diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index 7dcb352..02c5d2c 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -13,18 +13,6 @@ #include #include -static void on_each_cpu_mask(void (*func)(void *), void *info, int wait, - const struct cpumask *mask) -{ - preempt_disable(); - - smp_call_function_many(mask, func, info, wait); - if (cpumask_test_cpu(smp_processor_id(), mask)) - func(info); - - preempt_enable(); -} - /**********************************************************************/ /* @@ -87,7 +75,7 @@ void flush_tlb_all(void) void flush_tlb_mm(struct mm_struct *mm) { if (tlb_ops_need_broadcast()) - on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm)); + on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1); else local_flush_tlb_mm(mm); } @@ -98,7 +86,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) struct tlb_args ta; ta.ta_vma = vma; ta.ta_start = uaddr; - on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm)); + on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page, + &ta, 1); } else local_flush_tlb_page(vma, uaddr); } @@ -121,7 +110,8 @@ void flush_tlb_range(struct vm_area_struct *vma, ta.ta_vma = vma; ta.ta_start = start; ta.ta_end = end; - on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm)); + on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range, + &ta, 1); } else local_flush_tlb_range(vma, start, end); } diff --git a/arch/tile/include/asm/smp.h b/arch/tile/include/asm/smp.h index 532124a..1aa759a 100644 --- a/arch/tile/include/asm/smp.h +++ b/arch/tile/include/asm/smp.h @@ -43,10 +43,6 @@ void evaluate_message(int tag); /* Boot a secondary cpu */ void online_secondary(void); -/* Call a function on a specified set of CPUs (may include this one). */ -extern void on_each_cpu_mask(const struct cpumask *mask, - void (*func)(void *), void *info, bool wait); - /* Topology of the supervisor tile grid, and coordinates of boot processor */ extern HV_Topology smp_topology; @@ -91,9 +87,6 @@ void print_disabled_cpus(void); #else /* !CONFIG_SMP */ -#define on_each_cpu_mask(mask, func, info, wait) \ - do { if (cpumask_test_cpu(0, (mask))) func(info); } while (0) - #define smp_master_cpu 0 #define smp_height 1 #define smp_width 1 diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c index c52224d..a44e103 100644 --- a/arch/tile/kernel/smp.c +++ b/arch/tile/kernel/smp.c @@ -87,25 +87,6 @@ void send_IPI_allbutself(int tag) send_IPI_many(&mask, tag); } - -/* - * Provide smp_call_function_mask, but also run function locally - * if specified in the mask. - */ -void on_each_cpu_mask(const struct cpumask *mask, void (*func)(void *), - void *info, bool wait) -{ - int cpu = get_cpu(); - smp_call_function_many(mask, func, info, wait); - if (cpumask_test_cpu(cpu, mask)) { - local_irq_disable(); - func(info); - local_irq_enable(); - } - put_cpu(); -} - - /* * Functions related to starting/stopping cpus. */ diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c index 0793e42..d45833f 100644 --- a/drivers/net/wireless/orinoco/orinoco_usb.c +++ b/drivers/net/wireless/orinoco/orinoco_usb.c @@ -714,7 +714,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv, while (!ctx->done.done && msecs--) udelay(1000); } else { - wait_event_interruptible(ctx->done.wait, + swait_event_interruptible(ctx->done.wait, ctx->done.done); } break; diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index 0e641a1..c6154ca 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -1270,7 +1270,7 @@ static void ffs_data_put(struct ffs_data *ffs) BUG_ON(mutex_is_locked(&ffs->mutex) || spin_is_locked(&ffs->ev.waitq.lock) || waitqueue_active(&ffs->ev.waitq) || - waitqueue_active(&ffs->ep0req_completion.wait)); + swaitqueue_active(&ffs->ep0req_completion.wait)); kfree(ffs); } } diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index 7138540..616d19e 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -339,7 +339,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) spin_unlock_irq (&epdata->dev->lock); if (likely (value == 0)) { - value = wait_event_interruptible (done.wait, done.done); + value = swait_event_interruptible (done.wait, done.done); if (value != 0) { spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { @@ -348,7 +348,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len) usb_ep_dequeue (epdata->ep, epdata->req); spin_unlock_irq (&epdata->dev->lock); - wait_event (done.wait, done.done); + swait_event (done.wait, done.done); if (epdata->status == -ECONNRESET) epdata->status = -EINTR; } else { diff --git a/fs/buffer.c b/fs/buffer.c index 997b199..36d49f1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1425,10 +1425,23 @@ static void invalidate_bh_lru(void *arg) } put_cpu_var(bh_lrus); } + +static bool has_bh_in_lru(int cpu, void *dummy) +{ + struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); + int i; + for (i = 0; i < BH_LRU_SIZE; i++) { + if (b->bhs[i]) + return 1; + } + + return 0; +} + void invalidate_bh_lrus(void) { - on_each_cpu(invalidate_bh_lru, NULL, 1); + on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); diff --git a/include/linux/smp.h b/include/linux/smp.h index 78fd0a2..3001ba5 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -101,6 +101,22 @@ static inline void call_function_init(void) { } int on_each_cpu(smp_call_func_t func, void *info, int wait); /* + * Call a function on processors specified by mask, which might include + * the local one. + */ +void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, + void *info, bool wait); + +/* + * Call a function on each processor for which the supplied function + * cond_func returns a positive value. This may include the local + * processor. + */ +void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags); + +/* * Mark the boot cpu "online" so that it can call console drivers in * printk() and can access its per-cpu storage. */ @@ -131,6 +147,36 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info) local_irq_enable(); \ 0; \ }) +/* + * Note we still need to test the mask even for UP + * because we actually can get an empty mask from + * code that on SMP might call us without the local + * CPU in the mask. + */ +#define on_each_cpu_mask(mask, func, info, wait) \ + do { \ + if (cpumask_test_cpu(0, (mask))) { \ + local_irq_disable(); \ + (func)(info); \ + local_irq_enable(); \ + } \ + } while (0) +/* + * Preemption is disabled here to make sure the cond_func is called under the + * same condtions in UP and SMP. + */ +#define on_each_cpu_cond(cond_func, func, info, wait, gfp_flags)\ + do { \ + void *__info = (info); \ + preempt_disable(); \ + if ((cond_func)(0, __info)) { \ + local_irq_disable(); \ + (func)(__info); \ + local_irq_enable(); \ + } \ + preempt_enable(); \ + } while (0) + static inline void smp_send_reschedule(int cpu) { } #define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h index 3b555b4..28edba7 100644 --- a/include/linux/spinlock_rt.h +++ b/include/linux/spinlock_rt.h @@ -20,6 +20,7 @@ extern void __lockfunc rt_spin_lock(spinlock_t *lock); extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); extern void __lockfunc rt_spin_unlock(spinlock_t *lock); +extern void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock); extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); diff --git a/kernel/cpu.c b/kernel/cpu.c index 063c2bb..031c644 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -546,6 +546,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) err = -EBUSY; goto restore_cpus; } + migrate_enable(); cpu_hotplug_begin(); err = cpu_unplug_begin(cpu); @@ -598,7 +599,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) 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/rtmutex.c b/kernel/rtmutex.c index 6075f17..d759326 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -801,10 +801,8 @@ static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) /* * Slow path to release a rt_mutex spin_lock style */ -static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +static void __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); @@ -823,6 +821,23 @@ static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) rt_mutex_adjust_prio(current); } +static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) +{ + raw_spin_lock(&lock->wait_lock); + __rt_spin_lock_slowunlock(lock); +} + +static void noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock) +{ + int ret; + + do { + ret = raw_spin_trylock(&lock->wait_lock); + } while (!ret); + + __rt_spin_lock_slowunlock(lock); +} + void __lockfunc rt_spin_lock(spinlock_t *lock) { rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); @@ -853,6 +868,13 @@ void __lockfunc rt_spin_unlock(spinlock_t *lock) } EXPORT_SYMBOL(rt_spin_unlock); +void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock) +{ + /* NOTE: we always pass in '1' for nested, for simplicity */ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq); +} + void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) { rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); @@ -1064,7 +1086,8 @@ rt_mutex_slowtrylock(struct rt_mutex *lock) { int ret = 0; - raw_spin_lock(&lock->wait_lock); + if (!raw_spin_trylock(&lock->wait_lock)) + return ret; init_lists(lock); if (likely(rt_mutex_owner(lock) != current)) { diff --git a/kernel/smp.c b/kernel/smp.c index 9e800b2..d5f3238 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -712,3 +712,93 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait) return ret; } EXPORT_SYMBOL(on_each_cpu); + +/** + * on_each_cpu_mask(): Run a function on processors specified by + * cpumask, which may include the local processor. + * @mask: The set of cpus to run on (only runs on online subset). + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. + * + * If @wait is true, then returns once @func has returned. + * + * You must not call this function with disabled interrupts or + * from a hardware interrupt handler or from a bottom half handler. + */ +void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, + void *info, bool wait) +{ + int cpu = get_cpu(); + + smp_call_function_many(mask, func, info, wait); + if (cpumask_test_cpu(cpu, mask)) { + local_irq_disable(); + func(info); + local_irq_enable(); + } + put_cpu(); +} +EXPORT_SYMBOL(on_each_cpu_mask); + +/* + * on_each_cpu_cond(): Call a function on each processor for which + * the supplied function cond_func returns true, optionally waiting + * for all the required CPUs to finish. This may include the local + * processor. + * @cond_func: A callback function that is passed a cpu id and + * the the info parameter. The function is called + * with preemption disabled. The function should + * return a blooean value indicating whether to IPI + * the specified CPU. + * @func: The function to run on all applicable CPUs. + * This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to both functions. + * @wait: If true, wait (atomically) until function has + * completed on other CPUs. + * @gfp_flags: GFP flags to use when allocating the cpumask + * used internally by the function. + * + * The function might sleep if the GFP flags indicates a non + * atomic allocation is allowed. + * + * Preemption is disabled to protect against CPUs going offline but not online. + * CPUs going online during the call will not be seen or sent an IPI. + * + * You must not call this function with disabled interrupts or + * from a hardware interrupt handler or from a bottom half handler. + */ +void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags) +{ + cpumask_var_t cpus; + int cpu, ret; + + might_sleep_if(gfp_flags & __GFP_WAIT); + + if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { + preempt_disable(); + for_each_online_cpu(cpu) + if (cond_func(cpu, info)) + cpumask_set_cpu(cpu, cpus); + on_each_cpu_mask(cpus, func, info, wait); + preempt_enable(); + free_cpumask_var(cpus); + } else { + /* + * No free cpumask, bother. No matter, we'll + * just have to IPI them one by one. + */ + preempt_disable(); + for_each_online_cpu(cpu) + if (cond_func(cpu, info)) { + ret = smp_call_function_single(cpu, func, + info, wait); + WARN_ON_ONCE(!ret); + } + preempt_enable(); + } +} +EXPORT_SYMBOL(on_each_cpu_cond); diff --git a/kernel/softirq.c b/kernel/softirq.c index ca00a68..7d882cc 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -297,6 +297,44 @@ EXPORT_SYMBOL(local_bh_enable_ip); */ #define MAX_SOFTIRQ_RESTART 10 +#ifdef CONFIG_TRACE_IRQFLAGS +/* + * Convoluted means of passing __do_softirq() a message through the various + * architecture execute_on_stack() bits. + * + * When we run softirqs from irq_exit() and thus on the hardirq stack we need + * to keep the lockdep irq context tracking as tight as possible in order to + * not miss-qualify lock contexts and miss possible deadlocks. + */ +static DEFINE_PER_CPU(int, softirq_from_hardirq); + +static inline void lockdep_softirq_from_hardirq(void) +{ + this_cpu_write(softirq_from_hardirq, 1); +} + +static inline void lockdep_softirq_start(void) +{ + if (this_cpu_read(softirq_from_hardirq)) + trace_hardirq_exit(); + lockdep_softirq_enter(); +} + +static inline void lockdep_softirq_end(void) +{ + lockdep_softirq_exit(); + if (this_cpu_read(softirq_from_hardirq)) { + this_cpu_write(softirq_from_hardirq, 0); + trace_hardirq_enter(); + } +} + +#else +static inline void lockdep_softirq_from_hardirq(void) { } +static inline void lockdep_softirq_start(void) { } +static inline void lockdep_softirq_end(void) { } +#endif + asmlinkage void __do_softirq(void) { __u32 pending; @@ -308,7 +346,7 @@ asmlinkage void __do_softirq(void) __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); - lockdep_softirq_enter(); + lockdep_softirq_start(); cpu = smp_processor_id(); restart: @@ -324,7 +362,7 @@ restart: if (pending) wakeup_softirqd(); - lockdep_softirq_exit(); + lockdep_softirq_end(); account_system_vtime(current); __local_bh_enable(SOFTIRQ_OFFSET); @@ -582,9 +620,10 @@ void irq_enter(void) static inline void invoke_softirq(void) { #ifndef CONFIG_PREEMPT_RT_FULL - if (!force_irqthreads) + if (!force_irqthreads) { + lockdep_softirq_from_hardirq(); __do_softirq(); - else { + } else { __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); wakeup_softirqd(); @@ -618,7 +657,6 @@ static inline void invoke_softirq(void) void irq_exit(void) { account_system_vtime(current); - trace_hardirq_exit(); sub_preempt_count(IRQ_EXIT_OFFSET); if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); @@ -629,6 +667,7 @@ void irq_exit(void) if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) tick_nohz_stop_sched_tick(0); #endif + trace_hardirq_exit(); /* must be last! */ __preempt_enable_no_resched(); } diff --git a/kernel/timer.c b/kernel/timer.c index 7fa30e0..b7ef082 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1336,7 +1336,7 @@ unsigned long get_next_timer_interrupt(unsigned long now) 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); + rt_spin_unlock_after_trylock_in_irq(&base->lock); } else { expires = now + 1; } diff --git a/localversion-rt b/localversion-rt index 54e7da6..c1f2720 100644 --- a/localversion-rt +++ b/localversion-rt @@ -1 +1 @@ --rt75 +-rt76