016,7 +3016,7 @@ 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/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index bfeccbfde236..fddfaf19061c 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -1304,7 +1304,7 @@ static int ehea_reg_interrupts(struct net_device *dev) "%s-queue%d", dev->name, i); ret = ibmebus_request_irq(pr->eq->attr.ist1, ehea_recv_irq_handler, - IRQF_DISABLED, pr->int_send_name, + IRQF_NO_THREAD, pr->int_send_name, pr); if (ret) { netdev_err(dev, "failed registering irq for ehea_queue port_res_nr:%d, ist=%X\n", diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index c27fb3dda9f4..462427825cdd 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -4090,12 +4090,7 @@ 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 48406ca382f1..8afefc2cfd20 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 @@ -1931,10 +1931,9 @@ static int pch_gbe_xmit_frame(struct sk_buff *skb, struct net_device *netdev) adapter->stats.tx_length_errors++; return NETDEV_TX_OK; } - 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 4d6b254fc6c1..004c054c9b3e 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -2174,7 +2174,7 @@ static irqreturn_t rtl8139_interrupt (int irq, void *dev_instance) */ static void rtl8139_poll_controller(struct net_device *dev) { - disable_irq(dev->irq); + disable_irq_nosync(dev->irq); rtl8139_interrupt(dev->irq, dev); enable_irq(dev->irq); } diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 3a90af6d111c..e2e930e0c8c2 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1605,13 +1605,8 @@ 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 7145714a5ec9..2a1ed18f25cd 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -176,11 +176,7 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev) u16 destid; unsigned long flags; - 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 ((rnet->tx_cnt + 1) > RIONET_TX_RING_SIZE) { netif_stop_queue(ndev); diff --git a/drivers/of/base.c b/drivers/of/base.c index 9b6588ef0673..becc6ca07beb 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -54,7 +54,7 @@ static DEFINE_MUTEX(of_aliases_mutex); /* use when traversing tree through the allnext, child, sibling, * or parent members of struct device_node. */ -DEFINE_RWLOCK(devtree_lock); +DEFINE_RAW_SPINLOCK(devtree_lock); int of_n_addr_cells(struct device_node *np) { @@ -163,16 +163,14 @@ void of_node_put(struct device_node *node) EXPORT_SYMBOL(of_node_put); #endif /* !CONFIG_SPARC */ -struct property *of_find_property(const struct device_node *np, - const char *name, - int *lenp) +static struct property *__of_find_property(const struct device_node *np, + const char *name, int *lenp) { struct property *pp; if (!np) return NULL; - read_lock(&devtree_lock); for (pp = np->properties; pp != 0; pp = pp->next) { if (of_prop_cmp(pp->name, name) == 0) { if (lenp != 0) @@ -180,7 +178,20 @@ struct property *of_find_property(const struct device_node *np, break; } } - read_unlock(&devtree_lock); + + return pp; +} + +struct property *of_find_property(const struct device_node *np, + const char *name, + int *lenp) +{ + struct property *pp; + unsigned long flags; + + raw_spin_lock_irqsave(&devtree_lock, flags); + pp = __of_find_property(np, name, lenp); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return pp; } @@ -198,13 +209,13 @@ struct device_node *of_find_all_nodes(struct device_node *prev) { struct device_node *np; - read_lock(&devtree_lock); + raw_spin_lock(&devtree_lock); np = prev ? prev->allnext : allnodes; for (; np != NULL; np = np->allnext) if (of_node_get(np)) break; of_node_put(prev); - read_unlock(&devtree_lock); + raw_spin_unlock(&devtree_lock); return np; } EXPORT_SYMBOL(of_find_all_nodes); @@ -213,8 +224,20 @@ EXPORT_SYMBOL(of_find_all_nodes); * Find a property with a given name for a given node * and return the value. */ +static const void *__of_get_property(const struct device_node *np, + const char *name, int *lenp) +{ + struct property *pp = __of_find_property(np, name, lenp); + + return pp ? pp->value : NULL; +} + +/* + * Find a property with a given name for a given node + * and return the value. + */ const void *of_get_property(const struct device_node *np, const char *name, - int *lenp) + int *lenp) { struct property *pp = of_find_property(np, name, lenp); @@ -225,13 +248,13 @@ EXPORT_SYMBOL(of_get_property); /** Checks if the given "compat" string matches one of the strings in * the device's "compatible" property */ -int of_device_is_compatible(const struct device_node *device, - const char *compat) +static int __of_device_is_compatible(const struct device_node *device, + const char *compat) { const char* cp; - int cplen, l; + int uninitialized_var(cplen), l; - cp = of_get_property(device, "compatible", &cplen); + cp = __of_get_property(device, "compatible", &cplen); if (cp == NULL) return 0; while (cplen > 0) { @@ -244,6 +267,21 @@ int of_device_is_compatible(const struct device_node *device, return 0; } + +/** Checks if the given "compat" string matches one of the strings in + * the device's "compatible" property + */ +int of_device_is_compatible(const struct device_node *device, + const char *compat) +{ + unsigned long flags; + int res; + + raw_spin_lock_irqsave(&devtree_lock, flags); + res = __of_device_is_compatible(device, compat); + raw_spin_unlock_irqrestore(&devtree_lock, flags); + return res; +} EXPORT_SYMBOL(of_device_is_compatible); /** @@ -303,13 +341,14 @@ EXPORT_SYMBOL(of_device_is_available); struct device_node *of_get_parent(const struct device_node *node) { struct device_node *np; + unsigned long flags; if (!node) return NULL; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); np = of_node_get(node->parent); - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; } EXPORT_SYMBOL(of_get_parent); @@ -328,14 +367,15 @@ EXPORT_SYMBOL(of_get_parent); struct device_node *of_get_next_parent(struct device_node *node) { struct device_node *parent; + unsigned long flags; if (!node) return NULL; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); parent = of_node_get(node->parent); of_node_put(node); - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return parent; } @@ -351,14 +391,15 @@ struct device_node *of_get_next_child(const struct device_node *node, struct device_node *prev) { struct device_node *next; + unsigned long flags; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); next = prev ? prev->sibling : node->child; for (; next; next = next->sibling) if (of_node_get(next)) break; of_node_put(prev); - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return next; } EXPORT_SYMBOL(of_get_next_child); @@ -373,14 +414,15 @@ EXPORT_SYMBOL(of_get_next_child); struct device_node *of_find_node_by_path(const char *path) { struct device_node *np = allnodes; + unsigned long flags; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); for (; np; np = np->allnext) { if (np->full_name && (of_node_cmp(np->full_name, path) == 0) && of_node_get(np)) break; } - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; } EXPORT_SYMBOL(of_find_node_by_path); @@ -400,15 +442,16 @@ struct device_node *of_find_node_by_name(struct device_node *from, const char *name) { struct device_node *np; + unsigned long flags; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); np = from ? from->allnext : allnodes; for (; np; np = np->allnext) if (np->name && (of_node_cmp(np->name, name) == 0) && of_node_get(np)) break; of_node_put(from); - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; } EXPORT_SYMBOL(of_find_node_by_name); @@ -429,15 +472,16 @@ struct device_node *of_find_node_by_type(struct device_node *from, const char *type) { struct device_node *np; + unsigned long flags; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); np = from ? from->allnext : allnodes; for (; np; np = np->allnext) if (np->type && (of_node_cmp(np->type, type) == 0) && of_node_get(np)) break; of_node_put(from); - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; } EXPORT_SYMBOL(of_find_node_by_type); @@ -460,18 +504,20 @@ struct device_node *of_find_compatible_node(struct device_node *from, const char *type, const char *compatible) { struct device_node *np; + unsigned long flags; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); np = from ? from->allnext : allnodes; for (; np; np = np->allnext) { if (type && !(np->type && (of_node_cmp(np->type, type) == 0))) continue; - if (of_device_is_compatible(np, compatible) && of_node_get(np)) + if (__of_device_is_compatible(np, compatible) && + of_node_get(np)) break; } of_node_put(from); - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; } EXPORT_SYMBOL(of_find_compatible_node); @@ -493,8 +539,9 @@ struct device_node *of_find_node_with_property(struct device_node *from, { struct device_node *np; struct property *pp; + unsigned long flags; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); np = from ? from->allnext : allnodes; for (; np; np = np->allnext) { for (pp = np->properties; pp != 0; pp = pp->next) { @@ -506,20 +553,14 @@ struct device_node *of_find_node_with_property(struct device_node *from, } out: of_node_put(from); - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; } EXPORT_SYMBOL(of_find_node_with_property); -/** - * of_match_node - Tell if an device_node has a matching of_match structure - * @matches: array of of device match structures to search in - * @node: the of device structure to match against - * - * Low level utility function used by device matching. - */ -const struct of_device_id *of_match_node(const struct of_device_id *matches, - const struct device_node *node) +static +const struct of_device_id *__of_match_node(const struct of_device_id *matches, + const struct device_node *node) { if (!matches) return NULL; @@ -533,14 +574,33 @@ const struct of_device_id *of_match_node(const struct of_device_id *matches, match &= node->type && !strcmp(matches->type, node->type); if (matches->compatible[0]) - match &= of_device_is_compatible(node, - matches->compatible); + match &= __of_device_is_compatible(node, + matches->compatible); if (match) return matches; matches++; } return NULL; } + +/** + * of_match_node - Tell if an device_node has a matching of_match structure + * @matches: array of of device match structures to search in + * @node: the of device structure to match against + * + * Low level utility function used by device matching. + */ +const struct of_device_id *of_match_node(const struct of_device_id *matches, + const struct device_node *node) +{ + const struct of_device_id *match; + unsigned long flags; + + raw_spin_lock_irqsave(&devtree_lock, flags); + match = __of_match_node(matches, node); + raw_spin_unlock_irqrestore(&devtree_lock, flags); + return match; +} EXPORT_SYMBOL(of_match_node); /** @@ -559,15 +619,16 @@ struct device_node *of_find_matching_node(struct device_node *from, const struct of_device_id *matches) { struct device_node *np; + unsigned long flags; - read_lock(&devtree_lock); + raw_spin_lock_irqsave(&devtree_lock, flags); np = from ? from->allnext : allnodes; for (; np; np = np->allnext) { - if (of_match_node(matches, np) && of_node_get(np)) + if (__of_match_node(matches, np) && of_node_get(np)) break; } of_node_put(from); - read_unlock(&devtree_lock); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return np; } EXPORT_SYMBOL(of_find_matching_node); @@ -610,12 +671,12 @@ struct device_node *of_find_node_by_phandle(phandle handle) { struct device_node *np; - read_lock(&devtree_lock); + raw_spin_lock(&devtree_lock); for (np = allnodes; np; np = np->allnext) if (np->phandle == handle) break; of_node_get(np); - read_unlock(&devtree_lock); + raw_spin_unlock(&devtree_lock); return np; } EXPORT_SYMBOL(of_find_node_by_phandle); @@ -949,18 +1010,18 @@ int prom_add_property(struct device_node *np, struct property *prop) unsigned long flags; prop->next = NULL; - write_lock_irqsave(&devtree_lock, flags); + raw_spin_lock_irqsave(&devtree_lock, flags); next = &np->properties; while (*next) { if (strcmp(prop->name, (*next)->name) == 0) { /* duplicate ! don't insert it */ - write_unlock_irqrestore(&devtree_lock, flags); + raw_spin_unlock_irqrestore(&devtree_lock, flags); return -1; } next = &(*next)->next; } *next = prop; - write_unlock_irqrestore(&devtree_lock, flags); + raw_spin_unlock_irqrestore(&devtree_lock, flags); #ifdef CONFIG_PROC_DEVICETREE /* try to add to proc as well if it was initialized */ @@ -985,7 +1046,7 @@ int prom_remove_property(struct device_node *np, struct property *prop) unsigned long flags; int found = 0; - write_lock_irqsave(&devtree_lock, flags); + raw_spin_lock_irqsave(&devtree_lock, flags); next = &np->properties; while (*next) { if (*next == prop) { @@ -998,7 +1059,7 @@ int prom_remove_property(struct device_node *np, struct property *prop) } next = &(*next)->next; } - write_unlock_irqrestore(&devtree_lock, flags); + raw_spin_unlock_irqrestore(&devtree_lock, flags); if (!found) return -ENODEV; @@ -1028,7 +1089,7 @@ int prom_update_property(struct device_node *np, unsigned long flags; int found = 0; - write_lock_irqsave(&devtree_lock, flags); + raw_spin_lock_irqsave(&devtree_lock, flags); next = &np->properties; while (*next) { if (*next == oldprop) { @@ -1042,7 +1103,7 @@ int prom_update_property(struct device_node *np, } next = &(*next)->next; } - write_unlock_irqrestore(&devtree_lock, flags); + raw_spin_unlock_irqrestore(&devtree_lock, flags); if (!found) return -ENODEV; @@ -1072,12 +1133,12 @@ void of_attach_node(struct device_node *np) { unsigned long flags; - write_lock_irqsave(&devtree_lock, flags); + raw_spin_lock_irqsave(&devtree_lock, flags); np->sibling = np->parent->child; np->allnext = allnodes; np->parent->child = np; allnodes = np; - write_unlock_irqrestore(&devtree_lock, flags); + raw_spin_unlock_irqrestore(&devtree_lock, flags); } /** @@ -1091,7 +1152,7 @@ void of_detach_node(struct device_node *np) struct device_node *parent; unsigned long flags; - write_lock_irqsave(&devtree_lock, flags); + raw_spin_lock_irqsave(&devtree_lock, flags); parent = np->parent; if (!parent) @@ -1122,7 +1183,7 @@ void of_detach_node(struct device_node *np) of_node_set_flag(np, OF_DETACHED); out_unlock: - write_unlock_irqrestore(&devtree_lock, flags); + raw_spin_unlock_irqrestore(&devtree_lock, flags); } #endif /* defined(CONFIG_OF_DYNAMIC) */ diff --git a/drivers/pci/access.c b/drivers/pci/access.c index fdaa42aac7c6..1a6cc6730286 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -441,7 +441,7 @@ void pci_unblock_user_cfg_access(struct pci_dev *dev) WARN_ON(!dev->block_ucfg_access); dev->block_ucfg_access = 0; - wake_up_all(&pci_ucfg_wait); + wake_up_all_locked(&pci_ucfg_wait); raw_spin_unlock_irqrestore(&pci_lock, flags); } EXPORT_SYMBOL_GPL(pci_unblock_user_cfg_access); diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index 8d67467dd9ce..4085187de539 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -1156,7 +1156,7 @@ 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); @@ -1212,7 +1212,7 @@ 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 @@ -1435,11 +1435,11 @@ 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; } @@ -1680,7 +1680,7 @@ static void fcoe_recv_frame(struct sk_buff *skb) */ hp = (struct fcoe_hdr *) skb_network_header(skb); - stats = per_cpu_ptr(lport->dev_stats, get_cpu()); + stats = per_cpu_ptr(lport->dev_stats, get_cpu_light()); if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { if (stats->ErrorFrames < 5) printk(KERN_WARNING "fcoe: FCoE version " @@ -1712,13 +1712,13 @@ 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 e7522dcc296e..bfb83c08a3e8 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -719,7 +719,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) unsigned long sel_time = 0; struct fcoe_dev_stats *stats; - stats = per_cpu_ptr(fip->lp->dev_stats, get_cpu()); + stats = per_cpu_ptr(fip->lp->dev_stats, get_cpu_light()); list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; @@ -752,7 +752,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip) sel_time = fcf->time; } } - put_cpu(); + put_cpu_light(); if (sel_time && !fip->sel_fcf && !fip->sel_time) { sel_time += msecs_to_jiffies(FCOE_CTLR_START_DELAY); fip->sel_time = sel_time; diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 9de9db27e874..340998f662dc 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -724,10 +724,10 @@ 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/tty/serial/8250.c b/drivers/tty/serial/8250.c index eeadf1b8e093..0596a359d30c 100644 --- a/drivers/tty/serial/8250.c +++ b/drivers/tty/serial/8250.c @@ -38,6 +38,7 @@ #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> +#include <linux/kdb.h> #include <asm/io.h> #include <asm/irq.h> @@ -81,7 +82,16 @@ 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) @@ -2846,14 +2856,14 @@ serial8250_console_write(struct console *co, const char *s, unsigned int count) touch_nmi_watchdog(); - local_irq_save(flags); - if (up->port.sysrq) { - /* serial8250_handle_port() already took the lock */ + if (unlikely(in_kdb_printk())) { locked = 0; - } else if (oops_in_progress) { - locked = spin_trylock(&up->port.lock); - } else - spin_lock(&up->port.lock); + } else { + if (up->port.sysrq || oops_in_progress) + locked = spin_trylock_irqsave(&up->port.lock, flags); + else + spin_lock_irqsave(&up->port.lock, flags); + } /* * First save the IER then disable the interrupts @@ -2885,8 +2895,7 @@ serial8250_console_write(struct console *co, const char *s, unsigned int count) check_modem_status(up); if (locked) - spin_unlock(&up->port.lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&up->port.lock, flags); } static int __init serial8250_console_setup(struct console *co, char *options) diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index b418947b7107..a8b05594e468 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -1226,7 +1226,7 @@ static void cpm_uart_console_write(struct console *co, const char *s, { struct uart_cpm_port *pinfo = &cpm_uart_ports[co->index]; unsigned long flags; - int nolock = oops_in_progress; + int nolock = oops_in_progress || sysrq_in_progress; if (unlikely(nolock)) { local_irq_save(flags); diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 5e713d3ef1f4..93cdb92d1632 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -946,13 +946,12 @@ serial_omap_console_write(struct console *co, const char *s, unsigned int ier; int locked = 1; - local_irq_save(flags); if (up->port.sysrq) locked = 0; else if (oops_in_progress) - locked = spin_trylock(&up->port.lock); + 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 @@ -979,8 +978,7 @@ serial_omap_console_write(struct console *co, const char *s, check_modem_status(up); 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/sysrq.c b/drivers/tty/sysrq.c index 43db715f1502..5219738ffd11 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -492,6 +492,23 @@ static void __sysrq_put_key_op(int key, struct sysrq_key_op *op_p) sysrq_key_table[i] = op_p; } +#ifdef CONFIG_MAGIC_SYSRQ_FORCE_PRINTK + +int sysrq_in_progress; + +static void set_sysrq_in_progress(int value) +{ + sysrq_in_progress = value; +} + +#else + +static void set_sysrq_in_progress(int value) +{ +} + +#endif + void __handle_sysrq(int key, bool check_mask) { struct sysrq_key_op *op_p; @@ -500,6 +517,9 @@ void __handle_sysrq(int key, bool check_mask) unsigned long flags; spin_lock_irqsave(&sysrq_key_table_lock, flags); + + set_sysrq_in_progress(1); + /* * Raise the apparent loglevel to maximum so that the sysrq header * is shown to provide the user with positive feedback. We do not @@ -541,6 +561,9 @@ void __handle_sysrq(int key, bool check_mask) printk("\n"); console_loglevel = orig_log_level; } + + set_sysrq_in_progress(0); + spin_unlock_irqrestore(&sysrq_key_table_lock, flags); } diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 6c9b7cd6778a..a56c2231fed3 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -493,10 +493,14 @@ void tty_flip_buffer_push(struct tty_struct *tty) tty->buf.tail->commit = tty->buf.tail->used; spin_unlock_irqrestore(&tty->buf.lock, flags); +#ifndef CONFIG_PREEMPT_RT_FULL if (tty->low_latency) flush_to_ldisc(&tty->buf.work); else schedule_work(&tty->buf.work); +#else + flush_to_ldisc(&tty->buf.work); +#endif } EXPORT_SYMBOL(tty_flip_buffer_push); diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 8e0924f55446..820f7dc90061 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -71,7 +71,7 @@ static void put_ldisc(struct tty_ldisc *ld) * We really want an "atomic_dec_and_lock_irqsave()", * but we don't have it, so this does it by hand. */ - local_irq_save(flags); + local_irq_save_nort(flags); if (atomic_dec_and_lock(&ld->users, &tty_ldisc_lock)) { struct tty_ldisc_ops *ldo = ld->ops; @@ -82,7 +82,7 @@ static void put_ldisc(struct tty_ldisc *ld) kfree(ld); return; } - local_irq_restore(flags); + local_irq_restore_nort(flags); wake_up(&tty_ldisc_idle); } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 8cb9304e8d4f..32dfd76d8f92 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2145,7 +2145,7 @@ 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; @@ -2158,7 +2158,7 @@ irqreturn_t usb_hcd_irq (int irq, void *__hcd) 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/ci13xxx_udc.c b/drivers/usb/gadget/ci13xxx_udc.c index 9a0c3979ff43..f526873313e5 100644 --- a/drivers/usb/gadget/ci13xxx_udc.c +++ b/drivers/usb/gadget/ci13xxx_udc.c @@ -819,7 +819,7 @@ static struct { } dbg_data = { .idx = 0, .tty = 0, - .lck = __RW_LOCK_UNLOCKED(lck) + .lck = __RW_LOCK_UNLOCKED(dbg_data.lck) }; /** diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index b2639191549e..d4b05d1106af 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -830,9 +830,13 @@ 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 308a98bdb5f7..67ed18635597 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -34,6 +34,7 @@ #include <linux/sched.h> #include <linux/mount.h> #include <linux/namei.h> +#include <linux/delay.h> #include <asm/current.h> #include <asm/uaccess.h> diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 450f529a4eae..43afbb02856e 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -170,7 +170,7 @@ 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 19d8eb7fdc81..32c46802c43c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -331,8 +331,7 @@ 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; @@ -345,8 +344,7 @@ 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 @@ -358,9 +356,7 @@ 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); } /* @@ -394,8 +390,7 @@ 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); @@ -407,15 +402,12 @@ 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); @@ -3223,6 +3215,7 @@ 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 eb723d317043..d47b2660eea1 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -37,6 +37,7 @@ #include <linux/rculist_bl.h> #include <linux/prefetch.h> #include <linux/ratelimit.h> +#include <linux/delay.h> #include "internal.h" /* @@ -410,7 +411,7 @@ 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)) @@ -796,7 +797,7 @@ relock: if (!spin_trylock(&dentry->d_lock)) { spin_unlock(&dcache_lru_lock); - cpu_relax(); + cpu_chill(); goto relock; } @@ -1975,7 +1976,7 @@ again: if (dentry->d_count == 1) { if (inode && !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 ea54cdef04dd..34294b931b9f 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -464,12 +464,12 @@ 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 36254645b7cc..aabd97d8babf 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -837,10 +837,12 @@ static int exec_mmap(struct mm_struct *mm) } } task_lock(tsk); + local_irq_disable_rt(); active_mm = tsk->active_mm; tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + local_irq_enable_rt(); task_unlock(tsk); arch_pick_mmap_layout(mm); if (old_mm) { diff --git a/fs/file.c b/fs/file.c index 4c6992d8f3ba..fd0325842717 100644 --- a/fs/file.c +++ b/fs/file.c @@ -105,14 +105,14 @@ void free_fdtable_rcu(struct rcu_head *rcu) kfree(fdt->open_fds); kfree(fdt); } else { - fddef = &get_cpu_var(fdtable_defer_list); + fddef = &per_cpu(fdtable_defer_list, get_cpu_light()); spin_lock(&fddef->lock); fdt->next = fddef->next; fddef->next = fdt; /* vmallocs are handled from the workqueue context */ schedule_work(&fddef->wq); spin_unlock(&fddef->lock); - put_cpu_var(fdtable_defer_list); + put_cpu_light(); } } @@ -422,7 +422,7 @@ struct files_struct init_files = { .close_on_exec = (fd_set *)&init_files.close_on_exec_init, .open_fds = (fd_set *)&init_files.open_fds_init, }, - .file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock), + .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), }; /* diff --git a/fs/fs_struct.c b/fs/fs_struct.c index 78b519c13536..f5818c41f143 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -26,11 +26,11 @@ void set_fs_root(struct fs_struct *fs, struct path *path) { struct path old_root; + path_get_longterm(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; fs->root = *path; - path_get_longterm(path); write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) @@ -45,11 +45,11 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path) { struct path old_pwd; + path_get_longterm(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; - path_get_longterm(path); write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); @@ -57,6 +57,14 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path) path_put_longterm(&old_pwd); } +static inline int replace_path(struct path *p, const struct path *old, const struct path *new) +{ + if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) + return 0; + *p = *new; + return 1; +} + void chroot_fs_refs(struct path *old_root, struct path *new_root) { struct task_struct *g, *p; @@ -68,21 +76,16 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root) task_lock(p); fs = p->fs; if (fs) { + int hits = 0; spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); - if (fs->root.dentry == old_root->dentry - && fs->root.mnt == old_root->mnt) { - path_get_longterm(new_root); - fs->root = *new_root; + hits += replace_path(&fs->root, old_root, new_root); + hits += replace_path(&fs->pwd, old_root, new_root); + write_seqcount_end(&fs->seq); + while (hits--) { count++; - } - if (fs->pwd.dentry == old_root->dentry - && fs->pwd.mnt == old_root->mnt) { path_get_longterm(new_root); - fs->pwd = *new_root; - count++; } - write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); } task_unlock(p); diff --git a/fs/namespace.c b/fs/namespace.c index cfc6d4448aa5..311264b1002d 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -31,6 +31,7 @@ #include <linux/idr.h> #include <linux/fs_struct.h> #include <linux/fsnotify.h> +#include <linux/delay.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include "pnode.h" @@ -341,8 +342,14 @@ int mnt_want_write(struct vfsmount *mnt) * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); - while (mnt->mnt_flags & MNT_WRITE_HOLD) - cpu_relax(); + /* + * No need to keep preemption disabled accross the spin loop. + */ + while (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 @@ -352,9 +359,7 @@ int mnt_want_write(struct vfsmount *mnt) if (__mnt_is_readonly(mnt)) { mnt_dec_writers(mnt); ret = -EROFS; - goto out; } -out: preempt_enable(); return ret; } diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 0b1e885b8cf8..4c8095c6544f 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, KM_BIO_SRC_IRQ); for (i = 0; i < recs; i++) post_read_mst_fixup((NTFS_RECORD*)(kaddr + i * rec_size), rec_size); kunmap_atomic(kaddr, KM_BIO_SRC_IRQ); - 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 dffeb3795af1..57f0e4e86f0a 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -313,7 +313,7 @@ SYSCALL_DEFINE4(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/asm-generic/bug.h b/include/asm-generic/bug.h index 84458b0c38d1..97c1eafe24c3 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -3,6 +3,10 @@ #include <linux/compiler.h> +#ifndef __ASSEMBLY__ +extern void __WARN_ON(const char *func, const char *file, const int line); +#endif /* __ASSEMBLY__ */ + #ifdef CONFIG_BUG #ifdef CONFIG_GENERIC_BUG @@ -202,4 +206,18 @@ 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 diff --git a/include/asm-generic/cmpxchg-local.h b/include/asm-generic/cmpxchg-local.h index 2533fddd34a6..d8d4c898c1bb 100644 --- a/include/asm-generic/cmpxchg-local.h +++ b/include/asm-generic/cmpxchg-local.h @@ -21,7 +21,7 @@ static inline unsigned long __cmpxchg_local_generic(volatile void *ptr, if (size == 8 && sizeof(unsigned long) != 8) wrong_size_cmpxchg(ptr); - local_irq_save(flags); + raw_local_irq_save(flags); switch (size) { case 1: prev = *(u8 *)ptr; if (prev == old) @@ -42,7 +42,7 @@ static inline unsigned long __cmpxchg_local_generic(volatile void *ptr, default: wrong_size_cmpxchg(ptr); } - local_irq_restore(flags); + raw_local_irq_restore(flags); return prev; } @@ -55,11 +55,11 @@ static inline u64 __cmpxchg64_local_generic(volatile void *ptr, u64 prev; unsigned long flags; - local_irq_save(flags); + raw_local_irq_save(flags); prev = *(u64 *)ptr; if (prev == old) *(u64 *)ptr = new; - local_irq_restore(flags); + raw_local_irq_restore(flags); return prev; } diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 458f497738a4..3f8e27b16ed5 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -72,8 +72,52 @@ 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/console.h b/include/linux/console.h index 7453cfd593c8..e5b5dc0c737b 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -133,6 +133,7 @@ struct console { for (con = console_drivers; con != NULL; con = con->next) extern int console_set_on_cmdline; +extern struct console *early_console; extern int add_preferred_console(char *name, int idx, char *options); extern int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 6cb60fd2ea84..72e90bbf625a 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -66,8 +66,10 @@ enum { /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, CPU_PRI_MIGRATION = 10, - /* prepare workqueues for other notifiers */ - CPU_PRI_WORKQUEUE = 5, + + CPU_PRI_WORKQUEUE_ACTIVE = 5, /* prepare workqueues for others */ + CPU_PRI_NORMAL = 0, + CPU_PRI_WORKQUEUE_INACTIVE = -5, /* flush workqueues after others */ }; #define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */ @@ -167,6 +169,8 @@ extern struct sysdev_class cpu_sysdev_class; extern void get_online_cpus(void); extern void put_online_cpus(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) @@ -189,6 +193,8 @@ static inline void cpu_hotplug_driver_unlock(void) #define get_online_cpus() do { } while (0) #define put_online_cpus() 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 a6ecb34cf547..e23a7c021eeb 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 c3da42dd22ba..7c5e1765a0fd 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -49,7 +49,8 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; - int padding; + unsigned short migrate_disable; + unsigned short padding; }; #define FTRACE_MAX_EVENT \ diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index f743883f769e..7059ce231a36 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -60,7 +60,11 @@ #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 @@ -73,10 +77,17 @@ #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? @@ -86,7 +97,6 @@ #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/hrtimer.h b/include/linux/hrtimer.h index fd0dc30c9f15..0e3708636ce0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -111,6 +111,8 @@ 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_TIMER_STATS int start_pid; void *start_site; @@ -147,6 +149,7 @@ 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; @@ -187,6 +190,9 @@ 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]; }; @@ -374,6 +380,13 @@ 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 255491cf522e..4eaacf03e4a6 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -136,7 +136,7 @@ struct ida { struct ida_bitmap *free_bitmap; }; -#define IDA_INIT(name) { .idr = IDR_INIT(name), .free_bitmap = NULL, } +#define IDA_INIT(name) { .idr = IDR_INIT((name).idr), .free_bitmap = NULL, } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) int ida_pre_get(struct ida *ida, gfp_t gfp_mask); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 32574eef9394..cfd9f8de4dc2 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -126,6 +126,12 @@ extern struct cred init_cred; # 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 + #define INIT_TASK_COMM "swapper" /* @@ -180,6 +186,7 @@ extern struct cred init_cred; .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 a64b00e286f5..f70a65b2a051 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -61,6 +61,7 @@ * 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_SAMPLE_RANDOM 0x00000040 @@ -75,6 +76,7 @@ #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) @@ -219,7 +221,7 @@ 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); @@ -396,9 +398,13 @@ 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 @@ -452,8 +458,14 @@ 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); static inline void __raise_softirq_irqoff(unsigned int nr) @@ -465,6 +477,8 @@ static inline 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 @@ -505,8 +519,9 @@ 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. @@ -531,27 +546,36 @@ 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 @@ -600,17 +624,8 @@ 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); @@ -642,6 +657,12 @@ 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 bff29c58da23..3838b5355544 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -67,6 +67,7 @@ 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, @@ -90,12 +91,14 @@ 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/irqflags.h b/include/linux/irqflags.h index d176d658fe25..a52b35d4229f 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 6230f8556a4e..11c313e8561d 100644 --- a/include/linux/jbd_common.h +++ b/include/linux/jbd_common.h @@ -37,32 +37,56 @@ 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 388b0d425b50..9cc8ed96888f 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -4,7 +4,7 @@ #include <linux/types.h> #include <linux/compiler.h> -#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 jump_label_key { atomic_t enabled; diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 064725854db8..0d1ebfc9ff43 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -150,12 +150,14 @@ extern int kdb_register(char *, kdb_func_t, char *, char *, short); extern int kdb_register_repeat(char *, kdb_func_t, char *, char *, short, kdb_repeat_t); extern int kdb_unregister(char *); +#define in_kdb_printk() (kdb_trap_printk) #else /* ! CONFIG_KGDB_KDB */ #define kdb_printf(...) #define kdb_init(x) #define kdb_register(...) #define kdb_register_repeat(...) #define kdb_uregister(x) +#define in_kdb_printk() (0) #endif /* CONFIG_KGDB_KDB */ enum { KDB_NOT_INITIALIZED, diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e8b1597b5cf2..c485aaa618d6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -356,7 +356,7 @@ extern enum system_states { SYSTEM_HALT, SYSTEM_POWER_OFF, SYSTEM_RESTART, - SYSTEM_SUSPEND_DISK, + SYSTEM_SUSPEND, } system_state; #define TAINT_PROPRIETARY_MODULE 0 diff --git a/include/linux/lglock.h b/include/linux/lglock.h index 87f402ccec55..cdfcef312c79 100644 --- a/include/linux/lglock.h +++ b/include/linux/lglock.h @@ -71,6 +71,8 @@ extern void name##_global_lock_online(void); \ extern void name##_global_unlock_online(void); \ +#ifndef CONFIG_PREEMPT_RT_FULL + #define DEFINE_LGLOCK(name) \ \ DEFINE_SPINLOCK(name##_cpu_lock); \ @@ -197,4 +199,130 @@ preempt_enable(); \ } \ EXPORT_SYMBOL(name##_global_unlock); + +#else /* !PREEMPT_RT_FULL */ +#define DEFINE_LGLOCK(name) \ + \ + DEFINE_PER_CPU(struct rt_mutex, name##_lock); \ + DEFINE_SPINLOCK(name##_cpu_lock); \ + cpumask_t name##_cpus __read_mostly; \ + DEFINE_LGLOCK_LOCKDEP(name); \ + \ + static int \ + name##_lg_cpu_callback(struct notifier_block *nb, \ + unsigned long action, void *hcpu) \ + { \ + switch (action & ~CPU_TASKS_FROZEN) { \ + case CPU_UP_PREPARE: \ + spin_lock(&name##_cpu_lock); \ + cpu_set((unsigned long)hcpu, name##_cpus); \ + spin_unlock(&name##_cpu_lock); \ + break; \ + case CPU_UP_CANCELED: case CPU_DEAD: \ + spin_lock(&name##_cpu_lock); \ + cpu_clear((unsigned long)hcpu, name##_cpus); \ + spin_unlock(&name##_cpu_lock); \ + } \ + return NOTIFY_OK; \ + } \ + static struct notifier_block name##_lg_cpu_notifier = { \ + .notifier_call = name##_lg_cpu_callback, \ + }; \ + void name##_lock_init(void) { \ + int i; \ + LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \ + for_each_possible_cpu(i) { \ + struct rt_mutex *lock; \ + lock = &per_cpu(name##_lock, i); \ + rt_mutex_init(lock); \ + } \ + register_hotcpu_notifier(&name##_lg_cpu_notifier); \ + get_online_cpus(); \ + for_each_online_cpu(i) \ + cpu_set(i, name##_cpus); \ + put_online_cpus(); \ + } \ + EXPORT_SYMBOL(name##_lock_init); \ + \ + void name##_local_lock(void) { \ + struct rt_mutex *lock; \ + migrate_disable(); \ + rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_); \ + lock = &__get_cpu_var(name##_lock); \ + __rt_spin_lock(lock); \ + } \ + EXPORT_SYMBOL(name##_local_lock); \ + \ + void name##_local_unlock(void) { \ + struct rt_mutex *lock; \ + rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_); \ + lock = &__get_cpu_var(name##_lock); \ + __rt_spin_unlock(lock); \ + migrate_enable(); \ + } \ + EXPORT_SYMBOL(name##_local_unlock); \ + \ + void name##_local_lock_cpu(int cpu) { \ + struct rt_mutex *lock; \ + rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_); \ + lock = &per_cpu(name##_lock, cpu); \ + __rt_spin_lock(lock); \ + } \ + EXPORT_SYMBOL(name##_local_lock_cpu); \ + \ + void name##_local_unlock_cpu(int cpu) { \ + struct rt_mutex *lock; \ + rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_); \ + lock = &per_cpu(name##_lock, cpu); \ + __rt_spin_unlock(lock); \ + } \ + EXPORT_SYMBOL(name##_local_unlock_cpu); \ + \ + void name##_global_lock_online(void) { \ + int i; \ + rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ + spin_lock(&name##_cpu_lock); \ + for_each_cpu(i, &name##_cpus) { \ + struct rt_mutex *lock; \ + lock = &per_cpu(name##_lock, i); \ + __rt_spin_lock(lock); \ + } \ + } \ + EXPORT_SYMBOL(name##_global_lock_online); \ + \ + void name##_global_unlock_online(void) { \ + int i; \ + rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ + for_each_cpu(i, &name##_cpus) { \ + struct rt_mutex *lock; \ + lock = &per_cpu(name##_lock, i); \ + __rt_spin_unlock(lock); \ + } \ + spin_unlock(&name##_cpu_lock); \ + } \ + EXPORT_SYMBOL(name##_global_unlock_online); \ + \ + void name##_global_lock(void) { \ + int i; \ + rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ + for_each_possible_cpu(i) { \ + struct rt_mutex *lock; \ + lock = &per_cpu(name##_lock, i); \ + __rt_spin_lock(lock); \ + } \ + } \ + EXPORT_SYMBOL(name##_global_lock); \ + \ + void name##_global_unlock(void) { \ + int i; \ + rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ + for_each_possible_cpu(i) { \ + struct rt_mutex *lock; \ + lock = &per_cpu(name##_lock, i); \ + __rt_spin_unlock(lock); \ + } \ + } \ + EXPORT_SYMBOL(name##_global_unlock); +#endif /* PRREMPT_RT_FULL */ + #endif diff --git a/include/linux/list.h b/include/linux/list.h index cc6d2aa6b415..7a9851bbef04 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -362,6 +362,17 @@ static inline void list_splice_tail_init(struct list_head *list, list_entry((ptr)->next, type, member) /** + * 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/locallock.h b/include/linux/locallock.h new file mode 100644 index 000000000000..8fbc3938638f --- /dev/null +++ b/include/linux/locallock.h @@ -0,0 +1,230 @@ +#ifndef _LINUX_LOCALLOCK_H +#define _LINUX_LOCALLOCK_H + +#include <linux/spinlock.h> + +#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 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) + +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) + +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) + +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_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 + +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 4baadd18f4ad..c9e64e58f0d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1195,27 +1195,59 @@ 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 5b42f1b34eb7..c303a27981fe 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/page-debug-flags.h> +#include <linux/rcupdate.h> #include <asm/page.h> #include <asm/mmu.h> @@ -118,7 +119,11 @@ struct page { * system if PG_buddy is set. */ #if USE_SPLIT_PTLOCKS - spinlock_t ptl; +# ifndef CONFIG_PREEMPT_RT_FULL + spinlock_t ptl; +# else + spinlock_t *ptl; +# endif #endif struct kmem_cache *slab; /* SLUB: Pointer to slab */ struct page *first_page; /* Compound tail pages */ @@ -389,6 +394,9 @@ struct mm_struct { #ifdef CONFIG_CPUMASK_OFFSTACK struct cpumask cpumask_allocation; #endif +#ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head delayed_drop; +#endif }; static inline void mm_init_cpumask(struct mm_struct *mm) diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 9121595a8ebf..bdf1da2cf4b6 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -17,6 +17,17 @@ #include <linux/atomic.h> +#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 <linux/mutex_rt.h> +#else + /* * Simple, straightforward mutexes with strict semantics: * @@ -95,13 +106,6 @@ 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) \ @@ -167,6 +171,9 @@ 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 000000000000..c38a44b14da5 --- /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 <linux/rtmutex.h> + +/* FIXME: Just for __lockfunc */ +#include <linux/spinlock.h> + +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 a82ad4dd306a..a5bde7715be0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1760,6 +1760,7 @@ struct softnet_data { unsigned 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/of.h b/include/linux/of.h index 4948552d60f5..e87303dfbbfc 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -71,7 +71,7 @@ struct device_node { extern struct device_node *allnodes; extern struct device_node *of_chosen; extern struct device_node *of_aliases; -extern rwlock_t devtree_lock; +extern raw_spinlock_t devtree_lock; static inline bool of_have_populated_dt(void) { diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 961ecc7d30bc..2927c084ff50 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -30,6 +30,10 @@ enum { */ struct page_cgroup { unsigned long flags; +#ifdef CONFIG_PREEMPT_RT_BASE + spinlock_t pcg_lock; + spinlock_t pcm_lock; +#endif struct mem_cgroup *mem_cgroup; struct list_head lru; /* per cgroup LRU list */ }; @@ -96,30 +100,54 @@ 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, CACHE, 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 } static inline void move_lock_page_cgroup(struct page_cgroup *pc, unsigned long *flags) { +#ifndef CONFIG_PREEMPT_RT_BASE /* * We know updates to pc->flags of page cache's stats are from both of * usual context or IRQ context. Disable IRQ to avoid deadlock. */ local_irq_save(*flags); bit_spin_lock(PCG_MOVE_LOCK, &pc->flags); +#else + spin_lock_irqsave(&pc->pcm_lock, *flags); +#endif } static inline void move_unlock_page_cgroup(struct page_cgroup *pc, unsigned long *flags) { +#ifndef CONFIG_PREEMPT_RT_BASE bit_spin_unlock(PCG_MOVE_LOCK, &pc->flags); local_irq_restore(*flags); +#else + spin_unlock_irqrestore(&pc->pcm_lock, *flags); +#endif +} + +static inline void page_cgroup_lock_init(struct page_cgroup *pc) +{ +#ifdef CONFIG_PREEMPT_RT_BASE + spin_lock_init(&pc->pcg_lock); + spin_lock_init(&pc->pcm_lock); +#endif } #ifdef CONFIG_SPARSEMEM diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 9ca008f0c542..58163cd6cca1 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 b152d44fb181..7f336833f2c5 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -2,6 +2,7 @@ #define _LINUX_PID_H #include <linux/rcupdate.h> +#include <linux/atomic.h> enum pid_type { diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 58969b2a8a82..58d898278720 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -48,15 +48,23 @@ do { \ barrier(); \ } while (0) -#define preempt_enable_no_resched() \ +#define __preempt_enable_no_resched() \ do { \ barrier(); \ dec_preempt_count(); \ } while (0) +#ifndef CONFIG_PREEMPT_RT_BASE +# define preempt_enable_no_resched() __preempt_enable_no_resched() +# define preempt_check_resched_rt() do { } while (0) +#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(); \ + __preempt_enable_no_resched(); \ barrier(); \ preempt_check_resched(); \ } while (0) @@ -92,15 +100,38 @@ do { \ #else /* !CONFIG_PREEMPT_COUNT */ #define preempt_disable() do { } while (0) +#define __preempt_enable_no_resched() do { } while (0) #define preempt_enable_no_resched() do { } while (0) #define preempt_enable() do { } while (0) #define preempt_disable_notrace() do { } while (0) #define preempt_enable_no_resched_notrace() do { } while (0) #define preempt_enable_notrace() do { } while (0) +#define preempt_check_resched_rt() do { } while (0) #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() do { } while (0) +# define preempt_enable_nort() do { } while (0) +# ifdef CONFIG_SMP + extern void migrate_disable(void); + extern void migrate_enable(void); +# else /* CONFIG_SMP */ +# define migrate_disable() do { } while (0) +# define migrate_enable() do { } while (0) +# endif /* CONFIG_SMP */ +#else +# define preempt_disable_rt() do { } while (0) +# define preempt_enable_rt() do { } while (0) +# 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 f0e22f75143f..a53adf62ce7d 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -88,8 +88,15 @@ int no_printk(const char *fmt, ...) return 0; } +#ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); +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 extern int printk_needs_cpu(int cpu); extern void printk_tick(void); @@ -109,7 +116,6 @@ 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 9d4539c52e53..6b4bdf2097dd 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -231,7 +231,13 @@ 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); @@ -256,7 +262,7 @@ 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(); } #endif /* _LINUX_RADIX_TREE_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2cf4226ade7e..0e6fb5c9dce4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -92,6 +92,9 @@ 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. @@ -112,6 +115,7 @@ 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. @@ -147,6 +151,11 @@ 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 */ @@ -170,6 +179,8 @@ 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 */ @@ -274,7 +285,14 @@ 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? @@ -677,8 +695,12 @@ 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_read_acquire_bh(); +#endif } /* @@ -688,8 +710,12 @@ 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_read_release_bh(); __release(RCU_BH); +#endif local_bh_enable(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 67458468f1a8..6e503a364be6 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -57,7 +57,11 @@ static inline void exit_rcu(void) #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifndef CONFIG_PREEMPT_RT_FULL extern void synchronize_rcu_bh(void); +#else +# define synchronize_rcu_bh synchronize_rcu +#endif extern void synchronize_sched_expedited(void); extern void synchronize_rcu_expedited(void); @@ -67,19 +71,29 @@ 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); +#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 + /* A context switch is a grace period for RCU-sched and RCU-bh. */ static inline int rcu_blocking_is_gp(void) { diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index de17134244f3..5ebd0bbb6eaa 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -14,7 +14,7 @@ #include <linux/linkage.h> #include <linux/plist.h> -#include <linux/spinlock_types.h> +#include <linux/spinlock_types_raw.h> 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 000000000000..853ee367fef4 --- /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 cc0072e93e36..d0da966ad7a0 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 000000000000..b13832119591 --- /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 63d406554391..209be4b401a6 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -17,6 +17,10 @@ #include <asm/system.h> #include <linux/atomic.h> +#ifdef CONFIG_PREEMPT_RT_FULL +#include <linux/rwsem_rt.h> +#else /* PREEMPT_RT_FULL */ + struct rw_semaphore; #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK @@ -131,4 +135,6 @@ extern void down_write_nested(struct rw_semaphore *sem, int subclass); # define down_write_nested(sem, subclass) down_write(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 000000000000..802c6909900a --- /dev/null +++ b/include/linux/rwsem_rt.h @@ -0,0 +1,105 @@ +#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 <linux/rtmutex.h> + +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, char *name, + struct lock_class_key *key); + +# define rt_init_rwsem(sem) \ +do { \ + static struct lock_class_key __key; \ + \ + rt_mutex_init(&(sem)->lock); \ + __rt_rwsem_init((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_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); +} + +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c4f3e9b9bc5..1f6b11ad5312 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -63,6 +63,7 @@ struct sched_param { #include <linux/nodemask.h> #include <linux/mm_types.h> +#include <asm/kmap_types.h> #include <asm/system.h> #include <asm/page.h> #include <asm/ptrace.h> @@ -91,6 +92,7 @@ struct sched_param { #include <linux/latencytop.h> #include <linux/cred.h> #include <linux/llist.h> +#include <linux/hardirq.h> #include <asm/processor.h> @@ -359,6 +361,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); +extern void schedule_preempt_disabled(void); extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; @@ -1070,6 +1073,7 @@ struct sched_domain; #define WF_SYNC 0x01 /* waker goes to sleep after wakup */ #define WF_FORK 0x02 /* child wakeup after fork */ #define WF_MIGRATED 0x04 /* internal use, task got migrated */ +#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ #define ENQUEUE_WAKEUP 1 #define ENQUEUE_HEAD 2 @@ -1219,6 +1223,7 @@ 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 */ @@ -1255,6 +1260,12 @@ 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 cpumask_t cpus_allowed; #ifdef CONFIG_PREEMPT_RCU @@ -1353,6 +1364,9 @@ 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 @@ -1386,10 +1400,15 @@ 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; @@ -1429,6 +1448,9 @@ 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; @@ -1560,6 +1582,12 @@ 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 + unsigned long timer_offset; +#endif +#endif #endif /* CONFIG_TRACING */ #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */ struct memcg_batch_info { @@ -1572,10 +1600,26 @@ struct task_struct { #ifdef CONFIG_HAVE_HW_BREAKPOINT atomic_t ptrace_bp_refcnt; #endif +#ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head put_rcu; + int softirq_nestcnt; +#endif +#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM + int kmap_idx; + pte_t kmap_pte[KM_TYPE_NR]; +#endif }; -/* Future-safe accessor for struct task_struct's cpus_allowed. */ -#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) +#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(); +} /* * Priority of a process goes from 0..MAX_PRIO-1, valid RT @@ -1745,6 +1789,15 @@ 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) @@ -1752,6 +1805,7 @@ static inline void put_task_struct(struct task_struct *t) if (atomic_dec_and_test(&t->usage)) __put_task_struct(t); } +#endif extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st); extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st); @@ -1777,6 +1831,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_FROZEN 0x00010000 /* frozen for system suspend */ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */ #define PF_KSWAPD 0x00040000 /* I am kswapd */ +#define PF_STOMPER 0x00080000 /* I am a stomp machine thread */ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ @@ -2050,12 +2105,20 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); extern void rt_mutex_adjust_pi(struct task_struct *p); +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return tsk->pi_blocked_on != NULL; +} #else static inline int rt_mutex_getprio(struct task_struct *p) { return p->normal_prio; } # define rt_mutex_adjust_pi(p) do { } while (0) +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return false; +} #endif extern bool yield_to(struct task_struct *p, bool preempt); @@ -2135,6 +2198,7 @@ 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); @@ -2225,12 +2289,24 @@ 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 */ @@ -2533,7 +2609,7 @@ 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 @@ -2544,12 +2620,16 @@ 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 @@ -2612,6 +2692,26 @@ 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/seqlock.h b/include/linux/seqlock.h index c6db9fb33c44..a1dbf48d41f4 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -30,92 +30,12 @@ #include <linux/preempt.h> #include <asm/processor.h> -typedef struct { - unsigned sequence; - spinlock_t lock; -} seqlock_t; - -/* - * These macros triggered gcc-3.x compile-time problems. We think these are - * OK now. Be cautious. - */ -#define __SEQLOCK_UNLOCKED(lockname) \ - { 0, __SPIN_LOCK_UNLOCKED(lockname) } - -#define seqlock_init(x) \ - do { \ - (x)->sequence = 0; \ - spin_lock_init(&(x)->lock); \ - } while (0) - -#define DEFINE_SEQLOCK(x) \ - seqlock_t x = __SEQLOCK_UNLOCKED(x) - -/* Lock out other writers and update the count. - * Acts like a normal spin_lock/unlock. - * Don't need preempt_disable() because that is in the spin_lock already. - */ -static inline void write_seqlock(seqlock_t *sl) -{ - spin_lock(&sl->lock); - ++sl->sequence; - smp_wmb(); -} - -static inline void write_sequnlock(seqlock_t *sl) -{ - smp_wmb(); - sl->sequence++; - spin_unlock(&sl->lock); -} - -static inline int write_tryseqlock(seqlock_t *sl) -{ - int ret = spin_trylock(&sl->lock); - - if (ret) { - ++sl->sequence; - smp_wmb(); - } - return ret; -} - -/* Start of read calculation -- fetch last complete writer token */ -static __always_inline unsigned read_seqbegin(const seqlock_t *sl) -{ - unsigned ret; - -repeat: - ret = ACCESS_ONCE(sl->sequence); - if (unlikely(ret & 1)) { - cpu_relax(); - goto repeat; - } - smp_rmb(); - - return ret; -} - -/* - * Test if reader processed invalid data. - * - * If sequence value changed then writer changed data while in section. - */ -static __always_inline int read_seqretry(const seqlock_t *sl, unsigned start) -{ - smp_rmb(); - - return unlikely(sl->sequence != start); -} - - /* * Version using sequence counter only. * This can be used when code has its own mutex protecting the * updating starting before the write_seqcountbeqin() and ending * after the write_seqcount_end(). */ - typedef struct seqcount { unsigned sequence; } seqcount_t; @@ -197,7 +117,6 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); - return __read_seqcount_retry(s, start); } @@ -206,18 +125,30 @@ 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 @@ -231,31 +162,124 @@ static inline void write_seqcount_barrier(seqcount_t *s) s->sequence+=2; } +typedef struct { + struct seqcount seqcount; + spinlock_t lock; +} seqlock_t; + +/* + * These macros triggered gcc-3.x compile-time problems. We think these are + * OK now. Be cautious. + */ +#define __SEQLOCK_UNLOCKED(lockname) \ + { \ + .seqcount = SEQCNT_ZERO, \ + .lock = __SPIN_LOCK_UNLOCKED(lockname) \ + } + +#define seqlock_init(x) \ + do { \ + seqcount_init(&(x)->seqcount); \ + spin_lock_init(&(x)->lock); \ + } while (0) + +#define DEFINE_SEQLOCK(x) \ + seqlock_t x = __SEQLOCK_UNLOCKED(x) + +/* + * 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 = 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) +{ + return read_seqcount_retry(&sl->seqcount, start); +} + /* - * Possible sw/hw IRQ protected versions of the interfaces. + * Lock out other writers and update the count. + * Acts like a normal spin_lock/unlock. + * Don't need preempt_disable() because that is in the spin_lock already. */ +static inline void write_seqlock(seqlock_t *sl) +{ + spin_lock(&sl->lock); + __write_seqcount_begin(&sl->seqcount); +} + +static inline void write_sequnlock(seqlock_t *sl) +{ + __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); +} + +static inline void write_sequnlock_bh(seqlock_t *sl) +{ + __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); +} + +static inline void write_sequnlock_irq(seqlock_t *sl) +{ + __write_seqcount_end(&sl->seqcount); + spin_unlock_irq(&sl->lock); +} + +static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) +{ + unsigned long flags; + + spin_lock_irqsave(&sl->lock, flags); + __write_seqcount_begin(&sl->seqcount); + return flags; +} + #define write_seqlock_irqsave(lock, flags) \ - do { local_irq_save(flags); write_seqlock(lock); } while (0) -#define write_seqlock_irq(lock) \ - do { local_irq_disable(); write_seqlock(lock); } while (0) -#define write_seqlock_bh(lock) \ - do { local_bh_disable(); write_seqlock(lock); } while (0) - -#define write_sequnlock_irqrestore(lock, flags) \ - do { write_sequnlock(lock); local_irq_restore(flags); } while(0) -#define write_sequnlock_irq(lock) \ - do { write_sequnlock(lock); local_irq_enable(); } while(0) -#define write_sequnlock_bh(lock) \ - do { write_sequnlock(lock); local_bh_enable(); } while(0) - -#define read_seqbegin_irqsave(lock, flags) \ - ({ local_irq_save(flags); read_seqbegin(lock); }) - -#define read_seqretry_irqrestore(lock, iv, flags) \ - ({ \ - int ret = read_seqretry(lock, iv); \ - local_irq_restore(flags); \ - ret; \ - }) + do { flags = __write_seqlock_irqsave(lock); } while (0) + +static inline void +write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) +{ + __write_seqcount_end(&sl->seqcount); + spin_unlock_irqrestore(&sl->lock, flags); +} #endif /* __LINUX_SEQLOCK_H */ diff --git a/include/linux/signal.h b/include/linux/signal.h index a822300a253b..a4489006a5bb 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -229,6 +229,7 @@ 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 6cf8b5369b6e..ea9736d2f593 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -124,6 +124,7 @@ struct sk_buff_head { __u32 qlen; spinlock_t lock; + raw_spinlock_t raw_lock; }; struct sk_buff; @@ -925,6 +926,12 @@ 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 8cc38d3bab0c..78fd0a26fa05 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -80,7 +80,6 @@ void __smp_call_function_single(int cpuid, struct call_single_data *data, int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait); - /* * Generic and arch helpers */ @@ -173,6 +172,9 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, #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 7df6c17b0281..5fe7e40a269a 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -254,7 +254,11 @@ 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 <linux/rwlock.h> +#ifdef CONFIG_PREEMPT_RT_FULL +# include <linux/rwlock_rt.h> +#else +# include <linux/rwlock.h> +#endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: @@ -265,6 +269,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # include <linux/spinlock_api_up.h> #endif +#ifdef CONFIG_PREEMPT_RT_FULL +# include <linux/spinlock_rt.h> +#else /* PREEMPT_RT_FULL */ + /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ @@ -397,4 +405,6 @@ 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 e253ccd7a604..2a5ba05ebace 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 <linux/rwlock_api_smp.h> +#ifndef CONFIG_PREEMPT_RT_FULL +# include <linux/rwlock_api_smp.h> +#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 000000000000..3b555b4b52cf --- /dev/null +++ b/include/linux/spinlock_rt.h @@ -0,0 +1,166 @@ +#ifndef __LINUX_SPINLOCK_RT_H +#define __LINUX_SPINLOCK_RT_H + +#ifndef __LINUX_SPINLOCK_H +#error Do not include directly. Use spinlock.h +#endif + +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_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 73548eb13a5d..10bac715ea96 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 <asm/spinlock_types.h> -#else -# include <linux/spinlock_types_up.h> -#endif - -#include <linux/lockdep.h> - -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 <linux/spinlock_types_raw.h> -#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 <linux/spinlock_types_nort.h> +# include <linux/rwlock_types.h> #else -# define SPIN_DEBUG_INIT(lockname) +# include <linux/rtmutex.h> +# include <linux/spinlock_types_rt.h> +# include <linux/rwlock_types_rt.h> #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 <linux/rwlock_types.h> - #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 000000000000..f1dac1fb1d6a --- /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 000000000000..edffc4d53fc9 --- /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 <asm/spinlock_types.h> +#else +# include <linux/spinlock_types_up.h> +#endif + +#include <linux/lockdep.h> + +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 000000000000..1fe8fc069d9b --- /dev/null +++ b/include/linux/spinlock_types_rt.h @@ -0,0 +1,49 @@ +#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 + +/* + * 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/sysctl.h b/include/linux/sysctl.h index 703cfa33a3ca..b954c4136da3 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -932,6 +932,7 @@ enum #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/wait.h> +#include <linux/atomic.h> /* For the /proc/sys support */ struct ctl_table; diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 7faf933cced7..d224c0bae8df 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -38,6 +38,11 @@ struct sysrq_key_op { int enable_mask; }; +#ifdef CONFIG_MAGIC_SYSRQ_FORCE_PRINTK +extern int sysrq_in_progress; +#else +#define sysrq_in_progress 0 +#endif #ifdef CONFIG_MAGIC_SYSRQ /* Generic SysRq interface -- you may call it from any device driver, supplying diff --git a/include/linux/timer.h b/include/linux/timer.h index 6abd9138beda..b703477bd2d6 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -276,7 +276,7 @@ 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 5ca0951e1855..44b37510c14f 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/vmstat.h b/include/linux/vmstat.h index 65efb92da996..1b3f2efd3ad0 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.h b/include/linux/wait.h index 3efc9f3f43a0..1e904b88c1ea 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -157,7 +157,7 @@ void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode); +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_bit(wait_queue_head_t *, void *, int); int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); @@ -170,7 +170,8 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) -#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL) +#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) +#define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e228ca9e1b5a..3d8ac9de5ec2 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -254,9 +254,10 @@ enum { WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_NON_AFFINE = 1 << 6, /* free to move works around cpus */ - WQ_DRAINING = 1 << 6, /* internal: workqueue is draining */ - WQ_RESCUER = 1 << 7, /* internal: workqueue has rescuer */ + WQ_DRAINING = 1 << 7, /* internal: workqueue is draining */ + WQ_RESCUER = 1 << 8, /* internal: workqueue has rescuer */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 2720884287c3..6fda9fa2ba98 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -385,7 +385,7 @@ 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 d786b4fc02a4..8cef1d197dd2 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -47,6 +47,7 @@ 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 000000000000..28646db2c775 --- /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 <linux/tracepoint.h> + +#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 : "<none>", 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 <trace/define_trace.h> diff --git a/include/trace/events/latency_hist.h b/include/trace/events/latency_hist.h new file mode 100644 index 000000000000..d6b5d77c57aa --- /dev/null +++ b/include/trace/events/latency_hist.h @@ -0,0 +1,30 @@ +#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 43298f9810fb..dbc82d01e66a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1239,6 +1239,7 @@ config SLAB config SLUB bool "SLUB (Unqueued Allocator)" + depends on !PREEMPT_RT_FULL help SLUB is a slab allocator that minimizes cache line usage instead of managing queues of cached objects (SLAB approach). @@ -1250,6 +1251,7 @@ 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 0bf677aa0872..6b473cd16509 100644 --- a/init/Makefile +++ b/init/Makefile @@ -29,4 +29,4 @@ 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 217ed23e9487..1c0a673ecc4f 100644 --- a/init/main.c +++ b/init/main.c @@ -68,6 +68,7 @@ #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/perf_event.h> +#include <linux/posix-timers.h> #include <asm/io.h> #include <asm/bugs.h> @@ -378,11 +379,8 @@ static noinline void __init_refok rest_init(void) * at least once to get things moving: */ init_idle_bootup_task(current); - preempt_enable_no_resched(); - schedule(); - + schedule_preempt_disabled(); /* Call into cpu_idle with preempt disabled */ - preempt_disable(); cpu_idle(); } @@ -492,6 +490,7 @@ asmlinkage void __init start_kernel(void) * Interrupts are still disabled. Do necessary setups, then * enable them */ + softirq_early_init(); tick_init(); boot_cpu_init(); page_address_init(); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 5b4293d9819d..eec1d993ae5f 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -820,12 +820,17 @@ 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() @@ -839,15 +844,19 @@ static inline void pipelined_receive(struct mqueue_inode_info *info) wake_up_interruptible(&info->wait_q); return; } + /* + * Keep them in one critical section for PREEMPT_RT: + */ + preempt_disable_rt(); 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, + SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, size_t, msg_len, unsigned int, msg_prio, const struct timespec __user *, u_abs_timeout) { diff --git a/ipc/msg.c b/ipc/msg.c index 7385de25788a..06642ac5bb8f 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -259,12 +259,20 @@ static void expunge_all(struct msg_queue *msq, int res) while (tmp != &msq->q_receivers) { struct msg_receiver *msr; + /* + * Make sure that the wakeup doesnt preempt + * this CPU prematurely. (on PREEMPT_RT) + */ + preempt_disable_rt(); + msr = list_entry(tmp, struct msg_receiver, r_list); tmp = tmp->next; msr->r_msg = NULL; wake_up_process(msr->r_tsk); smp_mb(); msr->r_msg = ERR_PTR(res); + + preempt_enable_rt(); } } @@ -611,6 +619,12 @@ 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; @@ -624,9 +638,11 @@ 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 5215a81420df..5eaf6846d8cd 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -461,6 +461,13 @@ 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 @@ -472,6 +479,7 @@ static void wake_up_sem_queue_prepare(struct list_head *pt, q->pid = error; list_add_tail(&q->simple_list, pt); +#endif } /** @@ -485,6 +493,7 @@ 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; @@ -497,6 +506,7 @@ 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) diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 5068e2a4e75f..7bd0598bfe6a 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -199,4 +199,4 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE config MUTEX_SPIN_ON_OWNER - def_bool SMP && !DEBUG_MUTEXES + def_bool SMP && !DEBUG_MUTEXES && !PREEMPT_RT_FULL diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 24e7cb0ba26a..d0e93725d891 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,3 +1,10 @@ +config PREEMPT + bool + select PREEMPT_COUNT + +config PREEMPT_RT_BASE + bool + select PREEMPT choice prompt "Preemption Model" @@ -33,9 +40,9 @@ 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 help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) @@ -51,6 +58,21 @@ 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 preemptiple + RT kernel. + +config PREEMPT_RT_FULL + bool "Fully Preemptible Kernel (RT)" + depends on IRQ_FORCED_THREADING + select PREEMPT_RT_BASE + help + All and everything + endchoice config PREEMPT_COUNT diff --git a/kernel/Makefile b/kernel/Makefile index e898c5b9d02c..c961d3abfe4c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -7,8 +7,8 @@ obj-y = sched.o 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 \ rcupdate.o extable.o params.o posix-timers.o \ - kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ - hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ + kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o \ + hrtimer.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o sched_clock.o cred.o \ async.o range.o obj-y += groups.o @@ -29,7 +29,11 @@ obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o obj-$(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-$(CONFIG_LOCKDEP) += lockdep_proc.o @@ -41,6 +45,7 @@ endif obj-$(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 563f13609470..66dfb74045bf 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -46,7 +46,12 @@ static int cpu_hotplug_disabled; static struct { struct task_struct *active_writer; +#ifdef CONFIG_PREEMPT_RT_FULL + /* Makes the lock keep the task's state */ + spinlock_t lock; +#else struct mutex lock; /* Synchronizes accesses to refcount, */ +#endif /* * Also blocks the new readers during * an ongoing cpu hotplug operation. @@ -54,18 +59,128 @@ static struct { int refcount; } cpu_hotplug = { .active_writer = NULL, +#ifdef CONFIG_PREEMPT_RT_FULL + .lock = __SPIN_LOCK_UNLOCKED(cpu_hotplug.lock), +#else .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), +#endif .refcount = 0, }; +#ifdef CONFIG_PREEMPT_RT_FULL +# define hotplug_lock() rt_spin_lock(&cpu_hotplug.lock) +# define hotplug_unlock() rt_spin_unlock(&cpu_hotplug.lock) +#else +# define hotplug_lock() mutex_lock(&cpu_hotplug.lock) +# define hotplug_unlock() mutex_unlock(&cpu_hotplug.lock) +#endif + +struct hotplug_pcp { + struct task_struct *unplug; + int refcount; + struct completion synced; +}; + +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; + +retry: + hp = &__get_cpu_var(hotplug_pcp); + + if (!hp->unplug || hp->refcount || preempt_count() > 1 || + hp->unplug == current || (current->flags & PF_STOMPER)) { + hp->refcount++; + return; + } + preempt_enable(); + hotplug_lock(); + hotplug_unlock(); + 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 && + !(current->flags & PF_STOMPER)) + wake_up_process(hp->unplug); +} + +/* + * FIXME: Is this really correct under all circumstances ? + */ +static int sync_unplug_thread(void *data) +{ + struct hotplug_pcp *hp = data; + + preempt_disable(); + hp->unplug = current; + set_current_state(TASK_UNINTERRUPTIBLE); + while (hp->refcount) { + schedule_preempt_disabled(); + set_current_state(TASK_UNINTERRUPTIBLE); + } + set_current_state(TASK_RUNNING); + preempt_enable(); + complete(&hp->synced); + return 0; +} + +/* + * 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); + struct task_struct *tsk; + + init_completion(&hp->synced); + tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); + if (IS_ERR(tsk)) + return (PTR_ERR(tsk)); + kthread_bind(tsk, cpu); + wake_up_process(tsk); + wait_for_completion(&hp->synced); + return 0; +} + +static void cpu_unplug_done(unsigned int cpu) +{ + struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); + + hp->unplug = NULL; +} + void get_online_cpus(void) { might_sleep(); if (cpu_hotplug.active_writer == current) return; - mutex_lock(&cpu_hotplug.lock); + hotplug_lock(); cpu_hotplug.refcount++; - mutex_unlock(&cpu_hotplug.lock); + hotplug_unlock(); } EXPORT_SYMBOL_GPL(get_online_cpus); @@ -74,10 +189,10 @@ void put_online_cpus(void) { if (cpu_hotplug.active_writer == current) return; - mutex_lock(&cpu_hotplug.lock); + hotplug_lock(); if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer)) wake_up_process(cpu_hotplug.active_writer); - mutex_unlock(&cpu_hotplug.lock); + hotplug_unlock(); } EXPORT_SYMBOL_GPL(put_online_cpus); @@ -109,11 +224,11 @@ static void cpu_hotplug_begin(void) cpu_hotplug.active_writer = current; for (;;) { - mutex_lock(&cpu_hotplug.lock); + hotplug_lock(); if (likely(!cpu_hotplug.refcount)) break; __set_current_state(TASK_UNINTERRUPTIBLE); - mutex_unlock(&cpu_hotplug.lock); + hotplug_unlock(); schedule(); } } @@ -121,7 +236,7 @@ static void cpu_hotplug_begin(void) static void cpu_hotplug_done(void) { cpu_hotplug.active_writer = NULL; - mutex_unlock(&cpu_hotplug.lock); + hotplug_unlock(); } #else /* #if CONFIG_HOTPLUG_CPU */ @@ -211,13 +326,14 @@ 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; if (num_online_cpus() == 1) return -EBUSY; @@ -225,7 +341,26 @@ 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; + 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(); + return -EBUSY; + } + 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) { @@ -264,6 +399,9 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) check_for_tasks(cpu); out_release: + cpu_unplug_done(cpu); +out_cancel: + migrate_enable(); cpu_hotplug_done(); if (!err) cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); diff --git a/kernel/cred.c b/kernel/cred.c index 5791612a4045..944761380c37 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -35,7 +35,7 @@ static struct kmem_cache *cred_jar; static struct thread_group_cred init_tgcred = { .usage = ATOMIC_INIT(2), .tgid = 0, - .lock = __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock), + .lock = __SPIN_LOCK_UNLOCKED(init_tgcred.lock), }; #endif diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 4802eb5840e1..5b7455fada1e 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -553,7 +553,6 @@ int vkdb_printf(const char *fmt, va_list ap) int diag; int linecount; int logging, saved_loglevel = 0; - int saved_trap_printk; int got_printf_lock = 0; int retlen = 0; int fnd, len; @@ -564,8 +563,6 @@ 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, @@ -821,7 +818,6 @@ kdb_print_out: } else { __release(kdb_printf_lock); } - kdb_trap_printk = saved_trap_printk; preempt_enable(); return retlen; } @@ -831,9 +827,11 @@ 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/exit.c b/kernel/exit.c index e6e01b959a0e..90757807b27b 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -141,7 +141,7 @@ 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 0acf42c0af50..e3db0cba5f60 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -87,7 +87,7 @@ 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) @@ -197,7 +197,18 @@ 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 /* * macro override instead of weak attribute alias, to workaround @@ -542,6 +553,19 @@ 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. */ @@ -1026,6 +1050,9 @@ 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 = cputime_zero; tsk->cputime_expires.virt_exp = cputime_zero; tsk->cputime_expires.sched_exp = 0; @@ -1134,6 +1161,7 @@ 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 = cputime_zero; p->stime = cputime_zero; @@ -1195,6 +1223,9 @@ 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; diff --git a/kernel/futex.c b/kernel/futex.c index 067702335762..97e3f0f16553 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1422,6 +1422,16 @@ 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; @@ -2266,7 +2276,7 @@ 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; @@ -2288,8 +2298,7 @@ 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)) @@ -2310,20 +2319,55 @@ 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) { @@ -2332,9 +2376,10 @@ 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 { /* @@ -2347,7 +2392,8 @@ 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 ae34bf51682b..3991464c3066 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -49,6 +49,7 @@ #include <asm/uaccess.h> #include <trace/events/timer.h> +#include <trace/events/hist.h> /* * The timer bases: @@ -588,8 +589,7 @@ 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; @@ -624,6 +624,9 @@ 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 */ @@ -644,14 +647,23 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, int wakeup) { if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) { - if (wakeup) { - raw_spin_unlock(&base->cpu_base->lock); - raise_softirq_irqoff(HRTIMER_SOFTIRQ); - raw_spin_lock(&base->cpu_base->lock); - } else - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + if (!wakeup) + return -ETIME; - return 1; +#ifdef CONFIG_PREEMPT_RT_BASE + /* + * Move softirq based timers away from the rbtree in + * case it expired already. Otherwise we would have a + * stale base->first entry until the softirq runs. + */ + if (!hrtimer_rt_defer(timer)) + return -ETIME; +#endif + raw_spin_unlock(&base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + raw_spin_lock(&base->cpu_base->lock); + + return 0; } return 0; @@ -732,6 +744,11 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, } 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 */ @@ -846,6 +863,32 @@ 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 * @@ -889,6 +932,11 @@ 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) { @@ -985,8 +1033,20 @@ 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, wakeup); + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) { + ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup); + if (ret) { + /* + * 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); + } + } unlock_hrtimer_base(timer, &flags); @@ -1072,7 +1132,7 @@ int hrtimer_cancel(struct hrtimer *timer) if (ret >= 0) return ret; - cpu_relax(); + hrtimer_wait_for_timer(timer); } } EXPORT_SYMBOL_GPL(hrtimer_cancel); @@ -1151,6 +1211,7 @@ 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 @@ -1234,6 +1295,122 @@ 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) { } +static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } + +#endif + #ifdef CONFIG_HIGH_RES_TIMERS /* @@ -1244,7 +1421,7 @@ 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++; @@ -1280,6 +1457,14 @@ retry: timer = container_of(node, struct hrtimer, node); + trace_hrtimer_interrupt(raw_smp_processor_id(), + ktime_to_ns(ktime_sub( + 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 @@ -1303,7 +1488,10 @@ retry: break; } - __run_hrtimer(timer, &basenow); + if (!hrtimer_rt_defer(timer)) + __run_hrtimer(timer, &basenow); + else + raise = 1; } } @@ -1318,6 +1506,10 @@ retry: if (expires_next.tv64 == KTIME_MAX || !tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; + + if (raise) + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + return; } @@ -1393,17 +1585,17 @@ void hrtimer_peek_ahead_timers(void) 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: * @@ -1436,7 +1628,7 @@ 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; @@ -1461,10 +1653,16 @@ 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); } /* @@ -1486,6 +1684,7 @@ 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); @@ -1624,9 +1823,13 @@ 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 @@ -1739,9 +1942,7 @@ 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 470d08c82bbe..634620c1b291 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -156,8 +156,11 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) action = action->next; } while (action); +#ifndef CONFIG_PREEMPT_RT_FULL + /* FIXME: Can we unbreak that ? */ if (random & IRQF_SAMPLE_RANDOM) add_interrupt_randomness(irq); +#endif if (!noirqdebug) note_interrupt(irq, desc, retval); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 76000927da3f..87dc0539cebb 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -18,6 +18,7 @@ #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) @@ -26,6 +27,7 @@ static int __init setup_forced_irqthreads(char *arg) return 0; } early_param("threadirqs", setup_forced_irqthreads); +# endif #endif /** @@ -740,7 +742,15 @@ 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, false); - 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; } @@ -1070,6 +1080,9 @@ __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 1162f1030f18..0d2c381c2bdb 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 dc813a948be2..d09e0f51d182 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -341,6 +341,11 @@ 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\n"); + return 1; +#endif irqfixup = 1; printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); printk(KERN_WARNING "This may impact system performance.\n"); @@ -353,6 +358,11 @@ 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\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 c3c46c72046e..727ba59e38f9 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -105,8 +105,10 @@ void irq_work_run(void) if (llist_empty(this_list)) return; +#ifndef CONFIG_PREEMPT_RT_FULL BUG_ON(!in_irq()); BUG_ON(!irqs_disabled()); +#endif llnode = llist_del_all(this_list); while (llnode != NULL) { diff --git a/kernel/itimer.c b/kernel/itimer.c index d802883153da..2c582fc41579 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -214,6 +214,7 @@ 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 4e316e1acf58..a546d3303a2c 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -133,6 +133,15 @@ 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) @@ -182,6 +191,9 @@ static struct attribute * kernel_attrs[] = { &kexec_crash_size_attr.attr, &vmcoreinfo_attr.attr, #endif +#ifdef CONFIG_PREEMPT_RT_FULL + &realtime_attr.attr, +#endif NULL }; diff --git a/kernel/lockdep.c b/kernel/lockdep.c index b2e08c932d91..334d3c037b34 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3494,6 +3494,7 @@ 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 @@ -3508,6 +3509,7 @@ 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/mutex.c b/kernel/mutex.c index 89096dd8786f..a307cc9c9526 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -240,9 +240,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, /* didn't get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); spin_lock_mutex(&lock->wait_lock, flags); } diff --git a/kernel/panic.c b/kernel/panic.c index 3458469eb7c3..50f4de50e779 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -343,9 +343,11 @@ 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 e7cb76dc18f5..1d4c6096395a 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -701,7 +701,7 @@ 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; @@ -1223,7 +1223,7 @@ 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); @@ -1290,10 +1290,11 @@ 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; @@ -1307,13 +1308,13 @@ 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 @@ -1371,6 +1372,190 @@ void run_posix_cpu_timers(struct task_struct *tsk) } } +#ifdef CONFIG_PREEMPT_RT_BASE +#include <linux/kthread.h> +#include <linux/cpu.h> +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), + any_online_cpu(cpu_online_map)); + 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 __devinitdata 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_cpu_mask(cpu, cpu_possible_map) + 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 69185ae6b701..6a74800a6f66 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -439,6 +439,7 @@ 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)) || @@ -447,7 +448,8 @@ 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); @@ -764,6 +766,20 @@ 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 @@ -841,6 +857,7 @@ 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; @@ -849,9 +866,12 @@ 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))) @@ -889,10 +909,15 @@ 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); @@ -918,8 +943,18 @@ 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 7c0d5786940b..32741e27501c 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -284,6 +284,8 @@ 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, " @@ -311,6 +313,7 @@ static int create_image(int platform_mode) syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -437,6 +440,7 @@ static int resume_target_kernel(bool platform_mode) goto Enable_cpus; local_irq_disable(); + system_state = SYSTEM_SUSPEND; error = syscore_suspend(); if (error) @@ -470,6 +474,7 @@ static int resume_target_kernel(bool platform_mode) syscore_resume(); Enable_irqs: + system_state = SYSTEM_RUNNING; local_irq_enable(); Enable_cpus: @@ -549,6 +554,7 @@ int hibernation_platform_enter(void) goto Platform_finish; local_irq_disable(); + system_state = SYSTEM_SUSPEND; syscore_suspend(); if (pm_wakeup_pending()) { error = -EAGAIN; @@ -561,6 +567,7 @@ 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 4953dc054c53..691f46e148f4 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -171,6 +171,8 @@ 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(); @@ -181,6 +183,8 @@ 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 7982a0a841ea..9eabbbbae463 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -21,6 +21,7 @@ #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/console.h> +#include <linux/sysrq.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/nmi.h> @@ -44,13 +45,6 @@ #include <asm/uaccess.h> -/* - * Architectures can override it: - */ -void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...) -{ -} - #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) /* printk's without a loglevel use this.. */ @@ -511,6 +505,7 @@ static void __call_console_drivers(unsigned start, unsigned end) { struct console *con; + migrate_disable(); for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; @@ -519,7 +514,61 @@ static void __call_console_drivers(unsigned start, unsigned end) (con->flags & CON_ANYTIME))) con->write(con, &LOG_BUF(start), end - start); } + migrate_enable(); +} + +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +static void early_vprintk(const char *fmt, va_list ap) +{ + char buf[512]; + int n = vscnprintf(buf, sizeof(buf), fmt, ap); + if (early_console) + 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 int __read_mostly printk_killswitch; + +static int __init force_early_printk_setup(char *str) +{ + printk_killswitch = 1; + return 0; +} +early_param("force_early_printk", force_early_printk_setup); + +void printk_kill(void) +{ + printk_killswitch = 1; +} + +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 static int __read_mostly ignore_loglevel; @@ -781,12 +830,18 @@ 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()) || sysrq_in_progress; +#else + int lock = 1; +#endif - if (console_trylock()) { + if (lock && console_trylock()) { retval = 1; /* @@ -837,10 +892,17 @@ asmlinkage int vprintk(const char *fmt, va_list args) size_t plen; char special; + /* + * 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(); printk_delay(); - preempt_disable(); + migrate_disable(); /* This stops the holder of console_sem just where we want him */ raw_local_irq_save(flags); this_cpu = smp_processor_id(); @@ -957,14 +1019,21 @@ asmlinkage int vprintk(const char *fmt, va_list args) * will release 'logbuf_lock' regardless of whether it * actually gets the 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: raw_local_irq_restore(flags); - preempt_enable(); + migrate_enable(); return printed_len; } EXPORT_SYMBOL(printk); @@ -1221,8 +1290,8 @@ void printk_tick(void) int printk_needs_cpu(int cpu) { - if (cpu_is_offline(cpu)) - printk_tick(); + if (unlikely(cpu_is_offline(cpu))) + __this_cpu_write(printk_pending, 0); return __this_cpu_read(printk_pending); } @@ -1268,11 +1337,16 @@ again: _con_start = con_start; _log_end = log_end; con_start = log_end; /* Flush */ +#ifndef CONFIG_PREEMPT_RT_FULL raw_spin_unlock(&logbuf_lock); stop_critical_timings(); /* don't trace print latency */ call_console_drivers(_con_start, _log_end); start_critical_timings(); local_irq_restore(flags); +#else + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + call_console_drivers(_con_start, _log_end); +#endif } console_locked = 0; diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index c5b98e565aee..24dcc713bd00 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -77,6 +77,7 @@ 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? * @@ -96,6 +97,7 @@ 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 636af6d9c6e5..6689097c45ec 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -243,6 +243,7 @@ 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. @@ -252,3 +253,4 @@ 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/rcutree.c b/kernel/rcutree.c index 6b76d812740c..8c26a499ff99 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -170,6 +170,14 @@ 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); @@ -180,6 +188,7 @@ 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, @@ -225,6 +234,7 @@ 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. */ @@ -242,6 +252,7 @@ void rcu_bh_force_quiescent_state(void) force_quiescent_state(&rcu_bh_state, 0); } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); +#endif /* * Record the number of times rcutorture tests have been initiated and @@ -1221,7 +1232,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) else raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) - rcu_report_exp_rnp(rsp, rnp); + rcu_report_exp_rnp(rsp, rnp, true); rcu_node_kthread_setaffinity(rnp, -1); } @@ -1667,6 +1678,7 @@ 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 for invocation after a quicker grace period. */ @@ -1675,6 +1687,7 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) __call_rcu(head, func, &rcu_bh_state); } EXPORT_SYMBOL_GPL(call_rcu_bh); +#endif /** * synchronize_sched - wait until an rcu-sched grace period has elapsed. @@ -1707,6 +1720,7 @@ 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. * @@ -1723,6 +1737,7 @@ void synchronize_rcu_bh(void) wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +#endif /* * Check to see if there is any immediate RCU-related work to be done @@ -1877,6 +1892,7 @@ static void _rcu_barrier(struct rcu_state *rsp, mutex_unlock(&rcu_barrier_mutex); } +#ifndef CONFIG_PREEMPT_RT_FULL /** * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. */ @@ -1885,6 +1901,7 @@ void rcu_barrier_bh(void) _rcu_barrier(&rcu_bh_state, call_rcu_bh); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); +#endif /** * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 849ce9ec51fe..dca495d81304 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -451,7 +451,8 @@ static void rcu_preempt_check_callbacks(int cpu); static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp); +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ static int rcu_preempt_pending(int cpu); static int rcu_preempt_needs_cpu(int cpu); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 4b9b9f8a4184..936441dc5cac 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -336,7 +336,7 @@ static noinline 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; } @@ -407,7 +407,7 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && !rcu_preempted_readers_exp(rnp)) - rcu_report_exp_rnp(&rcu_preempt_state, rnp); + rcu_report_exp_rnp(&rcu_preempt_state, rnp, true); } else { local_irq_restore(flags); } @@ -731,7 +731,8 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) * * Caller must hold sync_rcu_preempt_exp_mutex. */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake) { unsigned long flags; unsigned long mask; @@ -744,7 +745,8 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) } if (rnp->parent == NULL) { raw_spin_unlock_irqrestore(&rnp->lock, flags); - wake_up(&sync_rcu_preempt_exp_wq); + if (wake) + wake_up(&sync_rcu_preempt_exp_wq); break; } mask = rnp->grpmask; @@ -777,7 +779,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) must_wait = 1; } if (!must_wait) - rcu_report_exp_rnp(rsp, rnp); + rcu_report_exp_rnp(rsp, rnp, false); } /* @@ -1069,9 +1071,9 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); * report on tasks preempted in RCU read-side critical sections during * expedited RCU grace periods. */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake) { - return; } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -1931,7 +1933,7 @@ EXPORT_SYMBOL_GPL(synchronize_sched_expedited); #endif /* #else #ifndef CONFIG_SMP */ -#if !defined(CONFIG_RCU_FAST_NO_HZ) +#if 1 /* !defined(CONFIG_RCU_FAST_NO_HZ) */ /* * Check to see if any future RCU-related work will need to be done diff --git a/kernel/relay.c b/kernel/relay.c index b6f803aacc6d..eae992d90833 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -340,6 +340,10 @@ 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); } /** @@ -357,6 +361,7 @@ 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 34683efa2cce..21e9ec4a96cf 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -43,7 +43,7 @@ int res_counter_charge(struct res_counter *counter, unsigned long val, struct res_counter *c, *u; *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); ret = res_counter_charge_locked(c, val); @@ -62,7 +62,7 @@ undo: spin_unlock(&u->lock); } done: - local_irq_restore(flags); + local_irq_restore_nort(flags); return ret; } @@ -79,13 +79,13 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val) unsigned long flags; struct res_counter *c; - local_irq_save(flags); + local_irq_save_nort(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); res_counter_uncharge_locked(c, val); spin_unlock(&c->lock); } - local_irq_restore(flags); + local_irq_restore_nort(flags); } diff --git a/kernel/rt.c b/kernel/rt.c new file mode 100644 index 000000000000..092d6b356d59 --- /dev/null +++ b/kernel/rt.c @@ -0,0 +1,442 @@ +/* + * kernel/rt.c + * + * Real-Time Preemption Support + * + * started by Ingo Molnar: + * + * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> + * + * 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 <andrea@suse.de> + * - 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 <tglx@timesys.com> + * - 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 <rostedt@goodmis.org> + * - debugged and patched Thomas Gleixner's rework. + * - added back the cmpxchg to the rework. + * - turned atomic require back on for SMP. + */ + +#include <linux/spinlock.h> +#include <linux/rtmutex.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/syscalls.h> +#include <linux/interrupt.h> +#include <linux/plist.h> +#include <linux/fs.h> +#include <linux/futex.h> +#include <linux/hrtimer.h> + +#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); + else if (!rwlock->read_depth) + ret = 0; + + if (ret) { + rwlock->read_depth++; + rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); + } 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; + + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + + /* + * recursive read locks succeed when current owns the lock + */ + if (rt_mutex_owner(lock) != current) + __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) +{ + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + + /* Release the lock only when read_depth is down to 0 */ + if (--rwlock->read_depth == 0) + __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) +{ + rwsem_release(&rwsem->dep_map, 1, _RET_IP_); + if (--rwsem->read_depth == 0) + 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); + +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); + else if (!rwsem->read_depth) + ret = 0; + + if (ret) { + rwsem->read_depth++; + rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); + } + 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; + + rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_); + + if (rt_mutex_owner(lock) != current) + 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, 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 f9d8482dd487..b52515820c1f 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 <srostedt@redhat.com> + * * See Documentation/rt-mutex-design.txt for details. */ #include <linux/spinlock.h> @@ -67,6 +73,12 @@ 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 @@ -90,6 +102,12 @@ 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 * @@ -136,6 +154,14 @@ 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: */ @@ -196,7 +222,7 @@ 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; /* @@ -247,13 +273,15 @@ 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; } @@ -298,6 +326,25 @@ 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 * @@ -307,8 +354,9 @@ 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 @@ -341,12 +389,14 @@ 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; @@ -371,7 +421,6 @@ 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); @@ -381,6 +430,13 @@ 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. * @@ -399,6 +455,23 @@ 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; @@ -423,7 +496,7 @@ 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); } @@ -478,7 +551,7 @@ 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); } /* @@ -517,7 +590,7 @@ 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); @@ -551,23 +624,316 @@ 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 noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + raw_spin_lock(&lock->wait_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); +} + +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(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 * @@ -631,9 +997,10 @@ 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)) { @@ -686,6 +1053,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock) int ret = 0; raw_spin_lock(&lock->wait_lock); + init_lists(lock); if (likely(rt_mutex_owner(lock) != current)) { @@ -799,12 +1167,12 @@ 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, @@ -818,17 +1186,38 @@ 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) */ @@ -897,7 +1286,6 @@ 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); @@ -917,7 +1305,7 @@ 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); @@ -966,6 +1354,35 @@ 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 53a66c85261b..6ec3dc1eab10 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.c b/kernel/sched.c index d6b149ccf925..1cc706da3676 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -189,6 +189,7 @@ 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; } @@ -941,7 +942,11 @@ 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 @@ -1277,6 +1282,7 @@ 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) @@ -2444,7 +2450,8 @@ 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(); } @@ -2459,7 +2466,8 @@ 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); @@ -2564,7 +2572,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p) printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } - + /* + * Clear PF_THREAD_BOUND, otherwise we wreckage + * migrate_disable/enable. See optimization for + * PF_THREAD_BOUND tasks there. + */ + p->flags &= ~PF_THREAD_BOUND; return dest_cpu; } @@ -2644,10 +2657,6 @@ 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)); } /* @@ -2825,8 +2834,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) smp_wmb(); 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); @@ -2882,40 +2910,6 @@ 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); - - BUG_ON(rq != this_rq()); - BUG_ON(p == current); - 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. * @@ -2932,6 +2926,18 @@ 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); @@ -3206,8 +3212,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) finish_lock_switch(rq, prev); 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 @@ -4354,6 +4364,126 @@ 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->rt.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() || p->flags & PF_THREAD_BOUND) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + WARN_ON_ONCE(p->migrate_disable_atomic); +#endif + + preempt_disable(); + if (p->migrate_disable) { + p->migrate_disable++; + preempt_enable(); + return; + } + + pin_current_cpu(); + p->migrate_disable = 1; + preempt_enable(); +} +EXPORT_SYMBOL_GPL(migrate_disable); + +void migrate_enable(void) +{ + struct task_struct *p = current; + const struct cpumask *mask; + unsigned long flags; + struct rq *rq; + + if (in_atomic() || p->flags & PF_THREAD_BOUND) { +#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; +#endif + return; + } + +#ifdef CONFIG_SCHED_DEBUG + WARN_ON_ONCE(p->migrate_disable_atomic); +#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->rt.nr_cpus_allowed = cpumask_weight(mask); + raw_spin_unlock_irqrestore(&rq->lock, flags); + } else + p->migrate_disable = 0; + + unpin_current_cpu(); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(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) @@ -4413,6 +4543,8 @@ need_resched: 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))) { @@ -4420,19 +4552,6 @@ 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; } @@ -4466,15 +4585,23 @@ need_resched: post_schedule(rq); - preempt_enable_no_resched(); + __preempt_enable_no_resched(); if (need_resched()) goto need_resched; } static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state) + 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. @@ -4483,15 +4610,37 @@ 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_is_pi_blocked(tsk)) + return; + + 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); +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + __preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline bool owner_running(struct mutex *lock, struct task_struct *owner) @@ -4556,7 +4705,16 @@ asmlinkage void __sched notrace preempt_schedule(void) 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); /* @@ -4652,9 +4810,9 @@ EXPORT_SYMBOL(__wake_up); /* * Same as __wake_up but called with the spinlock in wait_queue_head_t held. */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) { - __wake_up_common(q, mode, 1, 0, NULL); + __wake_up_common(q, mode, nr, 0, NULL); } EXPORT_SYMBOL_GPL(__wake_up_locked); @@ -5013,6 +5171,24 @@ void rt_mutex_setprio(struct task_struct *p, int prio) rq = __task_rq_lock(p); + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; @@ -5036,11 +5212,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio) enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio); +out_unlock: __task_rq_unlock(rq); } - #endif - void set_user_nice(struct task_struct *p, long nice) { int old_prio, delta, on_rq; @@ -5720,7 +5895,7 @@ SYSCALL_DEFINE0(sched_yield) __release(rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); do_raw_spin_unlock(&rq->lock); - preempt_enable_no_resched(); + __preempt_enable_no_resched(); schedule(); @@ -5734,9 +5909,17 @@ 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) @@ -5777,6 +5960,7 @@ 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()); @@ -5790,6 +5974,7 @@ int __sched __cond_resched_softirq(void) return 0; } EXPORT_SYMBOL(__cond_resched_softirq); +#endif /** * yield - yield the current processor to other threads. @@ -6168,11 +6353,12 @@ static inline void sched_init_granularity(void) #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->rt.nr_cpus_allowed = cpumask_weight(new_mask); + } cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = cpumask_weight(new_mask); } /* @@ -6223,7 +6409,7 @@ 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); @@ -6312,6 +6498,8 @@ 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. @@ -6324,7 +6512,12 @@ 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; } /* @@ -6669,6 +6862,12 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) migrate_nr_uninterruptible(rq); calc_global_load_remove(rq); break; + case CPU_DEAD: + if (per_cpu(idle_last_mm, cpu)) { + mmdrop(per_cpu(idle_last_mm, cpu)); + per_cpu(idle_last_mm, cpu) = NULL; + } + break; #endif } @@ -8375,7 +8574,8 @@ 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); } diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index a6710a112b4f..528032b18655 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -235,6 +235,9 @@ 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 @@ -484,6 +487,10 @@ 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(rt.nr_cpus_allowed); #undef PN #undef __PN #undef P diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 8a39fa3e3c6c..3747e53ee6a5 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -2899,6 +2899,10 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, */ if (idle == CPU_NEWLY_IDLE) break; + + if (raw_spin_is_contended(&this_rq->lock) || + raw_spin_is_contended(&busiest->lock)) + break; #endif /* @@ -3039,6 +3043,20 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, rem_load_move -= moved_load; if (rem_load_move < 0) break; + +#ifdef CONFIG_PREEMPT + /* + * NEWIDLE balancing is a source of latency, so preemptible + * kernels will stop after the first task is pulled to minimize + * the critical section. + */ + if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) + break; + + if (raw_spin_is_contended(&this_rq->lock) || + raw_spin_is_contended(&busiest->lock)) + break; +#endif } rcu_read_unlock(); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 84802245abd2..0007001f995e 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -60,11 +60,15 @@ SCHED_FEAT(OWNER_SPIN, 1) */ SCHED_FEAT(NONTASK_POWER, 1) +#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, 1) +#else +SCHED_FEAT(TTWU_QUEUE, 0) +#endif SCHED_FEAT(FORCE_SD_OVERLAP, 0) SCHED_FEAT(RT_RUNTIME_SHARE, 1) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 78fcacf8715e..c108b9ce0799 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -580,12 +580,9 @@ static inline int balance_runtime(struct rt_rq *rt_rq) static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) { - int i, idle = 1; + int i, idle = 1, throttled = 0; const struct cpumask *span; - if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) - return 1; - span = sched_rt_period_mask(); for_each_cpu(i, span) { int enqueue = 0; @@ -620,12 +617,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (!rt_rq_throttled(rt_rq)) enqueue = 1; } + if (rt_rq->rt_throttled) + throttled = 1; if (enqueue) sched_rt_rq_enqueue(rt_rq); raw_spin_unlock(&rq->lock); } + if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)) + return 1; + return idle; } @@ -657,8 +659,24 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) return 0; if (rt_rq->rt_time > runtime) { - rt_rq->rt_throttled = 1; - printk_once(KERN_WARNING "sched: RT throttling activated\n"); + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + /* + * Don't actually throttle groups that have no runtime assigned + * but accrue some time due to boosting. + */ + if (likely(rt_b->rt_runtime)) { + rt_rq->rt_throttled = 1; + printk_once(KERN_WARNING "sched: RT throttling activated\n"); + } else { + /* + * In case we did anyway, make it go away, + * replenishment is a joke, since it will replenish us + * with exactly 0 ns. + */ + rt_rq->rt_time = 0; + } + if (rt_rq_throttled(rt_rq)) { sched_rt_rq_dequeue(rt_rq); return 1; @@ -686,7 +704,8 @@ static void update_curr_rt(struct rq *rq) if (unlikely((s64)delta_exec < 0)) delta_exec = 0; - schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); diff --git a/kernel/signal.c b/kernel/signal.c index 206551563cce..739c2e40d982 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -344,13 +344,45 @@ 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; @@ -367,7 +399,10 @@ __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); } @@ -384,6 +419,13 @@ __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) @@ -393,6 +435,21 @@ 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; @@ -406,6 +463,21 @@ 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) @@ -554,7 +626,7 @@ 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 @@ -600,6 +672,8 @@ 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 */ @@ -682,6 +756,9 @@ void signal_wake_up(struct task_struct *t, int resume) set_tsk_thread_flag(t, TIF_SIGPENDING); + if (unlikely(t == current)) + return; + /* * For SIGKILL, we want to wake it up in the stopped/traced/killable * case. We don't check t->state here because there is a race with it @@ -1196,8 +1273,8 @@ 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; @@ -1222,6 +1299,39 @@ 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. */ @@ -1252,12 +1362,12 @@ 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; } @@ -1268,7 +1378,7 @@ 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; @@ -1515,7 +1625,8 @@ 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; @@ -1857,15 +1968,7 @@ 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(); schedule(); } else { /* diff --git a/kernel/softirq.c b/kernel/softirq.c index 2c71d91efff0..ca00a687c52b 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -21,9 +21,11 @@ #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/rcupdate.h> +#include <linux/delay.h> #include <linux/ftrace.h> #include <linux/smp.h> #include <linux/tick.h> +#include <linux/locallock.h> #define CREATE_TRACE_POINTS #include <trace/events/irq.h> @@ -61,6 +63,67 @@ char *softirq_to_name[NR_SOFTIRQS] = { "TASKLET", "SCHED", "HRTIMER", "RCU" }; +#ifdef CONFIG_NO_HZ +# ifdef CONFIG_PREEMPT_RT_FULL +/* + * On preempt-rt a softirq 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; + u32 warnpending = 0, pending = local_softirq_pending(); + + if (rate_limit >= 10) + return; + + if (pending) { + struct task_struct *tsk; + + tsk = __get_cpu_var(ksoftirqd); + /* + * 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. + */ + raw_spin_lock(&tsk->pi_lock); + + if (!tsk->pi_blocked_on && !(tsk->state == TASK_RUNNING)) + warnpending = 1; + + raw_spin_unlock(&tsk->pi_lock); + } + + if (warnpending) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + pending); + 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) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + local_softirq_pending()); + rate_limit++; + } +} +# endif +#endif + /* * we cannot loop indefinitely here to avoid userspace starvation, * but we also don't want to introduce a worst case 1/HZ latency @@ -76,6 +139,36 @@ static void wakeup_softirqd(void) wake_up_process(tsk); } +static void handle_pending_softirqs(u32 pending, int cpu, int need_rcu_bh_qs) +{ + struct softirq_action *h = softirq_vec; + unsigned int prev_count = preempt_count(); + + local_irq_enable(); + for ( ; pending; h++, pending >>= 1) { + unsigned int vec_nr = h - softirq_vec; + + if (!(pending & 1)) + continue; + + 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, (unsigned int) preempt_count()); + preempt_count() = prev_count; + } + if (need_rcu_bh_qs) + rcu_bh_qs(cpu); + } + local_irq_disable(); +} + +#ifndef CONFIG_PREEMPT_RT_FULL /* * preempt_count and SOFTIRQ_OFFSET usage: * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving @@ -206,7 +299,6 @@ EXPORT_SYMBOL(local_bh_enable_ip); asmlinkage void __do_softirq(void) { - struct softirq_action *h; __u32 pending; int max_restart = MAX_SOFTIRQ_RESTART; int cpu; @@ -215,7 +307,7 @@ asmlinkage void __do_softirq(void) account_system_vtime(current); __local_bh_disable((unsigned long)__builtin_return_address(0), - SOFTIRQ_OFFSET); + SOFTIRQ_OFFSET); lockdep_softirq_enter(); cpu = smp_processor_id(); @@ -223,36 +315,7 @@ 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 && --max_restart) @@ -267,6 +330,26 @@ restart: __local_bh_enable(SOFTIRQ_OFFSET); } +/* + * Called with preemption disabled from run_ksoftirqd() + */ +static int ksoftirqd_do_softirq(int cpu) +{ + /* + * Preempt disable stops cpu going offline. + * If already offline, we'll be on wrong CPU: + * don't process. + */ + if (cpu_is_offline(cpu)) + return -1; + + local_irq_disable(); + if (local_softirq_pending()) + __do_softirq(); + local_irq_enable(); + return 0; +} + #ifndef __ARCH_HAS_DO_SOFTIRQ asmlinkage void do_softirq(void) @@ -289,6 +372,191 @@ asmlinkage void do_softirq(void) #endif +static inline void local_bh_disable_nort(void) { local_bh_disable(); } +static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } +static inline void ksoftirqd_set_sched_params(void) { } +static inline void ksoftirqd_clr_sched_params(void) { } + +#else /* !PREEMPT_RT_FULL */ + +/* + * On RT we serialize softirq execution with a cpu local lock + */ +static DEFINE_LOCAL_IRQ_LOCK(local_softirq_lock); +static DEFINE_PER_CPU(struct task_struct *, local_softirq_runner); + +static void __do_softirq_common(int need_rcu_bh_qs); + +void __do_softirq(void) +{ + __do_softirq_common(0); +} + +void __init softirq_early_init(void) +{ + local_irq_lock_init(local_softirq_lock); +} + +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; + + if ((current->softirq_nestcnt == 1) && + local_softirq_pending() && + local_trylock(local_softirq_lock)) { + + local_irq_disable(); + if (local_softirq_pending()) + __do_softirq(); + local_irq_enable(); + local_unlock(local_softirq_lock); + WARN_ON(current->softirq_nestcnt != 1); + } + 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); + +/* For tracing */ +int notrace __in_softirq(void) +{ + if (__get_cpu_var(local_softirq_lock).owner == current) + return __get_cpu_var(local_softirq_lock).nestcnt; + return 0; +} + +int in_serving_softirq(void) +{ + int res; + + preempt_disable(); + res = __get_cpu_var(local_softirq_runner) == current; + preempt_enable(); + return res; +} +EXPORT_SYMBOL(in_serving_softirq); + +/* + * Called with bh and local interrupts disabled. For full RT cpu must + * be pinned. + */ +static void __do_softirq_common(int need_rcu_bh_qs) +{ + u32 pending = local_softirq_pending(); + int cpu = smp_processor_id(); + + current->softirq_nestcnt++; + + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + + __get_cpu_var(local_softirq_runner) = current; + + lockdep_softirq_enter(); + + handle_pending_softirqs(pending, cpu, need_rcu_bh_qs); + + pending = local_softirq_pending(); + if (pending) + wakeup_softirqd(); + + lockdep_softirq_exit(); + __get_cpu_var(local_softirq_runner) = NULL; + + current->softirq_nestcnt--; +} + +static int __thread_do_softirq(int cpu) +{ + /* + * Prevent the current cpu from going offline. + * pin_current_cpu() can reenable preemption and block on the + * hotplug mutex. When it returns, the current cpu is + * pinned. It might be the wrong one, but the offline check + * below catches that. + */ + pin_current_cpu(); + /* + * If called from ksoftirqd (cpu >= 0) we need to check + * whether we are on the wrong cpu due to cpu offlining. If + * called via thread_do_softirq() no action required. + */ + if (cpu >= 0 && cpu_is_offline(cpu)) { + unpin_current_cpu(); + return -1; + } + preempt_enable(); + local_lock(local_softirq_lock); + local_irq_disable(); + /* + * We cannot switch stacks on RT as we want to be able to + * schedule! + */ + if (local_softirq_pending()) + __do_softirq_common(cpu >= 0); + local_unlock(local_softirq_lock); + unpin_current_cpu(); + preempt_disable(); + local_irq_enable(); + return 0; +} + +/* + * Called from netif_rx_ni(). Preemption enabled. + */ +void thread_do_softirq(void) +{ + if (!in_serving_softirq()) { + preempt_disable(); + __thread_do_softirq(-1); + preempt_enable(); + } +} + +static int ksoftirqd_do_softirq(int cpu) +{ + return __thread_do_softirq(cpu); +} + +static inline void local_bh_disable_nort(void) { } +static inline void _local_bh_enable_nort(void) { } + +static inline void ksoftirqd_set_sched_params(void) +{ + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); +} + +static inline void ksoftirqd_clr_sched_params(void) +{ + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); +} + +#endif /* PREEMPT_RT_FULL */ /* * Enter an interrupt context. */ @@ -302,9 +570,9 @@ 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(); @@ -313,6 +581,7 @@ void irq_enter(void) #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED static inline void invoke_softirq(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!force_irqthreads) __do_softirq(); else { @@ -321,10 +590,14 @@ static inline void invoke_softirq(void) wakeup_softirqd(); __local_bh_enable(SOFTIRQ_OFFSET); } +#else + wakeup_softirqd(); +#endif } #else static inline void invoke_softirq(void) { +#ifndef CONFIG_PREEMPT_RT_FULL if (!force_irqthreads) do_softirq(); else { @@ -333,6 +606,9 @@ static inline void invoke_softirq(void) wakeup_softirqd(); __local_bh_enable(SOFTIRQ_OFFSET); } +#else + wakeup_softirqd(); +#endif } #endif @@ -353,7 +629,7 @@ void irq_exit(void) if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) tick_nohz_stop_sched_tick(0); #endif - preempt_enable_no_resched(); + __preempt_enable_no_resched(); } /* @@ -402,15 +678,45 @@ 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); } @@ -421,10 +727,7 @@ 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); } @@ -432,50 +735,119 @@ 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; @@ -486,29 +858,7 @@ 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); } @@ -531,7 +881,7 @@ 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); @@ -737,31 +1087,40 @@ void __init softirq_init(void) open_softirq(HI_SOFTIRQ, tasklet_hi_action); } +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) +void tasklet_unlock_wait(struct tasklet_struct *t) +{ + 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 int run_ksoftirqd(void * __bind_cpu) { + ksoftirqd_set_sched_params(); + set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { preempt_disable(); - if (!local_softirq_pending()) { - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } + if (!local_softirq_pending()) + schedule_preempt_disabled(); __set_current_state(TASK_RUNNING); while (local_softirq_pending()) { - /* Preempt disable stops cpu going offline. - If already offline, we'll be on wrong CPU: - don't process */ - if (cpu_is_offline((long)__bind_cpu)) + if (ksoftirqd_do_softirq((long) __bind_cpu)) goto wait_to_die; - local_irq_disable(); - if (local_softirq_pending()) - __do_softirq(); - local_irq_enable(); - preempt_enable_no_resched(); + __preempt_enable_no_resched(); cond_resched(); preempt_disable(); rcu_note_context_switch((long)__bind_cpu); @@ -774,6 +1133,7 @@ static int run_ksoftirqd(void * __bind_cpu) wait_to_die: preempt_enable(); + ksoftirqd_clr_sched_params(); /* Wait for kthread_stop */ set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { @@ -850,9 +1210,8 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, int hotcpu = (unsigned long)hcpu; struct task_struct *p; - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: p = kthread_create_on_node(run_ksoftirqd, hcpu, cpu_to_node(hotcpu), @@ -865,19 +1224,16 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, per_cpu(ksoftirqd, hotcpu) = p; break; case CPU_ONLINE: - case CPU_ONLINE_FROZEN: wake_up_process(per_cpu(ksoftirqd, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: if (!per_cpu(ksoftirqd, hotcpu)) break; /* Unbind so it can run. Fall thru. */ kthread_bind(per_cpu(ksoftirqd, hotcpu), cpumask_any(cpu_online_mask)); - case CPU_DEAD: - case CPU_DEAD_FROZEN: { + case CPU_POST_DEAD: { static const struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; diff --git a/kernel/spinlock.c b/kernel/spinlock.c index 84c7d96918bf..47fd3cf03a8e 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 2f194e965715..561ba3a7b8cf 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 */ struct task_struct *thread; /* stopper thread */ @@ -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; + } } } @@ -67,7 +69,7 @@ static void cpu_stop_queue_work(struct cpu_stopper *stopper, { 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); @@ -75,7 +77,23 @@ static void cpu_stop_queue_work(struct cpu_stopper *stopper, } 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); } /** @@ -109,7 +127,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) cpu_stop_init_done(&done, 1); cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work); - wait_for_completion(&done.completion); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -135,6 +153,7 @@ 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, @@ -153,15 +172,14 @@ 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(); + mutex_lock(&stopper_lock); for_each_cpu(cpu, cpumask) cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &per_cpu(stop_cpus_work, cpu)); - preempt_enable(); + mutex_unlock(&stopper_lock); } static int __stop_cpus(const struct cpumask *cpumask, @@ -171,7 +189,7 @@ static int __stop_cpus(const struct cpumask *cpumask, cpu_stop_init_done(&done, cpumask_weight(cpumask)); queue_stop_cpus_work(cpumask, fn, arg, &done); - wait_for_completion(&done.completion); + wait_for_stop_done(&done); return done.executed ? done.ret : -ENOENT; } @@ -259,13 +277,13 @@ 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; @@ -275,6 +293,16 @@ repeat: __set_current_state(TASK_RUNNING); + /* + * 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(); @@ -289,7 +317,13 @@ 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(); } else schedule(); @@ -317,6 +351,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, if (IS_ERR(p)) return notifier_from_errno(PTR_ERR(p)); get_task_struct(p); + p->flags |= PF_STOMPER; kthread_bind(p, cpu); sched_set_stop_task(cpu, p); stopper->thread = p; @@ -326,9 +361,9 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, /* strictly unnecessary, as first user will wake it */ wake_up_process(stopper->thread); /* mark enabled */ - 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); break; #ifdef CONFIG_HOTPLUG_CPU @@ -341,11 +376,11 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, /* kill the stopper */ kthread_stop(stopper->thread); /* drain remaining works */ - spin_lock_irq(&stopper->lock); + raw_spin_lock_irq(&stopper->lock); list_for_each_entry(work, &stopper->works, list) cpu_stop_signal_done(work->done, false); stopper->enabled = false; - spin_unlock_irq(&stopper->lock); + raw_spin_unlock_irq(&stopper->lock); /* release the stopper */ put_task_struct(stopper->thread); stopper->thread = NULL; @@ -376,7 +411,7 @@ 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); } @@ -570,7 +605,7 @@ int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, 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.c b/kernel/time.c index 73e416db0a1e..ba744cf80696 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -163,7 +163,6 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz) return error; if (tz) { - /* SMP safe, global irq locking makes it work. */ sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { @@ -173,12 +172,7 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz) } } if (tv) - { - /* SMP safe, again the code in arch/foo/time.c should - * globally block out interrupts when it runs. - */ return do_settimeofday(tv); - } return 0; } diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a470154e0408..21940eb049a1 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -74,9 +74,9 @@ u64 get_jiffies_64(void) u64 ret; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); ret = jiffies_64; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); return ret; } EXPORT_SYMBOL(get_jiffies_64); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 4b85a7a72526..419cbaa2f5c0 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -358,7 +358,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) { enum hrtimer_restart res = HRTIMER_NORESTART; - write_seqlock(&xtime_lock); + raw_spin_lock(&xtime_lock); + write_seqcount_begin(&xtime_seq); switch (time_state) { case TIME_OK: @@ -388,7 +389,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) break; } - write_sequnlock(&xtime_lock); + write_seqcount_end(&xtime_seq); + raw_spin_unlock(&xtime_lock); return res; } @@ -663,7 +665,8 @@ int do_adjtimex(struct timex *txc) getnstimeofday(&ts); - write_seqlock_irq(&xtime_lock); + raw_spin_lock_irq(&xtime_lock); + write_seqcount_begin(&xtime_seq); if (txc->modes & ADJ_ADJTIME) { long save_adjust = time_adjust; @@ -705,7 +708,8 @@ int do_adjtimex(struct timex *txc) /* fill PPS status fields */ pps_fill_timex(txc); - write_sequnlock_irq(&xtime_lock); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irq(&xtime_lock); txc->time.tv_sec = ts.tv_sec; txc->time.tv_usec = ts.tv_nsec; @@ -903,7 +907,8 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) pts_norm = pps_normalize_ts(*phase_ts); - write_seqlock_irqsave(&xtime_lock, flags); + raw_spin_lock_irqsave(&xtime_lock, flags); + write_seqcount_begin(&xtime_seq); /* clear the error bits, they will be set again if needed */ time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); @@ -916,7 +921,8 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) * just start the frequency interval */ if (unlikely(pps_fbase.tv_sec == 0)) { pps_fbase = *raw_ts; - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); return; } @@ -931,7 +937,8 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) time_status |= STA_PPSJITTER; /* restart the frequency calibration interval */ pps_fbase = *raw_ts; - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); pr_err("hardpps: PPSJITTER: bad pulse\n"); return; } @@ -948,7 +955,8 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) hardpps_update_phase(pts_norm.nsec); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); } EXPORT_SYMBOL(hardpps); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index da6c9ecad4e4..39de540fd7a7 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -63,13 +63,15 @@ int tick_is_oneshot_available(void) static void tick_periodic(int cpu) { if (tick_do_timer_cpu == cpu) { - write_seqlock(&xtime_lock); + raw_spin_lock(&xtime_lock); + write_seqcount_begin(&xtime_seq); /* Keep track of the next tick event */ tick_next_period = ktime_add(tick_next_period, tick_period); do_timer(1); - write_sequnlock(&xtime_lock); + write_seqcount_end(&xtime_seq); + raw_spin_unlock(&xtime_lock); } update_process_times(user_mode(get_irq_regs())); @@ -130,9 +132,9 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) ktime_t next; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); next = tick_next_period; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_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 4e265b901fed..c91100d99fb9 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -141,4 +141,5 @@ static inline int tick_device_is_functional(struct clock_event_device *dev) #endif extern void do_timer(unsigned long ticks); -extern seqlock_t xtime_lock; +extern raw_spinlock_t xtime_lock; +extern seqcount_t xtime_seq; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 40420644d0ba..b4d2351dc5b4 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -56,7 +56,8 @@ static void tick_do_update_jiffies64(ktime_t now) return; /* Reevalute with xtime_lock held */ - write_seqlock(&xtime_lock); + raw_spin_lock(&xtime_lock); + write_seqcount_begin(&xtime_seq); delta = ktime_sub(now, last_jiffies_update); if (delta.tv64 >= tick_period.tv64) { @@ -79,7 +80,8 @@ 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(&xtime_lock); + write_seqcount_end(&xtime_seq); + raw_spin_unlock(&xtime_lock); } /* @@ -89,12 +91,14 @@ static ktime_t tick_init_jiffy_update(void) { ktime_t period; - write_seqlock(&xtime_lock); + raw_spin_lock(&xtime_lock); + write_seqcount_begin(&xtime_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(&xtime_lock); + write_seqcount_end(&xtime_seq); + raw_spin_unlock(&xtime_lock); return period; } @@ -332,24 +336,18 @@ void tick_nohz_stop_sched_tick(int inidle) goto end; if (unlikely(local_softirq_pending() && cpu_online(cpu))) { - static int ratelimit; - - if (ratelimit < 10) { - printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", - (unsigned int) local_softirq_pending()); - ratelimit++; - } + softirq_check_pending_idle(); goto end; } ts->idle_calls++; /* Read jiffies and the time when jiffies were updated last */ do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); last_update = last_jiffies_update; last_jiffies = jiffies; time_delta = timekeeping_max_deferment(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) || arch_needs_cpu(cpu)) { @@ -798,6 +796,7 @@ 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 237841378c03..da9e1f9fa8f8 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -139,8 +139,8 @@ static inline s64 timekeeping_get_ns_raw(void) * This read-write spinlock protects us from races in SMP while * playing with xtime. */ -__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); - +__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(xtime_lock); +seqcount_t xtime_seq; /* * The current time @@ -222,7 +222,7 @@ void getnstimeofday(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); *ts = xtime; nsecs = timekeeping_get_ns(); @@ -230,7 +230,7 @@ void getnstimeofday(struct timespec *ts) /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); timespec_add_ns(ts, nsecs); } @@ -245,14 +245,14 @@ ktime_t ktime_get(void) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); secs = xtime.tv_sec + wall_to_monotonic.tv_sec; nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec; nsecs += timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); /* * Use ktime_set/ktime_add_ns to create a proper ktime on * 32-bit architectures without CONFIG_KTIME_SCALAR. @@ -278,14 +278,14 @@ void ktime_get_ts(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); *ts = xtime; tomono = wall_to_monotonic; nsecs = timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, ts->tv_nsec + tomono.tv_nsec + nsecs); @@ -313,7 +313,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) do { u32 arch_offset; - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); *ts_raw = raw_time; *ts_real = xtime; @@ -326,7 +326,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) nsecs_raw += arch_offset; nsecs_real += arch_offset; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); timespec_add_ns(ts_raw, nsecs_raw); timespec_add_ns(ts_real, nsecs_real); @@ -365,7 +365,8 @@ int do_settimeofday(const struct timespec *tv) if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&xtime_lock, flags); + raw_spin_lock_irqsave(&xtime_lock, flags); + write_seqcount_begin(&xtime_seq); timekeeping_forward_now(); @@ -381,7 +382,8 @@ int do_settimeofday(const struct timespec *tv) update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, timekeeper.mult); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -405,7 +407,8 @@ int timekeeping_inject_offset(struct timespec *ts) if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&xtime_lock, flags); + raw_spin_lock_irqsave(&xtime_lock, flags); + write_seqcount_begin(&xtime_seq); timekeeping_forward_now(); @@ -418,7 +421,8 @@ int timekeeping_inject_offset(struct timespec *ts) update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, timekeeper.mult); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -490,11 +494,11 @@ void getrawmonotonic(struct timespec *ts) s64 nsecs; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); nsecs = timekeeping_get_ns_raw(); *ts = raw_time; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); timespec_add_ns(ts, nsecs); } @@ -510,11 +514,11 @@ int timekeeping_valid_for_hres(void) int ret; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); return ret; } @@ -572,7 +576,8 @@ void __init timekeeping_init(void) read_persistent_clock(&now); read_boot_clock(&boot); - write_seqlock_irqsave(&xtime_lock, flags); + raw_spin_lock_irqsave(&xtime_lock, flags); + write_seqcount_begin(&xtime_seq); ntp_init(); @@ -593,7 +598,8 @@ void __init timekeeping_init(void) -boot.tv_sec, -boot.tv_nsec); total_sleep_time.tv_sec = 0; total_sleep_time.tv_nsec = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); } /* time in seconds when suspend began */ @@ -640,7 +646,8 @@ void timekeeping_inject_sleeptime(struct timespec *delta) if (!(ts.tv_sec == 0 && ts.tv_nsec == 0)) return; - write_seqlock_irqsave(&xtime_lock, flags); + raw_spin_lock_irqsave(&xtime_lock, flags); + write_seqcount_begin(&xtime_seq); timekeeping_forward_now(); __timekeeping_inject_sleeptime(delta); @@ -650,7 +657,8 @@ void timekeeping_inject_sleeptime(struct timespec *delta) update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, timekeeper.mult); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -673,7 +681,8 @@ static void timekeeping_resume(void) clocksource_resume(); - write_seqlock_irqsave(&xtime_lock, flags); + raw_spin_lock_irqsave(&xtime_lock, flags); + write_seqcount_begin(&xtime_seq); if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { ts = timespec_sub(ts, timekeeping_suspend_time); @@ -683,7 +692,8 @@ static void timekeeping_resume(void) timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; timekeeping_suspended = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); touch_softlockup_watchdog(); @@ -701,7 +711,8 @@ static int timekeeping_suspend(void) read_persistent_clock(&timekeeping_suspend_time); - write_seqlock_irqsave(&xtime_lock, flags); + raw_spin_lock_irqsave(&xtime_lock, flags); + write_seqcount_begin(&xtime_seq); timekeeping_forward_now(); timekeeping_suspended = 1; @@ -724,7 +735,8 @@ static int timekeeping_suspend(void) timekeeping_suspend_time = timespec_add(timekeeping_suspend_time, delta_delta); } - write_sequnlock_irqrestore(&xtime_lock, flags); + write_seqcount_end(&xtime_seq); + raw_spin_unlock_irqrestore(&xtime_lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); clocksource_suspend(); @@ -1101,13 +1113,13 @@ void get_monotonic_boottime(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); *ts = xtime; tomono = wall_to_monotonic; sleep = total_sleep_time; nsecs = timekeeping_get_ns(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec, ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs); @@ -1158,10 +1170,10 @@ struct timespec current_kernel_time(void) unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); now = xtime; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); return now; } @@ -1173,11 +1185,11 @@ struct timespec get_monotonic_coarse(void) unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); now = xtime; mono = wall_to_monotonic; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); @@ -1209,11 +1221,11 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); *xtim = xtime; *wtom = wall_to_monotonic; *sleep = total_sleep_time; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); } /** @@ -1225,9 +1237,9 @@ ktime_t ktime_get_monotonic_offset(void) struct timespec wtom; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqcount_begin(&xtime_seq); wtom = wall_to_monotonic; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqcount_retry(&xtime_seq, seq)); return timespec_to_ktime(wtom); } @@ -1239,7 +1251,9 @@ ktime_t ktime_get_monotonic_offset(void) */ void xtime_update(unsigned long ticks) { - write_seqlock(&xtime_lock); + raw_spin_lock(&xtime_lock); + write_seqcount_begin(&xtime_seq); do_timer(ticks); - write_sequnlock(&xtime_lock); + write_seqcount_end(&xtime_seq); + raw_spin_unlock(&xtime_lock); } diff --git a/kernel/timer.c b/kernel/timer.c index 9c3c62b0c4bc..c8c88d115aa7 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -75,6 +75,7 @@ struct tvec_root { struct tvec_base { spinlock_t lock; struct timer_list *running_timer; + wait_queue_head_t wait_for_running_timer; unsigned long timer_jiffies; unsigned long next_timer; struct tvec_root tv1; @@ -653,6 +654,36 @@ 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) @@ -679,12 +710,15 @@ __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) && 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) { @@ -695,14 +729,8 @@ __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; @@ -885,6 +913,29 @@ 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_tunning_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 @@ -953,7 +1004,7 @@ out: } 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 @@ -1013,7 +1064,7 @@ 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); @@ -1124,10 +1175,11 @@ static inline void __run_timers(struct tvec_base *base) spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); + base->running_timer = NULL; spin_lock_irq(&base->lock); } } - base->running_timer = NULL; + wake_up(&base->wait_for_running_timer); spin_unlock_irq(&base->lock); } @@ -1266,6 +1318,23 @@ unsigned long get_next_timer_interrupt(unsigned long now) */ if (cpu_is_offline(smp_processor_id())) return now + NEXT_TIMER_MAX_DELTA; + +#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)) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); + expires = base->next_timer; + rt_spin_unlock(&base->lock); + } else { + expires = now + 1; + } +#else spin_lock(&base->lock); if (time_before_eq(base->next_timer, base->timer_jiffies)) base->next_timer = __next_timer_interrupt(base); @@ -1274,7 +1343,7 @@ unsigned long get_next_timer_interrupt(unsigned long now) if (time_before_eq(expires, now)) return now; - +#endif return cmp_next_hrtimer_event(now, expires); } #endif @@ -1290,14 +1359,13 @@ 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); - printk_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); } @@ -1308,6 +1376,11 @@ 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 + + printk_tick(); hrtimer_run_pending(); if (time_after_eq(jiffies, base->timer_jiffies)) @@ -1634,6 +1707,7 @@ static int __cpuinit init_timers_cpu(int cpu) } spin_lock_init(&base->lock); + init_waitqueue_head(&base->wait_for_running_timer); for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); @@ -1673,7 +1747,7 @@ 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. @@ -1694,7 +1768,7 @@ 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 cd3134510f3d..2685322ab69b 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 @@ -214,6 +232,24 @@ 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 @@ -223,6 +259,74 @@ 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 5f39a07fe5ea..108a387e1459 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -36,6 +36,10 @@ 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 000000000000..9d49fcb8962f --- /dev/null +++ b/kernel/trace/latency_hist.c @@ -0,0 +1,1170 @@ +/* + * 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 <yyang@ch.mvista.com> + * + * Converted to work with the new latency tracer. + * Copyright (C) 2008 Red Hat, Inc. + * Steven Rostedt <srostedt@redhat.com> + * + */ +#include <linux/module.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/percpu.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <asm/atomic.h> +#include <asm/div64.h> + +#include "trace.h" +#include <trace/events/sched.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/hist.h> + +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 */ + unsigned long min_lat; + unsigned long max_lat; + unsigned long long below_hist_bound_samples; + unsigned long long above_hist_bound_samples; + unsigned 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, unsigned long latency, + unsigned 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 == ULONG_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)) { + unsigned long avg = (unsigned long) + div64_u64(my_hist->accumulate_lat, + my_hist->total_samples); + snprintf(minstr, sizeof(minstr), "%ld", + (long) my_hist->min_lat - my_hist->offset); + snprintf(avgstr, sizeof(avgstr), "%ld", + (long) avg - my_hist->offset); + snprintf(maxstr, sizeof(maxstr), "%ld", + (long) my_hist->max_lat - my_hist->offset); + } else { + strcpy(minstr, "<undef>"); + 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 = ULONG_MAX; + hist->max_lat = 0UL; + hist->total_samples = 0ULL; + hist->accumulate_lat = 0ULL; + + 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 && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + + 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 && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + + 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 && stop >= start) { + unsigned long latency = + nsecs_to_usecs(stop - start); + 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); + unsigned 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; + } + + /* + * 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 = nsecs_to_usecs(stop - next->preempt_timestamp_hist); + + 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)))) { + unsigned 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 = (unsigned long) div_s64(-latency_ns, 1000); + 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 = 0xFFFFFFFFUL; + } + 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 = 0xFFFFFFFFUL; + } + 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 = 0xFFFFFFFFUL; + } + 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 = 0xFFFFFFFFUL; + + 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 = 0xFFFFFFFFUL; + + 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 = 0xFFFFFFFFUL; + + 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 = 0xFFFFFFFFUL; + + 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/ring_buffer.c b/kernel/trace/ring_buffer.c index f5b7b5c1195b..c060f04adec6 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -478,7 +478,7 @@ struct ring_buffer_per_cpu { int cpu; atomic_t record_disabled; struct ring_buffer *buffer; - raw_spinlock_t reader_lock; /* serialize readers */ + spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; struct list_head *pages; @@ -1049,6 +1049,44 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, return -ENOMEM; } +static inline int ok_to_lock(void) +{ + if (in_nmi()) + return 0; +#ifdef CONFIG_PREEMPT_RT_FULL + if (in_atomic() || irqs_disabled()) + return 0; +#endif + return 1; +} + +static int +read_buffer_lock(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long *flags) +{ + /* + * If an NMI die dumps out the content of the ring buffer + * do not grab locks. We also permanently disable the ring + * buffer too. A one time deal is all you get from reading + * the ring buffer from an NMI. + */ + if (!ok_to_lock()) { + if (spin_trylock_irqsave(&cpu_buffer->reader_lock, *flags)) + return 1; + tracing_off_permanent(); + return 0; + } + spin_lock_irqsave(&cpu_buffer->reader_lock, *flags); + return 1; +} + +static void +read_buffer_unlock(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long flags, int locked) +{ + if (locked) + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); +} static struct ring_buffer_per_cpu * rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) { @@ -1064,7 +1102,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) cpu_buffer->cpu = cpu; cpu_buffer->buffer = buffer; - raw_spin_lock_init(&cpu_buffer->reader_lock); + spin_lock_init(&cpu_buffer->reader_lock); lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key); cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; @@ -1259,9 +1297,11 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) { struct buffer_page *bpage; struct list_head *p; + unsigned long flags; unsigned i; + int locked; - raw_spin_lock_irq(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); rb_head_page_deactivate(cpu_buffer); for (i = 0; i < nr_pages; i++) { @@ -1279,7 +1319,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) rb_check_pages(cpu_buffer); out: - raw_spin_unlock_irq(&cpu_buffer->reader_lock); + read_buffer_unlock(cpu_buffer, flags, locked); } static void @@ -1288,9 +1328,11 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, { struct buffer_page *bpage; struct list_head *p; + unsigned long flags; unsigned i; + int locked; - raw_spin_lock_irq(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); rb_head_page_deactivate(cpu_buffer); for (i = 0; i < nr_pages; i++) { @@ -1305,7 +1347,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, rb_check_pages(cpu_buffer); out: - raw_spin_unlock_irq(&cpu_buffer->reader_lock); + read_buffer_unlock(cpu_buffer, flags, locked); } /** @@ -2689,7 +2731,7 @@ unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) return 0; cpu_buffer = buffer->buffers[cpu]; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); /* * if the tail is on reader_page, oldest time stamp is on the reader * page @@ -2699,7 +2741,7 @@ unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) else bpage = rb_set_head_page(cpu_buffer); ret = bpage->page->time_stamp; - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); return ret; } @@ -2863,15 +2905,16 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; + int locked; if (!iter) return; cpu_buffer = iter->cpu_buffer; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); rb_iter_reset(iter); - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); } EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); @@ -3289,21 +3332,6 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } EXPORT_SYMBOL_GPL(ring_buffer_iter_peek); -static inline int rb_ok_to_lock(void) -{ - /* - * If an NMI die dumps out the content of the ring buffer - * do not grab locks. We also permanently disable the ring - * buffer too. A one time deal is all you get from reading - * the ring buffer from an NMI. - */ - if (likely(!in_nmi())) - return 1; - - tracing_off_permanent(); - return 0; -} - /** * ring_buffer_peek - peek at the next event to be read * @buffer: The ring buffer to read @@ -3321,22 +3349,17 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts, struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; unsigned long flags; - int dolock; + int locked; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; - dolock = rb_ok_to_lock(); again: - local_irq_save(flags); - if (dolock) - raw_spin_lock(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); event = rb_buffer_peek(cpu_buffer, ts, lost_events); if (event && event->type_len == RINGBUF_TYPE_PADDING) rb_advance_reader(cpu_buffer); - if (dolock) - raw_spin_unlock(&cpu_buffer->reader_lock); - local_irq_restore(flags); + read_buffer_unlock(cpu_buffer, flags, locked); if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; @@ -3358,11 +3381,12 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; struct ring_buffer_event *event; unsigned long flags; + int locked; again: - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); event = rb_iter_peek(iter, ts); - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); if (event && event->type_len == RINGBUF_TYPE_PADDING) goto again; @@ -3388,9 +3412,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event = NULL; unsigned long flags; - int dolock; - - dolock = rb_ok_to_lock(); + int locked; again: /* might be called in atomic */ @@ -3400,9 +3422,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, goto out; cpu_buffer = buffer->buffers[cpu]; - local_irq_save(flags); - if (dolock) - raw_spin_lock(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); event = rb_buffer_peek(cpu_buffer, ts, lost_events); if (event) { @@ -3410,9 +3430,8 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, rb_advance_reader(cpu_buffer); } - if (dolock) - raw_spin_unlock(&cpu_buffer->reader_lock); - local_irq_restore(flags); + read_buffer_unlock(cpu_buffer, flags, locked); + out: preempt_enable(); @@ -3497,17 +3516,18 @@ ring_buffer_read_start(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; + int locked; if (!iter) return; cpu_buffer = iter->cpu_buffer; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); arch_spin_lock(&cpu_buffer->lock); rb_iter_reset(iter); arch_spin_unlock(&cpu_buffer->lock); - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); } EXPORT_SYMBOL_GPL(ring_buffer_read_start); @@ -3541,8 +3561,9 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_event *event; struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; + int locked; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); again: event = rb_iter_peek(iter, ts); if (!event) @@ -3553,7 +3574,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) rb_advance_iter(iter); out: - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); return event; } @@ -3618,13 +3639,14 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; unsigned long flags; + int locked; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; atomic_inc(&cpu_buffer->record_disabled); - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing))) goto out; @@ -3636,7 +3658,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) arch_spin_unlock(&cpu_buffer->lock); out: - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); atomic_dec(&cpu_buffer->record_disabled); } @@ -3663,22 +3685,16 @@ int ring_buffer_empty(struct ring_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; - int dolock; + int locked; int cpu; int ret; - dolock = rb_ok_to_lock(); - /* yes this is racy, but if you don't like the race, lock the buffer */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - local_irq_save(flags); - if (dolock) - raw_spin_lock(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); ret = rb_per_cpu_empty(cpu_buffer); - if (dolock) - raw_spin_unlock(&cpu_buffer->reader_lock); - local_irq_restore(flags); + read_buffer_unlock(cpu_buffer, flags, locked); if (!ret) return 0; @@ -3697,22 +3713,16 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; - int dolock; + int locked; int ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 1; - dolock = rb_ok_to_lock(); - cpu_buffer = buffer->buffers[cpu]; - local_irq_save(flags); - if (dolock) - raw_spin_lock(&cpu_buffer->reader_lock); + locked = read_buffer_lock(cpu_buffer, &flags); ret = rb_per_cpu_empty(cpu_buffer); - if (dolock) - raw_spin_unlock(&cpu_buffer->reader_lock); - local_irq_restore(flags); + read_buffer_unlock(cpu_buffer, flags, locked); return ret; } @@ -3887,6 +3897,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, unsigned int commit; unsigned int read; u64 save_timestamp; + int locked; int ret = -1; if (!cpumask_test_cpu(cpu, buffer->cpumask)) @@ -3908,7 +3919,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, if (!bpage) goto out; - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + locked = read_buffer_lock(cpu_buffer, &flags); reader = rb_get_reader_page(cpu_buffer); if (!reader) @@ -4032,7 +4043,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer, memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit); out_unlock: - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + read_buffer_unlock(cpu_buffer, flags, locked); out: return ret; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f2bd275bb60f..9b2e20893033 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -359,11 +359,13 @@ static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); */ void trace_wake_up(void) { +#ifndef CONFIG_PREEMPT_RT_FULL const unsigned long delay = msecs_to_jiffies(2); if (trace_flags & TRACE_ITER_BLOCK) return; schedule_delayed_work(&wakeup_work, delay); +#endif } static int __init set_buf_size(char *str) @@ -719,6 +721,12 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) } #endif /* CONFIG_TRACER_MAX_TRACE */ +#ifndef CONFIG_PREEMPT_RT_FULL +static void default_wait_pipe(struct trace_iterator *iter); +#else +#define default_wait_pipe poll_wait_pipe +#endif + /** * register_tracer - register a tracer with the ftrace system. * @type - the plugin for the tracer @@ -1123,6 +1131,8 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; } EXPORT_SYMBOL_GPL(tracing_generic_entry_update); @@ -1850,9 +1860,10 @@ static void print_lat_help_header(struct seq_file *m) 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, "# |||| / _--=> migrate-disable\n"); + seq_puts(m, "# ||||| / delay \n"); + seq_puts(m, "# cmd pid |||||| time | caller \n"); + seq_puts(m, "# \\ / ||||| \\ | / \n"); } static void print_func_help_header(struct seq_file *m) @@ -3189,6 +3200,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) return 0; } +#ifndef CONFIG_PREEMPT_RT_FULL static unsigned int tracing_poll_pipe(struct file *filp, poll_table *poll_table) { @@ -3210,8 +3222,7 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table) } } - -void default_wait_pipe(struct trace_iterator *iter) +static void default_wait_pipe(struct trace_iterator *iter) { DEFINE_WAIT(wait); @@ -3222,6 +3233,20 @@ void default_wait_pipe(struct trace_iterator *iter) finish_wait(&trace_wait, &wait); } +#else +static unsigned int +tracing_poll_pipe(struct file *filp, poll_table *poll_table) +{ + struct trace_iterator *iter = filp->private_data; + + if ((trace_flags & TRACE_ITER_BLOCK) || !trace_empty(iter)) + return POLLIN | POLLRDNORM; + poll_wait_pipe(iter); + if (!trace_empty(iter)) + return POLLIN | POLLRDNORM; + return 0; +} +#endif /* * This is a make-shift waitqueue. diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 092e1f8d18dc..69b87009854c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -345,7 +345,6 @@ void trace_init_global_iter(struct trace_iterator *iter); void tracing_iter_reset(struct trace_iterator *iter, int cpu); -void default_wait_pipe(struct trace_iterator *iter); void poll_wait_pipe(struct trace_iterator *iter); void ftrace(struct trace_array *tr, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c212a7f934ec..69cc90808ed5 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -116,7 +116,8 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); - __common_field(int, padding); + __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 20dad0d7a163..1e6c33ea78b4 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -17,6 +17,7 @@ #include <linux/fs.h> #include "trace.h" +#include <trace/events/hist.h> static struct trace_array *irqsoff_trace __read_mostly; static int tracer_enabled __read_mostly; @@ -426,11 +427,13 @@ 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); } @@ -440,6 +443,7 @@ 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); } @@ -448,6 +452,7 @@ 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 */ @@ -473,6 +478,7 @@ 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); } @@ -482,11 +488,13 @@ 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); } @@ -496,6 +504,7 @@ 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); @@ -505,12 +514,14 @@ 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 51999309a6cf..c93de84fb8eb 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -591,6 +591,11 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) 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 71dd2363ab0f..b831e51c3489 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -129,11 +129,11 @@ 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(struct user_namespace *ns, uid_t uid) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 1d7bca7f4f52..c0c47d71f844 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -201,6 +201,8 @@ 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, @@ -235,10 +237,19 @@ 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; @@ -425,6 +436,7 @@ static void watchdog_prepare_cpu(int cpu) WARN_ON(per_cpu(softlockup_watchdog, cpu)); hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; + hrtimer->irqsafe = 1; } static int watchdog_enable(int cpu) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bb425b16372e..674d783f177b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -41,6 +41,7 @@ #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> +#include <linux/delay.h> #include "workqueue_sched.h" @@ -57,20 +58,10 @@ enum { WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ - WORKER_ROGUE = 1 << 4, /* not bound to any cpu */ - WORKER_REBIND = 1 << 5, /* mom is home, come back */ - WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ - WORKER_UNBOUND = 1 << 7, /* worker is unbound */ + WORKER_CPU_INTENSIVE = 1 << 4, /* cpu intensive */ + WORKER_UNBOUND = 1 << 5, /* worker is unbound */ - WORKER_NOT_RUNNING = WORKER_PREP | WORKER_ROGUE | WORKER_REBIND | - WORKER_CPU_INTENSIVE | WORKER_UNBOUND, - - /* gcwq->trustee_state */ - TRUSTEE_START = 0, /* start */ - TRUSTEE_IN_CHARGE = 1, /* trustee in charge of gcwq */ - TRUSTEE_BUTCHER = 2, /* butcher workers */ - TRUSTEE_RELEASE = 3, /* release workers */ - TRUSTEE_DONE = 4, /* trustee is done */ + WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND, BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER, @@ -84,7 +75,6 @@ enum { (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ - TRUSTEE_COOLDOWN = HZ / 10, /* for trustee draining */ /* * Rescue workers are used only on emergencies and shared by @@ -136,7 +126,7 @@ struct worker { unsigned long last_active; /* L: last active timestamp */ unsigned int flags; /* X: flags */ int id; /* I: worker id */ - struct work_struct rebind_work; /* L: rebind worker to cpu */ + int sleeping; /* None */ }; /* @@ -163,10 +153,8 @@ struct global_cwq { struct ida worker_ida; /* L: for worker IDs */ - struct task_struct *trustee; /* L: for gcwq shutdown */ - unsigned int trustee_state; /* L: trustee state */ - wait_queue_head_t trustee_wait; /* trustee wait */ struct worker *first_idle; /* L: first idle worker */ + wait_queue_head_t idle_wait; } ____cacheline_aligned_in_smp; /* @@ -660,66 +648,58 @@ static void wake_up_worker(struct global_cwq *gcwq) } /** - * 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, unsigned int cpu) +void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); + if (!worker->sleeping) + return; if (!(worker->flags & WORKER_NOT_RUNNING)) - atomic_inc(get_gcwq_nr_running(cpu)); + atomic_inc(get_gcwq_nr_running(smp_processor_id())); + 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, - unsigned int cpu) +void wq_worker_sleeping(struct task_struct *task) { - struct worker *worker = kthread_data(task), *to_wakeup = NULL; - struct global_cwq *gcwq = get_gcwq(cpu); - atomic_t *nr_running = get_gcwq_nr_running(cpu); + struct worker *worker = kthread_data(task); + struct global_cwq *gcwq; + int cpu; if (worker->flags & WORKER_NOT_RUNNING) - return NULL; + return; - /* this can only happen on the local cpu */ - BUG_ON(cpu != raw_smp_processor_id()); + if (WARN_ON_ONCE(worker->sleeping)) + return; + + worker->sleeping = 1; + cpu = smp_processor_id(); + gcwq = get_gcwq(cpu); + spin_lock_irq(&gcwq->lock); /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). * Please read comment there. - * - * NOT_RUNNING is clear. This means that trustee is not in - * charge and we're running on the local cpu w/ rq lock held - * and preemption disabled, which in turn means that none else - * could be manipulating idle_list, so dereferencing idle_list - * without gcwq lock is safe. */ - if (atomic_dec_and_test(nr_running) && !list_empty(&gcwq->worklist)) - to_wakeup = first_worker(gcwq); - return to_wakeup ? to_wakeup->task : NULL; + if (atomic_dec_and_test(get_gcwq_nr_running(cpu)) && + !list_empty(&gcwq->worklist)) { + worker = first_worker(gcwq); + if (worker) + wake_up_process(worker->task); + } + spin_unlock_irq(&gcwq->lock); } /** @@ -981,13 +961,38 @@ static bool is_chained_work(struct workqueue_struct *wq) return false; } -static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, - struct work_struct *work) +static void ___queue_work(struct workqueue_struct *wq, struct global_cwq *gcwq, + struct work_struct *work) { - struct global_cwq *gcwq; struct cpu_workqueue_struct *cwq; struct list_head *worklist; unsigned int work_flags; + + /* gcwq determined, get cwq and queue */ + cwq = get_cwq(gcwq->cpu, wq); + trace_workqueue_queue_work(gcwq->cpu, cwq, work); + + BUG_ON(!list_empty(&work->entry)); + + cwq->nr_in_flight[cwq->work_color]++; + work_flags = work_color_to_flags(cwq->work_color); + + if (likely(cwq->nr_active < cwq->max_active)) { + trace_workqueue_activate_work(work); + cwq->nr_active++; + worklist = gcwq_determine_ins_pos(gcwq, cwq); + } else { + work_flags |= WORK_STRUCT_DELAYED; + worklist = &cwq->delayed_works; + } + + insert_work(cwq, work, worklist, work_flags); +} + +static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, + struct work_struct *work) +{ + struct global_cwq *gcwq; unsigned long flags; debug_work_activate(work); @@ -1033,27 +1038,32 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, spin_lock_irqsave(&gcwq->lock, flags); } - /* gcwq determined, get cwq and queue */ - cwq = get_cwq(gcwq->cpu, wq); - trace_workqueue_queue_work(cpu, cwq, work); + ___queue_work(wq, gcwq, work); - BUG_ON(!list_empty(&work->entry)); + spin_unlock_irqrestore(&gcwq->lock, flags); +} - cwq->nr_in_flight[cwq->work_color]++; - work_flags = work_color_to_flags(cwq->work_color); +/** + * queue_work_on - queue work on specific cpu + * @cpu: CPU number to execute work on + * @wq: workqueue to use + * @work: work to queue + * + * Returns 0 if @work was already on a queue, non-zero otherwise. + * + * We queue the work to a specific CPU, the caller must ensure it + * can't go away. + */ +static int +__queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) +{ + int ret = 0; - if (likely(cwq->nr_active < cwq->max_active)) { - trace_workqueue_activate_work(work); - cwq->nr_active++; - worklist = gcwq_determine_ins_pos(gcwq, cwq); - } else { - work_flags |= WORK_STRUCT_DELAYED; - worklist = &cwq->delayed_works; + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = 1; } - - insert_work(cwq, work, worklist, work_flags); - - spin_unlock_irqrestore(&gcwq->lock, flags); + return ret; } /** @@ -1070,34 +1080,19 @@ int queue_work(struct workqueue_struct *wq, struct work_struct *work) { int ret; - ret = queue_work_on(get_cpu(), wq, work); - put_cpu(); + ret = __queue_work_on(get_cpu_light(), wq, work); + put_cpu_light(); return ret; } EXPORT_SYMBOL_GPL(queue_work); -/** - * queue_work_on - queue work on specific cpu - * @cpu: CPU number to execute work on - * @wq: workqueue to use - * @work: work to queue - * - * Returns 0 if @work was already on a queue, non-zero otherwise. - * - * We queue the work to a specific CPU, the caller must ensure it - * can't go away. - */ int queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { - int ret = 0; + WARN_ON(wq->flags & WQ_NON_AFFINE); - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { - __queue_work(cpu, wq, work); - ret = 1; - } - return ret; + return __queue_work_on(cpu, wq, work); } EXPORT_SYMBOL_GPL(queue_work_on); @@ -1143,6 +1138,8 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; + WARN_ON((wq->flags & WQ_NON_AFFINE) && cpu != -1); + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { unsigned int lcpu; @@ -1208,12 +1205,13 @@ static void worker_enter_idle(struct worker *worker) /* idle_list is LIFO */ list_add(&worker->entry, &gcwq->idle_list); - if (likely(!(worker->flags & WORKER_ROGUE))) { - if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer)) - mod_timer(&gcwq->idle_timer, - jiffies + IDLE_WORKER_TIMEOUT); - } else - wake_up_all(&gcwq->trustee_wait); + if (gcwq->nr_idle == gcwq->nr_workers) + wake_up_all(&gcwq->idle_wait); + + if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer)) { + mod_timer(&gcwq->idle_timer, + jiffies + IDLE_WORKER_TIMEOUT); + } /* sanity check nr_running */ WARN_ON_ONCE(gcwq->nr_workers == gcwq->nr_idle && @@ -1290,8 +1288,14 @@ __acquires(&gcwq->lock) return false; if (task_cpu(task) == gcwq->cpu && cpumask_equal(¤t->cpus_allowed, - get_cpu_mask(gcwq->cpu))) + get_cpu_mask(gcwq->cpu))) { + /* + * Since we're binding to a particular cpu and need to + * stay there for correctness, mark us PF_THREAD_BOUND. + */ + task->flags |= PF_THREAD_BOUND; return true; + } spin_unlock_irq(&gcwq->lock); /* @@ -1305,20 +1309,15 @@ __acquires(&gcwq->lock) } } -/* - * Function for worker->rebind_work used to rebind rogue busy workers - * to the associated cpu which is coming back online. This is - * scheduled by cpu up but can race with other cpu hotplug operations - * and may be executed twice without intervening cpu down. - */ -static void worker_rebind_fn(struct work_struct *work) +static void worker_unbind_and_unlock(struct worker *worker) { - struct worker *worker = container_of(work, struct worker, rebind_work); struct global_cwq *gcwq = worker->gcwq; + struct task_struct *task = worker->task; - if (worker_maybe_bind_and_lock(worker)) - worker_clr_flags(worker, WORKER_REBIND); - + /* + * Its no longer required we're PF_THREAD_BOUND, the work is done. + */ + task->flags &= ~PF_THREAD_BOUND; spin_unlock_irq(&gcwq->lock); } @@ -1330,7 +1329,6 @@ static struct worker *alloc_worker(void) if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); - INIT_WORK(&worker->rebind_work, worker_rebind_fn); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } @@ -1385,15 +1383,9 @@ static struct worker *create_worker(struct global_cwq *gcwq, bool bind) if (IS_ERR(worker->task)) goto fail; - /* - * A rogue worker will become a regular one if CPU comes - * online later on. Make sure every worker has - * PF_THREAD_BOUND set. - */ if (bind && !on_unbound_cpu) kthread_bind(worker->task, gcwq->cpu); else { - worker->task->flags |= PF_THREAD_BOUND; if (on_unbound_cpu) worker->flags |= WORKER_UNBOUND; } @@ -1670,13 +1662,6 @@ static bool manage_workers(struct worker *worker) gcwq->flags &= ~GCWQ_MANAGING_WORKERS; - /* - * The trustee might be waiting to take over the manager - * position, tell it we're done. - */ - if (unlikely(gcwq->trustee)) - wake_up_all(&gcwq->trustee_wait); - return ret; } @@ -2077,7 +2062,7 @@ repeat: if (keep_working(gcwq)) wake_up_worker(gcwq); - spin_unlock_irq(&gcwq->lock); + worker_unbind_and_unlock(rescuer); } schedule(); @@ -3026,7 +3011,6 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, if (IS_ERR(rescuer->task)) goto err; - rescuer->task->flags |= PF_THREAD_BOUND; wake_up_process(rescuer->task); } @@ -3216,171 +3200,76 @@ EXPORT_SYMBOL_GPL(work_busy); * gcwqs serve mix of short, long and very long running works making * blocked draining impractical. * - * This is solved by allowing a gcwq to be detached from CPU, running - * it with unbound (rogue) workers and allowing it to be reattached - * later if the cpu comes back online. A separate thread is created - * to govern a gcwq in such state and is called the trustee of the - * gcwq. - * - * Trustee states and their descriptions. - * - * START Command state used on startup. On CPU_DOWN_PREPARE, a - * new trustee is started with this state. - * - * IN_CHARGE Once started, trustee will enter this state after - * assuming the manager role and making all existing - * workers rogue. DOWN_PREPARE waits for trustee to - * enter this state. After reaching IN_CHARGE, trustee - * tries to execute the pending worklist until it's empty - * and the state is set to BUTCHER, or the state is set - * to RELEASE. - * - * BUTCHER Command state which is set by the cpu callback after - * the cpu has went down. Once this state is set trustee - * knows that there will be no new works on the worklist - * and once the worklist is empty it can proceed to - * killing idle workers. - * - * RELEASE Command state which is set by the cpu callback if the - * cpu down has been canceled or it has come online - * again. After recognizing this state, trustee stops - * trying to drain or butcher and clears ROGUE, rebinds - * all remaining workers back to the cpu and releases - * manager role. - * - * DONE Trustee will enter this state after BUTCHER or RELEASE - * is complete. - * - * trustee CPU draining - * took over down complete - * START -----------> IN_CHARGE -----------> BUTCHER -----------> DONE - * | | ^ - * | CPU is back online v return workers | - * ----------------> RELEASE -------------- */ -/** - * trustee_wait_event_timeout - timed event wait for trustee - * @cond: condition to wait for - * @timeout: timeout in jiffies - * - * wait_event_timeout() for trustee to use. Handles locking and - * checks for RELEASE request. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by trustee. - * - * RETURNS: - * Positive indicating left time if @cond is satisfied, 0 if timed - * out, -1 if canceled. - */ -#define trustee_wait_event_timeout(cond, timeout) ({ \ - long __ret = (timeout); \ - while (!((cond) || (gcwq->trustee_state == TRUSTEE_RELEASE)) && \ - __ret) { \ - spin_unlock_irq(&gcwq->lock); \ - __wait_event_timeout(gcwq->trustee_wait, (cond) || \ - (gcwq->trustee_state == TRUSTEE_RELEASE), \ - __ret); \ - spin_lock_irq(&gcwq->lock); \ - } \ - gcwq->trustee_state == TRUSTEE_RELEASE ? -1 : (__ret); \ -}) +static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + struct global_cwq *gcwq = get_gcwq(cpu); + struct worker *uninitialized_var(new_worker); + unsigned long flags; -/** - * trustee_wait_event - event wait for trustee - * @cond: condition to wait for - * - * wait_event() for trustee to use. Automatically handles locking and - * checks for CANCEL request. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by trustee. - * - * RETURNS: - * 0 if @cond is satisfied, -1 if canceled. - */ -#define trustee_wait_event(cond) ({ \ - long __ret1; \ - __ret1 = trustee_wait_event_timeout(cond, MAX_SCHEDULE_TIMEOUT);\ - __ret1 < 0 ? -1 : 0; \ -}) + action &= ~CPU_TASKS_FROZEN; -static int __cpuinit trustee_thread(void *__gcwq) -{ - struct global_cwq *gcwq = __gcwq; - struct worker *worker; - struct work_struct *work; - struct hlist_node *pos; - long rc; - int i; + switch (action) { + case CPU_UP_PREPARE: + BUG_ON(gcwq->first_idle); + new_worker = create_worker(gcwq, false); + if (!new_worker) + return NOTIFY_BAD; + case CPU_UP_CANCELED: + case CPU_ONLINE: + break; + default: + return notifier_from_errno(0); + } - BUG_ON(gcwq->cpu != smp_processor_id()); + /* some are called w/ irq disabled, don't disturb irq status */ + spin_lock_irqsave(&gcwq->lock, flags); - spin_lock_irq(&gcwq->lock); - /* - * Claim the manager position and make all workers rogue. - * Trustee must be bound to the target cpu and can't be - * cancelled. - */ - BUG_ON(gcwq->cpu != smp_processor_id()); - rc = trustee_wait_event(!(gcwq->flags & GCWQ_MANAGING_WORKERS)); - BUG_ON(rc < 0); + switch (action) { + case CPU_UP_PREPARE: + BUG_ON(gcwq->first_idle); + gcwq->first_idle = new_worker; + break; - gcwq->flags |= GCWQ_MANAGING_WORKERS; + case CPU_UP_CANCELED: + destroy_worker(gcwq->first_idle); + gcwq->first_idle = NULL; + break; - list_for_each_entry(worker, &gcwq->idle_list, entry) - worker->flags |= WORKER_ROGUE; + case CPU_ONLINE: + spin_unlock_irq(&gcwq->lock); + kthread_bind(gcwq->first_idle->task, cpu); + spin_lock_irq(&gcwq->lock); + gcwq->flags |= GCWQ_MANAGE_WORKERS; + start_worker(gcwq->first_idle); + gcwq->first_idle = NULL; + break; + } - for_each_busy_worker(worker, i, pos, gcwq) - worker->flags |= WORKER_ROGUE; + spin_unlock_irqrestore(&gcwq->lock, flags); - /* - * Call schedule() so that we cross rq->lock and thus can - * guarantee sched callbacks see the rogue flag. This is - * necessary as scheduler callbacks may be invoked from other - * cpus. - */ - spin_unlock_irq(&gcwq->lock); - schedule(); - spin_lock_irq(&gcwq->lock); + return notifier_from_errno(0); +} - /* - * Sched callbacks are disabled now. Zap nr_running. After - * this, nr_running stays zero and need_more_worker() and - * keep_working() are always true as long as the worklist is - * not empty. - */ - atomic_set(get_gcwq_nr_running(gcwq->cpu), 0); +static void flush_gcwq(struct global_cwq *gcwq) +{ + struct work_struct *work, *nw; + struct worker *worker, *n; + LIST_HEAD(non_affine_works); - spin_unlock_irq(&gcwq->lock); - del_timer_sync(&gcwq->idle_timer); spin_lock_irq(&gcwq->lock); + list_for_each_entry_safe(work, nw, &gcwq->worklist, entry) { + struct workqueue_struct *wq = get_work_cwq(work)->wq; - /* - * We're now in charge. Notify and proceed to drain. We need - * to keep the gcwq running during the whole CPU down - * procedure as other cpu hotunplug callbacks may need to - * flush currently running tasks. - */ - gcwq->trustee_state = TRUSTEE_IN_CHARGE; - wake_up_all(&gcwq->trustee_wait); + if (wq->flags & WQ_NON_AFFINE) + list_move(&work->entry, &non_affine_works); + } - /* - * The original cpu is in the process of dying and may go away - * anytime now. When that happens, we and all workers would - * be migrated to other cpus. Try draining any left work. We - * want to get it over with ASAP - spam rescuers, wake up as - * many idlers as necessary and create new ones till the - * worklist is empty. Note that if the gcwq is frozen, there - * may be frozen works in freezable cwqs. Don't declare - * completion while frozen. - */ - while (gcwq->nr_workers != gcwq->nr_idle || - gcwq->flags & GCWQ_FREEZING || - gcwq->trustee_state == TRUSTEE_IN_CHARGE) { + while (!list_empty(&gcwq->worklist)) { int nr_works = 0; list_for_each_entry(work, &gcwq->worklist, entry) { @@ -3394,189 +3283,54 @@ static int __cpuinit trustee_thread(void *__gcwq) wake_up_process(worker->task); } + spin_unlock_irq(&gcwq->lock); + if (need_to_create_worker(gcwq)) { - spin_unlock_irq(&gcwq->lock); - worker = create_worker(gcwq, false); - spin_lock_irq(&gcwq->lock); - if (worker) { - worker->flags |= WORKER_ROGUE; + worker = create_worker(gcwq, true); + if (worker) start_worker(worker); - } } - /* give a breather */ - if (trustee_wait_event_timeout(false, TRUSTEE_COOLDOWN) < 0) - break; - } - - /* - * Either all works have been scheduled and cpu is down, or - * cpu down has already been canceled. Wait for and butcher - * all workers till we're canceled. - */ - do { - rc = trustee_wait_event(!list_empty(&gcwq->idle_list)); - while (!list_empty(&gcwq->idle_list)) - destroy_worker(list_first_entry(&gcwq->idle_list, - struct worker, entry)); - } while (gcwq->nr_workers && rc >= 0); + wait_event_timeout(gcwq->idle_wait, + gcwq->nr_idle == gcwq->nr_workers, HZ/10); - /* - * At this point, either draining has completed and no worker - * is left, or cpu down has been canceled or the cpu is being - * brought back up. There shouldn't be any idle one left. - * Tell the remaining busy ones to rebind once it finishes the - * currently scheduled works by scheduling the rebind_work. - */ - WARN_ON(!list_empty(&gcwq->idle_list)); - - for_each_busy_worker(worker, i, pos, gcwq) { - struct work_struct *rebind_work = &worker->rebind_work; - - /* - * Rebind_work may race with future cpu hotplug - * operations. Use a separate flag to mark that - * rebinding is scheduled. - */ - worker->flags |= WORKER_REBIND; - worker->flags &= ~WORKER_ROGUE; + spin_lock_irq(&gcwq->lock); + } - /* queue rebind_work, wq doesn't matter, use the default one */ - if (test_and_set_bit(WORK_STRUCT_PENDING_BIT, - work_data_bits(rebind_work))) - continue; + WARN_ON(gcwq->nr_workers != gcwq->nr_idle); - debug_work_activate(rebind_work); - insert_work(get_cwq(gcwq->cpu, system_wq), rebind_work, - worker->scheduled.next, - work_color_to_flags(WORK_NO_COLOR)); - } + list_for_each_entry_safe(worker, n, &gcwq->idle_list, entry) + destroy_worker(worker); - /* relinquish manager role */ - gcwq->flags &= ~GCWQ_MANAGING_WORKERS; + WARN_ON(gcwq->nr_workers || gcwq->nr_idle); - /* notify completion */ - gcwq->trustee = NULL; - gcwq->trustee_state = TRUSTEE_DONE; - wake_up_all(&gcwq->trustee_wait); spin_unlock_irq(&gcwq->lock); - return 0; -} -/** - * wait_trustee_state - wait for trustee to enter the specified state - * @gcwq: gcwq the trustee of interest belongs to - * @state: target state to wait for - * - * Wait for the trustee to reach @state. DONE is already matched. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed - * multiple times. To be used by cpu_callback. - */ -static void __cpuinit wait_trustee_state(struct global_cwq *gcwq, int state) -__releases(&gcwq->lock) -__acquires(&gcwq->lock) -{ - if (!(gcwq->trustee_state == state || - gcwq->trustee_state == TRUSTEE_DONE)) { - spin_unlock_irq(&gcwq->lock); - __wait_event(gcwq->trustee_wait, - gcwq->trustee_state == state || - gcwq->trustee_state == TRUSTEE_DONE); - spin_lock_irq(&gcwq->lock); + gcwq = get_gcwq(get_cpu_light()); + spin_lock_irq(&gcwq->lock); + list_for_each_entry_safe(work, nw, &non_affine_works, entry) { + list_del_init(&work->entry); + ___queue_work(get_work_cwq(work)->wq, gcwq, work); } + spin_unlock_irq(&gcwq->lock); + put_cpu_light(); } -static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, +static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; struct global_cwq *gcwq = get_gcwq(cpu); - struct task_struct *new_trustee = NULL; - struct worker *uninitialized_var(new_worker); - unsigned long flags; action &= ~CPU_TASKS_FROZEN; - switch (action) { - case CPU_DOWN_PREPARE: - new_trustee = kthread_create(trustee_thread, gcwq, - "workqueue_trustee/%d\n", cpu); - if (IS_ERR(new_trustee)) - return notifier_from_errno(PTR_ERR(new_trustee)); - kthread_bind(new_trustee, cpu); - /* fall through */ - case CPU_UP_PREPARE: - BUG_ON(gcwq->first_idle); - new_worker = create_worker(gcwq, false); - if (!new_worker) { - if (new_trustee) - kthread_stop(new_trustee); - return NOTIFY_BAD; - } - } + switch (action) { + case CPU_DOWN_PREPARE: + flush_gcwq(gcwq); + break; + } - /* some are called w/ irq disabled, don't disturb irq status */ - spin_lock_irqsave(&gcwq->lock, flags); - - switch (action) { - case CPU_DOWN_PREPARE: - /* initialize trustee and tell it to acquire the gcwq */ - BUG_ON(gcwq->trustee || gcwq->trustee_state != TRUSTEE_DONE); - gcwq->trustee = new_trustee; - gcwq->trustee_state = TRUSTEE_START; - wake_up_process(gcwq->trustee); - wait_trustee_state(gcwq, TRUSTEE_IN_CHARGE); - /* fall through */ - case CPU_UP_PREPARE: - BUG_ON(gcwq->first_idle); - gcwq->first_idle = new_worker; - break; - - case CPU_DYING: - /* - * Before this, the trustee and all workers except for - * the ones which are still executing works from - * before the last CPU down must be on the cpu. After - * this, they'll all be diasporas. - */ - gcwq->flags |= GCWQ_DISASSOCIATED; - break; - - case CPU_POST_DEAD: - gcwq->trustee_state = TRUSTEE_BUTCHER; - /* fall through */ - case CPU_UP_CANCELED: - destroy_worker(gcwq->first_idle); - gcwq->first_idle = NULL; - break; - - case CPU_DOWN_FAILED: - case CPU_ONLINE: - gcwq->flags &= ~GCWQ_DISASSOCIATED; - if (gcwq->trustee_state != TRUSTEE_DONE) { - gcwq->trustee_state = TRUSTEE_RELEASE; - wake_up_process(gcwq->trustee); - wait_trustee_state(gcwq, TRUSTEE_DONE); - } - - /* - * Trustee is done and there might be no worker left. - * Put the first_idle in and request a real manager to - * take a look. - */ - spin_unlock_irq(&gcwq->lock); - kthread_bind(gcwq->first_idle->task, cpu); - spin_lock_irq(&gcwq->lock); - gcwq->flags |= GCWQ_MANAGE_WORKERS; - start_worker(gcwq->first_idle); - gcwq->first_idle = NULL; - break; - } - - spin_unlock_irqrestore(&gcwq->lock, flags); return notifier_from_errno(0); } @@ -3774,7 +3528,8 @@ static int __init init_workqueues(void) unsigned int cpu; int i; - cpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); + cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_ACTIVE); + hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_INACTIVE); /* initialize gcwqs */ for_each_gcwq_cpu(cpu) { @@ -3797,9 +3552,7 @@ static int __init init_workqueues(void) (unsigned long)gcwq); ida_init(&gcwq->worker_ida); - - gcwq->trustee_state = TRUSTEE_DONE; - init_waitqueue_head(&gcwq->trustee_wait); + init_waitqueue_head(&gcwq->idle_wait); } /* create the initial worker */ diff --git a/kernel/workqueue_sched.h b/kernel/workqueue_sched.h index 2d10fc98dc79..3bf73e24e1ea 100644 --- a/kernel/workqueue_sched.h +++ b/kernel/workqueue_sched.h @@ -4,6 +4,5 @@ * Scheduler hooks for concurrency managed workqueue. Only to be * included from sched.c and workqueue.c. */ -void wq_worker_waking_up(struct task_struct *task, unsigned int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task, - unsigned int cpu); +void wq_worker_running(struct task_struct *task); +void wq_worker_sleeping(struct task_struct *task); diff --git a/lib/Kconfig b/lib/Kconfig index 32f3e5ae2be5..63d81e811c1f 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -231,6 +231,7 @@ 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 82928f5ea049..13a937b16bfd 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -62,6 +62,28 @@ config MAGIC_SYSRQ keys are documented in <file:Documentation/sysrq.txt>. Don't say Y unless you really know what this hack does. +config MAGIC_SYSRQ_FORCE_PRINTK + bool "Force printk from Magic SysRq" + depends on MAGIC_SYSRQ && PREEMPT_RT_FULL + default n + help + Allow the output from Magic SysRq to be output immediately, even if + this causes large latencies. This can cause performance problems + for real-time processes. + + If PREEMPT_RT_FULL, printk() will not try to acquire the console lock + when interrupts or preemption are disabled. If the console lock is + not acquired the printk() output will be buffered, but will not be + output immediately. Some drivers call into the Magic SysRq code + with interrupts or preemption disabled, so the output of Magic SysRq + will be buffered instead of printing immediately if this option is + not selected. + + Even with this option selected, Magic SysRq output will be delayed + if the attempt to acquire the console lock fails. + + Don't say Y unless you really know what this hack does. + config STRIP_ASM_SYMS bool "Strip assembler-generated symbols during link" default n @@ -151,7 +173,7 @@ 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 a4da283f5dc0..5026c912dbf2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -37,8 +37,11 @@ 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 CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS)) obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o diff --git a/lib/debugobjects.c b/lib/debugobjects.c index a78b7c6e042c..9b622c994ecd 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -306,7 +306,10 @@ __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); @@ -1015,9 +1018,9 @@ static int __init debug_objects_replace_static_objects(void) } } + local_irq_enable(); printk(KERN_DEBUG "ODEBUG: %d of %d active objects replaced\n", cnt, obj_pool_used); - local_irq_enable(); return 0; free: hlist_for_each_entry_safe(obj, node, tmp, &objects, node) { diff --git a/lib/radix-tree.c b/lib/radix-tree.c index d9df7454519c..770453ac61e9 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -166,12 +166,13 @@ 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); @@ -206,6 +207,7 @@ 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 @@ -240,6 +242,7 @@ 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 4ceb05d772ae..181f3647818d 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -423,7 +423,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter) flush_kernel_dcache_page(miter->page); if (miter->__flags & SG_MITER_ATOMIC) { - WARN_ON(!irqs_disabled()); + WARN_ON_NONRT(!irqs_disabled()); kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ); } else kunmap(miter->page); @@ -463,7 +463,7 @@ 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; @@ -480,7 +480,7 @@ 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 503f087382a4..b5e924137ef3 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 5f3eacdd6178..f8247045a990 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) { @@ -155,6 +157,7 @@ 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()) @@ -296,3 +299,5 @@ 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 000000000000..9a218ca23053 --- /dev/null +++ b/localversion-rt @@ -0,0 +1 @@ +-rt23 diff --git a/mm/Kconfig b/mm/Kconfig index 011b110365c8..0526445c9b35 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -307,7 +307,7 @@ config NOMMU_INITIAL_TRIM_EXCESS config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" - depends on X86 && MMU + depends on X86 && MMU && !PREEMPT_RT_FULL select COMPACTION help Transparent Hugepages allows the kernel to use huge pages and diff --git a/mm/filemap.c b/mm/filemap.c index 03c5b0ec2b78..4a30d36ca4c8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2044,7 +2044,7 @@ 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, KM_USER0); if (likely(i->nr_segs == 1)) { int left; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 778554ffd639..abf5497cadcb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -683,37 +683,32 @@ static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg, return total; } -static bool __memcg_event_check(struct mem_cgroup *memcg, int target) +static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, + enum mem_cgroup_events_target target) { unsigned long val, next; val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]); next = __this_cpu_read(memcg->stat->targets[target]); /* from time_after() in jiffies.h */ - return ((long)next - (long)val < 0); -} - -static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target) -{ - unsigned long val, next; - - val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]); - - switch (target) { - case MEM_CGROUP_TARGET_THRESH: - next = val + THRESHOLDS_EVENTS_TARGET; - break; - case MEM_CGROUP_TARGET_SOFTLIMIT: - next = val + SOFTLIMIT_EVENTS_TARGET; - break; - case MEM_CGROUP_TARGET_NUMAINFO: - next = val + NUMAINFO_EVENTS_TARGET; - break; - default: - return; + if ((long)next - (long)val < 0) { + switch (target) { + case MEM_CGROUP_TARGET_THRESH: + next = val + THRESHOLDS_EVENTS_TARGET; + break; + case MEM_CGROUP_TARGET_SOFTLIMIT: + next = val + SOFTLIMIT_EVENTS_TARGET; + break; + case MEM_CGROUP_TARGET_NUMAINFO: + next = val + NUMAINFO_EVENTS_TARGET; + break; + default: + break; + } + __this_cpu_write(memcg->stat->targets[target], next); + return true; } - - __this_cpu_write(memcg->stat->targets[target], next); + return false; } /* @@ -724,25 +719,27 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) { preempt_disable(); /* threshold event is triggered in finer grain than soft limit */ - if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_THRESH))) { + if (unlikely(mem_cgroup_event_ratelimit(memcg, + MEM_CGROUP_TARGET_THRESH))) { + bool do_softlimit, do_numainfo; + + do_softlimit = mem_cgroup_event_ratelimit(memcg, + MEM_CGROUP_TARGET_SOFTLIMIT); +#if MAX_NUMNODES > 1 + do_numainfo = mem_cgroup_event_ratelimit(memcg, + MEM_CGROUP_TARGET_NUMAINFO); +#endif + preempt_enable(); + mem_cgroup_threshold(memcg); - __mem_cgroup_target_update(memcg, MEM_CGROUP_TARGET_THRESH); - if (unlikely(__memcg_event_check(memcg, - MEM_CGROUP_TARGET_SOFTLIMIT))) { + if (unlikely(do_softlimit)) mem_cgroup_update_tree(memcg, page); - __mem_cgroup_target_update(memcg, - MEM_CGROUP_TARGET_SOFTLIMIT); - } #if MAX_NUMNODES > 1 - if (unlikely(__memcg_event_check(memcg, - MEM_CGROUP_TARGET_NUMAINFO))) { + if (unlikely(do_numainfo)) atomic_inc(&memcg->numainfo_events); - __mem_cgroup_target_update(memcg, - MEM_CGROUP_TARGET_NUMAINFO); - } #endif - } - preempt_enable(); + } else + preempt_enable(); } static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) diff --git a/mm/memory.c b/mm/memory.c index 1b1ca176397e..a3ae5e7b0bfc 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3444,6 +3444,32 @@ 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_GPL(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_GPL(pagefault_enable); +#endif + /* * By the time we get here, we already hold the mm semaphore */ @@ -3992,3 +4018,35 @@ 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 cf332bc0080a..64ce279a984d 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -26,6 +26,7 @@ void use_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); + local_irq_disable_rt(); active_mm = tsk->active_mm; if (active_mm != mm) { atomic_inc(&mm->mm_count); @@ -33,6 +34,7 @@ void use_mm(struct mm_struct *mm) } tsk->mm = mm; switch_mm(active_mm, mm, tsk); + local_irq_enable_rt(); task_unlock(tsk); if (active_mm != mm) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 485be8976bba..49675c704a5b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -57,6 +57,7 @@ #include <linux/ftrace_event.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> +#include <linux/locallock.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -222,6 +223,18 @@ 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) \ + spin_lock_irqsave(&per_cpu(pa_lock, cpu).lock, flags) +# define cpu_unlock_irqrestore(cpu, flags) \ + spin_unlock_irqrestore(&per_cpu(pa_lock, cpu).lock, flags) +#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; static void set_pageblock_migratetype(struct page *page, int migratetype) @@ -581,7 +594,7 @@ 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. * @@ -592,16 +605,42 @@ 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); + + /* must delete as __free_one_page list manipulates */ + list_del(&page->lru); + /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ + __free_one_page(page, zone, 0, page_private(page)); + trace_mm_page_pcpu_drain(page, 0, page_private(page)); + to_free--; + } + WARN_ON(to_free != 0); + __mod_zone_page_state(zone, NR_FREE_PAGES, count); + 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; @@ -617,7 +656,7 @@ 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. */ @@ -625,28 +664,25 @@ static void free_pcppages_bulk(struct zone *zone, int count, batch_free = to_free; do { - 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); - /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ - __free_one_page(page, zone, 0, page_private(page)); - trace_mm_page_pcpu_drain(page, 0, page_private(page)); + list_add(&page->lru, dst); } while (--to_free && --batch_free && !list_empty(list)); } - __mod_zone_page_state(zone, NR_FREE_PAGES, count); - 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); __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order); - spin_unlock(&zone->lock); + spin_unlock_irqrestore(&zone->lock, flags); } static bool free_pages_prepare(struct page *page, unsigned int order) @@ -683,13 +719,13 @@ 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); if (unlikely(wasMlocked)) free_page_mlock(page); __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, order, get_pageblock_migratetype(page)); - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); } /* @@ -1065,16 +1101,18 @@ 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; - 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 @@ -1093,16 +1131,21 @@ 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); } } @@ -1119,7 +1162,14 @@ void drain_local_pages(void *arg) */ void drain_all_pages(void) { +#ifndef CONFIG_PREEMPT_RT_BASE on_each_cpu(drain_local_pages, NULL, 1); +#else + int i; + + for_each_online_cpu(i) + drain_pages(i); +#endif } #ifdef CONFIG_HIBERNATION @@ -1175,7 +1225,7 @@ void free_hot_cold_page(struct page *page, int cold) migratetype = get_pageblock_migratetype(page); set_page_private(page, migratetype); - local_irq_save(flags); + local_lock_irqsave(pa_lock, flags); if (unlikely(wasMlocked)) free_page_mlock(page); __count_vm_event(PGFREE); @@ -1202,12 +1252,19 @@ 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); } /* @@ -1302,7 +1359,7 @@ 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)) { @@ -1334,17 +1391,19 @@ 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_page_state(zone, NR_FREE_PAGES, -(1 << order)); + 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)) @@ -1352,7 +1411,7 @@ again: return page; failed: - local_irq_restore(flags); + local_unlock_irqrestore(pa_lock, flags); return NULL; } @@ -1901,8 +1960,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, if (*did_some_progress != COMPACT_SKIPPED) { /* 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, @@ -3680,14 +3739,16 @@ static int __zone_pcp_update(void *data) 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); - free_pcppages_bulk(zone, pcp->count, pcp); + cpu_lock_irqsave(cpu, flags); + isolate_pcp_pages(pcp->count, pcp, &dst); + free_pcppages_bulk(zone, pcp->count, &dst); setup_pageset(pset, batch); - local_irq_restore(flags); + cpu_unlock_irqrestore(cpu, flags); } return 0; } @@ -5053,6 +5114,7 @@ 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); } /* diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 2d123f94a8df..2e0d18d8e432 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -17,6 +17,7 @@ static void __meminit init_page_cgroup(struct page_cgroup *pc, unsigned long id) set_page_cgroup_array_id(pc, id); pc->mem_cgroup = NULL; INIT_LIST_HEAD(&pc->lru); + page_cgroup_lock_init(pc); } static unsigned long total_usage; diff --git a/mm/slab.c b/mm/slab.c index 83311c9aaf9d..5f0c5ef303d4 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -116,6 +116,7 @@ #include <linux/kmemcheck.h> #include <linux/memory.h> #include <linux/prefetch.h> +#include <linux/locallock.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -607,6 +608,12 @@ int slab_is_available(void) return g_cpucache_up >= EARLY; } +/* + * Guard access to the cache-chain. + */ +static DEFINE_MUTEX(cache_chain_mutex); +static struct list_head cache_chain; + #ifdef CONFIG_LOCKDEP /* @@ -668,38 +675,41 @@ static void slab_set_debugobj_lock_classes(struct kmem_cache *cachep) slab_set_debugobj_lock_classes_node(cachep, node); } -static void init_node_lock_keys(int q) +static void init_lock_keys(struct kmem_cache *cachep, int node) { - struct cache_sizes *s = malloc_sizes; + struct kmem_list3 *l3; if (g_cpucache_up < LATE) return; - for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) { - struct kmem_list3 *l3; + l3 = cachep->nodelists[node]; + if (!l3 || OFF_SLAB(cachep)) + return; - l3 = s->cs_cachep->nodelists[q]; - if (!l3 || OFF_SLAB(s->cs_cachep)) - continue; + slab_set_lock_classes(cachep, &on_slab_l3_key, &on_slab_alc_key, node); +} - slab_set_lock_classes(s->cs_cachep, &on_slab_l3_key, - &on_slab_alc_key, q); - } +static void init_node_lock_keys(int node) +{ + struct kmem_cache *cachep; + + list_for_each_entry(cachep, &cache_chain, next) + init_lock_keys(cachep, node); } -static inline void init_lock_keys(void) +static inline void init_cachep_lock_keys(struct kmem_cache *cachep) { int node; for_each_node(node) - init_node_lock_keys(node); + init_lock_keys(cachep, node); } #else -static void init_node_lock_keys(int q) +static void init_node_lock_keys(int node) { } -static inline void init_lock_keys(void) +static void init_cachep_lock_keys(struct kmem_cache *cachep) { } @@ -712,19 +722,67 @@ 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 /* - * Guard access to the cache-chain. + * 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 DEFINE_MUTEX(cache_chain_mutex); -static struct list_head cache_chain; +static void +slab_on_each_cpu(void (*func)(void *arg, int this_cpu), void *arg) +{ + unsigned int i; -static DEFINE_PER_CPU(struct delayed_work, slab_reap_work); + for_each_online_cpu(i) + func(arg, i); +} +#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 inline struct kmem_cache *__find_general_cachep(size_t size, gfp_t gfpflags) { @@ -1062,9 +1120,10 @@ static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3) if (l3->alien) { struct array_cache *ac = l3->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); } } } @@ -1079,9 +1138,9 @@ 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); } } } @@ -1160,11 +1219,11 @@ static int init_cache_nodelists_node(int node) cachep->nodelists[node] = l3; } - spin_lock_irq(&cachep->nodelists[node]->list_lock); + local_spin_lock_irq(slab_lock, &cachep->nodelists[node]->list_lock); cachep->nodelists[node]->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - spin_unlock_irq(&cachep->nodelists[node]->list_lock); + local_spin_unlock_irq(slab_lock, &cachep->nodelists[node]->list_lock); } return 0; } @@ -1189,7 +1248,7 @@ static void __cpuinit cpuup_canceled(long cpu) if (!l3) goto free_array_cache; - spin_lock_irq(&l3->list_lock); + local_spin_lock_irq(slab_lock, &l3->list_lock); /* Free limit for this kmem_list3 */ l3->free_limit -= cachep->batchcount; @@ -1197,7 +1256,7 @@ static void __cpuinit cpuup_canceled(long cpu) free_block(cachep, nc->entry, nc->avail, node); if (!cpumask_empty(mask)) { - spin_unlock_irq(&l3->list_lock); + unlock_l3_and_free_delayed(&l3->list_lock); goto free_array_cache; } @@ -1211,7 +1270,7 @@ static void __cpuinit cpuup_canceled(long cpu) alien = l3->alien; l3->alien = NULL; - spin_unlock_irq(&l3->list_lock); + unlock_l3_and_free_delayed(&l3->list_lock); kfree(shared); if (alien) { @@ -1285,7 +1344,7 @@ static int __cpuinit cpuup_prepare(long cpu) l3 = cachep->nodelists[node]; BUG_ON(!l3); - spin_lock_irq(&l3->list_lock); + local_spin_lock_irq(slab_lock, &l3->list_lock); if (!l3->shared) { /* * We are serialised from CPU_DEAD or @@ -1300,7 +1359,7 @@ static int __cpuinit cpuup_prepare(long cpu) alien = NULL; } #endif - spin_unlock_irq(&l3->list_lock); + local_spin_unlock_irq(slab_lock, &l3->list_lock); kfree(shared); free_alien_cache(alien); if (cachep->flags & SLAB_DEBUG_OBJECTS) @@ -1491,6 +1550,10 @@ 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_list3_init(&initkmem_list3[i]); if (i < MAX_NUMNODES) @@ -1669,14 +1732,13 @@ void __init kmem_cache_init_late(void) g_cpucache_up = LATE; - /* Annotate slab for lockdep -- annotate the malloc caches */ - init_lock_keys(); - /* 6) resize the head arrays to their final sizes */ mutex_lock(&cache_chain_mutex); - list_for_each_entry(cachep, &cache_chain, next) + list_for_each_entry(cachep, &cache_chain, next) { + init_cachep_lock_keys(cachep); if (enable_cpucache(cachep, GFP_NOWAIT)) BUG(); + } mutex_unlock(&cache_chain_mutex); /* Done! */ @@ -1769,12 +1831,14 @@ 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) @@ -1790,7 +1854,13 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr) } if (current->reclaim_state) current->reclaim_state->reclaimed_slab += nr_freed; - free_pages((unsigned long)addr, cachep->gfporder); + + if (!delayed) { + free_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) @@ -1798,7 +1868,7 @@ 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); } @@ -2017,7 +2087,8 @@ 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; @@ -2030,7 +2101,7 @@ 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); } @@ -2479,6 +2550,8 @@ kmem_cache_create (const char *name, size_t size, size_t align, slab_set_debugobj_lock_classes(cachep); } + init_cachep_lock_keys(cachep); + /* cache setup completed, link it into the list */ list_add(&cachep->next, &cache_chain); oops: @@ -2496,7 +2569,7 @@ EXPORT_SYMBOL(kmem_cache_create); #if DEBUG static void check_irq_off(void) { - BUG_ON(!irqs_disabled()); + BUG_ON_NONRT(!irqs_disabled()); } static void check_irq_on(void) @@ -2531,26 +2604,43 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, 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->nodelists[node]->list_lock); free_block(cachep, ac->entry, ac->avail, node); spin_unlock(&cachep->nodelists[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); + + spin_lock_irq(&per_cpu(slab_lock, cpu).lock); + __do_drain(arg, cpu); + list_splice_init(&per_cpu(slab_free_list, cpu), &tmp); + spin_unlock_irq(&per_cpu(slab_lock, cpu).lock); + free_delayed(&tmp); +} +#endif + static void drain_cpu_caches(struct kmem_cache *cachep) { struct kmem_list3 *l3; int node; - on_each_cpu(do_drain, cachep, 1); + slab_on_each_cpu(do_drain, cachep); check_irq_on(); for_each_online_node(node) { l3 = cachep->nodelists[node]; @@ -2581,10 +2671,10 @@ static int drain_freelist(struct kmem_cache *cache, nr_freed = 0; while (nr_freed < tofree && !list_empty(&l3->slabs_free)) { - spin_lock_irq(&l3->list_lock); + local_spin_lock_irq(slab_lock, &l3->list_lock); p = l3->slabs_free.prev; if (p == &l3->slabs_free) { - spin_unlock_irq(&l3->list_lock); + local_spin_unlock_irq(slab_lock, &l3->list_lock); goto out; } @@ -2598,8 +2688,8 @@ static int drain_freelist(struct kmem_cache *cache, * to the cache. */ l3->free_objects -= cache->num; - spin_unlock_irq(&l3->list_lock); - slab_destroy(cache, slabp); + local_spin_unlock_irq(slab_lock, &l3->list_lock); + slab_destroy(cache, slabp, false); nr_freed++; } out: @@ -2893,7 +2983,7 @@ 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 @@ -2923,7 +3013,7 @@ 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(&l3->list_lock); @@ -2934,10 +3024,10 @@ static int cache_grow(struct kmem_cache *cachep, spin_unlock(&l3->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; } @@ -3329,11 +3419,11 @@ 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 @@ -3449,7 +3539,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, return NULL; 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; @@ -3474,7 +3564,7 @@ __cache_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, obj_size(cachep), 1, cachep->flags, flags); @@ -3534,9 +3624,9 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) return NULL; 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, obj_size(cachep), 1, cachep->flags, flags); @@ -3584,7 +3674,7 @@ 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, &l3->slabs_free); } @@ -3847,12 +3937,12 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) { unsigned long flags; - local_irq_save(flags); debug_check_no_locks_freed(objp, obj_size(cachep)); if (!(cachep->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(objp, obj_size(cachep)); + local_lock_irqsave(slab_lock, flags); __cache_free(cachep, objp, __builtin_return_address(0)); - local_irq_restore(flags); + unlock_slab_and_free_delayed(flags); trace_kmem_cache_free(_RET_IP_, objp); } @@ -3876,13 +3966,13 @@ 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, obj_size(c)); debug_check_no_obj_freed(objp, obj_size(c)); + local_lock_irqsave(slab_lock, flags); __cache_free(c, (void *)objp, __builtin_return_address(0)); - local_irq_restore(flags); + unlock_slab_and_free_delayed(flags); } EXPORT_SYMBOL(kfree); @@ -3925,7 +4015,7 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) if (l3) { struct array_cache *shared = l3->shared; - spin_lock_irq(&l3->list_lock); + local_spin_lock_irq(slab_lock, &l3->list_lock); if (shared) free_block(cachep, shared->entry, @@ -3938,7 +4028,8 @@ static int alloc_kmemlist(struct kmem_cache *cachep, gfp_t gfp) } l3->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num; - spin_unlock_irq(&l3->list_lock); + unlock_l3_and_free_delayed(&l3->list_lock); + kfree(shared); free_alien_cache(new_alien); continue; @@ -3985,17 +4076,30 @@ 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[cpu] = new->new[cpu]; + new->new[cpu] = old; +} - new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()]; - new->new[smp_processor_id()] = 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) +{ + spin_lock_irq(&per_cpu(slab_lock, cpu).lock); + __do_ccupdate_local(info, cpu); + spin_unlock_irq(&per_cpu(slab_lock, cpu).lock); +} +#endif /* Always called with the cache_chain_mutex held */ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, @@ -4021,7 +4125,7 @@ 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; @@ -4032,9 +4136,11 @@ 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->nodelists[cpu_to_mem(i)]->list_lock); + local_spin_lock_irq(slab_lock, + &cachep->nodelists[cpu_to_mem(i)]->list_lock); free_block(cachep, ccold->entry, ccold->avail, cpu_to_mem(i)); - spin_unlock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock); + + unlock_l3_and_free_delayed(&cachep->nodelists[cpu_to_mem(i)]->list_lock); kfree(ccold); } kfree(new); @@ -4110,7 +4216,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, if (ac->touched && !force) { ac->touched = 0; } else { - spin_lock_irq(&l3->list_lock); + local_spin_lock_irq(slab_lock, &l3->list_lock); if (ac->avail) { tofree = force ? ac->avail : (ac->limit + 4) / 5; if (tofree > ac->avail) @@ -4120,7 +4226,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, memmove(ac->entry, &(ac->entry[tofree]), sizeof(void *) * ac->avail); } - spin_unlock_irq(&l3->list_lock); + local_spin_unlock_irq(slab_lock, &l3->list_lock); } } @@ -4259,7 +4365,7 @@ static int s_show(struct seq_file *m, void *p) continue; check_irq_on(); - spin_lock_irq(&l3->list_lock); + local_spin_lock_irq(slab_lock, &l3->list_lock); list_for_each_entry(slabp, &l3->slabs_full, list) { if (slabp->inuse != cachep->num && !error) @@ -4284,7 +4390,7 @@ static int s_show(struct seq_file *m, void *p) if (l3->shared) shared_avail += l3->shared->avail; - spin_unlock_irq(&l3->list_lock); + local_spin_unlock_irq(slab_lock, &l3->list_lock); } num_slabs += active_slabs; num_objs = num_slabs * cachep->num; @@ -4513,13 +4619,13 @@ static int leaks_show(struct seq_file *m, void *p) continue; check_irq_on(); - spin_lock_irq(&l3->list_lock); + local_spin_lock_irq(slab_lock, &l3->list_lock); list_for_each_entry(slabp, &l3->slabs_full, list) handle_slab(n, cachep, slabp); list_for_each_entry(slabp, &l3->slabs_partial, list) handle_slab(n, cachep, slabp); - spin_unlock_irq(&l3->list_lock); + local_spin_unlock_irq(slab_lock, &l3->list_lock); } name = cachep->name; if (n[0] == n[1]) { diff --git a/mm/swap.c b/mm/swap.c index 55b266dcfbeb..e3f7d6fa3192 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -31,6 +31,7 @@ #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> +#include <linux/locallock.h> #include "internal.h" @@ -41,6 +42,9 @@ 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(swap_lock); + /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. @@ -267,11 +271,11 @@ 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); } } @@ -327,12 +331,13 @@ 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(swap_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(swap_lock, activate_page_pvecs); } } @@ -373,12 +378,12 @@ 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(swap_lock, lru_add_pvecs)[lru]; page_cache_get(page); if (!pagevec_add(pvec, page)) ____pagevec_lru_add(pvec, lru); - put_cpu_var(lru_add_pvecs); + put_locked_var(swap_lock, lru_add_pvecs); } EXPORT_SYMBOL(__lru_cache_add); @@ -512,9 +517,9 @@ static void drain_cpu_pagevecs(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); @@ -542,18 +547,19 @@ 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(swap_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(swap_lock, lru_deactivate_pvecs); } } void lru_add_drain(void) { - drain_cpu_pagevecs(get_cpu()); - put_cpu(); + drain_cpu_pagevecs(local_lock_cpu(swap_lock)); + local_unlock_cpu(swap_lock); } static void lru_add_drain_per_cpu(struct work_struct *dummy) @@ -783,6 +789,9 @@ void __init swap_setup(void) { unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT); + local_irq_lock_init(rotate_lock); + local_irq_lock_init(swap_lock); + #ifdef CONFIG_SWAP bdi_init(swapper_space.backing_dev_info); #endif diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 27be2f0d4cb7..071155a6f83b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -782,7 +782,7 @@ 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(); @@ -821,12 +821,13 @@ 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; } @@ -900,7 +901,7 @@ 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); @@ -908,7 +909,8 @@ 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; @@ -945,7 +947,7 @@ 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/vmscan.c b/mm/vmscan.c index cb33d9cd4d65..39f9629346a1 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1344,8 +1344,8 @@ static int too_many_isolated(struct zone *zone, int file, */ static noinline_for_stack void putback_lru_pages(struct zone *zone, struct scan_control *sc, - unsigned long nr_anon, unsigned long nr_file, - struct list_head *page_list) + unsigned long nr_anon, unsigned long nr_file, + struct list_head *page_list, unsigned long nr_reclaimed) { struct page *page; struct pagevec pvec; @@ -1356,7 +1356,12 @@ putback_lru_pages(struct zone *zone, struct scan_control *sc, /* * Put back any unfreeable pages. */ - spin_lock(&zone->lru_lock); + spin_lock_irq(&zone->lru_lock); + + if (current_is_kswapd()) + __count_vm_events(KSWAPD_STEAL, nr_reclaimed); + __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed); + while (!list_empty(page_list)) { int lru; page = lru_to_page(page_list); @@ -1539,12 +1544,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, priority, &nr_dirty, &nr_writeback); } - local_irq_disable(); - if (current_is_kswapd()) - __count_vm_events(KSWAPD_STEAL, nr_reclaimed); - __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed); - - putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list); + putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list, nr_reclaimed); /* * If reclaim is isolating dirty pages under writeback, it implies diff --git a/mm/vmstat.c b/mm/vmstat.c index 8fd603b1665e..726f0b6b0508 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -216,6 +216,7 @@ 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); @@ -225,6 +226,7 @@ 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); @@ -257,6 +259,7 @@ 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)) { @@ -265,6 +268,7 @@ 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) @@ -279,6 +283,7 @@ 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)) { @@ -287,6 +292,7 @@ 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 55cd370724c3..3756e96c60a4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -222,14 +222,14 @@ 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 } @@ -1779,6 +1779,7 @@ 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) @@ -1800,6 +1801,7 @@ 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); @@ -2969,6 +2971,7 @@ enqueue: rps_unlock(sd); local_irq_restore(flags); + preempt_check_resched_rt(); atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); @@ -3034,16 +3037,46 @@ int netif_rx_ni(struct sk_buff *skb) { int err; - preempt_disable(); + migrate_disable(); err = netif_rx(skb); if (local_softirq_pending()) - do_softirq(); - preempt_enable(); + thread_do_softirq(); + migrate_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); @@ -3082,7 +3115,7 @@ 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); @@ -3407,7 +3440,7 @@ 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); } } @@ -3416,10 +3449,13 @@ 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) @@ -3757,6 +3793,7 @@ 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) @@ -3829,6 +3866,7 @@ 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); @@ -3903,10 +3941,17 @@ 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; @@ -6362,6 +6407,7 @@ 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))) { @@ -6372,6 +6418,9 @@ 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; } @@ -6638,8 +6687,9 @@ 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/sock.c b/net/core/sock.c index b23f174ab84c..a87eb16faabf 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2031,12 +2031,11 @@ 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 ab188ae12fd9..028eb47226e8 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -67,6 +67,7 @@ #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/fcntl.h> +#include <linux/sysrq.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> @@ -801,6 +802,30 @@ out_err: } /* + * 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 @@ -827,6 +852,11 @@ 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/route.c b/net/ipv4/route.c index 94cdbc55ca7e..5cb9301bb28c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -251,7 +251,7 @@ struct rt_hash_bucket { }; #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \ - defined(CONFIG_PROVE_LOCKING) + defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_PREEMPT_RT_FULL) /* * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks * The size of this table is a power of two and depends on the number of CPUS. diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 69fd7201129a..0ecdb72e032a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -680,6 +680,13 @@ 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 064d20fc9d0e..642d96c23c9d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2958,7 +2958,7 @@ 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 < 0 || status->band >= IEEE80211_NUM_BANDS)) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d9d4970b9b07..ed8ef1eb2569 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -89,6 +89,7 @@ #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> +#include <linux/delay.h> #ifdef CONFIG_INET #include <net/inet_common.h> @@ -673,7 +674,7 @@ 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(); } } @@ -928,7 +929,7 @@ 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 e8fdb172adbb..5a44c6e77cd8 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <linux/rculist.h> #include <linux/llist.h> +#include <linux/delay.h> #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 f221ddf69080..5f440097f6d2 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 |